Activity
From 01/04/2015 to 02/02/2015
02/02/2015
- 11:58 PM Revision a0eff325 (ceph): osd: handle no-op write with snapshot case
- If we have a transaction that does something to the object but it !exists
both before and after, we will continue thr... - 11:50 PM Bug #10697 (Duplicate): dumpling: valgrind leak ReplicatedPG::get_object_context
- https://github.com/ceph/ceph/pull/3552
- 10:02 PM Bug #10697: dumpling: valgrind leak ReplicatedPG::get_object_context
- Ah, I think you are right.
- 11:37 PM Revision cfab01e3 (ceph): rgw: move perf cleanup before context cleanup
- Fixes: #10722
Fixes: #10572
Backport: giant, firefly
This fixes a regression introduced in commit
de2e5fa048639de6c9... - 11:33 PM Revision 26966c4a (ceph): qa: use sudo even more when rsyncing /usr
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 3aa7797741f9cff06053a2f31550fe6929039692) - 11:33 PM Revision 6af48421 (ceph): qa: use sudo when rsyncing /usr so we can read everything
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit fa07c04231db2d130de54647957ffab4a7a53733) - 11:32 PM Revision 4074a91b (ceph): pybind: fix error hiding and inconsistency on librados load.
- When loading of librados failed, the real cause was hidden in some
circumstances due to exception rewriting. Addition... - 11:31 PM Bug #10723 (Resolved): rados python binding leaks Ioctx objects
- When setting up cinder with ceph, rados.Ioctx objects are leaked when creating and deleting volumes.
The problem i... - 11:31 PM rgw Bug #10722 (Resolved): rgw: regression following up fix for #10572
- 11:27 PM rgw Bug #10572: rgw: crash on shutdown, when syncing user stats
- The fix for this is broken. When backporting, please also cherry-pick the follow up fix.
- 10:51 PM Bug #10541 (Duplicate): objecter memory corruption
- I ended up with a somewhat similar patch while tracking down 10340, I think this is the same bug.
- 10:49 PM Bug #10464 (Resolved): osd/osd_types.h: 3123: FAILED assert(rwstate.empty())
- e00daf56ff054440574c861282f0b49bff1a50b9
- 10:37 PM CephFS Bug #10703: failures in libcephfs-java tests
- Are we supposed to provide any sort of ordering on MClientCap versus MClientRequest messages? Truncate and length iss...
- 01:44 PM CephFS Bug #10703: failures in libcephfs-java tests
- looks like the ftruncate failure is caused by out-of-order cap message (mds processes setattr request and cap message...
- 10:37 PM devops Bug #10532 (Rejected): Failed "joining thrashosds" - suspected low memory config on vps
- I'm going to declare this batch to be vps related.
- 10:33 PM CephFS Bug #10702: ceph-qa-suite: hung client-recovery task in nightlies
- Isn't the first umount supposed to fail, and then the "except run.CommandFailedError:" block forcibly cleans it up?
... - 06:53 AM CephFS Bug #10702: ceph-qa-suite: hung client-recovery task in nightlies
- it hung at...
- 10:27 PM Bug #10612 (Need More Info): "[ FAILED ] LibRadosCmd.OSDCmd " in upgrade:dumpling-x-firefly-dis...
- oddly, I see the osd sending -22 (as it should). Not sure what's going on.
- 10:18 PM Revision 0f9f4e53 (ceph): Merge remote-tracking branch 'upstream/next'
- 10:08 PM Revision cfcfafcb (ceph): Objecter::_op_submit_with_budget: add timeout before call
- Objecter::_send_op depends on the ontimeout field being filled in
to avoid 10340 and 9582.
Fixes: 10340
Signed-off-b... - 10:07 PM rbd Bug #10644: librbd: segfault on image close when watch fails
- Another case: http://qa-proxy.ceph.com/teuthology/teuthology-2015-02-01_23:00:02-rbd-next-distro-basic-multi/735235/t...
- 10:04 PM Bug #10616 (Resolved): osd/ReplicatedPG.cc: 5790: FAILED assert(ctx->new_obs.exists == ctx->new_s...
- This variant does not need to be backported, I think.
- 10:03 PM Bug #10633 (Resolved): osd: assert in lock in C_CopyFrom
- 09:56 PM Bug #10340: "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:dumpling-firefly-x:parallel-giant-di...
- 09:55 PM Bug #10340: "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:dumpling-firefly-x:parallel-giant-di...
- _op_submit_with_budget fills out op->ontimeout after calling _op_submit which calls _send_op so op->ontimeout is NULL...
- 04:43 PM Bug #10340: "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:dumpling-firefly-x:parallel-giant-di...
- Same in run:
http://pulpito.ceph.com/teuthology-2015-01-30_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Job: 732... - 08:48 PM Stable releases Tasks #10501: giant v0.87.1
- replace inline inventory with git backed wiki
- 08:47 PM rbd Feature #10462 (Resolved): rbd cli: use io hints for import/export etc
- 08:43 PM rbd Bug #10706 (Fix Under Review): librbd/ObjectMap.cc: 108: FAILED assert(object_no < object_map.siz...
- https://github.com/ceph/ceph/pull/3589
- 04:02 PM rbd Bug #10706 (In Progress): librbd/ObjectMap.cc: 108: FAILED assert(object_no < object_map.size())
- 07:30 PM rgw Bug #10719: "test_abort_multipart_upload" failed in upgrade:dumpling-firefly-x-next run
- And on baremetal
Run: http://pulpito.ceph.com/teuthology-2015-01-31_17:10:01-upgrade:dumpling-firefly-x-next-distro-... - 06:57 PM rgw Bug #10719 (Resolved): "test_abort_multipart_upload" failed in upgrade:dumpling-firefly-x-next run
- Run: http://pulpito.ceph.com/teuthology-2015-02-01_17:15:01-upgrade:dumpling-firefly-x-next-distro-basic-vps
Job: 73... - 07:27 PM CephFS Bug #10361 (Resolved): teuthology: only direct admin socket commands to active MDS
- 07:18 PM CephFS Bug #10720 (Rejected): MDS: valgrind leaks
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-30_23:04:02-fs-master-testing-basic-multi/733168/
http://qa-p... - 07:16 PM Bug #10643: "FAILED assert(other->is_writeable())" in upgrade:giant-x-next-distro-basic-vps run
- Same in
Run: http://pulpito.ceph.com/teuthology-2015-02-01_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Jobs: ['... - 06:35 PM Revision 00a3ac3b (ceph): 0.92
- 05:33 PM Revision dd5b1dc2 (ceph): Merge remote-tracking branch 'origin/next'
- Conflicts:
src/rgw/rgw_op.cc
src/rgw/rgw_rados.cc
src/rgw/rgw_rados.h - 05:24 PM Feature #7862 (Resolved): allow backfill/recovery while below min_size
- 05:23 PM Feature #7861 (Resolved): osd: allow writes on degraded objects
- 05:22 PM Revision e4541324 (ceph): Merge pull request #319 from athanatos/wip-min-size
- Wip min size
Reviewed-by: Sage Weil <sage@redhat.com> - 05:21 PM Revision 3c7500b6 (ceph): Merge pull request #3588 from athanatos/wip-10693
- Wip 10693
Reviewed-by: Sage Weil <sage@redhat.com> - 05:19 PM Revision c02e2939 (ceph): Merge pull request #3587 from athanatos/wip-10633
- ReplicatedPG::C_ProxyRead: fix dropped lock
Reviewed-by: Sage Weil <sage@redhat.com> - 05:18 PM Revision 1350b304 (ceph): Merge pull request #3538 from athanatos/wip-7862
- osd: allow recovery below min size
Reviewed-by: Sage Weil <sage@redhat.com> - 05:18 PM Revision 1f1c6b5e (ceph): Merge pull request #3539 from athanatos/wip-7861
- osd: allow writes on degraded objects
Reviewed-by: Sage Weil <sage@redhat.com> - 05:07 PM Revision c656bcec (ceph): PGLog: improve PGLog::check() debugging
- Related: 10718
Signed-off-by: Samuel Just <sjust@redhat.com> - 04:59 PM Bug #10718 (Resolved): osd/PGLog.h: 279: FAILED assert(log.log.size() == log_keys_debug.size())
- ceph version 0.91-1098-gd3b7616 (d3b76165be4b0c59ff7c292f6534a3aa4e2cd27a)
1: (ceph::__ceph_assert_fail(char const... - 04:50 PM Bug #10543 (New): "FAILED assert(m_seed < old_pg_num)" in upgrade:giant-x-hammer-distro-basic-vps...
- Seeing in
run: http://pulpito.ceph.com/teuthology-2015-01-31_17:05:03-upgrade:giant-x-next-distro-basic-vps/
Job: 7... - 04:38 PM Bug #10717: osd/ReplicatedPG.h: 786: FAILED assert(!ctx->snapset_obc)
- do_op needs to ignore the snapset_obc if !snapset_obc->obs.exists
- 04:33 PM Bug #10717 (Resolved): osd/ReplicatedPG.h: 786: FAILED assert(!ctx->snapset_obc)
ceph version 0.91-1098-gd3b7616 (d3b76165be4b0c59ff7c292f6534a3aa4e2cd27a)
1: (ceph::__ceph_assert_fail(char con...- 04:35 PM rbd Bug #10709 (Resolved): rbd watch creates 2 watchers?
- 03:05 PM rbd Bug #10709: rbd watch creates 2 watchers?
- https://github.com/ceph/ceph/pull/3578
- 03:03 PM rbd Bug #10709 (Fix Under Review): rbd watch creates 2 watchers?
- 02:13 PM rbd Bug #10709 (In Progress): rbd watch creates 2 watchers?
- 09:30 AM rbd Bug #10709 (Resolved): rbd watch creates 2 watchers?
- rbd watch in one terminal, then rbd status in another will show 2 clients. hit enter on the watch and then status ag...
- 04:32 PM devops Bug #10716 (Resolved): "FATAL: Chef::Exceptions::ChildConvergeError" in Octo
- Many tests failed with this.
One for example: http://magna002.ceph.redhat.com/teuthology-2015-02-02_02:32:01-rados-g... - 04:16 PM Revision ba1ea157 (ceph): Merge pull request #3578 from ceph/wip-10709
- rbd: watch command should unwatch before exiting
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:02 PM Bug #10711 (Rejected): ceph.in: connect before ping_monitor
- 03:02 PM Bug #10711: ceph.in: connect before ping_monitor
- Loic Dachary wrote:
> I'm confused because it works for me, in the current master. I get an ObjectNotFound error onl... - 10:58 AM Bug #10711 (Need More Info): ceph.in: connect before ping_monitor
- 10:58 AM Bug #10711: ceph.in: connect before ping_monitor
- I'm confused because it works for me, in the current master. I get an ObjectNotFound error only when the targeted mon...
- 10:48 AM Bug #10711 (Rejected): ceph.in: connect before ping_monitor
- [root@ceph ~]# ceph ping mon.a
Error connecting to cluster: ObjectNotFound - 04:01 PM rbd Bug #10714 (Fix Under Review): librbd: aio_flush() calls sychronous ImageWatcher flush method
- https://github.com/ceph/ceph/pull/3585
- 03:57 PM rbd Bug #10714 (In Progress): librbd: aio_flush() calls sychronous ImageWatcher flush method
- 12:23 PM rbd Bug #10714 (Resolved): librbd: aio_flush() calls sychronous ImageWatcher flush method
- ImageWatcher's aio_flush should be async to not block librbd's aio_flush().
- 03:54 PM Revision c58307bb (ceph): Merge pull request #3583 from jdurgin/wip-qemu-iotests
- qa: use correct binary path on rpm-based systems
Reviewed-by: Sage Weil <sage@redhat.com> - 03:52 PM Revision 0a8f1fe0 (ceph): Merge pull request #3584 from ceph/wip-optional-encoding
- encoding: ignore uninitialized instantiation in boost::optional decode
Reviewed-by: Sage Weil <sage@redhat.com> - 03:45 PM Revision 05ce2aa1 (ceph): qa: use correct binary path on rpm-based systems
- Fixes: #10715
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 03:37 PM rgw Bug #10354 (Duplicate): Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-...
- this really is a duplicate, do not set backport
- 03:34 PM rgw Bug #9878: rhel7 s3-tests fail due to missing reason
- already backported in giant with commit:1ccd73a16e1829b5519ec5b83b2554af173ad052
- 03:28 PM rbd Feature #10461 (Resolved): objectcacher: use librados io hints
- 03:28 PM rbd Feature #10461 (Fix Under Review): objectcacher: use librados io hints
- 03:28 PM rbd Feature #4087 (Resolved): rbd: bitmaps for tracking object existence
- 03:27 PM rbd Feature #8902 (Resolved): rbd mirroring: librbd: funnel snapshot, resize events via lock holder
- 03:22 PM Bug #7264: rados.py: exception catching when librados load fails hides error
- Pull request: https://github.com/ceph/ceph/pull/3565
- 03:15 PM Revision 4e4372b8 (ceph): rgw: check for timestamp for s3 keystone auth
- This commit ensures that we check for timestamp of s3 request is within
acceptable grace time of radosgw
Addresses so... - 03:15 PM Revision 98866208 (ceph): rgw: check keystone auth also for s3 post requests
- This patch adds keystone auth for s3 post requests, once a user fails in
cephx authentication, they are checked for k... - 03:14 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- I added the support for O_PATH in several places as well as unit test. The commit is on my github. Feel free to comme...
- 03:10 PM Revision debc0c59 (ceph): rgw: update swift subuser perm masks when authenticating
- Fixes: #9918
Backport: firefly, giant
It seems that we weren't setting the swift perm mask correctly.
Signed-off-by:... - 03:09 PM Revision 76f9de33 (ceph): fix can not disable max_size quota
- Currently if we enable quota and set max_size = -1, it doesn’t
mean max_size is unlimited as expected. Instead, it me... - 03:05 PM Revision d759e71c (ceph): rgw: RGWRados::get_obj() returns wrong len if len == 0
- Fixes: #9877
We only updated if len was > 0, should update it if r >= 0. This was the
culprit for issue #9877.
Backpo... - 03:05 PM Revision eb526af7 (ceph): rbd: watch command should unwatch before exiting
- Switched the rbd CLI tool to use the new watch/unwatch API
and properly unwatch the image before exiting. Additionall... - 03:02 PM Revision d21f4e32 (ceph): init-radosgw.sysv: set ulimit -n before starting daemon
- If we do the ulimit inside the daemon command we will have already
dropped privs and will fail.
Fixes: #9587
Backpor... - 02:41 PM Revision 7b5f746d (ceph): rgw: PutObjMetadata, clear bufferlist before appending into it
- Fixes: #9576
Backport: firefly, dumpling
We need to completely rewrite the bufferlist, not append into it.
Signed-o... - 02:39 PM Revision e24f27b7 (ceph): rgw: rados->set_attrs() updates bucket index
- Fixes: #5595
Backport: dumpling, firefly
We need to update the bucket index when updating object attrs, otherwise
we'... - 02:36 PM Revision b2f6f7f6 (ceph): rgw: send back ETag on S3 object copy
- Fixes: #9479
Backport: firefly, giant
We didn't send the etag back correctly. Original code assumed the etag
resided ... - 02:35 PM Revision 67ba4d34 (ceph): rgw: S3 object copy content type fix
- Fixes: #9478
Backport: firefly, giant
Content type for S3 object copy response should be set to
application/xml.
Sig... - 02:33 PM Revision 84e9b6c3 (ceph): rgw: http headers need to end with \r\n
- Fixes: #9254
Backport: firefly, giant
Reported-by: Benedikt Fraunhofer <fraunhofer@traced.net>
Signed-off-by: Yehuda... - 02:32 PM Revision 1cb09555 (ceph): rgw: remove swift user manifest (DLO) hash calculation
- Fixes: #9973
Backport: firefly, giant
Previously we were iterating through the parts, creating hash of the
parts eta... - 02:31 PM rgw Bug #9973: Validation of Swift DLO manifest object ETag doesn't match OpenStack Swift behavior
- add the commit to the description so that it can easily be picked when scraping redmine
- 02:29 PM Revision e230fabf (ceph): rgw: swift GET / HEAD object returns X-Timestamp field
- Fixes: #8911
Backport: giant, firefly, dumpling
Swift clients expect X-Timestamp header, dump it.
Signed-off-by: Yeh... - 02:27 PM Revision c24fab30 (ceph): rgw: use strict_strtoll() for content length
- instead of strict_strtol().
Backport: giant, firefly
Fixes: #10701
Reported-by: Axel Dunkel <ad@dunkel.de>
Signed-o... - 02:25 PM Revision 6aef29e3 (ceph): rgw-admin: create subuser if needed when creating user
- Fixes: #10103
Backport: firefly, giant
This turned up after fixing #9973. Earlier we also didn't create the
subuser i... - 02:20 PM Revision a5cb39cb (ceph): rgw: use s->bucket_attrs instead of trying to read obj attrs
- Fixes: #10307
Backport: firefly, giant
This is needed, since we can't really read the bucket attrs by trying to
read... - 02:15 PM Revision 425ee8a0 (ceph): rgw: use s->bucket_attrs instead of trying to read obj attrs
- Fixes: #10307
Backport: firefly, giant
This is needed, since we can't really read the bucket attrs by trying to
read... - 01:17 PM Stable releases Tasks #10560: dumpling v0.67.12
- re-run rbd_fsx_cache_writethrough
- 12:45 PM Bug #10513: ceph_test_librbd_fsx fails with thrasher
- On dumpling this time ( http://pulpito.ceph.com/loic-2015-01-29_15:39:38-rbd-dumpling-backports---basic-multi/730029/...
- 12:42 PM Bug #10700 (Resolved): ceph_test_rados EINVAL
- 12:11 PM CephFS Bug #10710: fuse_ll warning
- NB error handling code here should consider #10542
- 10:12 AM CephFS Bug #10710 (Resolved): fuse_ll warning
- client/fuse_ll.cc: In function 'void remount_cb(void*)':
warning: client/fuse_ll.cc:767:14: ignoring return value of... - 12:06 PM Revision 2a0e9b77 (ceph): encoding: ignore uninitialized instantiation in boost::optional decode
- POD types won't be initialized until the decode writes to them.
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 11:26 AM Fix #10519 (Resolved): Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph...
- 11:25 AM Bug #10713 (Closed): Unable to access some pgs
- I have been facing some network instability on my ceph cluster. (0.87)
################################### ceph ... - 11:12 AM Revision a63cccce (ceph): Merge pull request #3562 from liewegas/wip-lttng
- do_autogen.sh: default to --with-lttng, -L to build without
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:10 AM CephFS Bug #10712: TestFlush intermittent failure on scatter_writebehind event
- urgent by default since this causes qa tests to fail
- 11:04 AM CephFS Bug #10712: TestFlush intermittent failure on scatter_writebehind event
- http://pulpito.ceph.com/sage-2015-02-01_05:11:51-fs-master-distro-basic-multi/734532/
- 11:04 AM CephFS Bug #10712 (Resolved): TestFlush intermittent failure on scatter_writebehind event
The flush code isn't fully deterministic, sometimes the single log segment left behind just has a subtreemap event,...- 11:07 AM Revision 0af16c36 (ceph): Merge pull request #3485 from jdurgin/wip-merge-diff-testing
- Improve merge-diff test
- 11:04 AM Revision f40ee8c9 (ceph): do_autogen.sh: default to --with-lttng, -L to build without
- Get developers building with LTTNG by default.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:55 AM Revision de3b5c48 (ceph): Merge pull request #3549 from Ved-vampir/master
- Ceph: Fix
Reviewed-by: Sage Weil <sage@redhat.com> - 10:46 AM Revision 7590387e (ceph): librados: add missing tracepoints
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:29 AM Revision 57bac8ea (ceph): osd: change pg_stat plain to display CRUSH_ITEM_NONE in pgmap output s...
- Fixes: #10519
Signed-off-by: Kiseleva Alyona <akiselyova@mirantis.com> - 10:26 AM Revision 70db6644 (ceph): Merge pull request #304 from yuyuyu101/add-msgr-test
- rados: include msgr tests
- 10:26 AM Revision 082551ba (ceph): Merge pull request #3501 from yuyuyu101/wip-fix-async
- AsyncMessenger: Fix mix auth assert failed
- 10:24 AM Bug #10693: FAILED assert(soid < scrubber.start || soid >= scrubber.end): oi digest variant
- Can I expect it will fix #10689 ?
- 09:33 AM Revision 0d6963b3 (ceph): Merge branch 'wip-rbd-listwatchers'
- Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:32 AM Revision 4aa9f3f7 (ceph): man: add rbd status to doc/man/8/rbd.rst
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 09:04 AM Revision b357ce27 (ceph): Merge pull request #3533 from ceph/wip-disaster-doc
- doc: add cephfs disaster recovery guidance
Reviewed-by: Greg Farnum <gfarnum@redhat.com - 08:56 AM Revision a007c529 (ceph): doc: add cephfs disaster recovery guidance
- This is a place to put some useful notes about
the new offline recovery tooling.
Signed-off-by: John Spray <john.spr... - 05:51 AM Revision 6fc0b80a (ceph): rbd: add status command to list the watchers of an image
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 05:51 AM Revision 9dbd37bc (ceph): test: add rbd status to src/test/cli/rbd/help.t
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 05:34 AM rgw Bug #10447 (Need More Info): rx to radosgw is more than tx (more than ten times)
- More information about what you're actually seeing, providing some logs maybe will help here. I honestly have no idea...
- 05:06 AM Revision 2ac116e9 (ceph): add tests for ceph pg ls
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 05:06 AM Revision 4be91c63 (ceph): add CLI ceph pg ls-by-primary
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 05:03 AM Revision a1f634b5 (ceph): add CLI ceph pg ls [pool] [state]
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 03:33 AM Revision 1c164cf6 (ceph): get pg status with specific pool, osd, state
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 03:07 AM Revision 0e046bde (ceph): add is_acting_osd function to check if pg is on that osd
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
02/01/2015
- 11:58 PM RADOS Bug #9523: Both op threads and dispatcher threads could be stuck at acquiring the budget of files...
- Loic Dachary wrote:
> Did you manage to reproduce the problem ?
We increased the throttle to overcome this problem,... - 01:37 PM RADOS Bug #9523: Both op threads and dispatcher threads could be stuck at acquiring the budget of files...
- Did you manage to reproduce the problem ?
- 11:14 PM Revision 14e6a4cc (ceph): Fixes http://tracker.ceph.com/issues/10652
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 08:52 PM rgw Bug #10572 (Pending Backport): rgw: crash on shutdown, when syncing user stats
- This is fixed in next in commit:de2e5fa048639de6c9ee004a93ab295625fa3b94
I tried merging next to master, but ther... - 08:49 PM Bug #10705: rbd: qa/workunit test_lock_and_fence --image-shared appears broken.
- This is a bug in the suite - it's running the master version of the workunit with an older version of the client code...
- 08:37 PM Revision 34473f78 (ceph): librados: rectify the guard in RadosClient::wait_for_osdmap().
- RadosClient::wait_for_osdmap() did not signalize lack of connection
via -ENOTCONN error code when the Objecter instan... - 08:36 PM Revision 624c056d (ceph): librados: fix resources leakage in RadosClient::connect().
- If RadosClient::connect was called a second time (which could
happen as a part of recovery from failure), the instanc... - 08:30 PM Revision b40cb616 (ceph): Merge branch 'librbd-cache-iohint' of git://github.com/majianpeng/ceph
- Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
src/librbd/ImageC... - 06:38 PM rgw Bug #10708 (New): RGW swift API: POSTing multipart/form-data along with form data does not create...
- Steps to reproduce:
1. swift post container
2. swift post -H "x-account-meta-temp-url-key: secret"
3. keystone t... - 03:41 PM rgw Bug #10707 (Resolved): cls/test_cls_rgw.sh tests fail
- ...
- 03:40 PM rbd Bug #10706 (Resolved): librbd/ObjectMap.cc: 108: FAILED assert(object_no < object_map.size())
- ...
- 02:36 PM Revision 83a0a2e5 (ceph): osd: Cleanup boost optionals
- Signed-off-by: William A. Kennington III <william@wkennington.com>
(cherry picked from commit a53ead14c11304756717763... - 02:36 PM Revision eb30631e (ceph): support Boost 1.57.0
- Sometime after 1.55, boost introduced a forward declaration of
operator<< in optional.hpp. In 1.55 and earlier, when ... - 01:27 PM Bug #10458: librados: original pool name cached in IoCtxImpl may be used after pool is renamed
- https://github.com/ceph/ceph/pull/3515
- 12:54 PM Revision d0de7984 (ceph): Merge pull request #3556 from trociny/image_watcher-fixup
- librbd: RemoteAsyncRequest: fix comparison operator
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:49 PM Bug #10425: RadosClient::connect leaks Objecter if called twice
- tests https://github.com/ceph/ceph/pull/3519
- 12:16 PM Revision c4886cc0 (ceph): Merge pull request #3537 from ceph/wip-10688-boost-157
- #10688: support Boost 1.57.0
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:58 AM Revision 65fbf226 (ceph): librbd: RemoteAsyncRequest: fix comparison operator
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 07:42 AM Revision 1cf30e60 (ceph): rbd: use IO hints for read/write operations
- Import, export, and benchmark operations now use the librados
IO hints to indicate the read/write pattern and whether... - 06:36 AM Revision 26ba4315 (ceph): Merge remote-tracking branch 'origin/wip-4087'
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
src/librbd/LibrbdWriteback.cc
01/31/2015
- 11:13 PM rbd Bug #10652: "rbd: import failed: (38) Function not implemented" in multi-version-next-distro-basi...
- 11:13 PM rbd Bug #10652: "rbd: import failed: (38) Function not implemented" in multi-version-next-distro-basi...
- Should be fixed by PR https://github.com/ceph/ceph-qa-suite/pull/320
- 10:08 PM Revision 4cd7448f (ceph): Merge pull request #3545 from thesues/fix-cmp-xattr
- Fix ReplicatedPG do_xattr_cmp_u64
Backport: giant, firefly
Reviewed-by: Sage Weil <sage@redhat.com> - 10:01 PM rgw Bug #10106 (Pending Backport): rgw acl response should start with <?xml version="1.0" ?>
- 02:29 AM rgw Bug #10106 (Fix Under Review): rgw acl response should start with <?xml version="1.0" ?>
- 10:01 PM Revision e143ff7d (ceph): Merge pull request #3555 from ceph/wip-10106
- rgw: flush xml header on get acl request
Reviewed-by: Sage Weil <sage@redhat.com> - 09:16 PM Revision 3e7e21b0 (ceph): Merge pull request #3527 from wonzhq/op-stat
- osd: don't log op stats for proxy read in the cache tier
Reviewed-by: Sage Weil <sage@redhat.com> - 09:15 PM Revision b79c3490 (ceph): Merge pull request #3503 from ceph/wip-pg-reqids
- osd: index PGLog with optional extra_reqids in each log entry
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-b... - 09:13 PM Bug #10630: failed to decode json output from thrashosds
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2015-01-31_06:26:17-rados-wip-sage-testing-distro-basic-multi/733423
- 03:36 PM Bug #5818: leveldb 1.12: hang on shutdown (mon)
- http://pulpito.ceph.com/loic-2015-01-30_18:24:12-rados-v0.67.11---basic-multi/731949/...
- 11:09 AM Revision 7ac2cdf6 (ceph): Merge pull request #3554 from ceph/wip-10572
- rgw: finalize perfcounters after shutting down storage
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 11:06 AM Revision 346b4b02 (ceph): Merge pull request #3323 from ceph/wip-10445
- rgw: use gc for multipart abort
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:17 AM Revision bd8671f6 (ceph): ceph_test_rados: fix typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:03 AM Revision 99c48de3 (ceph): Merge pull request #3452 from majianpeng/iohint
- Iohint in librbd cache.
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:00 AM Revision ac161bf3 (ceph): librados: expose rados_{read|write}_op_assert_version() in C
- Previously, assert_version was only available in the C++ interface.
Signed-off-by: Kim Vandry <vandry@TZoNE.ORG> - 05:39 AM Revision 11b64247 (ceph): Add test case for librados assert_version()
- Signed-off-by: Kim Vandry <vandry@TZoNE.ORG>
- 04:09 AM Bug #10705 (Resolved): rbd: qa/workunit test_lock_and_fence --image-shared appears broken.
- ON RHEL 7.1 running test_lock_and_fence.sh...
- 02:42 AM Revision eb45f861 (ceph): rgw: flush xml header on get acl request
- Fixes: #10106
Backport: firefly, giant
dump_start() updates the formatter with the appropriate prefix, however,
we n... - 12:06 AM rgw Feature #10158 (Closed): rgw: sync agent support for bucket sharding
- This was not needed, all bucket sharding changes were compatible with the current sync agent interfaces.
01/30/2015
- 11:59 PM rgw Bug #6126 (Resolved): rgw: swift subuser access mask not working
- This was fixed around commit:9ee29b5355e9ffeac76707e8d4070bfff5dc99d5.
- 11:38 PM Stable releases Tasks #10501: giant v0.87.1
- List of rgw issues that need backporting, from Yehuda.
- 9918 RGW-Swift: SubUser access permissions, does not se... - 11:23 PM Stable releases Tasks #10501: giant v0.87.1
- update inventory to reflect issues / pull requests / git evolution
- 11:02 PM Stable releases Tasks #10501: giant v0.87.1
- updated the corresponding issues, thanks !
- 07:19 PM Stable releases Tasks #10501: giant v0.87.1
- I'd drop 10329, 10334 from the backport.
- 10:56 PM Bug #10697: dumpling: valgrind leak ReplicatedPG::get_object_context
- Although the OSD does not crash, I think the leak is real.
In the OSD.3 logs I see... - 02:35 PM Bug #10697 (Duplicate): dumpling: valgrind leak ReplicatedPG::get_object_context
- http://pulpito.ceph.com/loic-2015-01-29_15:41:06-rados-dumpling-backports---basic-multi/730305/
reports an object ... - 10:53 PM rgw Bug #10572 (Fix Under Review): rgw: crash on shutdown, when syncing user stats
- 10:34 PM Revision de2e5fa0 (ceph): rgw: finalize perfcounters after shutting down storage
- Fixes: #10572
Backport: giant, firefly
First disable the storage subsystem, then disable perfcounters.
Signed-off-by... - 09:52 PM Bug #10118: messenger drops messages between osds
- That's odd; this run does include all of the messenger delay options enabled, which might be relevant to this example...
- 09:14 PM Bug #10118: messenger drops messages between osds
- /a/samuelj-2015-01-30_10:00:54-rados-wip-sam-working-wip-testing-vanilla-fixes-basic-multi/732275/remote/ceph-osd.msg...
- 09:36 PM Revision 1ccd73a1 (ceph): rgw: send http status reason explicitly in fastcgi
- There are issues in certain versions of apache 2.4, where the reason is
not sent back. Instead, just provide the reas... - 09:29 PM Revision cab246d0 (ceph): librbd: Don't do readahead for random read.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 09:24 PM rgw Bug #10673 (Duplicate): giant s3test failures
- That's #9886. I cherry-picked the fix into giant now.
- 09:22 PM Revision 74343674 (ceph): Merge pull request #3516 from ceph/wip-mdsmon-args
- mon/MDSMonitor: fix gid/rank/state parsing
Reviewed-by: Huang Jun <hjwsm1989@gmail.com>
Reviewed-by: Dan Mick <dmick... - 09:15 PM rgw Bug #10698 (Resolved): rgw: not failing POST requests if keystone not configured
- 06:44 PM rgw Bug #10698 (Fix Under Review): rgw: not failing POST requests if keystone not configured
- 03:24 PM rgw Bug #10698 (Resolved): rgw: not failing POST requests if keystone not configured
- It will most likely fail later on due to access permissions on the bucket, unless bucket has a public write permissio...
- 09:14 PM Revision f0e82ede (ceph): Merge pull request #3551 from ceph/wip-10698
- rgw: fail s3 POST auth if keystone not configured
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:54 PM Revision 77689f18 (ceph): ReplicatedPG::C_ProxyRead: fix dropped lock
- Fixes: 10633
Signed-off-by: Samuel Just <sjust@redhat.com> - 08:54 PM Bug #10633: osd: assert in lock in C_CopyFrom
- I think it's not a use after free, but rather a recursive lock error. We tend to do a promote just after we do a pro...
- 08:27 PM Revision 7e8dccc9 (ceph): rados/thrash: add short_pg_log variant to encourage backfill
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 08:08 PM Bug #10629: osd/PG.cc: 2775: FAILED assert(values.size() == 2)
- dirty_info and dirty_big_info get set in PG::init in _create_lock_pg(
- 07:55 PM Bug #10629: osd/PG.cc: 2775: FAILED assert(values.size() == 2)
From teuthology-2015-01-28_17:05:01-upgrade:giant-x-next-distro-basic-multi/728068 logs I see that osd.0 was killed...- 12:19 AM Bug #10629: osd/PG.cc: 2775: FAILED assert(values.size() == 2)
- Seeing also in run: http://pulpito.ceph.com/teuthology-2015-01-28_17:05:01-upgrade:giant-x-next-distro-basic-multi/
... - 07:48 PM Revision 861a18b1 (ceph): rgw: fix partial GET in swift
- Fixes: #10553
backport: firefly, giant
Don't set the ret code to reflect partial download, just set the
response sta... - 07:45 PM Revision aac4c255 (ceph): osd/: add state PG_STATE_PEERED
- We need a state to represent the pg state where we are below
min_size, but trying to recover.
Signed-off-by: Samuel ... - 07:45 PM Revision 96c3af83 (ceph): PG: remove very obsolete comment about backfill_pos
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:45 PM Revision 63e5f578 (ceph): PG: break waiting_for_peered out of waiting_for_active
- waiting_for_peered now holds ops until peering completes (activation,
not necessarily state active). waiting_for_act... - 07:45 PM Revision c4793abb (ceph): osd_types: add last_peered, last_became_peered
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:45 PM Revision 5911b450 (ceph): PG::proc_master_log: assume les and history.les from log source
- Otherwise, we might later go peered (not active) and not distribute
a non-0 last_epoch_started. This should be safe ... - 07:45 PM Revision e5a96fdb (ceph): PG: move most of all_activated_and_commited into the AllReplicasActivat...
- It's confusing to have that logic split up so much.
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:45 PM Revision 818b91b7 (ceph): osd/: go "peered" instead of "active" when < min_size
- In the case of a replicated pool, the pg will transition to "peered"
rather than "active", where it can perform backf... - 07:45 PM Revision b31221af (ceph): OSD: allow recovery in peered
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:45 PM Revision 0e3af8d8 (ceph): ReplicatedPG: only populate_obc_watchers if active
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:45 PM Revision abd11548 (ceph): doc: add documentation for undersized
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:39 PM rgw Bug #10701 (Pending Backport): rgw: content length parsing calls strtol() instead of strtoll()
- 06:44 PM rgw Bug #10701 (Fix Under Review): rgw: content length parsing calls strtol() instead of strtoll()
- 06:35 PM rgw Bug #10701 (Resolved): rgw: content length parsing calls strtol() instead of strtoll()
- 07:37 PM Revision d3f1d6ea (ceph): Merge pull request #3553 from ceph/wip-10701
- rgw: use strict_strtoll() for content length
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:36 PM CephFS Bug #10703 (Duplicate): failures in libcephfs-java tests
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-28_23:04:02-fs-master-testing-basic-multi/729688/...
- 07:33 PM rgw Bug #10553 (Resolved): rgw: fail to download object in swift when range specified > 512k
- 06:59 PM rgw Bug #10553 (Pending Backport): rgw: fail to download object in swift when range specified > 512k
- 07:33 PM Revision 1f165d25 (ceph): ReplicatedPG: block writes on degraded objects for ec pools
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision 721c8783 (ceph): ReplicatedPG: if we got ENOENT and an obc, we need to check the locks
- Otherwise, we might return ENOENT out of order.
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:33 PM Revision 0a32d3b1 (ceph): ReplicatedPG::agent_maybe_evict: take write lock, skip on failure
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision 964d1775 (ceph): append_log: use remove_snap_mapped_object
- Backport: giant, firefly
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:33 PM Revision f5134c8b (ceph): ReplicatedPG::wait_for_unreadable_object: use prep_object_replica_pushe...
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision e00daf56 (ceph): ReplicatedPG::cancel_pull: drop_recovery_read lock
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision a8e041f0 (ceph): osd_types: add excl obc lock
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision a81f3e6e (ceph): ReplicatedPG::get_rw_locks: use excl lock for read & write_ordered
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:33 PM Revision a74296fb (ceph): PG::purge_strays: purge peer_missing as well
- Backport: giant, firefly
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:33 PM CephFS Bug #10702 (Resolved): ceph-qa-suite: hung client-recovery task in nightlies
- http://pulpito.ceph.com/teuthology-2015-01-28_23:04:02-fs-master-testing-basic-multi/729695/
I gathered the logs f... - 07:28 PM Revision 3bf42af2 (ceph): rgw: fix partial GET in swift
- Fixes: #10553
backport: firefly, giant
Don't set the ret code to reflect partial download, just set the
response sta... - 07:28 PM Revision f9abffbb (ceph): osd/: don't block writes on degraded objects
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:27 PM Revision c632fecb (ceph): osd/: update peer_missing and local missing if we write a degraded object
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:26 PM Revision 56b8fc8c (ceph): ReplicatedPG: always take recovery_read_lock for recovery
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:17 PM rgw Bug #10329 (Resolved): rgw: s3 need to return SignatureDoesNotMatch instead of AccessDenied
- no need to backport this one
- 07:14 PM rgw Bug #10354 (Resolved): Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-m...
- 06:53 PM Revision 1c25dbaf (ceph): rgw: use strict_strtoll() for content length
- instead of strict_strtol().
Backport: giant, firefly
Fixes: #10701
Reported-by: Axel Dunkel <ad@dunkel.de>
Signed-o... - 05:59 PM rbd Bug #10652: "rbd: import failed: (38) Function not implemented" in multi-version-next-distro-basi...
- Same
Run: http://pulpito.ceph.com/teuthology-2015-01-28_23:20:01-multi-version-master-distro-basic-multi/
Job: 7299... - 05:45 PM devops Bug #10532: Failed "joining thrashosds" - suspected low memory config on vps
- And again, could be vps related?
Run: http://pulpito.ceph.com/teuthology-2015-01-29_17:05:02-upgrade:giant-x-next-... - 05:27 PM Stable releases Tasks #10560: dumpling v0.67.12
- try v0.67.11 to establish a baseline
- 02:38 PM Stable releases Tasks #10560: dumpling v0.67.12
- rgw is green
- 02:36 PM Stable releases Tasks #10560: dumpling v0.67.12
- single rados issue
- 05:21 PM Revision b1435e6e (ceph): xio: Enforce at least two portals if bind
- Enforce at least two portals being set/created if one set
xio_portals_thread = 1 by mistake
Return the correct last u... - 05:11 PM Revision e6c2c823 (ceph): Merge pull request #3476 from ktdreyer/wip-rpm-radosgw-logrotate
- ceph.spec.in: move rgw logrotate to rgw subpackage
Reviewed-by: Boris Ranto <branto@redhat.com>
Reviewed-by: Sage We... - 05:09 PM Revision 6cffebd4 (ceph): Merge pull request #3437 from diurchenko/patch-2
- rgw: fix doc, wrong HTTP header name
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:53 PM rgw Bug #10667 (Resolved): Success code returned by rgw for POST request on container is 202 but swif...
- Fixed by commit:a0a5185b6bf527c51f08690bbdd929dfed25fcca
- 04:43 PM Revision f33f6640 (ceph): Merge pull request #3546 from zhouyuan/204_post_container
- rgw: Response 204 when post on containers
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:22 PM rgw Bug #10665 (Fix Under Review): RGW swift API: Adding custom metadata to containers using x-contai...
- 04:13 PM Bug #10700 (Resolved): ceph_test_rados EINVAL
- 2015-01-30 08:04:05,278.278 INFO:teuthology.orchestra.run.burnupi42.stderr:2015-01-30 08:05:49.341511 7f36eb874700 1...
- 04:10 PM rgw Bug #10645: using x-fresh-metadata=true in object copying using swift API copies custom metadata ...
- I still doubt if we need this. It seems like x-fresh-metadata header is used only internally by swift and is not a pa...
- 03:47 PM Linux kernel client Bug #8087: libceph: null deref in osd_reset -> __reset_osd -> __remove_osd
- I have reproduced the bug 3 times today and had full kernel logging activated the last time. The log and a screenshot...
- 03:39 PM Revision cbf0691b (ceph): rgw: fail s3 POST auth if keystone not configured
- Fixes: #10698
This fixes issue introduced in 8b3dfc9472022ea45ad24e02e0aa21dfdad798f8,
where if user does not exist, ... - 02:44 PM Bug #10546 (Fix Under Review): ceph time check start round bug in monitor.cc
- https://github.com/ceph/ceph/pull/3550
- 02:18 PM Revision 10ddab8a (ceph): doc: Fixed hyperlink.
- Signed-off-by: John Wilkins <jowilkin@redhat.com>
- 12:24 PM Fix #10519: Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph pg dump
- Now I did it :)
- 12:00 PM Revision a0a5185b (ceph): rgw: Response 204 when post on containers
- Currently POST request on container returns 202 if success. But in Swift
the code is 204. Let's use 204 to keep align... - 11:26 AM Bug #10643 (Pending Backport): "FAILED assert(other->is_writeable())" in upgrade:giant-x-next-dis...
- This was caused by missing backports on giant. Pull request has been created: https://github.com/ceph/ceph/pull/3548
- 11:18 AM Revision 0df7cf1e (ceph): mon: MDSMonitor: return if fs exists on 'fs new'
- We were just setting return code to -EINVAL, while allowing the logic to
continue regardless. If we are to return er... - 11:13 AM Bug #10670: osd segfault
- I found new details for this bug.
I repairing my cluster so:
1. disable autostart ceph on boot on nodes with die ... - 10:37 AM Revision b7ab6245 (ceph): xio: Remove whitespace changes
- Remove whitespace changes from xio's "spread and accept connections
using different portals" patch
Signed-off-by: Vu... - 08:04 AM Bug #10433: OSD osd/ReplicatedPG.cc: 5540: FAILED assert(soid < scrubber.start || soid >= scrubbe...
- Unfortunately, I still can not repeat this on the test stand....
- 07:36 AM Bug #10433: OSD osd/ReplicatedPG.cc: 5540: FAILED assert(soid < scrubber.start || soid >= scrubbe...
- Samuel.
This does not duplicate #8011. Today, the same error on Cache Pool. I think it depends on the Cache Pool sin... - 07:38 AM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Samuel.
yes, this is another mistake. http://tracker.ceph.com/issues/10433#note-3 - 05:23 AM Revision 7c802487 (ceph): ObjectCacher: Only r >= 0, it need the read data.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 05:23 AM Revision ef48a70d (ceph): osdc: only external_call can touch object.
- In fact if there is retry reading, the touch_bh also touch object.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 05:21 AM Revision ed209a5e (ceph): osdc: For read w/ DONTNEED, if read data contain all cached data, move ...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 04:59 AM rgw Feature #10696 (New): RGW swift API: Setting x-account-meta-quota-bytes for an account returns "4...
- Steps to reproduce:
1. curl -i "https://10.20.20.15:80/swift/v1" -X POST -H "x-auth-token: 7ac8302d386145b2b9b7c8f... - 04:05 AM rgw Feature #9400 (In Progress): object versioning: sync agent support
- 04:05 AM rgw Feature #9395 (Resolved): rgw: object versioning, olh functionality
- 04:05 AM rgw Feature #9396 (Resolved): rgw: object versioning, objclass support for olh
- 04:05 AM rgw Feature #9397 (Resolved): rgw: object versioning, tie to REST api
- 04:05 AM rgw Feature #9399 (Resolved): rgw: object versioning, bucket index log support for olh
- 04:03 AM rgw Feature #9394 (Resolved): rgw: object versioning, support for multiple object instances
- Object versioning merged at commit:7e5e1ea1a51637de1c9a37039f21d88aee43ee83
- 04:01 AM rgw Feature #10191 (Resolved): rgw: object versioning multi-zone support
- 04:01 AM rgw Feature #10454 (In Progress): rgw: sync agent incremental sync of versioned objects
- 04:01 AM rgw Cleanup #9772 (Resolved): rgw: reorganize RGWRados
- 04:01 AM rgw Feature #8216 (Resolved): rgw: object versioning objclass support
- 04:00 AM rgw Feature #8217 (Resolved): rgw: object versioning object overwrite / delete changes
- 04:00 AM rgw Feature #8218 (Resolved): rgw: object versioning manifest changes
- 03:49 AM Revision 3dca5ef5 (ceph): osdc: Make ObjectCahce can hanle read with DONTNEED.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:44 AM Revision 3d38e1f5 (ceph): osdc: touch hit bh although there are missing or rx bh.
- Avoid losing the hit bh when later read, it should touch hit bh like rx bh.
Signed-off-by: Jianpeng Ma <jianpeng.ma@... - 03:36 AM Revision 3687dcbc (ceph): osdc: Make ObjectCahce can hanle write with DONTNEED.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:29 AM Revision 28e73a7b (ceph): osdc: Make ObjectCache can accept fadvise_flags.
- The field flags of OSDRead/OSDWrite don't use anymore. Replace it with
fadvise_flags.
Signed-off-by: Jianpeng Ma <ji... - 03:29 AM Revision fc76c89d (ceph): osdc: add new filed dontneed in BufferHead.
- For read/write op with LIBRADOS_OP_FLAG_FADVISE_DONTNEED,
the hit bh set this as true and later move into the tail of... - 03:20 AM Revision 33732499 (ceph): Fix ReplicatedPG do_xattr_cmp_u64
- 1. bufferlist.c_str() will return a string which is longer than its real length.
This could cause an error result fro... - 01:37 AM Bug #9788: "Assertion: common/HeartbeatMap.cc: 79" placeholder for "hit suicide timeout" issues
- On vps again
Run: http://pulpito.ceph.com/teuthology-2015-01-28_17:05:01-upgrade:giant-x-next-distro-basic-vps/
J... - 01:34 AM Revision 707c78b5 (ceph): Only create a key of 256 bits length, not 256 bytes
- The actual open of the encrypted partition only uses the first 256 bits regardless.
Signed-off-by: Andrew Bartlett <... - 01:34 AM Revision c83a288a (ceph): Rework ceph-disk to allow LUKS for encrypted partitions
- LUKS allows for validation of the key at mount time (rather than
simply mounting a random partition), specification o... - 01:34 AM Revision 998b4615 (ceph): Change ceph-disk default to use LUKS for encrypted partitions
- LUKS allows for validation of the key at mount time (rather than
simply mounting a random partition), specification o... - 01:34 AM Revision 2113524b (ceph): Add tests for ceph dmcrypt encryption
- Signed-off-by: Andrew Bartlett <abartlet@catalyst.net.nz>
- 01:34 AM Revision 6a45b8ed (ceph): add all possible ceph-disk run-time requirements to build time deps
- There really should be a better way than this to ensure the right things are installed for make check.
The existing ... - 12:42 AM Revision 7e5e1ea1 (ceph): Merge pull request #3526 from ceph/wip-rgw-versioning-4
- Wip rgw versioning 4
Reviewed-by: Sage Weil <sage@redhat.com> - 12:24 AM Revision 4c50f6a7 (ceph): rgw: more merge related fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:07 AM Revision 01cc9d54 (ceph): rgw: fix merge artifact
- s/XMLArgs/RGWHTTPArgs
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:05 AM Revision f1471431 (ceph): Merge remote-tracking branch 'origin/master' into wip-rgw-versioning-4
- Conflicts:
src/rgw/rgw_admin.cc
01/29/2015
- 11:59 PM Bug #10695 (Resolved): nan from ceph osd df
- ...
- 11:32 PM Linux kernel client Bug #9928: kernel BUG at fs/ceph/caps.c:2307!
- I found the same trace in my logfiles but also a similar with a NULL dereference instead (kernel 3.14.28 stable + som...
- 11:06 PM rgw Bug #10194 (Resolved): rgw: fcgi connections are not closed when using mod-proxy-fcgi
- 11:06 PM Revision 243860b5 (ceph): Merge pull request #3125 from ceph/wip-10194-master
- Wip 10194 master
Reviewed-by: Sage Weil <sage@redhat.com> - 10:22 PM Revision e26023ee (ceph): PG: set scrubber.start = scrubber.end after scrub_compare_maps
- This is how the scrubber behaved prior to
218de829b1affa8ed413572736fcc3314f65730b
Fixes: 10693
Signed-off-by: Samue... - 10:21 PM Revision 4f9e6ed8 (ceph): PG: remove block_writes from scrubber
- block_writes is actually redundant, it is true iff scrubber.start !=
scrubber.end.
Signed-off-by: Samuel Just <sjust... - 10:09 PM Bug #10694 (Won't Fix): "Assertion: osd/Watch.cc: 290: FAILED assert(!cb)" in upgrade:dumpling-du...
- Run: http://pulpito.ceph.redhat.com/teuthology-2015-01-27_13:00:01-upgrade:dumpling-dumpling-distro-basic-magna/
Job... - 10:07 PM Bug #10693: FAILED assert(soid < scrubber.start || soid >= scrubber.end): oi digest variant
- 09:59 PM Bug #10693 (Resolved): FAILED assert(soid < scrubber.start || soid >= scrubber.end): oi digest va...
- 2015-01-28T07:11:26.339 INFO:tasks.ceph.osd.0.burnupi16.stderr:osd/ReplicatedPG.cc: In function 'void ReplicatedPG::f...
- 10:06 PM rgw Bug #10672: dumpling s3test failures
- Same issues
Run: http://pulpito.ceph.redhat.com/teuthology-2015-01-27_13:00:01-upgrade:dumpling-dumpling-distro-basi... - 10:06 PM Bug #8011 (Pending Backport): osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || s...
- 09:58 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Also, this is an entirely distinct bug, so I'm making this Pending Backport again and opening a new one.
- 09:57 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Making patch.
- 09:57 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- This most recent incarnation is due to oi digests: we block_writes until the end of COMPARE_MAPS. The assert should ...
- 09:48 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Irek, you are seeing the previous incarnation of this bug. The relevant fix has not yet been backported to firefly.
- 12:49 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Yes, I have the same error.
[root@ceph04 ceph]# ceph -v
ceph version 0.80.8 (69eaad7f8308f21573c604f121956e64679a... - 09:46 PM Bug #10670: osd segfault
- Feel free to mark it new again if there is more information.
- 09:45 PM Bug #10670 (Rejected): osd segfault
- It sounds a lot like there is something off with that glibc. You probably want to take it up with the appropriate ma...
- 09:31 PM rgw Feature #8224 (Resolved): rgw: test suite for object versioning
- 09:30 PM rgw Feature #8220 (Resolved): rgw: object versioning, garbage collector changes
- 09:30 PM rgw Feature #8219 (Resolved): rgw: object versioning RESTful api
- 09:30 PM rgw Feature #8222 (Resolved): rgw: object versioning, object creation changes
- 09:28 PM Revision 2980f3ac (ceph): Merge branch 'prio_hb_pkts' of git://github.com/wenjianhn/ceph
- Conflicts:
src/msg/Messenger.h - 09:17 PM Revision bed22b49 (ceph): doc: improve incomplete state documentation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:06 PM Revision 7237933f (ceph): Merge pull request #3543 from ceph/wip-hints
- librados: rename NOREUSE to NOCACHE
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Samuel Just <sjust@re... - 09:04 PM Revision 0e0e3e49 (ceph): Merge pull request #3295 from majianpeng/fix2
- osd: add per-pool fadvise-dontneed flag
Reviewed-by: Sage Weil <sage@redhat.com> - 09:03 PM Revision b29167c6 (ceph): Merge pull request #3392 from ceph/wip-crush-straw2
- crush: new straw2 bucket
Reviewed-by: Joao Eduardo Luis <joao@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com... - 09:03 PM Revision e41c0521 (ceph): Merge pull request #3495 from XinzeChi/wip-size-empty
- cleanup: replace some size() or length() with !empty()
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:00 PM Revision 89bd6b13 (ceph): librados: rename NOREUSE to NOCACHE
- As far as I can tell, the posix_fadvise() distinction between WONTNEED and
NOREUSE is subtle: one says I won't access... - 08:24 PM Revision 85717394 (ceph): support Boost 1.57.0
- Sometime after 1.55, boost introduced a forward declaration of
operator<< in optional.hpp. In 1.55 and earlier, when ... - 08:10 PM Bug #10634: watch-notify-same-primary.yaml failure
- I think you have to actually poll until you get your first line. Of course, please don't poll forever; use this handy...
- 07:29 PM Revision 2ad229c5 (ceph): osd: allow extra reqids to be stashed in each pg_log_entry_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:29 PM Revision 4d310a82 (ceph): osd: preserve extra_reqids in PGLog
- The log scraping is unfortunately O(n) in the size of the log. We can
also follow objects and then the prior_version... - 07:29 PM Revision eefdb32c (ceph): osd: preserved extra_reqids on promote, flush
- This fixes idempotency for operations across caching changes (promote,
flush and cache mode changes).
Fixes: #8935
S... - 07:29 PM Revision f6239065 (ceph): osd/PGLog: only do slow extra_reqid search of object appears at least once
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:24 PM Revision ca71376c (ceph): cls_rgw: fix rgw_bucket_olh_log_entry::epoch initialization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 06:53 PM Revision 61378f25 (ceph): add pg_string_state function
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 06:50 PM Bug #10691 (Fix Under Review): ceph-dencoder links to libtcmalloc, and shouldn't
- patch for master: https://github.com/ceph/ceph/pull/3542
- 06:25 PM Bug #10691: ceph-dencoder links to libtcmalloc, and shouldn't
- I'd love to have a LIBMDS_TYPES, but the reason we didn't do so already is that it's much harder than for the other s...
- 06:24 PM Bug #10691: ceph-dencoder links to libtcmalloc, and shouldn't
- Thanks Greg, I think you're right. Yesterday evening when I talked with Dan about this, he was musing whether it woul...
- 06:15 PM Bug #10691: ceph-dencoder links to libtcmalloc, and shouldn't
- Looks like the linkage is sneaking in via the autotools LIBMDS variable (which itself includes LIBPERFGLUE). We don't...
- 05:47 PM Bug #10691 (Resolved): ceph-dencoder links to libtcmalloc, and shouldn't
- The /usr/bin/ceph-dencoder binary links to libtcmalloc, and it has no need to link to it.
From a packaging perspec... - 06:39 PM Revision cd2491a1 (ceph): Merge pull request #3540 from athanatos/wip-sam-cache-object-context-ac...
- Wip sam cache object context across op
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redh... - 06:19 PM Bug #10616 (Pending Backport): osd/ReplicatedPG.cc: 5790: FAILED assert(ctx->new_obs.exists == ct...
- 06:18 PM Revision 880f9489 (ceph): Merge pull request #3536 from athanatos/wip-10616
- Wip 10616
Reviewed-by: Sage Weil <sage@redhat.com> - 06:09 PM Revision 32b9bb7a (ceph): QueueRing: a reduced contention queue
- A queue that provides multi-readers, multi-writers concurrency with a
reduced lock contention.
Signed-off-by: Yehuda... - 06:09 PM Revision 4feb8644 (ceph): rgw: reuse fcgx connection structure
- Fixes: #10194
Reuse the fcgx connection structure. It forces FCGX_Accept_r() freeing
up or reusing the connection if... - 06:04 PM Revision ecd5e5a2 (ceph): test/encoding/types.h: add new structs for testing
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 06:04 PM Revision 5849380c (ceph): cls_rgw: add missing struct test instance generator
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:38 PM rgw Bug #10690 (Can't reproduce): RGW swift API: Response returned by query with temp url and inline ...
- content-disposition metadata for object is supported by rgw and can be added either by POST or PUT request. If this m...
- 05:31 PM Revision 5808c77a (ceph): rgw: don't call send_response() explicitly
- This will make us send the response twice and clobber the http
state.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:31 PM Revision 4184387d (ceph): cls_rgw: fix encoding for cls_rgw_obj
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:31 PM Revision 18592393 (ceph): rgw-admin: set explicit "null" instance when needed
- When clearing a bucket, if instance is not found, set it to "null",
otherwise we'll just create a delete marker.
Sig... - 05:31 PM Revision 2e3f75fb (ceph): rgw: don't clear olh log if we lost in race
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:31 PM Revision b685baad (ceph): workunits/rgw: set radosgw-admin location through env variable
- add new RGW_ADMIN to be able to set call.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:31 PM Revision 00f21d8b (ceph): workunits/rgw: adjust radosgw-admin output parsing
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 05:31 PM Revision 0ace0f5e (ceph): rgw: fix a crash when getting ECANCELED in delete_obj()
- bufferlist::c_str() returns NULL if bufferlist is empty. We were
clearing the state, later on assigning s->obj_tag to... - 05:31 PM Revision caefe693 (ceph): rgw: version id should not contain underscore
- The problem is that we use underscore for the raw object name encoding.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:31 PM Revision 9c8424fe (ceph): rgw: guard olh modification
- Add a check that validates that object still exists. This shouldn't really be
an issue, as we later compare the tag.
... - 05:31 PM Bug #10689 (Duplicate): osd/ReplicatedPG.cc: FAILED assert(soid < scrubber.start || soid >= scrub...
- Having this error regularly (on every OSD) when deep-scrub is enabled.
Using ceph version 0.91-573-gae6bd61 (ae6bd61... - 05:26 PM rgw Bug #10062 (Pending Backport): s3-test failures using keystone authentication
- 05:25 PM Bug #10688 (Fix Under Review): Giant fails to build with Boost v1.57.0
- patch submitted to master: https://github.com/ceph/ceph/pull/3537
- 04:29 PM Bug #10688: Giant fails to build with Boost v1.57.0
- Petr's patch from http://pkgs.fedoraproject.org/cgit/ceph.git/tree/ceph-0.87-boost157.patch is attached to this ticket.
- 04:26 PM Bug #10688 (Resolved): Giant fails to build with Boost v1.57.0
- Fedora Rawhide (what will become Fedora 22) is about to update Boost to v1.57.0.
Ceph needed a small patch in orde... - 05:13 PM Revision 0b9859bb (ceph): cmake: Fix CMakelist.txt to compile librbd, libcommon
- Add file TextTable.cc to libcommon sources
Add files (ContextCompletion.cc, AsysncObjectThrottle.cc, CopyupRequest.cc... - 05:13 PM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same:
Run: http://pulpito.ceph.com/teuthology-2015-01-28_17:13:01-upgrade:firefly-x-next-distro-basic-multi/
Job: 7... - 05:08 PM Revision 51dd9b28 (ceph): xio: Spread and accept connections using different portals
- Accelio's xio_accept "light redirection" has limitation of 2 portals array only.
Change xio to overcome this limitati... - 04:54 PM Revision d5c8a57d (ceph): Merge pull request #3524 from ceph/wip-8251-2
- Wip 8251 2
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:48 PM Revision e761b748 (ceph): async: directly call delete without check
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:40 PM Revision dd3ad6b9 (ceph): Merge pull request #3535 from ceph/wip-librbd-tests
- tests: ensure RBD integration tests exercise all features
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:19 PM Revision b6fa40fe (ceph): Merge pull request #3530 from xinxinsh/wip-cleanup
- cleanup : remove unused perf counter
- 03:13 PM Stable releases Tasks #10560: dumpling v0.67.12
- update the inventory with a lot more details
- 02:51 PM Stable releases Tasks #10560: dumpling v0.67.12
- the ntp sepia lab issues were resolved, reschedule rados, rgw and rbd suites
- 02:38 PM Feature #10686 (In Progress): SHEC erasure code plugin
- 02:34 PM Feature #10686 (Resolved): SHEC erasure code plugin
- https://wiki.ceph.com/Planning/Blueprints/Hammer/Shingled_Erasure_Code_%28SHEC%29
https://github.com/ceph/ceph/pul... - 01:29 PM Revision 68c6f0e4 (ceph): mSHEC r44 initial commit
- Signed-off-by: Takeshi Miyamae <miyamae.takeshi@jp.fujitsu.com>
- 01:18 PM Revision e45e97be (ceph): run-make-check: use nproc and shorter git expression
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 12:53 PM Fix #10519: Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph pg dump
- It looks good :-) Would you mind proposing your modification via a pull request at https://github.com/ceph/ceph/pulls ?
- 10:55 AM Fix #10519: Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph pg dump
- I resolve it by replacing constant by string CRUSH_ITEM_NONE, like this:
$ ./ceph pg dump
pg_stat objects mip degr ... - 10:34 AM Bug #10676: Firefly: Ceph man page is out of sync with actual command options
- * firefly backport https://github.com/ceph/ceph/pull/3521
- 10:15 AM Revision c2c7f9fe (ceph): Merge pull request #3528 from RobertJansen1/patch-1
- corrected some confusing numbers
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:07 AM Revision 0a998f51 (ceph): edited failure conclusion
- Signed-off-by: Robert Jansen <r.jansen@fairbanks.nl>
- 10:03 AM Revision 4527e8f8 (ceph): corrected some confusing numbers
- Signed-off-by: Robert Jansen <r.jansen@fairbanks.nl>
- 08:57 AM rgw Bug #10684 (Resolved): RGW swift API: Response returned by GET request on account does not contai...
- Response header does not contain following headers:
x-account-bytes-used
x-account-container-count
x-account-obj... - 08:42 AM rgw Bug #10683 (Resolved): RGW swift API: GET request for container/object with query parameter limit...
- if value of query parameter "limit" is 0 rgw behaves as if limit parameter is not provided in GET query for container...
- 08:07 AM rgw Bug #10682 (Resolved): RGW swift API: specifying end_marker query parameter in url is not recogni...
- Steps to reproduce:
1. swift post container1
2. swift post container2
3. swift post container3
4. swift post co... - 07:23 AM Revision 94b60c5e (ceph): osd: don't log op stats for proxy read in the cache tier
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 02:16 AM Revision a66898fc (ceph): cleanup : remove unused perf counter
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 02:12 AM Revision 91f24f34 (ceph): librbd: copy-on-read should update the object map
- The new copy-on-read functionality needs to update the
object map when a copyup occurs for an object.
Signed-off-by:... - 02:12 AM Revision f4b9442a (ceph): cls_rbd: object_map_resize shrink protection
- When shrinking an object map, object_map_resize now ensures
that the objects being removed are initialized to default... - 02:12 AM Revision b63246f1 (ceph): librbd: refactor existing object map code to its own class
- As a preparation for switching all current object map manipulations
within librados callbacks to AIO, the existing ob... - 02:12 AM Revision 4328069e (ceph): test: correct two issues with the librados_test_stub
- Corrected a problem where the snapshot id was being incorrectly
replaced on history object versions. Also corrected ... - 02:12 AM Revision a8716518 (ceph): librbd: object map updates should use AIO
- Update the existing AbstractWrite state machine to handle
updating the object map before and after the object update.... - 02:12 AM Revision 7e751ce9 (ceph): librbd: Implement object map for tracking in-use objects
- The object map is stored in a new 'rbd_object_map.<id>'
object in the image's pool. The object map tracks blocks
that... - 02:12 AM Revision a41878a7 (ceph): librbd: Use object map for IO operations
- When the RBD object map feature is enabled, IO operations
now check whether or not an object exists before sending an... - 02:12 AM Revision 8571e476 (ceph): cls_rbd: Add support for image flags
- Image flags are an optional addition to the RBD image header
which can be used to preserve state. The flags support
... - 02:12 AM Revision 719515a8 (ceph): librbd: Use RBD image flags for invalid object maps
- If the RBD object map state is corrupted, flag the object map
as invalid so that it won't be used for IO operations.
... - 02:12 AM Revision 9aad59dc (ceph): librbd: Protect object map updates with a lock assertion
- Use the new assert_locked functionality to protect object
map updates to only the single client that holds the lock.
... - 02:12 AM Revision 8fa37677 (ceph): rbd: only enable object map if enabled in ceph config
- As a way to introduce the RBD object map as an optional tech
preview, only enable it for new images/clones if the
rbd... - 02:12 AM Revision 13fd6d1d (ceph): cls_rbd: Add methods for manipulating an image object map
- The object map will track the current state of each object
within an RBD image.
Signed-off-by: Jason Dillaman <dilla... - 01:14 AM Stable releases Tasks #10639: release firefly v0.80.8
- display more information about each issue link
- 12:51 AM Bug #10370 (Can't reproduce): "MaxWhileTries: 'wait_until_healthy'reached maximum tries (150) aft...
- marking this as can't reproduce for now
- 12:49 AM Bug #10431 (Resolved): PG can not finish peering due to mismatch between OSD peering queue and PG...
- A fix for this is already merged.
- 12:36 AM Revision ca214c96 (ceph): rgw: also convert sharded replicalog entries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 12:10 AM Revision 0a4956e2 (ceph): rgw: get rid of replicalog index_by_instance param
- We convert old entries anyway, just complicates everything. Only use
that was kept is the one needed for the conversi... - 12:05 AM rgw Bug #10311 (Resolved): Object is deleted automatically if conditional PUT returns 412
- 12:04 AM rgw Bug #10311: Object is deleted automatically if conditional PUT returns 412
- No need for backport tag. There's no conditional PUT in firefly / giant.
01/28/2015
- 11:56 PM Revision 778a53ab (ceph): rgw-admin: add replicalog update command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:56 PM Revision 791c15bd (ceph): rgw: convert old replicalog entries if needed
- If reading a bucket replicalog entry and one doesn't exist, fall back to
the old key, and convert it to the new one. ... - 11:56 PM Revision c4a6eabb (ceph): rgw: fixing rebase casualties
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:34 PM Bug #10681: osd crashed (in many jobs) in upgrade:firefly-x-giant-distro-basic-multi run
- Running suite - http://pulpito.front.sepia.ceph.com/teuthology-2015-01-28_19:22:43-upgrade:firefly-x-giant-distro-bas...
- 11:08 PM Bug #10681 (Resolved): osd crashed (in many jobs) in upgrade:firefly-x-giant-distro-basic-multi run
- backported to giant
- 10:41 PM Bug #10681: osd crashed (in many jobs) in upgrade:firefly-x-giant-distro-basic-multi run
- 8d29a4a231666830914903b95599d80da7b97def was recently backported to firefly. It includes a test for the fixed proble...
- 10:08 PM Bug #10681 (Resolved): osd crashed (in many jobs) in upgrade:firefly-x-giant-distro-basic-multi run
- Run: http://pulpito.ceph.com/teuthology-2015-01-25_18:13:01-upgrade:firefly-x-giant-distro-basic-multi/
Jobs: 722253... - 10:55 PM Revision aa038684 (ceph): osd: handle no-op write with snapshot case
- If we have a transaction that does something to the object but it !exists
both before and after, we will continue thr... - 10:52 PM Bug #10262 (Pending Backport): osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- 10:49 PM Stable releases Tasks #10641: release firefly v0.80.9
- update inventory
- 10:05 PM CephFS Bug #10550 (Resolved): Assertion in ceph-mds on failures in ::init
- Merged to master.
- 05:02 PM CephFS Bug #10550: Assertion in ceph-mds on failures in ::init
- I made a pull reuqest via github. Commit log has been improved as well. Direct link: https://github.com/ceph/ceph/pul...
- 12:06 PM CephFS Bug #10550: Assertion in ceph-mds on failures in ::init
- Thanks for the patch. Please could you resend that as either a github pull request or if that is not possible, a git...
- 10:04 PM Revision 94bb2652 (ceph): Merge pull request #3514 from rzarzynski/wip-10550
- mds: Wip 10550
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:12 PM rgw Bug #10329: rgw: s3 need to return SignatureDoesNotMatch instead of AccessDenied
- Unexpected but harmless backport from v0.90 to v0.89 ...
- 09:05 PM Stable releases Tasks #10501: giant v0.87.1
- remove more redundant information
- 08:52 PM Stable releases Tasks #10501: giant v0.87.1
- cleanup redundant entries
- 08:34 PM Stable releases Tasks #10501: giant v0.87.1
- add to each commit the release tag it belongs to
- 06:38 PM Stable releases Tasks #10501: giant v0.87.1
- fix references to tickets
- 05:01 PM Stable releases Tasks #10501: giant v0.87.1
- update the inventory with information discovered by following cherry pick references. Add to the display of a list of...
- 09:02 PM rgw Bug #10334: rgw: s3 need to return InvalidAccessKeyId instead of AccessDenied
- There seemed to be a harmless spurious backport in master...
- 09:02 PM CephFS Feature #10679 (New): Add support for the chattr +i command (immutable file)
- To add an additional layer of protection for files I would like to see
support for the chattr +i command added for ... - 08:16 PM Revision 8820d4c3 (ceph): Merge pull request #3520 from ceph/dumpling-rsync-qa
- Dumpling rsync qa
Reviewed-by: John Spray <john.spray@redhat.com> - 08:02 PM Bug #10678: Hammer: Ceph man page is out of sync with actual command options
- Here are the differences between Giant and the current master branch for Hammer:...
- 07:52 PM Bug #10678 (Resolved): Hammer: Ceph man page is out of sync with actual command options
For hammer the ceph man page doesn't match the ceph -h.- 07:55 PM Bug #10677: Giant: Ceph man page is out of sync with actual command options (giant)
- These are the differences from firefly to giant of ceph -h:...
- 07:52 PM Bug #10677 (Resolved): Giant: Ceph man page is out of sync with actual command options (giant)
In Giant the ceph man page doesn't match the ceph -h.- 07:50 PM Bug #10676 (Resolved): Firefly: Ceph man page is out of sync with actual command options
In firefly the ceph man page doesn't match the ceph -h.- 07:44 PM Revision 18a40ff2 (ceph): qa: use sudo even more when rsyncing /usr
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 3aa7797741f9cff06053a2f31550fe6929039692) - 07:44 PM Revision d2bdf3dd (ceph): qa: use sudo when rsyncing /usr so we can read everything
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit fa07c04231db2d130de54647957ffab4a7a53733) - 07:20 PM Revision 95c176d7 (ceph): do not try and install libcephfs-java via extra_packages
- It's been added to the default install task, because the
package name varies across distros.
Fixes: #10510
Signed-o... - 07:18 PM Revision 30e5f3d9 (ceph): do not try and install libcephfs-java via extra_packages
- It's been added to the default install task, because the
package name varies across distros.
Fixes: #10510
Signed-o... - 06:23 PM rgw Bug #10672: dumpling s3test failures
- Same in run http://pulpito.ceph.redhat.com/teuthology-2015-01-26_20:27:53-upgrade:dumpling-dumpling-distro-basic-magn...
- 02:56 PM rgw Bug #10672 (Duplicate): dumpling s3test failures
- http://pulpito.ceph.redhat.com/teuthology-2015-01-26_22:04:01-rgw-dumpling-distro-basic-magna/
- 05:57 PM devops Bug #10330: apt-mirror timeouts
- I have a caching nginx proxy up on mira056 that appears to be working well.
- 05:27 PM devops Bug #10330: apt-mirror timeouts
- More like these.
Run: http://pulpito.ceph.com/teuthology-2015-01-27_17:05:04-upgrade:giant-x-next-distro-basic-multi... - 05:54 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- I think it's probably best to merge it all as one pull request; there's nothing urgent here and that way we'll know w...
- 05:41 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- Thank you for your review. You are right, on Linux the call should not fail with ELOOP if there was O_PATH present in...
- 05:36 PM Revision 5e898170 (ceph): Merge pull request #3499 from ceph/wip-perf-filter
- common: filtering in `perf dump`
Reviewed-by: Sage Weil <sage@redhat.com> - 05:09 PM Bug #10425: RadosClient::connect leaks Objecter if called twice
- Link to pull request: https://github.com/ceph/ceph/pull/3513
- 04:48 PM rgw Bug #10674 (Duplicate): "testAccountHead (test.functional.tests.TestAccount) ... ERROR" in upgrad...
- Run: http://pulpito.ceph.com/teuthology-2015-01-27_17:13:01-upgrade:firefly-x-next-distro-basic-multi/
Job: ['726069... - 04:43 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- Also see in run: http://pulpito.ceph.com/teuthology-2015-01-27_17:13:01-upgrade:firefly-x-next-distro-basic-multi/
J... - 04:12 PM Bug #7264: rados.py: exception catching when librados load fails hides error
- I am working on this.
- 04:07 PM rgw Bug #10665: RGW swift API: Adding custom metadata to containers using x-container-meta-name is no...
- https://github.com/ceph/ceph/pull/3561
Waiting for the review. - 09:56 AM rgw Bug #10665 (Resolved): RGW swift API: Adding custom metadata to containers using x-container-meta...
- Steps to reproduce:
1. swift post container
2. curl -i https://10.20.20.15:80/swift/v1/container -X POST -H "X-Au... - 04:02 PM Stable releases Tasks #10639: release firefly v0.80.8
- display cherry picked commits as a detail of each commit, display issues discovered thru cherry picked commits
- 01:39 PM Stable releases Tasks #10639 (Resolved): release firefly v0.80.8
- associate commits with the issue of the commit from which they were cherry picked
- 03:57 PM Revision 1cb10d7a (ceph): async: add same behavior when message seq mismatch with simple
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 03:45 PM Revision c2170bb9 (ceph): Merge pull request #3508 from zhouyuan/submodule_https_git
- Update git submodule to use the same https protocol
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:34 PM Revision 8d56ade9 (ceph): tests: ensure RBD integration tests exercise all features
- The RBD_FEATURES environment variables was not being exported to
the Python and C++ integration tests. This resulted... - 02:57 PM rgw Bug #10673 (Duplicate): giant s3test failures
- http://pulpito.ceph.redhat.com/teuthology-2015-01-27_02:02:01-rgw-giant-distro-basic-magna/
- 02:30 PM Bug #10671 (Rejected): rados cppool don't work if target is a ecpool
- I'm trying to copy a ec pool to another ecpool but when I try I face the error bellow:
root@ceph0001:~# rados cppo... - 01:59 PM Revision 8ed4f120 (ceph): Merge pull request #316 from ceph/wip-active-asok-10361
- mds_scrub_checks: only direct ops at the active MDS
Reviewed-by: John Spray <john.spray@redhat.com> - 01:49 PM Bug #10670: osd segfault
- After a segmentation fault, server hangs (sometimes with a kernel panic).
- 01:03 PM Bug #10670 (Rejected): osd segfault
- Hi!
I have cluster with 5 nodes. After update glibc (CVE-2015-0235), 12 hours later 2 nodes is dies. After reset, at... - 12:58 PM rgw Bug #10606: civetweb keeps receiving data after client canceled download
- I am using this gateway only for downloading, I mean e.g. the node receives 10 GB (from the ceph cluster) and only se...
- 12:50 PM rgw Bug #10669 (Can't reproduce): RGW swift API: temp url generated using x-account-meta-temp-url key...
- In swift if temp url has expired it wont allow accessing the object even if a valid auth token is passed. But ceph is...
- 12:32 PM rgw Bug #10668 (Resolved): RGW swift API: Setting x-account-meta-temp-url-key is successful but this ...
- Setting x-account-meta-temp-url-key succeeds and temp url generated using this key works but response header of HEAD ...
- 11:37 AM Revision b6d6f90a (ceph): mon/MDSMonitor: fix gid/rank/state parsing
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:45 AM rgw Bug #10667 (Resolved): Success code returned by rgw for POST request on container is 202 but swif...
- Swift response:
curl -i http://10.0.2.15:8080/v1/AUTH_b2419ea9588d49ddbd8c006b5eb199ff/container -X POST -H "X-Auth-... - 10:35 AM rgw Bug #10666 (Resolved): RGW swift API: Response header of GET request for container does not conta...
- In swift response returned by GET on container:
curl -i http://10.0.2.15:8080/v1/AUTH_b2419ea9588d49ddbd8c006b5eb199... - 10:30 AM devops Bug #10438: RPM not found
- That was correct after update
- 09:42 AM Revision 9b9a682f (ceph): msg/Pipe: set dscp as CS6 for heartbeat socket
- To prioritize the heartbeat packets in the the diffserv-aware device.
Thanks dtaht. - 09:28 AM Revision 1e236a37 (ceph): mds: don't join on thread which has not been runned.
- Fixes: #10550
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 08:59 AM rgw Feature #10664 (New): RGW swift API: Setting x-container-meta-quota-count and x-container-meta-qu...
- In swift to specify the max limits on the no of object and bytes that can be stored in a container, headers x-contain...
- 07:27 AM rgw Bug #10663 (Resolved): RGW swift API: Response header of COPY request for object does not contain...
- Steps to reproduce:
1. swift post container
2. swift upload container file1
Response returned by rgw:
3. curl... - 07:16 AM rgw Bug #10662 (Resolved): RGW swift API: Providing custom metadata header in COPY operation does not...
- Steps to reproduce:
1. swift post container
2. swift upload container file1
3. curl -i https://10.20.20.15:80/sw... - 07:14 AM rgw Bug #10636: "[ FAILED ] cls_rgw.gc_defer" in upgrade:giant-x-next-distro-basic-vps run
- The test is thrash sensitive. Note the rgw.gc_list call that took almost 5 seconds (just enough to fail the test):
<... - 06:23 AM Revision 6939e8c5 (ceph): Update git submodule to use the same https protocol
- Make more convenient for hosts with git protocol blocked
Signed-off-by: Yuan Zhou <yuan.zhou@intel.com> - 05:56 AM rgw Bug #10661 (Resolved): RGW swift API: Response header of POST request for object does not contain...
- Steps to reproduce:
1. swift post container
2. curl -i https://object.jiocloud.com:80/swift/v1/container/test -X... - 05:23 AM rgw Bug #10660 (Closed): RGW swift API:To merge earlier uploaded segments x-object-manifest header ca...
- Steps to reproduce:
Common steps:
1. dd if=/dev/zero of=test0 bs=1048576 count=1
2. dd if=/dev/zero of=test1 b... - 04:54 AM Revision ee3174db (ceph): rados: add size/min_size combinations to rados/thrash
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:13 AM rgw Feature #10647: In the last step of Multipart upload, swift API container/object/?multipart-manif...
- The link http://ceph.com/docs/master/radosgw/swift/ states that creating large object is supported.
> Create Large O... - 02:46 AM Bug #10458 (Fix Under Review): librados: original pool name cached in IoCtxImpl may be used after...
- https://github.com/ceph/ceph/pull/3507
- 02:16 AM Revision 893e5cd1 (ceph): doc: Adds man page for ceph.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
(cherry picked from commit 76da87a64ca6b3cc0ceeaf63e19a9f440d... - 02:16 AM Revision 15596ffe (ceph): doc: Adds man page for ceph under man/.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
(cherry picked from commit ffd6c7e49686f8f92ddb400ffdec625207... - 02:16 AM Revision e539971e (ceph): doc: Adds updated man page for ceph under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
(cherry picked from commit 8de9a0f437822c770600c19a9f61977745... - 01:52 AM CephFS Bug #10448 (Resolved): wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() ...
- 01:16 AM Revision 0c5e4580 (ceph): Merge pull request #3505 from ceph/wip-fuse-regress-note
- Update PendingReleaseNotes for ceph-fuse change in Giant
- 12:48 AM Revision e3938109 (ceph): librbd: make librbd cache send read op with fadvise_flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 12:48 AM Revision a23676bf (ceph): librbd: Don't do readahead for random read.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 12:32 AM Revision 8d0295cb (ceph): rgw: extend replica log api (purge-all)
- Adding a new purge-all option for the replica log api, which completely
removes a replica log object.
Signed-off-by:... - 12:25 AM Revision 6b0151c4 (ceph): utime: extend utime parsing
- Since we sometimes encode it as <sec>.<usec>, also try to parse it using
this format.
Signed-off-by: Yehuda Sadeh <y... - 12:24 AM Revision e274e109 (ceph): rgw: fix replica log indexing
- Fixes: #8251
Previously we were indexing the replica log only by bucket name, even
though we were provided with the ... - 12:15 AM Bug #10659 (Duplicate): "Caught signal (Aborted)" in upgrade:dumpling-firefly-x-giant-distro-basi...
- Run: http://pulpito.ceph.com/teuthology-2015-01-25_18:10:02-upgrade:dumpling-firefly-x-giant-distro-basic-multi
Job:... - 12:07 AM Bug #10658 (Resolved): "osd/osd_types.h: 3011: FAILED assert(rwstate.empty())" in upgrade:dumplin...
- Run: http://pulpito.ceph.com/teuthology-2015-01-25_18:10:02-upgrade:dumpling-firefly-x-giant-distro-basic-multi/
Job...
01/27/2015
- 11:28 PM CephFS Feature #10498: ObjectCacher: order wakeups when write calls block on throttling
- Let's do ordered wakeups!
- 02:43 PM CephFS Feature #10498: ObjectCacher: order wakeups when write calls block on throttling
- 11:13 PM CephFS Bug #10449 (Resolved): MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message...
- #10657 is a feature ticket for the warning.
The libceph bug reference to #5429 is being tracked in #8087 and doesn... - 11:06 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Created #10649 to track the need to overcome sessiontable size limit, to avoid overloading this ticket.
I agree th... - 04:50 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- it's a kernel bug. hang request prevents mds from trimming completed_requests in sessionmap. there is nothing to do w...
- 11:11 PM CephFS Feature #10657 (Resolved): MDS: warn when clients are not advancing their oldest_client_tid
- There was a bug in the kernel client which prevented it from updating the oldest_client_tid shared with the MDS. This...
- 11:04 PM CephFS Bug #10465: Audit and fix ceph-qa-suite exec tasks
- commit:8a5f76d10bc8bf0358f5215ac2aadfb210691507 in master fixes the dd location; there were no other yaml fragments p...
- 11:00 PM Revision 8a5f76d1 (ceph): fs: move into the ceph-fuse mount before doing a test
- Fixes: #10465
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 10:44 PM CephFS Bug #10423 (In Progress): update hadoop gitbuilders
- 10:27 PM CephFS Bug #10302 (Resolved): "fsync-tester.sh: line 10: lsof: command not found"
- I actually created another ticket for this a few days ago but forgot, let's keep discussion there: #10600
- 07:28 AM CephFS Bug #10302: "fsync-tester.sh: line 10: lsof: command not found"
- This turned up in a test on next branch.
http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-24_23:04:03-fs-next-... - 10:23 PM rbd Bug #10652: "rbd: import failed: (38) Function not implemented" in multi-version-next-distro-basi...
- This would be a bug in the suite. It's using a new client (master/next) against un-upgraded osds.
- 05:29 PM rbd Bug #10652 (Resolved): "rbd: import failed: (38) Function not implemented" in multi-version-next-...
- Run: http://pulpito.ceph.com/teuthology-2015-01-25_23:20:01-multi-version-next-distro-basic-multi/
Job: ['723094']
... - 10:21 PM rbd Bug #10605 (Duplicate): "[ FAILED ] LibRBD.TestClone" test in upgrade:firefly-x-next-distro-bas...
- 10:01 PM Bug #10567: Python Ioctx should retain a reference to the cluster object
- 10:00 PM Bug #10398 (Can't reproduce): coredump in remote/vpm089/ in upgrade:dumpling-x-firefly-distro-bas...
- 09:59 PM Bug #10434 (Resolved): ceph pg dump: num_objects_misplaced is missing for pools and summary
- 09:58 PM Bug #10479 (Duplicate): Object will be treated as "not exist" if primary shard is lost or failed ...
- http://tracker.ceph.com/issues/10017
- 09:56 PM Bug #9235 (Resolved): unittest_histogram test case Histogram.Position fail
- 09:56 PM Bug #10499 (Rejected): "INFO: rcu_sched detected stalls on CPUs/tasks" in upgrade:dumpling-x-fire...
- VM noise
- 09:55 PM Bug #10439 (Resolved): 'ceph tell' should fail if daemon is not found
- 09:53 PM Bug #9971 (Duplicate): OSD crashes again after restarting due to op thread time out at writing pg...
- 09:53 PM Bug #9971: OSD crashes again after restarting due to op thread time out at writing pg dirty log
- If so, I think this is a duplicate of 10157.
- 09:53 PM Bug #10635 (Duplicate): "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:giant-x-next-distro-basi...
- 09:52 PM Bug #10601 (Duplicate): thrashosd shutdown: No JSON object could be decoded
- #10630
- 09:51 PM Bug #10349 (Resolved): crushtool --show-choose-tries is a noop for indep rules
- 09:50 PM Bug #10607 (Won't Fix): Test failure on RHEL6 - OSDCap.ParseGood
- i think this is a bug in the older version of boost::spirit ...
- 09:49 PM Bug #10216 (Resolved): gf-complete and jerasure call exit(1)
- 09:49 PM Bug #10609 (Duplicate): "os/FileJournal.cc: 1693: FAILED assert(0)" v0.80.8 in upgrade:firefly-fi...
- 09:49 PM Bug #10531 (Rejected): "exception from mon" in upgrade:giant-x-next-distro-basic-vps run
- i think these are all memory. we need to reduce the vps count per machine i think :(
- 09:46 PM Feature #10559: add a norebalance flag
- This seems about right to me!
- 04:08 PM Feature #10559: add a norebalance flag
- so we are going to add an osdmap flag named "norebalance" which acts quite like the "nobackfill", while the "nobackfi...
- 09:45 PM Bug #10618 (Rejected): Unable to inject single boolean config
- --foo=false works, --no-foo works, --foo false does not. it's confusing, i know.
- 09:42 PM Bug #10611 (Resolved): "[ FAILED ] LibRadosMisc" tests failed in upgrade:giant-x-next-distro-ba...
- it was the rbd feature thing, fixe dnow
- 09:39 PM Bug #10004: ceph osd find does not correctly report crush locations
- I see that current master reports the full location for a test cluster, as does firefly, but I don't have a dual-bran...
- 09:39 PM Bug #10115 (Can't reproduce): mon not running. osd is dead
- 09:38 PM Bug #9485 (Resolved): Monitor crash due to wrong crush rule set
- 09:37 PM Bug #9285 (Resolved): osd: promoted object can get evicted before promotion completes
- 09:34 PM Bug #10468: osd crashed at OpRequest::_dump_op_descriptor_unlocked
- maybe releated to #10631
- 09:31 PM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- pid_max and the open files ulimit are the two limits to watch out for, yep!
- 09:31 PM Bug #10554 (Resolved): init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure cod...
- 09:26 PM Bug #7986 (Can't reproduce): 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2...
- 09:23 PM Bug #10211 (Pending Backport): gf-complete exit(1) because of misaligned structure
- 09:22 PM Bug #10018 (Pending Backport): OSD assertion failure if the hinfo_key xattr is not there (corrupt...
- 09:22 PM Bug #10171 (Resolved): DBObjectMap: ghobject_t header key excludes hash for EC pools
- 09:21 PM Bug #10325 (Pending Backport): Erasure coding's cauchy parameter "w" in CEPH giant is incompatibl...
- 09:19 PM Bug #10356 (Rejected): new optracker requests show up with bad age
- i think it was stuck for that long (~13 hrs) and just hadn't reached the optracker
- 09:17 PM Bug #10399 (Need More Info): kvm die with assert(m_seed < old_pg_num)
- what version are you running now, and have you seen this since? this version was a random development version shortl...
- 09:14 PM Bug #10473 (Rejected): mon: not discarding messages from disconnected clients (firefly)
- i misread the log
- 09:11 PM Bug #10512 (Pending Backport): osd: cancel_flush requeues blocked events after blocking event
- 09:11 PM Bug #10512 (Resolved): osd: cancel_flush requeues blocked events after blocking event
- 09:06 PM Bug #10017 (Resolved): OSD wrongly marks object as unfound if only the primary is corrupted for E...
- 09:04 PM Bug #10617 (Pending Backport): osd: pgs for deleted pools don't finish getting removed if osd res...
- 09:04 PM Revision a3eedc2a (ceph): Merge pull request #3480 from liewegas/wip-10617
- osd: continue interrupted pg deletion on pool removal (bug 10617)
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:58 PM Revision 8b22bf6c (ceph): Merge pull request #3454 from hjwsm1989/optracker-op-wq
- use shardid as a key of the shardinfo when "dump_op_pq_state".
Reviewed-by: Sage Weil <sage@redhat.com> - 08:57 PM Revision 533b4589 (ceph): Merge pull request #3430 from majianpeng/misc
- Misc
Reviewed-by: Sage Weil <sage@redhat.com> - 08:57 PM Revision 61cecdbc (ceph): Merge pull request #312 from ceph/wip-prio-hb-pkts
- exercise osd heartbeat prioritization
- 08:56 PM Revision a76f5ce0 (ceph): Merge pull request #296 from majianpeng/master
- rados.py: Add write_fadvise_dontneed field
- 08:56 PM Revision 74e584b2 (ceph): Merge pull request #3311 from xinxinsh/fix1
- disable tcmalloc by default when enable jemalloc
Reviewed-by: Sage Weil <sage@redhat.com> - 08:55 PM Feature #10555 (Resolved): Don't allow empty pool names
- 08:55 PM Revision 496a37e6 (ceph): Merge pull request #3394 from ceph/wip-10555
- mon: Do not allow empty pool names when creating
Reviewed-by: Sage Weil <sage@redhat.com> - 08:55 PM Revision 0be7925a (ceph): Update PendingReleaseNotes for ceph-fuse change in Giant
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 08:54 PM Revision 4d3c7ecc (ceph): Merge pull request #3444 from ceph/wip-mon-pgtemp
- osd: OSDMap: remove pg temps for inexistent pools
Reviewed-by: Sage Weil <sage@redhat.com> - 08:54 PM Revision f1c9b24f (ceph): Merge pull request #3465 from liewegas/wip-mon-features
- mon/OSDMonitor: validate crush features for osd (not just mon)
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 08:54 PM Revision 597c18ad (ceph): Merge pull request #3475 from tchaikov/osdmap-remove-unused-variables
- osd/OSDMap: remove unused variables
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Sage Weil <sage@red... - 08:53 PM Revision dba0abbd (ceph): Merge pull request #3477 from liewegas/wip-noreuse
- librados: add NOREUSE fadvise hint
Reviewed-by: Jianpeng Ma <jianpeng.ma@intel.com> - 08:46 PM Revision 50647876 (ceph): Merge pull request #3504 from ceph/wip-10553
- rgw: fix partial GET in swift
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:26 PM Revision 4c22dac3 (ceph): Merge pull request #302 from ceph/wip-crush-tunables
- ceph: set crush tunables
- 07:25 PM Revision c4fea8c8 (ceph): rados: exercise a few different crush tunable profiles
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:20 PM CephFS Bug #10361 (Fix Under Review): teuthology: only direct admin socket commands to active MDS
- https://github.com/ceph/ceph-qa-suite/pull/316
Passed a local test, just running the scrub task against a cluster. - 06:42 PM CephFS Bug #10361 (In Progress): teuthology: only direct admin socket commands to active MDS
- Testing a quick fix.
- 07:17 PM Revision 8d2715eb (ceph): mds_scrub_checks: only direct ops at the active MDS
- Change the config option from mds_id to mds_rank to reflect the
fact that it's the rank we want to make use of (and w... - 07:14 PM Bug #10654 (Can't reproduce): osd: balance_reads hits osd/ReplicatedPG.cc: 398: FAILED assert(nee...
- ...
- 07:11 PM devops Bug #10266 (Resolved): Can't kill runs on magan002 "AuthenticationException: Authentication failed."
- I believe this was an old issue from when the lab was first setup which I resolved shortly after this was opened.
- 06:57 PM rgw Bug #9576 (Pending Backport): rgw: update object content-length doesn't work correctly
- 06:55 PM rgw Bug #6801 (Rejected): RGW on arm: 'saw valgrind issues'
- 06:55 PM rgw Bug #8411 (Can't reproduce): "Segmentation fault" in radosgw in upgrade:dumpling-dumpling-testing...
- 06:55 PM Bug #10629: osd/PG.cc: 2775: FAILED assert(values.size() == 2)
- Interesting that both leveldb stores are empty in the 2 data directories. As far as we knew osd.2 should not have al...
- 03:24 AM Bug #10629: osd/PG.cc: 2775: FAILED assert(values.size() == 2)
I can't use the tool to operate on the extracted tars because they are incomplete (no journal nor superblock, for e...- 06:53 PM rgw Bug #10195 (Closed): s3 java jdk conn.getobject(...) (get s3 object) method fails with latest ver...
- see the feature ticket #10333
- 06:52 PM rgw Bug #10303 (Can't reproduce): "..s3.test_list_multipart_upload ... FAIL" in upgrade:firefly:newer...
- 06:50 PM rgw Bug #10445 (Fix Under Review): Radosgw hang, corrupt manifest?
- 06:48 PM rgw Bug #8059 (Resolved): ACL updated in master zone not updating in slave
- 06:47 PM rgw Bug #8991 (Resolved): rgw: RGWRados::list_bi_log_entries() doesn't clear list
- 06:45 PM rgw Bug #10177 (Can't reproduce): test_multipart_upload failed in upgrade:dumpling-firefly-x:parallel...
- 06:42 PM rgw Bug #10475 (Fix Under Review): rgw: setting bucket metadata via swift api removes existing metadata
- 10:45 AM rgw Bug #10475: rgw: setting bucket metadata via swift api removes existing metadata
- Now waiting for the review.
https://github.com/ceph/ceph/pull/3561 - 06:42 PM rgw Bug #10606 (Need More Info): civetweb keeps receiving data after client canceled download
- 04:39 PM rgw Bug #10606: civetweb keeps receiving data after client canceled download
- What do you mean huge rx vs tx? Much more reads than writes?
- 06:38 PM rgw Bug #10553: rgw: fail to download object in swift when range specified > 512k
- pull request #3504,
- 06:37 PM rgw Bug #10219 (Resolved): s3-tests failing to clone
- 06:23 PM Revision fc896760 (ceph): Merge pull request #3471 from yuandong1222/rgw-format-mtime
- rgw: format mtime of radosgw-admin bucket stats
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:17 PM Bug #10634: watch-notify-same-primary.yaml failure
- http://qa-proxy.ceph.com/teuthology/samuelj-2015-01-23_06:57:45-rados-master-wip-testing-vanilla-fixes-basic-multi/71...
- 06:17 PM Bug #10634: watch-notify-same-primary.yaml failure
- ...
- 05:55 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- Hmm, just looking at the man page for open() aren't you supposed to perform an open on a symlink with O_NOFOLLOW if y...
- 01:56 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- I have added support for O_NOFOLLOW in Client::open and extended unittest as well. It works for me. Patch in attachme...
- 05:49 PM Bug #10012: Configuration parameters not picked up outside of the [global] section.
- This is continuing to cause trouble for users in various ways. Here's a report of a value in [global] not impacting t...
- 05:40 PM CephFS Bug #10382 (Resolved): mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- Thanks!
- 05:15 PM CephFS Bug #10382: mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- https://github.com/ceph/ceph/pull/3502
- 02:54 PM CephFS Bug #10382 (Pending Backport): mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- Can you prepare a backport branch please?
- 05:40 PM Revision e045ad4a (ceph): Merge pull request #3502 from ceph/wip-10382-giant
- [giant backport] mds: handle heartbeat_reset during shutdown
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:37 PM Revision 333b4445 (ceph): Merge remote-tracking branch 'origin/next'
- 05:14 PM Revision 9f865fae (ceph): mds: handle heartbeat_reset during shutdown
- Because any thread might grab mds_lock and call heartbeat_reset
immediately after a call to suicide() completes, this... - 04:55 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Also, I'm using Apache + FastCGI... exclude a possible issue with civetweb.
- 04:35 PM Bug #9384: OSD is crashing while io is running and querying withadmin socket
- Any idea which release this fix will be incorporated in, now that the state says "resolved"? We currently had to disa...
- 04:35 PM rgw Feature #10647: In the last step of Multipart upload, swift API container/object/?multipart-manif...
- This is swift SLO, which we don't support at the moment.
- 10:13 AM rgw Feature #10647 (New): In the last step of Multipart upload, swift API container/object/?multipart...
- Steps to reproduce:
1. dd if=/dev/zero of=test0 bs=1048576 count=1
2. dd if=/dev/zero of=test1 bs=1048576 count... - 04:35 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- happened again, i believe with the latest fix applied.
ubuntu@teuthology:/a/teuthology-2015-01-25_23:10:02-knfs-ne... - 04:30 PM Stable releases Tasks #10560: dumpling v0.67.12
- re-schedule rados, rgw, rbd runs
- 04:09 PM Stable releases Tasks #10560: dumpling v0.67.12
- killed because incorrectly selected teuthology dumpling branch
- 04:24 PM Revision 77bd883b (ceph): test_msgr: add auth enabled basic test
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:01 PM Revision 408db651 (ceph): async_msgr: crc configuration in messenger
- Add new header_crc and data_crc configuration booleans, and use
them consistently to govern whether CRC is performed ... - 03:12 PM Revision ce941f6c (ceph): async: Delete authorizer when connected
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:12 PM Revision af266c02 (ceph): Merge pull request #3497 from trociny/test-10439
- tests: bring back useful test 'ceph tell osd.foo'
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:49 PM rgw Bug #10645: using x-fresh-metadata=true in object copying using swift API copies custom metadata ...
- x-fresh-metadata is not documented in the links you provided but a little description about it is given in https://wi...
- 11:59 AM rgw Bug #10645: using x-fresh-metadata=true in object copying using swift API copies custom metadata ...
- Could you please provide a link where this particular header x-fresh-metadata is documented?
I cannot find it here h... - 08:03 AM rgw Bug #10645 (Resolved): using x-fresh-metadata=true in object copying using swift API copies custo...
- If x-fresh-metadata=true header is passed in object copying operation then the new object created should not contain ...
- 11:17 AM Revision a8e25797 (ceph): common: filtering in `perf dump`
- So that we can get out a particular subsystem
or particular counter without dumping
everything. Should make tests th... - 11:10 AM Revision e98b5a9a (ceph): Move the sched_scrub to a new tick timer which does not need to hold th...
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
- 11:05 AM rgw Bug #10650 (Resolved): Response header of swift API PUT /container/object returned by RGW does no...
- Steps to reproduce:
1. swift post container
2. curl -i https://object.jiocloud.com:80/swift/v1/container/file1 -X... - 11:04 AM CephFS Feature #10649 (Resolved): Store MDS tables without size limit
- Created from #10449
Currently MDS tables are written as single objects, in a single writefull, implicitly limited ... - 10:48 AM rgw Feature #10648 (New): content-type for object is not getting updated either during object create ...
- Steps to rerpoduce:
1. swift post container
2. curl -i https://object.jiocloud.com:80/swift/v1/container/file1 -X... - 09:38 AM rgw Feature #10646 (New): x-timestamp and x-trans-id metadata for object are not returned by RGW.
- Body Response of Head operation on object does not contain x-timestamp and x-trans-id header returned by RGW.
Steps ... - 08:51 AM Revision e5ddc502 (ceph): tests: bring back useful test 'ceph tell osd.foo'
- The test was removed in 1189138 (mon: make ceph tell mon.* version
work) as it began to fail due to #10439. After it ... - 08:33 AM Revision 5b8d47c3 (ceph): PG looking-up/checking does not need to hold the osd_lock since it is b...
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
- 07:33 AM Revision 7c59bc0a (ceph): cleanup: replace some length() with !empty()
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 07:17 AM Revision 17add067 (ceph): cleanup: replace some size() with !empty()
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 06:34 AM Revision 5a654e32 (ceph): Merge pull request #2563 from ceph/wip-7467
- rgw: support multiple host names
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:39 AM rbd Bug #10644 (Fix Under Review): librbd: segfault on image close when watch fails
- https://github.com/ceph/ceph/pull/3494
- 01:18 AM rbd Bug #10644 (Resolved): librbd: segfault on image close when watch fails
- From http://qa-proxy.ceph.com/teuthology/sage-2015-01-24_15:03:19-rbd-next-distro-basic-multi/721344/
This can hap... - 12:09 AM Revision 69575263 (ceph): Merge pull request #315 from ceph/wip-10577
- Added "branch: dumpling" to fix #10577
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:00 AM Revision d261e324 (ceph): Added "branch: dumpling" to fix #10577
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
01/26/2015
- 11:06 PM Bug #10643 (Resolved): "FAILED assert(other->is_writeable())" in upgrade:giant-x-next-distro-basi...
- Run: http://pulpito.ceph.com/teuthology-2015-01-24_17:05:02-upgrade:giant-x-next-distro-basic-vps/
Jobs: ['721645', ... - 09:42 PM Revision 9e9d7c91 (ceph): ceph: set crush tunables
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:14 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- I'm facing with the same issue and I realised when I restart the radosgw the gc became clean but the __shadow__ objec...
- 08:51 PM Stable releases Tasks #10642 (Resolved): emperor end of life
- Although Emperor end of life has passed, there still are issues marked to be backported to emperor. They should be re...
- 08:42 PM Stable releases Tasks #10641 (Resolved): release firefly v0.80.9
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 08:12 PM Stable releases Tasks #10501: giant v0.87.1
- update the inventory
- 07:50 PM Revision d5cb91e5 (ceph): Merge pull request #3492 from ceph/wip-gmock
- tests: add Google C++ Mocking Framework
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:26 PM Revision 695f6c22 (ceph): Merge pull request #314 from ceph/wip-wait-for-failure
- ceph: test pg removal interruption; add ceph daemon failur einjection support
- 07:09 PM rbd Bug #10637 (Resolved): librbd: async resize down can deadlock (at least with stub librados)
- commit:5301b2b7057a49eb336dbe2ab3e49f4d5bbdc0a9
- 05:58 PM rbd Bug #10637 (Fix Under Review): librbd: async resize down can deadlock (at least with stub librados)
- 08:23 AM rbd Bug #10637 (Resolved): librbd: async resize down can deadlock (at least with stub librados)
- This seems to be from a callback from a finisher waiting on another callback from an operation it runs, which ends up...
- 07:07 PM Revision 9408d0f7 (ceph): Merge pull request #3493 from ceph/wip-10637
- librbd: trim header update not using AIO
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:59 PM rbd Subtask #4092 (Resolved): rbd: re-read header when watch is re-established
- 05:43 PM Revision e6256968 (ceph): Merge pull request #3388 from dachary/wip-make-check
- tests: centos7 needs nc to run make check
- 05:34 PM Stable releases Tasks #10560: dumpling v0.67.12
- update with the latest backport work
- 03:15 PM Stable releases Tasks #10560: dumpling v0.67.12
- properly indent issues that need backporting
- 02:30 PM Stable releases Tasks #10560: dumpling v0.67.12
- schedule rgw suite against dumpling-backports
- 02:27 PM Stable releases Tasks #10560: dumpling v0.67.12
- inventory of issues waiting for a dumpling backport
- 01:34 PM Stable releases Tasks #10560: dumpling v0.67.12
- Add tests analysis tracking
- 01:11 AM Stable releases Tasks #10560: dumpling v0.67.12
- Add issues to each merge requests
- 12:56 AM Stable releases Tasks #10560: dumpling v0.67.12
- Dig deeper to link isolated commits to the matching issue
- 05:24 PM Revision b36b5c9e (ceph): Merge pull request #3345 from dachary/wip-install-epel
- tests: better EPEL installation method
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 05:22 PM Revision 9a9670c2 (ceph): tests: better EPEL installation method
- It does not depend on a specific version of the EPEL release package.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 04:45 PM Bug #9987 (Resolved): mon: min_last_epoch_complete tracking broken
- min_last_epoch_complete was introduced by commit:208959a0dcacba40116730702021090a24865eb3 in v0.79, after dumpling: n...
- 04:44 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- Hmm, I don't remember where this came from but it might have been somebody cross-compiling for OS X. As marked, it's ...
- 03:42 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- O_SYMLINK sounds like BSD extension to me. We really want it?
Anyway, the Client::open() lacks support for O_NOFOLLO... - 04:41 PM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Is this in the kernel tree, and is there something we should do on the server side as well?
- 09:08 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- I had our cluster running under full load for some days and the bug still did not appear.
- 03:57 PM Revision 3916c835 (ceph): JounralingObjectStore: journal->committed_thru after replay
- It's possible that the osd stopped between when the filestore
op_seq file was updated and when the journal was trimme... - 03:51 PM Bug #9806: Objecter: resend linger ops on split
- The commit:cb9262abd7fd5f0a9f583bd34e4c425a049e56ce does not apply cleanly on dumpling which suggests more should be ...
- 02:34 PM Stable releases Tasks #10640 (Resolved): inventory of suites to run for validation
- h3. Integration suites
rados
rgw
rbd
fs
h3. QE suites
h4. dumpling
rados
rbd
rgw
fs
ceph-deploy
u... - 02:34 PM Stable releases Tasks #10639 (Resolved): release firefly v0.80.8
- ** isolated commit commit:69eaad7f8308f21573c604f121956e64679a52a7 0.80.8
** isolated commit commit:852d7b5b3c019c02... - 12:29 PM Bug #10618: Unable to inject single boolean config
- What cluster configuration do you have? I tried it on default configuration, first and second command works correctly...
- 11:44 AM Documentation #5834: Change Availability text in all of the man pages
- https://github.com/ceph/ceph/pull/3455
- 11:44 AM Documentation #5834: Change Availability text in all of the man pages
- Should be closed now.
- 11:42 AM Revision 17988032 (ceph): Merge pull request #3455 from bveuille/wip-documentation
- doc: Change Availability text in all of the man pages
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:09 AM Revision bf05ec18 (ceph): tests: replace existing gtest 1.5.0 with gmock/gtest 1.7.0
- Google Testing Framework is included by default within the Google
C++ Mocking Framework. Update makefiles to use new... - 03:15 AM Revision 5301b2b7 (ceph): librbd: trim header update not using AIO
- The original trim header update code was using blocking IO to
update the header. After migrating to an asynchronous ... - 02:01 AM Revision 83d15403 (ceph): bufferlist: add more test case for bufferlist::get_contiguous.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:01 AM Revision b14e7d35 (ceph): bufferlist: Refactor func get_contiguous.
- Now it can rebuild the related prt not all prt
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 01:49 AM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Daniel Schneller wrote:
> We got hit by this issue heavily last week on a production cluster where all the OSDs cras... - 01:47 AM Revision 8d29a4a2 (ceph): osd: handle no-op write with snapshot case
- If we have a transaction that does something to the object but it !exists
both before and after, we will continue thr... - 01:38 AM Bug #10634: watch-notify-same-primary.yaml failure
- see ceph-qa-suite.git wip-wn branch. this doesn't quite work (i think readline() doesn't block and wait for the line...
- 01:06 AM Revision 5cbe0c57 (ceph): gmock: use Google C++ Mocking Framework for unit tests
- The 'src/gmock' directory is extracted from the 1.7.0
release located at https://code.google.com/p/googlemock/
gmock...
01/25/2015
- 11:46 PM Stable releases Tasks #10560: dumpling v0.67.12
- Find pull requests for some isolated commits
- 10:23 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- We got hit by this issue heavily last week on a production cluster where all the OSDs crashed over and over with this...
- 09:16 PM rgw Bug #10445: Radosgw hang, corrupt manifest?
- I'm not sure. Last time it happened, I had ~15 multipart uploads I couldn't cancel. Once this starts happening, it ta...
- 08:55 PM Revision c602a854 (ceph): Merge pull request #3486 from ceph/wip-librbd-trim-error
- librbd: trim would not complete if exclusive lock is lost
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:59 PM Revision e1aecdf8 (ceph): Merge pull request #3487 from ceph/wip-install-deps
- install-deps: fix LC_ALL setting
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:45 PM Revision ca1d21e3 (ceph): install-deps: fix LC_ALL setting
- On my box LC_ALL=C# includes the '#' in the value without
a space between C and '#' and things go completely bonkers.... - 07:12 AM Revision e4a97c60 (ceph): librados_test_stub: add IoCtx::get_instance_id()
- This fixes make check
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 07:10 AM Revision f6406c99 (ceph): qa: small improvements to merge-diff test
- * Use set -e to detect errors
* no need to retry cleanup in a loop now that rbd-fuse closes images
* use --no-progres... - 04:55 AM Bug #8942 (Resolved): Bad JSON output in ceph osd tree
- yeah looks ok now:...
01/24/2015
- 11:53 PM rgw Bug #10636 (Won't Fix): "[ FAILED ] cls_rgw.gc_defer" in upgrade:giant-x-next-distro-basic-vps run
- Run: http://pulpito.ceph.com/teuthology-2015-01-23_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Job: ['719897']
... - 11:51 PM Bug #10635 (Duplicate): "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:giant-x-next-distro-basi...
- Run: http://pulpito.ceph.com/teuthology-2015-01-23_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Job: ['719919']
... - 11:39 PM Revision 75bdfecd (ceph): librados: fix typo in docs
- There is no rados_destroy(), only rados_ioctx_destroy().
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 11:39 PM Revision 4e884144 (ceph): rbd-fuse: clean up when shutdown
- Close all open images and librados state. This cleans up watches so we
don't need to wait for them to timeout in test... - 11:37 PM Revision f3bdd385 (ceph): Merge branch 'wip-8902'
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
- 11:05 PM Revision dfa96c58 (ceph): librbd: Add maintenance operation requests to ImageWatcher
- Snapshot, flatten, and resize maintenance operations can now
be coordinated via the client holding the exclusive lock... - 11:05 PM Revision 376c7e0f (ceph): librbd: Coordinate maintenance through exclusive lock leader
- When the exclusive lock feature is enabled, only a single client can
modify the image. As a result, certain maintena... - 11:05 PM Revision 71e84e04 (ceph): cls_lock: New assert_locked operation
- The assert_locked operation can be combined with other
RADOS ops to prevent an update to a locked object when
the cli... - 11:05 PM Revision 1b6467b7 (ceph): librbd: assert header lock ownership for maint operations
- The resize, flatten, and snapshot maintenance operations now
use the new assert_lock feature to ensure that the curre... - 11:05 PM Revision cd9d8eb7 (ceph): librbd: add more robust retry handling to maintenance ops
- When image locking is enabled, snapshot create, resize, and
flatten are coordinated with the lock owner. Previously,... - 11:05 PM Revision 4ac3cd72 (ceph): librbd: throttle async progress callbacks
- Ensure that no more than one outstanding progress callback
is queued for notification. This will allow remote progre... - 11:03 PM Revision 398bc964 (ceph): librbd: Create async versions of long-running maintenance operations
- Resize and flatten now have async versions. The existing resize
and flatten operations now use the async versions int... - 11:03 PM Revision e6f12805 (ceph): librados: Expose RadosClient instance id through librados
- Allow librados clients to utilize the global id of the RadosClient.
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 08:21 PM Bug #10634 (Resolved): watch-notify-same-primary.yaml failure
- ubuntu@teuthology:/a/samuelj-2015-01-23_06:57:45-rados-master-wip-testing-vanilla-fixes-basic-multi/719763
- 08:19 PM Bug #10633 (Resolved): osd: assert in lock in C_CopyFrom
- ...
- 06:45 PM Bug #10632 (Duplicate): ceph-objectstore-tool: crash in FileJournal.cc
- ...
- 06:43 PM Bug #10631 (Can't reproduce): osd: crash in TrackedOp::dump()
- ...
- 06:40 PM Bug #10630 (Resolved): failed to decode json output from thrashosds
- ubuntu@teuthology:/a/samuelj-2015-01-23_06:57:45-rados-master-wip-testing-vanilla-fixes-basic-multi/719316...
- 06:28 PM Bug #10629 (Duplicate): osd/PG.cc: 2775: FAILED assert(values.size() == 2)
- ...
- 08:33 AM Revision 87ef4620 (ceph): rgw: format mtime of radosgw-admin bucket stats
- use formatter.dump_stream to format mtime
Change-Id: Ib1747b5389e29a4c5ab0499fcdb8cbaa926ae30c
Signed-off-by: Dong Y... - 07:51 AM Revision 48910a52 (ceph): Merge pull request #3479 from ceph/wip-librbd-close-deadlock
- librbd: potential deadlock on close_image
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:28 AM Revision dc1630e9 (ceph): librbd: trim would not complete if exclusive lock is lost
- The trim completion context was not properly invoked if the
image's exclusive lock was lost between issuing a librado... - 07:01 AM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- This issue is resolved after increasing the open file limit and maximum no of threads
config reference
/etc/sec... - 06:42 AM Revision f6145a38 (ceph): suites/rbd: Add rbd api tests with exclusive locking features
- Keep testing the old, non-default features in a renamed yaml file.
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 06:42 AM Revision 87478973 (ceph): suites/rbd: split qemu and librbd tests
- qemu tests take a long time. We'll want to test more combinations of
options with librbd directly.
Signed-off-by: Jo... - 06:42 AM Revision f2224b9a (ceph): suites/rbd: add copy-on-read tests
- Add as a facet of librbd tests, since they all use cloning, and to a
couple tests with thrashing.
Signed-off-by: Jos... - 01:10 AM Revision 7e5619dc (ceph): Merge pull request #303 from ceph/wip-10388
- tasks/mds_flush: use new stray/purge perfcounters
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:43 AM Bug #10596 (Resolved): error when building ceph on ubuntu 14
- 12:41 AM Revision 53836948 (ceph): Merge pull request #3466 from delco225/master
- installation error on ubuntu 14 corrected
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:35 AM Revision 3347e0da (ceph): bug: error when installing ceph dependencies with install-deps.sh
- The parsing is sensitive to i18n and will fail if, for instance, it is set to French.
Workaround the problem by alway... - 12:30 AM rbd Feature #4088 (Resolved): rbd: optionally copy-on-read instead of copy-on-write
- Implemented in several commits ending with commit:b304af344ec727f71b353dd200fc0970560c12be
- 12:08 AM Revision 4e90a310 (ceph): osd: add failure injection on pg removals
- Trigger a failure before final PG removal so we can test that the OSD will
complete interrupted PG removal.
Signed-o...
01/23/2015
- 11:50 PM Bug #10617 (Fix Under Review): osd: pgs for deleted pools don't finish getting removed if osd res...
- 05:56 PM Bug #10617 (In Progress): osd: pgs for deleted pools don't finish getting removed if osd restarts
- 05:38 PM Bug #10617 (Resolved): osd: pgs for deleted pools don't finish getting removed if osd restarts
- ubuntu@teuthology:/a/sage-2015-01-23_06:28:59-rados:thrash-wip-txn-noappend-distro-basic-multi/718890
load_pgs ign... - 11:43 PM Revision 3e540b2f (ceph): rados/singleton: test interrupted pg removal
- Inject osd failure during pg removal. Verify the OSD successfully
recovers.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:27 PM CephFS Bug #10620: TestFlush fails on formatting mistake
- ceph-qa-suite commit:41a99f58ccbbc09ee7b5355e598c426cef1d8775
- 09:22 PM CephFS Bug #10620 (Resolved): TestFlush fails on formatting mistake
- ...
- 11:24 PM Revision 41a99f58 (ceph): mds_flush: fix the flush test output expectations
- Fixes: #10620
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 11:21 PM Revision cb74060c (ceph): ceph: no need to stop() before restart()
- restart() will stop if the daemon is running. This will get rid of the
spurious error
2015-01-23 15:19:36,828.828 E... - 11:20 PM Revision 83dd3d58 (ceph): ceph: add wait_for_failure command
- Expect and then ignore a daemon failure.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:09 PM devops Subtask #10628: Set up samba gitbuilders for RHEL/CentOS
- And if possible I imagine people would prefer we squash these samba builders into the same resource domain if possibl...
- 11:02 PM devops Subtask #10628 (Rejected): Set up samba gitbuilders for RHEL/CentOS
- Right now we're building Samba for precise and trusty. We also want to build it for whatever else we have running in ...
- 11:04 PM CephFS Feature #10627: teuthology: qa: enable Samba runs on RHEL
- Apparently Fedora *just* enabled the Ceph VFS and RHEL doesn't, so not until we push on those.
And even then we'll... - 10:48 PM CephFS Feature #10627: teuthology: qa: enable Samba runs on RHEL
- i wonder if we can run upstream samba now?
- 10:43 PM CephFS Feature #10627 (New): teuthology: qa: enable Samba runs on RHEL
- We need a gitbuilder and some teuthology installation changes. We can get other people to make those, but this umbrel...
- 10:50 PM Revision ea07aed8 (ceph): samba: run only on ubuntu until #10627 is resolved
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 1dcff968a4fc359086723e8a3cb941051297f14a) - 10:50 PM Revision c234887f (ceph): samba: run only on ubuntu until #10627 is resolved
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 1dcff968a4fc359086723e8a3cb941051297f14a) - 10:49 PM Revision 1dcff968 (ceph): samba: run only on ubuntu until #10627 is resolved
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 10:14 PM Revision 12553812 (ceph): Merge pull request #3482 from ktdreyer/wip-rpm-glob-man-pages
- ceph.spec.in: use wildcards to capture man pages
- 10:08 PM Revision 9b220bdd (ceph): ceph.spec.in: use wildcards to capture man pages
- Use wildcard to capture gzipped man pages for ceph-clsinfo(8) and
librados-config(8). In addition to future-proofing ... - 10:05 PM CephFS Bug #10624 (Resolved): hung samba tests after lsof failure
- http://pulpito.ceph.com/teuthology-2015-01-21_23:14:02-samba-master-testing-basic-multi/717177/, and in one other rec...
- 09:54 PM CephFS Bug #9994: ceph-qa-suite: nfs mount timeouts
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-21_23:10:01-knfs-master-testing-basic-multi/717164/
Ubuntu ... - 09:44 PM Revision 96bc1f49 (ceph): Merge pull request #3040 from cchengleo/wip-copy-on-read
- RBD copy on read
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:33 PM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- It looks like both issues are related to resource starvation. Could it be that the maximum number of process / thread...
- 01:28 AM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- See same issue in v0.80.8.
Run: http://pulpito.ceph.com/teuthology-2015-01-21_19:13:02-upgrade:dumpling-x-firefly-... - 07:29 PM Revision 313d6a5a (ceph): rgw: access appropriate shard on bi_get(), bi_put()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 07:29 PM Revision 51e3ffae (ceph): rgw: reorder bucket cleanup on bucket overwrite
- First read the new instance info, then remove it, not the other way
around. Artifact of bucket sharding merge with ob... - 07:20 PM Revision b304af34 (ceph): librbd: clean up log message for copy-on-read
- Signed-off-by: Cheng Cheng <ccheng.leo@gmail.com>
- 06:55 PM Revision 879fd0c1 (ceph): osd: do not ignore deleted pgs on startup
- These need to get instantiated so that we can complete the removal process.
Fixes: #10617
Signed-off-by: Sage Weil <... - 06:09 PM rgw Bug #10475: rgw: setting bucket metadata via swift api removes existing metadata
- Implemented correct metadata merging and deletion according to:
http://docs.openstack.org/api/openstack-object-stora... - 08:13 AM rgw Bug #10475 (In Progress): rgw: setting bucket metadata via swift api removes existing metadata
- Sending new metadata to an object will erase existing ones too.
I couldn't test it, because development version has ... - 06:00 PM Revision 6f6facb9 (ceph): librbd: potential deadlock on close_image
- The owner_lock was incorrectly held when unregistering the image
watcher. It was possible for the ImageWatcher finis... - 05:47 PM Bug #10618 (Rejected): Unable to inject single boolean config
- I want to deactivate log to stderr/syslog.
I tried "ceph tell mon.a injectargs --no-log_to_stderr", it returned
... - 05:27 PM Revision e9170335 (ceph): test: add rados_nobjects_list_xyz functions to librados test stub
- The new RBD copy-on-read unit test case uses these RADOS functions
to verify that the CoR operation was successful. ... - 05:27 PM Revision bda293ad (ceph): librbd: fix copy-on-read / resize down race condition
- There was a rare race condition between a pending CoR operation
and a resize down operation resulting in a CoR copyup... - 05:27 PM Revision 7c7f072a (ceph): librbd: eliminate CoR callback
- When issuing the CoR copyup request, there is no need to keep
initialize the librados callback. Treat the CoR as a f... - 05:27 PM Revision 9790b0f9 (ceph): librbd: use finisher for copy-on-read copyup fulfillment
- When the RBD cache is enabled, the ObjectCacher does not allow
reentrancy to read the full object. As a temporary wo... - 05:12 PM devops Bug #10330: apt-mirror timeouts
- Similar in
Run: http://pulpito.ceph.com/teuthology-2015-01-22_14:00:18-upgrade:firefly-x-giant-distro-basic-vps/
Jo... - 05:08 PM devops Bug #10511: "test.functional.tests.TestAccount" fail in upgrade:firefly-x-next-distro-basic-multi...
- And same in
Run: http://pulpito.ceph.com/teuthology-2015-01-22_14:00:18-upgrade:firefly-x-giant-distro-basic-vps/
... - 04:52 PM devops Bug #10511: "test.functional.tests.TestAccount" fail in upgrade:firefly-x-next-distro-basic-multi...
- Same issue
Run: http://pulpito.ceph.com/teuthology-2015-01-22_17:13:02-upgrade:firefly-x-next-distro-basic-multi/
J... - 05:08 PM Revision cfce41d1 (ceph): ReplicatedPG::hit_set_persist: update ssc->snapset as well
- This is a hack. The correct answer is to adapt this method and
finish_ctx to allow this method to use finish_ctx. T... - 05:07 PM Revision f1f6f0bd (ceph): ReplicatedPG::hit_set_persist: write out oi.digest, these objects are i...
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 05:06 PM Revision 4dda030a (ceph): librados: add FADVISE_NOREUSE
- We left this off because it seemed the same as DONTNEED, but there is a
subtle distinction: DONTNEED means nobody wil... - 05:06 PM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same
Run: http://pulpito.ceph.com/teuthology-2015-01-22_14:00:18-upgrade:firefly-x-giant-distro-basic-vps/
Job: ['7... - 05:01 PM devops Bug #10532: Failed "joining thrashosds" - suspected low memory config on vps
- Same
Run: http://pulpito.ceph.com/teuthology-2015-01-22_14:00:18-upgrade:firefly-x-giant-distro-basic-vps/
Job:... - 04:48 PM Bug #10616: osd/ReplicatedPG.cc: 5790: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head...
- 04:48 PM Bug #10616: osd/ReplicatedPG.cc: 5790: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head...
- ubuntu@teuthology:/a/samuelj-2015-01-22_22:03:29-rados-wip-sam-working-wip-testing-vanilla-fixes-basic-multi/718600/r...
- 04:47 PM Bug #10616 (Resolved): osd/ReplicatedPG.cc: 5790: FAILED assert(ctx->new_obs.exists == ctx->new_s...
- -3> 2015-01-22 22:53:26.560136 7f621276e700 10 osd.3 514 handle_replica_op osd_repop_reply(osd.3.0:3457 2.0 ack, ...
- 04:47 PM Revision a73b8f81 (ceph): Merge pull request #3456 from ceph/wip-4092
- librbd: schedule header refresh after watch error
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:37 PM Revision 9edd0a53 (ceph): ceph.spec.in: move rgw logrotate to rgw subpackage
- Prior to this commit, the radosgw logrotate config was in the main
"ceph" package. This meant that if a user had inst... - 03:43 PM devops Tasks #10587: split ceph-mon, ceph-osd, and ceph-mds in the Debian and Red Hat packages
- In addition to the ceph-mon file list above, today I found that the @ceph-rest-api@ command-line utility should also ...
- 03:26 PM Revision 050a59ec (ceph): osd/OSDMap: remove unused variables
- Signed-off-by: Kefu Chai <tchaikov@gmail.com>
- 03:19 PM Revision 55dfe032 (ceph): librbd: schedule header refresh after watch error
- If a librados watch error occurs, it is possible that one
or more events were missed. Therefore, flag the header as
... - 02:20 PM Revision b782030e (ceph): Merge pull request #3472 from armaseg/master
- doc: Some files still use http://ceph.newdream.net
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:32 PM Bug #10458: librados: original pool name cached in IoCtxImpl may be used after pool is renamed
- Initial proposal of the patch in attachment.
- 11:37 AM Bug #10615: Some files still use http://ceph.newdream.net
- https://github.com/ceph/ceph/pull/3472
Related: #9922 http://tracker.ceph.com/issues/9922 - 11:03 AM Bug #10615 (Resolved): Some files still use http://ceph.newdream.net
- This probably redirects to http://ceph.com but ceph.newdream.net still appears in some places:
$ grep -rnw 'ceph' ... - 11:28 AM Revision 33f0afdd (ceph): doc: Some files still use http://ceph.newdream.net
- This probably redirects to http://ceph.com but ceph.newdream.net still appears in some places
http://tracker.ceph.co... - 10:13 AM Revision 9ace238e (ceph): teuthology: some suites still use http://ceph.newdream.net
- This probably redirects to http://ceph.com but ceph.newdream.net still appears in some places
http://tracker.ceph.co... - 08:57 AM Revision 17663514 (ceph): Merge pull request #3469 from tchaikov/fix-bashism-in-ceph-debugpack
- ceph-debugpack: fix bashism of {1..10}
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:03 AM Revision 2d60db3b (ceph): Merge pull request #3449 from wonzhq/rocksdb-del
- RocksDBStore: filterpolicy is not deleted when RocksDBStore destructs
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 02:53 AM Revision 2f9b3bdc (ceph): ceph-debugpack: fix bashism of {1..10}
- * replaces {1..10} with $(seq 10)
* fixes 772220@bugs.debian.org
Signed-off-by: Kefu Chai <tchaikov@gmail.com> - 02:26 AM Revision 5652a1df (ceph): cls_rgw; fix json decoding and encoding of certain type
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 02:12 AM Revision ed709884 (ceph): bufferptr: add judgement in set_length() to make don't beyond the raw_l...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:12 AM Revision dfccd3d1 (ceph): bufferptr: Make set_offset() don't beyond the length.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:09 AM Revision f9d82e63 (ceph): test: Add --write-fadvise-dontned option to ceph_test_rados
- This test case for feature 'ceph osd pool set poolname
write_fadivse_dontneed ture|false'.
Signed-off-by: Jianpeng M... - 01:54 AM Revision 075c604f (ceph): librados: Fix error comment.
- ceph_osd_op.flags use CEPH_OSD_OP_FLAG_* rather than CEPH_OSD_FLAG_*.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.... - 01:53 AM Revision f7109847 (ceph): mon: Add "ceph osd pool set/get write_fadvise_dontnned" command
- Using set command, we can set pool write mode like with
LIBRADOS_OP_FLAG_FADVISE_DONTNEED which indicate osd backend ... - 01:32 AM Revision d26fe350 (ceph): pg_pool_t: clean up code.
- Using has_flag() insteand of get_flags() & pg_pool_t::FLAG_*
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 01:32 AM Revision 0f56b478 (ceph): ReplicatedPG: handle OSDOp with pg_pool_t::FLAG_WRITE_FADVISE_DONTNEED.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 01:31 AM Revision ec3f79d6 (ceph): osd: Add pg_pool_t FLAG_WRITE_FADVISE_DONTNEED
- This flag mean all write for this pool don't cache data in osd side
afting writing.
This mainly for situation which w... - 01:29 AM Revision 376b5854 (ceph): rgw: generate version ids that don't change when urldecoded
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 01:29 AM Revision 65f28716 (ceph): rgw: hash bucket shard by original object name, not transformed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 01:04 AM Revision a9c882f0 (ceph): ReplicatedPG: Remove the duplicated code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 12:53 AM Revision 67c46375 (ceph): ReplicatedPG: Add some mark_delay events.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 12:06 AM Revision 5548bbe1 (ceph): rgw: use bucket shard for olh operations
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
01/22/2015
- 11:51 PM Revision 026c9cb2 (ceph): Merge pull request #3467 from ktdreyer/wip-packaging-description-format...
- ceph.spec.in: standardize capitalization and punctuation
- 11:45 PM Revision fff3cf91 (ceph): ceph.spec.in: capitalization and punctuation
- Ensure that each sub-package's %description starts with a capital letter
and ends with a dot.
rpmlint has a rule tha... - 11:39 PM Bug #10596 (In Progress): error when building ceph on ubuntu 14
- 11:39 PM Bug #10596: error when building ceph on ubuntu 14
- ...
- 11:26 PM Revision e4b5bedc (ceph): rgw: api adjustments following a merge
- Merged bucket sharding and object versioning.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:17 PM Bug #10531: "exception from mon" in upgrade:giant-x-next-distro-basic-vps run
- Similar issue but with memory problem.
Run: http://pulpito.ceph.com/teuthology-2015-01-21_17:05:02-upgrade:giant-x... - 10:45 PM Revision dd3ebf38 (ceph): Merge pull request #3424 from dachary/wip-reuse-dmcrypt
- ceph-disk: do not reuse partition if encryption required
Reviewed-by: Sage Weil <sage@redhat.com> - 10:19 PM Revision b01ef218 (ceph): Merge remote-tracking branch 'origin/master' into wip-rgw-versioning-4
- Conflicts:
src/cls/rgw/cls_rgw_client.cc
src/cls/rgw/cls_rgw_client.h
src/rgw/rgw_bucket.cc
src/rgw/rgw_common.h
... - 09:56 PM Revision c71ecae7 (ceph): mon/OSDMonitor: validate crush features for osd (not just mon)
- We need to check that the OSD features are met as well.
Backport: giant, firefly
Signed-off-by: Sage Weil <sage@redh... - 09:52 PM devops Bug #10591 (Resolved): Missing packages in upgrade:dumpling-dumpling-distro-basic-magna run
- 09:29 PM rbd Bug #10614 (Resolved): fsx krbd test needs update for mandatory locking
- 09:27 PM rbd Bug #10614 (Fix Under Review): fsx krbd test needs update for mandatory locking
- 09:14 PM rbd Bug #10614 (Resolved): fsx krbd test needs update for mandatory locking
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-21_23:06:01-krbd-master-testing-basic-multi/717107/teuthology.log
- 09:28 PM Revision 9a3ac5ff (ceph): Merge pull request #3464 from ceph/wip-10614
- test/librbd/fsx.c: disable RBD exclusive locking for krbd
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:27 PM rbd Bug #10613 (Resolved): krbd test needs update for mandatory locking
- 08:59 PM rbd Bug #10613 (Fix Under Review): krbd test needs update for mandatory locking
- 08:44 PM rbd Bug #10613 (Resolved): krbd test needs update for mandatory locking
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-21_23:06:01-krbd-master-testing-basic-multi/717105/teuthology.log
- 09:25 PM Revision f31910d8 (ceph): Merge pull request #3285 from ceph/wip-10439
- pybind: ceph_argparse: validate incorrectly formed targets
Reviewed-by: Dan Mick <dan.mick@redhat.com> - 09:11 PM Revision 6a025ef3 (ceph): PGLog: trim mod_desc after appending to the log
- We'll want he callers up the chain to take the log
entry as a const ref.
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:11 PM Revision 96504033 (ceph): PG::add_log_entry: no need to 0 offset in append_log
- No longer used.
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:11 PM Revision 27dcb148 (ceph): osd/: pass log_entries in write path as const ref
- We need to use them after the submit_transaction call, so
we can't pass them by non-const ref.
Signed-off-by: Samuel... - 09:11 PM Revision cd7ed04d (ceph): osd/: s/backfill_read/recovery_read for obc locking
- We are going to expand our usage of this for normal
replica recovery.
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:11 PM Revision 46212362 (ceph): PGBackend: rename clear_state to clear_recovery_state
- This is called when we complete recovery, and does not clear
all state. clear_recovery_state is clearer.
Signed-off... - 09:05 PM Revision 448a3c33 (ceph): Merge remote-tracking branch 'origin/next'
- 09:03 PM Revision a6eadaef (ceph): rbd image_read.sh: disable exclusive locking
- Until the kernel supports RBD exclusive locking, this test
has been updated to create shared images (exclusive lockin... - 07:53 PM Bug #10536 (Resolved): _scrub and digests: osd/ReplicatedPG.cc: 7506: FAILED assert(!i->mod_desc....
- 07:53 PM Bug #10534 (Resolved): full-object read crc 0x######## != expected 0x######## on
- 07:52 PM Bug #10603 (Resolved): [ FAILED ] LibRadosMisc.CloneRange
- 12:00 AM Bug #10603: [ FAILED ] LibRadosMisc.CloneRange
- ObjectStore::_update_op doesn't update dest_oid
- 12:00 AM Bug #10603 (Resolved): [ FAILED ] LibRadosMisc.CloneRange
- 015-01-20T16:28:30.567 INFO:teuthology.orchestra.run.plana52:Running: 'adjust-ulimits ceph-coverage /home/ubuntu/ceph...
- 07:40 PM Feature #10477 (Resolved): pg query should output the replicas the primary is waiting on between ...
- 07:34 PM Revision 33a68604 (ceph): Merge pull request #3458 from liewegas/wip-vstart
- vstart.sh: pull default CEPH_PORT from .ceph_port
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:27 PM Bug #10474 (Resolved): Testing wip-9780-9781 hung ceph-objectstore-tool on import
- https://github.com/ceph/ceph/pull/3317
- 12:41 AM Bug #10474 (Fix Under Review): Testing wip-9780-9781 hung ceph-objectstore-tool on import
- 07:26 PM Revision f13cda59 (ceph): Merge pull request #3317 from ceph/wip-10474
- FileJournal: Fix hang in FileJournal::close()
Reviewed-by: Sage Weil <sage@redhat.com> - 07:19 PM Bug #10524 (Resolved): FAILED assert(peer_missing.count(fromshard))
- https://github.com/ceph/ceph/pull/3460
- 07:19 PM Revision 235d97a6 (ceph): Merge pull request #3460 from athanatos/wip-10524
- Wip 10524
Reviewed-by: Sage Weil <sage@redhat.com> - 07:15 PM Revision edd345a7 (ceph): Merge pull request #3461 from athanatos/wip-10535
- ceph_test_objectstore: enable keyvaluestore experimental option
Reviewed-by: Sage Weil <sage@redhat.com> - 07:14 PM Revision ded972ed (ceph): Merge pull request #3462 from athanatos/wip-10536
- ReplicatedPG::_scrub: don't record digests for snapdirs
Reviewed-by: Sage Weil <sage@redhat.com> - 07:12 PM Revision b5a8f802 (ceph): Merge pull request #3459 from athanatos/wip-10603
- ObjectStore::_update_op: treat CLONERANGE2 like CLONE
Reviewed-by: Sage Weil <sage@redhat.com> - 07:11 PM Bug #10517 (Resolved): ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- https://github.com/ceph/ceph/pull/3457
- 07:01 PM Bug #10517: ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- 07:11 PM Revision 387a3798 (ceph): Merge pull request #3350 from liewegas/wip-10477
- osd: populate blocked_by with peers we are trying to activate
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:11 PM Revision 2a38fb80 (ceph): Merge pull request #3457 from athanatos/wip-txn-append
- Wip txn append
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 07:10 PM Revision 1afd1c65 (ceph): Merge pull request #3351 from liewegas/wip-10512
- osd: fix blocked vs blocking rqeuest requeue order on interval change
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:10 PM Revision a4a9ec9d (ceph): Merge pull request #3363 from liewegas/wip-cache-fix
- osd: fix ReplicatedPG::cancel_proxy_read_ops()
Reviewed-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 07:09 PM rgw Bug #10475: rgw: setting bucket metadata via swift api removes existing metadata
- FWIW I filed this based on reading RGWPutMetadata::execute() during a review: https://github.com/ceph/ceph/blob/6f44f...
- 07:09 PM Revision 266cf2e5 (ceph): Merge pull request #3365 from liewegas/wip-peering
- osd: new activating pg state between peering and active
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:06 PM Revision f51ff28f (ceph): vstart.sh: pull default CEPH_PORT from .ceph_port
- This lets you put a unique port in .ceph_port in your working dir and
vstart.sh instances will avoid each other witho... - 07:01 PM Bug #10564 (Duplicate): test/multi_stress_watch.cc: 60: FAILED assert(!ret)
- #10441
- 06:58 PM Bug #10612 (Won't Fix): "[ FAILED ] LibRadosCmd.OSDCmd " in upgrade:dumpling-x-firefly-distro-b...
- debian 7.0
Run: http://pulpito.ceph.com/teuthology-2015-01-19_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps/
... - 06:54 PM Bug #10611: "[ FAILED ] LibRadosMisc" tests failed in upgrade:giant-x-next-distro-basic-multi run
- Same in run http://pulpito.ceph.com/teuthology-2015-01-20_17:13:01-upgrade:firefly-x-next-distro-basic-multi/
suite:... - 06:47 PM Bug #10611 (Resolved): "[ FAILED ] LibRadosMisc" tests failed in upgrade:giant-x-next-distro-ba...
- Run: http://pulpito.ceph.com/teuthology-2015-01-20_17:05:01-upgrade:giant-x-next-distro-basic-multi/
Jobs: ['71551... - 06:27 PM Feature #10452 (Resolved): ceph osd df
- 06:17 PM Revision 0eca13dd (ceph): crush: fix dump for hammer tunables
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:17 PM Revision 32a1ead9 (ceph): Add crush_ln to calculate nature log efficently
- Crush_ln is a function that could calculate ln(x+1) * 4096, which is exactly maps [0,0xffff]
(corresponding to real n... - 06:17 PM Revision 62899124 (ceph): crush: improve straw2 adjustment slightly
- This improves the accuracy for low weights especially...
Signed-off-by: Sage Weil <sage@redhat.com> - 06:17 PM Revision 35fcb04e (ceph): Change crush_ln to provide 32 more digits.
- 32 more digits(more precision) were given by crush_ln, so we dont
need to do left shift in bucket_straw2_choose now.... - 06:16 PM Revision 7023eabd (ceph): crush: add allowed_bucket_algs tunable
- This tunable is a bitmask indicating which bucket algorithms are allowed.
For now, the only purpose is to affect get_... - 06:16 PM Revision 325fc567 (ceph): crush: introduce CRUSH_V4 feature bit
- Introduce a feature bit that reflects whether straw2 buckets are in use.
Clients need to support them before they can... - 06:16 PM Revision 6e084f62 (ceph): unittest_crush: rename straw tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:16 PM Revision 242293c9 (ceph): crush: add a straw2 bucket type
- This is an improved straw bucket that correctly avoids any data movement
between items A and B when neither A nor B's... - 06:16 PM Revision d4ec7570 (ceph): crush: move default bucket choice into CrushWrapper helper
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:10 PM Revision 14eb1a73 (ceph): crush/builder: fix warnings
- crush/builder.c: In function 'crush_remove_list_bucket_item':
crush/builder.c:977:13: warning: comparison between sig... - 06:01 PM Cleanup #10094: Create new git repo for json_spirit
- Any news on this request?
The original code is from http://www.codeproject.com/Articles/20027/JSON-Spirit-A-C-JSON... - 05:00 PM devops Bug #10570 (Resolved): "ERROR 403: Forbidden" (v0.67.x)
- tested in sepaia and octo:
http://pulpito.front.sepia.ceph.com/teuthology-2015-01-21_11:54:26-upgrade:dumpling-dumpl... - 04:28 PM Bug #10609 (Duplicate): "os/FileJournal.cc: 1693: FAILED assert(0)" v0.80.8 in upgrade:firefly-fi...
- Run: http://pulpito.ceph.com/teuthology-2015-01-21_17:05:02-upgrade:firefly-firefly-distro-basic-multi/
Job: ['716... - 04:20 PM Revision a76641b5 (ceph): Merge pull request #3425 from vuhuong/wip-xio-fork
- xio: Enable xio option to call fork init
Reviewed-by: Matt Benjamin <matt@cohortfs.com> - 04:16 PM Revision f28ce7f4 (ceph): Merge pull request #3453 from FrankYu/master
- Doc: Fix the extra blank space in doc/start/quick-rbd.rst
- 04:15 PM Revision 8cc3e17b (ceph): Merge pull request #3451 from xiaoxichen/fix_memstore_statfs
- Fix memstore free space caculation
Reviewed-by: Sage Weil <sage@redhat.com> - 03:28 PM rbd Subtask #4092 (Fix Under Review): rbd: re-read header when watch is re-established
- 03:04 PM Revision 07eadc45 (ceph): FileJournal: Fix hang in FileJournal::close()
- On FileStore::umount() when stopping and in ENOSPC condition,
don't let write_thread_entry() get stuck in commit_cond... - 02:53 PM Revision 2865e13f (ceph): doc: Change Availability text in all of the man pages
- http://tracker.ceph.com/issues/5834 fixes:#5834
signed-off-by: Baptiste Veuillez--Mainard <baptiste.veuillez--mainard... - 02:16 PM Subtask #2741 (Resolved): mon: Single-Paxos: Sync: Assess requirements for QA tests
- 01:49 PM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- After increasing the open file limit from 1024 to 64536 on node01 , random osds wer not stopped instead they were res...
- 08:28 AM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- It seems to have create the no of threads to run the osds
2015-01-22 13:50:16.631942 7f4b5df62700 -1 common/Thread... - 07:41 AM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- +Failed osd log on node 01+
ceph version 0.87 (c51c8f9d80fa4e0168aa52685b8de40e42758578)
1: /usr/bin/ceph-osd()... - 07:18 AM Bug #10554: init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure coding cluster...
- we tried to create osd 239 on node 15 using different disk( sdq sdr sds etc...)and we got same error as reported abo...
- 01:07 PM Bug #10458: librados: original pool name cached in IoCtxImpl may be used after pool is renamed
- I am working on this bug.
- 12:58 PM Revision b04f698f (ceph): Doc: Fix the extra blank space in doc/start/quick-rbd.rst
- Signed-off-by: Frank Yu <flyxiaoyu@gmail.com>
- 11:41 AM Revision 99300289 (ceph): osd: OSDMap: remove pg temps for inexistent pools
- f513f66f48383a07c70ca18a4dba6c2449ea9860 prevented the monitor from
handling pg_temps on pools that had been removed ... - 11:35 AM Fix #10519 (In Progress): Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in c...
- 11:35 AM Fix #10519: Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph pg dump
- To reproduce this problem you can create a cluster with 2 OSDs and create an erasure coded pool using the default set...
- 11:28 AM Fix #10519: Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph pg dump
- Going to fix it.
- 10:57 AM Revision 34f5c178 (ceph): use shardid as a key of the shardinfo when "dump_op_pq_state".
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 10:27 AM Bug #10607: Test failure on RHEL6 - OSDCap.ParseGood
- $ cat /etc/redhat-release
Red Hat Enterprise Linux Server release 6.5 (Santiago) - 10:26 AM Bug #10607 (Won't Fix): Test failure on RHEL6 - OSDCap.ParseGood
- ...
- 09:42 AM CephFS Bug #10550: Assertion in ceph-mds on failures in ::init
- Proposal of the patch attached.
- 09:15 AM Revision db24cee5 (ceph): Merge pull request #3450 from zhouyuan/rgw_doc_typo
- doc: Fix a typo in radosgw-admin doc
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:19 AM Revision 804deec1 (ceph): Fix memstore free space caculation
- Originally if memstore run out of space, it will report a very
large positive number as free space. For example:
roo... - 08:13 AM Revision 62391512 (ceph): RocksDBStore: filterpolicy is not deleted when RocksDBStore destructs
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 07:43 AM rgw Bug #10606 (Can't reproduce): civetweb keeps receiving data after client canceled download
- Hi,
I am testing civetweb, I am getting huge rx with little tx, after investigating the issue, I found that civetweb... - 06:10 AM Revision 2e8bb1eb (ceph): test/librbd/fsx.c: disable RBD exclusive locking for krbd
- Until the kernel supports RBD exclusive locking, this test
has been updated to disable the new feature.
Fixes: #1061... - 05:31 AM Revision 9ad9ba8d (ceph): doc: Fix a typo in radosgw-admin doc
- Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
- 03:59 AM Feature #9781 (Resolved): ceph_objectstore_tool: On import handle splits
- 12:40 AM Feature #9781 (Fix Under Review): ceph_objectstore_tool: On import handle splits
- 03:59 AM Feature #9780 (Resolved): ceph_objectstore_tool: Add OSDMap information to pg export
- 12:40 AM Feature #9780 (Fix Under Review): ceph_objectstore_tool: Add OSDMap information to pg export
- 03:54 AM Bug #10430 (Resolved): osd/osd_types.cc: 456: FAILED assert(m_seed < old_pg_num)
- 12:41 AM Bug #10430 (Fix Under Review): osd/osd_types.cc: 456: FAILED assert(m_seed < old_pg_num)
- 03:54 AM Bug #10427 (Resolved): Generating past intervals can crash OSD because of a missing OSDMap
- 12:42 AM Bug #10427 (Fix Under Review): Generating past intervals can crash OSD because of a missing OSDMap
- 03:54 AM Bug #8121 (Resolved): ReplicatedBackend::build_push_op() should handle a short read or assert
- 12:40 AM Bug #8121 (Fix Under Review): ReplicatedBackend::build_push_op() should handle a short read or as...
- 02:16 AM Revision 008698b3 (ceph): doc: Change Availability text in all of the man pages
- http://tracker.ceph.com/issues/5834 fixes:#5834
signed-off-by: Baptiste Veuillez--Mainard <baptiste.veuillez--mainard... - 01:30 AM Revision 6f44f7a0 (ceph): Revert "Revert "Merge remote-tracking branch 'origin/wip-bi-sharding-3'...
- Following a merge of next to master, the feature got reverted (because
it was reverted on next). Undoing.
This rever... - 12:52 AM rbd Bug #10605 (Duplicate): "[ FAILED ] LibRBD.TestClone" test in upgrade:firefly-x-next-distro-bas...
- Run: http://pulpito.ceph.com/teuthology-2015-01-20_17:18:01-upgrade:firefly-x-next-distro-basic-vps/
Job: 715615
... - 12:51 AM Revision ddfbe40f (ceph): Merge pull request #277 from ceph/wip-9780-9781
- ceph-objectstore-tool import/export and related fixes
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:49 AM Revision 09c11071 (ceph): Merge pull request #3246 from ceph/wip-9780-9781
- ceph-objectstore-tool import/export and related fixes
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:45 AM Bug #10604 (Duplicate): osd crash in upgrade:dumpling-dumpling-distro-basic-multi run
- Run: http://pulpito.ceph.com/teuthology-2015-01-21_11:54:26-upgrade:dumpling-dumpling-distro-basic-multi/
Job: 716... - 12:43 AM Revision 90a90bb2 (ceph): rgw: set default value for swift versioning extension
- Otherwise we're going to crash if not found.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:36 AM Revision a463b92e (ceph): ceph_test_rados_api_misc: do not assert rbd feature match
- This test fails on upgrades when we (or the server) have new
features. Make it less fragile.
Fixes: #10576
Signed-o... - 12:35 AM Revision 8ba48d10 (ceph): ceph_test_rados_api_misc: do not assert rbd feature match
- This test fails on upgrades when we (or the server) have new
features. Make it less fragile.
Fixes: #10576
Signed-o... - 12:32 AM Revision dc11ef13 (ceph): PGBackend: fix and clarify be_select_auth_object
- Previously, auth would end up containing every object without a
self-evident defect -- even if they did not match eac... - 12:21 AM Revision 26656e32 (ceph): rgw: fix bucket removal with data purge
- Called by radosgw-admin user rm, need to set the versioning status
correctly.
Signed-off-by: Yehuda Sadeh <yehuda@re... - 12:11 AM Revision 07038a79 (ceph): Merge branch 'next'
- 12:10 AM rbd Bug #10592 (Resolved): lock blacklist test needs updating for mandatory locking
- commit:946958c13ccde932315a1e5b340e08c9fead009b
- 12:01 AM Revision b18b14b1 (ceph): ObjectStore::_update_op: treat CLONERANGE2 like CLONE
- Fixes: #10603
Signed-off-by: Samuel Just <sjust@redhat.com>
01/21/2015
- 11:29 PM Revision 4d7a6a75 (ceph): Merge pull request #3251 from theanalyst/fix/rgw/s3-10062
- wip: rgw: check keystone auth also for s3 post requests
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:23 PM Revision e1c38bd5 (ceph): librbd: gracefully handle deleted/renamed pools
- snap_unprotect and list_children both attempt to scan all
pools. If a pool is deleted or renamed during the scan,
the... - 10:13 PM Revision 3c339d4a (ceph): suites/rados: exercise heartbeat prioritization
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:03 PM RADOS Feature #8679: improve logging statements
- Wow.
- 09:57 PM Revision 4e1d00ca (ceph): Merge pull request #3441 from dachary/wip-resolve-symlinks
- test/ceph-disk.sh: resolve symlinks before check
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 09:53 PM Revision 9d382e5a (ceph): Merge pull request #3381 from liewegas/wip-pg-stat-updates
- osd: avoid spamming monitor with unchanged pg stats
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:52 PM Revision e203673c (ceph): Merge pull request #3393 from ceph/wip-osd-df
- osd: ceph osd df [tree] command
Reviewed-by: Sage Weil <sage@redhat.com> - 09:52 PM Revision 6633f8a3 (ceph): Merge pull request #3409 from trociny/wip-osd_pool_flags
- osd: new pool safeguard flags: nodelete, nopgchange, nosizechange
Reviewed-by: Sage Weil <sage@redhat.com> - 09:25 PM Bug #9735 (Resolved): "rados lock list" doesn't output final end-of-line
- 09:03 PM Bug #10602 (Can't reproduce): osd heartbeat issues, stuck recoverying/degraded, and repeating age...
timeout expired in wait_for_all_up...- 08:54 PM rbd Subtask #4092 (In Progress): rbd: re-read header when watch is re-established
- 08:44 PM rbd Fix #8903 (In Progress): rbd mirroring: librbd: fix watch/notify usage
- Re-registering of the watch was implemented under #8900.
- 08:29 PM Bug #10601 (Duplicate): thrashosd shutdown: No JSON object could be decoded
Found in
dzafman-2015-01-20_13:03:28-rados:thrash-wip-zafman-testing---basic-multi/715179
dzafman-2015-01-20_13...- 08:28 PM Revision 14cdb9bb (ceph): rbd: ensure aio_write buffer isn't invalidated during image import
- The buffer provided to aio_write shouldn't be invalidated until
after aio_write has indicated that the operation has ... - 08:26 PM rbd Feature #10462 (Fix Under Review): rbd cli: use io hints for import/export etc
- 08:25 PM rbd Bug #10590 (Pending Backport): rbd import_export.sh workunit failed
- 07:58 PM rbd Bug #10590 (Fix Under Review): rbd import_export.sh workunit failed
- 06:37 PM rbd Bug #10590 (In Progress): rbd import_export.sh workunit failed
- 08:23 PM Revision 4d3b49e9 (ceph): rbd: ensure aio_write buffer isn't invalidated during image import
- The buffer provided to aio_write shouldn't be invalidated until
after aio_write has indicated that the operation has ... - 08:13 PM Revision 1739f0c1 (ceph): Use qemu-kvm in the qemu task for rpm based systems.
- Signed-off-by: Andrew Schoen <aschoen@redhat.com>
- 08:04 PM Revision a592c467 (ceph): test/ceph-disk.sh: resolve symlinks before check
- Make sure symlinks are resolved in command_fixture()
before compare result of which command and the current
path.
Si... - 08:02 PM Revision 500f4b43 (ceph): rgw: assign versioned_epoch on bucket listing response
- For some reason this was missing.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 07:59 PM Revision 34876833 (ceph): Merge pull request #3426 from jdurgin/wip-10592
- qa: disable automatic locking for manual locking test
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:30 PM Revision 9dc89b23 (ceph): Merge pull request #3259 from trociny/pg_dump_plain
- mon: improvements for 'ceph pg dump' in plain format
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 06:19 PM rbd Bug #10122 (Pending Backport): "LibRBD.TestClone" FAILED in upgrade:dumpling-x-firefly-distro-bas...
- 05:50 PM Feature #10452: ceph osd df
- 05:49 PM Feature #9956 (Resolved): osd: reenable alloc hints if kernel is known to be safe
- 05:17 PM devops Bug #10591: Missing packages in upgrade:dumpling-dumpling-distro-basic-magna run
- Please link commits instead of just mentioning a hash:
https://github.com/ceph/ceph-qa-chef/commit/758a7c7b3746334... - 05:08 PM Revision f9e088fc (ceph): ceph_manager: In Thrasher disable ceph_objectstore_tool tests if old re...
- Require ceph-objectstore-tool to be available on all OSD nodes
Log a message when tool is not available
Signed-off-b... - 05:08 PM Revision 4a195c78 (ceph): ceph_manager: In Thrasher randomly remove past intervals
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:08 PM Revision e0b0d41e (ceph): ceph_manager: Re-enable Thrasher ceph-objectstore-tool testing
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:08 PM Revision 4eda2967 (ceph): ceph_manager: Thrasher fixes to run() calls to set check_status = False
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:08 PM Revision b239dadc (ceph): ceph_manager: Fix Thrasher kill_osd() to ignore pool going away
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:08 PM Revision bff23583 (ceph): Fix objectstore name changed to keyvaluestore
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:08 PM Revision 14e27650 (ceph): Fix wrapped line
- 05:08 PM Revision e5876126 (ceph): Formatting changes
- 03:56 PM Revision 2c3dc372 (ceph): Merge pull request #3431 from XinzeChi/wip-compile-warning
- osd: fix some compile warning
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:37 PM Revision 8cbfac42 (ceph): Wrong HTTP header name
- According to http://docs.openstack.org/api/openstack-object-storage/1.0/content/POST_updateObjectMeta__v1__account___...
- 03:09 PM CephFS Bug #10579 (Resolved): ceph-qa-suite: can't run quota tests on kernel client
- Thanks!
- 02:41 PM CephFS Bug #10579 (Fix Under Review): ceph-qa-suite: can't run quota tests on kernel client
- https://github.com/ceph/ceph/pull/3436
https://github.com/ceph/ceph-qa-suite/pull/308 - 03:08 PM Revision 4761c2c0 (ceph): Merge pull request #308 from ceph/wip-10579
- suites/fs: isolate quota task
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:08 PM Revision 373473d3 (ceph): Merge pull request #3436 from ceph/wip-10579
- qa: move fs quota to its own dir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:49 PM Feature #10463: use SEEK_DATA/SEEK_HOLE for FileStore fiemap() implementation
- @sage
do we need to reserve or fallback to fiemap if SEEK_DATA not supported? - 02:39 PM Revision 82159315 (ceph): suites/fs: isolate quota task
- Quota script is moved out of fs/misc so that kclient
doesn't try to run it. Update cfuse suite to find
the new locat... - 02:38 PM rgw Bug #10243: civetweb is hitting a limit (number of threads 1024)
- Hi, any news about changing civetweb github repo?
- 02:36 PM Revision a0af5de9 (ceph): qa: move fs quota to its own dir
- This is because running fs/misc on a kclient
should not include quota (quota not supported
on kernel client).
Fixes:... - 02:32 PM Revision 21b11a0e (ceph): Merge pull request #3402 from ceph/wip-10388
- #10388 PerfCounters for MDCache: strays and recovery
- 02:19 PM CephFS Bug #10550: Assertion in ceph-mds on failures in ::init
- I am working on this.
- 12:04 PM Bug #10425: RadosClient::connect leaks Objecter if called twice
- I am attaching the first proposal of patch for your review.
Besides rectifying the Objecter leak, two additional t... - 11:09 AM Bug #10596 (Resolved): error when building ceph on ubuntu 14
- when runing ./install-deps.sh
update-alternatives: utilisation de « /usr/bin/g++ » pour fournir « /usr/bin/c... - 09:10 AM Revision 2ce38db1 (ceph): osd: fix some compile warning
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 08:54 AM Revision 84c2c25d (ceph): Merge pull request #3433 from FrankYu/master
- Doc: Fix the typo in doc/rbd/rados-rbd-cmds.rst
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:47 AM Revision b9be97f7 (ceph): Doc: Fix the typo in doc/rbd/rados-rbd-cmds.rst
- Fix the typo in doc/rbd/rados-rbd-cmds.rst, also add explanation/example
when creating an image without specifying po... - 03:28 AM Revision 35badbc6 (ceph): Merge pull request #3427 from jdurgin/wip-cram
- test: fix rbd cli tests for new feature bit
Reviewed-by: Sage Weil <sage@redhat.com> - 03:20 AM Revision 97a69691 (ceph): mon: do not prime pg_temp when the current acting is < min_size
- The PG is down anyway.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:20 AM Revision 7a1305b6 (ceph): mon: prime pg_temp
- Prime pg_temp values for
- any osd that goes up/down or has a reweight change
- all osds on crush map change
We'r... - 03:20 AM Revision f6fa254c (ceph): mon: cap the amount of time we spend priming pg_temp
- Default to 500ms, which should be enough for most clusters and not very
disruptive.
Signed-off-by: Sage Weil <sage@r... - 03:20 AM Revision 4fcbd146 (ceph): mon: be more careful about when we prime all pgs
- If we mark down or weight down, pgs will go *away* from an osd and we can
focus just on the ones that are there now.
... - 03:20 AM Revision 7a04762f (ceph): mon/PGMap: keep osd -> pg mapping in memory
- Optimize for the case where the mapping does not change so that we are
not thrashing the in-memory structure.
Signed... - 01:13 AM Revision fe93f73a (ceph): test: fix rbd cli tests for new feature bit
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
01/20/2015
- 11:56 PM Revision 946958c1 (ceph): qa: disable automatic locking for manual locking test
- Automatic locking hides the ESHUTDOWN from the caller, which is how
this test detects that blacklisting works.
Fixes... - 11:24 PM Revision c68ecc74 (ceph): xio: Enable xio option to call fork init
- Ceph fork when running as daemon. This fix call xio option to enforce
Accelio to explicitly call ibv_fork_init() to a... - 09:17 PM Revision 46347fcc (ceph): osd: Transction::append SHOULD NOT modify other.op_bl
- the other.op_bl SHOULD NOT be changes during append operation,
we use additional bufferlist to avoid this problem
Ch... - 09:17 PM Revision b1b299d3 (ceph): osd: revert d427ca35404a30e1f428859c3274e030f2f83ef6
- d427ca35404a30e1f428859c3274e030f2f83ef6 reversed the order of localt
and op_t, while some logic depends on the order... - 08:07 PM CephFS Bug #10416 (Resolved): quota test failures
- That appears to have been the issue.
- 07:58 PM Revision 988d007e (ceph): ReplicatedPG::on_change: clear cache at the end
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:30 PM Revision 64a4cb8b (ceph): Merge pull request #3408 from ceph/wip-10257
- mon: PGMonitor: several stats output error fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 07:29 PM CephFS Feature #10498: ObjectCacher: order wakeups when write calls block on throttling
- ObjectCacher::file_write did hang about 3 hours...
- 06:47 PM Revision 8453f712 (ceph): mon: Do not allow empty pool names when creating
- Fixes: #10555
Signed-off-by: Wido den Hollander <wido@42on.com> - 06:21 PM Revision 58ab125d (ceph): Merge pull request #3423 from yuyuyu101/rename-test-msgr
- test_msgr: Rename unittest_msgr to ceph_test_msgr
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:07 PM Revision 68af5109 (ceph): ceph-disk: do not reuse partition if encryption required
- If encryption is required, an existing journal partition must not be
reused. If an existing partition that was not pr... - 05:42 PM rbd Documentation #7807: fix hostname on docu
- Hi, I will try to change it !
- 05:05 PM Revision e92d2e4c (ceph): rados: include msgr tests
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:59 PM Revision 48963bab (ceph): test_msgr: Rename unittest_msgr to ceph_test_msgr
- Because ceph_test_msgr will run a lot of times than unittest expected,
move it into qa suites.
Signed-off-by: Haomai... - 04:18 PM Revision b311e7c3 (ceph): mon: PGMonitor: skip zeroed osd stats on get_rule_avail()
- Fixes: #10257
Signed-off-by: Joao Eduardo Luis <joao@redhat.com> - 04:13 PM Revision 8be6a6ab (ceph): mon: PGMonitor: available size 0 if no osds on pool's ruleset
- get_rule_avail() may return < 0, which we were using blindly assuming it
would always return an unsigned value. We w... - 04:02 PM Revision 079fac2e (ceph): Merge pull request #3192 from gravitystorm/patch-1
- Replace placeholder with 'gateway'
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:57 PM rbd Bug #10592 (Fix Under Review): lock blacklist test needs updating for mandatory locking
- https://github.com/ceph/ceph/pull/3426
- 03:31 PM rbd Bug #10592 (Resolved): lock blacklist test needs updating for mandatory locking
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-14_23:00:01-rbd-master-testing-basic-multi/704116/teuthology.log
- 03:47 PM Revision e84f27e3 (ceph): doc: Replace placeholder with 'gateway'
- This section is where all the placeholders are replaced by example text, this one had been missed out.
Signed-off-by... - 03:45 PM Revision 72e146ce (ceph): Merge pull request #3414 from vuhuong/wip-cmake-fix
- cmake: Fix CMakelist.txt to remove depleted files
Reviewed-by: Sage Weil <sage@redhat.com> - 03:38 PM devops Bug #10591: Missing packages in upgrade:dumpling-dumpling-distro-basic-magna run
- I did some manual investigation in this and found because there was a newer version of ceph available on the main rep...
- 03:28 PM devops Bug #10591: Missing packages in upgrade:dumpling-dumpling-distro-basic-magna run
- I looked into this a bit and am confused: why is @libcephfs-jni@ "not going to be installed" ?
- 03:11 PM devops Bug #10591 (Resolved): Missing packages in upgrade:dumpling-dumpling-distro-basic-magna run
- Run http://pulpito.ceph.redhat.com/teuthology-2015-01-19_21:13:46-upgrade:dumpling-dumpling-distro-basic-magna/
Jobs... - 03:11 PM Revision 541637d5 (ceph): librbd: copy-on-read for clones, add an option for copy-on-read
- Signed-off-by: Min Chen <minchen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com>
Signed-off-by: Yunc... - 03:11 PM Revision 701a248a (ceph): librbd: copy-on-read for clones, read entire object from parent
- Signed-off-by: Min Chen <minchen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com>
Signed-off-by: Yunc... - 03:11 PM Revision f408c8e4 (ceph): librbd: copy-on-read for clones, write entire object into child asychro...
- Signed-off-by: Min Chen <minchen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com>
Signed-off-by: Yunc... - 03:11 PM Revision 8c47800b (ceph): librbd: copy-on-read
- Asychronously perform copyup on read path.
Sychronously perform copyup on write path.
Signed-off-by: Cheng Cheng <... - 03:11 PM Revision 190c185b (ceph): librbd: copy-on-read
- Addressed Jason's review comments.
Signed-off-by: Cheng Cheng <ccheng.leo@gmail.com> - 03:00 PM rbd Bug #10590 (Resolved): rbd import_export.sh workunit failed
- From http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-18_23:00:02-rbd-next-distro-basic-multi/712107/teuthology...
- 02:38 PM devops Bug #10532: Failed "joining thrashosds" - suspected low memory config on vps
- Same
Run http://pulpito.front.sepia.ceph.com/teuthology-2015-01-19_18:18:01-upgrade:firefly-x-giant-distro-basic-v... - 02:13 PM devops Bug #10526 (Resolved): Gitbuilder mirror not syncing
- 02:10 PM devops Bug #10526 (In Progress): Gitbuilder mirror not syncing
- nginx solution seems to be working well. We just need to stop the periodic mirroring on the host.
- 01:22 PM Revision 2b86479b (ceph): Merge pull request #3419 from Nairolf21/wip-documentation
- doc: Introduce the term MON at http://ceph.com/docs/master/rados/
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:19 PM Revision 88b10321 (ceph): Introduce the term MON at http://ceph.com/docs/master/rados/
- http://tracker.ceph.com/issues/10203 Fixes:#10203
Signed-off-by: Florian Coste <fcoste21@gmail.com> - 01:13 PM Revision b7cc6afb (ceph): Merge pull request #3421 from hazem92/wip-documentation
- doc: mon should be listed before osd
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:10 PM Revision 08faee07 (ceph): doc: mon should be listed before osd
- When deploying a Ceph cluster, the mon must be run first.
In the list shown at http://ceph.com/docs/master/rados/conf... - 12:53 PM Stable releases Tasks #10501: giant v0.87.1
- Josh would like
* https://github.com/ceph/ceph/pull/3403
* https://github.com/ceph/ceph/pull/3405
* https://git... - 12:36 PM Revision 852ea874 (ceph): Merge pull request #3420 from Anols/wip-documentation
- doc: missing the reference to "ceph-deploy-new"
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:42 AM devops Tasks #10587 (Resolved): split ceph-mon, ceph-osd, and ceph-mds in the Debian and Red Hat packages
- ceph-mon and ceph-osd should be their own subpackages.
ceph-mon should contain:... - 11:39 AM Bug #10257: Ceph df doesn't report MAX AVAIL correctly when using rulesets and OSD in ruleset is ...
- to be backported to giant and firefly: 8be6a6ab2aa5a000a39c73a98b11a0ab32fffa1c and b311e7c36273efae39aa2602c1f8bd90d...
- 11:29 AM Bug #10257 (Pending Backport): Ceph df doesn't report MAX AVAIL correctly when using rulesets and...
- 11:36 AM rbd Bug #10576 (Resolved): LibRadosMisc test failed (RBD_ALL_FEATURES mismatch on upgrade)
- 11:26 AM Bug #10488: osd erasure-code-profile set is sometimes not idempotent
- ubuntu@teuthology:/a/sage-2015-01-19_18:35:10-rados-wip-dho-distro-basic-multi/713735
- 11:21 AM Bug #10485: unreadable ceph-osd core dump (firefly)
- ???ubuntu@teuthology:/a/sage-2015-01-19_18:35:10-rados-wip-dho-distro-basic-multi/713884 (firefly)
- 11:15 AM Revision 119add67 (ceph): Merge pull request #3418 from ThomasCantin/wip-documentation
- doc: Network Configuration Reference duplicate string #3418
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:06 AM Revision 6b1c92c2 (ceph): Doc : Documentation#10205
- Missing the reference of "ceph-deploy-new".
https://tracker.ceph.com/issues/10205
Signed-off-by: AYARI <ayari_anis@... - 10:48 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- How many objects are getting processed? Does it keep processing the same object, or is it processing different object...
- 10:32 AM Revision b8dd228c (ceph): doc bug 10206
- 09:29 AM rgw Bug #10584 (Resolved): AttributeError raised with new changes to exceptions in agent
- 08:40 AM rgw Bug #10584 (Fix Under Review): AttributeError raised with new changes to exceptions in agent
- Pull request opened https://github.com/ceph/radosgw-agent/pull/19
- 08:20 AM rgw Bug #10584 (Resolved): AttributeError raised with new changes to exceptions in agent
- ...
- 09:12 AM rbd Feature #8569 (In Progress): RBD Mirroring::
- 09:06 AM Linux kernel client Feature #10585 (Resolved): use new, more reliable version of watch/notify
- The interface exposed by librados has everything that needs to be
available to the user and a description of most of... - 09:02 AM rbd Feature #8900 (Resolved): rbd mirroring: librbd:making image locking mandatory
- commit:ccadff1445ce8525e4c2419dca63683f0bc1c113 and the surrounding ones
- 08:11 AM Revision 8d1de54b (ceph): Merge pull request #3164 from ceph/wip-librbd-rados-stub
- librados test driver and librbd unit test
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:49 AM Stable releases Tasks #10560: dumpling v0.67.12
- match existing commits with the issue the refer to
- 07:46 AM Bug #10583 (Closed): keyvaluestore: properly handle db backend error
- user report: http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/22840
Different db backend has own logi... - 06:26 AM Revision ae6bd610 (ceph): Merge pull request #3411 from ceph/wip-10576
- ceph_test_rados_api_misc: do not assert rbd feature match
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:21 AM Documentation #10203 (Resolved): documentation: explain the term MON
- 04:45 AM Documentation #10203: documentation: explain the term MON
- https://github.com/ceph/ceph/pull/3419
- 04:41 AM Documentation #10203: documentation: explain the term MON
- Fixed
- 12:24 AM Documentation #10203: documentation: explain the term MON
- I'll do this.
- 05:11 AM Documentation #10204 (Resolved): documentation: mon should be listed before osd
- 04:56 AM Documentation #10204: documentation: mon should be listed before osd
- https://github.com/ceph/ceph/pull/3421
- 12:27 AM Documentation #10204: documentation: mon should be listed before osd
- I will take in charge this bug !
- 04:59 AM Documentation #10206 (Resolved): documentation: Network Configuration Reference duplicate string
- 04:47 AM Documentation #10206: documentation: Network Configuration Reference duplicate string
- Fixed. https://github.com/ceph/ceph/pull/3418
- 04:52 AM Documentation #10205 (Resolved): documentation: reference to ceph-deploy should be a link
- 04:45 AM Documentation #10205: documentation: reference to ceph-deploy should be a link
- https://github.com/ceph/ceph/pull/3420
- 04:47 AM Linux kernel client Bug #10352: libceph delayed work items aren't teared down properly
- 04:46 AM Linux kernel client Bug #10352: libceph delayed work items aren't teared down properly
- This turned out to have nothing to do with how we tear down delayed_works - that code is fine.
The problem was rbd m... - 04:04 AM Linux kernel client Bug #8087: libceph: null deref in osd_reset -> __reset_osd -> __remove_osd
- actually the restart was a few hours earlier at about 22:53 and the crash was at 03:12, so it might also be unrelated...
- 03:21 AM Linux kernel client Bug #8087: libceph: null deref in osd_reset -> __reset_osd -> __remove_osd
- I noticed this before, but have not reproduced it systematically. We have currently 82 OSDs and I restarted them simu...
- 02:28 AM Linux kernel client Bug #8087: libceph: null deref in osd_reset -> __reset_osd -> __remove_osd
- Also, how many OSDs do you have? How exactly did you restart all OSDs simultaneously - paste exact commands. Was th...
- 02:22 AM Linux kernel client Bug #8087: libceph: null deref in osd_reset -> __reset_osd -> __remove_osd
- Reported in #5429:...
- 02:28 AM Revision 9147c629 (ceph): ceph_test_rados_api_misc: do not assert rbd feature match
- This test fails on upgrades when we (or the server) have new
features. Make it less fragile.
Fixes: #10576
Signed-o... - 02:18 AM Linux kernel client Bug #5429: libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
- This ticket has it mixed up with another issue, we are tracking rb_erase() in #8087.
I'll post your comment and repl... - 01:50 AM Linux kernel client Bug #5429: libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
- During some tests, I stumbled upon this bug in rb_erase triggered osd_reset() -> __reset_osd() -> __remove_osd(). But...
- 01:54 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Up until now, I could not reproduce the bug with all the patches applied. But I stumpled across bug #5429 which is ma...
- 12:26 AM Revision 6d209c20 (ceph): rgw: cors set attrs on bucket using appropriate call
- Following rebase, we should call the appropriate function when setting
attrs on a bucket.
Signed-off-by: Yehuda Sade...
01/19/2015
- 11:58 PM Revision 0b6300d9 (ceph): rgw: start pending entries attr name by timestamp
- This will make it (roughly) possible to get these sorted by time.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision 11befabf (ceph): rgw: break if done when timing out pending olh ops
- Entries are now sorted by timestamp (older to newer). Break if found
that entry has not timed out.
Signed-off-by: Ye... - 11:58 PM Revision 2c367981 (ceph): rgw: switch index ops to new apis
- following a rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision 69311320 (ceph): rgw: fix setting of versioned epoch when removing object instance
- Beforehand if rgwx-versioned-epoch was passed, we ended up always
creating a delete marker. We don't do that now if r... - 11:58 PM Revision 03f2d0cf (ceph): rgw: handle 'null' instance when setting delete marker
- Don't set 'null' instance for a delete marker. We use empty string for
this specific case.
Signed-off-by: Yehuda Sad... - 11:58 PM Revision e23a32d6 (ceph): rgw: fix unitest compilation
- Add the needed extra param for bilog_flags.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision f51a5a94 (ceph): cls_rgw: user swap() instead of assignment operator
- More efficient this way. A fix following code review.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision b999bc79 (ceph): cls_rgw: fix rgw_bi_log_entry::dump()
- Add missing instance field.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision eaf19a5e (ceph): cls_rgw: cleanup, add read_bucket_header()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:58 PM Revision dd7ffdb6 (ceph): rgw, cls_rgw: log versioned operations in bucket index log
- Add the following log ops:
- link_olh
- link_olh_del
- unlink_instance
Log operations if needed. Use current vers... - 11:58 PM Revision 2718ecc8 (ceph): rgw: fix use of rgw_remove_object() versioning_status param
- Param passed is the versioning status, and not a boolean.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision 0bf69915 (ceph): rgw: add bucket index log flags, use these for marking versioned ops
- We want to mark operations as versioned. This is needed by the sync
agent, so that we know how to handle bucket index... - 11:58 PM Revision 91695693 (ceph): rgw: multi object delete sends delete marker info
- The api requires that we send information about whether the operation
was on a delete marker (either created or remov... - 11:58 PM Revision 2a9a1937 (ceph): rgw_admin: don't reuse -o command line option
- Follow up on code review
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:58 PM Revision bfb50682 (ceph): rgw: fix olh guarding scheme
- is_olh() will return false if object is not yet an olh, although we
started the process into turning it into one. We ... - 11:58 PM Revision 842da1fe (ceph): rgw: only retry on ECANCELED before doing the operation
- After we did the operation (e.g., link olh, remove) we don't need to
retry. We got ECANCELED, therefore the operation... - 11:58 PM Revision 7a090be5 (ceph): cls_rgw: bound bi log listing appropriately
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 9b31a839 (ceph): rgw: break out of inifinite ECANCELED state
- Don't wait forever, we might be in this state due to a bug, so it's
better to abort with EIO at this point.
Signed-o... - 11:57 PM Revision e8afa65f (ceph): rgw: multi object delete supports versioning
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision c4cf0e2e (ceph): cls/rgw: when removing delete marker, clean up instance entry
- Since we create the instance entry at the bucket index, we should also
remove it. Otherwise we end up with objects th... - 11:57 PM Revision fa7afd15 (ceph): rgw: when deleting object version return -ENOENT if needed
- If can't do bi_get() on the object, we should treat it as non existent
and just return.
Signed-off-by: Yehuda Sadeh ... - 11:57 PM Revision f1f9a5f9 (ceph): rgw: delete obj, handle null instance in all paths
- When passing rgw_obj structures to the bucket index, we should remove
the "null" instance, pass an empty instance ins... - 11:57 PM Revision d707db2c (ceph): rgw: no need to set tag on object we're removing
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision cecea507 (ceph): rgw: only set olh attr on actual olh object
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision ecd5496d (ceph): rgw: dump versioned epoch on system user bucket listing
- The sync agent will need this info.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision b664903f (ceph): rgw, cls_rgw: clean up olh artifacts when dropping last version
- This is still missing one piece, however, it works like this:
1. bucket index log reflects last version was removed (... - 11:57 PM Revision 12ef0ac9 (ceph): rgw, cls_rgw: conditionally remove olh object
- still not completely working, need to debug
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 7024ebde (ceph): rgw: fix caching for remove_system_obj()
- Align the RGWCache method with the RGWRados method. Also, don't use obj
head removal objclass call, as it's for data ... - 11:57 PM Revision 3dd6994b (ceph): rgw: remove clutter
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision fc996012 (ceph): rgw: multipart meta object shouldn't be versioned
- This object is already unique due to the upload id associated with it.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 85aa7253 (ceph): rgw: limit print length of bufferlist buffer
- These specific buffers are not null terminated.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 4e82209a (ceph): cls_rgw: only maintain object if there are preserved xattrs
- rgw.obj_remove op doesn't need to keep the object around if there aren't
preserved xattrs found.
Signed-off-by: Yehu... - 11:57 PM Revision 6a05cc10 (ceph): rgw: fix a few regressions
- - need to increase olh epoch if converting plain entry, otherwise
ordering is skewed
- if entry is olh (e.g., col... - 11:57 PM Revision 630c0ba6 (ceph): cls_rgw: don't increase epoch when converting plain entry
- Plain entries that are getting converted gets epoch 1, as these are non
versioned ones, and every entry following the... - 11:57 PM Revision 8f5e0739 (ceph): rgw: allow setting of explicit object version on non-versioned bucket
- If system user has set explicit olh version and/or object instance id,
treat it as the bucket was versioned anyway. T... - 11:57 PM Revision fe158ecc (ceph): rgw: use correct objv_tracker for bucket instance
- When trying to create a bucket that already existed, use the
objv_tracker of the newly created instance, and not of t... - 11:57 PM Revision 8cf22f7a (ceph): rgw: fix get_system_obj() caching
- Originally this was get_obj(), but in the cleanup work this was changed
to get_system_obj() with somewhat different p... - 11:57 PM Revision b947c7c7 (ceph): rgw: cleaup RGWRados::copy_obj()
- separate into multiple methods.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 09035027 (ceph): rgw: propagate version id when putting obj
- A system user can set the rgwx-version-id http param, and it's now sent
to the objclass.
Signed-off-by: Yehuda Sadeh... - 11:57 PM Revision 9b88af67 (ceph): rgw: copy obj does versioning too
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 38b93527 (ceph): rgw: move versioning handling to Object::Write::write_meta()
- Instead of having to call set_olh() after calling write_meta(), do it
inside that method. This way we (mostly) don't ... - 11:57 PM Revision 6c08f58a (ceph): rgw: reduce use of Object::get_obj()
- We should avoid using this one, as it's not going to point at the object
instance in case it's an olh. Only kept the ... - 11:57 PM Revision d57cdd0c (ceph): rgw: parse copy location version id
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision aa0667da (ceph): cls_rgw, rgw: pending_log can hold multiple entries per epoch
- This is needed, so that we can later replay operations, using the epoch
for idempotency.
Signed-off-by: Yehuda Sadeh... - 11:57 PM Revision 37d15f2d (ceph): cls_rgw: link, unlink olh ops can get epoch
- If epoch is specified, we need to handle updates differently, only
update the olh itself if passed epoch is newer tha... - 11:57 PM Revision 8787b926 (ceph): rgw, cls_rgw: provide optional version id, versioned epoch to olh ops
- Let system users specify optional params: rgwx-version-id,
rgwx-versioned-epoch. These will apply to object modificat... - 11:57 PM Revision 37856d0e (ceph): rgw: Object::Read::read() returns total bytes read
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision b4f3de04 (ceph): rgw: Object::Read operations should use state->obj
- and not the provided obj, as it might have been an olh, therefore we
have prepare() that sets the state.obj as the ef... - 11:57 PM Revision 2093aab6 (ceph): cls_rgw: revise null object instance handling, versioned epoch
- Separate the versioned epoch from the object entry version, since in the
case of null instane entries the object vers... - 11:57 PM Revision 445a4ac2 (ceph): cls_rgw: don't write list entry when converting when deleting
- when converting the plain entry into a versioned entry, don't write the
list entry if this is a delete op with a null... - 11:57 PM Revision 333f8d21 (ceph): rgw: time out pending olh entries
- remove old pending entries
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 56787ff2 (ceph): cls_rgw: implement dump() and generate test instances
- Add missing methods for some cls_rgw op types.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 90ed9a21 (ceph): cls_rgw: clean up compilation warnings
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 3de35d89 (ceph): rgw: remove unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision aa888abe (ceph): rgw: remove warning
- This cleanup is not essential at this point
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision bda15613 (ceph): rgw: read bucket owner when following olh if pending entries
- We need to read the bucket owner, so that we'd be able to apply any
changes to the object. Bucket owner is needed for... - 11:57 PM Revision a871a8d2 (ceph): rgw: send x-amz-version-id and x-amz-delete_marker header fields
- send these fields on obj delete as defined by the api. This required
adding an index read so that we can identify whe... - 11:57 PM Revision 16f1b24f (ceph): cls_rgw: remove instance entry when removing delete marker
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 3f29f0aa (ceph): rgw: encode timestamp in pending olh info
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 01b8e614 (ceph): rgw, cls_rgw: improve olh atomicity
- Add olh_tag attr to olh object, and use it instead of obj_tag as object
data may be colocated with the olh. Use the o... - 11:57 PM Revision 79bb0fdf (ceph): cls_rgw: guard certain operations using olh tag
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 33b19e7f (ceph): cls_rgw: inc olh epoch when updating log
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 9e655709 (ceph): rgw, cls_rgw: fix update of olh to reflect non existing object
- need to update olh appropriately when removing the last reference of an
object.
Signed-off-by: Yehuda Sadeh <yehuda@... - 11:57 PM Revision 5ab83ef9 (ceph): cls_rgw: add missing cls_cxx_create()
- This was found during code read, not necessarily a real issue, however,
we counted on the object being created implic... - 11:57 PM Revision 5e825003 (ceph): rgw: add dump_string_header()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 7f139286 (ceph): rgw, cls_rgw: multiple changes related to obj removal
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision ba34ecfb (ceph): rgw: propagate object owner and mtime for deletion marker
- deletion marker needs to have object owner and mtime properties.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision b8b832b5 (ceph): rgw: adjust versioning enable/suspend api
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 3e48a49f (ceph): rgw: fix access to object through the null instance
- Beforehand we were following olh if the explicit 'null' instance was
specified.
Signed-off-by: Yehuda Sadeh <yehuda@... - 11:57 PM Revision a8180bac (ceph): cls_rgw, rgw-admin: create bi list operation
- Can now list bucket index entries that correspond to a single key. This
is useful when debugging versioned objects is... - 11:57 PM Revision 3593b6c8 (ceph): rgw, cls_rgw: add bi put
- An admin operation to set bucket index entries.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 4f622cc1 (ceph): osd: fix filter_prefix scoping in omap_get_vals
- filter_prefix should only affect the case where it's greater than
start_after, otherwise we'll end up with a key equa... - 11:57 PM Revision 5bca3b98 (ceph): formatter: no need for dynamic allocation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 0a3df98d (ceph): rgw: send "null" version id if needed
- on bucket list versions
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 70139017 (ceph): cls_rgw: keep null-versioned object as versioned object
- when olh is created. Mark the object as such, so that we'll know to
handle it correctly. This is needed so that we co... - 11:57 PM Revision 9c347b92 (ceph): rgw-admin, cls_rgw: add bi_get objclass operation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 75b90502 (ceph): common, rgw: json escaping gets input buf size
- We now deal with strings that embed a null character.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision cec02f99 (ceph): cls_rgw: add missing flags encoding to rgw_bucket_dir_entry::dump()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision de3c5ecf (ceph): cls_rgw, rgw-admin: move bi_get() entry encoding to cls
- Create a new structure to hold entry info, so that we can later creata a
bi_list() operation.
Signed-off-by: Yehuda ... - 11:57 PM Revision 55877bef (ceph): cls_rgw: unlink object instance
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision bb8365a2 (ceph): rgw: unlink obj instance
- use new objclass method
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision ed1813dd (ceph): rgw: follow olh where needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision a6d65bb0 (ceph): cls_rgw: update olh log when unlinking entry
- Need to update log so that later client will be able to appropriately
remove the object.
Signed-off-by: Yehuda Sadeh... - 11:57 PM Revision 89f93721 (ceph): cls_rgw: more cleanup
- move versioned data and olh handling into class methods.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 47f2bffe (ceph): rgw: convert RGWRados::get_attr() to new interface
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision ca3104b5 (ceph): cls_rgw: reorganize rgw_bucket_link_olh()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision fd9bffeb (ceph): cls_rgw: more cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 7f5c0107 (ceph): rgw: adjust to new interfaces
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision b0cc9e45 (ceph): rgw: purge intent log
- We don't use the intent log anymore, just remove it.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision 8d7c8828 (ceph): rgw: remove unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 9ec08b53 (ceph): rgw: switch get_obj_iterate() to new interface
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 8ccf603e (ceph): rgw: remove more unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision cd8c60e6 (ceph): rgw: rework prepare_get_obj(), get_obj()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision d32d9454 (ceph): rgw: change RGWRados::get_attr()
- This is an interim fix, will need to make it work similarly to the other
calls.
Signed-off-by: Yehuda Sadeh <yehuda@... - 11:57 PM Revision 7788daaa (ceph): rgw: clean up system obj interfaces
- Create a new structure to use, RGWRados::SystemObject, similar to the
previous changes made for the data objects.
Si... - 11:57 PM Revision 5c3985f6 (ceph): rgw: s/RGWRados::ObjectCtx/RGWObjectCtx
- Can't forward declare nested class.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:57 PM Revision b7715249 (ceph): rgw: get rid of put_obj_meta(), replace with put_system_obj()
- Last use of put_obj_meta() was for system object, simplify it for that
specific use case and rename.
Signed-off-by: ... - 11:57 PM Revision c5eb6f74 (ceph): rgw: remove old index update calls
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision e3a4898d (ceph): rgw: remove unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 71afabfb (ceph): rgw: switch RGWRados::delete_obj() to new interface
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision 4855c873 (ceph): rgw: fix missing state initalization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision ce2abdec (ceph): rgw: start reorganizing RGWRados
- Need to reduce the various states of the different operations. The aim
is to separate the system objects operations f... - 11:57 PM Revision db143ea6 (ceph): rgw: remove plain object processor
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:57 PM Revision aec13bdc (ceph): rgw: pass around object context refrences, remove unused code
- We want to make it clear that the object context is required for
non-system objects, pass it by reference (rather tha... - 11:57 PM Revision 99cc362e (ceph): rgw: don't use put_system_obj() for data objects
- Use the new interface instead.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:26 PM CephFS Feature #10498 (Fix Under Review): ObjectCacher: order wakeups when write calls block on throttling
- 10:31 AM CephFS Feature #10498: ObjectCacher: order wakeups when write calls block on throttling
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-14_23:04:01-fs-master-testing-basic-multi/704465/
We've see... - 10:00 PM Revision a6b8e823 (ceph): tasks/mds_flush: use new stray/purge perfcounters
- Where previously we only tracked RADOS-level delete
ops during deletion, now also verify that they
correspond to the ... - 09:20 PM Revision 1b2ec972 (ceph): Merge pull request #285 from ceph/wip-9883
- tasks/mds_journal_repair: create new test
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:56 PM Revision ffee996e (ceph): cmake: Fix CMakelist.txt to remove depleted files
- - remove depleted tools/ceph_mon_store_converter_srcs
- replace librbd source file (WatchCtx.cc to ImageWatcher.cc)
... - 08:39 PM Revision 0ab0ce7e (ceph): Merge pull request #3334 from dachary/wip-10216-jerasure-sync
- erasure-code: update jerasure/gf-complete submodules
- 08:39 PM Revision 82ad6c5c (ceph): Merge pull request #3375 from XinzeChi/wip-journal-seq
- osd: fix journal header.committed_up_to
Reviewed-by: Sage Weil <sage@redhat.com> - 08:38 PM Revision dd99b7d9 (ceph): Merge pull request #3320 from wonzhq/lfn_open
- FileStore: return error if get_index fails in lfn_open
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 08:38 PM Revision 01af73bc (ceph): Merge pull request #3211 from yuyuyu101/wip-10172
- AsyncMessenger: Bind thread to core, use buffer read and fix some bugs
- 08:36 PM Revision 075012bd (ceph): Merge pull request #3221 from ceph/wip-9440
- mon: log health changes to clog
Reviewed-by: Sage Weil <sage@redhat.com> - 08:35 PM Revision 8318a2e5 (ceph): Merge pull request #3382 from xinxinsh/wip-fix
- fix command 'ceph pg dump_stuck degraded'
Reviewed-by: Sage Weil <sage@redhat.com> - 08:33 PM Revision d53275c6 (ceph): ceph_test_objectstore: fix keyvaluestore name
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:08 PM Revision 738f8687 (ceph): PGBackend: do not update oi digest on inconsistent object
- Otherwise, repair can race with the oi update. Also, it doesn't really
make sense to update the oi attr if the objec... - 08:01 PM Bug #10157: PGLog::(read|write)_log don't write out rollback_info_trimmed_to
- Hi sam:
"EC pgs will tend to send an unnecessary transaction with the first operation after boot."
This unneces... - 07:50 PM Revision 8ab3c41d (ceph): osd: new pool safeguard flags: nodelete, nopgchange, nosizechange
- * nodelete - pool can't be deleted
* nopgchange - pool's pg and pgp num can't be changed
* nosizechange - pool's size... - 07:36 PM Revision bf13a4e0 (ceph): tasks/mds_journal_repair: create new test
- This tests the new #9883 repair functionality
where we selectively scrape dentries out of
the journal while the MDS i... - 07:36 PM Revision 2c1cef6b (ceph): tasks/mds_journal_repair: add test_table_tool
- Explicit test of the tool's various modes, to
complement the places it's used in other tests.
Signed-off-by: John Sp... - 06:50 PM Revision c15f2d50 (ceph): Merge pull request #3338 from ceph/wip-recover-dentries
- #9883 tools/cephfs: add recover_dentries to journaltool
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:36 PM Bug #10441 (Resolved): osd: dup watch can reply before watch is persisted
- 06:35 PM Feature #10172 (Resolved): AsyncMessenger: Bind async thread to special cpu core
- 06:35 PM Bug #10494 (Resolved): unittest_msgr : segmentation fault
- https://github.com/ceph/ceph/pull/3211#event-221219768
- 06:35 PM Feature #10396 (Resolved): Add ms_inject_* support for AsyncMessenger
- https://github.com/ceph/ceph/pull/3211#event-221219768
- 06:27 PM rbd Bug #10576 (Fix Under Review): LibRadosMisc test failed (RBD_ALL_FEATURES mismatch on upgrade)
- it asserts RBD_ALL_FEATURES, but that has changed. https://github.com/ceph/ceph/pull/3411
- 11:06 AM rbd Bug #10576: LibRadosMisc test failed (RBD_ALL_FEATURES mismatch on upgrade)
- Same in
Run http://pulpito.ceph.com/teuthology-2015-01-18_17:05:01-upgrade:giant-x-next-distro-basic-multi/
Jobs ... - 11:02 AM rbd Bug #10576: LibRadosMisc test failed (RBD_ALL_FEATURES mismatch on upgrade)
- Same in
Run http://pulpito.ceph.com/teuthology-2015-01-18_17:13:01-upgrade:firefly-x-next-distro-basic-multi/
J... - 09:41 AM rbd Bug #10576 (Resolved): LibRadosMisc test failed (RBD_ALL_FEATURES mismatch on upgrade)
- Run http://pulpito.ceph.com/teuthology-2015-01-18_17:10:01-upgrade:dumpling-firefly-x-next-distro-basic-multi/
Job... - 05:59 PM devops Bug #10571: "No package ceph-debuginfo-0.67.10 available" in upgrade:dumpling-dumpling-distro-bas...
- This should be resolved with the fixes from #10570
- 08:51 AM devops Bug #10571 (Rejected): "No package ceph-debuginfo-0.67.10 available" in upgrade:dumpling-dumpling...
- Run http://pulpito.ceph.redhat.com/teuthology-2015-01-16_18:21:03-upgrade:dumpling-dumpling-distro-basic-magna/
Jo... - 05:59 PM devops Bug #10570: "ERROR 403: Forbidden" (v0.67.x)
- So I old dumpling releases were having a problem building cephfs-java which I believe was related to the IBM java tha...
- 08:20 AM devops Bug #10570 (Resolved): "ERROR 403: Forbidden" (v0.67.x)
- In sepia and octo such errors in upgrade/dumpling suite
Run http://pulpito.ceph.com/teuthology-2015-01-16_15:09:46... - 05:47 PM Revision 836ab86d (ceph): osdc: Constrain max number of in-flight read requests
- Constrain the number of in-flight RADOS read requests to the
cache size. This reduces the chance of the cache memory... - 05:46 PM Revision 2964efaf (ceph): Revert "Enforce cache size on read requests"
- This reverts commit b7784dc1baa47560a733fe9dcd2acec51bc93165.
- 05:45 PM Bug #10535 (Resolved): ceph_test_objectstore keyvaluestore error
- i pushed a fix for this to master
- 05:45 PM Revision e4c5b153 (ceph): Revert "rbd: ObjectCacher reads can hang when reading sparse files"
- This reverts commit 711a7e6f81983ff2091caa0f232af914a04a041c.
- 05:39 PM Revision f9f695c0 (ceph): Merge pull request #3400 from kylinstorage/fix-rbd-watch
- fix rbd watch command for v2 image
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:33 PM Revision 0dca0737 (ceph): Merge remote-tracking branch 'origin/wip-bi-sharding-3'
- 05:26 PM Revision 6613358d (ceph): Revert "Merge remote-tracking branch 'origin/wip-bi-sharding-3' into next"
- This reverts commit f79d8f24e9c0bf0d0b37270eba2745a878f2caed, reversing
changes made to 896c8899ac28eb0403bfaa20454f3... - 05:17 PM Revision a6bca747 (ceph): Merge pull request #298 from ceph/wip-bi-sharding-3
- Wip bi sharding 3
- 05:14 PM Revision f79d8f24 (ceph): Merge remote-tracking branch 'origin/wip-bi-sharding-3' into next
- 04:38 PM rbd Feature #4088 (Fix Under Review): rbd: optionally copy-on-read instead of copy-on-write
- https://github.com/ceph/ceph/pull/3040
- 04:38 PM Revision ac93c285 (ceph): Merge pull request #3396 from leseb/doc-openstack-fix-glance
- doc: Fix OpenStack Glance configuration
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:34 PM Revision ce1e1fe4 (ceph): Merge pull request #3401 from FrankYu/master
- Doc: rbd-snapshot: Fix the typo
- 04:25 PM Revision 081f49b4 (ceph): librbd: complete all pending aio ops prior to closing image
- It was possible for an image to be closed while aio operations
were still outstanding. Now all aio operations are tr... - 04:06 PM Revision b5e79a88 (ceph): Merge pull request #3374 from dachary/wip-mailmap
- mailmap updates
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:56 PM rbd Bug #10122: "LibRBD.TestClone" FAILED in upgrade:dumpling-x-firefly-distro-basic-vps run
- Fix requires backporting #10270 to Dumpling release.
- 03:46 PM rgw Cleanup #9772: rgw: reorganize RGWRados
- 03:46 PM rgw Feature #8217: rgw: object versioning object overwrite / delete changes
- 03:46 PM rgw Feature #8216: rgw: object versioning objclass support
- 03:46 PM rgw Feature #8218: rgw: object versioning manifest changes
- 03:45 PM rgw Feature #8473 (Resolved): rgw: Shard bucket index objects to improve single bucket PUT throughput
- merged at commit:0dca07379b0fd0cda5e84a861257cf9a741f4900
- 03:30 PM Revision c23e42e7 (ceph): librbd: gracefully handle deleted/renamed pools
- snap_unprotect and list_children both attempt to scan all
pools. If a pool is deleted or renamed during the scan,
the... - 03:28 PM Revision 436923c6 (ceph): librbd: gracefully handle deleted/renamed pools
- snap_unprotect and list_children both attempt to scan all
pools. If a pool is deleted or renamed during the scan,
the... - 03:16 PM Revision 66f3bd62 (ceph): tools: output per-event errors from recover dentries
- 02:20 PM CephFS Bug #10361: teuthology: only direct admin socket commands to active MDS
- Filesystem.get_active_names is in master now!
- 02:09 PM Revision 36830ebc (ceph): tools/cephfs: add recover_dentries to journaltool
- This is intended as a comparatively safe recovery
operation, where we compare the versions
of journalled dentries wit... - 02:09 PM Revision 478659f3 (ceph): JournalTool: handle corrupt fnodes
- 02:09 PM Revision d94a7a8f (ceph): tools: remove duplicated InoTable encoding
- ...and add a method to InoTable so that we can
artifically acquire inodes.
Signed-off-by: John Spray <john.spray@red... - 02:09 PM Revision 1dc023b3 (ceph): fix handling of io.read retval
- (it returns length read, which was falling through as
a spurious nonzero "error") - 02:09 PM Revision 5f348313 (ceph): fixup some oversized lines
- 02:09 PM Revision e2ae91fc (ceph): tweak comment wording in recover_dentries
- 02:09 PM Revision 9d917575 (ceph): tools: recover_dentries efficiency
- Avoid a redundant stat, and gather updates to a frag
into a single OMAP get/set.
Still could be heaps more efficient... - 02:09 PM Revision 3e15fd5f (ceph): tools: handle hardlinks in recover_dentries
- Signed-off-by: Johh Spray <john.spray@redhat.com>
- 01:52 PM Revision 46326ffb (ceph): mds: perfcounters for RecoveryQueue
- Define these at MDCache scope, as RecoveryQueue is
not an official subsystem to be made visible to
external parties.
... - 01:06 PM Revision 62b4e439 (ceph): mds/MDCache: stray/purge perfcounters
- Fixes: #10388
Signed-off-by: John Spray <john.spray@redhat.com> - 01:03 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- Sam's proposed update https://github.com/athanatos/ceph/commit/738f8687d5345965b8c725f9d7f7429aaf28f7a9 currently in ...
- 12:00 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- Yeah, the bug appears to be a race between the oi update and recover_primary.
- 11:58 AM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- First, we probably need to not update the oi digest if we are going to repair the object.
- 10:38 AM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- trying to reproduce by running on bare metal http://pulpito.ceph.com/loic-2015-01-19_19:39:07-rados:basic:tasks:scrub...
- 12:34 PM Feature #9440 (Resolved): mon: log all changes to health in the central log
- 12:19 PM Revision 4bd0894c (ceph): Doc: rbd-snapshot: Fix the typo
- Signed-off-by: Frank Yu <flyxiaoyu@gmail.com>
- 11:51 AM Bug #10566 (Duplicate): osd/ReplicatedPG.cc: 8729: FAILED assert(peer_missing.count(fromshard)) f...
- 11:24 AM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same
Run http://pulpito.ceph.com/teuthology-2015-01-16_18:13:02-upgrade:firefly-x-giant-distro-basic-multi/
Jobs [... - 11:21 AM devops Bug #10581 (Rejected): "Error Downloading Packages" in upgrade:firefly-firefly-distro-basic-vps run
- Run http://pulpito.ceph.com/teuthology-2015-01-17_17:00:02-upgrade:firefly-firefly-distro-basic-vps/
Jobs ['708802... - 10:49 AM CephFS Feature #9883 (Resolved): journal-tool: smarter scavenge (conditionally update dir objects)
- Merged in commit:c15f2d5056dedabfb7761b74c8622c61ab1f8477! :)
- 10:41 AM Bug #10534: full-object read crc 0x######## != expected 0x######## on
- Looks like d427ca35404a30e1f428859c3274e030f2f83ef6 reversed the order of localt (which contains the create_collectio...
- 10:41 AM rgw Fix #10569 (Resolved): re-organize utilities and modules in the agent
- merged commit 88a6638 into master from wip-10569
- 08:59 AM rgw Fix #10569 (Fix Under Review): re-organize utilities and modules in the agent
- PR opened https://github.com/ceph/radosgw-agent/pull/18/files
- 07:17 AM rgw Fix #10569 (Resolved): re-organize utilities and modules in the agent
- A lot of exceptions and utilities are in a couple of modules, mainly the client and worker ones.
Moving them into ... - 10:36 AM CephFS Bug #10579 (Resolved): ceph-qa-suite: can't run quota tests on kernel client
- The kclient doesn't support fs quotas. Right now we do so, because the quota test is in ceph/qa/workunits/misc, and t...
- 09:28 AM devops Bug #10575 (Won't Fix): "Error timed out while getting http://apt-mirror.front.sepia.ceph.com"
- Run http://pulpito.ceph.com/teuthology-2015-01-18_17:05:01-upgrade:firefly-firefly-distro-basic-multi/
Jobs ['7094... - 09:04 AM Revision 07e1d18f (ceph): rbd: fix bug about rbd watch command
- the header oid should be prefix+image_id, rather than prefix+image_name
Signed-off-by: Yunchuan Wen <yunchuanwen@ubu... - 08:56 AM rgw Bug #10572: rgw: crash on shutdown, when syncing user stats
- http://pulpito.ceph.com/yehudasa-2015-01-16_13:13:03-rgw-wip-bi-sharding-3---basic-multi/706889/
- 08:55 AM rgw Bug #10572 (Resolved): rgw: crash on shutdown, when syncing user stats
- A crash during shutdown when sync user stats operation is running:...
- 08:41 AM rbd Documentation #10478 (Resolved): Update Glance configuration docs for Juno
- Thanks Sebastien!
commit:d29aef5eb99c2ee807855177ed9ecee7eef37532 - 08:30 AM rgw Bug #10544 (New): "s3tests.functional.test_s3.test_multipart_upload ... FAIL" in upgrade:dumpling...
- 07:45 AM Bug #10517: ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2015-01-18_20:48:05-rados-wip-sage-testing-distro-basic-multi/710841
- 07:37 AM Bug #10517: ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- anothe instance:
0> 2015-01-19 01:42:09.620190 7f348ecef700 -1 ./os/ObjectStore.h: In function 'void ObjectSt... - 07:26 AM CephFS Bug #10413: samba: coredumps after tests run
- Sent to Samba upstream here: https://lists.samba.org/archive/samba-technical/2015-January/104851.html
- 07:25 AM CephFS Bug #10412: samba: failed smbtorture run
- -Sent to samba upstream here: https://lists.samba.org/archive/samba-technical/2015-January/104851.html-
(EDIT: sor... - 07:18 AM rgw Bug #10475: rgw: setting bucket metadata via swift api removes existing metadata
- I've started to work on it.
- 06:42 AM Bug #10425 (In Progress): RadosClient::connect leaks Objecter if called twice
- Cool, thanks. I assign it to myself to track this, let me know if you need any help.
- 05:11 AM Bug #10425: RadosClient::connect leaks Objecter if called twice
- I am working on this bug.
- 05:58 AM CephFS Feature #10390 (In Progress): mds: throttle deletes in flight
- 04:46 AM Revision 751e5042 (ceph): Merge pull request #3397 from liewegas/wip-prealloc
- mon: fix globalid when prealloc value is larger than max
- 04:17 AM CephFS Feature #10388 (In Progress): Add MDS perf counters for stray/purge status
- 12:49 AM Revision bbaf582e (ceph): mon: handle case where mon_globalid_prealloc > max_global_id
- This triggers with the new larger mon_globalid_prealloc value. It didn't
trigger on the existing cluster I tested on...
01/18/2015
- 09:55 PM Revision d29aef5e (ceph): doc: Fix OpenStack Glance configuration
- Glance has not completely moved to 'store' yet so we need to configure
the store in the DEFAULT section as well.
Fix... - 08:43 PM Bug #10525 (Resolved): "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-bas...
- 08:26 PM Bug #10567 (Resolved): Python Ioctx should retain a reference to the cluster object
- The following Python script segfaults:...
- 07:19 PM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- Hi Loic,
I am wondering if this is a good candidate for back-port? Thanks! - 06:44 PM Revision 8379b454 (ceph): Merge pull request #3361 from wonzhq/watch-notify
- osd/ReplicatedPG: force promotion for watch/notify ops
Reviewed-by: Sage Weil <sage@redhat.com> - 06:43 PM Revision f078a429 (ceph): Merge pull request #3395 from liewegas/wip-cache-none
- osd: skip all of maybe_handle_cache if cachemode is none
- 06:42 PM Revision e7f9bffa (ceph): Merge pull request #3315 from majianpeng/fix6
- bug fix
Reviewed-by: Sage Weil <sage@redhat.com> - 06:41 PM Revision ba73ef93 (ceph): Merge pull request #3385 from majianpeng/misc
- Misc
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:41 PM Revision 31eb4c61 (ceph): Merge pull request #3194 from dachary/wip-10350-erasure-code-choose-tries
- resolve and document most common erasure coded pool pain points
Documentation-Reviewed-by: Italo Santos <okdokk@gmai... - 06:39 PM Revision 1d1215fe (ceph): mon: change mon_globalid_prealloc to 10000 (from 100)
- 100 ids (session 100 authentications) can be consumed quite quickly if
the monitor is being queried by the CLI via sc... - 06:37 PM Revision be1416a0 (ceph): mon: silently ignore mark_down, mark_disposable on AnonConnection
- This mirrors 0a49db8e6fa141a36ca964e68017d02b81ae7a3c but was not captured
by 9fff0c53bdc7bb332df1a710da3de71e3c41bec... - 06:37 PM Revision 87b3e960 (ceph): Merge remote-tracking branch 'gh/wip-xio'
- Reviewed-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 78fd69f1 (ceph): Merge pull request #3391 from liewegas/wip-pool-delete
- mon: global option to prevent pool deletion
Reviewed-by: John Spray <john.spray@redhat.com> - 01:57 PM rbd Documentation #10478: Update Glance configuration docs for Juno
- Fix proposed here: https://github.com/ceph/ceph/pull/3396/files
- 10:26 AM Bug #10566 (Duplicate): osd/ReplicatedPG.cc: 8729: FAILED assert(peer_missing.count(fromshard)) f...
- ...
- 10:19 AM Bug #10564 (Duplicate): test/multi_stress_watch.cc: 60: FAILED assert(!ret)
- ...
- 06:27 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- wip-10455 worked in that it allowed me to clean up the unwanted uploads. Unfortunately, I think it was only cosmetic....
- 01:14 AM Revision 8a0d1241 (ceph): crushtool: fix cli tests for new tree output
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:14 AM Revision ea5166ef (ceph): mon/OSDMonitor: drop unnecessary stringify
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:14 AM Revision 9aa00063 (ceph): common/TextTable: do padding during final step
- We don't know the full width until we get all table entries. Do not do
any padding before that. In particular, setw... - 01:14 AM Revision 169d6805 (ceph): mon/OSDMonitor: don't -nan for variance when no osds
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:14 AM Revision b5e1bd1f (ceph): mon/OSDMonitor: pull totals into the table format
- Signed-off-by: Sage Weil <sage@redhat.com>
01/17/2015
- 06:31 PM Revision 46988823 (ceph): osd/ReplicatedPG: skip all of maybe_handle_cache if caching is off
- Return quickly and avoid all of the checks.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:58 PM Revision 871c3ec5 (ceph): crush/CrushWrapper: drop weights from crush dump_tree
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:58 PM Revision 04c09ed2 (ceph): crushtool: add --tree option
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:57 PM Revision 26921f43 (ceph): crush: introduce a helper class for dumping crush tree.
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision 3f9b4d1f (ceph): crush: use CrushTreeDumper for dumping crush tree.
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision 3e2eaa4b (ceph): osd: use CrushTreeDumper for printing osd tree.
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision b42c7e28 (ceph): Add a type (weightf_t) to output float weights.
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision 4bae3a8d (ceph): mon: ceph osd df -- a new command to show OSD utilization
- Fixes: #10452
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 04:57 PM Revision 1d984a52 (ceph): osd: use weightf_t type when outputing weights by osd tree command
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision 9e22f617 (ceph): osd: use TextTable for osd tree command output
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:57 PM Revision 7a045184 (ceph): crush, osdmap: use weightf_t helper for all weights
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:57 PM Revision 022950ec (ceph): crush/CrushTreeDumper: add missing close_section
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:57 PM Revision 86729e79 (ceph): osd, crush: caps for headers
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:21 PM Revision 2970e783 (ceph): Merge pull request #299 from ceph/wip-10538
- Add v0.80.8 to firefly stable suites (issue 10538)
- 01:08 PM Bug #10534: full-object read crc 0x######## != expected 0x######## on
An OP_MKCOLL is being put in out of order. Somehow under simple situations the data somehow gets written, but I as...- 11:52 AM Revision 4d0e0ae3 (ceph): AsyncConnection: Fix memory leak for AsyncConnection
- *_handler will store a reference to AsyncConnection, it need to explicit reset
it.
Signed-off-by: Haomai Wang <haoma...
01/16/2015
- 10:45 PM Revision 78b040ce (ceph): rgw: s/RGWRadosCtx/ObjectCtx
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:45 PM Revision 11a8881c (ceph): Merge pull request #300 from ceph/restore_giant-x_on_master
- Restored giant-x suite on master
- 10:45 PM Revision 19ca3538 (ceph): Merge pull request #301 from ceph/restore_giant-x_on_next
- Restore giant x on next
- 10:42 PM Revision 4c8a5ced (ceph): rgw: change multipart upload id magic
- Fixes: #10271
Backport: firefly, giant
Some clients can't sign requests correctly with the original magic
prefix.
R... - 10:42 PM Revision b10c0d51 (ceph): rgw: url decode http query params correctly
- Fixes: #10271
Backport: firefly
This got broken by the fix for #8702. Since we now only url_decode if
we're in query... - 10:42 PM Revision 24c13d87 (ceph): rgw: change multipart upload id magic
- Fixes: #10271
Backport: firefly, giant
Some clients can't sign requests correctly with the original magic
prefix.
R... - 10:41 PM Revision 617002d3 (ceph): rgw: url decode http query params correctly
- Fixes: #10271
Backport: firefly
This got broken by the fix for #8702. Since we now only url_decode if
we're in query... - 10:41 PM Revision fa5f8325 (ceph): rgw: move RGWRadosCtx into RGWRados
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:41 PM Revision b1dd4a71 (ceph): rgw: initial versioned object removal implementation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:41 PM Revision 1d49393c (ceph): rgw, cls_rgw: don't remove olh objects
- A single head object can contain both olh data, and object data. Don't
remove object if it has olh information on it,... - 10:41 PM Revision 3b1ea1dd (ceph): cls_rgw: allow olh linking to null instance objects
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:41 PM Revision 559e705e (ceph): rgw: set olh if object has been versioned
- Bucket could have versioning suspended, but object has been versioned,
so once object has olh pointer in it, we need ... - 10:41 PM Revision 7f26ab76 (ceph): rgw: request state and various op functionality use rgw_obj_key
- instead of plain string. This is needed so that we use the object
instance in the processing.
Signed-off-by: Yehuda ... - 10:41 PM Revision 674a7543 (ceph): rgw: fix rgw_obj initialization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:41 PM Revision cd13c5af (ceph): cls_rgw: update the appropriate prev key entry
- We need to update the previous key entry that it's no longer the latest,
need to use the list entry, not the data ent... - 10:41 PM Revision 4dadae3b (ceph): rgw, cls_rgw: cls_bucket_list returns raw key in map
- This is needed so that we dump the objects in the required order (from
newest to oldest versions for each object). Wh... - 10:41 PM Revision 1488c032 (ceph): rgw: add support for version-id-marker
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:41 PM Revision 8d25ec63 (ceph): rgw: bucket versioning status is tri-state
- disabled, enabled, suspended.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:40 PM Revision a76e5376 (ceph): Merge remote-tracking branch 'origin/next'
- 10:36 PM Revision 5dfe1526 (ceph): cls_rgw: deletion marker needs to keep instance entry
- Otherwise we wouldn't be able to find it when we remove it.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision 105ba489 (ceph): rgw: propagate dirent flags to rgw (from cls), other fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision debee800 (ceph): rgw: restful api now dumps versions
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision 1dcdea37 (ceph): rgw: cleanup, get rid of req_state::object
- We don't want this extra memory allocation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision 303db77a (ceph): rgw: object manifest should reflect instance
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision 337e5236 (ceph): rgw: add 'versioning', and 'versions' to handled subresources
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision bde5a8a1 (ceph): rgw: add get_type() to rgw ops
- This is needed so that we can identify ops correctly.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision bb649ff4 (ceph): cls_rgw: revise the data model
- We don't need to keep a listing entry for the olh.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision 9cf200c1 (ceph): rgw: bucket listing gets extra param for versioning
- Can specify whether we want to see versions or not.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision 9e3065b4 (ceph): rgw, cls_rgw: list object versions is optional
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision cb94d55c (ceph): rgw: more atomicity fixes, set_olh()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision 7a086195 (ceph): rgw: tie set_olh() to object completion
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision bc4dd1f5 (ceph): cls_rgw: olh trim op is read/write
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision 983c68e4 (ceph): rgw: follow olh if needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision 8819b387 (ceph): rgw: update json encoding for rgw_obj
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:36 PM Revision fb45e059 (ceph): rgw: olh atomicity groundwork
- still more to do
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:36 PM Revision bf9d319e (ceph): rgw: guard against racing writes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:34 PM Revision 5471e87a (ceph): Added "force-branch: firefly-original" to make sure we run on good s3te...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:33 PM Revision 896c8899 (ceph): Merge remote-tracking branch 'origin/wip-10271' into next
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
- 10:33 PM Revision 67b73a98 (ceph): rgw, cls_rgw: trim olh log functionality
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 1802136b (ceph): rgw: apply olh log functionality
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision b5c54f07 (ceph): cls_rgw: olh init op
- Need an op to initialize olh when a new olh is created. It will set its
initial version and tag.
Signed-off-by: Yehu... - 10:33 PM Revision 2d86a68d (ceph): rgw: implement rgw_bucket_olh_log_entry::dump()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision d669a7e7 (ceph): rgw-admin: add olh readlog command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision b11551e8 (ceph): rgw: new api to retrieve olh log
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision b2490b54 (ceph): rgw: bucket index link olh interface
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision da05386e (ceph): cls_rgw: object instance olh linking
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision bf115941 (ceph): cls_rgw: bucket index link olh
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 928b2561 (ceph): cls_rgw: prepare groundwork for olh
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 038073f7 (ceph): cls_rgw: encode / decode obj and list index keys
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 16b5c82d (ceph): rgw: obj_stat() follows on olh
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision f32ceaee (ceph): rgw: some code cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 988310cd (ceph): rgw: init olh tag
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision d139f8dd (ceph): rgw: gen rand lowercase string (stl string version)
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision da98d133 (ceph): rgw: adjust return code when generating random strings
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision 57629b30 (ceph): rgw: initial olh implementation
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:33 PM Revision f6bb8255 (ceph): rgw: gen rand lower alphanumberic string
- add a function to generate a random lowercase string, don't want other
characters.
Signed-off-by: Yehuda Sadeh <yehu... - 10:33 PM Revision cb658266 (ceph): rgw: remove old unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:32 PM Revision b2ea8e8f (ceph): rgw: interface adjustment following a rebase
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:32 PM Bug #10534: full-object read crc 0x######## != expected 0x######## on
- 07:12 PM Bug #10534: full-object read crc 0x######## != expected 0x######## on
I reproduced this without snapshots and found a case where a single replica on a single osd was bad. A touch, writ...- 10:26 PM Revision 68af4a24 (ceph): rgw: generate random instance id
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:26 PM Revision 8941d6ff (ceph): rgw: clean up some locator use
- We don't use locators anymore. New objects are always created having the
locator equals to the object name. Don't all... - 10:26 PM Revision 6979c70c (ceph): radosgw-admin: some commands use object_version param
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:26 PM Revision 54f2e0ac (ceph): rgw: adapt to new objclass interface
- use rgw_obj_key instead of string, and pass it on to the objclass.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:26 PM Revision 36978037 (ceph): radosgw-admin: adapt to new interfaces
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:26 PM Revision 6c930f99 (ceph): test: cls_rgw fixes
- adapt to new objclass interfaces
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:24 PM Revision fe435a68 (ceph): rgw: rename cls_rgw_obj::key to cls_rgw_obj::loc
- to avoid confusion.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:24 PM Revision 840b0862 (ceph): cls_rgw: change data structures to keep single object key structure
- instead of keeping the key name and instance separately. Also, translate
key structure into the index key string repr... - 10:24 PM Revision cb3694fb (ceph): rgw, cls_rgw: various datastructures use new rgw_obj_key
- Instead of using a string for referencing object's index key, use a
rgw_obj_key structure that's also references the ... - 10:18 PM Revision 99da88c9 (ceph): rgw: rename rgw_obj::key to rgw_obj::loc
- to avoid confusion
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:18 PM Revision 201467df (ceph): rgw: remove unused code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:18 PM Revision 45586aa2 (ceph): rgw: decouple object name from index representation
- We can't have a direct mapping between the object name to the way we
index it in the bucket index. Have rgw_obj provi... - 10:18 PM Revision 20c45eba (ceph): rgw, cls_rgw: add accounted_size for object metadata entry
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:18 PM Revision b383b52d (ceph): rgw: enable s3 get/set versioning ops
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:17 PM Revision 0d97b40a (ceph): rgw: get bucket versioning status op
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:17 PM Revision 7cd5e9d9 (ceph): rgw: restful op to set bucket versioning
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:12 PM Revision 8ed79d66 (ceph): rgw: add versioning_enabled field to bucket info
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:08 PM Revision a845139d (ceph): Merge pull request #3292 from kylinstorage/rbd-merge-diff-v2
- rbd: merge diff files
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 07:48 PM Revision 927a9905 (ceph): Restored giant-x on next
- Signed-off-by: Yuri Weinstein <yuriw@magna002.ceph.redhat.com>
- 07:46 PM Revision 21a4afc2 (ceph): Restored giant-x suite on master
- Signed-off-by: Yuri Weinstein <yuriw@magna002.ceph.redhat.com>
- 06:36 PM Revision 92319316 (ceph): Merge pull request #3318 from XinzeChi/wip-scrub
- osd: support schedule scrub between some time defined by users
Reviewed-by David Zafman <dzafman@redhat.com> - 06:32 PM Revision a1f3fdc8 (ceph): Merge pull request #3090 from ceph/wip-mon-fixes
- mon: fix issues with mixed-version monitors features
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Joao Ed... - 06:12 PM Revision 50547dc3 (ceph): mon: PGMonitor: fix division by zero on stats dump
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 05:12 PM Revision dbaa1420 (ceph): rgw: bilog marker related fixes
- Fix the way we parse the marker. Instead of specifying whether it's a
sharded or not sharded bucket, we pass a shard_... - 04:51 PM Revision eee9da43 (ceph): Merge pull request #3390 from ceph/wip-librbd-coverity
- librbd: fix coverity false-positives for tests
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:41 PM Revision c4548f68 (ceph): pybind: ceph_argparse: validate incorrectly formed targets
- Prior to this patch find_cmd_target() would perform the following
parsing for any given command:
- check if it's a "... - 04:34 PM Revision ab996c14 (ceph): mon: Elector: output features in handle_propose()
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 04:34 PM Revision 80a9d998 (ceph): mon: Monitor: return 'required_features' on get_required_features()
- We were returning 'quorum_features' instead. This would lead to funny
and weird behavior. I hate funny.
Backport: ... - 04:34 PM Revision bb48ebe1 (ceph): mon: Elector: put dangling message reference
- Backport: emperor,firefly,giant
Signed-off-by: Joao Eduardo Luis <joao@redhat.com> - 04:33 PM Revision 0a369b9b (ceph): mon: mkfs compatset may be different from runtime compatset
- When we create a monitor we set a given number of compat features on
disk to clearly state the features a given monit... - 03:54 PM Revision 6b982e4c (ceph): mon/OSDMonitor: require mon_allow_pool_delete = true to remove pools
- This is a simple safety check. Since we default to true it is currently
opt-in.
Backport: giant, firefly
Signed-off... - 03:53 PM devops Bug #10511: "test.functional.tests.TestAccount" fail in upgrade:firefly-x-next-distro-basic-multi...
- And one more failure here - http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-14_18:13:01-upgrade:firefly-x-gian...
- 03:39 PM Bug #10430: osd/osd_types.cc: 456: FAILED assert(m_seed < old_pg_num)
- possibly a similar problem in the objecter: #10399
- 03:37 PM Bug #10543 (Duplicate): "FAILED assert(m_seed < old_pg_num)" in upgrade:giant-x-hammer-distro-bas...
- 03:34 PM Bug #10543: "FAILED assert(m_seed < old_pg_num)" in upgrade:giant-x-hammer-distro-basic-vps run
- Same problem in http://pulpito.ceph.com/teuthology-2015-01-13_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Jobs... - 02:47 PM rgw Bug #10271 (Resolved): Radosgw urlencode
- 02:43 PM rgw Bug #10271 (Pending Backport): Radosgw urlencode
- 02:42 PM rgw Bug #10271 (Resolved): Radosgw urlencode
- 01:20 PM Stable releases Tasks #10560 (Rejected): dumpling v0.67.12
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 12:33 PM Stable releases Tasks #10501 (In Progress): giant v0.87.1
- 12:01 PM Feature #10559 (Resolved): add a norebalance flag
- During peering, normally, the primary chooses the best acting set possible, and then starts a backfill to move that a...
- 11:33 AM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- ...
- 11:32 AM Bug #10524 (In Progress): FAILED assert(peer_missing.count(fromshard))
- 08:30 AM Bug #10524 (Need More Info): FAILED assert(peer_missing.count(fromshard))
- 05:42 AM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- https://github.com/ceph/ceph/pull/3389 will provide more information about the problem the next time it happens. I un...
- 11:23 AM Revision b20ea5a2 (ceph): tests: centos7 needs nc to run make check
- It is not added to ceph.spec.in because the requirement disapeared after
firefly.
Signed-off-by: Loic Dachary <ldach... - 10:49 AM Revision 28f8b132 (ceph): Merge pull request #3384 from liewegas/wip-crush-tests
- crush: minor reorg of crush unit tests
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:43 AM devops Bug #10532: Failed "joining thrashosds" - suspected low memory config on vps
- See the same in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-13_17:18:01-upgrade:firefly-x-next-distro-basi...
- 09:10 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Yes, I had no assumption to make a fix for a cuttlefish on purpose. I asked Mike (as he running newer release) to com...
- 09:07 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Hi Andrey, that does look like this bug on cuttlefish. We haven't been backporting anything to cuttlefish for a long ...
- 08:29 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Hi, another cephx crash (vm90277.bt.txt). Lines are related to latest cuttlefish and this crash appears for a first t...
- 08:49 AM Revision 3ee69e3b (ceph): osd: fix journal header.committed_up_to
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 08:31 AM Revision e85197c6 (ceph): test: add test for osd scrub
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 08:30 AM Revision f4b94e05 (ceph): osd: support schedule scrub between some time defined by users
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 08:14 AM Revision 881fe330 (ceph): test: Using different filename for different test case.
- Some test case use tmp file to test.But they used same file and create
in the same directory. If we do in parallel, i... - 07:24 AM Revision d7ccf71d (ceph): qa: ignore duplicates in rados ls
- These can happen with split or with state changes due to reordering
results within the hash range requested. It's eas... - 07:20 AM Revision 65bf3b08 (ceph): qa: ignore duplicates in rados ls
- These can happen with split or with state changes due to reordering
results within the hash range requested. It's eas... - 06:19 AM Revision 1511198f (ceph): Striep: s/OSDExtent/ObjectExtent
- OSDExtent already removed.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Signed-off-by: Jianpeng Ma <jianpeng.m... - 06:18 AM Revision bb582d92 (ceph): librados: clean up code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:18 AM Revision 7cfdba24 (ceph): librbd: clean up code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 05:58 AM Revision 2a4cbfcc (ceph): Merge pull request #3335 from ceph/wip-cephfs-tabletool
- Create cephfs-table-tool
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:54 AM Revision a60b815c (ceph): Merge pull request #3383 from ceph/wip-10552
- client: fix getting zero-length xattr
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:47 AM Revision 87d10d39 (ceph): Merge pull request #3358 from ceph/wip-mon-propose
- mon: improve paxos proposals
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 05:45 AM Revision bed740bb (ceph): Merge pull request #3342 from ceph/wip-10311
- rgw: only keep track for cleanup of rados objects that were written
Reviewed-by: Ray Lv <xiangyulv@gmail.com> - 05:24 AM Revision 2da23116 (ceph): Merge pull request #3362 from FrankYu/master
- Doc: Fix the indentation in doc/rbd/rbd-snapshot.rst
- 05:15 AM Revision aed937ca (ceph): Merge pull request #3346 from timfreund/update-radosgw-python-swift-exa...
- doc: Replace cloudfiles with swiftclient in Python Swift example
- 05:13 AM Revision 15112cc3 (ceph): Merge pull request #3359 from ceph/wip-mon-converter
- drop ceph_mon_store_converter
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 05:13 AM Revision 441d0aa7 (ceph): Merge pull request #3373 from jdurgin/wip-rados-ls-dups
- qa: ignore duplicates in rados ls
Reviewed-by: Sage Weil <sage@redhat.com> - 05:10 AM Revision 7372ac7a (ceph): crush: move two crush tests over
- CrushWrapper handles map manipulation, crush.cc tests the placement.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:06 AM Revision ddb91b2f (ceph): crush: rename unit tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:56 AM Linux kernel client Bug #10450 (Resolved): NULL pointer dereference at send_mds_reconnect
- 02:41 AM Revision 7e1553ce (ceph): rgw: fix partial GET in swift
- Fixes: #10553
backport: firefly, giant
Don't set the ret code to reflect partial download, just set the
response sta... - 02:26 AM Revision e7d5fddc (ceph): client: fix getting zero-length xattr
- Fixes: #10552
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:26 AM Revision 3eceda9f (ceph): Merge pull request #3378 from xinxinsh/wip-cleanup
- cleanup unused varibles
Reviewed-by: Sage Weil <sage@redhat.com> - 01:12 AM Revision 97c18813 (ceph): osd/PG: do not republish unchanged pg stats
- If the PG stats have not changed, do not republish. Note that previously
we would gratuitously update the timestamp;... - 01:12 AM Revision 65d3342a (ceph): osd/osd_types: add operator== for pg stat types
- Tedious, but necessary.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:12 AM Revision d2e10494 (ceph): osd/PG: avoid most of publish_stats_to_osd for non-primary
- No need to take the lock in the non-primary case. Just make sure we reset
the valid flag so that it is always false ... - 12:45 AM Revision ea153c3f (ceph): mds: abstract SessionMapStore from SessionMap
- This is similar to what I did for InodeStore a while back:
introduce a logical separation between the persisted attri... - 12:45 AM Revision b8ffe5c2 (ceph): mds: give MDSTables a `rank` attribute
- ...so that they (like the new SessionMapStore)
can be used outside of a live MDS in tool code.
Signed-off-by: John S... - 12:45 AM Revision 2f316063 (ceph): tools: create cephfs-table-tool
- It was unnatural to shoehorn resetting tables
into the journaltool. This new tool initially
can simply dump or reset... - 12:40 AM Revision aef69572 (ceph): Merge branch 'wip-firefly-rgw-backports' into firefly
- 12:01 AM Feature #10555 (Resolved): Don't allow empty pool names
- Currently you can create pools with a empty name:...
- 12:00 AM Bug #10554 (Resolved): init: ceph-osd (...) main process (...) killed by ABRT signal- Erasure cod...
- We are creating Erasure coded cluster with 15 nodes and each node has 36 drives. we are able to create the healthy er...
01/15/2015
- 10:27 PM Revision 1b01399a (ceph): Fixed typos
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:26 PM CephFS Bug #10368: Assertion in _trim_expired_segments
- one possible cause:
there are more than one contexts in mdlog's wait_for_safe list. there is a context executed af... - 07:52 AM CephFS Bug #10368: Assertion in _trim_expired_segments
Had no joy reproducing with mds_auto_repair more recently (on diff. test nodes), but did manage on a vstart cluster...- 10:14 PM Revision cbfa98f8 (ceph): Added new v0.80.8 to
- /newer
singleton/version
singleton/version-x
Added more logging
Signed-off-by: Yuri Weinstein <yuri.weinstein@inktan... - 10:01 PM Revision b1d9f602 (ceph): Merge pull request #288 from dmick/master
- Tweaks to calamari-setup
- 09:53 PM CephFS Bug #10552 (Resolved): ceph-fuse: failed bufferlist assert when reading xattrs
- Thanks Zheng. Merged to master in commit:a60b815c85f07d7ac10b6d23fd1618c6334ddcf7.
- 06:25 PM CephFS Bug #10552 (Fix Under Review): ceph-fuse: failed bufferlist assert when reading xattrs
- triggered by new test case
- 10:53 AM CephFS Bug #10552: ceph-fuse: failed bufferlist assert when reading xattrs
- That assert is from 2013, by the way; I'm not sure what we might have changed to break it. :/
- 10:52 AM CephFS Bug #10552 (Resolved): ceph-fuse: failed bufferlist assert when reading xattrs
- ...
- 09:44 PM rgw Bug #10311 (Pending Backport): Object is deleted automatically if conditional PUT returns 412
- 09:44 PM rgw Bug #10311 (Resolved): Object is deleted automatically if conditional PUT returns 412
- 08:30 PM Revision d8d608d6 (ceph): erasure-code: update links to jerasure upstream
- It moved from bitbucket to jerasure.org
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 08:26 PM Revision dac666f7 (ceph): erasure-code: tests use different pool/profile names
- Use different erasure coded pool names and profiles to avoid deletion /
creation races. The more expensive alternativ... - 08:26 PM Revision 4d07a32e (ceph): crush: update tries statistics for indep rules
- http://tracker.ceph.com/issues/10349 Fixes: #10349
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 08:26 PM Revision 2f87ac80 (ceph): crush: set_choose_tries = 100 for erasure code rulesets
- It is common for people to try to map 9 OSDs out of a 9 OSDs total ceph
cluster. The default tries (50) will frequent... - 08:26 PM Revision 8b64fe93 (ceph): erasure-code: set max_size to chunk_count() instead of 20
- The ruleset created for an erasure coded pool has max_size set to a
fixed value of 20, which may be incorrect when mo... - 08:26 PM Revision 02cab93f (ceph): documentation: add troubleshooting erasure coded PGs section
- Add a new section to the PG troubleshooting section that covers the most
common problems reported when an erasure cod... - 08:26 PM Revision 6c345282 (ceph): erasure-code: update jerasure/gf-complete submodules
- jerasure:
git log --no-merges --pretty=%s \
8fe20c6608385d6a1f38db89aec5cba85ccf04ac..02731df4c1eae1819c4453c9d3ab... - 07:51 PM Bug #9971: OSD crashes again after restarting due to op thread time out at writing pg dirty log
- Hi Samuel:
After further investigation, we've identified this problem as a very big transaction(thousands ops in o... - 07:36 PM Bug #9971 (New): OSD crashes again after restarting due to op thread time out at writing pg dirty...
- Hi Sam,
We came across of this issue a couple of times and Dong Lei did some analysis, Dong will provide more detail... - 07:46 PM Revision c3fb34c1 (ceph): Merge pull request #3380 from trhoden/doc_cephextras
- doc: add cases where ceph-extras is not needed
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 07:40 PM Revision fc01b010 (ceph): doc: add cases where ceph-extras is not needed
- The Ceph Extras repo is not needed on EL7 distributions or
Fedora
http://tracker.ceph.com/issues/9793 Refs: #9793
S... - 07:23 PM Revision f24f646d (ceph): ceph_objectstore_tool: Check that pool exists before allowing import
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision b1f12f09 (ceph): ceph_objectstore_tool: Add special exit code for test infrastructure
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision 19fdeea8 (ceph): ceph_objectstore_tool: Check for splits and fail import if there were s...
- Add osdmap into metadata_section
On export put metadata_section before file data
Fixes: #9780
Signed-off-by: David ... - 07:23 PM Revision f34b930b (ceph): ceph_objectstore_tool: Fixes to not encode OSDMap due to CRC checking
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision da3be804 (ceph): ceph_objectstore_tool: Verify that object pool and pgid pool match
- Also, earlier check for invalid --pgid with import op
Signed-off-by: David Zafman <dzafman@redhat.com> - 07:23 PM Revision 68b27e25 (ceph): ceph_objectstore_tool: On import following a split skip objects no long...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision afda6e4f (ceph): ceph_objectstore_tool: Handle import of pg which OSD has split
- Fail import if import data doesn't include OSDMap and can't find it locally
See if local map can be read for import's... - 07:23 PM Revision 05d916ed (ceph): ceph_objectstore_tool: For import get object_info_t available for each ...
- Add object_info_t to object_begin so we have at object create time
This will be useful for importing from multiple er... - 07:23 PM Revision b9a04846 (ceph): osd: build_push_op() handle short reads so recipient doesn't crash
- Fixes: #8121
Signed-off-by: David Zafman <dzafman@redhat.com> - 07:23 PM Revision 7fb721c1 (ceph): osd: Pass oldest_map when generating past intervals
- From load_pgs() the superblock hasn't been published yet
so we need to retrieve the value of oldest_map depending on ... - 07:23 PM Revision 0c5b66da (ceph): osd: Get pgid ancestor from last_map when building past intervals
- Fixed OSD::build_past_intervals_parallel() and PG::generate_past_intervals()
Fixes: #10430
Signed-off-by: David Zaf... - 07:23 PM Revision 2dc29deb (ceph): ceph-objectstore-tool, test: Fix objectstore name changed to keyvaluestore
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision 22b71744 (ceph): ceph-objectstore-tool: Remove --pretty-format and use new --format options
- Call new_formatter() with --format specified argument
Signed-off-by: David Zafman <dzafman@redhat.com> - 07:23 PM Revision 3de2d3bf (ceph): ceph_objectstore_tool: validate pgid before calling PG::_has_removal_fl...
- The "meta" directory could be removed when trying to removing pgid 0.0
Signed-off-by: David Zafman <dzafman@redhat.com> - 07:23 PM Revision 5cb69252 (ceph): ceph_objectstore_tool: read_fd() doesn't handle ^D from tty stdin, don'...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision fe936026 (ceph): ceph_objectstore_tool: Fix import-rados skipping of snapshots
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision ddc4613e (ceph): ceph_objectstore_tool: Get g_ceph_context available to import-rados
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision f727d2ea (ceph): ceph_objectstore_tool: import-rados shouldn't import internal namespace...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision 62dd912f (ceph): ceph_objectstore_tool: Allow the metadata_section to be anywhere in the...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:23 PM Revision 196c8112 (ceph): ceph_objectstore_tool: Check cluster_fsid before allowing an import
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:22 PM Revision 062d3b02 (ceph): Merge pull request #3379 from ceph/wip-mon-drop-conversion
- mon: drop store conversion code
Reviewed-by: Sage Weil <sage@redhat.com> - 07:21 PM Revision 11062d2f (ceph): Merge pull request #3377 from ceph/wip-fail-idempotent
- mon/MDSMonitor: make 'mds fail' idempotent for IDs
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:20 PM Revision 80473f63 (ceph): os/FileJournal: Fix journal write fail, align for direct io
- when config journal_zero_on_create true, osd mkfs will fail when zeroing journal.
journal open with O_DIRECT, buf sho... - 07:13 PM Revision cc0dba52 (ceph): mon: encode stashed monmap with all features
- latest_monmap that we stash is only used locally--the encoded bl is never shared. Which means we should just use CEPH...
- 07:07 PM Revision 7bb7b1ec (ceph): AsyncConnection: Fix deadlock if socket failed when replacing
- If client reconnect a already mark_down endpoint, server-side will detect
remote reset happen, so it will reset exist... - 07:07 PM Revision c65df9b5 (ceph): test_msgr: Add SyntheticInjectTest
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 2bc16752 (ceph): AsyncConnection: Don't discard out_q and unregister when replacing
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 296e5457 (ceph): AsyncConnection: Fix replacing cause original state lossy
- Because AsyncConnection won't enter "open" tag from "replace" tag,
the codes which set reply_tag won't be used when e... - 07:07 PM Revision 898d43db (ceph): async: adjust test_msgr and normalize log output format
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision f7f25b4c (ceph): AsyncConnection: Don't increment connect_seq if connect failed
- If connection sent many messages without acked, then it was marked down.
Next we get a new connection, it will issue ... - 07:07 PM Revision bd627e77 (ceph): Event: Fix typo
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision e823af41 (ceph): AsyncConnection: Don't alloc buffer when reenter "READ_FRONT" state
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 4b900a6f (ceph): test_msgr: Add SyntheticWorkload to do message measurement
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 2f923836 (ceph): Event: Fix incorrect memset
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision a1753902 (ceph): AsyncConnection: set state_offset=0 in case of reuse this connection
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 50771dd7 (ceph): AsyncConnection: Enhance replace process
- Make handle_connect_msg follow lock rule: unlock any lock before acquire
messenger's lock. Otherwise, deadlock will h... - 07:07 PM Revision a75ac0ea (ceph): AsyncConnection: Add ms_inject_* to AsyncConnection
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision e84d1344 (ceph): AsyncConnection: Add omissive STATE_WAIT state
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision e7db9114 (ceph): AsyncMessenger: wait for dispatch event done
- In order to avoid deadlock like:
1. mark_down_all with holding lock
2. ms_dispatch_reset
3. get_connection want to ge... - 07:07 PM Revision 9a84a905 (ceph): test_msgr: Add random usleep to Dispatcher impl
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 34cbd4c7 (ceph): AsyncConnection: Avoid calling callback after delteing AsyncMessenger
- Now when calling mark_down/mark_down_all, it will dispatch a reset event.
If we call Messenger::shutdown/wait, and it... - 07:07 PM Revision 9fc24d4e (ceph): test_msgr: Add test for a message with large payload
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision 0a7c331c (ceph): AsyncMessenger: allow RESETSESSION whenever we forget an endpoint
- Learn from SimpleMessenger(8cd1fdd7a778eb84cb4d7161f73bc621cc394261)
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> - 07:07 PM Revision abb4e682 (ceph): AsyncMessenger: Retry binding on addresses if binding fails
- Learn from commit(2d4dca757eaa7572ed4d8a1c798c9c09e5ada3d7) for
SimpleMessenger:
If binding on a IP-Address fails, d... - 07:07 PM Revision 24fd12f4 (ceph): MessengerTest: Add markdown with caller lock tests
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision a98b9e2f (ceph): AsyncConnection: Fix mark_down race condition
- Previously, if caller want to mark_down one connection and caller is event
thread callback, it will block for the wak... - 07:07 PM Revision 44a01894 (ceph): AsyncConnection: using send_keepalive instead of _send_keepalive_or_ack
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision cb3e1bf4 (ceph): AsyncConnection: Adjust backoff wakeup granularity
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:07 PM Revision f4fcff16 (ceph): AsyncMessenger: Bind async thread to special cpu core
- Now, 2-4 async op thread can fully meet a OSD's network demand with SSD
backend. So we can bind limited thread to spe... - 07:07 PM Revision 8d2af2fa (ceph): AsyncMessenger: Using EventCenter instead of poll for bind
- Totally avoid extra thread in AsyncMessenger now. The bind socket will be
regarded as a normal socket and will dispat... - 07:07 PM Revision d93bdade (ceph): AsyncConnection: Using buffer read to avoid small read overhead
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:00 PM CephFS Bug #10415 (Resolved): libcephfs: test failures
- 06:53 PM CephFS Feature #10504: kclient: include client version in client_metadata
- pushed a kernel patch to testing branch
- 06:46 PM Revision 0aeba0f2 (ceph): ceph_objectstore_tool: Describe super_ver values
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 06:27 PM rgw Bug #10553 (Fix Under Review): rgw: fail to download object in swift when range specified > 512k
- 04:06 PM rgw Bug #10553 (Resolved): rgw: fail to download object in swift when range specified > 512k
- 06:10 PM Revision d91fe8b3 (ceph): test_shared_cache::get_next: fix get_next call on uninitialized value
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:10 PM Revision 37dc4238 (ceph): shared_cache: reduce duplication between get_next's
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 05:54 PM CephFS Bug #10413: samba: coredumps after tests run
- samba guys proposes a fix on their side, the new fix should go into upstream soon
- 05:33 PM Revision 9db59697 (ceph): fix command 'ceph pg dump_stuck degraded'
- undersized not valid: undersized not in inactive|unclean|stale
undersized not valid: undersized doesn't represent a... - 05:06 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- * The file content change while the OSD is running
* deep-scrub / repair does notice something is wrong but does *no... - 02:12 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- This is what should happen...
- 12:54 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- The difference between the bad and the good log is that the object to be repaired is on the primary for the bad and o...
- 10:12 AM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- Maybe the problem is that recovery should not try to recover an object that's already repaired ?
- 04:22 PM Bug #10534: full-object read crc 0x######## != expected 0x######## on
- Also seen as a corrupt test file:
2015-01-15 12:19:05,431.431 INFO:tasks.rados.rados.0.plana02.stderr:1718: oid 1 ... - 11:42 AM Bug #10534: full-object read crc 0x######## != expected 0x######## on
The yaml file that reproduced this issue:...- 04:06 PM Revision 34081562 (ceph): mon: Monitor: drop StoreConverter code
- We no longer convert stores on upgrade. Users coming from bobtail or
before sould go through an interim version such... - 04:02 PM Revision 1d814b76 (ceph): ceph_mon: no longer attempt store conversion on start
- People upgrading from bobtail or previous clusters should first go
through an interim version (quite a few to pick fr... - 04:01 PM Revision a385a8d1 (ceph): Merge pull request #6 from lebauce/rbd-fixes
- rbd: RBD fixes
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 03:11 PM Revision d4a64474 (ceph): Merge pull request #3376 from dachary/wip-10547-formatter
- common: restore format fallback semantic
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:58 PM Revision 447d4699 (ceph): mon: Monitor: health to clog writes every X seconds on the second
- 3600 will mean every hour, on the hour; 60 will mean every minute, on
the minute. This will allow the monitors to sp... - 02:58 PM Revision 7ce770d9 (ceph): mon: Monitor: health summary to clog on get_health()
- Output health summary to clog on Monitor::get_health() (called during,
e.g., 'ceph -s', 'ceph health' and alikes) if ... - 02:58 PM Revision e2d66ae3 (ceph): mon: Monitor: 'get_health()' returns overall health status
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 02:58 PM Revision 81a2faf3 (ceph): mon: Monitor: write health status to clog every X seconds
- Instead of writing the health status only when a user action calls
get_health(), have the monitor writing it every X ... - 02:58 PM Revision fcd7aa00 (ceph): mon: Monitor: reset health status cache on _reset()
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 02:58 PM Revision ae1032e2 (ceph): mon: Monitor: cache 'summary' string to avoid dups on clog
- By caching the summary string we can avoid writing dups on clog.
We will still write dups every 'mon_health_to_clog_... - 02:49 PM devops Bug #10549 (Resolved): 'sudo yum -y install xx 0.80.6" issues on centos, debian, rhel
- This is an issue that has plagued us where the original sha1 is compiled before the tag is pushed and thus the built ...
- 10:09 AM devops Bug #10549 (Resolved): 'sudo yum -y install xx 0.80.6" issues on centos, debian, rhel
- Run http://pulpito.front.sepia.ceph.com/teuthology-2015-01-14_17:00:03-upgrade:firefly-firefly-distro-basic-vps/
J... - 02:23 PM Revision 889969e2 (ceph): mon/MDSMonitor: make 'mds fail' idempotent for IDs
- Was returning ENOENT, should succeed for 'fail' on
a non-existent name, as the fail operation makes
it cease to exist... - 02:19 PM Revision edd90900 (ceph): rbd: add tests for read/write and snapshots
- 02:18 PM Revision 5671536b (ceph): rbd: clean images and pools in tests
- 02:15 PM Revision 75e9c455 (ceph): rbd: fix error handling for write, seek and flush
- 02:13 PM Revision 921a14b1 (ceph): rbd: fix calls to wrong C functions
- 01:30 PM rgw Bug #10544: "s3tests.functional.test_s3.test_multipart_upload ... FAIL" in upgrade:dumpling-x-fir...
- 12:29 PM Revision b957fa8e (ceph): tests: adapt to new json-pretty format
- The json-pretty format was modified for readability and now includes
additional newlines / spaces. Either switch to j... - 12:27 PM Revision 97609a33 (ceph): test: rename test_activate_osd
- It was incorrectly shadowing test_run_osd.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 12:26 PM Revision 8d8ce96b (ceph): common: restore format fallback semantic
- When Formatter::create replaced new_formatter, the handling of an
invalid format was also incorrectly changed. When a... - 12:16 PM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- ...
- 11:54 AM Revision a6cb7470 (ceph): Merge pull request #3370 from ceph/wip-10382
- mds: handle heartbeat_reset during shutdown
- 11:04 AM CephFS Bug #9994: ceph-qa-suite: nfs mount timeouts
- This continues to be a problem; e.g. http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-11_23:10:01-knfs-next-tes...
- 10:20 AM CephFS Bug #10550 (Resolved): Assertion in ceph-mds on failures in ::init
init() can call suicide in various error handling paths before it starts progress thread, but in suicide() it tries...- 10:14 AM Revision e9aeaf81 (ceph): mailmap: Loic Dachary name normalization
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 10:14 AM Revision d80ded9d (ceph): mailmap: David Zhang affiliation
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 09:02 AM Stable releases Tasks #10501 (Rejected): giant v0.87.1
- 08:10 AM Bug #6301: ceph-osd hung by XFS using linux 3.10
- Is this with 64k directories ?
We don't have the problem anymore - all our OSD now use standard xfs format - (that... - 08:01 AM Feature #9792: make it harder to remove cluster data pools
- This would be a great addition.
A interval should be configureable for how long a pool stays in 'pending' mode. By... - 07:25 AM Bug #10547 (Resolved): test/crush/TestCrushWrapper.cc:853: Failure
- 04:41 AM Bug #10547 (Fix Under Review): test/crush/TestCrushWrapper.cc:853: Failure
- https://github.com/ceph/ceph/pull/3376
- 02:29 AM Bug #10547 (Resolved): test/crush/TestCrushWrapper.cc:853: Failure
- Introduced in https://github.com/ceph/ceph/pull/3366...
- 05:06 AM Revision 33ba23f0 (ceph): common/shared_cache.hpp: empty() iff weak_refs is empty
- Also, add a comment to clarify usage.
Signed-off-by: Samuel Just <sjust@redhat.com> - 05:06 AM Revision 4b47886c (ceph): ReplicatedPG: on_chnage: clarify object_contexts.clear() comment
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:47 AM Revision d532f3ed (ceph): remove unused hold_map_lock in _open_lock_pg
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 02:31 AM Revision 97486559 (ceph): man: add help for rbd merge-diff command
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: Li Wang <liwang@ubuntukylin.com> - 01:36 AM Revision 6fb5e093 (ceph): rbd: fix test
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:32 AM Revision 9a1b29d0 (ceph): Merge remote-tracking branch 'lb/newrbd'
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:30 AM Revision f5bfcec1 (ceph): fix go-rados -> go-ceph renames
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:41 AM Revision 6986ec1c (ceph): osd/PG: populate blocked_by with peers we are trying to activate
- Once peering finishes, all osds need to persist their info and ack before
we are fully active. Populate blocked_by w...
01/14/2015
- 11:51 PM Revision 79bfffb5 (ceph): rgw: remove swift user manifest (DLO) hash calculation
- Fixes: #9973
Backport: firefly, giant
Previously we were iterating through the parts, creating hash of the
parts eta... - 11:51 PM Revision fd49cbc5 (ceph): rgw: use s->bucket_attrs instead of trying to read obj attrs
- Fixes: #10307
Backport: firefly, giant
This is needed, since we can't really read the bucket attrs by trying to
read... - 11:51 PM Revision 534624b7 (ceph): init-radosgw.sysv: set ulimit -n before starting daemon
- If we do the ulimit inside the daemon command we will have already
dropped privs and will fail.
Fixes: #9587
Backpor... - 11:51 PM Revision 2d61fc76 (ceph): rgw: S3 object copy content type fix
- Fixes: #9478
Backport: firefly, giant
Content type for S3 object copy response should be set to
application/xml.
Sig... - 11:51 PM Revision 8682d1b1 (ceph): rgw: send back ETag on S3 object copy
- Fixes: #9479
Backport: firefly, giant
We didn't send the etag back correctly. Original code assumed the etag
resided ... - 11:51 PM Revision 31f5e332 (ceph): rgw: RGWRados::get_obj() returns wrong len if len == 0
- Fixes: #9877
We only updated if len was > 0, should update it if r >= 0. This was the
culprit for issue #9877.
Backpo... - 11:51 PM Revision 30963fdc (ceph): rgw: rados->set_attrs() updates bucket index
- Fixes: #5595
Backport: dumpling, firefly
We need to update the bucket index when updating object attrs, otherwise
we'... - 11:51 PM Revision ac799f08 (ceph): fix can not disable max_size quota
- Currently if we enable quota and set max_size = -1, it doesn’t
mean max_size is unlimited as expected. Instead, it me... - 11:51 PM Revision 71d119f2 (ceph): rgw: index swift keys appropriately
- Fixes: #10471
Backport: firefly, giant
We need to index the swift keys by the full uid:subuser when decoding
the jso... - 11:51 PM Revision 011a8c3b (ceph): rgw: http headers need to end with \r\n
- Fixes: #9254
Backport: firefly, giant
Reported-by: Benedikt Fraunhofer <fraunhofer@traced.net>
Signed-off-by: Yehuda... - 11:44 PM Revision e00f9bf1 (ceph): lib: add full support for RADOS block devices
- 11:25 PM Revision 95424168 (ceph): Merge pull request #3366 from ceph/wip-formatter
- formatter: improve pretty output, rename factory method
Reviewed-by: Dan Mick <dan.mick@redhat.com> - 11:12 PM Revision 5b0e8aef (ceph): mailmap: Yehuda Sadeh name normalization
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 11:11 PM Revision 4ca69313 (ceph): doc/release-notes: typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:11 PM Revision 3f03a7b2 (ceph): doc/release-notes: v0.91
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:10 PM Revision 3d420ff1 (ceph): radosgw_admin: don't use boto for testing 301 responses
- boto follows up on the redirects. Switched to using httplib2 for sending
this request.
Signed-off-by: Yehuda Sadeh <... - 11:02 PM Revision e7cc6117 (ceph): qa: ignore duplicates in rados ls
- These can happen with split or with state changes due to reordering
results within the hash range requested. It's eas... - 10:50 PM Revision 6fa29f6f (ceph): Merge pull request #3372 from ceph/wip-10539
- qa: fail_all_mds between fs reset and fs rm
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:38 PM Revision adc9bdae (ceph): rgw: set default region and zone to all clients
- Otherwise it's going to use zone 'default' for client.0, not as expected. Also
add region configuration to task.
Sig... - 10:08 PM Revision e5591f8a (ceph): qa: fail_all_mds between fs reset and fs rm
- Because fs reset opens a brief window for the previously
failed MDSs to spring back into life.
Fixes: #10539
Signed... - 10:00 PM Revision 26a2df28 (ceph): mailmap: Josh Durgin name normalization
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 09:48 PM Revision d6a9d25c (ceph): doc/release-notes: v0.80.8
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:44 PM Revision 45e9cd5b (ceph): Fix make check blockers.
- Replace ceph-helpers.sh check for ms_nocrc with the new formula
for this. Fixes make check for default build.
Addi... - 09:44 PM Revision daefad7a (ceph): xio: enable accelio debug on level 2
- Enable accelio debug (mostly on connection) on level 2
and sync with XioConnection debug events
Signed-off-by: Vu Ph... - 09:44 PM Revision aa5f1955 (ceph): xio: Get the right Accelio errno code
- Get the right Accelio errno code on xio_send_msg in
order to correctly requeue or fail the xmsg
Signed-off-by: Vu Ph... - 09:44 PM Revision 37719c3b (ceph): Dequeue XioMsg on send-fail
- If a message send hard fails, don't omit to remove it from the
send_q--this results in an assert when the queue is in... - 09:44 PM Revision d16e1817 (ceph): Reduce lock spam in XioPortal SubmitQueue.
- In SubmitQueue::deq, scan up to nlanes, exit immediately with
found work, recalling last lane.
Yield to Accelio iff ... - 09:44 PM Revision f276145f (ceph): xio: initial mark_* and queueing/flow control
- This changes implements explicit support for Accelio sender-side
flow control, which requires queuing messages for la... - 09:44 PM Revision 1c2efde8 (ceph): xio: Enable Accelio flow control with msgs and bytes throttlers
- * Enable Accelio flow control in general
* Read out policy for messages and bytes throttlers from connection's peer_t... - 09:43 PM Revision 3c7e857b (ceph): xio: Configure Accelio internal pool
- Temporarily hardcoded all 6 allocators + growing quantum and max size
1k allocator - quantum 4k - max 256k
4k allocat... - 09:43 PM Revision dcfb80a8 (ceph): Accelio Autotools glue.
- Add Accelio to build process with --enable-xio is provided.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:43 PM Revision aba35bca (ceph): cmake: add xio
- Signed-off-by: Casey Bodley <casey@linuxbox.com>
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:43 PM Revision 610d66f5 (ceph): Ceph Accelio/RDMA Transport (XioMessenger).
- XioMessenger implements a Ceph Messenger provider for Accelio,
a high-performance messaging transport by Mellanox. C... - 09:43 PM Revision a0642371 (ceph): Cosmetic ceph_mon.cc.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:43 PM Revision 53bc4d17 (ceph): Cosmetic ceph_osd.cc.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:42 PM Revision fd5cd938 (ceph): Cosmetic ceph_mds.cc.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:42 PM Revision d53b378e (ceph): Introduce Message flag values used by XioMessenger.
- These correspond to bits in Message::magic and the erstwhile
"special_handling" member.
Signed-off-by: Matt Benjamin... - 09:42 PM Revision b4447e9a (ceph): Add Message::set_src(const entity_name_t& src)
- Permit setting the source endpoint of a Message.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:42 PM Revision a96373fa (ceph): Remove pure virtuals from Message::CompletionHook.
- This was introduced for XioMessenger, but is no longer used.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:42 PM Revision ef7e7355 (ceph): Add intrusive list anchor for Message dispatch to Message.
- This is currently used by XioMessenger dispatch strategies, but
could be extended to other Messenger types.
Signed-o... - 09:42 PM Bug #10541: objecter memory corruption
- Working on the same project with Jason. His patch above seems to address the crash, but now all reads come back with ...
- 04:46 PM Bug #10541: objecter memory corruption
- With more testing, I get crashes in this section even without an OSD going down. The following patch seems to mostly...
- 01:51 PM Bug #10541 (Duplicate): objecter memory corruption
- With ceph 0.90, we have been fighting infrequent memory corruption with our client programs using librados. Unfortun...
- 09:42 PM Revision 984a3eed (ceph): Add MDataPing.
- This message type is used for Messenger testing.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:41 PM Revision 71d08b4a (ceph): Accelio ceph::buffer Extensions
- Adds custom buffer::raw type xio_mempool, with hooks into Accelio
memory lifecycle.
The xio_mempool type is non-shar... - 09:41 PM Revision 4cbf2d55 (ceph): Cosmetic: Normalize an entity_name_t initialization in ceph-syn.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:41 PM Revision 2ffacbe6 (ceph): msg: crc configuration in messenger
- Add new header_crc and data_crc configuration booleans, and use
them consistently to govern whether CRC is performed ... - 09:40 PM Revision b677a86f (ceph): Build rbd-fuse as a C++ unit (matching its existing linkage).
- Since rbd-fuse is linking C++ libraries, link it with the C++
runtime as we already do for ceph-fuse.
Signed-off-by:... - 09:40 PM Revision 80b3ff0e (ceph): mon: OSDMonitor sends maps over connection
- Signed-off-by: Casey Bodley <casey@linuxbox.com>
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:40 PM Revision 9fff0c53 (ceph): msg: remove create_anon_connection from Messenger
- the monitor now defines its own subclass of Connection to use for
Monitor::handle_forward(), rather than tying it to ... - 09:40 PM Revision 2401c3ba (ceph): dout: dlog_p macro for should_gather
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
Signed-off-by: Casey Bodley <casey@linuxbox.com>
Signed-off-by: Matt... - 09:40 PM Revision a39cbe2b (ceph): atomic: add and sub return their result
- Signed-off-by: Casey Bodley <casey@linuxbox.com>
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:40 PM Revision 0f6b9f28 (ceph): Combined CMake Build for Hammer
- CMake Ceph Build System (Firefly)
CMake. Add tests.
Respace src/CMakeLists.txt.
CMake. Spacing cleanups.
CMake for ... - 09:39 PM Revision 4368e0a5 (ceph): Null tracepoint macro when !WITH_LTTNG.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:39 PM Revision f57383ae (ceph): Don't use __cplusplus to mean !__KERNEL__
- Of course, this is Linux-centric.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:39 PM Revision 71e49879 (ceph): Add missing Messenger::create ms_type in test_msgr.
- Fixes trivial build breakage.
Signed-off-by: Matt Benjamin <matt@cohortfs.com> - 09:39 PM Revision 3ce683a3 (ceph): Fixup int_types.h.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 08:39 PM Revision 3424baed (ceph): librbd: fix coverity false-positives for tests
- Coverity flagged two variables as uninitialized prior to use.
Explicitly initialize the variables in the constructors... - 08:16 PM Revision 231cb99a (ceph): Merge pull request #297 from ceph/wip-10525
- Changed to "osd map max advance: 1000"
- 07:47 PM Revision f3a57ee6 (ceph): rgw: wait for completion only if not completion available
- In a bucket aio operation, wait for completions only if there are no
completions available. Otherwise we might wait f... - 07:33 PM Revision 2f01037d (ceph): Added warning "osd_map_max_advance" to the whitelist to aviod fail on it
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 06:16 PM Bug #10546 (Resolved): ceph time check start round bug in monitor.cc
- HI all,
My ceph cluster report clock skew even after time syncing 30min ago, so i'm digging in the src code of cep... - 05:48 PM Revision 833b2777 (ceph): ceph_test_objectstore: enable keyvaluestore experimental option
- Fixes: #10535
Signed-off-by: Samuel Just <sjust@redhat.com> - 05:47 PM Revision 204fa0f0 (ceph): ReplicatedPG::_scrub: don't record digests for snapdirs
- They are always empty, and the finish_ctx machinery doesn't really
work for snapdirs anyway.
Fixes: #10536
Signed-of... - 04:57 PM Revision 5c8ee338 (ceph): Merge remote-tracking branch 'gh/next'
- 04:29 PM Revision 0172069d (ceph): common/shared_cache.hpp: restructure clear()
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:03 PM Bug #10545 (Rejected): osd.0 "crashed with signal 9" in upgrade:dumpling-firefly-x-next-distro-ba...
- It was killod by oom-killer
- 03:37 PM Bug #10545 (Rejected): osd.0 "crashed with signal 9" in upgrade:dumpling-firefly-x-next-distro-ba...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:15:01-upgrade:dumpling-firefly-x-next-distro...
- 03:57 PM devops Bug #10528 (Resolved): issues with apt-mirror with wheezy packages
- This should be fixed. I suspect its being caused by apt-mirror just having too many distros/mirrors in a single confi...
- 03:40 PM devops Feature #10046 (Resolved): run make check on every pull request
- it has not caused trouble in the past week
- 03:32 PM CephFS Bug #10539: Error EINVAL: all MDS daemons must be inactive before removing filesystem
- thanks for the quick fix !
- 02:54 PM CephFS Bug #10539 (Resolved): Error EINVAL: all MDS daemons must be inactive before removing filesystem
- Merged to ceph-qa-suite master in commit:6fa29f6f19331df59d15e7470b81f4cf5f0e9689
- 02:07 PM CephFS Bug #10539 (Fix Under Review): Error EINVAL: all MDS daemons must be inactive before removing fil...
My fault!
https://github.com/ceph/ceph/pull/3372- 11:50 AM CephFS Bug #10539 (Resolved): Error EINVAL: all MDS daemons must be inactive before removing filesystem
- *make check* sometimes fails on "test/cephtool-test-mds.sh":http://workbench.dachary.org/ceph/ceph/blob/master/src/te...
- 02:52 PM Bug #10533 (Won't Fix): librados: duplicate object in rados_list() result
- The client is stateful, so yes, but according to sage split can cause problems, as can readdir being unpredictable an...
- 02:52 PM Bug #10531: "exception from mon" in upgrade:giant-x-next-distro-basic-vps run
- Looks like similar issue in this job:
http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-11_19:13:02-upgrade:d... - 01:52 PM Bug #10531: "exception from mon" in upgrade:giant-x-next-distro-basic-vps run
- Same problem in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:05:02-upgrade:giant-x-next-distro-basic-...
- 02:48 PM rgw Bug #10544 (Closed): "s3tests.functional.test_s3.test_multipart_upload ... FAIL" in upgrade:dumpl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-11_19:13:02-upgrade:dumpling-x-firefly-distro-basi...
- 02:01 PM Bug #10525: "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-basic-vps run
- Final fixes - https://github.com/ceph/ceph-qa-suite/pull/297
- 01:56 PM Bug #10543 (Duplicate): "FAILED assert(m_seed < old_pg_num)" in upgrade:giant-x-hammer-distro-bas...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:05:02-upgrade:giant-x-next-distro-basic-vps/...
- 01:54 PM CephFS Bug #10542 (Resolved): ceph-fuse cap trimming fails with: mount: only root can use "--options" op...
This appears to be from:...- 12:29 PM devops Bug #10537 (Resolved): runnnig out of space at ceph_site
- Cleared out some old cephdrop stuff (which is backed up if we sitll need it) as well as very old stuff in rpm-testing...
- 10:16 AM devops Bug #10537 (Resolved): runnnig out of space at ceph_site
- We are at 100% full on /home/
Had to delete a couple of files, including a 2gb.bin one that was 2GB.
We are in ... - 12:17 PM Bug #10534: full-object read crc 0x######## != expected 0x######## on
This object which has one good and one bad replica has identical object_info_t on both osd.0 and osd.2
{ "oid": ...- 11:56 AM Bug #10534: full-object read crc 0x######## != expected 0x######## on
- ...
- 12:00 PM Revision 9daeaec5 (ceph): mds: handle heartbeat_reset during shutdown
- Because any thread might grab mds_lock and call heartbeat_reset
immediately after a call to suicide() completes, this... - 11:16 AM Bug #10118: messenger drops messages between osds
- From the logs, something happened in the messenger to change the message ordering:
osd 0:
2015-01-13 23:56:27.853... - 10:31 AM Bug #10118: messenger drops messages between osds
- Seen on a master run rados:thrash run
http://qa-proxy.ceph.com/teuthology/dzafman-2015-01-13_16:52:51-rados:thrash... - 09:42 AM Bug #10536 (Resolved): _scrub and digests: osd/ReplicatedPG.cc: 7506: FAILED assert(!i->mod_desc....
- The problem is that finish_ctx does not really work on snapdirs (snaptrimmer does not use finish_ctx, and make_writea...
- 08:29 AM Revision 74bef7f4 (ceph): Merge pull request #291 from dachary/wip-10018-scrub
- add erasure code repair / scrub tests (take 2)
Reviewed-by: David Zafman <dzafman@redhat.com> - 07:39 AM Bug #10535: ceph_test_objectstore keyvaluestore error
- 07:34 AM Bug #10535 (Resolved): ceph_test_objectstore keyvaluestore error
- 2015-01-14T05:29:24.136 INFO:teuthology.orchestra.run.plana56.stdout:[ RUN ] ObjectStore/StoreTest.collect_metad...
- 06:26 AM Revision fc5cb3cf (ceph): osd/ReplicatedPG: remove unnecessary parameters
- In functions can_skip_promote and do_cache_redirect.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 06:25 AM Revision 78b2cf03 (ceph): osd: force promotion for watch/notify ops
- Watch/notify ops can't be proxied.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 06:18 AM Revision c8bef13c (ceph): osd/OpRequest: add osd op flag CEPH_OSD_RMW_FLAG_PROMOTE
- This flag indicates the osd op needs to force a promotion when there is
a cache tier.
Signed-off-by: Zhiqiang Wang <... - 05:34 AM Revision 2e5dcf2a (ceph): test: add write_fadvise_dontneed.yaml to test write_fadvise_dontneed.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:48 AM Revision ba32cc30 (ceph): Changed to "osd map max advance: 1000"
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:44 AM Revision 2098a6cc (ceph): Merge pull request #295 from ceph/wip-10525
- Changed to "osd map max advance: 1000"
- 03:42 AM Revision 9868966b (ceph): Changed to "osd map max advance: 1000"
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:36 AM Revision 717dffe7 (ceph): rados.py: Add write_fadvise_dontneed field
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:21 AM Revision a78a93e5 (ceph): rgw: bi list, update marker only if result not empty
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision f060dd65 (ceph): rgw: update calls to handle bucket sharding
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision 9d17bd0a (ceph): rgw: fix linkage following rebase
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision d19a49d3 (ceph): cls_rgw: call ioctx->aio_operate() under lock
- close a race window
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 03:21 AM Revision 33dc07cc (ceph): rgw: initialize RGWBucketInfo::num_shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision 24aec123 (ceph): rgw: fix memory leak
- We were iterating on both completion_objs, and completions assuming that
they follow each other. They don't do it. Wh... - 03:21 AM Revision 0b5d8033 (ceph): rgw: only keep track for cleanup of rados objects that were written
- Fixes: #10311
We're keeping track of rados objects that we've written so that we could
clean them up if needed. Earl... - 03:21 AM Revision ce0ed6bb (ceph): test: fix test_cls_rgw
- Adjust to new api calls.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 03:21 AM Revision 15703cf9 (ceph): cls_rgw: extend shards marker api
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision 9536f74a (ceph): rgw: write multi shard markers on replica_log appropriately
- When getting a list of shard_id#marker, iterate through the shards and
write each as needed.
Signed-off-by: Yehuda S... - 03:21 AM Revision 71016659 (ceph): rgw: pass num shards on bucket initialization
- Need to pass the actual num shards that are going to be used for this
specific bucket. Bucket may be created by apply... - 03:21 AM Revision 37a11862 (ceph): rgw: max shards configuration is part of the zone config
- The zone config params are set in the region configuration. Also,
there's a ceph.conf configurable (rgw_override_buck... - 03:21 AM Revision c07af12c (ceph): cls_rgw: remove incorrect function declaration
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision d52a8b10 (ceph): rgw: bucket_index_shard_hash_type fixes
- add initializations, json encode /decode.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 03:21 AM Revision a2c3680b (ceph): cls_rgw: list bi log should not return marker entry
- The marker should be served as a lower bound, but should not be
returned.
Signed-off-by: Yehuda Sadeh <yehuda@redhat... - 03:21 AM Revision 0d9c2d34 (ceph): rgw: bucket replica log, handle shard ids
- bucket replica log can now save entries by the specified shard id
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 03:21 AM Revision a063cbac (ceph): rgw: modify bucket instance shard marker ids
- Instead of having the markers prefixed by the oids, use the bucket
instance id.
Signed-off-by: Yehuda Sadeh <yehuda@... - 03:21 AM Revision 6b1c4a0b (ceph): cls_rgw: clean up CLSRGWConcurrentIO
- Class is no longer a template, and keeps a map of oids by shard_id. Call
issue_op() using both shard_id and oids. Sha... - 03:21 AM Revision 0d1f97ff (ceph): rgw, cls_rgw: keep shard ids with oids
- Instead of just having the list of oids, keep the shard ids together, so
that we can know on which shard the operatio... - 03:21 AM Revision 381f68ac (ceph): rgw: bi log list/trim can get specific bucket shard
- bucket shard can be specified on the bucket instance param. It can be
added like this: <bucket-instance>[:shard-id]
... - 03:21 AM Revision 87934706 (ceph): rgw: use new BucketShard structure for index manipulation calls
- Instead of recalculating the hash every call, do it once, and pass this
structure around. Also, will be used for logg... - 03:21 AM Revision a33ca59e (ceph): rgw: data changes log, log info by bucket shard id
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision d31e84ea (ceph): rgw: improve bucket sharding hashing
- Amplify small source changes.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 03:21 AM Revision 44bc63b1 (ceph): rgw: decode the req_state bucket instance id if needed
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 03:21 AM Revision 47665b23 (ceph): cls_rgw, rgw: switch different ops to new concurrent infrastructure
- Make all the relevant ops use the CLSRGWConcurrentIO infrastructure,
which simplifies things.
Signed-off-by: Yehuda ... - 03:21 AM Revision f9b280ea (ceph): Adjust bi log listing to work with multiple bucket shards.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 9e45a7cd (ceph): Adjust bi log trim implementation to work with multiple bucket shards.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 231fa0e6 (ceph): Fix get_bucket_instance_info, only build the oid if it is empty.
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
- 03:21 AM Revision 8a04c0a6 (ceph): Fix the multipart uploads functional test failures due to bucket index ...
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
- 03:21 AM Revision 56feee79 (ceph): Adjust bucket listing to work with multiple shards.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 9c5acd67 (ceph): Adjust bucket stats/index checking/index rebuild/tag timeout implementa...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 04441f28 (ceph): cls_rgw, rgw: create base class for common bucket shard operations
- Instead of copy pasting the same code all over again, create a base
class for the needed concurrent IO operations.
S... - 03:21 AM Revision 30d0a49c (ceph): rgw: generalize container type for concurrent IO base class
- Turned the ConcurrentIO class a template, so that we could use different
kind of containers that are needed for the d... - 03:21 AM Revision 90a3920c (ceph): Add a new field to bucket info indicating the number of shards of this ...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 5d004d3e (ceph): Implement sharding for bucket creation.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 03:21 AM Revision 751fd07b (ceph): Adjust rgw bucket prepare/complete OP to work with multiple bucket inde...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 02:47 AM CephFS Bug #10382: mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- This will need backport to giant
- 02:44 AM CephFS Bug #10382 (Fix Under Review): mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- https://github.com/ceph/ceph/pull/3370
- 01:21 AM Revision ded00c88 (ceph): Merge pull request #294 from ceph/wip-10525
- Replaced step for v0.80.6 with v0.80.7
- 01:18 AM Revision 4d5068cb (ceph): Replaced step for v0.80.6 with v0.80.7
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
01/13/2015
- 10:51 PM Revision 364b8681 (ceph): mon/Paxos: consolidate finish_round()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:51 PM Revision 67a90dd7 (ceph): mon: accumulate a single pending transaction and propose it all at once
- Previous we would queue lots of distinct encoded Transactions from various
callers, usually one per PaxosService. Th... - 09:36 PM Revision a4f13008 (ceph): Merge pull request #292 from ceph/wip-10525
- Fixes http://tracker.ceph.com/issues/10525
- 09:36 PM Bug #10534 (Resolved): full-object read crc 0x######## != expected 0x######## on
- 2015-01-13 18:55:18,979.979 INFO:tasks.ceph.osd.0.plana02.stderr:2015-01-13 18:55:18.860647 7fe6d209b700 -1 log_chann...
- 09:33 PM Revision b44c816e (ceph): Fixes http://tracker.ceph.com/issues/10525
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 08:31 PM Revision f08d95a5 (ceph): repair_test: rework to remove levels of indirection
- The commit is large but does not introduce any semantic change and
consists primarily in code moving around, re-inden... - 08:31 PM Revision f3bd336d (ceph): repair_test: rework indentation to make it pep8 clean
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 08:31 PM Revision 0465c0c5 (ceph): ceph_manager: add object helpers
- Add CephManager.methods to get information regarding the pools and PGs
used to store a given object.
Signed-off-by: ... - 08:31 PM Revision ae686583 (ceph): ceph_manager: add ceph-objectstore-tool wrapper
- Add the CephManager.objectstore_tool method to encapsulate a call to
ceph-objectstore-tool. The wrapper can convert a... - 08:31 PM Revision e580eca3 (ceph): repair_test: hinfo_key error injection
- Add a function dedicated to erasure coded pools tests, similar to
repair_test_1. Add a corrupter that removes the hin... - 08:23 PM Revision d1595863 (ceph): PendingReleaseNotes: make a note about librados flag changes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:18 PM Revision 5a1fd855 (ceph): Merge pull request #3360 from mattrichards/bump_rados_version
- librados: bump rados version number
Reviewed-by: Sage Weil <sage@redhat.com> - 08:10 PM Revision 725d6609 (ceph): 0.91
- 07:22 PM Revision bd4926c4 (ceph): ceph_manager: rework indentation to make it pep8 clean
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:18 PM Revision 7234481b (ceph): ceph_manager: define pool context
- To create a pool before running a code bloc and remove it after.
with manager.pool("mypool"):
mytest..
S... - 07:18 PM Revision 50e7e6df (ceph): ceph_manager: fix docstring typo
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:17 PM Revision 6f8b54ca (ceph): Merge pull request #2697 from ceph/wip-8900
- RBD image watcher and new exclusive lock handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:14 PM Revision 940a990b (ceph): Merge pull request #290 from ceph/revert-250-wip-10018-scrub
- Revert "add erasure code repair / scrub tests"
- 07:12 PM Revision 7029dba0 (ceph): Revert "add erasure code repair / scrub tests"
- 06:57 PM Revision f36b1718 (ceph): Merge pull request #286 from ceph/wip-10261-wusui
- Calamari_setup now allows > 1 mon.
- 06:56 PM Revision b8ce73f2 (ceph): Merge pull request #3254 from trociny/feature-10036
- osd: osd tree to show primary-affinity value
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:55 PM Revision 6c4a523c (ceph): Merge pull request #3281 from ceph/wip-10441-b
- osd: fix watch ordering bug 10441 option b
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Josh Durgin <jdu... - 06:54 PM Revision 00c30dd0 (ceph): Merge pull request #3290 from ceph/wip-da-SCA-20150102
- Coverity and SCA fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 06:54 PM Revision 733ce25c (ceph): Merge pull request #3302 from ceph/wip-9956
- os/FileStore: verify kernel is new enough before using extsize ioctl
Reviewed-by: Samuel Just <sjust@redhat.com> - 06:53 PM Revision c82f8177 (ceph): Merge pull request #3305 from majianpeng/fix5
- fix bugs about sync_filesystem
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 06:44 PM Revision 4d52523c (ceph): Merge pull request #250 from dachary/wip-10018-scrub
- add erasure code repair / scrub tests
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Loic Dachary <ldac... - 06:31 PM Bug #10533: librados: duplicate object in rados_list() result
- It's been a long time since I worked on the listing code and I think it's been rewritten since then, but once upon a ...
- 04:54 PM Bug #10533: librados: duplicate object in rados_list() result
- For reference - it was also caught by this job
http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:13:01-u... - 04:32 PM Bug #10533 (Won't Fix): librados: duplicate object in rados_list() result
- This occurred on a mixed firefly+next cluster with thrashing going on in the background.
It was detected by an rbd... - 05:29 PM Revision 75b70b7e (ceph): Merge pull request #289 from ceph/wip-10525
- Fixes http://tracker.ceph.com/issues/10525
- 05:25 PM Revision 7d857e61 (ceph): Fixes http://tracker.ceph.com/issues/10525
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 05:23 PM Bug #10525: "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-basic-vps run
- See https://github.com/ceph/ceph-qa-suite/pull/294 (Replaced step for v0.80.6 with v0.80.7)
http://pulpito.front... - 01:39 PM Bug #10525: "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-basic-vps run
- And more here https://github.com/ceph/ceph-qa-suite/pull/292
tests:
http://pulpito.front.sepia.ceph.com/teutholog... - 09:32 AM Bug #10525 (Fix Under Review): "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-di...
- Test run http://pulpito.front.sepia.ceph.com/teuthology-2015-01-13_09:33:23-upgrade:firefly-firefly-distro-basic-multi/
- 09:18 AM Bug #10525: "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-basic-vps run
- Old tests until 0.80.8 don't have "peering queue fix" and have to be changed to have:...
- 09:15 AM Bug #10525: "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-basic-vps run
- the older releases need osd map max advance = 100 in the conf to work around the peering queue bug.
- 08:28 AM Bug #10525 (Resolved): "HEALTH_WARN 44 pgs peering" failure in upgrade:firefly-firefly-distro-bas...
- Run http://pulpito.front.sepia.ceph.com/teuthology-2015-01-11_17:00:03-upgrade:firefly-firefly-distro-basic-vps/
J... - 05:00 PM Revision 5ef4380a (ceph): ci: fix travis status link
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:44 PM Bug #10430: osd/osd_types.cc: 456: FAILED assert(m_seed < old_pg_num)
- 04:43 PM Bug #8121: ReplicatedBackend::build_push_op() should handle a short read or assert
- 04:42 PM Bug #10474: Testing wip-9780-9781 hung ceph-objectstore-tool on import
- 04:42 PM Bug #10427: Generating past intervals can crash OSD because of a missing OSDMap
- 04:34 PM Revision c1fad23c (ceph): doc: project name change
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:32 PM Revision 9264d250 (ceph): common/Formatter: new_formatter -> Formatter::create
- Also make the default formatter selection more explicit.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:20 PM Revision 617ad5dd (ceph): common/Formatter: improve json-pretty whitespace
- The whitespace for the current pretty mode is awkward and weird. Move
to a more standard approach. It's more newlin... - 04:06 PM Revision 83c3b130 (ceph): common/Formatter: add newline to flushed output if m_pretty
- This applies to json-pretty and xml-pretty modes.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:04 PM Bug #10524 (In Progress): FAILED assert(peer_missing.count(fromshard))
- "ReplicatedBackend::prepare_pull":http://workbench.dachary.org/ceph/ceph/blob/master/src/osd/ReplicatedPG.cc#L8709 wi...
- 03:32 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- the bad peer is selected as a good peer because PGBackend::be_select_auth_object things the bad peer is an authoritat...
- 12:55 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- 12:55 PM Bug #10524: FAILED assert(peer_missing.count(fromshard))
- ubuntu@teuthology:/a/samuelj-2015-01-12_21:02:00-rados-wip-sam-testing-wip-testing-vanilla-fixes-basic-multi/700477
- 10:12 AM Bug #10524 (Need More Info): FAILED assert(peer_missing.count(fromshard))
- I'm not able to reproduce it on master or even using the exact same commit. Will wait for it to show up again.
- 08:41 AM Bug #10524 (In Progress): FAILED assert(peer_missing.count(fromshard))
- https://github.com/ceph/ceph-qa-suite/blob/master/tasks/scrub_test.py using ceph master succeeds when run alone (no t...
- 06:17 AM Bug #10524 (Resolved): FAILED assert(peer_missing.count(fromshard))
- http://qa-proxy.ceph.com/teuthology/samuelj-2015-01-07_13:21:03-rados-wip-sam-testing-wip-testing-vanilla-fixes-basic...
- 03:56 PM Revision e2a7b17f (ceph): osd/PG: remove unnecessary publish_stats_to_osd() in all_activated_and_...
- We queue the AllReplicasActivated event, and when that is processed we
call on_activated(), which publishes our pg st... - 03:55 PM Revision 77bc23c3 (ceph): osd/PG: add 'activating' pg state between peering and active
- When peering completes we wait for everybody to commit the PG info before
going active. The peering state is cleared... - 03:49 PM devops Bug #10532 (Won't Fix): Failed "joining thrashosds" - suspected low memory config on vps
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-11_17:05:01-upgrade:giant-x-next-distro-basic-vps/...
- 03:45 PM Bug #10531 (Rejected): "exception from mon" in upgrade:giant-x-next-distro-basic-vps run
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-11_17:05:01-upgrade:giant-x-next-distro-basic-vps/...
- 03:34 PM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Still a problem http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:13:01-upgrade:firefly-x-next-distro-basi...
- 03:31 PM devops Bug #10511: "test.functional.tests.TestAccount" fail in upgrade:firefly-x-next-distro-basic-multi...
- Still an issue http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-12_17:13:01-upgrade:firefly-x-next-distro-basic...
- 03:27 PM Revision d58cbada (ceph): doc: update doc layouts
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 03:08 PM Revision a6f5682d (ceph): Merge pull request #3364 from ceph/wip-quota-test
- qa: set -e explicitly in quota test
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:06 PM devops Bug #10526: Gitbuilder mirror not syncing
- I'm working on a solution using nginx.
- 10:12 AM devops Bug #10526: Gitbuilder mirror not syncing
- Example: http://gitbuilder.ceph.redhat.com/ceph-deb-precise-x86_64-basic/ref/master/pool/main/c/ceph/...
- 08:52 AM devops Bug #10526: Gitbuilder mirror not syncing
- I was thinking about using a caching proxy instead of running reposync on apt-mirror.sepia.ceph.com.
The Fedora in... - 08:42 AM devops Bug #10526 (Resolved): Gitbuilder mirror not syncing
- The gitbuilder.ceph.redhat.com mirror is perpetually out-of-sync. It can't continue this way.
I propose we use a c... - 02:58 PM Revision b578a53b (ceph): qa: set -e explicitly in quota test
- Previously was set in hashbang, which meant
that "./quota.sh" was OK, but "sh ./quota.sh" would
just run through igno... - 02:47 PM Revision d8e1f675 (ceph): Merge pull request #3336 from ceph/wip-fs-reset
- mon: implement `fs reset`
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:44 PM devops Fix #5900: Create a Python package for ceph Python bindings
- I think we discussed this on IRC a couple weeks ago, but returning to it now:
We still need Ceph's @make install@ ... - 02:34 PM Revision 8d706cd0 (ceph): osd/ReplicatedPG: init ignore_cache in second OpContext ctor
- *** CID 1262558: Uninitialized scalar field (UNINIT_CTOR)
Signed-off-by: Sage Weil <sage@redhat.com> - 02:28 PM Revision 792ac7c4 (ceph): osd/ReplicatedPG: fix cancel_proxy_read_ops
- Two issues:
1) We invalidate the iterator when we delete the item
2) In the requeue==false case we should still clea... - 02:28 PM Revision 69eaad7f (ceph): 0.80.8
- 02:07 PM Revision 01174518 (ceph): repair_test: hinfo_key error injection
- Add a function dedicated to erasure coded pools tests, similar to
repair_test_1. Add a corrupter that removes the hin... - 02:07 PM Revision 236049b2 (ceph): ceph_manager: add ceph-objectstore-tool wrapper
- Add the CephManager.objectstore_tool method to encapsulate a call to
ceph-objectstore-tool. The wrapper can convert a... - 01:42 PM Revision 372665d1 (ceph): ceph_manager: add object helpers
- Add CephManager.methods to get information regarding the pools and PGs
used to store a given object.
Signed-off-by: ... - 01:42 PM Revision f3a91d2e (ceph): repair_test: rework indentation to make it pep8 clean
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 01:37 PM Revision 0df5e84b (ceph): ceph_manager: In Thrasher disable ceph_objectstore_tool tests if old re...
- Require ceph-objectstore-tool to be available on all OSD nodes
Log a message when tool is not available
Signed-off-b... - 01:37 PM Revision b6f7b17b (ceph): ceph_manager: In Thrasher randomly remove past intervals
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:37 PM Revision 1903b7be (ceph): ceph_manager: Re-enable Thrasher ceph-objectstore-tool testing
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:37 PM Revision cf8bc063 (ceph): ceph_manager: Thrasher fixes to run() calls to set check_status = False
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:37 PM Revision 7d4bb552 (ceph): ceph_manager: Fix Thrasher kill_osd() to ignore pool going away
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:37 PM Revision e2494c50 (ceph): Fix objectstore name changed to keyvaluestore
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:37 PM Revision 666aecc1 (ceph): ceph_manager: define pool context
- To create a pool before running a code bloc and remove it after.
with manager.pool("mypool"):
mytest..
S... - 01:37 PM Revision 1f14626b (ceph): ceph_manager: fix docstring typo
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 01:37 PM Revision 764f6159 (ceph): ceph_manager: rework indentation to make it pep8 clean
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 01:37 PM Revision 9203259e (ceph): repair_test: rework to remove levels of indirection
- The commit is large but does not introduce any semantic change and
consists primarily in code moving around, re-inden... - 01:31 PM Bug #10370: "MaxWhileTries: 'wait_until_healthy'reached maximum tries (150) after waiting for 900...
- Sure looks to me like the error here is the HEALTH_WARN on stuck PGs, rather than the MDS not reporting health (presu...
- 01:29 PM Bug #10146 (Resolved): ceph-disk: sometimes the journal symlink is not created
- https://github.com/ceph/ceph/pull/3172
- 01:28 PM CephFS Bug #10381 (Resolved): health HEALTH_WARN mds ceph239 is laggy
- Whoops, this fell through the cracks.
Anyway, the MDS map has pool 0 set to use for data, but the OSDMap doesn't h... - 01:25 PM Bug #10176 (Resolved): Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- 01:24 PM Bug #10375 (Rejected): OSD journal partition link could be broken after off linking the disk via ...
- Tupper, is this reproducible? which kernel? doesn't sounds like a ceph problem.
- 01:24 PM Bug #10375: OSD journal partition link could be broken after off linking the disk via storcli and...
- it sounds like udev is failing to create the link. this is a problem with either the megaraid driver or with udev..
- 01:22 PM Bug #10397 (Can't reproduce): "Caught signal (Bus error)" in upgrade:dumpling-firefly-x:parallel-...
- 01:18 PM Bug #10132 (Resolved): osd: tries to set ioprio when the config option is blank
- 01:17 PM Bug #10435 (Closed): ceph-osd stops with "Caught signal (Aborted)" or "osd/PG.cc: 2683: FAILED as...
- in certain cases it is possible to move the file, but in general no. we're working on a tool to move entire pgs at a...
- 01:15 PM Bug #9916 (Resolved): osd: crash in check_ops_in_flight
- 01:13 PM Bug #10439 (Fix Under Review): 'ceph tell' should fail if daemon is not found
- 01:11 PM Bug #10282 (Resolved): gf-complete: missing .gitignore entry for .dirstamp
- 01:07 PM Bug #10242 (Can't reproduce): FAILED assert(backfill_targets.empty() || backfill_targets == want_...
- 12:52 PM devops Bug #10528 (Resolved): issues with apt-mirror with wheezy packages
- Jenkins is failing with a task that depends on installing some packages for wheezy.
On the apt-mirror server I ran... - 12:45 PM devops Bug #10515 (Need More Info): chef / apt-get compete during parallel runs
- In both cases, the error occurs when apt is being called by chef. The parallel processes are on different hosts. Sand...
- 11:07 AM devops Bug #10492 (Duplicate): rhel7 missing packadges
- This is just a duplicate of the centos6 #10460...
- 11:02 AM devops Bug #10492: rhel7 missing packadges
- Run is teuthology-2015-01-08_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps
- 10:27 AM Revision 7c664fad (ceph): Doc: Fix the indentation in doc/rbd/rbd-snapshot.rst
- 10:07 AM Revision fc7fa308 (ceph): Merge pull request #3343 from dachary/wip-10505-centos-parted
- tests: install parted in centos Dockerfile
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 09:56 AM devops Bug #10460 (Resolved): Missing packadge centos6
- I believe this was due to the centos gitbuilder being down which was resolved last week.Please re-assign and reopen i...
- 09:49 AM Revision 1c01c3a4 (ceph): tests: create unittest_librbd
- The existing ceph_test_librbd integration tests are now used
within unittest_librbd as unit tests run during 'make ch... - 09:49 AM Revision c105003b (ceph): tests: add mock librados API for supporting unit tests
- The new librados_test_stub library can be used by unit tests
as a replacement for the librados shared library. The l... - 08:34 AM Revision 1e9da43f (ceph): include: moved RBD's generic FunctionContext wrapper
- FunctionContext uses boost::function to allow the Context
interface to invoke arbitrary functions. This eliminates
t... - 08:10 AM Revision 1483a439 (ceph): msg/simple: remove redundant calling of setsockopt
- set_socket_options() will be called in Pipe::accept().
Signed-off-by: Jian Wen <wenjianhn@gmail.com> - 07:51 AM Revision 9ef6ce56 (ceph): FileJournal: check fsync/fdatasync result.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 07:24 AM Revision 140104d1 (ceph): test: remove unused imports
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:00 AM CephFS Bug #10387 (Resolved): ceph-fuse doesn't release capability on deleted directory
- 06:43 AM CephFS Bug #10387: ceph-fuse doesn't release capability on deleted directory
- I wouldn't bother backporting: the symptom is just some dir objects that don't get cleaned up until next client unmou...
- 06:27 AM Revision e3678f41 (ceph): mon: check min_size range.
- When set min_size value:
A:for replicated pool, the value must be between in 1 and size
B:for erasure pool, the value... - 06:27 AM Revision 3f030035 (ceph): test/mon: Add test case for ceph osd pool set size/min_size.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:27 AM Revision 3cbe5da1 (ceph): mon: check size must larger than zero.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:21 AM Revision be2d82bd (ceph): test: add testify/assert dep
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:18 AM Revision ec33d673 (ceph): ci: add librbd-dev dependency
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:15 AM Revision 36974cdb (ceph): test: add test for root package
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:15 AM Revision 44c15bf4 (ceph): rbd: add rbd package
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:01 AM Revision ac99e00c (ceph): ci: test in sub dirs
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:57 AM Revision 94b23c6d (ceph): doc: setup docs for multiple packages
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:54 AM Revision ae9281be (ceph): rados: fix import path
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:54 AM Revision 253495ee (ceph): rados: move rados to its own package
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:35 AM Revision 64ba2d55 (ceph): ci: use stable release
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:17 AM Revision 7945f8d6 (ceph): librbd: flush pending AIO requests under all existing flush scenarios
- AIO requests that are waiting on the image lock should be flushed
during all existing RBD flush scenarios. A few flu... - 04:14 AM Revision 2dd0f038 (ceph): librbd: AIO requests should retry lock requests
- Added a timer to support retrying AIO lock requests until
they are successful.
Signed-off-by: Jason Dillaman <dillam... - 03:56 AM Revision 4377f00b (ceph): tasks/calamari_setup: use ice_version to completely specify iceball
- Previously, the task would search for the lexicographically-greatest
filename matching ICE-*.tar.gz; now it builds a ... - 03:56 AM Revision bbe22d2f (ceph): tasks/calamari_setup: remove HTTP-downloaded iceball, if any
- Fixes: #10522
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 03:56 AM Revision 4c27048b (ceph): tasks/calamari_setup: build ice-tools virtualenv if building iceball
- ice-tools needs a virtualenv populated to properly run to build
an iceball; add the commands to do that. Also remove... - 02:10 AM Bug #10505 (Resolved): test/centos/Dockerfile.in is missing parted
- https://github.com/ceph/ceph/pull/3343
- 01:29 AM Revision dc10ccc9 (ceph): rados: use old object list api
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:09 AM Revision 7b89a827 (ceph): rgw-admin: create subuser if needed when creating user
- Fixes: #10103
Backport: firefly, giant
This turned up after fixing #9973. Earlier we also didn't create the
subuser i... - 01:09 AM Revision 9ee29b53 (ceph): rgw: update swift subuser perm masks when authenticating
- Fixes: #9918
Backport: firefly, giant
It seems that we weren't setting the swift perm mask correctly.
Signed-off-by:... - 01:02 AM Revision 6176ec5f (ceph): librbd: differentiate between R/O vs R/W RBD features
- The new RBD exclusive lock feature should be treated as a
feature that is only applied when the image is opened in
R/... - 01:02 AM Revision 544ed961 (ceph): librbd: Add internal unit test cases
- The new unit tests cover the modifications made to integrate
the internal librbd functionality with the new ImageWatc... - 01:02 AM Revision 17f22d98 (ceph): librbd: Add ImageWatcher unit test cases
- Directly unit test the new ImageWatcher class to complement
the existing librbd integration tests of exclusive lock
h... - 01:01 AM Revision d298fdda (ceph): rgw: send http status reason explicitly in fastcgi
- There are issues in certain versions of apache 2.4, where the reason is
not sent back. Instead, just provide the reas... - 01:01 AM Revision 4297e3bf (ceph): rbd: Allow CLI to optionally create shared images
- Images that are flagged as shared cannot use the RBD
object map nor RBD mirroring features.
Signed-off-by: Jason Dil... - 01:01 AM Revision 5160281b (ceph): librbd: Add convenience library to support unit tests
- Unit tests need access to the private symbols of librbd no
longer exported from librbd.so. A new librbd_internal
con... - 01:01 AM Revision ccadff14 (ceph): librbd: Integrate librbd with new exclusive lock feature
- Operations that update the image now require the exclusive lock
if the feature is enabled. AIO write and discard ope... - 01:00 AM Revision 9ee80b33 (ceph): librados: bump rados version number
- As a follow-on to 49d114f1fff90e5c0f206725a5eb82c0ba329376,
increment the "extra" version field so clients can easily... - 12:20 AM Revision d784bc47 (ceph): Merge pull request #3316 from ceph/wip-10471
- rgw: index swift keys appropriately
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:08 AM Revision 4dbde594 (ceph): Merge remote-tracking branch 'gh/wip-slow-backend-firefly' into firefly
- 12:01 AM Revision f5668d6b (ceph): librbd: Create image exclusive lock watch/notify handler
- The new watch/notify handler replaces the existing header
update watch/notify handler and adds support for managing
i...
01/12/2015
- 10:36 PM Revision d226f34d (ceph): drop tiobench tests
- The tiobench software has been abandoned upstream for years. Fedora and
Debian are no longer shipping the tiobench pa... - 10:13 PM rgw Documentation #8271: Document support for S3 multi-object delete
- Can we make this happen? See http://tracker.newdream.net/issues/2797
- 10:00 PM Revision 2ecd8748 (ceph): osd: enable filestore_extsize by default
- Note that this will only get used if the kernel is new enough; if it is
older than 3.5 the option will get disabled a... - 09:59 PM Revision b76d0dc0 (ceph): os/FileStore: verify kernel is new enough before using extsize ioctl
- Old kernels have an XFS bug that exposes uninitialized data when the
extsize hint is set and only partially written. ... - 08:06 PM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- ...
- 07:33 PM Revision c219c43c (ceph): Merge pull request #3352 from kylinstorage/fix-10503
- Fix bug 10503: http://tracker.ceph.com/issues/10503
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:30 PM CephFS Bug #10387: ceph-fuse doesn't release capability on deleted directory
- do we need to backport this. the directory will be deleted when all of its child dentries get trimmed from the cache
- 03:26 PM CephFS Bug #10387 (Pending Backport): ceph-fuse doesn't release capability on deleted directory
- This was merged to master in commit:e9a29c58b6d40933afbf711afcf7b872b4005585; does it need a backport?
- 07:23 PM Revision c3eee83f (ceph): fs: enable client quota on cfuse_workunit_misc
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com> - 07:17 PM Revision c3335c7a (ceph): msg/Pipe: inject delay in stop_and_wait
- Inject a delay in stop_and_wait. This will mostly affect the connection
race Pipe takeover code which currently call... - 07:17 PM Revision 300d4c6f (ceph): msg/simple: do not stop_and_wait on mark_down
- We originally blocked in mark_down for fast dispatch threads
to complete to avoid various races in the code. Most of... - 07:17 PM Revision 1261bf24 (ceph): Revert "Objecter: disable fast dispatch of CEPH_MSG_OSD_OPREPLY messages"
- This reverts commit 3f23709c474292f9239f77a6cce26309fc86ce29.
We have changed mark_down() behavior so that it no lon... - 07:17 PM Revision 1dbe8f5a (ceph): SimpleMessenger: Pipe: do not block on takeover while holding global lock
- We previously were able to cause deadlocks:
1) Existing pipe is fast_dispatching
2) Replacement incoming pipe is acce... - 05:37 PM Revision f4ff12ae (ceph): drop ceph_mon_store_converter
- This was needed for upgrades in the cuttlefish era; no longer useful.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:23 PM Revision 54b1de63 (ceph): tasks/s3tests: add slow backend configurable
- Adding this so that we can modify the clients' conf file as needed with slow backend.
This can be achieved by:
overr... - 05:16 PM Revision 03d01eb6 (ceph): rgw: mark ec related rgw suites as slow backend
- We want to avoid tests that time out due to a too slow backend.
Reviwed-by: Josh Durgin <josh.durgin@inktank.com>
Si... - 04:53 PM rgw Bug #10103: swift tests failing
- fix comment mentioned issue #9973 as the regression culprit. It's actually issue #9918.
- 04:39 PM Revision 4ecea7e5 (ceph): Merge pull request #3203 from majianpeng/fix1
- avoid memcopy from librados to caller buffer
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjus... - 04:36 PM rgw Bug #10379 (Fix Under Review): rgw: object versioning, remove last version needs to remove olh
- 04:33 PM rgw Bug #10271 (Fix Under Review): Radosgw urlencode
- 04:30 PM Revision 4af06a06 (ceph): Merge pull request #3287 from ceph/emperor-10351
- mount.ceph: avoid spurious error message
- 04:26 PM Revision 187c85a5 (ceph): Merge pull request #3034 from dachary/wip-10017-erasure-code-repair
- erasure code repair when there are two failures
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:23 PM Revision fb72b9e4 (ceph): Merge pull request #3148 from mslovy/optimazation_wbthrottle
- os: WBThrottle: optimize the map to unordered_map
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:21 PM rgw Bug #10471 (Pending Backport): rgw: metadata sync doesn't create subusers correctly
- 04:20 PM Revision 16c023d8 (ceph): osd: requeue PG when we skip handling a peering event
- If we don't handle the event, we need to put the PG back into the peering
queue or else the event won't get processed... - 03:58 PM Bug #10514 (Won't Fix): workunit osdc/stress_objectcacher.sh fails with no error message (giant)
- This test turns out to use a lot more memory than I thought.
- 09:01 AM Bug #10514: workunit osdc/stress_objectcacher.sh fails with no error message (giant)
- This was killed by the oom-killer, but it doesn't use the cluster at all, which makes me more suspicious of it being ...
- 06:37 AM Bug #10514 (Won't Fix): workunit osdc/stress_objectcacher.sh fails with no error message (giant)
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/693791/...
- 03:14 PM CephFS Bug #10413: samba: coredumps after tests run
- We talked about this in standup; Zheng is going to send it to the Samba guys.
- 03:00 PM Revision 86306966 (ceph): qa: add `fs reset` to cephtool tests
- This is just a superficial "I can call it" test,
it's actual behaviour is checked elsewhere.
Signed-off-by: John Spr... - 03:00 PM Revision a4152dbf (ceph): mon/MDSMonitor: add confirm flag to fs reset
- This was already in the command map but was not
being checked.
Signed-off-by: John Spray <john.spray@redhat.com> - 03:00 PM Revision 1713ffd8 (ceph): mon: implement `fs reset`
- This is for use in CephFS disaster recovery. When
the metadata pool has been forcibly reset to a single-MDS
metadata... - 02:09 PM Feature #9598: re-enable Objecter fast dispatch
- * giant backport https://github.com/ceph/ceph/pull/3356
- 01:10 PM rgw Tasks #10518 (Resolved): radosgw-agent: catch master up with v1.2?
- 11:15 AM rgw Tasks #10518 (Fix Under Review): radosgw-agent: catch master up with v1.2?
- After discussing in #ceph-devel, the following PR will resolve this : https://github.com/ceph/radosgw-agent/pull/16
- 09:51 AM rgw Tasks #10518 (Resolved): radosgw-agent: catch master up with v1.2?
- There is a "v1.2" branch in https://github.com/ceph/radosgw-agent/tree/v1.2 , but not all the changes have been merge...
- 12:06 PM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- Right ! The following is much easier:...
- 12:01 PM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- Loic,
On CentOS these days, it's now possible to just do "yum install epel-release" instead of having to go look u... - 11:31 AM CephFS Bug #10503 (Resolved): ceph-fuse: quota code is not 32-bit safe for vxattr output
- Fix merged to master in commit:c219c43cc2943c794378214d77566e3f0d3f394a
- 11:28 AM Bug #10488: osd erasure-code-profile set is sometimes not idempotent
- ubuntu@teuthology:/a/sage-2015-01-11_12:05:20-rados-firefly-distro-basic-multi/697291
- 11:27 AM CephFS Bug #10416: quota test failures
- Pushed a config change for the cfuse_workunit_misc yaml fragment to master in commit:c3eee83fb09a8f37faa71fa8fa78b632...
- 11:09 AM CephFS Bug #10416 (In Progress): quota test failures
- ....no. I'll fix that and we'll see if things work better, thanks!
- 10:37 AM Bug #10513 (Won't Fix): ceph_test_librbd_fsx fails with thrasher
- josh: There's no trace of the actual error in the teuthology or ceph client logs. Looking at the syslogs, this and se...
- 06:14 AM Bug #10513 (Won't Fix): ceph_test_librbd_fsx fails with thrasher
- http://pulpito.ceph.com/loic-2015-01-08_10:36:47-rbd-giant-backports-testing-basic-vps/690698/...
- 10:29 AM Fix #10519 (Resolved): Replace numerical value 0x7fffffff / MAX_UINT with CRUSH_ITEM_NONE in ceph...
- The numerical value representing CRUSH_ITEM_NONE confuses people : it looks like a bug. Having CRUSH_ITEM_NONE or ano...
- 10:04 AM Bug #10485: unreadable ceph-osd core dump (firefly)
- ...
- 08:35 AM Bug #10517: ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- Dong Yuan should look at this.. but Sam perhaps I should also try to finish the series that gets rid of append entirely?
- 08:26 AM Bug #10517: ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- ubuntu@teuthology:/a/samuelj-2015-01-07_13:21:03-rados-wip-sam-testing-wip-testing-vanilla-fixes-basic-multi/689604
- 08:25 AM Bug #10517 (Resolved): ./os/ObjectStore.h: 598: FAILED assert(op->oid < om.size())
- wip-sam-testing, but I think this code was not affected.
-2> 2015-01-08 00:48:19.737753 7f6a6a4b0700 0 -- 10.... - 08:24 AM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- How was this fixed?
- 07:51 AM Bug #9891: "Assertion: os/DBObjectMap.cc: 1214: FAILED assert(0)" in upgrade:firefly-x-giant-dist...
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/694324/...
- 07:38 AM devops Bug #10515: chef / apt-get compete during parallel runs
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/694240/
apt-get fails (mean... - 07:34 AM devops Bug #10515 (Won't Fix): chef / apt-get compete during parallel runs
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/694228/
Maybe because paral... - 07:27 AM Bug #9308: EBUSY on umount of osd volume after ceph-osd shutdown
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/694164/...
- 07:16 AM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- The fix was reverted by commit:ea90d9f46b2716df6e10dccaed908fd235f2000c which is probably why it showed up again at h...
- 07:03 AM Bug #10499: "INFO: rcu_sched detected stalls on CPUs/tasks" in upgrade:dumpling-x-firefly-distro-...
- http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/693936
- 07:00 AM Bug #9921: msgr/osd/pg dead lock giant
- * giant backport https://github.com/ceph/ceph/pull/3356
- 06:48 AM Bug #9921: msgr/osd/pg dead lock giant
- * http://pulpito.ceph.com/loic-2015-01-10_11:54:25-rados-giant-backports-testing-basic-vps/693791/ with remote/vpm099...
- 05:54 AM devops Bug #10152: drop tiobench references
- * ceph-qa-suite giant backport https://github.com/ceph/ceph-qa-suite/pull/287
- 05:49 AM Revision 1f694767 (ceph): Fix bug 10503: http://tracker.ceph.com/issues/10503
- ceph-fuse: quota code is not 32-bit safe for vxattr output
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com> - 05:45 AM Revision 4aa02f84 (ceph): osd: add an option to prioritize heartbeat traffic
- By default every hardware queue of a network interface is assigned a
pfifo_fast QDisc. When network congestion occurs... - 01:28 AM Revision 11bdfb41 (ceph): osd: requeue blocked op before flush it was blocked on
- If we have request A (say, cache-flush) that blocks things, and then
request B that gets blocked on it, and we have a... - 01:05 AM Revision c80c2cf3 (ceph): test: modify test/cli/rbd/help.t for merge-diff
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 01:05 AM Revision d300220a (ceph): rbd: test case for rbd merge-diff
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com> - 01:04 AM Revision 337f8219 (ceph): rbd: merge two diff files into one single file
- Note: It does not do the merging work if
either of the source diff files is stripped,
since which complicates the pro... - 01:03 AM Revision 9c82efcc (ceph): rbd: parse diff file body for diff merging
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Rev... - 01:02 AM Revision b4720ae6 (ceph): rbd: parse diff file header for diff merging
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Rev...
01/11/2015
- 11:35 PM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- please remove the sudo before /home/ubuntu/cephtest/fsx-mpi. Otherwise rank of all processes will be zero
- 10:38 PM CephFS Bug #10416: quota test failures
- The configure log is look like below:
overrides:
admin_socket:
branch: master
ceph:
conf:
... - 05:25 PM Bug #10512 (Resolved): osd: cancel_flush requeues blocked events after blocking event
- ubuntu@teuthology:/a/sage-2015-01-09_21:43:43-rados-firefly-distro-basic-multi/694675
- 03:55 PM Revision 538bad38 (ceph): Merge pull request #2948 from ceph/wip-promote
- osd: promote_object separation; proxy read
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@... - 12:11 PM devops Bug #10511 (Rejected): "test.functional.tests.TestAccount" fail in upgrade:firefly-x-next-distro-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-10_17:13:01-upgrade:firefly-x-next-distro-basic-mu...
- 10:35 AM devops Bug #10310 (Resolved): Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- 07:54 AM Feature #9979 (Resolved): osd: cache: proxy reads (instead of redirect)
- 07:53 AM Feature #9980 (Resolved): osd: cache: proxy reads during promote
- 07:04 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- If your linux distribution is Oracle Linux, you may need to install xfsprogs-qa-devel by "yum install -y xfsprogs-qa-...
- 04:35 AM Revision 1554fbc8 (ceph): osd/ReplicatedPG: improve proxy read cancelation
- Avoid taking the PG lock for a canceled read op (if we are lucky). Recheck
after the lock is taken for good measure.... - 04:35 AM Revision f42ef1e3 (ceph): ceph_test_rados: add some debug output
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:35 AM Revision 70d3d08a (ceph): osd: tiering: add proxy read support
- wip 9979
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 04:35 AM Revision 4dc9990e (ceph): osd: tiering: add cache mode READPROXY
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 04:35 AM Revision 8e145e08 (ceph): osd: tiering: proxy reads during promote
- wip 9980. Do proxy read and async promotion for writeback.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 04:35 AM Revision ce14310c (ceph): test: add proxy read test
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 04:35 AM Revision 759db93f (ceph): osd/ReplicatedPG: allow reads to proxy etc even if blocked
- If we are not write ordered, continue with cache checks so that we can
(among other things) proxy reads while promoti... - 04:35 AM Revision bfb71a4e (ceph): osd: tiering: cancel and requeue proxy read when needed
- Cancel and requeue proxy read on the following cases:
1) on_shutdown
2) on_change
3) background promotion is done
Si... - 04:35 AM Revision 43f13af6 (ceph): osd: tiering: proxy instead of redirect read in writeback mode when the
- cache pool is full
To preserve read op order
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 04:35 AM Revision 650f1d98 (ceph): osd: tiering: avoid duplicate promotion on proxy read
- Do not promote if it is already undergoing in maybe_handle_cache.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.... - 04:35 AM Revision 1c8b679d (ceph): osd/ReplicatedPG: put proxy read completion on finisher
- We can't use the synchronous completion callbacks (in fast dispatch
context) do to the proxy read completion work.
S... - 04:35 AM Revision 1d89f181 (ceph): osd/ReplicatedPG: make op argument to promote_object optional
- For now, we still always pass it. In preparation, however, we modify
promote_object() so that it will work when op i... - 04:35 AM Revision 8645ed76 (ceph): osd/ReplicatedPG: factor out common exists case from all cache modes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:35 AM Revision 5361bc04 (ceph): osd/ReplicatedPG: factor out must_promote case from all cache modes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:35 AM Revision 2a67b0a0 (ceph): osd/ReplicatdPG: adjust braces (no semantic change)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:35 AM Revision a4a41494 (ceph): osd/ReplicatedPG: drop unnecessary cache_mode checks
- This currently enumerates all cache modes except none, and we don't
arrive in this function when caching is disabled.... - 04:35 AM Revision a03d375e (ceph): osd/ReplicatedPG: pass promote error to all blocked operations
- This isn't the most elegant strategy, but it is the best we can do
right now.
Signed-off-by: Sage Weil <sage@redhat.... - 04:35 AM Revision 9ed2ac78 (ceph): osd/ReplicatedPG: separate promotion from the triggering op
- Remove the triggering op from the internal promote machinery.
We keep the optional op arg to promote_object() only b...
01/10/2015
- 11:25 PM Revision 9c50ed07 (ceph): Merge pull request #3309 from trociny/wip-9483
- OSD: add a get_latest_osdmap command to the admin socket
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:48 PM Feature #10477 (Fix Under Review): pg query should output the replicas the primary is waiting on ...
- 01:56 PM Revision 2bbab059 (ceph): OSD: add a get_latest_osdmap command to the admin socket
- The command blocks and ensures we have the latest map from the
mon. This is useful in testing and to "unstick" cluste... - 01:21 PM Revision d5e8ef50 (ceph): doc: Fix PHP librados documentation
- 12:54 PM Revision b2a3c505 (ceph): Merge pull request #3348 from ceph/wip-mon-wishlist
- doc: mon janitorial list is now a wishlist
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:09 PM Revision a16e72cf (ceph): doc: mon janitorial list is now a wishlist
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 08:40 AM Bug #10490 (Duplicate): osd: bad state machine event, RequestBackfilPrio in RepRecovering
- this was missing backport, already inf irefly
- 05:43 AM Revision 585efcb7 (ceph): Merge remote-tracking branch 'gh/next'
- 05:43 AM Revision 58b5e028 (ceph): Merge pull request #3327 from ceph/wip-peeringqueue
- osd: fix peering queue bug
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:00 AM Feature #10509 (Closed): mon: wishlist tracking ticket
- *This is a tracking ticket for the monitor wishlist in src/doc/mon-wishlist.txt*
h3. Low-hanging fruit
* audit ... - 03:59 AM Subtask #10508 (New): mon: finer-grain Paxos::is_readable() / PaxosService::is_readable()
- Rationale: a given service S should be able to read its committed state even though a Paxos proposal is happening, as...
- 03:57 AM Feature #10507 (Resolved): mon: have an OpTracker
- much like we have for the osd
1. Instead of passing messages back and forth, we will pass OpRequests
2. We may ... - 03:54 AM RADOS Cleanup #10506 (New): mon: get rid of QuorumServices
- A QuorumService is an abstraction allowing for easier management of services requiring a quorum to work correctly.
... - 02:50 AM Revision 19955fca (ceph): doc: Replace cloudfiles with swiftclient in Python Swift example
- The Cloud Files client library is no longer supported by Rackspace.
Users installing the package receive the followin... - 01:41 AM Revision 54613689 (ceph): mon: paxos: queue next proposal after waking up callbacks
- Signed-off-by: Joao Eduardo Luis <joao@redhat.com>
- 01:33 AM Feature #10452: ceph osd df
- I created a pull request with incomplete implementation
https://github.com/ceph/ceph/pull/3347
more for discuss... - 12:56 AM Revision 18d6a083 (ceph): Merge pull request #3344 from ceph/wip-librbd-snap-unprotect
- librbd: shadow variable in snap_unprotect
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:10 AM Revision 1f557c56 (ceph): Calamari_setup now allows > 1 mon.
- Signed-off-by: Warren Usui <warren.usui@inktank.com>
Fixes: #10261
01/09/2015
- 11:53 PM Revision 3c7cacf0 (ceph): mon/OSDMonitor: fix double-free on old MOSDBoot
- send_latest() does an m->put().
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picke... - 11:13 PM Revision d3755324 (ceph): rgw: return InvalidAccessKeyId instead of AccessDenied
- Fixes: #10334
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 56af795b1046a4c1bfba59e1fef... - 11:13 PM Revision dd57af2f (ceph): rgw: return SignatureDoesNotMatch instead of AccessDenied
- Fixes: #10329
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit ef75d720f289ce2e18c0047380a... - 11:05 PM Revision a2388348 (ceph): tests: install parted in centos Dockerfile
- It is needed to run root ceph-disk tests.
http://tracker.ceph.com/issues/10505 Fixes: #10505
Signed-off-by: Loic Da... - 11:05 PM Revision 852d7b5b (ceph): osd: requeue PG when we skip handling a peering event
- If we don't handle the event, we need to put the PG back into the peering
queue or else the event won't get processed... - 10:57 PM Revision 7f826747 (ceph): ci: use ceph next tree
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 10:54 PM Revision c1080b22 (ceph): doc: Clean up pool usage.
- Signed-off-by: John Wilkins <jowilkin@redhat.com>
- 10:54 PM Revision 38f424d7 (ceph): doc: Cleanup RGW pool usage.
- Signed-off-by: John Wilkins <jowilkin@redhat.com>
- 10:52 PM Revision 8b9c58c4 (ceph): Merge pull request #3341 from liewegas/wip-10504
- client: add ceph version to metadata
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:52 PM Revision ddde5818 (ceph): rados: add support for object listing
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 10:46 PM Revision 2b8309e8 (ceph): rados: set reasonable default buf size
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 10:41 PM Revision e6a4ab13 (ceph): client: include ceph and git version in client metadata
- Fixes: #10504
Signed-off-by: Sage Weil <sage@redhat.com> - 10:30 PM Revision ac6674c1 (ceph): Merge pull request #3325 from ceph/wip-nits
- allow 'ops' instead of 'dump_ops_in_flight'
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:18 PM Revision f90c48f2 (ceph): Revert "rgw: switch to new watch/notify API"
- This reverts commit dc67cd69604ec4e4df846b818ec739dc7b09a537.
Conflicts:
src/rgw/rgw_rados.cc - 10:12 PM Revision 3fb080ff (ceph): Merge pull request #3250 from ceph/wip-10372
- osdc/Objecter: improve pool deletion detection
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:45 PM Revision 6d7acd37 (ceph): Merge pull request #3313 from ceph/wip-asok-get-subtrees
- Add MDS "get subtrees" asok command
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redh... - 09:29 PM Revision fe56c439 (ceph): Merge pull request #3312 from ceph/wip-mdscacheobject-const
- mds: support constness in MDSCacheObjects
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:00 PM Revision 573f0f1f (ceph): rados: fix receiver name
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:37 PM Revision 4b43b9e1 (ceph): rados: add get_pool_name
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:13 PM Revision 5a248f6c (ceph): rados: add rados_ioctx_pool_stat
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:58 PM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- direct io failure is fixed by "ceph: fix reading inline data when i_size > PAGE_SIZE"
- 04:18 PM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- the directio failure is caused by the 'reading inline data' changes
- 10:47 AM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- Zheng?
- 07:37 PM Revision 62e6137f (ceph): rados: add ioctx destroy method
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:33 PM Revision 7316c3d7 (ceph): rados: rename pool to ioctx
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:11 PM Revision 7ca7bc53 (ceph): doc: add doc file
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:34 PM Revision 7f3497b0 (ceph): Merge pull request #3248 from dachary/wip-table-formatter
- add table to Formatter
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:26 PM Revision f8878172 (ceph): doc: Added section to install priorities/preferences.
- Signed-off-by: John Wilkins <jowilkin@redhat.com>
- 06:23 PM Revision bf8f0625 (ceph): rgw: only keep track for cleanup of rados objects that were written
- Fixes: #10311
We're keeping track of rados objects that we've written so that we could
clean them up if needed. Earl... - 05:13 PM Revision 7d17a17d (ceph): Merge pull request #3324 from mattrichards/rados_translate_op_flag
- librados: Translate operation flags from C APIs
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:52 PM Revision 7c5faceb (ceph): Merge pull request #3328 from xiaoxichen/memstore_size_u64
- Bump memstore_device_bytes from U32 to U64
Reviewed-by: Sage Weil <sage@redhat.com> - 03:42 PM Revision ca87973f (ceph): Merge pull request #3337 from dachary/wip-10494-disable-unittest-msgr
- tests: temporarily disable unittest_msgr
- 03:21 PM Revision 55a5c5f2 (ceph): tests: temporarily disable unittest_msgr
- http://tracker.ceph.com/issues/10494 Refs: #10494
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 03:02 PM Bug #10505 (Resolved): test/centos/Dockerfile.in is missing parted
- it is needed for ceph-disk tests to run
- 02:51 PM CephFS Feature #10504: kclient: include client version in client_metadata
- That userspace bit got merged.
- 02:48 PM CephFS Feature #10504: kclient: include client version in client_metadata
- https://github.com/ceph/ceph/pull/3341 for the userspace side!
- 01:53 PM CephFS Feature #10504 (Resolved): kclient: include client version in client_metadata
- It would be helpful for debugging. Probably just put it in Client::populate_metadata() for userspace; I imagine the k...
- 02:48 PM Revision d4aec89e (ceph): Merge pull request #3331 from dachary/wip-10493-async-port
- msg: initialize AsyncConnection::port
Reviewed-by: Haomai Wang<haomaiwang@gmail.com> - 02:42 PM Revision 2710b2e3 (ceph): Merge pull request #279 from ceph/wip-cephfs-cleanup
- Assorted cleanup in the CephFS tests
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:27 PM Revision 1c1897e6 (ceph): mds: give CDir a dump() method for JSON output
- Useful when listing subtrees via admin socket.
Signed-off-by: John Spray <john.spray@redhat.com> - 02:27 PM Revision 26e7d5fa (ceph): mds: add asok command for getting subtreemap
- For when we want to inspect this from a test or
during debugging.
Signed-off-by: John Spray <john.spray@redhat.com> - 02:20 PM Revision a58d1042 (ceph): mds: support constness in MDSCacheObjects
- So that one can have const CInode and CDir references
from time to time.
Signed-off-by: John Spray <john.spray@redha... - 02:12 PM Bug #10372 (Pending Backport): FAILED assert(check_latest_map_ops.find(op->tid) (firefly,giant)
- 01:48 PM CephFS Bug #10503 (Resolved): ceph-fuse: quota code is not 32-bit safe for vxattr output
- From the gitbuilders:...
- 01:28 PM Revision e9033bb1 (ceph): librbd: shadow variable in snap_unprotect and list_children
- The shadow variable prevented snap_unprotect from returning the
correct error return code.
Signed-off-by: Jason Dill... - 01:16 PM Revision cf432fa6 (ceph): doc: Add Librados PHP documentation
- 12:57 PM Revision 9e356cdd (ceph): Merge pull request #3332 from dachary/wip-9570-filejournal
- journal related cleanups
Reviewed-by: Jianpeng Ma <jianpeng.ma@intel.com> - 12:22 PM Stable releases Tasks #10501 (Resolved): giant v0.87.1
h3. integration
* branch : https://github.com/ceph/ceph/tree/giant-backports
* inventory http://workbench.da...- 12:20 PM Revision d994e601 (ceph): common: Formatter: cosmetic re-indent
- Signed-off-by: Andreas Peters <andreas.joachim.peters@cern.ch>
- 12:20 PM Revision e797dcf6 (ceph): common: Formatter: add TableFormatter class
- For more human readable and shell parsable output.
Signed-off-by: Andreas Peters <andreas.joachim.peters@cern.ch> - 12:19 PM Revision 9406b7f7 (ceph): osd: accumulate authoritative peers during recovery
- When PGBackend::be_compare_scrubmaps finds multiple good peers, it only
keeps the last one. This is fine for replicat... - 12:19 PM Revision c528d87a (ceph): erasure-code: test repair when file is removed
- Add tests for when files disappear from the file system :
* file is missing from the primary OSD
* file is missi... - 12:16 PM Revision 16c6d0d5 (ceph): erasure-code: relax cauchy w restrictions
- A restriction that the w parameter of the cauchy technique is limited to
8, 16 or 32 was added incorrectly while refa... - 12:11 PM Revision adf8798d (ceph): crush/CrushWrapper: fix _search_item_exists
- Reported-by: Pawel Sadowski <ceph@sadziu.pl>
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit ee... - 12:11 PM Revision ced24726 (ceph): crush/builder: prevent bucket weight underflow on item removal
- It is possible to set a bucket weight that is not the sum of the item
weights if you manually modify/build the CRUSH ... - 12:11 PM Revision 636b98fa (ceph): crush/CrushWrapper: fix create_or_move_item when name exists but item d...
- We were using item_exists(), which simply checks if we have a name defined
for the item. Instead, use _search_item_e... - 12:05 PM Revision ecc3bcab (ceph): os: remove debug message leftover in FileJournal
- The len of the buffer shows in the message above anyway.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 12:05 PM Revision bcdbbd56 (ceph): os: fix confusing indentation in FileJournal::corrupt
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 11:17 AM Bug #10499 (Rejected): "INFO: rcu_sched detected stalls on CPUs/tasks" in upgrade:dumpling-x-fire...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2015-01-07_19:13:02-upgrade:dumpling-x-firefly-distro-basi...
- 11:05 AM devops Bug #10308 (Resolved): "FATAL: Chef::Exceptions::ChildConvergeError" in upgrade:dumpling-x-firefl...
- 11:02 AM CephFS Feature #10498 (New): ObjectCacher: order wakeups when write calls block on throttling
- The ObjectCacher can block write calls if the dirty data limits are exceeded by sleeping on a cond. Unfortunately, we...
- 10:57 AM Revision 63c8dd0a (ceph): msg: initialize AsyncConnection::port
- http://tracker.ceph.com/issues/10493 Fixes: #10493
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 10:12 AM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- Ken, you maybe right, but we need to address this issue from high level standpoint, so those issues causing lots of s...
- 05:30 AM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- Yuri Weinstein wrote:
> In run http://pulpito.ceph.redhat.com/teuthology-2015-01-07_02:10:01-samba-firefly-distro-ba... - 10:09 AM Revision 997c0c3d (ceph): tasks/cephfs: remove `config` from Filesystem cons
- This was only used in get_first_mon, which doesn't actually
need the parameter itself. Makes it easier to casually
u... - 10:09 AM Revision b1e35a42 (ceph): tasks/mds_auto_repair: remove unneeded log settings
- The small segments and small segment limit
were used when doing a hacky flush by doing
IO and waiting: now that we ha... - 10:09 AM Revision 951d6c29 (ceph): tasks/cephfs: use set_conf() from test case class
- ...because this is the one that will store up
changes to roll back during teardown.
Doing this makes it easy to run ... - 10:09 AM Revision 5e3f5766 (ceph): tasks/cephfs: be more precise in set_clients_block
- Instead of blocking the whole port range (which
might make OSDs running on that node collateral
damage), read the MDS... - 10:09 AM Revision 8630c4ab (ceph): tasks/cephfs: move ROOT_INO into filesystem module
- ...so that other tests can get at it.
Signed-off-by: John Spray <john.spray@redhat.com> - 10:09 AM Revision 4ff48195 (ceph): tasks/cephfs: umount unused clients before running
- When unused clients were mounted during an fs new,
they would end up in a state where they stalled
on subsequent atte... - 10:09 AM Revision cfbc277c (ceph): tasks/cephfs: move common setUp/tearDown to parent
- Now that we have more of these cases, there was lots
of duplication in setup and teardown. For some tests
the "reset... - 10:08 AM Revision 6d79e391 (ceph): tasks/cephfs: move wait_until helpers to testcase
- ...so that other test cases can use them
Signed-off-by: John Spray <john.spray@redhat.com> - 10:07 AM Revision 213641f3 (ceph): tasks/ceph: update mds auth caps to 'allow *'
- Since the new 'tell' for the MDS was introduced,
caps have to have the '*' to permit running remote
administrative co... - 09:56 AM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- If I'm understanding my quick skim correctly, this is not "MPI tests are failing" but "this mpi-fsx" test is failing,...
- 03:39 AM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- Is this a new failure on the existing cluster, or something that's come up on the new cluster?
- 09:33 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Thanks for that, I'll try to test it if I get a chance.
I believe I've narrowed the original problem that gets me ... - 09:12 AM Bug #10497 (Resolved): librados: c api does not translate op flag
- This means the flags aren't passed to rados as intended, and don't work through the C api.
Fixed in master by http... - 08:15 AM Revision c60f88ba (ceph): Bump memstore_device_bytes from U32 to U64
- U32 limit the max size of memstore to a few GB, which
block our test on memstore performance(as a phototype).
Bump i... - 07:29 AM Bug #10494: unittest_msgr : segmentation fault
- The following happened with a run done with a different set of flags....
- 07:03 AM Bug #10494: unittest_msgr : segmentation fault
- Another assert...
- 06:39 AM Bug #10494: unittest_msgr : segmentation fault
- Another run fails in a different way:...
- 06:31 AM Bug #10494: unittest_msgr : segmentation fault
- Run with...
- 06:29 AM Bug #10494 (Resolved): unittest_msgr : segmentation fault
- Steps to reproduce:...
- 06:45 AM Bug #10493 (Resolved): AsyncConnection::port is not initialized
- 03:00 AM Bug #10493 (Fix Under Review): AsyncConnection::port is not initialized
- https://github.com/ceph/ceph/pull/3331
- 02:55 AM Bug #10493 (Resolved): AsyncConnection::port is not initialized
- The http://workbench.dachary.org/ceph/ceph/blob/master/src/msg/async/AsyncConnection.cc#L185 constructor does not ini...
- 04:51 AM Bug #10216: gf-complete and jerasure call exit(1)
- https://github.com/ceph/ceph/pull/3334
- 04:01 AM Bug #9570 (Can't reproduce): osd crash in FileJournal::WriteFinisher::entry() aio
- It looks like it did not show up in the past three months, mark it "Can't reproduce" until it does.
- 03:58 AM Fix #10443 (Rejected): compressing ceph-test-dbg takes a long time
- there is no way to fix this
- 02:40 AM Bug #10383 (Resolved): unittest_msgr : illegal instruction
- 02:31 AM Revision c26ebd38 (ceph): Merge pull request #3217 from boydc2014/firefly
- clear data and payload after removed from ops_in_flight
Reviewed-by: Sage Weil <sage@redhat.com> - 02:18 AM Revision 8811df3e (ceph): FileStore: return error if get_index fails in lfn_open
- (*index).index is NULL if get_index fails, need to return error in this
case.
Signed-off-by: Zhiqiang Wang <zhiqiang... - 01:30 AM Revision f93e531d (ceph): Fix mpi calls
- added missing -o option to mpi exec.
added gmnt file reference to mpi exec.
run fsx-mpi as sudo.
run chef task so tha... - 01:15 AM Linux kernel client Bug #10418: ceph: can't block inside wait loops
- 12:33 AM Bug #10479: Object will be treated as "not exist" if primary shard is lost or failed to get atrr ...
- Hi, i remembered samuel do a work which repair single object. After this, we can easyly make the object repair and wa...
- 12:32 AM Revision b67b7e7a (ceph): Merge pull request #3127 from ktdreyer/firefly-no-epoch
- Revert "ceph.spec.: add epoch"
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com>... - 12:31 AM Revision db927186 (ceph): Merge pull request #3128 from dachary/wip-10281-make-check-fedora-20
- tests: fixes to run make check on fedora 20
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjus... - 12:30 AM Revision 0d4abdaf (ceph): Merge pull request #3169 from ceph/wip-8797-firefly
- Wip 8797 firefly
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: L... - 12:28 AM Revision 1fdcb524 (ceph): Merge pull request #3179 from dachary/wip-9998-crush-underfloat-firefly
- crush: fix weight underfloat issue (firefly)
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sju... - 12:28 AM Revision 4b7b1b03 (ceph): Merge pull request #3220 from ceph/wip-mon-backports.firefly
- mon: backports for #9987 against firefly
Reviewed-by: Joao Eduardo Luis <joao@redhat.com>
Reviewed-by: Sage Weil <sa... - 12:26 AM Revision 4897ba4a (ceph): Merge pull request #3258 from ceph/wip-10372-firefly
- osd: fix librados pool deletion race on firefly
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <s... - 12:14 AM Revision 492ccc90 (ceph): osd: requeue PG when we skip handling a peering event
- If we don't handle the event, we need to put the PG back into the peering
queue or else the event won't get processed... - 12:14 AM Revision 20be188d (ceph): osd: assert there is a peering event
- This became conditional way back in 12e22b3d44eba51a70d8babebc2684f0c46575a7
for unclear reasons. It probably predat...
01/08/2015
- 09:16 PM Revision 49d114f1 (ceph): librados: Translate operation flags from C APIs
- The operation flags in the public C API are a distinct enum
and need to be translated to Ceph OSD flags, like as happ... - 09:09 PM Revision 8d52782a (ceph): rgw: use gc for multipart abort
- Fixes: #10445
Instead of chewing through a potentially very large list of objects
synchronously, leave it to the gar... - 09:06 PM Revision 1e444e91 (ceph): Merge pull request #3321 from cernceph/wip-nobarrier-doc
- doc: don't suggest mounting xfs with nobarrier
Reviewed-by: Sage Weil <sage@redhat.com> - 08:57 PM Revision c2929f14 (ceph): Merge pull request #3322 from dachary/wip-10426-test-directories
- tests: group clusters in a single directory
Reviewed-by: Sage Weil <sage@redhat.com> - 08:32 PM Revision 8033c749 (ceph): Merge pull request #283 from ceph/issue-10275
- Use qemu-kvm in the qemu task for rpm based systems.
- 08:31 PM Revision 5644a320 (ceph): Use qemu-kvm in the qemu task for rpm based systems.
- Signed-off-by: Andrew Schoen <aschoen@redhat.com>
- 07:16 PM devops Bug #10492 (Duplicate): rhel7 missing packadges
- Packages for os_type 'centos' and ceph hash 'b67b7e7ad72a1af96f9fb26ade815e65f72b4cb0' not found...
- 06:39 PM Revision 1b22857f (ceph): Merge pull request #3306 from ceph/wip-10041
- client: fix mount timeout
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:36 PM Revision 6edfcc1d (ceph): mds: allow 'ops' as shorthand for 'dump_ops_in_flight'
- This is an extremely annoying thing to type when working with a
production cluster.
Signed-off-by: Sage Weil <sage@r... - 06:36 PM Revision 1617fbb3 (ceph): osd: allow 'ops' as shorthand for 'dump_ops_in_flight'
- This is an extremely annoying thing to type when working with a
production cluster.
Signed-off-by: Sage Weil <sage@r... - 06:33 PM Bug #10431: PG can not finish peering due to mismatch between OSD peering queue and PG peering queue
- Hi sage, sorry for my first commit in the PR which add a unnecessary lock. But what I did in the second commit is wha...
- 01:25 PM Bug #10431 (Fix Under Review): PG can not finish peering due to mismatch between OSD peering queu...
- I believe we just found this bug.. can you please look at
https://github.com/ceph/ceph/pull/3326 - 06:00 PM Bug #10490 (Duplicate): osd: bad state machine event, RequestBackfilPrio in RepRecovering
- ...
- 05:52 PM CephFS Feature #1398: qa: multiclient file io test
- See #10489 for a related issue.
- 05:50 PM CephFS Feature #1398 (Fix Under Review): qa: multiclient file io test
- pull request #284 for wip-1398-multiclientio-wusui has been made.
commit: f93e531de6fa69a3ad32117c613094fc0aa0283e - 01:16 PM CephFS Feature #1398: qa: multiclient file io test
- changes look ok, although you can probably just use mnt.0 instead of the gmnt symlink.
also, make sure the -dev p... - 05:18 PM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- Running teuthology using the following yaml demonstrates this problem:...
- 05:15 PM CephFS Subtask #10489: Mpi tests fail on both ceph-fuse and kclient
- Running teuthology using the following yaml demonstrates this problem:...
- 05:05 PM CephFS Subtask #10489 (New): Mpi tests fail on both ceph-fuse and kclient
- Mpi tests fail on ceph-fuse and kclient. I will post some tests and results that demonstrate this failure.
- 04:37 PM Bug #10281 (Resolved): firefly: make check fails on fedora 20
- 04:34 PM Bug #9987: mon: min_last_epoch_complete tracking broken
- * firefly backport https://github.com/ceph/ceph/pull/3220
- 04:33 PM Bug #10372 (Resolved): FAILED assert(check_latest_map_ops.find(op->tid) (firefly,giant)
- 04:21 PM Feature #10426 (Resolved): group test mini cluster directories together
- 02:13 AM Feature #10426 (Fix Under Review): group test mini cluster directories together
- 04:01 PM Bug #10483 (Duplicate): erasure-code-profile set fails on mon thrashing
- 11:38 AM Bug #10483 (Duplicate): erasure-code-profile set fails on mon thrashing
- http://pulpito.ceph.com/sage-2015-01-06_09:44:19-rados-wip-sage-testing-firefly---basic-multi/688168/...
- 04:00 PM Bug #10488 (Resolved): osd erasure-code-profile set is sometimes not idempotent
- When http://workbench.dachary.org/ceph/ceph/blob/giant/src/mon/OSDMonitor.cc#L4531 compares the profile to be created...
- 01:38 PM Bug #10487 (Can't reproduce): logclient: setting clog_to_monitor=false on live osd crashes
- ...
- 01:15 PM Support #10486: OSD Keeps Going Down
- Shun Mok Bhark wrote:
> Looking further up the log it has a osd_ping stamps.
- 01:15 PM Support #10486: OSD Keeps Going Down
- Looking further up the log it has a osd_ping stamps.
Isn't this a failed assert?
9: (ceph::__ceph_assert_fail... - 01:12 PM Support #10486: OSD Keeps Going Down
- if you look further up in the log you should see why it is crashing.. a segfault message or failed assert or something?
- 01:07 PM Support #10486 (New): OSD Keeps Going Down
- Hello,
I am encountering an issue where an OSD (OSD.1) keeps going down and out.
Initially I thought it was a d... - 01:00 PM rbd Documentation #10478: Update Glance configuration docs for Juno
- I found this is not a bug exactly as it only have lacking line under the DEFAULT section that you should put rbd in t...
- 12:59 PM rgw Bug #10445: Radosgw hang, corrupt manifest?
- I pushed a change to wip-10445. Now, instead of waiting for the completion, it'll just send it to the garbage collect...
- 12:59 PM rgw Bug #10445: Radosgw hang, corrupt manifest?
- you can run:...
- 09:36 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Ah I see what you mean. But I'm not sure what is causing these specific uploads to be so slow to remove. If I start a...
- 09:28 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- I don't see the gateway stuck in infinite loop. It just goes too slow, so the client retries (while the first operati...
- 07:13 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Ok I still don't know how it gets into this state to begin with but right now I have objects or partial uploads where...
- 12:27 PM Bug #10485 (Resolved): unreadable ceph-osd core dump (firefly)
- http://pulpito.ceph.com/sage-2015-01-06_09:44:19-rados-wip-sage-testing-firefly---basic-multi/688290/
has a core dum... - 11:59 AM Bug #10484 (Won't Fix): unable to revive osd with valgrind
- if its kill -9 it sounds like daemon-helper, which would be triggered by a network blip killing the connections from ...
- 11:52 AM Bug #10484 (Won't Fix): unable to revive osd with valgrind
- http://pulpito.ceph.com/sage-2015-01-06_09:44:19-rados-wip-sage-testing-firefly---basic-multi/688210/
It looks lik... - 11:53 AM Revision 3d2fbf70 (ceph): tests: group clusters in a single directory
- Group all test directories used for mini clusters into a single
sub-directory (testdir). This is easier to cleanup ma... - 11:26 AM Bug #6003: journal Unable to read past sequence 406 ...
- http://qa-proxy.ceph.com/teuthology/sage-2015-01-06_09:44:19-rados-wip-sage-testing-firefly---basic-multi/688065/
<p... - 11:16 AM rgw Bug #10482 (Won't Fix): rgw: older versions need to be able to sign requests with 'versions' subr...
- In firefly and giant we need to make it handle the 'versions' subresource correctly when listing buckets (even thoug...
- 11:03 AM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- In run http://pulpito.ceph.redhat.com/teuthology-2015-01-07_02:10:01-samba-firefly-distro-basic-magna/
We get @'su... - 11:02 AM Revision 3c1d3ddc (ceph): Merge pull request #3215 from dachary/wip-10384-ceph-test-helper-races
- tests: resolve ceph-helpers races
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:40 AM CephFS Bug #10041 (Resolved): ceph-fuse: never exit when no MDS server is available
- Merged into master as of commit:1b22857f2bc945ad2f5e60a2cc6f9be24d977079.
- 08:49 AM Revision bd7be04d (ceph): doc: don't suggest mounting xfs with nobarrier
- nobarrier is dangerous, so stop suggesting it as an example osd mount
options xfs.
Signed-off-by: Dan van der Ster <... - 08:43 AM Linux kernel client Bug #10418: ceph: can't block inside wait loops
- Hi Zheng,
I noticed you fixed the one in ceph_mdsc_sync(). There seem to be two more of these:
wait_event_inte... - 06:14 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- ok, i have now a test running with all three kernel patches plus the one mentioned in #10450.
- 04:39 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- looks like kernel bug, please try attached kernel patches
- 02:07 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Out of 8 crashes, there was only one incident with slow requests in the logs. I added the mds/mon logs for further in...
- 05:29 AM Revision 8b3dfc94 (ceph): rgw: check keystone auth also for s3 post requests
- This patch adds keystone auth for s3 post requests, once a user fails in
cephx authentication, they are checked for k... - 04:05 AM Revision 574be5ba (ceph): Merge pull request #280 from ceph/wip-10387-cleanup
- tasks/mds_flush: remove #10387 workaround
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:58 AM Feature #9948 (In Progress): osd: add scrub result query interface
- 03:15 AM Bug #9235: unittest_histogram test case Histogram.Position fail
- * firefly backport https://github.com/ceph/ceph/pull/3128
- 03:11 AM devops Feature #10046: run make check on every pull request
- had to fix a) timeout, b) output overflow when rebuilding the container because its dependencies changed, c) fix fail...
- 03:01 AM Bug #10384 (Resolved): ceph-test-helpers may race
- 03:01 AM Bug #10389 (Resolved): init-ceph stop may return before daemons are stopped
- 02:29 AM Revision 27cb78bd (ceph): mon, os: check the result of sync_filesystem.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:25 AM Revision fa96bb4d (ceph): librbd: Stub out new exclusive image feature
- When an image is flagged with the exclusive feature, only a
single client can modify the image. This is groundwork f... - 02:25 AM Revision 3646e1e4 (ceph): encoding: wrap ENCODE_START/FINISH arguments
- Wrapped the bufferlist argument with parentheses to prevent
compile errors when attempting to pass a dereferenced buf... - 01:55 AM Revision 4280d004 (ceph): Merge pull request #3310 from ceph/wip-mdsmonitor-fixes
- MDSMonitor fixes
- 12:24 AM Bug #10479 (Duplicate): Object will be treated as "not exist" if primary shard is lost or failed ...
- When reading an object, if primary shard is lost or primary OSD can't get attr from this shard, e.g, EIO, primary wil...
01/07/2015
- 10:20 PM Revision 478629bd (ceph): rgw: index swift keys appropriately
- Fixes: #10471
Backport: firefly, giant
We need to index the swift keys by the full uid:subuser when decoding
the jso... - 10:19 PM Revision d73f0b86 (ceph): If trusty, use older version of qemu
- Fixes #10319
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(Cherry-picked from 46a1a4cb670d30397979cd89808a2e4... - 10:14 PM Revision efe801ff (ceph): If trusty, use older version of qemu
- Fixes #10319
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cherry-picked from 46a1a4cb670d30397979cd89808a2e4... - 09:59 PM Revision 6caa4fa4 (ceph): If trusty, use older version of qemu
- Fixes #10319
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cherry-picked from 46a1a4cb670d30397979cd89808a2e4... - 09:23 PM Revision f31020da (ceph): Merge pull request #3167 from ceph/wip-10307
- rgw: use s->bucket_attrs instead of trying to read obj attrs
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-... - 06:59 PM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- there are some file lock related fixes after 3.14. did you see something like below in ceph.log
slow request 121.3... - 06:15 PM Bug #10468: osd crashed at OpRequest::_dump_op_descriptor_unlocked
- We tested a long period of time about cephs,metadata poll and data poll are separated,we write 64KB file about 48 hou...
- 06:13 PM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- sudo yum install ceph-devel-0.67.11 -y --> I am wondering if there is a version issue here. This returns an error co...
- 04:59 PM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- Same set of problems in this run http://pulpito.ceph.redhat.com/teuthology-2015-01-06_22:00:01-rados-dumpling-distro-...
- 05:12 PM Revision c1b547c4 (ceph): Inherit teuthology's log level
- Signed-off-by: Zack Cerza <zack@redhat.com>
(cherry picked from commit 31ff241f5a74d455d6e61f02065f2df43d3fa978) - 05:10 PM Revision bae3bc8e (ceph): Merge pull request #282 from ceph/wip-10469
- Inherit teuthology's log level
- 04:58 PM devops Bug #10308: "FATAL: Chef::Exceptions::ChildConvergeError" in upgrade:dumpling-x-firefly-distro-ba...
- Same set of problems in this run http://pulpito.ceph.redhat.com/teuthology-2015-01-06_22:00:01-rados-dumpling-distro-...
- 04:53 PM Revision 31ff241f (ceph): Inherit teuthology's log level
- Signed-off-by: Zack Cerza <zack@redhat.com>
- 04:44 PM rbd Documentation #10478 (Resolved): Update Glance configuration docs for Juno
- Hi,
It seems there is a bug or maybe on the documentations mentioned on http://ceph.com/docs/master/rbd/rbd-openst... - 04:01 PM Bug #10474 (Fix Under Review): Testing wip-9780-9781 hung ceph-objectstore-tool on import
- 03:59 PM Bug #10474: Testing wip-9780-9781 hung ceph-objectstore-tool on import
This is a caused the journal's write thread waiting for full_state to go to FULL_NOTFULL, at the same time that onl...- 03:14 PM Bug #10474: Testing wip-9780-9781 hung ceph-objectstore-tool on import
- End of log shows entire umount sequence.
2015-01-06 15:38:59.771186 7f7692bce900 5 filestore(/var/lib/ceph/osd/ce... - 12:42 PM Bug #10474: Testing wip-9780-9781 hung ceph-objectstore-tool on import
This thread didn't notice that write_stop is set in ENOSPC handling:
Thread 5 (Thread 0x7f7688a43700 (LWP 47834)...- 12:22 PM Bug #10474 (Resolved): Testing wip-9780-9781 hung ceph-objectstore-tool on import
- ceph-objectstore-tool --data-path /var/lib/ceph/osd/ceph-2 --journal-path /var/lib/ceph/osd/ceph-2/journal --log-file...
- 03:47 PM Revision 1c1f7c35 (ceph): Merge pull request #3036 from dachary/wip-make-check
- packages: add python-virtualenv and xmlstarlet
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 03:08 PM Feature #10477 (Resolved): pg query should output the replicas the primary is waiting on between ...
- - useful state name (not just 'inactive')
- qeury needs to say who we are waiting for
- blocked_by set needs to be ... - 02:31 PM Revision f6bcbe37 (ceph): tasks/mds_flush: remove #10387 workaround
- Now that #10387 is fixed in master, we can tighten
up this test to ensure that the expected deletions
are happening.
... - 02:30 PM Revision e9a29c58 (ceph): Merge pull request #3269 from ceph/wip-10387
- client: close dirfrag whem rmdir
Reviewed-by: John Spray <john.spray@redhat.com> - 02:13 PM Revision c400ba1e (ceph): mon/MDSMonitor: respect MDSMAP_DOWN when promoting standbys
- Previously, a standby could become active even if 'cluster_down'
had been run. This was awkward, because it would ge... - 02:13 PM Revision 97cc409f (ceph): mon/MDSMonitor: fix `mds fail` for standby MDSs
- This command takes a gid, rank or name, but
in the name case it would previously only work if
the named daemon had a ... - 02:06 PM rgw Bug #10471 (Fix Under Review): rgw: metadata sync doesn't create subusers correctly
- 09:48 AM rgw Bug #10471 (Resolved): rgw: metadata sync doesn't create subusers correctly
- 01:25 PM rgw Bug #10475 (Resolved): rgw: setting bucket metadata via swift api removes existing metadata
- According to http://docs.openstack.org/api/openstack-object-storage/1.0/content/POST_updateContainerMeta__v1__account...
- 01:22 PM rgw Bug #10307 (Pending Backport): rgw: setting bucket attributes (swift POST on bucket) sometimes fail
- 10:39 AM Bug #10473 (Rejected): mon: not discarding messages from disconnected clients (firefly)
- observed on a 0.80.7 cluster: very old log messages on peon mons still being repeatedly resent to the leader, despite...
- 09:52 AM Revision 487c22a8 (ceph): init-ceph: stop returns before daemons are dead
- The existence of the pidfile must be checked outside of the loop to send
a signal to the daemon. Otherwise the daemon... - 09:14 AM Revision fd4ac46b (ceph): crush/crush.c: prevent DIVIDE_BY_ZERO
- Fix for:
CID 1219471 (#1 of 1): Division or modulo by zero (DIVIDE_BY_ZERO)
divide_by_zero: In function call crush_... - 09:14 AM Revision b99508b3 (ceph): osd/ClassHandler.cc: move stat into error handling
- There is no security advantage to check if the class file
exists before opening it but the file could be removed or
e... - 09:14 AM Revision 3d08a687 (ceph): msg/async/AsyncConnection.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision b0870082 (ceph): src/mds/MDS.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 678ece89 (ceph): common/Cycles.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision b7b13d21 (ceph): ceph_monstore_tool.cc: unsigned can't be less than zero
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 2bd18331 (ceph): msg/async/EventSelect.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 7b5ccb73 (ceph): msg/async/AsyncMessenger.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision a58446c4 (ceph): tools/ceph_authtool.cc: reduce scope of some variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 78542f9a (ceph): ceph_objectstore_tool.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 5ca47099 (ceph): test/librados/snapshots.cc: fix resource leak, delete op
- Fix for:
CID 1260395 (#2 of 2): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable op going out of scope leaks ... - 09:14 AM Revision 8511b559 (ceph): librados/librados.cc: fix UNINIT issue
- Fix for issues introduced with cba4ed44f:
CID 1256099 (#1 of 1): Uninitialized pointer read (UNINIT)
uninit_use: Us... - 09:14 AM Revision c27e0fe9 (ceph): mds/MDLog.cc: fix uninitialized pointer read
- Fix for Coverity issue:
CID 1238902 (#1 of 1): Uninitialized pointer read (UNINIT)
uninit_use: Using uninitialized ... - 09:14 AM Revision aacdaae1 (ceph): src/common/obj_bencher: fix some UNINIT issues
- Make sure concurrentios is always >= 0 to fix these coverity
issues and to prevent bad_alloc/negative array sizes:
C... - 09:14 AM Revision 1a00fb70 (ceph): test/librados/aio.cc: release completion before exit
- CID 1242020 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable my_completion going out of scope
leak... - 09:14 AM Revision 3ccd792f (ceph): client/Client.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 69f82236 (ceph): ceph_context.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 369af322 (ceph): perf_counters.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 42417e2d (ceph): KeyValueStore.cc: prefer !empty() over size() for emptiness check
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 252fc03b (ceph): ceph_objectstore_tool.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 936b98a2 (ceph): client/Client.cc: cleanup code to silence cppcheck
- Remove not needed goto statement and silence cppcheck
warning about possible null pointer deref of 'in'.
Signed-off-... - 09:14 AM Revision 36dd487a (ceph): configure.ac: fix warnings about unknown commands
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision 2ab4003c (ceph): mds/Capability.h: init num_revoke_warnings in constructor
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:14 AM Revision f19c2e68 (ceph): mds/Server.cc: fix compiler warning
- Fix compiler warning caused by twice checking but missing
final else block.
In file included from mds/MDS.h:20:0,
... - 09:14 AM Revision ed7ca162 (ceph): test_mon_workloadgen.cc: fix warning about self init
- Fix for:
[src/test/mon/test_mon_workloadgen.cc:351]: (error) Member variable
'whoami' is initialized by itself.
Si... - 09:14 AM Revision 79d63a08 (ceph): bench/tp_bench.cc: fix warning about self init
- Fix for:
[src/test/bench/tp_bench.cc:103]: (error) Member variable 'next'
is initialized by itself.
Signed-off-by:... - 09:14 AM Revision 2f542094 (ceph): test/librados/aio.cc: delete AioCompletion* before return
- CID 1242018: Resource leak (RESOURCE_LEAK)
leaked_storage: Variable aio_completion going out of scope leaks
the sto... - 08:44 AM rgw Bug #10354: Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-multi run
- Same problems in run http://pulpito.ceph.com/teuthology-2015-01-06_17:15:01-upgrade:dumpling-firefly-x:parallel-next-...
- 08:27 AM Revision 485d1390 (ceph): client: fix mount timeout
- implement a simple timeout mechanism for make_request()
Fixes: #10041
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 07:39 AM rbd Bug #10139: librbd cpu usage 4x higher than krbd
- Ran perf testing with same fio spec using the librados_test_stub (in-process, simulated RADOS backend). I don't see ...
- 07:28 AM Revision 397b2616 (ceph): common: Don't call ioctl(BTRFS_IOC_SYNC) in sync_filesystem.
- From the manual of syncfs, it first appeared in Linux 2.6.39. At this
point, btrfs didn't as a stable production. So ... - 07:26 AM Revision 3f7faa4d (ceph): common: Directly return the result of syncfs().
- In commit 808c644248e4, it will try sync() if syncfs() return error.
No evidence prove this way can work. And sync() ... - 06:14 AM Revision 1c38895f (ceph): disable tcmalloc by default when enable jemalloc
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 03:57 AM Fix #9484: OSD: block until we have the same map as the client on pg commands
- Please look at https://github.com/ceph/ceph/pull/3309 which might be solution for this issue.
- 03:55 AM Feature #9483: OSD: add a get_newest_map command to the admin socket
- https://github.com/ceph/ceph/pull/3309
- 12:28 AM CephFS Bug #10041 (Fix Under Review): ceph-fuse: never exit when no MDS server is available
01/06/2015
- 11:24 PM Revision 6fd348fe (ceph): Merge remote-tracking branch 'origin/wip-10270' into master
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
src/librados/IoCtxImpl.cc
src/librados/IoCtxImpl.h - 10:54 PM Bug #10468 (Resolved): osd crashed at OpRequest::_dump_op_descriptor_unlocked
- when test cephfs,osd crush.
ceph version 0.90 (08bd1e1eee37c80ee033c067f678236da38b1694)
coredump information:... - 09:48 PM Revision 1a13d92b (ceph): Merge branch 'wip-fast-txn'
- Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:29 PM Revision fda60197 (ceph): osd: add feature CEPH_FEATURE_OSD_TRANSACTION_MAY_LAYOUT (1ULL<<47)>>)
- This feature determine whether we use tbl encode for transaction of use
the new map layout.
The primary uses peer_fe... - 09:29 PM Revision 0354305d (ceph): osd: fix Transaction::get_data_offset bug when map layout used
- add following offset:
sizeof(__u8) + // encode struct_v
sizeof(__u8) + // encode compat_v
sizeof(__u3... - 09:29 PM Revision 5d665252 (ceph): ceph-object-corpus: drop compat with old ObjectStore::Transaction
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:29 PM Revision 95d2174e (ceph): osd/ECBackend: make sure localt uses tbl is ec txn does
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:29 PM Revision 3bd00421 (ceph): osd: remove unused Transaction fields
- We don't need sobject and pool_override anymore since we don't need to
support anything older than dumpling.
Change-... - 09:29 PM Revision dbae9225 (ceph): osd: Add Transaction::TransactionData for fast encode/decode
- TransactionData wrap the following fields:
__le64 ops;
__le32 largest_data_len;
__le32 largest_data... - 09:29 PM Revision 3db4f696 (ceph): osd: new format for Transaction encode/decode
- This patch add a new fixed size struct Transaction::Op to represent
all actions.
All coll and ghobject used by the t... - 09:29 PM Revision a4575d10 (ceph): osd: add encode/deocde impl for new layout
- When use_tbl is true, Transaction::encode will give the same result as
before, while when use_tbl is false, Transacti... - 09:29 PM Revision 6b2103b7 (ceph): osd: new Transaction::iterator interface
- This patch add new Transaction::iterator interface according to new
encode/decode layout. The new iterator give the w... - 09:29 PM Revision d427ca35 (ceph): osd: Transaction::append & Transaction::swap
- Finish append and swap for new Transaction encode/decode layout.
Since append will modify the op_bl now, we changed ... - 09:29 PM Revision 1889d390 (ceph): ceph_perf_objectstore: fix warning
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:29 PM Revision 5da6b41f (ceph): osd: build fields for Transaction::iterator when tbl is used
- When tbl is used (for compatibility), the Transaction::begin method need
to build all fields used by iterator. That i... - 07:18 PM CephFS Feature #1398: qa: multiclient file io test
- Here's the story so far.
The teuthology tests for mpi testing used a yaml file with the following tasks:... - 07:08 PM CephFS Bug #10416: quota test failures
- the nondeterministic design is nightmare
- 11:00 AM CephFS Bug #10416: quota test failures
- It is not fixed already:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-26_23:04:02-fs-master-testing-basic-... - 06:53 PM Bug #6301: ceph-osd hung by XFS using linux 3.10
- Some ceph error log when the xfs memory allocation deadlock...
- 05:45 PM Bug #6301: ceph-osd hung by XFS using linux 3.10
- We face to this problem in centos 7, kernel 3.10.0-123.el7.x86_64
We download the kernel source http://vault.centos.... - 06:36 PM CephFS Bug #10412 (Resolved): samba: failed smbtorture run
- this bug was introduced after giant
- 08:18 AM CephFS Bug #10412 (Pending Backport): samba: failed smbtorture run
- 04:26 AM CephFS Bug #10412 (Fix Under Review): samba: failed smbtorture run
- 06:35 PM Revision ebfe2306 (ceph): Merge pull request #3272 from trociny/tell-mon-version
- cli: make ceph tell mon.* version work
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:34 PM Revision 34c0e17d (ceph): Merge pull request #3196 from tchaikov/shadow-cct
- client, librados, osdc: do not shadow Dispatcher::cct
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:32 PM Revision 815bb9c2 (ceph): Merge pull request #3298 from majianpeng/fix5
- TestLFNIndex.cc: For root, dont do permission operations.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:10 PM Revision de021345 (ceph): tests: resolve ceph-helpers races
- Some tests were racing against the monitor. On a fast machine it worked
but slower machines (or sometime when running... - 06:07 PM Revision d7142d9a (ceph): Merge pull request #3283 from dachary/wip-make-debs
- debian: create a repository from sources
Reviewed-by: Sage Weil <sage@redhat.com> - 04:26 PM Revision 386ab7ce (ceph): Merge pull request #3301 from ktdreyer/rm-tiobench
- #10152: qa: drop tiobench suite
Reviewed-by: Sage Weil <sage@redhat.com> - 04:25 PM Revision b23da979 (ceph): Merge pull request #278 from ceph/wip-rm-tiobench
- #10152: drop tiobench tests
- 04:22 PM Feature #9956 (Fix Under Review): osd: reenable alloc hints if kernel is known to be safe
- 04:20 PM Revision 60513210 (ceph): Merge pull request #3300 from ceph/wip-10412
- client: fix use-after-free bug in unmount()
Reviewed-by: Sage Weil <sage@redhat.com> - 04:00 PM Revision bea2d4a8 (ceph): qa: drop tiobench suite
- The tiobench software has been abandoned upstream for years. Fedora and
Debian are no longer shipping the tiobench pa... - 03:59 PM Revision 8a317125 (ceph): drop tiobench tests
- The tiobench software has been abandoned upstream for years. Fedora and
Debian are no longer shipping the tiobench pa... - 03:46 PM Bug #9978 (Closed): keyvaluestore: void ECBackend::handle_sub_read
- 03:45 PM Revision 8618a537 (ceph): cli: ceph: easier debugging (pdb) with 'CEPH_DBG=1'
- 'CEPH_DBG=1 ceph foo' will now drop a pdb shell for interactive
debugging. Way better than fiddling with the source ... - 03:26 PM rgw Bug #10354 (Pending Backport): Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro...
- 03:25 PM rbd Bug #10270 (Pending Backport): "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-dist...
- commit:53929ba1751fad9c9cd8545c4cd6985982d2eb5f
- 03:11 PM Revision 9330ad60 (ceph): Merge pull request #3276 from ceph/wip-repop
- Add MOSDRepOp and MOSDRepOpReply
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:50 PM Revision 68c27cfb (ceph): Merge pull request #3299 from wonzhq/compile-warn
- cleanup: fix a compile warning
Reviewed-by: Sage Weil <sage@redhat.com> - 02:45 PM Revision 226b61aa (ceph): common/PriorityQueue: add test cases for it
- 02:29 PM Revision aff4499a (ceph): common/PrioritizedQueue: do not 'using namespace std'
- * do not assume `using namespace std` before including
PrioritizedQueue.h
Signed-off-by: Kefu Chai <tchaikov@gmail... - 02:09 PM Bug #10402 (Rejected): ceph-objectstore-tool import may need to add an OSDMap for old epoch
We are rebuilding past intervals on all imports and setting the pg epoch and same_interval_since to the OSD epoch. ...- 01:47 PM Feature #9953 (Resolved): osd: efficient ObjectStore::Transaction encoding
- 12:59 PM Feature #10452: ceph osd df
- I'd really like this data to be exposed up through Calamari too...
- 12:53 PM Feature #9781: ceph_objectstore_tool: On import handle splits
- 12:22 PM Revision 55f8fee2 (ceph): client: fix use-after-free bug in unmount()
- If there is error, _release_fh() already outputs error message.
No need to print extra error message
Fixes: #10412
S... - 11:26 AM CephFS Bug #10465: Audit and fix ceph-qa-suite exec tasks
- Also, I noticed this because http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-26_23:04:02-fs-master-testing-bas...
- 11:26 AM CephFS Bug #10465 (Resolved): Audit and fix ceph-qa-suite exec tasks
- suites/fs/basic/tasks/cfuse_workunit_suites_truncate_delay.yaml executes a dd and a truncate on a file in the local n...
- 11:16 AM Bug #10464 (Resolved): osd/osd_types.h: 3123: FAILED assert(rwstate.empty())
- ceph version 0.90-632-gcd1ed1e (cd1ed1e08f72042113305aef431f9276881aaa8b)
1: (ceph::__ceph_assert_fail(char const*... - 11:03 AM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- Zheng, we've got a new failing directio test at http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-28_23:08:01-kc...
- 10:42 AM CephFS Bug #10413: samba: coredumps after tests run
- That looks good to me (I guess?), but I don't think putting it into our own samba repo is the right place. IIRC we're...
- 10:39 AM Feature #9961 (Resolved): osd: new MOSDClientSubOp and Reply
- 10:19 AM rbd Feature #7924 (Closed): Openstack: make long-running operations async in cinder
- in openstack tracker: https://bugs.launchpad.net/cinder/+bug/1401335
- 10:11 AM Feature #10463 (Resolved): use SEEK_DATA/SEEK_HOLE for FileStore fiemap() implementation
- > In an exchange on linux-fsdevel yesterday it became clear that even when
> FIEMAP isn't buggy it's not a good inte... - 09:51 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Aaron Bassett wrote:
> https://github.com/ceph/ceph/blob/master/src/rgw/rgw_rados.cc#L589
>
> Reading this sectio... - 09:47 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- https://github.com/ceph/ceph/blob/master/src/rgw/rgw_rados.cc#L589
Reading this section, it looks to me that if pa... - 09:34 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- I did some more testing, this time I tried taking the cache tier out of play and set it up with:
a) civetweb, usin... - 09:27 AM Linux kernel client Bug #10313 (Need More Info): IO drop outs/timeouts on one of the rbd client
- 09:25 AM Linux kernel client Bug #10208: libceph: intermittent hangs under memory pressure
- A similar problem with krbd I was debugging with a user offline went away with 3.18 as far as they can tell.
I assum... - 09:22 AM rbd Feature #10462 (Resolved): rbd cli: use io hints for import/export etc
- 09:22 AM rbd Feature #10461 (Resolved): objectcacher: use librados io hints
- 09:20 AM rbd Feature #4095 (Rejected): rbd: 2-phase commit for snapshot creation
- leader stuff makes this unnecessary
- 09:06 AM rgw Feature #9932 (Resolved): rgw: map swift X-Storage-Policy header to rgw pools
- commit:77c1a35a827f4f285a4a2b47eba62465fc67d126
- 09:03 AM rgw Feature #10191 (In Progress): rgw: object versioning multi-zone support
- 08:48 AM devops Bug #10152: drop tiobench references
- The tiobench removal has been merged for ceph.git and ceph-qa-suite.git.
Proposal to remove tiobench from ceph-q... - 08:02 AM devops Bug #10152: drop tiobench references
- Proposal to remove tiobench from ceph-qa-suite.git: https://github.com/ceph/ceph-qa-suite/pull/278
- 07:46 AM devops Bug #10152: drop tiobench references
- Proposal to remove tiobench from ceph.git: https://github.com/ceph/ceph/pull/3301
- 08:36 AM Revision 93d39a84 (ceph): cleanup: fix a compile warning
- warning: 'pi' may be used uninitialized in this function
[-Wmaybe-uninitialized]
Signed-off-by: Zhiqiang Wang <zhiqi... - 08:23 AM Revision ea3ed5bb (ceph): TestLFNIndex.cc: For root, dont do permission operations.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 08:10 AM devops Bug #9725: Error "'sudo yum install ceph-radosgw-0.67.11 -y'"in upgrade:dumpling-x-firefly-distro...
- And also 'sudo yum install ceph-radosgw-0.87 -y'
Run http://pulpito.ceph.redhat.com/teuthology-2015-01-05_05:32:02... - 08:06 AM devops Bug #9725: Error "'sudo yum install ceph-radosgw-0.67.11 -y'"in upgrade:dumpling-x-firefly-distro...
- Seems to be wide spread now.
For example in this run in octo
http://pulpito.ceph.redhat.com/teuthology-2015-01-05_... - 07:57 AM devops Bug #10460 (Resolved): Missing packadge centos6
- From cron log:...
- 07:46 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Regarding the stuck requests .. I have definitely seen one or two stuck mds requests. But I had then thought they wer...
- 05:31 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- I think there was a stuck request, which prevented mds from trimming completed_requests
- 06:42 AM rgw Feature #10453 (In Progress): rgw: sync agent full sync of versioned objects
- 06:38 AM RADOS Feature #10459 (New): osd: allow startup option to skip processing old maps
- If we know that we have healthy PGs, it is mostly a waste of time for an OSD that has been down for a long time to sp...
- 03:21 AM Bug #9235 (Pending Backport): unittest_histogram test case Histogram.Position fail
- 03:19 AM Bug #8654 (Pending Backport): Parsing /etc/lsb-release for OSD metadata is not portable
- 02:24 AM Revision 8a178392 (ceph): Merge pull request #3293 from ktdreyer/help-missing-keyutils-libs-devel
- configure: show package name when libkeyutils is missing
- 12:54 AM Revision 4a42a81c (ceph): Merge pull request #3294 from ceph/wip-fix-copyfrom
- osd: fix copyfrom
Reviewed-by: Samuel Just <sjust@redhat.com>
01/05/2015
- 11:39 PM Revision 0f83a181 (ceph): Merge pull request #3226 from ceph/wip-10319-wusui
- If trusty, use older version of qemu
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 11:35 PM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- push a fix to the testing branch
- 03:44 PM CephFS Bug #10448: wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() of fs/ceph/...
- I don't think rbd uses anything under fs/ceph, so here's a category where Zheng and Sage are more likely to notice it.
- 10:37 PM Revision 488355cc (ceph): osd: fix object_copy_data_t compat encoding
- If the omap_data map is empty, we want an empty bufferlist.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:28 PM Revision 6ccdce56 (ceph): Merge pull request #3189 from ceph/wip-10329
- Wip 10329
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:03 PM CephFS Feature #1398: qa: multiclient file io test
- Here's what appears to be a bunch of problems:...
- 04:05 PM CephFS Feature #1398: qa: multiclient file io test
- Here's what looks to be the last issue:...
- 08:54 PM Revision d5e2ca16 (ceph): Merge pull request #3277 from ceph/wip-watch-leak
- librados: fix a memory leak in watch
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:53 PM Revision 78d2d310 (ceph): Add MOSDRepOp and MOSDRepOpReply
- Add the two new message type and change the corresponding code flow as well.
Basically the idea to have MOSDRepOp is... - 08:53 PM Revision ed503776 (ceph): osd/PG: print last_update_applied if != last_update
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:34 PM Revision f9f64e19 (ceph): Merge pull request #3206 from ceph/wip-librados-init
- librados: init last_objver
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:19 PM Revision 6ca2eb86 (ceph): configure: show pkg names when libkeyutils is missing
- Prior to this commit, when ./configure can't find libkeyutils, it would
bail out with a terse error message.
Some of... - 07:16 PM Revision d253badb (ceph): Merge remote-tracking branch 'gh/next'
- 07:16 PM Revision 3a2e2df7 (ceph): Merge pull request #3247 from ceph/wip-10422
- mon: provide encoded canonical full OSDMap from primary
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 07:16 PM devops Feature #7454: ceph-disk: support osd removal / ceph-disk remove
- I just want to mention one thing about the zap subcommand.
Sometimes I will hit some problem with zap subcommand a... - 10:26 AM devops Feature #7454 (In Progress): ceph-disk: support osd removal / ceph-disk remove
- Current plan is to add two new sub-commands: "deactivate" and "destroy".
Deactivate is intended to mirror activate... - 06:51 PM Linux kernel client Bug #10450: NULL pointer dereference at send_mds_reconnect
- it's already fixed by commit 00bd8edb86 (ceph: fix null pointer dereference in discard_cap_releases()), this fix is i...
- 01:35 AM Linux kernel client Bug #10450: NULL pointer dereference at send_mds_reconnect
- Submitted by pressing enter at the wrong time. So here are more details:
When our mds crashes (see #10449), some c... - 01:32 AM Linux kernel client Bug #10450 (Resolved): NULL pointer dereference at send_mds_reconnect
- When our mds crashes (see #10449), some kernel throw
- 06:20 PM CephFS Bug #10413 (Fix Under Review): samba: coredumps after tests run
- https://github.com/ceph/samba/pull/1
- 05:48 AM CephFS Bug #10413 (In Progress): samba: coredumps after tests run
- smbd can call cephwrap_{getcwd,chdir,stat} after umount
- 05:36 PM Revision 5cf84e63 (ceph): librados: fix leak of WatchContext on unwatch
- The lifecycle matches that of the watch linger_op. Note that it is NULL
for notify.
Signed-off-by: Sage Weil <sage@... - 04:07 PM Bug #10458 (Resolved): librados: original pool name cached in IoCtxImpl may be used after pool is...
- This isn't a big deal since (1) pool renames are rare and (2) it's only used in a few methods:...
- 03:49 PM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- If this is two separate bugs I'd like to figure out if we can prevent the session_info_t from growing so large pretty...
- 03:54 AM CephFS Bug #10449: MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message too long"
- Funnily enough, I was just noticing this in the code while working on #9883 -- all the MDS table persistence code use...
- 01:30 AM CephFS Bug #10449 (Resolved): MDS crashing in "C_SM_Save::finish" due to OSD response "-90 ((90) Message...
- The relevant part of the log is the following:...
- 03:48 PM rgw Bug #10268 (Pending Backport): s3tests.functional.test_s3.test_bucket_create_exists fails with 'S...
- 03:47 PM rgw Bug #10334 (Pending Backport): rgw: s3 need to return InvalidAccessKeyId instead of AccessDenied
- commit:56af795b1046a4c1bfba59e1fefde272bb0e5c1e
- 03:47 PM rgw Bug #10329 (Pending Backport): rgw: s3 need to return SignatureDoesNotMatch instead of AccessDenied
- commit:ef75d720f289ce2e18c0047380a16b7688864560
- 03:45 PM rgw Bug #9478 (Pending Backport): Incorrect content type in response header
- commit:31963459a0a869c4d32f55baa629f36df33eaa90
- 03:45 PM rgw Bug #9479 (Pending Backport): ETag is not included in the XML response to put object copy operation
- commit:b1bfc3a7e0c9088f01f8ff770ae14f569fbc570d
- 03:44 PM rgw Bug #9877 (Pending Backport): In some cases it's possible for rgw to segfault on http COPY
- commit:fe7bf06366adaf787816d1e68f5e3f68e8c91134
- 03:43 PM rgw Bug #9918 (Pending Backport): RGW-Swift: SubUser access permissions, does not seems to work
- commit:5d9f36f757a7272c24d2c9adc31db1ed5e712992
- 03:42 PM rgw Bug #9973 (Pending Backport): Validation of Swift DLO manifest object ETag doesn't match OpenStac...
- commit:ef6d3ad964d34bc526dc4435486bd5c8cdc3b230
- 03:39 PM rgw Bug #5595 (Pending Backport): object has a Content-Type, but its content_type property is not sho...
- commit:f833f12a200ecc2c4f74ddb443d6fa61b7ad14db
- 03:33 PM Feature #10457: Permanently mark daemons and clusters which use experimental features
- I've marked this as High and assigned this to Sage since I would have liked to gate the experimental feature merge on...
- 03:32 PM Feature #10457 (New): Permanently mark daemons and clusters which use experimental features
- We want to know if a cluster we are debugging has *ever* used experimental features. Probably we can dump them as par...
- 03:28 PM CephFS Bug #10436: ceph-fuse: snapshot flushing from page cache to Client is not coherent
- Just to be clear, the problem here is that
1) there is dirty data in the page cache
2) a snapshot happens
3) ceph-... - 03:26 PM CephFS Bug #10323: lock get stuck in snap->sync state
- https://github.com/ceph/ceph/pull/3270
- 03:26 PM CephFS Bug #10343: qa/workunits/snaps/snaptest-xattrwb.sh fails
- https://github.com/ceph/ceph/pull/3270
- 03:22 PM Fix #6483 (Resolved): osd: does not fill in OSDOp::rval member
- commit:1d661ca97299352ef96f923baf1ead0ef5d7bb8e
- 03:11 PM Feature #7195 (Resolved): librados: complete C write object operation bindings
- commit:770942aa9ccd2553e0200f1a387a8b702a72ca7b
- 03:10 PM Feature #7194 (Resolved): librados: omap in the c api
- commit:995fea9a4435f6a7229a4aad7a955d0ba471c9af
- 03:09 PM Feature #7193 (Resolved): librados: object operation bindings for reads
- commit:242a6c85239397fdc19064b4a36c338b569892c8
- 03:07 PM rgw Feature #7214 (Rejected): radosgw-agent should work with older versions of python-requests
- it no longer uses requests
- 02:54 PM devops Tasks #10455: Improvements to the tracker - suggestion
- re: #2 - yes that's correct, it will also help us at the end of major releases (and minor as well) to make assessment...
- 02:50 PM devops Tasks #10455: Improvements to the tracker - suggestion
- 1. we could put stable branch (firefly, giant, etc) vs master. the master vs next changes so often I'm not sure its ...
- 02:30 PM devops Tasks #10455 (Resolved): Improvements to the tracker - suggestion
- In the context of "nightlies" (altho it may benefit our community and downstream development as well) - it seems that...
- 01:53 PM Revision b5c24e45 (ceph): qa: add test_tell, which currently is used only for testing 'ceph tell ...
- The test requires at least two monitors run.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 01:28 PM Revision f95022e8 (ceph): Merge pull request #3291 from majianpeng/fix2
- test/bufferlist: Remove chmod operation.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:51 PM Revision 244777d8 (ceph): test/bufferlist: For root, don't do permission operation for read_file
- case.
For root user, it meet those error:
test/bufferlist.cc:1880: Failure
Value of: bl.read_file("testfile"... - 11:52 AM Feature #10452: ceph osd df
- This would indeed be a nice feature. At Penguin, we had written some scripts that output the same information (but g...
- 11:43 AM Feature #10452: ceph osd df
- Sage Weil wrote:
> i can't decide whether it makes sense to make this look like the ceph osd tree output or not.. it... - 10:58 AM Feature #10452 (Resolved): ceph osd df
- command that will output a table of
- osd id (or crush tree node?)
- crush weight
- reweight weight
- actual re... - 11:15 AM Bug #10422 (Resolved): osdmap full crc mismatch due to divergent cache_target_{dirty,full}_ratio_...
- 11:01 AM rgw Feature #10454 (Resolved): rgw: sync agent incremental sync of versioned objects
- 11:00 AM rgw Feature #10453 (Resolved): rgw: sync agent full sync of versioned objects
- 10:01 AM Revision 3b4e021c (ceph): qa: refactor 'ceph -w' magic in test_mon_misc by introducing helper
- functions ceph_watch_start and ceph_watch_wait so they can be reused
in other tests.
Signed-off-by: Mykola Golub <mg... - 10:01 AM Revision 11891383 (ceph): mon: make ceph tell mon.* version work
- Fixes: #6767
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 09:51 AM Revision 0b6ab827 (ceph): rbd: add an option merge-diff
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Sig... - 09:51 AM Revision bca862c3 (ceph): rbd: parse merge-diff arguments
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Sig... - 09:51 AM Revision c7cc6af7 (ceph): rbd: write a diff description into the merged diff file
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
Rev... - 08:57 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Well I tried the same setup again with civetweb instead of apache. It ran 10-15% slower, which was fine, it made it f...
- 08:28 AM rgw Bug #10445: Radosgw hang, corrupt manifest?
- Not sure what triggers your original issue, althgouh I assume it's similar to what I see in the log. Basically what I...
- 08:52 AM Bug #10411: PG stuck incomplete after failed node
- Ok, so for future reference..
What *additional* information would you need to be able to reproduce this? AFAIK the... - 08:32 AM Bug #10411 (Can't reproduce): PG stuck incomplete after failed node
- 08:41 AM rgw Bug #10354 (Fix Under Review): Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro...
- This is duplicate of 10329, there's a pull request pending. Note though that the pull request is against master, but ...
- 08:39 AM Bug #10433 (Duplicate): OSD osd/ReplicatedPG.cc: 5540: FAILED assert(soid < scrubber.start || soi...
- 02:14 AM Revision c37abeaf (ceph): Merge pull request #3261 from tchaikov/async-msgr
- AsyncMessenger: a trivial refactory and a fix
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
01/04/2015
- 11:38 PM CephFS Bug #10448 (Resolved): wrong parameter passed to ceph_zero_pape_vector_range() in striped_read() ...
- Hi, all
A bug is found in striped_read() of fs/ceph/file.c.
striped_read() calls ceph_zero_pape_vector_range() at... - 04:01 AM Revision 5a8256e4 (ceph): mount.ceph: avoid spurious error message
- /etc/mtab in most modern distributions is a symbol link to
/proc/self/mounts.
Fixes: #10351
Signed-off-by: Yan, Zhen... - 01:22 AM rgw Bug #10447 (Closed): rx to radosgw is more than tx (more than ten times)
- Hi, I am using radosgw (using civetweb, but happens with apache too), rx to the gateway is more than 10 times the tx ...
Also available in: Atom