Project

General

Profile

Activity

From 02/12/2016 to 03/12/2016

03/12/2016

11:17 PM Revision 5077d729 (ceph): Merge remote-tracking branch 'origin/master' into wip-rgw-ldap
Yehuda Sadeh
11:16 PM Revision 40e92c02 (ceph): test: disable test_rgw_ldap
for now
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
09:02 PM Revision a0a8dcc2 (ceph): rgw: free components on shutdown
Also, use ldout in rgw_file.h in 3 places.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
09:02 PM Revision de8367bc (ceph): rgw: require openldap library client headers
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
09:02 PM Revision 46a34790 (ceph): rgw_ldap: merge cleanups
* match LDAPHelper op return codes to RGW (-POSIX)
* make temporary LDAP handle local (MT-safe)
* add required --enco...
Matt Benjamin
09:02 PM Revision e93778c3 (ceph): rgw/Makefile.am: add a missing .h file
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:04 PM Revision bdcff151 (ceph): mds: fix FSMap upgrade on mixed mon versions
The upgrade path was asserting that FSMap::filesystems
was empty. This would be violated if FSMap was initially
load...
John Spray
05:57 PM Revision 38fd3f19 (ceph): rgw: LDAP pass-through authentication
Implement a new external authenticator based on LDAP and the
new external token format.
External LDAP auth now works...
Matt Benjamin
04:39 PM Revision e52f7b40 (ceph): mds: fix FSMap upgrade with daemons in the map
This would trigger a sanity() assertion because
you'd have standbys in a Filesystem::mds_map, instead
of in standby_d...
John Spray
03:54 PM Bug #15086 (Resolved): ceph-detect-init jessie says sysvinit instead of systemd
Nathan Cutler
02:03 PM Revision 41cf5606 (ceph): Merge remote-tracking branch 'gh/jewel'
Sage Weil
02:02 PM Revision 37605d0e (ceph): Merge branch 'wip-15086' of git://github.com/SUSE/ceph
Reviewed-by: Sage Weil <sage@redhat.com> Sage Weil
12:53 PM Revision ebdcd29b (ceph): Merge pull request #870 from ceph/wip-rbd-mirror
rbd: add some missing workunits
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
11:32 AM Revision e10c6e48 (ceph): common: buffer: put a guard for stat() syscall during read_file
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
11:32 AM Revision 7b33156b (ceph): common: thread: allow set_affinity() to return a error code
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
11:05 AM Revision 1ea1735d (ceph): osd: fix wrong counter for batch objects removal during remove_dir()
The problem here is that we may skip some meta objects which shall not be
counted since they are not really queued. B...
xie xingguo
08:02 AM Revision 12d151f4 (ceph): osd: initialize last_recalibrate field at construction
So we don't get an overflowed duration on the first entry of
promote_throttle_recalibrate() call.
Signed-off-by: xie...
xie xingguo
07:15 AM Revision 4e145658 (ceph): Fix review comments
Signed-off-by: Vasu Kulkarni <vasu@redhat.com> Vasu Kulkarni
06:24 AM rgw Bug #14949: radosgw-admin link failure
Bucket test2 is created by user iceberg, i used link to change its owner to flex.
The bucket ACL has been updated:...
Flex Gao
06:13 AM rgw Bug #14949: radosgw-admin link failure
Abhishek Lekshmanan wrote:
> Can you try if radosgw-admin bucket link --bucket=test2 --bucket-id default.24601.1 --u...
Flex Gao
04:23 AM Bug #15053: v10.0.4 points at the wrong commit and fails to build with deb
I don't understand how that fixes things ? If someone checkout the v10.0.4 tag, it still has the v in debian/changelo... Loïc Dachary
03:55 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
03:07 AM Revision f1a44907 (ceph): ceph.spec.in: disable lttng and babeltrace explicitly
before this change, we do not pacakge tracepoint probe shared libraries
on rhel7. but "configure" script enables them...
Kefu Chai
02:23 AM Revision 57fd7f85 (ceph): test/librados/test.cc: clean up EC pools' crush rules too
SetUp was adding an erasure-coded pool, which automatically adds
a new crush rule named after the pool, but only remo...
Dan Mick
01:54 AM rbd Bug #15104 (Resolved): qa: verify_pool.sh: syntax error
Josh Durgin
01:09 AM rbd Bug #15104 (Fix Under Review): qa: verify_pool.sh: syntax error
*jewel PR*: https://github.com/ceph/ceph/pull/8068 Nathan Cutler
12:56 AM rbd Bug #15104 (In Progress): qa: verify_pool.sh: syntax error
https://wiki.ubuntu.com/DashAsBinSh#function Nathan Cutler
12:32 AM rbd Bug #15104: qa: verify_pool.sh: syntax error
guessing this is a bashism, since /bin/sh is dash where this failed Josh Durgin
12:29 AM rbd Bug #15104 (Resolved): qa: verify_pool.sh: syntax error
... Josh Durgin
01:48 AM Revision 750701b6 (ceph): Merge pull request #8068 from SUSE/wip-15104
qa/workunits/rbd: use POSIX function definition
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:40 AM Revision 93863e7e (ceph): Merge pull request #7663 from javacruft/wip-pybind-flags
pybind: Ensure correct python flags are passed
Reviewed-by: Boris Ranto <branto@redhat.com>
Reviewed-by: Ken Dreyer ...
Josh Durgin
01:35 AM Revision a7f7339d (ceph): Merge pull request #7856 from jdurgin/wip-cython-cleanup
configure.ac: update help strings for cython
Reviewed-by: Kefu Chai <tchaikov@gmail.com>
Josh Durgin
01:20 AM Revision 4a721225 (ceph): Merge remote-tracking branch 'origin/wip-josh-testing'
Josh Durgin
01:06 AM Revision 3c1d464f (ceph): Merge pull request #8067 from athanatos/wip-fix-filestore-warning
FileStore: fix initialization order for m_disable_wbthrottle
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
01:03 AM Revision 996be8ef (ceph): qa/workunits/rbd: use POSIX function definition
In scripts with /bin/sh shebang, we must use POSIX function definitions to
avoid syntax errors on platforms that link...
Nathan Cutler
12:56 AM Revision d9af48ab (ceph): ReplicatedPG: be more careful about calling publish_stats_to_osd() corr...
We had moved the call out of eval_repop into a lambda, but that left out
a few other code paths and is fragile. So ju...
Greg Farnum
12:26 AM rbd Bug #15103 (Resolved): librbd: read_flags test fails to find balance_reads flag when exporting sn...
http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54643/teuthology.log Josh Durgin
12:22 AM rbd Bug #15102 (Resolved): librbd: exclusive lock AcquireRequest failed assert m_image_ctx.journal ==...
http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54614/teuthology.log... Josh Durgin
12:20 AM Revision 2ae6d54f (ceph): rgw: swift object versioning data structure changes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:20 AM Revision 54ea09c3 (ceph): rgw: copy swift versioned object to destination if overwritten
Only allow if target bucket owner is the source bucket owner.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:20 AM Revision da9120aa (ceph): rgw: dump X-Versions-Location HTTP header of Swift API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
12:20 AM Revision 06c77160 (ceph): rgw: improve naming of Swift versioned object's copies.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
12:20 AM Revision 86167635 (ceph): rgw: disable swift versioning by default
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:18 AM rbd Bug #15101 (Resolved): librbd: remove_snap TimeOut failure
http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-wip-josh-testing---basic-multi/54607/teuthology.log... Josh Durgin
12:10 AM Feature #15100 (Resolved): qa: test building a librados application
Compile and run a librados application outside of the ceph build system, so that we can be sure librados.h[pp] is sti... Josh Durgin
12:01 AM Bug #15047 (Resolved): Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
Nathan Cutler

03/11/2016

11:58 PM Revision c5b00be0 (ceph): Merge pull request #8034 from SUSE/wip-15047
packaging: make infernalis -> jewel upgrade work
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Ken Dreyer
11:45 PM Bug #14815 (Resolved): os/filestore: mount may return OK even if it encounters internal error.
https://github.com/ceph/ceph/pull/7707 xie xingguo
11:36 PM Revision 77ca8030 (ceph): Merge pull request #868 from ceph/wip-fio-ver
Update fio version to 2.7
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
11:29 PM rbd Bug #15097: journal.sh fails when removing image
same issue in the new rbd_mirror_image_replay workunit: http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28... Josh Durgin
11:23 PM rbd Bug #15097 (Resolved): journal.sh fails when removing image
Occurs on master as well as wip-josh-testing. From http://qa-proxy.ceph.com/teuthology/joshd-2016-03-11_15:03:28-rbd-... Josh Durgin
11:27 PM Bug #15047 (Fix Under Review): Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
https://github.com/ceph/ceph/pull/8034 is ready to merge Nathan Cutler
11:12 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
In run http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-11_02:10:01-upgrade:infernalis-x-jewel-distro-basic-... Yuri Weinstein
10:03 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
Run: http://pulpito.ceph.com/teuthology-2016-03-11_10:42:14-upgrade:client-upgrade-jewel-distro-basic-vps/
Jobs: ['5...
Yuri Weinstein
11:24 PM Bug #15098 (Resolved): "stop ceph-all" no longer stops ceph
on Trusty only
Run: http://pulpito.ceph.com/teuthology-2016-03-10_21:13:02-ceph-deploy-jewel-distro-basic-vps/
Jobs...
Yuri Weinstein
11:23 PM Bug #15096 (Rejected): Setting os_enable_op_tracker to false on running osd can crash it
This is caused by the fix I'm working on, not an existing issue. David Zafman
11:12 PM Bug #15096 (Rejected): Setting os_enable_op_tracker to false on running osd can crash it

2016-03-11 15:11:10.717324 7f77b97fa700 -1 common/TrackedOp.cc: In function 'void OpTracker::unregister_inflight_op...
David Zafman
11:22 PM Revision a230a383 (ceph): debian: make infernalis -> jewel upgrade work
Attempts to install jewel ceph-common, ceph-mon, ceph-osd, and ceph-base
package over infernalis ceph package fail du...
Nathan Cutler
11:16 PM Revision ba4badf4 (ceph): FileStore: fix initialization order for m_disable_wbthrottle
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
11:06 PM Bug #15095 (Resolved): "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:infernalis-x-jewel-d...
Maybe related/similar to #15012
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-11_02:10:01-upgrade...
Yuri Weinstein
10:55 PM Revision 81b9928f (ceph): ceph-detect-init: return systemd on Debian Jessie
http://tracker.ceph.com/issues/15086 Fixes: #15086
Signed-off-by: Nathan Cutler <ncutler@suse.com>
Nathan Cutler
10:51 PM Revision 4466d2fa (ceph): rbd: add some missing workunits
Signed-off-by: Josh Durgin <jdurgin@redhat.com> Josh Durgin
10:46 PM devops Bug #15090: archive.ubuntu.com hash mismatch in upgrade:client-upgrade-jewel-distro-basic-vps
Not missing packages; apparently-broken upstream repo Dan Mick
09:57 PM devops Bug #15090 (Resolved): archive.ubuntu.com hash mismatch in upgrade:client-upgrade-jewel-distro-ba...
Run: http://pulpito.ceph.com/teuthology-2016-03-11_10:42:14-upgrade:client-upgrade-jewel-distro-basic-vps/
Job: 5326...
Yuri Weinstein
10:42 PM Revision 4c97aac8 (ceph): Revert "test/time: no need to abs(uint64_t) for comparing"
This reverts commit da0f6608dd6cc3356e727e739575f496c2b6a590.
unittest_time fails:
[==========] Running 4 tests fro...
Sage Weil
10:34 PM Revision 2b07695f (ceph): unittest_compression_zlib: do not assume buffer will be null terminated
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
10:29 PM Revision ff3b4569 (ceph): Merge pull request #8063 from gregsfortytwo/wip-fix-fsmap-decode
Wip fix fsmap decode
Reviewed-by: Sage Weil <sage@redhat.com>
Greg Farnum
10:09 PM rbd Bug #15092: "rbd: image creation failed" in upgrade:client-upgrade-jewel-distro-basic-vps
We'll need to adjust the client-upgrade tests to not use new features. Josh Durgin
10:06 PM rbd Bug #15092 (Resolved): "rbd: image creation failed" in upgrade:client-upgrade-jewel-distro-basic-vps
Run: http://pulpito.ceph.com/teuthology-2016-03-11_10:42:14-upgrade:client-upgrade-jewel-distro-basic-vps/
Job: 5326...
Yuri Weinstein
10:08 PM Revision 6f273eb5 (ceph): rgw: use std::unique_ptr for rgw_aws4_auth management.
This is purely for code maintainability.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Radoslaw Zarzynski
10:04 PM rgw Bug #15091 (Resolved): Exception during orig_placement_pools = len(out['placement_pools'])
'adjust-ulimits ceph-coverage /home/ubuntu/cephtest/archive/coverage radosgw-admin --log-to-stderr --format json -n c... Vasu Kulkarni
09:58 PM Bug #15086 (Fix Under Review): ceph-detect-init jessie says sysvinit instead of systemd
*jewel PR*: https://github.com/ceph/ceph/pull/8062 Nathan Cutler
09:26 PM Bug #15086 (In Progress): ceph-detect-init jessie says sysvinit instead of systemd
Nathan Cutler
07:28 PM Bug #15086 (Resolved): ceph-detect-init jessie says sysvinit instead of systemd
... Sage Weil
09:47 PM Revision 1cf29067 (ceph): Merge pull request #7752 from somnathr/wip-odsync-write
FileStore: Added O_DSYNC write scheme
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redha...
Samuel Just
09:41 PM Revision 2cc736c3 (ceph): FSMap: actually include the legacy MDSMap in Filesystems when upgrading
Signed-off-by: Greg Farnum <gfarnum@redhat.com> Greg Farnum
09:36 PM Revision a83989d0 (ceph): FSMap: decode old MDSMaps properly
We accidentally left a few members out that the MDSMap had!
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
09:22 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Kefu,
I built your new change earlier today and deployed it to my test cluster. It's been running for about 6 hour...
Steve Taylor
05:35 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Is an orthogonal fix to add a trim_thru epoch (instead of inferring it from oldest_map) to the message? That way one... Sage Weil
08:28 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
steve, the new changeset in https://github.com/ceph/ceph/pull/8017 is targeting master.
and its backport to hammer...
Kefu Chai
06:00 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
thank you Steve, i appreciate your help and testing. it's expected. that change is simpler than the one i was thinkin... Kefu Chai
09:08 PM rgw Backport #15089 (Resolved): hammer: Bucket owner isn't changed after unlink/link
https://github.com/ceph/ceph/pull/8583 Nathan Cutler
09:08 PM rgw Backport #15088 (Rejected): infernalis: Bucket owner isn't changed after unlink/link
Nathan Cutler
09:04 PM rgw Bug #15087 (Resolved): rgw zone set failure --log-to-stderr --format json -n client.1 -n client.1...
cli fails during zone set
http://magna002.ceph.redhat.com/vasu-2016-03-11_00:54:46-rgw-jewel---basic-magna/214784/...
Vasu Kulkarni
09:02 PM Backport #15040: infernalis: test/librados/tier.cc doesn't completely clean up EC pools
Well, it cherry-picks to hammer just fine, apparently (though the cherry-picked line is missing): #15051 Nathan Cutler
05:34 PM Backport #15040: infernalis: test/librados/tier.cc doesn't completely clean up EC pools
I see this in hammer-x run
http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-11_02:10:03-upgrade:hammer-x-jewel...
Yuri Weinstein
01:26 AM Backport #15040: infernalis: test/librados/tier.cc doesn't completely clean up EC pools
IIRC we already have it in hammer Loïc Dachary
08:47 PM Revision 23487e05 (ceph): Merge pull request #8058 from yehudasa/wip-rgw-clean-log
cleanup
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
Yehuda Sadeh
08:39 PM Revision 9e83f5bf (ceph): mon: make the minimum crush tunables configurable
If they cluster is using very old tunables, as inferred by whether it
requires a newer version of CRUSH, issue a heal...
Sage Weil
08:37 PM Revision 88f13807 (ceph): rados: add ceph:: namespace to bufferlist type
After a fresh install, applications that had been including rados.hpp cannot resolve bufferlist, which is in ceph:: s... Noah Watkins
08:36 PM Revision 565d1c73 (ceph): crush: report minimum_required_version when dumping tunables
This mimics the feature bit enforcement in OSDMap.cc but it does it based
on the version string. This is useful when...
Sage Weil
07:37 PM Revision 78dc1b3d (ceph): rgw_ldap: merge cleanups
* match LDAPHelper op return codes to RGW (-POSIX)
* make temporary LDAP handle local (MT-safe)
* add required --enco...
Matt Benjamin
07:28 PM Revision 1d18a637 (ceph): rgw: silence compilation warnings
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
07:27 PM Revision a0c816be (ceph): rgw: cleanup of debug messages
use ldout instead of derr and lderr and increase logging level
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
07:24 PM Revision b1f0cb90 (ceph): Merge pull request #7944 from trociny/wip-rbd-mirror-image-replayer-async
rbd-mirror: ImageReplayer async start/stop
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:22 PM Revision 99a6934a (ceph): Merge pull request #8028 from dillaman/wip-librbd-journal-replay
librbd: replaying a journal op post-refresh requires locking
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:03 PM Revision 193b3002 (ceph): Merge pull request #7483 from liewegas/wip-osd-boot
osd: resolve boot vs NOUP set + clear race
Reviewed-by: Samuel Just <sjust@redhat.com>
Samuel Just
06:39 PM Revision 9aaf672c (ceph): Merge pull request #8030 from yehudasa/wip-rgw-sync-status
adds the radosgw-admin sync status command that gives a human readable status of the sync process at a specific zone
...
Orit Wasserman
06:34 PM Revision 1b897a96 (ceph): os/bluestore/KernelDevice: fix signed/unsigned warning
os/bluestore/KernelDevice.cc: In member function ‘virtual int KernelDevice::open(std::string)’:
os/bluestore/KernelDe...
Sage Weil
06:33 PM Revision d963eb72 (ceph): os/ObjectStore: drop collection attr deprecated warnings
Can't silent these and we have no users left. They'll be removed
soon, but I'm tired of sifting through all the warn...
Sage Weil
06:29 PM Revision f9dbf545 (ceph): osd/PGLog: fix warning
osd/PGLog.h: In member function 'virtual unsigned int PGLog::get_subsys() const':
osd/PGLog.h:39:28: warning: enumera...
Sage Weil
06:21 PM Revision 97b90e62 (ceph): Merge pull request #7615 from ceph/wip-14678
rgw: store system object meta in cache when creating it
Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
Yehuda Sadeh
06:18 PM rgw Bug #11076 (Pending Backport): Bucket owner isn't changed after unlink/link
PR 8037 Yehuda Sadeh
06:17 PM Revision c20d9c5f (ceph): Merge pull request #8037 from yehudasa/wip-bucket-link
rgw:bucket link now set the bucket.instance acl (bug fix)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:11 PM Revision 2f818794 (ceph): Merge pull request #8013 from yehudasa/wip-rgw-multisite-fixes
rgw multisite fixes
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
06:09 PM Revision 4bd31fae (ceph): ghobject_t: use # instead of ! as a separator
! (and @) confuse less's search (/ then ! is magic). # behaves
as expected.
Tried to fix this in 30b257c66b9d35d2f3...
Sage Weil
05:55 PM Bug #14244 (Resolved): "SELinux denials found" in rados-jewel-distro-basic-smithi
Sage Weil
05:54 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
This passed fs suite testing (although of course that doesn't exercise RADOS bits at all). http://pulpito.ceph.com/gr... Greg Farnum
02:11 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
Updating description with test name so that I can find it on a search John Spray
01:29 AM Bug #14962 (In Progress): PG::publish_stats_to_osd() does not get called when trimming snap objec...
Okay, the problem actually got started in cc1b2c6f342b17d6e304560c23f4ce310d6690d9 ("ReplicatedPG: move client reply ... Greg Farnum
05:45 PM Bug #13915 (Can't reproduce): "failed: mon_thrash" in upgrade:hammer-hammer-distro-basic-openstack
Sage Weil
05:40 PM Bug #15037 (Resolved): ceph_argparse: test_ceph_argparse.TestOSD.test_reweight_by_utilization fails
Sage Weil
05:39 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
and in http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-10_17:10:02-upgrade:hammer-x-infernalis-distro-basic-vp... Yuri Weinstein
05:39 PM Bug #15049 (Resolved): ceph.py wait_for_daemons doesn't work with firefly
Sage Weil
05:39 PM Revision a303f9de (ceph): Merge pull request #863 from ceph/wip-15049
rados/singleton-nomsgr/all/11429: no mds Sage Weil
05:37 PM Backport #14799 (Resolved): hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread...
Sage Weil
04:00 AM Backport #14799 (Fix Under Review): hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboos...
https://github.com/ceph/teuthology/pull/818 Loïc Dachary
05:36 PM Revision e22fa18e (ceph): Merge pull request #824 from ceph/wip-multi-filesystems
Test updates for multi-filesystem support Greg Farnum
05:36 PM Revision e805ebc4 (ceph): Update fio version to 2.7
Signed-off-by: Vasu Kulkarni <vasu@redhat.com> Vasu Kulkarni
05:36 PM Revision a7a0dac6 (ceph): Merge pull request #6953 from jcsp/wip-fsmap
Multi-filesystem support
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
05:35 PM Bug #15053 (Resolved): v10.0.4 points at the wrong commit and fails to build with deb
fixed debian/changelog 'v', and tagged v10.0.5 Sage Weil
01:38 AM Bug #15053 (Resolved): v10.0.4 points at the wrong commit and fails to build with deb
http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-deb-trusty-amd64-basic/log.cgi?log=ea45099808051017fb05582555f126cba... Loïc Dachary
05:29 PM Bug #15073: osd: osdmap write not ordered before pgs consume map
https://github.com/liewegas/ceph/commit/wip-15073 Sage Weil
02:02 PM Bug #15073 (Resolved): osd: osdmap write not ordered before pgs consume map
/a/sage-2016-03-10_19:53:19-rados:thrash-wip-bluestore---basic-mira/52021
- osdmap write txn is queued
- pg consu...
Sage Weil
05:22 PM Bug #15012 (Resolved): "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distr...
tested http://pulpito.ceph.com/teuthology-2016-03-11_02:10:03-upgrade:hammer-x-jewel-distro-basic-vps/52696/ Yuri Weinstein
05:21 PM Revision 74294039 (ceph): Merge branch 'master' into jewel
Greg Farnum
05:15 PM Revision 49c3521b (ceph): Merge pull request #7465 from liewegas/wip-promote-throttle
osd: probabilistic cache tier promotion throttling
Reviewed-by: Samuel Just <sjust@redhat.com>
Sage Weil
05:07 PM Revision 96c1da9c (ceph): Merge tag 'v10.0.5'
v10.0.5
Conflicts:
debian/changelog
Sage Weil
05:05 PM Revision 5acb2655 (ceph): v10.0.5
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
05:01 PM CephFS Bug #15060 (Duplicate): client: Leak_StillReachable from boost::detail::get_once_per_thread_epoch()
http://tracker.ceph.com/issues/14794, which got fixed yesterday. Greg Farnum
11:18 AM CephFS Bug #15060 (Duplicate): client: Leak_StillReachable from boost::detail::get_once_per_thread_epoch()
http://pulpito.ceph.com/teuthology-2016-03-09_14:03:10-fs-jewel---basic-smithi/49376/... John Spray
05:00 PM Bug #14794 (Resolved): Objecter: valgrind unclean
https://github.com/ceph/teuthology/pull/817
Added a valgrind exception and it passed the tests without getting angry.
Greg Farnum
04:57 PM Revision 10ca7f3e (ceph): debian/changelog: Remove stray 'v' in version
Signed-off-by: Dan Mick <dan.mick@redhat.com>
(cherry picked from commit 0f7730c8f444657d4aaffa28c12bbcd602a2e3b8)
Dan Mick
04:48 PM Backport #15081 (Resolved): hammer: When logging to a file fails, ceph logs excessively to stderr
https://github.com/ceph/ceph/pull/10227 Nathan Cutler
04:39 PM Revision 48d929c4 (ceph): msg: async: improve _send_keepalive_or_ack() a little
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
04:36 PM Backport #15051 (In Progress): hammer: test/librados/tier.cc doesn't completely clean up EC pools
Xiaoxi Chen
04:35 PM Revision cbc7cdb1 (ceph): msg: async: fix connection perf counter description
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
04:33 PM Revision ddbb0ab9 (ceph): rgw: add handling of memory allocation failure in AWS4 auth.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
04:33 PM Backport #15024 (In Progress): hammer: clock skew report is incorrect by "ceph health detail" com...
Xiaoxi Chen
04:27 PM Bug #12194: osd crash FAILED assert(!parent->get_log().get_missing().is_missing(soid))
I'm seeing the exact same issue in a production cluster, that was created as Hammer (0.94.2) and since upgraded to 0.... Luis Periquito
04:14 PM Revision 8733c40e (ceph): Merge branch 'master' of github.com:ceph/ceph
Sage Weil
04:14 PM Revision 57c6d3b6 (ceph): Merge branch 'debian-stretch-dep-fix' of git://github.com/rldleblanc/ceph
Reviewed-by: Sage Weil <sage@redhat.com>
# Conflicts:
# debian/control
Sage Weil
04:13 PM Revision 55a66975 (ceph): os/filestore: add filestore_punch_hole = false option
Make punch hole usage optional.
Default to off, since it's relatively untested.
Signed-off-by: Sage Weil <sage@redh...
Sage Weil
04:08 PM Bug #15077 (Fix Under Review): filestore fails ObjectStore/StoreTest.Synthetic/1
https://github.com/ceph/ceph/pull/8050 Sage Weil
04:02 PM Bug #15077: filestore fails ObjectStore/StoreTest.Synthetic/1
broken by commit:7bd95b595fddb8a4e618a2c7df1ba04eccf0829d (punch hole fix) Sage Weil
03:27 PM Bug #15077 (Resolved): filestore fails ObjectStore/StoreTest.Synthetic/1
... Sage Weil
04:02 PM Revision 400975b0 (ceph): os/filestore: fix punch hole usage in _zero
If we punch a hole that extends past EOF, ObjectStore semantics are
that the file size is also extended. Do that.
N...
Sage Weil
04:00 PM Revision d4cf1904 (ceph): keyring permissions for mon daemon
The command:
sudo ceph-mon --cluster ceph --mkfs -i $NODE_NAME --keyring $PATH_MON_KEYRING
Writes a new keyring wit...
Owen Synge
03:50 PM Revision b96cfda4 (ceph): Merge pull request #8045 from tchaikov/wip-scrubstore-cleanup
osd/ScrubStore: remove unused function
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:42 PM Backport #15022 (In Progress): hammer: keyring permisions for mon deamon
Xiaoxi Chen
03:41 PM Revision 35f6c5c9 (ceph): os/bluestore: fix OP_TRY_RENAME
We don't need to create the dest onode.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
03:41 PM Revision 19e6b643 (ceph): os/bluestore: ref ovec for CLONE, CLONERANGE
This keeps ovec up to date. Marginally more efficient.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
03:41 PM Revision bd2285f6 (ceph): osd: use correct shard for temp scrub object
Use ghobject_t type throughout. Make ghobject_t variant of
spg_t::make_temp_object().
Signed-off-by: Sage Weil <sag...
Sage Weil
03:41 PM Revision 3dcadb43 (ceph): os/bluestore: print debug on ENOTEMPTY
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision a2ecb1a8 (ceph): os/bluestore/BlueStore: do not cow_rmw_tail at or past eof
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision 33b70582 (ceph): ceph_test_objectstore: add a few checks to the rename test
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision e8b94aec (ceph): os/filestore: make read replace (not append) to result bl
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision 6dcc4998 (ceph): os/memstore: assert src and dst collection match on rename
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision fcb07869 (ceph): ceph_test_objectstore: rename assumes target does not exist
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:41 PM Revision f2f0e7d7 (ceph): os/bluestore: fix _rename
Update the *target* object ref in ovec.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
03:41 PM Revision 166a7a98 (ceph): osd: simplify split vs backfill behavior
This is more future-proof, in case we add special backfill
completion work in the future. In the worst case we will ...
Sage Weil
03:41 PM Revision 6a60c12e (ceph): osd/ScrubStore: do not use temp collection
Temp collections are deprecated, and used only internally by
FileStore for compat reasons.
Signed-off-by: Sage Weil ...
Sage Weil
03:41 PM Revision eee3d700 (ceph): include/buffer: make is_partial work on empty ptr
Add a few unit tests.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
03:41 PM Revision b71f9f14 (ceph): os/bluestore: make _do_omap_clear debug line pretty
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:33 PM Revision 56fe749e (ceph): Merge pull request #7707 from xiexingguo/xxg-wip-14815
osd: filestore: fix wrong scope of result code for error cases during mount
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:32 PM Revision 4adeb410 (ceph): Merge pull request #7726 from tchaikov/wip-fix-ftbfs-gcc6
test/time: no need to abs(uint64_t) for comparing
Reviewed-by: Adam Emerson <aemerson@redhat.com>
Sage Weil
03:32 PM Bug #14952 (Resolved): New pools have bogus "stuck inactive/unclean" HEALTH_ERR messages until th...
Sage Weil
03:32 PM Revision 07c41fcd (ceph): Merge pull request #7955 from ErwanAliasr1/evelu-check-bufferlist
test/bufferlist: Avoid false-positive tests
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:31 PM Revision a1490dc1 (ceph): Merge pull request #7980 from liewegas/wip-14952
mon: initialize last_* timestamps on new pgs to creation time
Reviewed-by: John Spray <john.spray@redhat.com>
Sage Weil
03:31 PM Bug #14606 (Resolved): rest.py fails
Sage Weil
03:30 PM Revision 5d745b2b (ceph): Merge pull request #7982 from liewegas/wip-14606
qa/workunits/rest/test.py: add confirmation to 'mds setmap' Sage Weil
03:30 PM Bug #14616 (Pending Backport): When logging to a file fails, ceph logs excessively to stderr
Sage Weil
03:29 PM Revision 4ab0fc51 (ceph): Merge pull request #7983 from liewegas/wip-14616
log: do not repeat errors to stderr
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
03:29 PM Revision c9124548 (ceph): Merge pull request #8004 from liewegas/wip-rados-test-stderr
qa/workunits/rados/test.sh: capture stderr too Sage Weil
03:29 PM rbd Bug #15078 (Resolved): client upgrade(osd/mon: hammer, client: jewel) 1 test failure TestLibRBD.T...
osd/mon: in hammer, client on jewel
out of 43, 1 test failed: TestLibRBD.TestCreateLsDeletePP
http://magna002.cep...
Vasu Kulkarni
03:29 PM Revision 243a36b3 (ceph): Merge pull request #8006 from liewegas/wip-big-pages
os/bluestore/KernelDevice: force block size Sage Weil
03:28 PM rgw Bug #13600 (Resolved): RadosGW can't bind to port below 1024 with Infernalis
Sage Weil
03:28 PM Revision 13446653 (ceph): Merge pull request #8019 from kmroz/wip-upstream-civetweb-low-ports-6
rgw: drop permissions of rgw/civetweb after startup
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:26 PM Bug #15011: TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
Continued my debugging and reach that state :
In https://github.com/ceph/ceph/blob/master/src/common/SubProcess.h#...
Anonymous
03:16 PM rbd Bug #15076 (Won't Fix): client upgrade(osd: firefly, client: jewel) rbd import_export firefly wor...
OSD is firefly and Client is jewel, seen failures during rbd delete and other areas, workunit is from firefly
http...
Vasu Kulkarni
02:50 PM rgw Bug #14949 (Need More Info): radosgw-admin link failure
Abhishek Lekshmanan
09:33 AM rgw Bug #14949: radosgw-admin link failure
Can you try if radosgw-admin bucket link --bucket=test2 --bucket-id default.24601.1 --uid=flex works? Abhishek Lekshmanan
02:39 PM Revision eb1c5feb (ceph): Merge pull request #8007 from wido/se-mirror-mail
mirrors: Change contact e-mail address for se.ceph.com
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
02:39 PM Revision f0c512b0 (ceph): Merge pull request #7991 from xiexingguo/xxg-wip-remove-upthrupending
osd: remove up_thru_pending field, which is never used
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
02:30 PM CephFS Bug #14805: Hadoop tests failing with EPERM
Maybe this has same issue as the python libcephfs tests did, they were creating files with mode 0, which used to work John Spray
02:29 PM Fix #14932: Improve ceph-disk error message when there is not enough space to create journal part...
I just tested this with SUSE version:
major:
10
minor:
0
revision:
3-928-g...
Owen Synge
02:23 PM CephFS Bug #15075 (Resolved): "suspicious RCU usage" message in knfs, kcephfs tests
Zheng, does this look familiar to you?
http://pulpito.ceph.com/teuthology-2016-03-09_17:10:02-knfs-jewel-testing-b...
John Spray
02:15 PM Revision 9e86b539 (ceph): Merge pull request #8023 from roidayan/xio-remove_unused_variable
xio: remove unused variable
Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
02:12 PM Revision b61692ba (ceph): rbd-mirror: ImageReplayer async start/stop
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:12 PM Revision b0e1eb52 (ceph): test: ImageReplayer on_stop/on_start error tests
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:12 PM Revision 866a7048 (ceph): test: rbd_mirror_image_replay improve commit position parsing
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:12 PM Revision 3295253d (ceph): test: add rbd-mirror test script
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:11 PM CephFS Bug #15061 (Duplicate): TestStrays.test_snapshot_remove failing, objects remain in data pool
Ah, I thought it sounded familiar, but I couldn't find the ticket. Thanks. John Spray
11:57 AM CephFS Bug #15061: TestStrays.test_snapshot_remove failing, objects remain in data pool
It's an OSD issue. dup of http://tracker.ceph.com/issues/14962 Zheng Yan
11:32 AM CephFS Bug #15061: TestStrays.test_snapshot_remove failing, objects remain in data pool
... John Spray
11:31 AM CephFS Bug #15061 (Duplicate): TestStrays.test_snapshot_remove failing, objects remain in data pool

http://pulpito.ceph.com/teuthology-2016-03-07_18:04:01-fs-master---basic-smithi/45775/
Reproduces locally on vst...
John Spray
02:08 PM Revision 39b27ef9 (ceph): librbd: protect against duplicate journal events
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:07 PM Revision a795d34c (ceph): librbd: protect against journal replay shutdown race condition
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:03 PM CephFS Feature #15074 (New): multifs: infer client's target filesystem based on its auth caps
Usually, if a client subscribes to unqualified "mdsmap", it'll get whichever filesystem is marked as the legacy files... John Spray
01:53 PM CephFS Feature #15072 (New): mon: multifs: auth caps of MDS->mon connections to limit by FSCID
MDSs already only receive a populated MDSMap once they have been assigned a rank.
These caps should be used by MDS...
John Spray
01:51 PM CephFS Feature #15071 (New): mds: client: multifs: auth caps on client->MDS connections to limit by FSCID
When a client is to be limited to a particular filesystem, it needs to not only be restricted to seeing that MDSMap, ... John Spray
01:49 PM CephFS Feature #15070 (Resolved): mon: client: multifs: auth caps on client->mon connections to limit th...
Currently clients with 'mds allow r' capabilities can see any MDSMap.
We would like to be able to craft client aut...
John Spray
01:47 PM CephFS Feature #15069 (Resolved): MDS: multifs: enable two filesystems to point to same pools if one of ...
The 'damaged' flag on a filesystem prevents any MDS from being assigned a rank in that filesystem. While a filesyste... John Spray
01:43 PM CephFS Feature #15068 (Resolved): fsck: multifs: enable repair tools to read from one filesystem and wri...
To create a workflow in which the user marks an existing filesystem damaged, and then goes through a repair process w... John Spray
01:41 PM CephFS Feature #15067 (Resolved): mon: client: multifs: enable clients to map a filesystem name to a FSCID

Currently clients have to specify the ID of the filesystem they want to connect to (or specify no ID to get the leg...
John Spray
01:40 PM CephFS Feature #15066 (Rejected): multifs: Allow filesystems to be assigned RADOS namespace as well as p...
Everywhere we accept a pool argument currently (e.g. in "ceph fs new"), we should additionally accept a RADOS namespa... John Spray
01:37 PM CephFS Feature #15065 (Resolved): multifs: add standby_for_fscid setting on MDS and pass in MMDSBeacon
Currently in MDSMonitor::prepare_beacon:... John Spray
01:33 PM CephFS Fix #15064 (Closed): multifs: tweak text on "flag set enable multiple"
(Requested by Greg https://github.com/ceph/ceph/pull/6953#issuecomment-194731565)
Currently when someone tries to ...
John Spray
01:30 PM CephFS Feature #15063 (Resolved): multifs: option to disable sanity() calls
(Requested by Greg https://github.com/ceph/ceph/pull/6953#discussion-diff-55642577R359)
The MDSMonitor calls FSMap...
John Spray
01:28 PM CephFS Fix #15062 (Resolved): multifs cleanup: pass feature bits into MDSMap from Filesystem::encode
Currently a static set of bits is passed when encoding MDSMap in Filesystem objects.
https://github.com/ceph/ceph/...
John Spray
12:39 PM Revision fdeb1255 (ceph): test: periodic failure in TestJournalReplay.SnapRename
Force the refresh of the image to pick up the new snapshot
name before testing that it successfully was renamed.
Sig...
Jason Dillaman
12:39 PM Revision aa6a8d3a (ceph): librbd: replaying a journal op post-refresh requires locking
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:15 PM Revision a54bf91d (ceph): tasks/cephfs: cover fancy layout in test_strays
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
11:04 AM rbd Bug #14483: Flattening an rbd image with a running Qemu instances causes librbd worker threads to...
Hm. I think this is still an issue. I updated everything to 0.94.6 and this still happens. What's the most helpful th... Christian Theune
10:40 AM Revision 9915752a (ceph): tasks/cephfs: enable multi fs flag
Cluster won't let you create more than without
setting this flag explicitly.
Signed-off-by: John Spray <john.spray@r...
John Spray
10:40 AM Revision e1634ed2 (ceph): tasks/cephfs: debug in wait_for_daemons
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:39 AM Revision 53f4430d (ceph): tasks/cephfs: further thrasher fixes
Move the thrasher-specific methods out of CephManager
into MDSThrasher and plumb them into MDSCluster.
Signed-off-by...
John Spray
10:39 AM Revision e666fddf (ceph): tasks/cephfs: switch off extra daemons in TestStrays
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:39 AM Revision 9ca3721d (ceph): tasks/cephfs: simplify recreate()
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision 22b350de (ceph): tasks: generalise cephfs classes for multi-fs
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision 3c3804ec (ceph): tasks/cephfs: update test_runner for mds_cluster
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision b02afb2a (ceph): tasks: fix mds_thrash for multi filesystems
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision 951102df (ceph): tasks/cephfs: rename Filesystem.reset to recreate
Name was ambiguous wrt "fs reset"
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
10:36 AM Revision e2176667 (ceph): tasks/cephfs: move the journaltool smoke test into python land
This is one of those things that had a convoluted .yaml file
because it predated the ability to write explicit proced...
John Spray
10:36 AM Revision 212a507e (ceph): tasks/cephfs: fix datascan for multiple filesystems
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision 79357c2c (ceph): suites: add fs/multifs
Separate because it wants a larger MDS count. Points
to the new tests in test_failover.py.
Signed-off-by: John Spra...
John Spray
10:36 AM Revision c94d5025 (ceph): tasks/cephfs: add TestStandbyReplay
In addition to the multi-fs tests, more localised
standby-replay cases.
Signed-off-by: John Spray <john.spray@redhat...
John Spray
10:36 AM Revision 09f239f2 (ceph): tasks/cephfs: update test_journal_repair for multi fs
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
10:36 AM Revision 8528cccf (ceph): tasks: add cephfs TestMultiFilesystems
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
09:54 AM Revision e2b297a4 (ceph): osd: introduce command of 'osd tier rm'
introduce command of 'osd tier rm' as an alias of 'osd tier remove'
Signed-off-by: Dongsheng Yang <dongsheng.yang@ea...
Yang Dongsheng
09:54 AM Revision 95377621 (ceph): osd: introduce command of 'osd tier rm-overlay'
introduce command of 'osd tier rm-overlay' as an alias of 'osd tier remove-overlay'
Signed-off-by: Dongsheng Yang <d...
Yang Dongsheng
09:54 AM Revision ccc5e711 (ceph): config-key: introduce command of 'config-key rm'
introduce command of 'config-key rm' as an alias of 'config-key del'
Signed-off-by: Dongsheng Yang <dongsheng.yang@e...
Yang Dongsheng
09:53 AM Revision 397dae84 (ceph): mds: introduce command of 'mds rm_data_pool'
introduce command of 'mds rm_data_pool' as an alias of 'mds remove_data_pool'
Signed-off-by: Dongsheng Yang <dongshe...
Yang Dongsheng
09:53 AM Revision 19c61b18 (ceph): mon: introduce a comamnd of 'mon rm'
introduce command of 'mon rm' as an alias of 'mon remove'
Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Yang Dongsheng
09:53 AM Revision 4fa3f80e (ceph): osd: introduce a command of 'osd pool rm'
introduce command of 'osd pool rm' as an alias of 'osd pool delete'
Signed-off-by: Dongsheng Yang <dongsheng.yang@ea...
Yang Dongsheng
09:20 AM Revision b0b1dfb1 (ceph): mon: Introduce command of 'auth rm'
Introduce command of "auth rm" as an alias of "auth del"
Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Yang Dongsheng
08:04 AM Revision 164de7aa (ceph): Merge pull request #7923 from RustShen/master
doc: add cinder backend section to rbd-openstack.rst
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:52 AM Revision 439991a4 (ceph): osd/ScrubStore: remove unused function
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
05:43 AM Revision 223191f9 (ceph): common/config_opts.h: add osd_crush_initial_weight
Signed-off-by: You Ji <jiyou09@gmail.com> Ji You
05:36 AM Revision cecdc49e (ceph): osd: cleanup: Specify both template types for create_request()
Code consistency
Signed-off-by: David Zafman <dzafman@redhat.com>
David Zafman
05:32 AM devops Bug #15058 (Rejected): zipimport.ZipImportError: bad local file header in /usr/lib/python2.7/site...
make install gave the following error --
creating 'dist/ceph_disk-1.0.0-py2.7.egg' and adding 'build/bdist.linux-x...
Jai S
05:20 AM CephFS Backport #15057: infernalis: deleting striped file in cephfs doesn't free up file's space
NOTE: Original PR not yet merged. Nathan Cutler
05:16 AM CephFS Backport #15057 (Rejected): infernalis: deleting striped file in cephfs doesn't free up file's space
https://github.com/ceph/ceph/pull/8041 Nathan Cutler
05:19 AM CephFS Backport #15056: hammer: deleting striped file in cephfs doesn't free up file's space
NOTE: Original PR not yet merged. Nathan Cutler
05:16 AM CephFS Backport #15056 (Resolved): hammer: deleting striped file in cephfs doesn't free up file's space
https://github.com/ceph/ceph/pull/8042 Nathan Cutler
05:10 AM Bug #14968 (Resolved): common/obj_bencher.cc: fix verification crashing when there's no objects
Loïc Dachary
05:10 AM devops Bug #14402 (Resolved): ceph init script unconditionally sources /lib/lsb/init-functions
Loïc Dachary
05:10 AM CephFS Bug #13268 (Resolved): Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
Loïc Dachary
04:53 AM Backport #13335 (In Progress): hammer: OSD crashed when reached pool's max_bytes quota
Loïc Dachary
04:42 AM rbd Backport #14824: hammer: rbd and pool quota do not go well together
Moving to Ceph for cross reference purposes Loïc Dachary
04:37 AM Bug #15019 (Duplicate): hammer: fs test fails with log [ERR] : OSD full dropping all updates 100%...
This is a manifestation of an incomplete backport for which an the followup has been scheduled at http://tracker.ceph... Loïc Dachary
04:18 AM Backport #15055 (In Progress): hammer: mon: implement reweight-by-utilization feature
Loïc Dachary
04:17 AM Backport #15055 (Resolved): hammer: mon: implement reweight-by-utilization feature
https://github.com/ceph/ceph/pull/8026 Loïc Dachary
04:16 AM Feature #15054 (Resolved): mon: implement reweight-by-utilization feature
https://github.com/ceph/ceph/pull/7890
https://github.com/ceph/ceph/pull/8027
Loïc Dachary
03:38 AM CephFS Bug #15050 (Fix Under Review): deleting striped file in cephfs doesn't free up file's space
https://github.com/ceph/ceph/pull/8040
https://github.com/ceph/ceph/pull/8041
https://github.com/ceph/ceph/pull/8042
Zheng Yan
03:03 AM CephFS Bug #15050: deleting striped file in cephfs doesn't free up file's space
Well spotted. Greg Farnum
02:25 AM CephFS Bug #15050: deleting striped file in cephfs doesn't free up file's space
we don't handle 'stripe_count > 1' properly when purging stray.... Zheng Yan
03:20 AM Revision 99ec1839 (ceph): mds: fix stray purging in 'stripe_count > 1' case
Fixes: #15050
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
03:15 AM Revision 81d7b0d3 (ceph): Merge pull request #7999 from liewegas/wip-armhf
a few armhf (32-bit build) fixes
Reviewed-by: Dan Mick <dmick@redhat.com>
Dan Mick
03:10 AM CephFS Backport #13809 (Resolved): hammer: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
Loïc Dachary
03:10 AM CephFS Backport #13813 (Resolved): hammer: Daily segfault ll_forget reader couldn't read tag
Loïc Dachary
03:09 AM Backport #14873 (Resolved): hammer: rados bench seq crashes (v0.94.6)
Loïc Dachary
03:09 AM devops Backport #14946 (Resolved): hammer: redhat-lsb-core dependency was dropped, but is still needed
Loïc Dachary
03:09 AM Backport #14969 (Resolved): hammer: common/obj_bencher.cc: fix verification crashing when there's...
Loïc Dachary
03:09 AM Backport #14974 (Resolved): hammer: common/obj_bencher.cc: make verify error fatal
Loïc Dachary
03:09 AM Backport #14978 (Resolved): hammer: tools, test: Add ceph-objectstore-tool to operate on the meta...
Loïc Dachary
03:05 AM Revision 35eae5fb (ceph): Merge pull request #7911 from dzafman/wip-meta-list-hammer
hammer: tools, test: Add ceph-objectstore-tool to operate on the meta collection
Reviewed-by: Loic Dachary <ldachary...
Loïc Dachary
03:03 AM Revision c59b9944 (ceph): Merge pull request #7903 from branch-predictor/bp-hammer-force-bench-smoke
hammer: tools/rados: add bench smoke tests
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:02 AM Revision dd66eb91 (ceph): Merge pull request #7876 from SUSE/wip-14946-hammer
hammer: redhat-lsb-core dependency was dropped, but is still needed
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:00 AM Revision de43aba0 (ceph): Merge pull request #7817 from asheplyakov/hammer-bug-14873
hammer: tools: fix race condition in seq/rand bench (part 2)
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com>
R...
Loïc Dachary
03:00 AM Revision 48dfac64 (ceph): Merge pull request #7896 from asheplyakov/hammer-bug-14873-p1
hammer: tools: fix race condition in seq/rand bench (part 1)
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewe...
Loïc Dachary
02:59 AM Revision 5c217477 (ceph): Merge pull request #865 from ceph/wip-dbg-packages-1
packages: update for all the new debug packages we have in jewel vasukulkarni
01:40 AM Revision 7663b9f0 (ceph): crushtool: Don't crash when called on a file that isn't a crushmap
Fixes: #8286
Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
Brad Hubbard
01:36 AM Fix #8286 (In Progress): 0.80~rc1: `crushtool` crash
https://github.com/ceph/ceph/pull/8038
Before:
$ ./crushtool -d /etc/hosts|& head -2
terminate called after th...
Brad Hubbard
01:22 AM Revision e719cb16 (ceph): osdc: Reverse the probing vector in better way.
Signed-off-by: song baisen song.baisen@zte.com.cn ceph zte
01:21 AM Revision 3e96a92e (ceph): packages: update for all the new debug packages we have in jewel
Signed-off-by: Greg Farnum <gfarnum@redhat.com> Greg Farnum
12:51 AM Revision 2408f8dc (ceph): rgw: store system object meta in cache when creating it
Fixes: #14678
When creating the system object we can easily also get the object's meta, so
keep it in the cache.
Si...
Yehuda Sadeh
12:08 AM Revision 4d59b1d3 (ceph): rgw:bucket link now set the bucket.instance acl
Fixes: #11076
Signed-off-by: Zengran Zhang <zhangzengran@h3c.com>
Zengran Zhang

03/10/2016

11:55 PM CephFS Bug #15050: deleting striped file in cephfs doesn't free up file's space
Can you describe in a little more detail how you were creating and deleting these files? You talk about them being 10... Greg Farnum
07:08 PM CephFS Bug #15050 (Resolved): deleting striped file in cephfs doesn't free up file's space
I've been creating large (16-64 GB) files in an otherwise empty test cephfs (mounted via the kernel client in linux 4... Mike Shuey
11:42 PM Bug #8885: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()

Found it! It isn't a destructor race, but rather a register_inflight_op() being called out of the OpRequest const...
David Zafman
03:08 PM Bug #8885: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()

#0 0x00007f5353fe3cc9 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56
#1 0x00007f5...
David Zafman
11:41 PM Revision e730a984 (ceph): Merge pull request #7891 from rzarzynski/wip-rgw-content-disp
rgw: multiple Swift API compliance improvements for TempURL (Radoslaw Zarzynsk)
Reviewed-by: Yehuda Sadeh <yehuda@re...
Yehuda Sadeh
10:57 PM Revision 2ea72c1d (ceph): Merge pull request #7990 from x11562/rgw_unused_vector
rgw: remove unused vector
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:53 PM Revision e6ecc65e (ceph): Merge pull request #8031 from ceph/wip-rgw-usage
rgw: admin api for retrieving usage info (Ji Chen)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Matt B...
Yehuda Sadeh
10:50 PM Revision 356aaf26 (ceph): Merge pull request #8036 from yehudasa/wip-rgw-support-json-format-v2
rgw: support json format for admin policy API (Dunrong Huang)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed...
Yehuda Sadeh
10:26 PM Revision adccab01 (ceph): Merge pull request #7874 from badone/wip-coverity-rgw_lib-uninit
[rgw] RGWLib::env is not used so remove it
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:22 PM Revision b988f79b (ceph): rgw_admin: policy dump --xml backward compatibility
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
10:14 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I made the change locally and deployed a custom build to the OSD hosts in my test environment. I restarted all of the... Steve Taylor
09:00 AM Bug #13990 (Fix Under Review): Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashi...
https://github.com/ceph/ceph/pull/8017 Kefu Chai
05:18 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
> all OSDs are stuck with the same oldest map and therefore prevent each other from trimming their caches unnecessari... Kefu Chai
10:11 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
Nathan Cutler
09:39 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
> Why does the "install.upgrade" task do "apt-get install" and not "apt-get upgrade" ?
Excellent question! there's...
Ken Dreyer
09:16 PM Bug #15047 (Fix Under Review): Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
*jewel PR*: https://github.com/ceph/ceph/pull/8034 Nathan Cutler
09:02 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
I just finished going over the teuthology.log. Please bear with me:
First we have the install task, which installs...
Nathan Cutler
07:49 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
... Nathan Cutler
07:16 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
Can you re-try with the @wip-strict-debian-deps@ branch ( https://github.com/ceph/ceph/pull/7931 ) ?
Ken Dreyer
06:38 PM Bug #15047: Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
The actual error:
2016-03-10T02:34:38.385 INFO:teuthology.orchestra.run.vpm133.stderr:dpkg: error processing archi...
Dan Mick
04:49 PM Bug #15047 (Resolved): Packaging problem in upgrade:infernalis-x-jewel-distro-basic-vps
Run: http://pulpito.ceph.com/teuthology-2016-03-10_02:10:02-upgrade:infernalis-x-jewel-distro-basic-vps/
Jobs: ['505...
Yuri Weinstein
10:09 PM Backport #15051 (Resolved): hammer: test/librados/tier.cc doesn't completely clean up EC pools
https://github.com/ceph/ceph/pull/8052 Nathan Cutler
10:08 PM Bug #13878: test/librados/tier.cc doesn't completely clean up EC pools
Added hammer backport based on IRC discussion with Yuri and Dan:... Nathan Cutler
03:34 AM Bug #13878: test/librados/tier.cc doesn't completely clean up EC pools
from dmick: mon calls crushtool with a timeout of 5s (mon_lease), and kills it if it takes longer. Because of accumul... Loïc Dachary
01:42 AM Bug #13878 (Pending Backport): test/librados/tier.cc doesn't completely clean up EC pools
Loïc Dachary
10:04 PM Revision fae3b5b7 (ceph): Merge pull request #859 from ceph/wip-15014
Add packages.yaml Greg Farnum
10:00 PM Revision 6393565f (ceph): osd: make promote_probability_millis atomic_t
This is almost always read, so it should be cheap.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
09:54 PM Revision acb4a27a (ceph): remove ceph_real_time_t typedef and overrides using it
The two tests exercising stat2() and mtime2() have been collapsed
into one.
Signed-off-by: Matt Benjamin <mbenjamin@...
Matt Benjamin
09:46 PM Revision fd4d8cee (ceph): include/encoding: do not try to be clever with list encoding
In c++11 std::list::size() is O(1). No need to be clever.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
09:46 PM Fix #8286: 0.80~rc1: `crushtool` crash
Brad Hubbard
09:42 PM Revision 1b922e54 (ceph): test/pybind/test_ceph_argparse: fix reweight-by-utilization tests
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit d0f87131962b26cef9e31fa11651771856c41164)
Sage Weil
09:42 PM Revision 06a2a759 (ceph): man/8/ceph.rst: remove invalid option for reweight-by-*
--yes-i-really-mean-it is not valid option for reweight-by-*
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry pic...
Kefu Chai
09:37 PM Backport #15040: infernalis: test/librados/tier.cc doesn't completely clean up EC pools
Loic, does it have to be in hammer as well? Yuri Weinstein
01:45 AM Backport #15040 (In Progress): infernalis: test/librados/tier.cc doesn't completely clean up EC p...
Loïc Dachary
01:44 AM Backport #15040 (Resolved): infernalis: test/librados/tier.cc doesn't completely clean up EC pools
https://github.com/ceph/ceph/pull/7987 Loïc Dachary
09:36 PM Revision 6524f8bb (ceph): osd/PG: only set split child last_backfill if within PG range
If last_backfill is within the parent's PG range, set teh child to MIN.
If it's in the child's, the parent is done.
...
Sage Weil
09:35 PM Revision a1333f54 (ceph): rgw: support json format for admin policy API
Fixes: #14090, #14091
- before this patch:
$ curl -s -X GET http://radosrgw:9090/admin/bucket?format=json&policy&buc...
Dunrong Huang
09:35 PM Revision dd24f517 (ceph): rgw: support json format output for rados-admin policy command
when use rados-admin to get policy with parameter --format=json:
$ radosgw-admin policy --bucket=m8x --format=json
p...
Dunrong Huang
09:35 PM Revision 3a8b0e3d (ceph): rgw: remove unused header file
Signed-off-by: Dunrong Huang <riegamaths@gmail.com> Dunrong Huang
09:18 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
Yuri Weinstein
09:15 PM Bug #15012 (Fix Under Review): "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jew...
Yuri Weinstein
09:15 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
https://github.com/ceph/ceph-qa-suite/pull/864
Note: cherry-pick to infernalis
Yuri Weinstein
08:14 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
the final workunit, after the upgrade, should not have
branch: firefly
Sage Weil
06:03 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
Hmm, looking at the failed job: ... Nathan Cutler
05:27 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
I see that #11548 fixed a similar issue by adding a workunit ( https://github.com/ceph/ceph/commit/348a3d3c9880e7d022... Nathan Cutler
04:43 PM Bug #15012: "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distro-basic-vps
Run: http://pulpito.ceph.com/teuthology-2016-03-10_02:10:02-upgrade:hammer-x-jewel-distro-basic-vps/
Job: 50505
Log...
Yuri Weinstein
09:18 PM Revision 9a631ced (ceph): Removed branch: firefly from 4-after.yaml
Fixes #15012
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 872aed9e72d0bac1fc211525...
Yuri Weinstein
09:15 PM Revision 0f9c65d0 (ceph): Merge pull request #864 from ceph/wip-15012-jewel
Removed branch: firefly from 4-after.yaml Sage Weil
09:13 PM Revision 872aed9e (ceph): Removed branch: firefly from 4-after.yaml
Fixes #15012
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
Yuri Weinstein
09:03 PM Revision 740c52d6 (ceph): Merge pull request #8027 from liewegas/wip-reweight-fix
test/pybind/test_ceph_argparse: fix reweight-by-utilization tests
Reviewed-by: Kefu Chai <kchai@redhat.com>
Greg Farnum
07:13 PM Bug #15011: TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
Ok I got wrong on my assumptions. The prototypes makes the last argument optional. I have so to determine why and who... Anonymous
09:51 AM Bug #15011: TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
I worked on it trying to understand where this decoding error comes from.
The decoding complains comes from https:...
Anonymous
07:13 PM Revision 461bd7fa (ceph): Merge pull request #6656 from jmunhoz/wip-bucket-request-payment-usage-log
rgw: add bucket request payment feature usage statistics integration
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:27 PM Bug #15027 (Need More Info): Infernalis: backport? mon: pg stuck creating, even though an active+...
I take it back.. this wasn't a race. I can't figure out why the pg wasn't removed from the creating_pgs set, though. :( Sage Weil
06:25 PM Revision c85573ad (ceph): rgw: also dump realm in radosgw-admin sync status command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:08 PM Revision c812bbae (ceph): Merge pull request #8021 from branch-predictor/bp-bench-full-bw
common/obj_bencher.cc: bump the precision of bandwidth field
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:22 PM Revision d8f4d9ee (ceph): FileStore: Added O_DSYNC write scheme
lfn_open can now open file handle in O_DSYNC mode based on the
filestore_odsync_write config option. This should help...
Somnath Roy
05:11 PM Bug #15049 (Fix Under Review): ceph.py wait_for_daemons doesn't work with firefly
https://github.com/ceph/ceph-qa-suite/pull/863 Sage Weil
05:06 PM Bug #15049 (Resolved): ceph.py wait_for_daemons doesn't work with firefly
2016-03-10T08:23:20.200 INFO:teuthology.orchestra.run.smithi041:Running: 'sudo adjust-ulimits ceph-coverage /home/ubu... Sage Weil
05:11 PM devops Backport #15048 (In Progress): infernalis: RPM packaging puts ceph_daemon.py in ceph-common, Debi...
Nathan Cutler
05:01 PM devops Backport #15048 (Rejected): infernalis: RPM packaging puts ceph_daemon.py in ceph-common, Debian ...
https://github.com/ceph/ceph/pull/8029 Nathan Cutler
05:06 PM Revision 3625b8c4 (ceph): rados/singleton-nomsgr/all/11429: no mds
The newer cephfs logic wants to use the 'status' command on the
daemon, but that doesn't exist on firefly. Luckly we...
Sage Weil
05:03 PM Revision 70d3e130 (ceph): Merge pull request #7675 from vmcloud/wip-12917
rgw: adjust the request_uri to support absoluteURI of http request Matt Benjamin
05:01 PM devops Bug #15046 (Pending Backport): RPM packaging puts ceph_daemon.py in ceph-common, Debian packaging...
Nathan Cutler
04:59 PM devops Bug #15046: RPM packaging puts ceph_daemon.py in ceph-common, Debian packaging puts it in ceph (s...
The ... Nathan Cutler
02:56 PM devops Bug #15046 (Resolved): RPM packaging puts ceph_daemon.py in ceph-common, Debian packaging puts it...
Hi,
I would like to report an issue specific to Infernalis.
It is no more possible to use "ceph daemon" command...
Florent B
04:50 PM Bug #14998 (Fix Under Review): Build failures with Boost 1.60
I've resolved the issue in https://github.com/ceph/ceph/pull/7984 Robert LeBlanc
04:23 PM Revision c0cbc5f5 (ceph): Merge pull request #862 from ceph/wip-odsync
rados: Enable odsync write for pggrow thrasher Sage Weil
04:13 PM Revision d0f87131 (ceph): test/pybind/test_ceph_argparse: fix reweight-by-utilization tests
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:13 PM Revision 797f1d41 (ceph): man/8/ceph.rst: remove invalid option for reweight-by-*
--yes-i-really-mean-it is not valid option for reweight-by-*
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
04:03 PM Bug #14794: Objecter: valgrind unclean
This is known behavior in Boost which they claim is a false positive, their bug history is at https://svn.boost.org/t... Adam Emerson
06:16 AM Bug #14794: Objecter: valgrind unclean
I think this came in as part of the locking changes you've been making? If this is an internal boost issue we can jus... Greg Farnum
03:45 PM Revision 88e86d77 (ceph): rados: Enable odsync write for pggrow thrasher
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
02:50 PM Revision d9ac0474 (ceph): log: do not repeat errors to stderr
If we get an error writing to the log, log it only once to stderr.
This avoids generating, say, 72 GB of ENOSPC error...
Sage Weil
02:38 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
if we just trim old snaps, num_object in 'ceph df' does not change (even we wait for a long time). If we create and d... Zheng Yan
01:52 PM Revision 76b14507 (ceph): Merge pull request #8025 from roidayan/xio-remove_duplicate_peer_addr_a...
xio: remove duplicate assignment of peer addr
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
01:48 PM CephFS Bug #15045 (Resolved): CephFSVolumeClient.evict should be limited by path, not just auth ID
John Spray
01:33 PM Revision d1627f5d (ceph): xio: remove duplicate assignment of peer addr
Signed-off-by: Roi Dayan <roid@mellanox.com> Roi Dayan
01:30 PM Revision 6ec676df (ceph): mon: add 'osd utilization' command
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 5b757eff868dbce2393beadd9fe2522372288cc0)
Sage Weil
01:30 PM Revision 9a9d147a (ceph): osd/MonCommand: add/fix up 'osd [test-]reweight-by-{pg,utilization}'
- show before/after pg placement stats
- add test- variants that don't do anything
- only allow --no-increasing on th...
Sage Weil
01:30 PM Revision 76eb3c8f (ceph): qa/workunits/cephtool/test.sh: test reweight-by-x commands
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 28b33a5b57e3f898808bd8ccc5e314667f84912a)
Sage Weil
01:30 PM Revision f4b4ef76 (ceph): mon/OSDMonitor: fix indentation
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 47b650c1497b8eaf37cfcb7e3b9fda12d8cf2d7a)
Sage Weil
01:30 PM Revision f13cdeaf (ceph): mon: make reweight max_change default configurable
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 8a9429d85bc99874dc9871b43b2d0c7ad1086803)
Sage Weil
01:30 PM Revision 55ad2c77 (ceph): mon: make max_osds an optional arg
We keep the config option with the default (4), but let you
specify the max # of osds to reweight as a third optional...
Sage Weil
01:30 PM Revision 241f7626 (ceph): mon: remove range=100 from reweight-by-* commands
Specifying the range makes it skip instead of error when you give
it a bad value.
Signed-off-by: Sage Weil <sage@red...
Sage Weil
01:30 PM Revision 94134d91 (ceph): osd/OSDMap: add summarize_mapping_stats
Calculate some basic stats about the PG distribution.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from...
Sage Weil
01:20 PM Revision 5a78390d (ceph): suites: invoke libcephfs python tests
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
01:16 PM Revision 932f75d1 (ceph): mon: make reweight-by-* max_change an argument
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit a70eaabcfc1cc1dfb9b6ba2d7f71b3d76496eb55)
Sage Weil
01:16 PM Revision d8372cea (ceph): osd: add mon_reweight_max_osds to limit reweight-by-* commands
Add configurable mon_reweight_max_osds which limits the number
of OSDs modified each time reweight-by-* is called (by...
Dan van der Ster
01:16 PM Revision 6a422b26 (ceph): osd: add mon_reweight_max_change option which limits reweight-by-*
Add a configurable mon_reweight_max_change which limits be default
the reweight-by-* commands to only change an OSDs ...
Dan van der Ster
01:16 PM Revision d3635b79 (ceph): test: add simple test for new reweight-by-* options
Test validity of --no-increasing and --yes-i-really-mean-it.
Signed-off-by: Dan van der Ster <daniel.vanderster@cern...
Dan van der Ster
01:16 PM Revision e993851b (ceph): osd: add sure and no-increasing options to reweight-by-*
Add a --no-increasing option to reweight-by-* which can be used to only decrease
OSD weights without increasing any. ...
Dan van der Ster
12:58 PM Revision 9cf46b84 (ceph): test: correct journal test failure caused by two merged commits
Commit 21d9595 changed the journal width to 3 objects while commit
a00eae0 changed the signature of the journal creat...
Jason Dillaman
12:38 PM Bug #15037 (Fix Under Review): ceph_argparse: test_ceph_argparse.TestOSD.test_reweight_by_utiliza...
https://github.com/ceph/ceph/pull/8024 Kefu Chai
01:08 AM Bug #15037 (Resolved): ceph_argparse: test_ceph_argparse.TestOSD.test_reweight_by_utilization fails
This causes 'make check' to fail on master.
From http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-a...
Josh Durgin
12:31 PM Revision 8affb392 (ceph): xio: remove unused variable
Signed-off-by: Roi Dayan <roid@mellanox.com> Roi Dayan
12:31 PM Revision e68e37f3 (ceph): rgw: require openldap library client headers
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
12:27 PM Revision a693be27 (ceph): tasks/cephfs: vstart & fuse improvements
A couple of corner cases that would get tripped up sometimes
in a vstart_runner.py environment.
Signed-off-by: John ...
John Spray
12:11 PM Revision 4e9b9539 (ceph): mon: update for multiple filesystems
This is a big logic change throughout MDSMonitor,
and additonally some new commands to handle
per-fs variants of what...
John Spray
12:11 PM Revision 0ed5eb7a (ceph): tools/cephfs: update for FSMap
Everywhere we used to take a rank, we now
take a role (<fscid:rank>)
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
12:11 PM Revision 226639de (ceph): client: update for multi-filesystems
Two main changes:
* handle client_mds_namespace setting to subscribe
to a particular MDSMap
* subscribe to FSMap...
John Spray
12:11 PM Revision 3c2f28a2 (ceph): test: update argparse test for rmfailed
rmfailed argument used to be an integer greater than
zero, now any string is acceptable (because we accept
fs:rank ro...
John Spray
12:11 PM Revision eb881010 (ceph): mds: make FSMap.get_filesystem return const
To make it clearer that anyone modifying a filesystem
should be using modify_filesystem()
Note that FSMap is still a...
John Spray
12:11 PM Revision 9b362858 (ceph): mds: set FSMap encoding version to 6
It was 10, but that wasn't actually necessary,
6 is enough to get ahead of the MDSMap version.
Signed-off-by: John S...
John Spray
11:55 AM rbd Subtask #13296: Mirroring API + rbd CLI updates for images
Jason Dillaman wrote:
>
> Also add journal details/mirroring status support to 'rbd info' and 'rbd status'
What...
Ricardo Dias
11:50 AM Revision 7a461a43 (ceph): common/obj_bencher.cc: bump the precision of bandwidth field
When calculated final average bandwidth exceeds 999MB, it starts
to get printed in scientific notation. Bump up the b...
Piotr Dałek
11:18 AM Revision 5a320176 (ceph): mds: handle get_mds_info as const
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
11:18 AM Revision ce37bbfe (ceph): mds: introduce fs_cluster_id_t type
Unique identifier for a filesystem within
the ceph cluster. Abbreviated to `fscid`,
deliberately chosen to not confl...
John Spray
11:18 AM Revision 00022bf9 (ceph): mds: add FSMap
FSMap encapsulates a collection of MDSMaps, one
for each filesystem, and a collection of standby
MDS daemons that hav...
John Spray
11:18 AM Revision ccbd2665 (ceph): messages: add MFSMap
For mon clients that subscribe to 'fsmap'.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
11:18 AM Revision 93fdd95b (ceph): mon: initialize last_* timestamps on new pgs to creation time
Currently, when you create a pool, until the PGs peer you generate a health
error like
8 pgs are stuck i...
Sage Weil
11:18 AM Revision a30d9ca5 (ceph): vstart: don't call "fs new" repeatedly
It was doing it once for each MDS, which is safe
(because it's idempotent) but silly.
Signed-off-by: John Spray <joh...
John Spray
11:18 AM Revision 9ff5cb18 (ceph): vstart: don't set max_mds to use all daemons
This is only useful if you want to test a
single namespace with no standbys. It's easier
to initially have max_mds=1...
John Spray
11:18 AM Revision 7778d162 (ceph): include/CompatSet: trivial const-ness fix
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
11:18 AM Revision 8ae92c10 (ceph): java: add O_DIRECTORY to libcephfs interface
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
11:18 AM Revision c3a8a09e (ceph): java: update libcephfs tests to learn pool name
Don't assume the data/metadata pools are called
"data" and "metadata".
Signed-off-by: John Spray <john.spray@redhat....
John Spray
11:18 AM Revision 1cd71d35 (ceph): messages: fix strings for MMonGetVersionReply
It previously described itself as "mon_check_map_ack"
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
11:18 AM Revision 99c17509 (ceph): doc: cephfs admin command list
Creating this skeleton to include the new
"ceph fs ..." commands. Needs filling out
with prose about purpose and res...
John Spray
11:18 AM Revision 22ff1224 (ceph): qa: update cephtool test for CephFS multi filesystems
Includes adding test for the enable_multiple flag.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
11:12 AM devops Bug #15042 (Fix Under Review): btrfs buildrequire added to fix make check does not get installed ...
*master PR*: https://github.com/ceph/ceph/pull/8016
Deeper analysis in the commit message there.
Nathan Cutler
06:29 AM devops Bug #15042 (Resolved): btrfs buildrequire added to fix make check does not get installed by insta...
https://github.com/ceph/ceph/pull/7742 fixed a make check failure by adding a buildtime dependency:... Nathan Cutler
11:08 AM CephFS Bug #15008: fuse expects root inode number to be FUSE_ROOT_ID
*jewel PR*: https://github.com/ceph/ceph/pull/7976 Nathan Cutler
09:11 AM Revision 23e72e4b (ceph): librbd: make journal start_external_replay not block
Its caller shall check the journal is in right state.
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
09:11 AM Revision 3fb51529 (ceph): journal: provide method to check if journaler initialized
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
09:05 AM CephFS Bug #12776 (Resolved): qa: standby MDS not shutting down, "reached maximum tries (50) after waiti...
Zheng Yan
09:04 AM CephFS Bug #13583 (Resolved): Client::_fsync() on a given file does not wait unsafe requests that create...
Zheng Yan
09:03 AM CephFS Bug #13675 (Resolved): Failure in LibCephFS.DirLs
Zheng Yan
09:02 AM CephFS Bug #13729 (Resolved): Daily segfault ll_forget reader couldn't read tag
Zheng Yan
09:00 AM CephFS Bug #14196 (Resolved): test_object_deletion fails (tasks.cephfs.test_damage.TestDamage)
Zheng Yan
08:59 AM CephFS Bug #14374 (Resolved): MDS asok handlers trigger lock cycle assertion if they take mds_lock
Zheng Yan
08:59 AM CephFS Bug #14380 (Resolved): "ceph mds setmap" crashes mon on invalid input
Zheng Yan
08:58 AM CephFS Bug #14379 (Resolved): Add confirmation flag to "ceph mds rmfailed"
Zheng Yan
08:56 AM Revision c49de8c1 (ceph): Merge remote-tracking branch 'origin/jewel'
Conflicts:
src/client/Client.h
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
08:52 AM Revision 65bbe222 (ceph): Merge pull request #812 from ceph/jewel-10436
suites/fs: enable all snapshost test scripts Greg Farnum
08:52 AM CephFS Bug #10436 (Resolved): ceph-fuse: snapshot flushing from page cache to Client is not coherent
Greg Farnum
08:52 AM Revision dedcbc6b (ceph): Merge pull request #7495 from ukernel/jewel-10436
client: flush kernel pagecache before creating snapshot
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
08:33 AM Revision c218c53d (ceph): global: record target user and group strings
Useful so we don't have to do a reverse lookup when dropping permissions
in civetweb.
Signed-off-by: Karol Mroz <kmr...
Karol Mroz
08:33 AM Revision f50c332b (ceph): global_init: add run_pre_init argument to function signature
Allows running the global_pre_init() separately in order to parse config
options prior to invoking global_init().
Si...
Karol Mroz
08:33 AM Revision 422c749b (ceph): rgw_main: break up frontend config parsing
Before invoking global_init(), determine which frontends are configured.
If Civetweb is to be used, ensure it will be...
Karol Mroz
08:33 AM Revision e3d8d65f (ceph): rgw: instruct civetweb to drop permissions
Get uid set in g_ceph_context and pass to civetweb where setuid()/setgid()
will be invoked. This Allows for starting ...
Karol Mroz
08:15 AM Revision 2294c73d (ceph): Packaging: Removing conditional BuildRequires for btrfs-progs
By pull request 7742, the btrfs-progs package was considered as a BuildRequires
only when --with tests was engaged li...
Erwan Velu
08:14 AM devops Feature #15043 (Resolved): Build and distribute packages for Ubuntu 16.04 LTS (Xenial Xerus)
Ubuntu 16.04 LTS (Xenial Xerus) is just around the corner and it is going to be big for us (it's going to be released... Frode Nordahl
08:05 AM Bug #15010 (Need More Info): simple->async peer got "failed lossy con, dropping message"
Haomai Wang
06:49 AM Revision 44f7b872 (ceph): Merge pull request #7798 from ukernel/wip-mds-snap
A few more snapshot fixes, mostly around snapshotted inode/dentry tracking
Reviewed-by: Sage Weil <sage@redhat.com>
...
Greg Farnum
06:43 AM CephFS Bug #14996 (Resolved): libcephfs hangs on shutdown if an unclosed opendir handle exists
Greg Farnum
06:43 AM Revision d783e967 (ceph): Merge pull request #7994 from ukernel/jewel-14996
Merge: Fix client handling of "lost" open directories on shutdown
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
06:31 AM Revision 5fe3ff3f (ceph): Modifications to rbd-openstack.rst
Original configuration is not working
'enabled_backends' should be changed accordingly
Signed-off-by: RustShen <rus...
RustShen
06:31 AM Revision f69046cf (ceph): Merge pull request #731 from ceph/wip-scrub-repair
Wip scrub repair Greg Farnum
06:29 AM Revision fafaaf42 (ceph): Merge remote-tracking branch 'origin/greg-fs-testing-3-7-damage'
Greg Farnum
06:26 AM CephFS Bug #14800 (Resolved): [ceph-fuse] Fh ref might leak at umounting
Greg Farnum
06:25 AM Revision eaded2ea (ceph): Merge pull request #7686 from david-z/wip-fix-fh-ref-leak
ceph-fuse: Fix potential filehandle ref leak at umount
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Greg F...
Greg Farnum
06:25 AM Revision 9f69cb1a (ceph): Merge remote-tracking branch 'origin/greg-fs-testing-3-7-damage'
Greg Farnum
06:24 AM CephFS Bug #14798 (Resolved): free fds being exhausted eventually because freed fds are never put back
Greg Farnum
06:24 AM Revision d63186f4 (ceph): Merge pull request #7685 from david-z/wip-fix-put-free-fd-back
[cephfs] fix free fds being exhausted eventually because freed fds are never put back
Reviewed-by: Yan, Zheng <zyan@...
Greg Farnum
06:22 AM Revision 9ae84868 (ceph): Merge pull request #7003 from jcsp/wip-cephfs-tmap-migrate
tools/cephfs: add tmap_upgrade
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redhat.c...
Greg Farnum
06:12 AM CephFS Bug #15038 (Resolved): unittest_mds_types: inode_t.compare_equal fails
Greg Farnum
03:13 AM CephFS Bug #15038 (Fix Under Review): unittest_mds_types: inode_t.compare_equal fails
https://github.com/ceph/ceph/pull/8014 Zheng Yan
01:11 AM CephFS Bug #15038 (Resolved): unittest_mds_types: inode_t.compare_equal fails
This causes 'make check' to fail on master.
http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-amd64-...
Josh Durgin
06:12 AM Revision 6f81a7ad (ceph): Merge pull request #8014 from ukernel/wip-15038
mds: fix inode_t::compare()
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
05:38 AM Bug #14995 (Resolved): "ceph version 10.0.3 was not installed, found 10.0.4."
Dan Mick
05:38 AM Bug #14995: "ceph version 10.0.3 was not installed, found 10.0.4."
Investigated; from IRC:
http://pulpito.ceph.com/teuthology-2016-03-09_02:10:10-upgrade:infernalis-x-jewel-distro-b...
Dan Mick
03:40 AM Revision 1856de38 (ceph): Merge pull request #8012 from zmc/jewel
man/8/ceph-disk: fix formatting issue
Reviewed-by: Dan Mick <dmick@redhat.com>
Dan Mick
03:23 AM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
mon calls crushtool with a timeout of 5s (mon_lease), and kills it if it takes longer. Because of accumulated EC-poo... Dan Mick
01:51 AM Bug #14849 (Duplicate): (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis...
Loïc Dachary
01:51 AM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
http://tracker.ceph.com/issues/15040 is the backport of http://tracker.ceph.com/issues/13878 which explains the issue Loïc Dachary
01:40 AM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
That happens because validating the crushmap is blocking the mon. If the validation takes more than mon_lease ... the... Loïc Dachary
03:04 AM rbd Documentation #15041 (Resolved): Write RBD image mirroring documentation
Jason Dillaman
02:57 AM Revision 5d2693d3 (ceph): Merge pull request #8010 from dillaman/wip-15032-infernalis
librbd: possible QEMU deadlock after creating image snapshots
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
02:53 AM rbd Bug #14908 (Resolved): Journal replay needs to conditionally refresh the image between events
Jason Dillaman
02:50 AM Revision 9b79d05c (ceph): mds: fix inode_t::compare()
Fixes: #15038
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
02:48 AM rbd Backport #15032 (Fix Under Review): infernalis: QEMU VM hangs talking to RBD via librbd
Jason Dillaman
02:48 AM rbd Backport #15033 (Fix Under Review): hammer: QEMU VM hangs talking to RBD via librbd
Jason Dillaman
01:51 AM Revision 4fdd10d5 (ceph): Merge pull request #7978 from dillaman/wip-14908
librbd: refresh image if required before replaying journal ops
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:32 AM rbd Subtask #14663 (Resolved): Integrate librbd with journal tag allocation
Jason Dillaman
01:32 AM rbd Subtask #14869 (Resolved): journal library should re-use thread pool and timer
Jason Dillaman
01:30 AM Revision e3ea4e39 (ceph): Merge pull request #8009 from dillaman/wip-14988
test: reproducer for writeback CoW deadlock
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:29 AM Bug #14922: osd/ReplicatedPG: break out loop if we encounter error during do_pg_op()
https://github.com/ceph/ceph/pull/7844 xie xingguo
01:25 AM Revision 4260b08f (ceph): Merge pull request #8005 from dillaman/wip-rbd-lock-fence
pybind: flag an RBD image as closed regardless of result code
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:23 AM Revision facd50d5 (ceph): Merge pull request #8001 from dillaman/wip-rbd-cram
test: update rbd integration cram tests for new default features
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:13 AM Bug #15039 (Resolved): test/ceph_objectstore_tool.py fails
This causes 'make check' to fail.
http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-amd64-basic/log....
Josh Durgin
01:06 AM Revision 0d9fb7a7 (ceph): test: reproducer for writeback CoW deadlock
Refs: #14988
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
01:02 AM Revision 93be4c6e (ceph): rgw_admin: minor output cleanups
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
01:02 AM Revision 03f8e624 (ceph): rgw_admin: show oldest metadata change not applied
in radosgw-admin sync status
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
01:02 AM Revision eea64de6 (ceph): rgw_admin: show more data sync info
in radosgw-admin sync status command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
01:02 AM Revision 453bc556 (ceph): rgw_admin: report oldest data not synced
in radosgw-admin sync status
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
01:02 AM Revision 3d58c14c (ceph): rgw: silence some noisy log messages
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
01:02 AM Revision b15f1ec1 (ceph): rgw_admin: a command to show sync status
show it in a human readable way
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:37 AM Revision f8c623d7 (ceph): Merge pull request #860 from ceph/wip-krbd-fio
Fixes for krbd test cases
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:16 AM Bug #15036 (Closed): doc build full of warnings and errors, sphinx-build exits with success
part of admin/build-doc:
$ build-doc/virtualenv/bin/sphinx-build -a -n -b dirhtml -d doctrees doc build-doc/output...
Dan Mick

03/09/2016

11:46 PM Revision 977bed09 (ceph): man/8/ceph-disk: fix formatting issue
ERROR: /srv/autobuild-ceph/gitbuilder.git/build/doc/man/8/ceph-disk.rst:39: Unexpected indentation.
WARNING: /srv/aut...
Sage Weil
11:12 PM Revision 281d63df (ceph): librbd: complete cache reads on cache's dedicate thread
If a snapshot is created out-of-band, the next IO will result in the
cache being flushed. If pending writeback data ...
Jason Dillaman
11:11 PM Revision 621e3aef (ceph): test: reproducer for writeback CoW deadlock
Refs: #14988
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 16b6efdd24b25ba1f6bc6586...
Jason Dillaman
11:10 PM rbd Backport #15032 (In Progress): infernalis: QEMU VM hangs talking to RBD via librbd
Jason Dillaman
09:52 PM rbd Backport #15032 (Resolved): infernalis: QEMU VM hangs talking to RBD via librbd
https://github.com/ceph/ceph/pull/8010 Nathan Cutler
11:09 PM rbd Backport #15033 (In Progress): hammer: QEMU VM hangs talking to RBD via librbd
Jason Dillaman
09:52 PM rbd Backport #15033 (Resolved): hammer: QEMU VM hangs talking to RBD via librbd
https://github.com/ceph/ceph/pull/8011 Nathan Cutler
11:00 PM Revision f9e5ae80 (ceph): librbd: complete cache reads on cache's dedicate thread
If a snapshot is created out-of-band, the next IO will result in the
cache being flushed. If pending writeback data ...
Jason Dillaman
10:50 PM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
Sage, what does that PR have to do with this bug? Is the spare rule somehow making crushtool time out, or something?... Dan Mick
10:34 PM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
Additional logging added in prepare_new_pool shows:
prepare_new_pool failed with -22: error running crushmap throu...
Dan Mick
10:37 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
*master PR*: https://github.com/ceph/ceph/pull/8009 (reproducer -- confirms not an issue in Jewel) Jason Dillaman
09:52 PM rbd Bug #14988 (Pending Backport): QEMU VM hangs talking to RBD via librbd
Note that there is no master PR for this issue. Jason is going to do the fix in infernalis and then backport it from ... Nathan Cutler
09:46 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
Shouldn't be an issue in Jewel due to new asynchronous internals Jason Dillaman
09:26 PM rbd Bug #14988 (In Progress): QEMU VM hangs talking to RBD via librbd
Jason Dillaman
09:13 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
If an AIO request results in an image refresh due to a new snapshot creation, the cache will be flushed. When this o... Jason Dillaman
10:36 PM Revision 7ffbe409 (ceph): test: reproducer for writeback CoW deadlock
Refs: #14988
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 16b6efdd24b25ba1f6bc6586...
Jason Dillaman
10:28 PM Revision 48e40fcd (ceph): mon: default ec min_size to k+1
If m OSDs are down and we allow writes to the remaining k, the
PG could be unpeerable if one of these k goes down dur...
Dan van der Ster
10:18 PM Revision 3d404f2e (ceph): Merge pull request #7906 from dillaman/wip-14869
journal: re-use common threads between journalers
Conflicts:
src/journal/JournalPlayer.cc
src/librbd/Journal.cc
s...
Josh Durgin
10:08 PM Revision ce33a41c (ceph): osd: drop unused from arg from handle_pg_peering_evt
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
10:03 PM Revision cfed9b6a (ceph): Merge pull request #7958 from trociny/wip-rbd-mirror-fixup
rbd-mirror: minor fix-ups for initial skeleton implementation
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Revi...
Josh Durgin
10:02 PM Revision 55efa7ae (ceph): Merge pull request #7884 from dillaman/wip-14663
librbd: allocate new journal tag after acquiring exclusive lock
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
10:02 PM rbd Bug #14789 (Resolved): Truncate of non-existent object results in object map flagged as exists
Josh Durgin
10:01 PM Revision 3538f111 (ceph): Merge pull request #7772 from xinxinsh/wip-14789
librbd: truncate does not need to mark the object as existing in the object map
Reviewed-by: Josh Durgin <jdurgin@re...
Josh Durgin
09:58 PM Revision e929b0b2 (ceph): osd: only pass history to handle_pg_peering_evt
We were passing the whole pg_info, but we only need the
history.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
09:55 PM rbd Bug #15034 (Resolved): Possible inconsistent IO when using configured for multiple op threads
When 'rbd_op_threads' is set to a value higher than 1 (defaults to 1), it's quite possible for an aio flush op to com... Jason Dillaman
09:52 PM Revision 363e4318 (ceph): doc: Add French mirror
Signed-off-by: Wido den Hollander <wido@42on.com> Wido den Hollander
09:42 PM Revision 868b7945 (ceph): mirrors: Change contact e-mail address for se.ceph.com
Signed-off-by: Wido den Hollander <wido@42on.com> Wido den Hollander
09:32 PM Revision 89daecf4 (ceph): Merge pull request #8003 from liewegas/wip-ceph-disk-doc
man/8/ceph-disk: fix formatting issue Zack Cerza
09:21 PM Revision 100b0db1 (ceph): Reflect that ceph-dbg is dropped
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
09:18 PM Revision 705927ff (ceph): Add packages.yaml
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
09:13 PM Revision 9a480e23 (ceph): Merge pull request #7927 from oritwas/wip-rgw-fix-default
rgw: RGWZoneParams::create should not handle -EEXIST error
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Sage Weil
08:45 PM Revision cec8f23b (ceph): Merge remote-tracking branch 'gh/jewel'
Sage Weil
08:05 PM Revision 5e23cba1 (ceph): Merge pull request #7768 from xinxinsh/wip-fix-zero
osd: filestore: FALLOC_FL_PUNCH_HOLE must be used with FALLOC_FL_KEEP_SIZE
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
08:04 PM Bug #14922 (Resolved): osd/ReplicatedPG: break out loop if we encounter error during do_pg_op()
Sage Weil
08:03 PM Revision 811229ba (ceph): Merge pull request #7844 from xiexingguo/xxg-wip-14922
osd: replicatedpg: break out loop if we encounter fatal error during do_pg_op()
Reviewed-by: Sage Weil <sage@redhat....
Sage Weil
08:03 PM Revision 9c13921f (ceph): Merge pull request #7864 from dillaman/wip-librados-aio-notify
librados: race condition on aio_notify completion handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil
08:02 PM Revision 96face6e (ceph): Merge pull request #7928 from branch-predictor/bp-radostool-reduce-mem
tools/rados: reduce "rados put" memory usage by op_size
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
08:01 PM Revision af5d1b1a (ceph): Merge pull request #7967 from tchaikov/wip-si-cast-coverity
common/strtol.cc: fix the coverity warnings
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Sage Weil
07:59 PM Bug #15031 (Resolved): msg/async: debug spam on throttle
... Sage Weil
07:25 PM RADOS Bug #15015: prepare_new_pool doesn't return failure string ss
As discussed in IRC, no, that PR is only a test branch for diagnosing a monitor upgrade problem; really the error str... Dan Mick
12:27 AM RADOS Bug #15015: prepare_new_pool doesn't return failure string ss
https://github.com/ceph/ceph/commit/026db9204d9baad743a01c03b8b09fef89e7df2f looks good, do you have a PR with it ? Loïc Dachary
07:20 PM Bug #14983: osd: handle EIO in handle_sub_read
Samuel Just wrote:
> osd 5 is getting an EIO on object 2/ab64d095/100000578e9.00001458/head. We don't handle this w...
Aaron T
07:07 PM Revision 42a9e65c (ceph): Merge pull request #7948 from avnerbh/fix_avoid_enqueue_dup_code
msg: remove duplicated code - local_delivery will now call 'enqueue'
Reviewed-by: Kefu Chai <kchai@redhat.com>
Revie...
Sage Weil
07:06 PM Revision 2b9775db (ceph): Merge pull request #7890 from liewegas/wip-reweight
mon: osd [test-]reweight-by-{pg,utilization} command updates
Reviewed-by: Samuel Just <sjust@redhat.com>
Sage Weil
06:57 PM Revision 4c3c2ae4 (ceph): common: WeightedPriorityQueue Boost 1.60.0 requires some more
comparisions for advanced lookp and insertion functions.
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com>
Robert LeBlanc
06:56 PM Revision ca160372 (ceph): pybind: flag an RBD Image as closed regardless of result code
The image will always be closed -- the error code just alerts the
user to any possible error encountered when closing...
Jason Dillaman
06:55 PM Revision a8e82a38 (ceph): librbd: permit watch flush to return error code
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
06:46 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
/a/sage-2016-03-08_12:22:24-rados-wip-sage-testing---basic-smithi/47523 Sage Weil
06:43 PM Documentation #15030 (Closed): OpenStack Nova configuration is misleading
The section [1], describes putting rbd_user and rbd_secret_uuid in nova.conf and says this is required for attaching ... Sam Matzek
06:38 PM Revision bc627922 (ceph): rgw: free components on shutdown
Also, use ldout in rgw_file.h in 3 places.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
06:37 PM Revision bd6c64da (ceph): qa/workunits/rados/test.sh: capture stderr too
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:31 PM Revision 0ea13ca9 (ceph): rgw: LDAP pass-through authentication
Implement a new external authenticator based on LDAP and the
new external token format.
External LDAP auth now works...
Matt Benjamin
06:25 PM Revision 661891aa (ceph): mon: remove range=100 from reweight-by-* commands
Specifying the range makes it skip instead of error when you give
it a bad value.
Signed-off-by: Sage Weil <sage@red...
Sage Weil
06:18 PM Bug #14995: "ceph version 10.0.3 was not installed, found 10.0.4."
Still failing latest runs:
http://pulpito.ceph.com/teuthology-2016-03-09_02:10:10-upgrade:infernalis-x-jewel-distr...
Yuri Weinstein
06:11 PM rbd Bug #13122 (Resolved): rbd: stripingv2 feature bit not set when unnecessary for striping params
This was fixed sometime in the recent rbd cli refactor. Josh Durgin
05:55 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I spent some time looking at the OSD code yesterday. If I'm reading OSD::handle_osd_map() correctly, then the problem... Steve Taylor
05:29 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
30 is the @osd_target_transaction_size@. i am preparing a changeset to force the OSD trim osdmaps even if the incomin... Kefu Chai
05:30 PM Revision 8dcaacbb (ceph): man/8/ceph-disk: fix formatting issue
ERROR: /srv/autobuild-ceph/gitbuilder.git/build/doc/man/8/ceph-disk.rst:39: Unexpected indentation.
WARNING: /srv/aut...
Sage Weil
04:56 PM rbd Subtask #15029 (Resolved): Use watch/notify to alert to specific changes in the rbd_mirroring object
This will eliminate to constantly poll the object for updates -- instead, it would only need to pull the object after... Jason Dillaman
04:55 PM Revision cf0665e8 (ceph): osd: pg: remove get_log_write_pos() method
which is never used.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
04:42 PM Revision ed7906e5 (ceph): test: update rbd integration cram tests for new default features
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:32 PM rbd Bug #15028 (Resolved): Deep-flatten incorrectly updates fast-diff stats
Flattening a clone of an empty image with fast-diff and deep-flatten enabled results in all objects being flagged as ... Jason Dillaman
03:54 PM Revision 2bb6ef9d (ceph): rgw: ldap token glue
Based on feedback from upstream RGW, introduce a new json-format
token structure representing credentials for pass-th...
Matt Benjamin
03:52 PM Revision 87ca3efe (ceph): rgw: add a pure c++, header-only base64 encode/decode
interface is based on strings, but takes boost::string_ref
when encoding, column-wrap is controlled by the <wrap_wid...
Matt Benjamin
03:52 PM Revision 5a5969e9 (ceph): os/bluestore/BlueStore: For overwrite a extent, allocate new extent rat...
This bug introduce by commit:b0b4b6de362f0edf. This commit forget this
case which overwrite(0, bluestore_min_alloc_si...
Jianpeng Ma
03:50 PM Revision 06586037 (ceph): Merge pull request #7847 from wido/mirroring-fixes
Updated scripts and documentation for mirrors
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
03:48 PM Revision 0a7407b2 (ceph): mirror: Add examle rsync daemon configuration
This can be used by mirrors to offer a rsync service to end-users
Signed-off-by: Wido den Hollander <wido@42on.com>
Wido den Hollander
03:48 PM Revision 2025d631 (ceph): Add script to test connectivity and availability of Ceph mirrors
Signed-off-by: Wido den Hollander <wido@42on.com> Wido den Hollander
03:48 PM Revision 63be401a (ceph): doc: Updated docs with additional mirror information
Signed-off-by: Wido den Hollander <wido@42on.com> Wido den Hollander
03:47 PM Bug #15027 (Can't reproduce): Infernalis: backport? mon: pg stuck creating, even though an active...
... Sage Weil
03:31 PM Revision 2dc78c86 (ceph): Merge pull request #7552 from dachary/wip-14669-key-management
ceph-disk: key management support
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:28 PM Revision 39954dac (ceph): os/bluestore/BlueStore: Allow _dump_onode dynamic accept log level.
Make _dump_onode dynamic accept different log level in different case.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel...
Jianpeng Ma
03:24 PM rbd Fix #15026 (New): use derr instead of cerr in rbd cli actions
... Ilya Dryomov
03:18 PM Revision 0a930e42 (ceph): Merge pull request #7995 from majianpeng/bluestore-dump-onode
osd: bluestore: allow _dump_onode dynamic accept log level
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
03:13 PM Revision 5c7f74ef (ceph): Merge pull request #7996 from majianpeng/bluestore-fullextent-overwrite
osd: bluestore: for overwrite a extent, allocate new extent on min_alloc_size write
Reviewed-by: Sage Weil <sage@red...
Sage Weil
02:48 PM Revision b413a8f4 (ceph): cls_rgw: use sized uint64_t for encoded time_t
The size of time_t varies between architectures--do not encode it
directly.
Reported-by: Eric Lee <eric.lee@hgst.com...
Sage Weil
02:47 PM Revision f42b86b2 (ceph): test/librgw_file_*: use size_t* for rgw_read arg
Fixes 32-bit build.
Signed-off-by: Eric Lee <eric.lee@hgst.com>
Signed-off-by: Eric Lee
02:06 PM Revision e515f142 (ceph): client: pass proper old snap context to queue_cap_snap()
the snap realm for split point can be newly created, its snap context
is empty in this case.
Signed-off-by: Yan, Zhe...
Yan, Zheng
02:06 PM Revision bd611ab1 (ceph): client: flush kernel pagecache before creating snapshot
Fixes: #10436
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
02:05 PM CephFS Bug #14758 (Resolved): failed TestJournalRepair test on smithi
In this case, mds.b was going into resolve (rank 0), while mds.a was remaining in standby. That's correct (rank 1 is... John Spray
11:53 AM CephFS Bug #14758 (New): failed TestJournalRepair test on smithi
John Spray
11:52 AM CephFS Bug #14758 (Rejected): failed TestJournalRepair test on smithi
The link in the report was wrong, it was actually:
http://pulpito.ceph.com/teuthology-2016-02-12_14:03:01-fs-jewel--...
John Spray
06:34 AM CephFS Bug #14758: failed TestJournalRepair test on smithi
Hmm, we haven't seen this since then, and there have been some smithi runs so it's apparently not just infrastructure... Greg Farnum
01:21 PM Bug #14399 (Duplicate): "ReplicatedPG.cc: 10483: FAILED assert(obc)" in rados-hammer-distro-basic...
Kefu Chai
01:20 PM Backport #12848 (Fix Under Review): ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED...
https://github.com/ceph/ceph/pull/7883 Kefu Chai
11:50 AM CephFS Feature #14642: Validate layouts everywhere we load them
Yes, and in testing I also found other places in the MDS that get upset with zeros, so the ticket probably either nee... John Spray
06:46 AM CephFS Feature #14642: Validate layouts everywhere we load them
John, I think maybe you said in the user thread that we seem to guard against this on inputs, right? So we've no idea... Greg Farnum
11:17 AM Revision 1ea8769b (ceph): osd: remove up_thru_pending field, which is never used
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
09:41 AM Revision d29f610b (ceph): Merge pull request #7960 from SUSE/wip-docdev-mon
doc/dev: continue writing Testing in the cloud chapter
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
09:14 AM rbd Bug #15007: Cannot rebuild object map in in-flight IO
Due to the upgrade to infernalis it would be fine to get the ability for live enabling the object map. Jonas +1 Tim Förster
08:01 AM rbd Bug #15007: Cannot rebuild object map in in-flight IO
Jason Dillaman wrote:
> > Object Map Rebuild: 99% complete...failed.
> > rbd: rebuilding object map failed: (16) De...
Jonas Keidel
08:47 AM Revision 585ffedb (ceph): Mon: When create pool use the crush rule consider the pool size
Fixes: #14509
Signed-off-by: song baisen song.baisen@zte.com.cn
ceph zte
08:38 AM Backport #13335: hammer: OSD crashed when reached pool's max_bytes quota
> The commit introduces a regression
The commit exposes a bug in the test which assumes it's possible to write mor...
Alexey Sheplyakov
03:37 AM Backport #13335: hammer: OSD crashed when reached pool's max_bytes quota
The commit introduces a regression and is reverted by http://tracker.ceph.com/issues/15019 Loïc Dachary
03:36 AM Backport #13335 (New): hammer: OSD crashed when reached pool's max_bytes quota
Loïc Dachary
08:25 AM Bug #15025: New added OSD always down when full flag is set
Follow is the analyze from log and code:
1. New osd.4 start up, osdmap is 0, send a MMonSubscribe message to monitor...
Libin Wu
07:23 AM Bug #15025 (Resolved): New added OSD always down when full flag is set
When some osd in cluster is full, for example:
/dev/vdb1 15717356 15278696 438660 98% /var/lib/ceph/osd/ce...
Libin Wu
08:23 AM Revision 323c2679 (ceph): doc/dev: Continue writing Testing in the cloud chapter
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
07:51 AM Revision aa338379 (ceph): common: build with blkdev on all platforms
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:51 AM Revision 2be40292 (ceph): rbd: build rbd binary on all platforms
(excluding linux specific features)
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
07:51 AM Revision 88c666d1 (ceph): compat: don't call gcc explicitly
`$(CC) -dumpversion` works for clang too, as it supports gcc
compatibility for -dumpversion option.
Signed-off-by: M...
Mykola Golub
07:51 AM Revision 27f2d806 (ceph): stop.sh: make more portable
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:50 AM Revision 1ae56003 (ceph): freebsd: use sysctl instead of nproc
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:50 AM Revision 48a1ba58 (ceph): rocksdb: more portable make invocation
- export CC and CXX, so the same compiler is used
- use NPROC
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
07:50 AM Revision a5722264 (ceph): common: include malloc.h only on linux
On freebsd <malloc.h> has been replaced by <stdlib.h>
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
07:50 AM Revision 6ce4744a (ceph): compat: fix build on non-linux
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:35 AM Revision 18e33f24 (ceph): buffer: add symmetry operator==() and operator!=()
* add const_iterator(const iterator&) so an iterator can be converted to
const_iterator
* add tests for operator==(...
Kefu Chai
06:50 AM CephFS Bug #14255: qa: we are filling smithi disks with ffsb workloads
This is still happening (http://pulpito.ceph.com/teuthology-2016-03-07_18:04:01-fs-master---basic-smithi/45723/, http... Greg Farnum
06:45 AM CephFS Bug #14807 (Need More Info): MDS crashes repeatedly after upgrade to Infernalis from Hammer
Greg Farnum
06:44 AM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
Bumping down priority as it's just the backport. Greg Farnum
06:43 AM CephFS Bug #14608 (Need More Info): snaptests.yaml failure: [WRN] open_snap_parents has:" in cluster log
For whatever reason we don't actually have the logs here (any more?), and it doesn't seem to have reproduced elsewher... Greg Farnum
06:43 AM CephFS Bug #14996 (Fix Under Review): libcephfs hangs on shutdown if an unclosed opendir handle exists
https://github.com/ceph/ceph/pull/7994 Zheng Yan
06:40 AM Revision 8fc1b1b0 (ceph): client: close opened dirs when umounting
Fixes: #14996
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
06:40 AM Revision 9e344173 (ceph): ceph_test_libcephfs: shutdown without closing file/dir
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 AM CephFS Bug #14196: test_object_deletion fails (tasks.cephfs.test_damage.TestDamage)
Bumping down priority as it's just the backport now. Greg Farnum
05:57 AM Bug #14766: OSD reporting ENOTEMPTY and crashing
trying to figure out what causes the duplicate pairs to appear using the logs provided at http://www.spinics.net/list... Loïc Dachary
04:20 AM Bug #14766: OSD reporting ENOTEMPTY and crashing
@xingyi wu giant is no longer backported or released. It is better to upgrade to hammer. Loïc Dachary
05:00 AM Bug #15010: simple->async peer got "failed lossy con, dropping message"
I can't reproduce this:
http://pulpito.ceph.com/haomai-2016-03-08_23:38:41-rados-master---basic-multi
http://pulpit...
Haomai Wang
03:02 AM Bug #15010: simple->async peer got "failed lossy con, dropping message"
@greg
the clue is these lines:
2016-03-08 05:42:17.669564 7f26b1d12700 0 -- 172.21.15.47:6805/2508 >> 172.21.15....
Haomai Wang
04:37 AM Bug #15019: hammer: fs test fails with log [ERR] : OSD full dropping all updates 100% full
* *fail* http://pulpito.ceph.com/loic-2016-03-01_20:26:33-fs-hammer-backports---basic-multi/
** *new bug* (happened ...
Loïc Dachary
03:26 AM Bug #15019 (In Progress): hammer: fs test fails with log [ERR] : OSD full dropping all updates 10...
https://github.com/ceph/ceph/pull/7977 Wei-Chung Cheng
03:23 AM Bug #15019: hammer: fs test fails with log [ERR] : OSD full dropping all updates 100% full

Wei-Chung Cheng
03:00 AM Bug #15019 (Duplicate): hammer: fs test fails with log [ERR] : OSD full dropping all updates 100%...
https://github.com/ceph/ceph/pull/7977 Wei-Chung Cheng
03:44 AM Backport #13808 (In Progress): infernalis: segfault in Objecter::handle_watch_notify
Nathan Cutler
03:43 AM Backport #13807 (In Progress): hammer: segfault in Objecter::handle_watch_notify
Nathan Cutler
03:42 AM Revision 38b9c0b2 (ceph): osdc/Objecter: call notify completion only once
If we race with a reconnect we could get a second notify message
before the notify linger op is torn down. Ensure we...
Sage Weil
03:37 AM Bug #13098 (Pending Backport): OSD crashed when reached pool's max_bytes quota
Loïc Dachary
03:27 AM Backport #15024 (Resolved): hammer: clock skew report is incorrect by "ceph health detail" command
https://github.com/ceph/ceph/pull/8051 Nathan Cutler
03:27 AM rgw Backport #15023 (Resolved): hammer: rgw: user quota may not adjust on bucket removal
https://github.com/ceph/ceph/pull/8113 Nathan Cutler
03:26 AM Backport #15022 (Resolved): hammer: keyring permisions for mon deamon
https://github.com/ceph/ceph/pull/8049 Nathan Cutler
03:26 AM Backport #15021 (Rejected): infernalis: keyring permisions for mon deamon
Nathan Cutler
02:50 AM Revision f4b210e7 (ceph): rgw: remove unused vector
Signed-off-by: Na Xie <xie.na@h3c.com> x11562
02:43 AM Revision 1c24f581 (ceph): Fix recent failures due to HEALTH_WARN check issues
There were recent failures due to HEALTH_WARN check unrelated
to script, this fix basically bypasses this issue by us...
Vasu Kulkarni
02:09 AM rbd Fix #3588 (Resolved): rbd.py's clone should take stripe parms, call rbd_clone2
Fixed as part of the new image create api use in commit:c3be44ed8f9d99d7257156f2e0bf7ef6ea1b5761 Josh Durgin
01:53 AM CephFS Bug #15008 (Fix Under Review): fuse expects root inode number to be FUSE_ROOT_ID
https://jenkins.ceph.com/job/ceph-pull-requests/2751/ Zheng Yan

03/08/2016

11:59 PM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
@sage I think the problem is that libboost itself is linked against tcmalloc. http://pulpito.ceph.com/loic-2016-03-07... Loïc Dachary
06:57 PM Backport #14799 (Can't reproduce): hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost...
teuthology pulled packages from teh right url, but apparently it build incorrectly because it still linked against tc... Sage Weil
06:54 PM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
the problem here is that it didn't use the notcmalloc package .. tcmalloc and valgrind to not mix. Sage Weil
06:36 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
* http://pulpito.ceph.com/loic-2016-03-07_21:24:13-fs-hammer-backports---basic-multi/45877
* http://pulpito.ceph.com...
Loïc Dachary
11:57 PM Revision 79e2f189 (ceph): client: fix root inode number for fuse
fuse assigns a fix inode number (FUSE_ROOT_ID) for root inode
(FUSE_ROOT_ID is usually equal to MDS_INO_ROOT). But in...
Yan, Zheng
11:33 PM Bug #15017: ceph-osd segfault during start process
OSD starts ok after renaming one certain pg directory... Sergey Baukin
10:30 PM Bug #15017 (Can't reproduce): ceph-osd segfault during start process
ceph-osd gets segmentation fault signal in 10 seconds after start.
(Ubuntu 14.04, ceph 0.94.6-1trusty)
2016-03-...
Sergey Baukin
11:22 PM Revision 2c01f911 (ceph): Merge pull request #7986 from liewegas/wip-xxhash
xxhash: use clone of xxhash.git; add .gitignore
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
10:14 PM Revision d7e42213 (ceph): rgw: handle error when fetching data log changes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
10:14 PM Bug #14314: "/log/SubsystemMap.h: 62: FAILED assert(sub < m_subsys.size())" in rados-infernalis-d...
the packages on the host that crashes were not getting upgraded, though. Sage Weil
10:13 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
Seen in run:
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-08_02:00:01-rados-infernalis-distro-basic-ope...
Yuri Weinstein
09:54 PM Bug #14927 (Duplicate): "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-d...
Sage Weil
12:58 AM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
Here is a simplified upgrade test that can be used to reproduce the issue (can run on teuthology box):... Yuri Weinstein
12:53 AM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
Latest test with errors @failed with error -22@
http://qa-proxy.ceph.com/teuthology/teuthology-2016-03-07_02:10:10-...
Yuri Weinstein
09:53 PM Bug #14935 (Duplicate): "[ FAILED ] ClsHello.Filter" in upgrade:infernalis-x-jewel-distro-basic...
Sage Weil
09:53 PM Bug #14849 (Fix Under Review): (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-inf...
the timeout comes from mon_lease.
https://github.com/ceph/ceph/pull/7987
Sage Weil
09:49 PM Bug #14849: (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis-distro-basi...
crushtool test timeout. took 7s, timeout is 5s. Sage Weil
09:46 PM Revision 15a419be (ceph): test/librados/test.cc: clean up EC pools' crush rules too
SetUp was adding an erasure-coded pool, which automatically adds
a new crush rule named after the pool, but only remo...
Dan Mick
09:21 PM Bug #14468: osd: dup op detection doesn't handle guarded writes
I think storing failed ops would be problematic too. At least, it would break the current ability we have to return ... Sage Weil
09:04 PM Bug #14468: osd: dup op detection doesn't handle guarded writes
Right, what I mentioned was assuming we stored the result of failed ops as well. Josh Durgin
08:25 PM Bug #14468: osd: dup op detection doesn't handle guarded writes
It's not the length of the log that's the problem, though. Apparently we just don't remember ops which have a possibl... Greg Farnum
08:17 PM Bug #14468: osd: dup op detection doesn't handle guarded writes
With object map it becomes more important since we're dropping the guard sooner, and have more of a chance to hit the... Josh Durgin
07:58 PM Bug #14468: osd: dup op detection doesn't handle guarded writes
It seems like the short answer is "don't pipeline guarded and non-guarded ops".
We can make the crash go away by s...
Sage Weil
09:18 PM Revision aab91667 (ceph): xxHash: add .gitignore for build artifacts
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
09:04 PM Revision 517a9d6d (ceph): .gitmodules: use github.com/ceph/xxHash clone
This lets us add our own commits, if necessary.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
08:42 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
Hmm, we were seeing this a lot, but I haven't seen it recently.. has it gone away? Sage Weil
08:42 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
That last failure included the 13862 partial fix (altho it was an upgrade from 0.94.5). Sage Weil
08:33 PM Bug #14616 (Fix Under Review): When logging to a file fails, ceph logs excessively to stderr
https://github.com/ceph/ceph/pull/7983 Sage Weil
08:28 PM Bug #14745 (Resolved): osd: call doesn't force promotion from ec base tier
Sage Weil
08:27 PM Bug #14797 (Need More Info): osd: add all backfill osd to backfill_targets
Sage Weil
08:08 PM Bug #13971 (Need More Info): "test/multi_stress_watch.cc: 61: FAILED assert(!ret)" in rados-hamme...
Odd we haven't seen this on master. I don't see anything that may have inadvertantly fixed it except haomai's recent... Sage Weil
07:59 PM Bug #14289 (Resolved): "No space left on device" + "FAILED assert(0 == "unexpected error")" in ra...
we've shorteend the rados bench durations Sage Weil
07:59 PM Bug #14245 (Resolved): "cluster [ERR] OSD full" in rados-jewel-distro-basic-smithi
we've already shortened the rados bench duration Sage Weil
07:57 PM RADOS Bug #15015 (New): prepare_new_pool doesn't return failure string ss
prepare_new_pool calls lots of things that can put failure reasons into ss, but (the one-argument form of) it does no... Dan Mick
07:55 PM Bug #13939: PGs stuck in "creating" when created just after deleting another pool
We dropped down the number of PGs to a more polite level; anybody wanting to reproduce it would probably have to subj... Greg Farnum
07:48 PM Bug #13939: PGs stuck in "creating" when created just after deleting another pool
John, have you seen this again? What's weird is I don't think it's happening in the rados suite... Sage Weil
07:45 PM Bug #14008 (Can't reproduce): "FAILED assert(0 == "out of order op")" in rbd-hammer-distro-basic-...
probably slowness + short pg log Sage Weil
07:45 PM Bug #13350 (Resolved): "Error cancelling global ust listener thread" errors
Sage Weil
07:43 PM Bug #13915: "failed: mon_thrash" in upgrade:hammer-hammer-distro-basic-openstack
Yuri, have you seen this since? Sage Weil
07:39 PM Bug #14606 (Fix Under Review): rest.py fails
https://github.com/ceph/ceph/pull/7982 Sage Weil
07:34 PM rgw Bug #13635 (Resolved): radosgw duplicate email address
Yehuda Sadeh
07:34 PM Revision bdcc8404 (ceph): qa/workunits/rest/test.py: add confirmation to 'mds setmap'
Broken when we added the confirmation in
fc3554e36af439ef1cec0be3d98ca0fabe15ba73
Fixes: #14606
Signed-off-by: Sage ...
Sage Weil
07:28 PM Bug #13963 (Can't reproduce): monclient leak on shutdown
Sage Weil
07:27 PM Bug #14135 (Can't reproduce): osd: leak of Session from ms_verify_authorizor
Sage Weil
07:27 PM rgw Bug #14816 (Resolved): rgw: failed to use s3 bucket since commit 2f706ef
Fixed in commit:1e472685577c13a9ca373521dacced91be6d0417
Yehuda Sadeh
07:27 PM Bug #14364 (Fix Under Review): librados, objecter: op_submit() returns after request completion, ...
https://github.com/ceph/ceph/pull/7981 Sage Weil
07:27 PM Bug #14766: OSD reporting ENOTEMPTY and crashing
I'm now pretty confident that this is the same issue as the scrub bug described in the ceph-users thread '[ceph-users... Samuel Just
08:17 AM Bug #14766: OSD reporting ENOTEMPTY and crashing
we also encountered this bug serval months ago. Our cluster runs giant-0.87.2, with EC backended. When recovering or ... xingyi wu
01:37 AM Bug #14766: OSD reporting ENOTEMPTY and crashing
Nevermind, OSD::remove_dir does the right thing. Samuel Just
01:10 AM Bug #14766: OSD reporting ENOTEMPTY and crashing
I'm fairly sure this is a bug in ObjectStore::collection_list_partial. hobject_t start is stuffed without ceremony i... Samuel Just
07:20 PM Bug #14028 (Won't Fix): PG stats are not refresh within osd_pg_stat_report_interval_max
I think I was wrong in that email. As long as the OSD reports in as healthy I don't think its necessary for the OSD ... Sage Weil
07:15 PM Bug #14562 (Won't Fix): hammer: rados/test.sh: erasure-code-profile set name:testprofile failed
this was the monthrasher pausing hte ceph-mon process while it was running crushtool to validate a crush map (which h... Sage Weil
07:14 PM rgw Bug #14826: rgw: bucket listing following object delete is partial
We need to make sure that we don't leak any bucket index pending entries. Yehuda Sadeh
07:13 PM Bug #14671 (Duplicate): ceph-objectstore-tool: Can't find OSDMap for pg epoch 232
Sage Weil
07:13 PM Bug #14666 (Resolved): memstore: fails to set cid on collection
Sage Weil
07:09 PM rgw Bug #14820: s3cmd rb --recursive doesn't decrease total_entries in stats
It seems like duplicate of #14507. Yehuda Sadeh
07:09 PM rgw Bug #14507 (Pending Backport): rgw: user quota may not adjust on bucket removal
PR 7586 Yehuda Sadeh
07:08 PM Bug #14842: ceph-disk: /sys/block/<device>/queue/physical_block_size is not obeyed
Can we just switch to parted? That would solve the partition length issue, too. Sage Weil
07:05 PM Bug #13844 (Rejected): ceph df MAX AVAIL is incorrect for simple replicated pool
Nils, in your case, the result is correct.. your usage is bounded by osd.17, which looks like it will fill up after a... Sage Weil
07:01 PM Bug #13805 (Pending Backport): segfault in Objecter::handle_watch_notify
commit:987f68a8df292668ad241f4769d82792644454dd Sage Weil
06:52 PM Bug #14952 (Fix Under Review): New pools have bogus "stuck inactive/unclean" HEALTH_ERR messages ...
https://github.com/ceph/ceph/pull/7980 Sage Weil
06:50 PM Backport #14592: osd crashes when handling a stale pg-create message (hammer)
oops, wrong bug Sage Weil
12:36 AM Backport #14592 (Fix Under Review): osd crashes when handling a stale pg-create message (hammer)
-https://github.com/ceph/ceph/pull/7963- (closed) Sage Weil
06:46 PM Revision 433afce6 (ceph): mon: initialize last_* timestamps on new pgs to creation time
Currently, when you create a pool, until the PGs peer you generate a health
error like
8 pgs are stuck i...
Sage Weil
06:23 PM Bug #14995 (Resolved): "ceph version 10.0.3 was not installed, found 10.0.4."
Sage Weil
06:23 PM Bug #14995: "ceph version 10.0.3 was not installed, found 10.0.4."
the tag wasn't pushed, but is now. the branch being tested just needs to be rebuilt. Sage Weil
06:14 PM Bug #14995: "ceph version 10.0.3 was not installed, found 10.0.4."
This is either a build or packaging issue.
http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/sha1/6018ccd6c...
Zack Cerza
06:21 PM rbd Bug #14908 (Fix Under Review): Journal replay needs to conditionally refresh the image between ev...
*PR*: https://github.com/ceph/ceph/pull/7978 Jason Dillaman
04:52 PM rbd Bug #14908 (In Progress): Journal replay needs to conditionally refresh the image between events
Jason Dillaman
06:20 PM Revision b705a71b (ceph): librbd: refresh image if required before replaying journal ops
Fixes: #14908
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
06:02 PM Revision 1a800f60 (ceph): rgw: rework completion notifier and manager lifecycle
completion manager is now refcounted, and keeps track of all the
notifiers. This is needed so that when we shut down ...
Yehuda Sadeh
06:02 PM Revision 9106e8ad (ceph): rgw: reorder RGWRados::finalize()
first stop all sync threads, then delete them. Might be referencing
each other.
Signed-off-by: Yehuda Sadeh <yehuda@...
Yehuda Sadeh
06:02 PM Revision 5ecacfe6 (ceph): rgw: stop async_rados thread first
Need to shut this thread first, so that async callbacks don't
occur when we shut down the data/meta sync processors.
...
Yehuda Sadeh
06:02 PM Revision 03d60e39 (ceph): rgw: silence some debug messasges
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:02 PM Revision 5914ae9d (ceph): rgw: abort early in realm reload if already reloading
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:02 PM Revision ea29b711 (ceph): rgw: don't equeue async cr rados operations if going down
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
05:59 PM Bug #15010: simple->async peer got "failed lossy con, dropping message"
I'm not following the first part of that story — if we injected an error that was detected in line 359, we'd jump to ... Greg Farnum
05:26 PM Bug #15010: simple->async peer got "failed lossy con, dropping message"
Initial judge:
simple side:
1. accept async connect
2. inject happen when enter https://github.com/ceph/ceph/blo...
Haomai Wang
04:06 PM Bug #15010: simple->async peer got "failed lossy con, dropping message"
/a/sage-2016-03-07_17:50:09-rados-wip-sage-testing---basic-smithi/45466 Sage Weil
04:06 PM Bug #15010 (Can't reproduce): simple->async peer got "failed lossy con, dropping message"
... Sage Weil
05:47 PM Bug #15011: TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
And more suprisingly in osd pool create testing :
./test/mon/osd-crush.sh:129: TEST_crush_rule_create_erasure: ex...
Anonymous
05:44 PM Bug #15011: TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
I got the same trace in another test :
../qa/workunits/cephtool/test.sh:1702: test_mon_crushmap_validation: prin...
Anonymous
04:17 PM Bug #15011 (Resolved): TEST_crush_reject_empty: ceph osd setcrushmap error on BTRFS
When running a make check on current master on my local btrfs system I have the following trace :
../qa/workunits/...
Anonymous
05:41 PM Bug #15012 (Resolved): "[ FAILED ] LibRadosTwoPoolsPP.Whiteout" in upgrade:hammer-x-jewel-distr...
Run: http://pulpito.ceph.com/teuthology-2016-03-08_02:10:13-upgrade:hammer-x-jewel-distro-basic-vps/
Jobs: 46407
Lo...
Yuri Weinstein
04:58 PM rbd Bug #14986 (Closed): rbd export/export-diff with needs to protect against unintended journal replay
The journal actually won't be replayed since export/export-diff open the image read-only. This prevents the journal ... Jason Dillaman
04:56 PM Bug #14998: Build failures with Boost 1.60
Adding comment from the mailing-list here:
Reverting https://github.com/ceph/ceph/pull/7654 makes the build
succee...
Abhishek Lekshmanan
04:46 PM Bug #14976 (Resolved): rpm: broken dep with libboost_program_options-mt.so.1.53.0
Sage Weil
04:45 PM rbd Bug #14953 (Rejected): can add 'rbd lock' to format 1 images
Jason Dillaman
04:43 PM rbd Bug #14953: can add 'rbd lock' to format 1 images
@Vasu, the "rbd lock"-related commands are to be considered as advisory locks. There is no enforcement within librbd... Jason Dillaman
04:41 PM rbd Bug #14988 (Need More Info): QEMU VM hangs talking to RBD via librbd
Josh Durgin
04:37 PM Revision 1c99dc2f (ceph): doc/release-notes: v10.0.4
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:33 PM Revision bc565e05 (ceph): Merge pull request #7966 from dachary/wip-release-notes
release-notes: draft v10.0.4 release notes Sage Weil
04:32 PM Bug #14175 (Pending Backport): clock skew report is incorrect by "ceph health detail" command
Joao, shall we backport this change to hammer? Kefu Chai
04:28 PM Bug #14950 (Pending Backport): keyring permisions for mon deamon
Kefu Chai
04:26 PM Bug #14950 (Resolved): keyring permisions for mon deamon
Kefu Chai
03:19 PM Bug #14950 (Fix Under Review): keyring permisions for mon deamon
Kefu Chai
04:24 PM Bug #14992 (Rejected): "rados ls -p xxx" hangs forever when all "rbd_directory" obj replica osds ...
in this case, rbd_directory is mapped to osd.{6,4,16}. and all osds serving that pg are down and in at that moment. t... Kefu Chai
04:22 PM Revision 8384f16d (ceph): Merge pull request #7880 from SUSE/wip_keyring_permisions_for_mon_deamo...
mon: fix keyring permissions
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
04:21 PM Revision 46007d27 (ceph): Merge pull request #7121 from efirs/ef_eversion_t_no_sprintf
osd: Replace snprintf with faster implementation in eversion_t::get_key_name
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
04:21 PM Revision 34b7c824 (ceph): Merge pull request #7141 from jecluis/wip-mon-clockskew
mon: make clock skew checks sane
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
04:20 PM Revision b533cf10 (ceph): Merge pull request #7899 from liewegas/wip-osd-markdown
test/osd: Relax the timing intervals in osd-markdown.sh Sage Weil
04:20 PM Revision 84caba52 (ceph): Merge pull request #7900 from liewegas/wip-bluefs-alignment
osd: bluefs: fix alignment for odd page sizes
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
04:20 PM Revision bdd2ddb3 (ceph): Merge pull request #7904 from liewegas/wip-log-delete
log: use delete[]
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Sage Weil
04:19 PM rbd Bug #14780 (Resolved): librbd: TaskFinisher lifetime no longer matches ImageWatcher
Josh Durgin
04:19 PM Revision 7eba5bae (ceph): osd: inline advance_map()
This has shrunk over time and is short enough it's easier to
follow the code with it inline.
Signed-off-by: Sage Wei...
Sage Weil
04:19 PM Revision 7139a232 (ceph): osd: handle boot racing with NOUP set + clear
Resolve this race:
- osd sends boot message
- mon sets NOUP
- mon receives and drops boot message
- mon later clear ...
Sage Weil
04:14 PM Revision 7784ffe6 (ceph): rados/thrash/workloads/radosbench: shorten 300s->200s
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:06 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
New logs with debug-ms=1:
https://api.access.redhat.com/rs/cases/01549888/attachments/04e45b4a-6ae7-4b6f-9347-741f...
Steve Taylor
02:39 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Steve, the logs are helpful.
> but I'm confident that this test reproduced the behavior we're seeing in production...
Kefu Chai
04:01 PM Revision 4ded44aa (ceph): journal: possible race condition during fetch playback
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
03:35 PM Revision 39828952 (ceph): test: fix errors introduced by rebase to master
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
03:35 PM Bug #13563 (Resolved): "[ FAILED ] LibRadosAioEC.RoundTripSparseReadPP" in upgrade:hammer-x-inf...
Loïc Dachary
03:34 PM Bug #13421 (Won't Fix): ceph-osd Segmentation fault in pthread_join
Marking back to Won't Fix Samuel Just
03:33 PM Bug #15009 (Can't reproduce): [ FAILED ] LibRadosAioEC.RoundTripSparseReadPP
http://pulpito.ceph.com/loic-2016-02-28_21:51:29-rados-hammer-backports---basic-multi/32583/... Loïc Dachary
03:30 PM Bug #14942 (Won't Fix): centos packages issue for dumpling in upgrade:dumpling-firefly-x-hammer-d...
Loïc Dachary
03:29 PM Bug #14942: centos packages issue for dumpling in upgrade:dumpling-firefly-x-hammer-distro-basic-...
Yes, we can stop running this suite and Sam says we can stop running anything that starts with dumpling. Loïc Dachary
03:28 PM Bug #14983: osd: handle EIO in handle_sub_read
osd 5 is getting an EIO on object 2/ab64d095/100000578e9.00001458/head. We don't handle this well, updating the subj... Samuel Just
03:27 PM CephFS Bug #15008 (Resolved): fuse expects root inode number to be FUSE_ROOT_ID
it's not true when mounting into subdir Zheng Yan
03:22 PM Bug #8007 (Can't reproduce): osd: hang on shutdown with valgrind on trusty
I've not seen any instance of this bug in the past year on trust involving either hammer or infernalis. Loïc Dachary
03:20 PM Bug #14708: Semi-crashed OSDs cause cluster to hang
We do have a watchdog thread which should have killed any osd with hung threads (see the .*timeout.* and .*suicide_ti... Samuel Just
03:20 PM Bug #9308 (Can't reproduce): EBUSY on umount of osd volume after ceph-osd shutdown
I've not seen this in any infernalis / hammer suites in the past year. Loïc Dachary
03:16 PM Bug #11856 (Can't reproduce): osd - scrubbing slot leaked
Samuel Just
03:15 PM Bug #13940 (Won't Fix): OSDs fail to start on reboot with dmcrypt/luks
Samuel Just
03:08 PM Revision b37f135c (ceph): journal: clean up playback notification handling
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:50 PM rbd Bug #15007 (Resolved): Cannot rebuild object map in in-flight IO
> Object Map Rebuild: 99% complete...failed.
> rbd: rebuilding object map failed: (16) Device or resource busy
Jason Dillaman
02:03 PM Revision 21d95952 (ceph): journal: properly handle tag transition
Now that the tag concept has been re-used for delineating epochs for
librbd, we need playback to properly handle the ...
Jason Dillaman
02:03 PM Revision b7103740 (ceph): tests: updated test cases for librbd journal tag allocation
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:03 PM Revision 174359ba (ceph): cls_rbd: support for uuid to represent a mirrored pool
This uuid will be used as the client id for remote peer image
journals. This will allow the uuid to be also utilized...
Jason Dillaman
02:03 PM Revision 9892fd78 (ceph): librbd: allocate new uuid when enabling mirroring
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:03 PM Revision dbcbaa6e (ceph): librbd: update journal client and tag data structures
The mirror peer now holds remote's image id as well as a collection
of bootstrap sync points. The tag now contains u...
Jason Dillaman
02:03 PM Revision 708c72cb (ceph): rbd-mirror: local pool id no longer stored in client registration
The remote pool name should match the remote pool name.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
02:03 PM Revision a4dd7885 (ceph): journal: helper method to retrieve in-memory client data
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:03 PM Revision cbcfedf7 (ceph): librbd: add tag handling to journal state machine
The journal will not retrieve the tag class for the image within
the journal in addition to the most recently allocat...
Jason Dillaman
02:03 PM Revision 16d5e695 (ceph): librbd: allocate new journal tag when acquiring exclusive lock
The journal tag tracks a write epoch within the image, so before
allowing writes to proceed, ensure the journal entri...
Jason Dillaman
02:03 PM Revision 8444da84 (ceph): librbd: improved debugging for journal client / tag processing
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:03 PM Revision 3325b871 (ceph): journal: additional debug messages surrounding commit updates
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
01:51 PM Revision 19798efd (ceph): Merge pull request #7742 from ErwanAliasr1/evelu-spec
Adding build requires
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Boris Ranto <branto@redhat.com>
Rev...
Ken Dreyer
12:57 PM Revision 92628f56 (ceph): common/strtol.cc: fix the coverity warnings
* promote the compared types properly to address the signed/unsigned
comparison warnings. this also fixes the poten...
Kefu Chai
12:11 PM Revision a00eae00 (ceph): journal: pass metadata instead of finisher to FutureImpl
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:11 PM Revision f983b80a (ceph): journal: use provided work queue and timer
This avoids the need to open two threads per journaler.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
12:11 PM Revision 3496e777 (ceph): librbd: own the lifecycle of the journaler's threads
This is the first step in merging the journal threads into the
librbd singleton thread pool.
Signed-off-by: Jason Di...
Jason Dillaman
12:11 PM Revision 7fd230f6 (ceph): rbd-mirror: integrate single thread pool for all processing
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
11:31 AM Revision 37f3fc9e (ceph): Merge pull request #7972 from badone/wip-CMakeLists-dup-line
cmake: Remove duplicate find_package libcurl line.
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
09:59 AM Revision 5cd4ce51 (ceph): selinux: Allow to manage locks
We currently create the ceph lock by an unconfined process (ceph-disk).
Unconfined processes inherit the context from...
Boris Ranto
09:57 AM Revision 519b03f4 (ceph): selinux: allow dac_override capability
Fixes: #14870
Signed-off-by: Boris Ranto <branto@redhat.com>
Boris Ranto
07:54 AM Bug #15003 (In Progress): [hammer, master?] ec pool deep scrub turns up inconsistent objects inco...
Nathan Cutler
12:07 AM Bug #15003: [hammer, master?] ec pool deep scrub turns up inconsistent objects inconsistently
Scratch that, still looking. Samuel Just
05:56 AM Revision 052075e6 (ceph): librbd: skip truncate request if object does not exist
Signed-off-by: xinxin shu <xinxin.shu@intel.com> xinxin shu
05:09 AM CephFS Bug #9679: Ceph hadoop terasort job failure
I forgot to mention, I tested both: Hadoop 2.7.1 and 2.7.2 with the same outcome.
64 bit Arch linux circa Jan 2015. ...
Dmitry Buzz
05:01 AM CephFS Bug #9679: Ceph hadoop terasort job failure
Greg,
My setup was simple: ceph jni bindings were build from ceph repo.
Cehp hadoop2 integration was build from h...
Dmitry Buzz
12:00 AM CephFS Bug #9679: Ceph hadoop terasort job failure
Dmitry, can you elucidate more on your environment? Which Hadoop, and what bindings did you use to connect Ceph and H... Greg Farnum
05:03 AM Revision bf611566 (ceph): release-notes: draft v10.0.4 release notes
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
05:03 AM Revision d8cdb5fe (ceph): scripts: ceph-release-note rewrite PR title case
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
04:02 AM Backport #15002: hammer: objects unfound after repair (fixed by repeering the pg)
h3. original description
d51806f5b330d5f112281fbb95ea6addf994324e I think fixed it upstream
Two things for this...
Loïc Dachary
03:59 AM Bug #15006 (Resolved): objects unfound after repair (fixed by repeering the pg)
https://github.com/ceph/ceph/pull/4269 Loïc Dachary
03:00 AM Revision 7083829c (ceph): Merge pull request #6604 from ukernel/hammer-13268
hammer: client: added permission check based on getgrouplist
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Loïc Dachary
02:58 AM Revision 651e49ea (ceph): Merge pull request #6551 from ceph/hammer-client-inoderef
hammer: client inoderef
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Loïc Dachary
02:15 AM CephFS Bug #14805: Hadoop tests failing with EPERM
old libcephfs only has permission check for open. Now, It has full permission checks (open, lookup, setattr ...) Zheng Yan
02:12 AM Bug #8885 (In Progress): SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
I have been able to reproduce and found an additional locking issue. Still trying to find and fix the issue describe... David Zafman
02:04 AM Revision c88b863c (ceph): Merge pull request #7959 from kmroz/wip-add-rgw-to-stopsh
script: add missing stop_rgw variable to stop.sh script
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:50 AM Revision e48c708b (ceph): doc/rados/operations/crush: rewrite crush tunables section
- break it down by tunable profile
- explicitly call out the migration impact for each profile jump.
Signed-off-by: ...
Sage Weil
01:50 AM Revision fa7beb0c (ceph): mon: warn on straw_calc_version=0
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
01:50 AM Revision 0cdb3af1 (ceph): crush: remove straw_calc_version check from has_*_tunables()
Since we do not set this when we set tunables, we should not check it
when we report which tunables they have set. F...
Sage Weil
01:10 AM Revision 000344ef (ceph): crush: make default tunables 'firefly'
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
12:31 AM Revision d2edf751 (ceph): Merge remote-tracking branch 'origin/wip-damage-table' into greg-fs-tes...
https://github.com/ceph/ceph-qa-suite/pull/782
Conflicts:
tasks/cephfs/test_scrub_checks.py
Reviewed-by: Greg Farn...
Greg Farnum
12:29 AM Revision ca0eed07 (ceph): Merge branch 'wip-damage-table' of git://github.com/jcsp/ceph into greg...
Conflicts:
src/mds/MDCache.cc
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
12:20 AM Revision c0a2c102 (ceph): Merge remote-tracking branch 'origin/wip-scrub-repair' into greg-fs-tes...
https://github.com/ceph/ceph-qa-suite/pull/731 Greg Farnum
12:19 AM Revision 97635811 (ceph): Merge branch 'wip-scrub-repair' of git://github.com/ukernel/ceph into g...
https://github.com/ceph/ceph/pull/6682
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Greg Farnum <gfa...
Greg Farnum

03/07/2016

11:55 PM Backport #15002 (In Progress): hammer: objects unfound after repair (fixed by repeering the pg)
https://github.com/ceph/ceph/pull/7961 David Zafman
10:09 PM Backport #15002 (Resolved): hammer: objects unfound after repair (fixed by repeering the pg)
https://github.com/ceph/ceph/pull/7961 Samuel Just
11:55 PM CephFS Bug #14805: Hadoop tests failing with EPERM
Do you have any idea what about the client permission checking is busting Hadoop? We want to fix it properly (or at l... Greg Farnum
11:55 PM Bug #15003 (Pending Backport): [hammer, master?] ec pool deep scrub turns up inconsistent objects...
-Fixed in 75e28bee082c20b8d90928ef29deedb94704a2de in master.- Samuel Just
11:47 PM Bug #15003 (Duplicate): [hammer, master?] ec pool deep scrub turns up inconsistent objects incons...
Deep scrub intermittently turns up inconsistent pgs. Rescrubbing nondeterministically either results in the pg going... Samuel Just
11:51 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
Is there something tricky about invoking that call when trimming? It'll probably go in faster if you do it and we tes... Greg Farnum
08:58 PM Revision 796331d6 (ceph): Merge branch 'master' of github.com:ceph/ceph
Sage Weil
08:50 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
@Nathan I created a little noise in this ticket, my apologies.
Now on plan of attack.
Dan and I ran several sim...
Yuri Weinstein
08:36 PM Revision 37f14a5d (ceph): Merge branch 'wip-conf-root' of https://github.com/liewegas/ceph
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
src/common/config.cc
Sage Weil
08:18 PM Revision 2f3a9c68 (ceph): rgw: don't clobber first_chunk on retry
A racing object sync can end up with multiple calls to cb.complete() which
in turn will end up with this method getti...
Yehuda Sadeh
08:07 PM Revision 9ef7bb15 (ceph): Merge pull request #7914 from dillaman/wip-tests-template-specialization
test: correct librbd errors discovered with unoptimized cmake build
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:27 PM Revision 019d9e17 (ceph): packaging: Adding redhat-rpm-config
Some part of the rados compilation process is expecting redhat-hardened-cc1.
That's surely because of the FORTIFY com...
Erwan Velu
07:27 PM Revision 754d2103 (ceph): packaging: Moving Cython into distro specific area
To get the spec file into a consistent state, let's move Cython into the distro
specific are of the spec file.
Signe...
Erwan Velu
07:27 PM Revision 7d48d21a (ceph): packaging: Adding btrfs build require
When doing a 'make check', 'qa/workunits/ceph-helpers.sh' does expect the 'btrfs'
command to be available. If not, th...
Erwan Velu
06:59 PM Revision 48599465 (ceph): krbd: do not test unsupported striping feature
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
06:57 PM Revision eb29adfb (ceph): tasks/rbd_fio: create sane image name based on feature set
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
06:35 PM Backport #14592: osd crashes when handling a stale pg-create message (hammer)
Creating teuthology reproducer. Samuel Just
06:18 PM Revision 737bd0d0 (ceph): Merge pull request #858 from ceph/wip-pg-dump
tasks/ceph_manager: dump pgs if other peering timeouts expire Zack Cerza
05:32 PM Bug #14708: Semi-crashed OSDs cause cluster to hang
I just had this again on a different server, same traceback. This time Ceph behaved more gracefully, setting the mons... Christian Theune
05:28 PM Revision 216967d6 (ceph): Merge pull request #7628 from liewegas/wip-journal-block-size
os/filestore/FileJournal: set block size via config option
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Sage Weil
05:27 PM Revision f78d7e8b (ceph): Merge pull request #7705 from renhwsky/renhw-wip-pgmonitor-get_rule_avail
mon/pgmonitor: use appropriate forced conversions in get_rule_avail Sage Weil
05:27 PM Revision 3634ed52 (ceph): Merge pull request #7775 from branch-predictor/bp-bl-eradication
os/ObjectStore: implement more efficient get_encoded_bytes()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:25 PM Revision b62add00 (ceph): Merge pull request #7845 from aiicore/pthread_setname_fix
common: set thread name from correct thread
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:24 PM Revision 6fc5c460 (ceph): Merge pull request #7850 from jupiturliu/kstore-latency
osd: kstore: latency breakdown
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:24 PM Bug #14910 (Resolved): cephtool/test.sh: test_mon_tell test unreliable
Sage Weil
05:23 PM Revision 3a72d21e (ceph): Merge pull request #7861 from tchaikov/wip-14910
qa/workunits/cephtool/test.sh: wait longer in ceph_watch_start()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:23 PM Revision 020c7894 (ceph): Merge pull request #7863 from branch-predictor/bp-faster-name-gen
common/obj_bencher.cc: faster object name generation
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
05:21 PM Revision 6deba7c6 (ceph): tasks/ceph_manager: dump pgs if other peering timeouts expire
We were doing this for one of the recovery timeouts but not all of them.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:52 PM rbd Documentation #15000 (Resolved): Need better documentation to describe RBD image features
Jason Dillaman
04:46 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I just performed a simple test where I manually created and deleted a single rbd snapshot and waited 15 minutes or so... Steve Taylor
03:56 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
As I watched this test it was apparent that osd maps were getting trimmed occasionally, but certainly not every time ... Steve Taylor
02:39 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
downloaded the log, will check them out tomorrow.
fwiw, OSD does not trim osdmap periodically, instead, osdmap tri...
Kefu Chai
04:41 PM Revision 60b71ec0 (ceph): stop: Add missing stop_rgw variable
Signed-off-by: Karol Mroz <kmroz@suse.com> Karol Mroz
04:22 PM Revision 80ef3477 (ceph): Merge pull request #7954 from SUSE/wip-docdev
doc/dev: various refinements
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:34 PM RADOS Bug #14999 (New): Lttng: rados library linkage causes indefinite pthread hang
The following program wil hang indefinitely.
When the main thread exits, two pthreads will keep running, I believ...
Robert Augusteijn
03:00 PM Revision 4a5875a1 (ceph): doc/dev: start Testing in the cloud chapter
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
02:43 PM Bug #14998 (Resolved): Build failures with Boost 1.60
Using boost 1.60 causes build failures in current master with the following errors:... Abhishek Lekshmanan
02:25 PM CephFS Bug #14996: libcephfs hangs on shutdown if an unclosed opendir handle exists
I think we should unify open file/directory handle Zheng Yan
10:41 AM CephFS Bug #14996 (Resolved): libcephfs hangs on shutdown if an unclosed opendir handle exists

This will hang on shutdown:...
John Spray
01:18 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
@Roy,
From the backtrace, Ceph is waiting for a cache flush to complete. The thread responsible for handling cac...
Jason Dillaman
01:05 PM Revision f7eb860d (ceph): rbd-mirror: avoid recursive lock in timer
m_lock is used both by m_timer and refresh_images(), which is
scheduled by the timer, so run it with `safe_callbacks ...
Mykola Golub
01:05 PM Revision 303e2c98 (ceph): rbd-mirror: properly update replayers
Previously update_replayers always deleted replayers due to using
empty peers set.
Signed-off-by: Mykola Golub <mgol...
Mykola Golub
01:05 PM Revision 803eb511 (ceph): rbd-mirror: spawn replayer thread
Also, wait for it to finish only if it has been started.
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
01:04 PM Revision ed035a3b (ceph): rbd-mirror: don't log error on empty pool
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
01:04 PM Revision 098be66c (ceph): rbd-mirror: improve logging
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
01:03 PM Bug #14924 (Resolved): scrub_test failure
Kefu Chai
10:30 AM Revision 75b2f430 (ceph): ceph.in: Minor python3 specific changes
Signed-off-by: Sarthak Munshi <sarthakmunshi@gmail.com> Sarthak Munshi
09:36 AM Revision a565d333 (ceph): test/bufferlist: Avoid false-positive tests
The current code is using the length of ptr to determine if the string is
correct.
As 'ptr' is a copy of the origina...
Erwan Velu
09:27 AM Revision 37afe5c5 (ceph): doc/dev: various refinements
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
09:19 AM Revision 6d31e5df (ceph): Merge pull request #7951 from badone/wip-cls_hello-grammar
cls_hello: Fix grammatical error in description comment
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
08:00 AM Bug #14995 (Resolved): "ceph version 10.0.3 was not installed, found 10.0.4."
We're seeing this in a lot of runs. It might just be a consequence of scheduling across release tags, but I'm not sur... Greg Farnum
07:59 AM Revision e3fdaae9 (ceph): mds: set bad dirfrag's version to 1
there are lots of places assume 'version == 0' means dirfrag is
uninitialized
Signed-off-by: Yan, Zheng <zyan@redhat...
Yan, Zheng
07:59 AM Revision f2de29e3 (ceph): mds: scrub fragstat.mtime and rstat.rctime
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision dad48ecb (ceph): mds: store ScrubHeader refernce in CInode's scrub_info_t
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision db12397f (ceph): mds: handle non-recursive scrubbing
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision a51fd656 (ceph): mds: use scrubstack code to scrub single dentry
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 6cda4de9 (ceph): mds: remove old scrub_dentry code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 2a671521 (ceph): mds: and 'recursive/repair' options to scrub_path asok command
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision f13fb479 (ceph): mds: don't ignore scrubbing non-regular non-directory inodes
The overhead of scrubbing them is low, so don't treat them specially.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
07:59 AM Revision 84ed3cd7 (ceph): mds: make scrubstack queue CInode instead of CDentry
There are two problems that enqueue CDentry in scrub stack. First,
the scrub stack code can't handle base inodes; sec...
Yan, Zheng
07:59 AM Revision f2d01c18 (ceph): mds: remove obsoleted FIXME from scrubstack code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 72b9339e (ceph): mds: and 'force' options to scrub_path asok command
'force' means check whole subtree (don't skip scrubbing entries
not modified since last scrub)
Signed-off-by: Yan, Z...
Yan, Zheng
07:59 AM Revision 700e5131 (ceph): mds: fix typo
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision f8749997 (ceph): mds: improve passed_validation check.
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision c8609d13 (ceph): Continuation: delete self after calling _done()
make sure Continuation delete itself even when virtual function
_done() is overwrited.
Signed-off-by: Yan, Zheng <zy...
Yan, Zheng
07:59 AM Revision 82bd4716 (ceph): mds: queue non-recursive scrub to top of scrub stack
non-recursive scrub blocks admin socket, make it have earliest service
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
07:59 AM Revision d98c516a (ceph): mds: use MDSInternalContextBase instead of Context in scrub stack code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 7f83e3df (ceph): mds: report dirfrag stats error found by scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 1c52d444 (ceph): mds: remove unused 'Context *' parameter from MDCache::repair_foo_stats()
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision a656f94f (ceph): mds: improve debug message for CDir::check_rstat()
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision aa1477f1 (ceph): mds: improve debug message for CInode::validate_disk_state
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 2da94496 (ceph): mds: set ScrubHeader for dirfrag when doing non-recursive scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 0ea991e4 (ceph): mds: skip scrubbing dentries not modified since last scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision f29091b5 (ceph): mds: check dirfrag rstat when dirfrag is fetched
This avoids the problem that dirfrag becomes imcomplete before
ValidationContinuation::_dirfrags() get called;
Signe...
Yan, Zheng
07:59 AM Revision a9ca637f (ceph): mds: check both frag_stat and nest_stat when validating inode
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 94bc0fb3 (ceph): mds: don't crash when scrub finds bad fragstat/rstat
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 5a9944d7 (ceph): mds: properly free CInode::ValidationContinuation
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 7760fc2b (ceph): mds: repair fragstat/rstat errors in dirfrag
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision e900ea43 (ceph): mds: repair fragstat/rstat errors in inode
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision 1cc9d52e (ceph): mds: check all items even when CInode::validate_disk_state() finds errors
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
07:59 AM Revision a2def5e2 (ceph): mds: don't getxattr and setxattr at the same time
If an osd request contains write operation, the reply will not
carry output data. So we can't getxattr and setxattr i...
Yan, Zheng
07:26 AM Revision 5810eb0f (ceph): tools/rados: reduce rados put memory usage by op_size
indata.append(char*, len) causes buffer "buf" to be physically copied
to new memory block. Make static buffer pointin...
Piotr Dałek
04:12 AM Revision 11222c5c (ceph): cmake: Remove duplicate find_package libcurl line.
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> Brad Hubbard
03:52 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rgw... Loïc Dachary
03:51 AM Stable releases Tasks #14692: hammer v0.94.7
h3. powercycle... Loïc Dachary
03:50 AM Stable releases Tasks #14692: hammer v0.94.7
h3. fs... Loïc Dachary
03:49 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rbd... Loïc Dachary
03:46 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rados ... Loïc Dachary
03:24 AM Stable releases Tasks #14692: hammer v0.94.7
h3. upgrade... Loïc Dachary
03:40 AM Bug #14992 (Rejected): "rados ls -p xxx" hangs forever when all "rbd_directory" obj replica osds ...
It is easy to reproduce:
1.ceph osd pool create testpool 128 128
2.rbd create testpool/testimg --size 10240
3.ceph...
science luo
03:12 AM Revision 7e95acb4 (ceph): Merge pull request #7946 from SUSE/wip-doc-dev-teuth
doc/dev: integrate testing into the narrative
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:30 AM Revision d6a48d96 (ceph): cls_hello: Fix grammatical error in description comment
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> Brad Hubbard
01:15 AM rgw Bug #14991 (Won't Fix - EOL): rgw core dump with ceph::log::Log::is_inside_log_lock
i used ceph 0.94.5 for rgw with mutil regions,but when i restart my radosgw service,it will core dump,the core dump f... Diluga Salome
01:06 AM Revision f4bd1fc9 (ceph): mds: allow client to request caps when opening file
Allow client to request xattrs while opening file. MDS adds xattrs
and corresponding caps to the reply. This is impor...
Yan, Zheng

03/06/2016

08:11 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
... Jason Dillaman
06:28 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
@Roy: Upgrading is recommended anyway, but before you take that step you can try setting "rbd_non_blocking_aio" to fa... Nathan Cutler
06:01 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
I can try with a newer Ceph, but #13726 seems to be dependant upon RBD cache being disabled but it should be enabled ... Roy Keene
07:51 PM Revision b145c494 (ceph): Merge pull request #857 from smithfarm/wip-move-plus-to-clusters
suites/smoke/1node: move + to clusters/ subdirectory Yuri Weinstein
07:41 PM Revision 5b570653 (ceph): doc/dev: integrate testing into the narrative
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
06:31 PM Revision 59585b6b (ceph): suites/smoke/1node: move + to clusters/ subdirectory
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
02:19 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
If I had a reproducer, I wouldn't be asking you to reproduce ;) I would suggest trying to replicate what you describ... Ilya Dryomov
06:58 AM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
We will try! But where we can get custom kernels, and whats is scenario of reproduce? Set weight of some osd to 0? Or... Ruslan Usifov
09:00 AM Revision c8230189 (ceph): msg: remove duplicated code - local_delivery will now call 'enqueue'
This simplify the code and clarify that for each local message,
'local_delivery_thread' simply tries to 'fast_dispat...
Avner BenHanoch
08:03 AM Revision e9046700 (ceph): Event: fix clock skew problem
Default constructor of utime_t generates the same default time value,
so after the loop, we only keep the last list f...
wei jin

03/05/2016

10:49 PM rbd Bug #14988: QEMU VM hangs talking to RBD via librbd
@Roy: Can you reproduce this on 0.94.6? If not, it is probably http://tracker.ceph.com/issues/13726 Nathan Cutler
08:44 PM rbd Bug #14988 (Resolved): QEMU VM hangs talking to RBD via librbd
I'm having a repeatable hang in QEMU (v2.4.1) talking to a Ceph (v0.95.4) RBD via librbd.
I've acquired a core fil...
Roy Keene
05:29 PM Revision 6018ccd6 (ceph): Merge pull request #7862 from theanalyst/rgw/doc-insecure-keystone
doc: rgw explain keystone's verify ssl switch
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
05:25 PM Revision a794ea5f (ceph): Merge pull request #7887 from cbodley/wip-rgw-test-multi-period
test/rgw: add multisite test for meta sync across periods
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
05:25 PM Revision 2286463b (ceph): Merge pull request #7827 from cbodley/wip-rgw-period-meta-logs
rgw: fixes for per-period metadata logs
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
04:28 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
It's not immediately obvious what the problem is - there are a few different possibilities and not enough information... Ilya Dryomov
02:35 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Sorry but more old logs alredy rotated and we haven't them Ruslan Usifov
09:53 AM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
What about a syslog for the night of Feb 26 - the attached one starts at ~7 o'clock? I need to see syslogs for the e... Ilya Dryomov
02:55 PM Revision a9493f23 (ceph): Merge pull request #7941 from SUSE/wip-teuos-intro
doc: detailed description of bugfixing workflow
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:54 PM Revision a0572bc5 (ceph): doc: detailed description of bugfixing workflow
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
12:08 PM Revision 602c61b3 (ceph): rgw: fix usage log aggregation
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
09:51 AM Revision cf8c30ac (ceph): init-ceph.in: allow case-insensitive true in `osd crush update on start'
I noticed this when openstack/puppet-ceph sliently converted my 'true'
to 'True' in ceph.conf.
Signed-off-by: Eric C...
Eric Cook
08:49 AM Revision c0074935 (ceph): rgw: add virtual error bucket per user in usage logs
Log under the virtual error bucket '-' when bucket not found
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
08:49 AM Revision 59d098c7 (ceph): rgw: avoid showing payer when payer == owner
If the payer matches the owner it shows the owner only.
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
01:09 AM Revision 19f6c8d4 (ceph): Merge pull request #7933 from ceph/wip-doc-dist-ceph-detect-init
doc: add ceph-detect-init(8) source to dist tarball
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
12:32 AM rbd Bug #14986 (Closed): rbd export/export-diff with needs to protect against unintended journal replay
If journaling is enabled on an image, reading from the image HEAD will result in a journal replay. If the image was ... Jason Dillaman

03/04/2016

11:22 PM Revision 44600cb3 (ceph): objclass: add cls_cxx_stat2()
allows retrieving high definition mtime
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
11:19 PM Revision 2c23b6a9 (ceph): Merge pull request #7938 from dmick/jewel
debian/changelog: Remove stray 'v' in version Zack Cerza
11:13 PM Revision e2fcfdf0 (ceph): librados: add mtime2() that uses timespec and ceph::real_time
Need for setting higher resolution time
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
11:13 PM Revision 8cfdaa64 (ceph): test: add a test for stat2(), mtime2()
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
10:53 PM Revision d0c57aec (ceph): debian/changelog: Remove stray 'v' in version
Signed-off-by: Dan Mick <dan.mick@redhat.com>
(cherry picked from commit 0f7730c8f444657d4aaffa28c12bbcd602a2e3b8)
Dan Mick
10:45 PM Revision 56ca5732 (ceph): Merge pull request #7937 from saru95/patch--1
ceph_daemon.py: Resolved ImportError to work with python3
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
10:12 PM Revision 28cc0ca6 (ceph): Merge pull request #7936 from ceph/wip-fix-debian-build
debian/changelog: Remove stray 'v' in version Zack Cerza
10:05 PM Revision 9e47cef3 (ceph): ceph_daemon.py: Resolved ImportError to work with python3
Signed-off-by: Sarthak Munshi <sarthakmunshi@gmail.com> Sarthak Munshi
10:04 PM Revision 1353fe51 (ceph): rgw: implement find_oldest_log_period for RGWMetadataManager
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision faa60bc1 (ceph): rgw: pull first log period from master if not found locally
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 762c075b (ceph): rgw: meta log rest handlers avoid get_log()
RGWMetadataManager::get_log() will allocate a log and keep it in memory.
this could lead to a potential denial of ser...
Casey Bodley
10:04 PM Revision 5434db93 (ceph): rgw: use current period for InitSyncStatus
the InitSyncStatus coroutine records the position to start incremental
sync after finishing a full sync. this should...
Casey Bodley
10:04 PM Revision 9a6771a8 (ceph): rgw: fix for RGWCoroutinesManager::run() return value
the 'int ret' variable of the inner scope was shadowing an 'int ret'
variable in the outer scope, so we weren't propa...
Casey Bodley
10:04 PM Revision da5f3e7e (ceph): rgw-admin: add read_current_period_id() helper function
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 873cf398 (ceph): rgw: make RGWMetaSyncCR wakeups thread-safe
now that the shards will be coming and going after startup, they need to
be reference counted and protected by a mute...
Casey Bodley
10:04 PM Revision dbb93405 (ceph): rgw: only write meta sync shard markers if can_adjust_marker
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision b8a4a9d9 (ceph): rgw: add RGWStatObjCR for async raw_obj_stat
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision f8804b34 (ceph): rgw: make RGWMetadataLog::get_shard_oid public and const
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 8044dcb0 (ceph): rgw: initialize async_rados before meta_mgr
RGWMetadataManager::init() will depend on async_rados
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
10:04 PM Revision 1b4d1e30 (ceph): rgw: period history behaves with no current_period
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
09:56 PM Revision a1ea7180 (ceph): rgw: TempURL in radosgw behaves now like its Swift's counterpart.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
09:56 PM Revision f25adc26 (ceph): rgw: ONLY const-correctness and formatting improvements in TempURL.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
09:52 PM Revision 5694397c (ceph): rgw: use TempURL when requested regardless of auth token presence.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
09:52 PM Revision a99f5827 (ceph): rgw: improve support for Swift's URL schema with account name inside.
Fixes: #11163
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Radoslaw Zarzynski
09:52 PM Revision c6f48ff0 (ceph): rgw: use Swift account name in TempURL.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
09:52 PM Revision 154d8654 (ceph): rgw: don't use req_state::bucket_name in TempURL of Swift API.
Fixes: #14806
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Radoslaw Zarzynski
09:33 PM rbd Bug #14984 (Resolved): rbdmap.service should include RBDMAPFILE environment variable
/usr/bin/rbdmap requires the RBDMAPFILE variable to be set. I've worked around this on my machines by adding Environm... Paul Rawson
08:30 PM Bug #14983: osd: handle EIO in handle_sub_read
Attaching output of 'ceph pg dump --format=json' and 'ceph osd dump --format=json'
Aaron T
08:24 PM Bug #14983: osd: handle EIO in handle_sub_read
Attaching log files either as plaintext or bzipped plaintext failed, so they can be downloaded individually or as a t... Aaron T
08:21 PM Bug #14983 (Resolved): osd: handle EIO in handle_sub_read
My 41-OSD cluster suffered a four drive failures in rapid succession several weeks ago. I added new drives and have b... Aaron T
08:05 PM Revision 4ad230a3 (ceph): librados: new stat2() that returns ceph::real_time
Hiding ceph_real_time behind ceph_real_time_t
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
07:42 PM Revision 0f7730c8 (ceph): debian/changelog: Remove stray 'v' in version
Signed-off-by: Dan Mick <dan.mick@redhat.com> Dan Mick
07:22 PM Revision e386562e (ceph): librados: add stat2() calls that return high resultion mtime
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:37 PM Revision ede8deeb (ceph): Merge pull request #7918 from ceph/wip-rgw-payer-yehuda
rgw: link payer info to usage logging
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
05:26 PM Revision 01c0a5f5 (ceph): etc/sysconfig/ceph: set 128MB tcmalloc cache size
Bump up from tcmalloc's default cache size.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
Ken Dreyer
04:35 PM Revision c8ec17aa (ceph): doc: add ceph-detect-init(8) source to dist tarball
Prior to this commit, the tarball from "make dist" did not include the
ceph-detect-init(8) man page rST source.
Sign...
Ken Dreyer
03:47 PM Revision d720540e (ceph): Merge pull request #7929 from yehudasa/wip-submodules-fix
submodules: revert an accidental change
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
03:29 PM Revision 46310e3c (ceph): mailmap: Javen Wu affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 8b0b4ef5 (ceph): mailmap: You Ji affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 0e536f5e (ceph): mailmap: Edward Yang affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 337ea900 (ceph): mailmap: Yankun Li affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 7ef9c90a (ceph): mailmap: Willem Jan Withagen affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 510ae025 (ceph): mailmap: Dongsheng Yang affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 7883d7c2 (ceph): mailmap: Abhishek Varshney affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision fc1578a9 (ceph): mailmap: Avner BenHanoch affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 013db9c5 (ceph): mailmap: Luis Periquito affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 50a05b1b (ceph): mailmap: Mike Shuey affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision d47cbcc2 (ceph): mailmap: Marcus Watts affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision 1ee635af (ceph): mailmap: Zack Cerza affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:29 PM Revision c988ab26 (ceph): mailmap: Subramanyam Varanasi affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:28 PM rbd Subtask #14981 (Resolved): rbd-mirror daemon systemd / upstart scripts
Jason Dillaman
03:15 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Aditional attach syslog for 27-02-2016
Ruslan Usifov
03:06 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
We attached syslog from 192.169.31.220 for 26 feb 2016
We make osdmap, but maps exist only begin from 5732
Ruslan Usifov
02:50 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
This seems to be more serious than I thought. Could you send over as many osdmaps going back from 5800 as possible (... Ilya Dryomov
09:42 AM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
We waited when rebalance was done, then launch rsync.
And yes of course, misderected happens doesn't only one nod...
Ruslan Usifov
03:11 PM Revision 91bc1145 (ceph): mailmap: Rémi Buisson affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:10 PM Revision 35c372b1 (ceph): mailmap: Mehdi Abaakouk affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:10 PM Revision 06a88b06 (ceph): mailmap: Kefu Chai name normalization
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:09 PM Revision d5844d25 (ceph): mailmap: Jason Dillaman name normalization
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:08 PM Revision 178d5b2d (ceph): mailmap: Aaron Bassett affiliation
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> Abhishek Lekshmanan
03:03 PM Bug #14955 (Resolved): unittest_bufferlist.sh failing
Samuel Just
03:02 PM Revision fc88f488 (ceph): Merge pull request #7910 from ceph/wip-14955
buffer: increment history alloc as well in raw_combined
Reviewed-by: Sage Weil <sage@redhat.com>
Samuel Just
03:01 PM Revision 5a1b15d8 (ceph): debian: package librgw_file* tests
The "make install" command installs these files, but the Debian
packaging did not include them.
Signed-off-by: Ken D...
Ken Dreyer
02:57 PM Revision 11b1cdc6 (ceph): debian: tighten sub-package version dependencies
Prior to this change, users could possibly install some ceph
sub-packages with differing versions. Make each sub-pack...
Ken Dreyer
02:54 PM Revision 2f7d1c9d (ceph): submodules: revert an accidental change
revert changes that went in in commit f1ac0de5bfd974258c257470feae5ff03054873e.
This affects ceph-erasure-code-corpus...
Yehuda Sadeh
02:53 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Update--it's now been approximately 20 hours since my latest test finished and my osd map cache still has 2,125 maps.... Steve Taylor
11:29 AM Revision 8c1f7ebd (ceph): rgw: RGWZoneParams::create should not handle -EEXIST error
It should be handled by the caller
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
11:25 AM Revision 2fe0f8eb (ceph): Merge pull request #7916 from ceph/wip-14975
rgw: adjust error code when bucket does not exist in copy operation
rgw: don't override error when initializing zoneg...
Orit Wasserman
08:06 AM Revision 9cbd6a46 (ceph): Merge pull request #856 from SUSE/wip-opensuse-distros-hammer
distros: add yaml fragments for openSUSE 13.2 and 42.1
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
07:28 AM Backport #14964 (In Progress): infernalis: Objects promoted unnecessarily when deleting from cache
Rajat Garg
07:24 AM Revision e65a2f67 (ceph): distros: add yaml fragments for openSUSE 13.2 and 42.1
Signed-off-by: Nathan Cutler <ncutler@suse.com>
(cherry picked from commit 3458adb5d3b749453848fc5edbaeedaeff84853c)
Nathan Cutler
06:49 AM rgw Bug #14980 (Closed): A period commit fails with Invalid Argument error
Created zonegroup, zone and added user to the zone. While updating the period I hit the following error:
#radosgw-...
Shilpa MJ
04:34 AM Revision f794adad (ceph): tests: Add TEST_no_segfault_for_bad_keyring to test/mon/misc.sh
94da46b6e31cac206cb32fc5bd3159209ee25e8c adds
TEST_no_segfault_for_bad_keyring which requires changes to run
in hamme...
Brad Hubbard
04:25 AM Backport #14961 (In Progress): hammer: PK11_DestroyContext() is called twice if PK11_DigestFinal(...
Brad Hubbard
03:29 AM Backport #14960 (In Progress): infernalis: PK11_DestroyContext() is called twice if PK11_DigestFi...
https://github.com/ceph/ceph/pull/7920 Brad Hubbard
03:27 AM devops Backport #14861 (Resolved): hammer: ceph init script unconditionally sources /lib/lsb/init-functions
Loïc Dachary
03:25 AM Revision 522e3e8d (ceph): Merge pull request #7797 from SUSE/wip-14861-hammer
hammer: ceph init script unconditionally sources /lib/lsb/init-functions
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Loïc Dachary
03:22 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
02:59 AM Revision ee740834 (ceph): add param 'order' to Create() and Image.Clone(), and upgrade ci ceph ve...
Signed-off-by: Crazykev <crazykev@zju.edu.cn> Crazykev
02:38 AM Backport #14979 (In Progress): hammer: ceph_test_rados: incorrect buffer at pos ...
Loïc Dachary
02:37 AM Backport #14979 (Resolved): hammer: ceph_test_rados: incorrect buffer at pos ...
https://github.com/ceph/ceph/pull/7917 Loïc Dachary
02:34 AM Bug #10794 (Pending Backport): ceph_test_rados: incorrect buffer at pos ...
Loïc Dachary
02:22 AM Revision 1c927c02 (ceph): Merge pull request #854 from SUSE/wip-opensuse-distros
distros: add yaml fragments for openSUSE 13.2 and 42.1
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:19 AM Backport #14978 (In Progress): hammer: tools, test: Add ceph-objectstore-tool to operate on the m...
Loïc Dachary
02:18 AM Backport #14978 (Resolved): hammer: tools, test: Add ceph-objectstore-tool to operate on the meta...
https://github.com/ceph/ceph/pull/7911 Loïc Dachary
02:17 AM Feature #14977 (Resolved): tools, test: Add ceph-objectstore-tool to operate on the meta collection
https://github.com/ceph/ceph/pull/5197 Loïc Dachary
02:13 AM Revision 0186062d (ceph): ceph-disk: display the function name with the log messages
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision 977bf038 (ceph): ceph-disk: destroy does not unmap block/journal
The dmcrypt boolean needs to be set for destroy to ensure the
journal/block partitions are 'cryptsetup remove'.
Sign...
Loic Dachary
02:13 AM Revision 15db7feb (ceph): ceph-disk: make dmcrypt_unmap idempotent
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision 67f9e8da (ceph): ceph-disk: re-using an OSD partition bugous test
When re-using an OSD partition, the test of the partition type is done
against a non-existent variable.
Signed-off-b...
Loic Dachary
02:13 AM Revision bd4bd5c6 (ceph): ceph-disk: simplify trigger
The ceph-disk trigger deals with dmcrypt mapping which is redundant with
what ceph-disk activate-* does when the --dm...
Loic Dachary
02:13 AM Revision 1ec58fcf (ceph): ceph-disk: implement lockbox key management
Instead of storing the dmcrypt keys in the /etc/ceph/dmcrypt-keys
directory, they are stored in the monitor. If a mac...
Loic Dachary
02:13 AM Revision 67ef329a (ceph): ceph-disk: add a description for each subcommand
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision d355a383 (ceph): doc: update ceph-disk to refer to ceph-disk --help
The ceph-disk page is often obsolete, mostly because maintaining
it requires a significant amount of copy/paste and r...
Loic Dachary
02:13 AM Revision 4d42a567 (ceph): ceph-disk: implement list for lockbox
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision b36859ce (ceph): ceph-disk: protect list with activate lock
list may try to mount partitions to figure out the OSD id and other
details. If it does so while the OSD is activated...
Loic Dachary
02:13 AM Revision 869eb3af (ceph): tests: verify ceph-disk activate-lockbox
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision 48c21ced (ceph): ceph-disk: implement deactivate --once
It is mostly useful for test purposes.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary
02:13 AM Revision ed56cef1 (ceph): tests: make ceph-disk workunit resilient to non ascii
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
02:13 AM Revision 0b4ab0d3 (ceph): ceph-disk: improve trigger verbosity
The ceph-disk activate errors were ignored and not displayed. Capture
stdout/stderr and display it if the exit code i...
Loic Dachary
02:13 AM Revision 94c5df45 (ceph): tests: verify ceph-disk lockbox activation scenarii
Simulate the cases where the activation (via udev running trigger)
sequences are:
* journal then lockbox
* data then...
Loic Dachary
02:13 AM Revision 003dc154 (ceph): ceph-disk: map after luks formatting
dmcrypt_map is idempotent, it does not matter that it is called multiple
times when activating or preparing a device....
Loic Dachary
02:13 AM Revision e51ac3ee (ceph): ceph-disk: protect destroy with the activate lock
So that it does not race against an activation.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary
02:13 AM Revision 59a74190 (ceph): Merge pull request #7909 from SUSE/wip-14770
ceph-detect-init: return correct value on recent SUSE distros
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:06 AM Revision 94da46b6 (ceph): tests: make sure no segfault occurs when using some bad keyring
Signed-off-by: Dunrong Huang <riegamaths@gmail.com>
(cherry picked from commit 2eb0bf32244fc174d56cc42e2298c67d8b5299...
Dunrong Huang
02:02 AM Revision a371c0f1 (ceph): auth: fix a crash issue due to CryptoHandler::create() failed
In this case(e.g. user passes wrong key), attempts to call the CryptoKey.ckh will lead to a segfault.
This patch fix...
Dunrong Huang
02:02 AM Revision af5da4f2 (ceph): auth: fix double PK11_DestroyContext() if PK11_DigestFinal() failed
Signed-off-by: Dunrong Huang <riegamaths@gmail.com>
(cherry picked from commit e9e05333ac7c64758bf14d80f6179e001c0fdb...
Dunrong Huang
12:07 AM Revision 4727d426 (ceph): rgw: avoid showing payer when payer == owner
If the payer matches the owner it shows the owner only.
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid

03/03/2016

11:49 PM Bug #14976: rpm: broken dep with libboost_program_options-mt.so.1.53.0
Is this happening on any other host besides smithi024? if it's restricted to that one server, I suspect that host's r... Ken Dreyer
11:28 PM Bug #14976 (Resolved): rpm: broken dep with libboost_program_options-mt.so.1.53.0
... Sage Weil
11:13 PM Revision c3f031a3 (ceph): ceph-objectstore-tool, osd: Fix import handling
Use same_interval_since set to zero to communicate that an import has happened
and the correct value needs to be comp...
David Zafman
10:59 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Was the massive rsync you've provided warnings for done during rebalancing or after rebalancing completed? Do you ha... Ilya Dryomov
08:12 AM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Osd maps from 5970 to 5981 are in attachment Ruslan Usifov
10:18 PM Revision 155a53d6 (ceph): Merge pull request #7786 from ceph/wip-rgw-indexless
rgw: indexless buckets (Yehuda Sadeh)
- can define a policy, for which buckets are indexless
- users can then crea...
Yehuda Sadeh
10:06 PM Revision b7d022f6 (ceph): rgw: indexless buckets
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
10:04 PM Revision f1ac0de5 (ceph): rgw: configurable index type
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:56 PM Revision 21348aba (ceph): tasks/cephfs: add test case for scrub repair
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
09:56 PM Revision 41747d6f (ceph): tasks/cephfs: remove extraneous ;s in test_client_limits
These are harmless but they stand out in some editors.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
09:56 PM Revision 7a97fcbe (ceph): tasks/cephfs: avoid sleep in test_client_cache_size
Instead of waiting 30s and then checking, use
wait_until_true to complete as soon as the
condition is met. Test runs...
John Spray
09:56 PM Revision 67b711de (ceph): tasks/cephfs: optionally stat() in background
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
09:56 PM Revision aa193b31 (ceph): tasks: move wait_for_health up into CephFSTestCase
...so that TestDamage can use it too.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
09:56 PM Revision 356579be (ceph): tasks/cephfs: update TestDamage
...to account for the behavioural changes with
the addition of DamageTable.
Signed-off-by: John Spray <john.spray@re...
John Spray
09:56 PM Revision ffee5902 (ceph): suites: update log whitelist for TestDamage
For branch wip-damage-table.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
09:56 PM Revision ec0db68b (ceph): tasks: add TestDamage.test_damaged_dentry
A more detailed test for the case of damaged dentries,
because the handling involves the system passing through
a sta...
John Spray
09:56 PM Revision 905b1d9a (ceph): rgw: don't override error when initializing zonegroup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:49 PM Revision 0b48c868 (ceph): rgw: adjust error code when bucket does not exist in copy operation
Fixes: #14975
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
09:46 PM rgw Bug #14975 (Resolved): rgw: test_object_copy_bucket_not_found failure
getting NoSuchKey instead of NuSuchBucket. Happens in current master. Yehuda Sadeh
09:44 PM Revision 3458adb5 (ceph): distros: add yaml fragments for openSUSE 13.2 and 42.1
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
09:44 PM Revision 18a75f11 (ceph): test: use StrEq for C-style string matching
If compiler optimizations are enabled, strings will be copied,
resulting in different memory addresses.
Signed-off-b...
Jason Dillaman
09:43 PM Revision d0e3da2e (ceph): common/buffer: correct list_iterator::operator!= behavior
It was actually behaving as if it were operator==. This results
in loops running off the end of empty bufferlists.
...
Jason Dillaman
09:43 PM Revision bc60ba3e (ceph): Merge pull request #7764 from rzarzynski/wip-rgw-etag-dlo
rgw: multiple improvements regarding etag calculation for SLO/DLO of Swift API.
Reviewed-by: Yehuda Sadeh <yehuda@re...
Yehuda Sadeh
09:43 PM Revision 0357d875 (ceph): test: librbd template specializations leaking between translation units
A CMake build with optimizations disabled can result in a template
specialization for one test being reused by anothe...
Jason Dillaman
08:27 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I ran another test with 0.94.5-183-ge1b9208. I created a simple script that created and deleted a bunch of rbd snapsh... Steve Taylor
09:34 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Steve,
so the osdmaps are being trimmed fine on both OSD and monitor (v0.94.5) with the given settings. here could...
Kefu Chai
04:29 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Steve Taylor wrote:
> Mon and osd logs uploaded to support case 01549888. They're too big to upload here.
Thanks ...
Vikhyat Umrao
07:09 PM Bug #14955 (Fix Under Review): unittest_bufferlist.sh failing
https://github.com/ceph/ceph/pull/7910 Samuel Just
06:40 PM Bug #14955: unittest_bufferlist.sh failing
73dcd26fc8798e09d93520c583d63edb28ffc631 Samuel Just
06:35 PM Bug #14955: unittest_bufferlist.sh failing
ah CEPH_BUFFER_TRACK=true
bisect running
Samuel Just
06:25 PM Bug #14955: unittest_bufferlist.sh failing
Odd, it passes if I run the test directly. Samuel Just
06:24 PM Bug #14955: unittest_bufferlist.sh failing
Running main() from gmock_main.cc
[==========] Running 94 tests from 7 test cases.
[----------] Global test environ...
Samuel Just
03:18 AM Bug #14955 (Resolved): unittest_bufferlist.sh failing
Like it says, see eg http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-amd64-basic/#origin/master
It...
Greg Farnum
07:07 PM Revision 1335871f (ceph): buffer: increment history alloc as well in raw_combined
Introduced in 73dcd26fc8798e09d93520c583d63edb28ffc631
Fixes: #14955
Signed-off-by: Samuel Just <sjust@redhat.com>
Samuel Just
07:02 PM Revision 647723ec (ceph): tools, test: Add ceph-objectstore-tool to operate on the meta collection
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 31fa89f24997c3e9b4f8795ea28938ab65493d10)...
David Zafman
06:49 PM Revision 1de7e478 (ceph): osd/MonCommand: add/fix up 'osd [test-]reweight-by-{pg,utilization}'
- show before/after pg placement stats
- add test- variants that don't do anything
- only allow --no-increasing on th...
Sage Weil
06:49 PM Revision 28b33a5b (ceph): qa/workunits/cephtool/test.sh: test reweight-by-x commands
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:49 PM Revision 47b650c1 (ceph): mon/OSDMonitor: fix indentation
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:49 PM Revision 8a9429d8 (ceph): mon: make reweight max_change default configurable
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:49 PM Revision 651f05b6 (ceph): mon: make max_osds an optional arg
We keep the config option with the default (4), but let you
specify the max # of osds to reweight as a third optional...
Sage Weil
06:49 PM Revision ea9abe53 (ceph): osd/OSDMap: add summarize_mapping_stats
Calculate some basic stats about the PG distribution.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
06:49 PM Revision 5b757eff (ceph): mon: add 'osd utilization' command
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:49 PM Revision a70eaabc (ceph): mon: make reweight-by-* max_change an argument
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:35 PM Revision 04fd5695 (ceph): mds: add "damage ls" `tell` command.
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
06:35 PM Revision 507a78b2 (ceph): mds: enable dirs to go complete with corrupt dentries
Previously I was returning EIO for WAIT_COMPLETE waiters,
which caused requests to get stuck when waiting
for a reque...
John Spray
06:35 PM Revision 434ba9a4 (ceph): tools: create mdsdir frag in cephfs-data-scan init
MDS used to ignore missing dirfrag objects. Now that
they're detected and flagged, we need to explicitly
inject them...
John Spray
06:35 PM Revision 38cb31ac (ceph): mds: add "ceph tell mds damage rm"
For situations where an MDS needs to be told
that something it thought was damaged is no longer
damaged.
Signed-off-...
John Spray
06:35 PM Revision 65e5b85d (ceph): common: add config mds_damage_table_max_entries
Define how many entries DamageTable will store before
giving up and marking a rank damaged.
Signed-off-by: John Spra...
John Spray
06:35 PM Revision 309f20af (ceph): mds: add DamageTable class
A registry of places that damage to the metadata
tree has been detected. Allows more fine grained
error handling ins...
John Spray
06:35 PM Revision f816e34f (ceph): mds: add MDS::damage_table
Global instance per daemon.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
06:35 PM Revision 3f8a6c49 (ceph): mds: call into DamageTable from CDir
Signed-off-by: John Spray <john.spray@redhat.com> John Spray
06:35 PM Revision 21f91fd1 (ceph): mds/MDCache: no need to handle badfrag stray any more
DamageTable takes care of it now.
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
06:35 PM Revision 652191d4 (ceph): mds: generate -EIO on damaged path traverse
...by calling into DamageTable::is_dentry_damaged etc
Signed-off-by: John Spray <john.spray@redhat.com>
John Spray
06:35 PM Revision e065e3ba (ceph): mds: add health report for whether there is damage
We can make this more detailed later if needed:
the idea is primarily to cue the administrator
to go investigate in m...
John Spray
06:35 PM Revision 4773d133 (ceph): mds: don't suicide() from MDLog I/O functions
suicide() from anything invoked with a Finisher
would crash trying to join the finisher thread.
This is the last plac...
John Spray
06:35 PM Revision 9a9bfda9 (ceph): mds: fix handling failures opening root
Previously this called suicide, which isn't in general
safe to call from just anywhere (it joins the finisher
thread,...
John Spray
06:35 PM Revision be3544f1 (ceph): Merge remote-tracking branch 'gh/jewel'
Sage Weil
06:34 PM Revision ea450998 (ceph): v10.0.4
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
06:32 PM Revision ac8dca8c (ceph): mds: report dirfrag stats error found by scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision abe4de30 (ceph): mds: remove unused 'Context *' parameter from MDCache::repair_foo_stats()
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 3609bd6e (ceph): mds: improve debug message for CDir::check_rstat()
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 9da17324 (ceph): mds: improve debug message for CInode::validate_disk_state
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 56cd3903 (ceph): mds: set ScrubHeader for dirfrag when doing non-recursive scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision cc1f9027 (ceph): mds: don't ignore scrubbing non-regular non-directory inodes
The overhead of scrubbing them is low, so don't treat them specially.
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
06:32 PM Revision 78e80dea (ceph): mds: make scrubstack queue CInode instead of CDentry
There are two problems that enqueue CDentry in scrub stack. First,
the scrub stack code can't handle base inodes; sec...
Yan, Zheng
06:32 PM Revision 72885103 (ceph): mds: remove obsoleted FIXME from scrubstack code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 712a98d3 (ceph): mds: and 'force' options to scrub_path asok command
'force' means check whole subtree (don't skip scrubbing entries
not modified since last scrub)
Signed-off-by: Yan, Z...
Yan, Zheng
06:32 PM Revision d1fec4fd (ceph): mds: fix typo
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 2681bd14 (ceph): mds: improve passed_validation check.
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision d7737557 (ceph): Continuation: delete self after calling _done()
make sure Continuation delete itself even when virtual function
_done() is overwrited.
Signed-off-by: Yan, Zheng <zy...
Yan, Zheng
06:32 PM Revision 6c59383d (ceph): mds: queue non-recursive scrub to top of scrub stack
non-recursive scrub blocks admin socket, make it have earliest service
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
06:32 PM Revision 61b35494 (ceph): mds: use MDSInternalContextBase instead of Context in scrub stack code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 1e9f2a2b (ceph): mds: check all items even when CInode::validate_disk_state() finds errors
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 950d4117 (ceph): mds: don't getxattr and setxattr at the same time
If an osd request contains write operation, the reply will not
carry output data. So we can't getxattr and setxattr i...
Yan, Zheng
06:32 PM Revision c1f3ef04 (ceph): mds: set bad dirfrag's version to 1
there are lots of places assume 'version == 0' means dirfrag is
uninitialized
Signed-off-by: Yan, Zheng <zyan@redhat...
Yan, Zheng
06:32 PM Revision 3f749582 (ceph): mds: scrub fragstat.mtime and rstat.rctime
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 5651a0d6 (ceph): mds: store ScrubHeader refernce in CInode's scrub_info_t
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision e3ef072a (ceph): mds: handle non-recursive scrubbing
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 53275215 (ceph): mds: use scrubstack code to scrub single dentry
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 506b536c (ceph): mds: remove old scrub_dentry code
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:32 PM Revision 4000f014 (ceph): mds: and 'recursive/repair' options to scrub_path asok command
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision cfe7296e (ceph): mds: properly free CInode::ValidationContinuation
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision 1c7833a6 (ceph): mds: repair fragstat/rstat errors in dirfrag
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision db55452c (ceph): mds: repair fragstat/rstat errors in inode
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision 4c6842c0 (ceph): mds: skip scrubbing dentries not modified since last scrub
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision bb0b294e (ceph): mds: check dirfrag rstat when dirfrag is fetched
This avoids the problem that dirfrag becomes imcomplete before
ValidationContinuation::_dirfrags() get called;
Signe...
Yan, Zheng
06:10 PM Revision 7fd1d699 (ceph): mds: check both frag_stat and nest_stat when validating inode
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision 45e942ce (ceph): mds: don't crash when scrub finds bad fragstat/rstat
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
06:10 PM Revision 62731d02 (ceph): ceph-detect-init: return correct value on recent SUSE distros
http://tracker.ceph.com/issues/14770 Fixes: #14770
Signed-off-by: Nathan Cutler <ncutler@suse.com>
Nathan Cutler
04:49 PM Revision 96d79ba2 (ceph): common/obj_bencher.cc: make verify error fatal
When run without "--no-verify", all verification errors are noted,
but they are not forwarded/reported anywhere else ...
Piotr Dałek
04:47 PM Revision d8756208 (ceph): common/obj_bencher.cc: make verify error fatal
When run without "--no-verify", all verification errors are noted,
but they are not forwarded/reported anywhere else ...
Piotr Dałek
04:47 PM Revision 04fe9517 (ceph): test/test_rados_tool.sh: force rados bench rand and seq
This forces rados bench rand and seq to execute, so if there's
a regression in any of above, it won't go unnoticed.
...
Piotr Dałek
04:39 PM Backport #14973 (In Progress): infernalis: common/obj_bencher.cc: make verify error fatal
Loïc Dachary
04:38 PM Backport #14973 (Resolved): infernalis: common/obj_bencher.cc: make verify error fatal
https://github.com/ceph/ceph/pull/7905 Loïc Dachary
04:38 PM Backport #14974 (In Progress): hammer: common/obj_bencher.cc: make verify error fatal
Loïc Dachary
04:38 PM Backport #14974 (Resolved): hammer: common/obj_bencher.cc: make verify error fatal
https://github.com/ceph/ceph/pull/7903 Loïc Dachary
04:37 PM Feature #14971 (Pending Backport): common/obj_bencher.cc: make verify error fatal
Loïc Dachary
03:21 PM Feature #14971 (Fix Under Review): common/obj_bencher.cc: make verify error fatal
Patches:
Hammer: https://github.com/ceph/ceph/pull/7903
Infernalis: https://github.com/ceph/ceph/pull/7905
Maste...
Piotr Dalek
01:58 PM Feature #14971 (Resolved): common/obj_bencher.cc: make verify error fatal
Loïc Dachary
04:15 PM Revision 3a1b307d (ceph): Merge pull request #7897 from branch-predictor/bp-bench-errors-fatal
common/obj_bencher.cc: make verify error fatal
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
04:13 PM Revision 50653cf8 (ceph): global: complain about parse errors after we open the log
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:13 PM Revision 6c4aafe9 (ceph): config: more parse_errors into md_config_t
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:10 PM Feature #14972 (Fix Under Review): add support for subscription-manager
https://github.com/ceph/ceph/pull/7907 Loïc Dachary
03:39 PM Feature #14972 (Resolved): add support for subscription-manager
The file */etc/rhsm/facts/ceph_usage.facts* must be updated on a regular basis via cron with the following structure
...
Loïc Dachary
03:48 PM rbd Subtask #14869 (Fix Under Review): journal library should re-use thread pool and timer
*PR*: https://github.com/ceph/ceph/pull/7906 Jason Dillaman
03:04 PM Revision 658bba85 (ceph): common/obj_bencher.cc: make verify error fatal
When run without "--no-verify", all verification errors are noted,
but they are not forwarded/reported anywhere else ...
Piotr Dałek
02:42 PM Revision 23f459cc (ceph): log: use correct delete[]
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:42 PM Revision 58250f59 (ceph): log: fix some whitespace
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:40 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
the test expects num_objects in data pool become zero.Due to this bug, it fails. Zheng Yan
01:06 PM Bug #14962: PG::publish_stats_to_osd() does not get called when trimming snap objects (TestStrays...
the latest good commit is 82896f2c6e2655db8c9a05a7cc31a9e65c9aa350 Zheng Yan
10:10 AM Bug #14962 (Resolved): PG::publish_stats_to_osd() does not get called when trimming snap objects ...
http://pulpito.ceph.com/zyan-2016-03-02_06:21:11-fs-wip-zyan-testing-testing-basic-mira/37805/
'ceph df' shows the...
Zheng Yan
02:38 PM CephFS Bug #14684 (Resolved): test_scrub_checks fails
Sage Weil
02:37 PM Revision 799ea24b (ceph): Merge pull request #7757 from ukernel/jewel-14684
mon/MDSMonitor.cc: properly note beacon when health metrics changes
Reviewed-by: John Spray <john.spray@redhat.com>
Sage Weil
02:15 PM Revision 9483cae6 (ceph): Merge pull request #7882 from branch-predictor/bp-unconfuse-health-1
mon: unconfuse object count skew message
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
02:08 PM CephFS Bug #14970 (Rejected): Post-new-layouts clients crash talking to older MDSs
Ah, I see: we reused the version, makes sense. Thanks! John Spray
02:01 PM CephFS Bug #14970: Post-new-layouts clients crash talking to older MDSs
I think this only affects older MDS with feature bit (1<<58) Zheng Yan
01:48 PM CephFS Bug #14970 (Rejected): Post-new-layouts clients crash talking to older MDSs
By sheer coincidence I had a vstart cluster created before rebasing on master, and a client compiled after rebasing o... John Spray
02:06 PM Bug #14498 (Can't reproduce): cephx error: NSS AES final round failed: -8190 while bootstrapping ...
Sage Weil
02:04 PM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
Thanks Samuel for the update.
Unfortunately, I am unable to hit this issue currently after I happen to do an upgr...
Deepthi Dharwar
02:01 PM Revision f792a3f6 (ceph): PGMonitor: unconfuse object count skew message
"Pool <pool> has too few pgs" is okay assuming it does not take other
pools into account. And since it does, it is co...
Piotr Dałek
01:54 PM Revision 353edf44 (ceph): Merge pull request #7898 from oritwas/wip-cmake-add-fs_types
cmake: add common/fs_types.cc to libcommon
Reviewed-by: John Spray <john.spray@redhat.com>
John Spray
01:53 PM Backport #13288: hammer: stuck recovering, unfound hit set due to removing it while !active
or, we can encode the osdmap (i.e. pg_pool_t) in the same old way before the GMT feature bit is introduced. Kefu Chai
01:51 PM Revision 8ce41ccc (ceph): Merge pull request #7881 from aclamk/ceph-df-used-fix
mon: fix calculation of %USED
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:49 PM Revision 9127a4c7 (ceph): Merge pull request #7892 from majianpeng/bluestore-leak-unwritten-extent
osd: bluestore: fix check for write falling within the same extent
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:46 PM Revision fcc459c8 (ceph): os/bluestore/BlueStore: Don't leak trim overlay data before write.
Suppose: bluestore_overlay_max_length=bluestore_min_alloc_size;
bluestore_overlay_max = 2;
For the following ops:
wri...
Jianpeng Ma
01:43 PM Backport #14965 (Need More Info): hammer: Objects promoted unnecessarily when deleting from cache
This is a non-trivial backport and we're not sure if it's needed. Assigning to myself until I can get clarification. Nathan Cutler
11:35 AM Backport #14965 (Rejected): hammer: Objects promoted unnecessarily when deleting from cache
Nathan Cutler
01:41 PM Revision a9db6ee7 (ceph): Merge pull request #7886 from stiopaa1/blueStoreOverrides
osd: bluestore: add 'override' to virtual functions
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:40 PM Revision 84747dcb (ceph): Merge pull request #7895 from majianpeng/bluestore-trim-overlay
os/bluestore/BlueStore: Don't leak trim overlay data before write. Sage Weil
01:35 PM Backport #14783 (Resolved): hammer: test_bit_vector.cc uses magic numbers against #defines that vary
Sage Weil
01:35 PM Revision d314849a (ceph): Merge pull request #7672 from dachary/wip-14783-hammer
hammer: test_bit_vector.cc uses magic numbers against #defines that vary Sage Weil
01:34 PM Revision ed4295b0 (ceph): Fix alignment in bluefs
Signed-off-by: Dan Mick <dmick@redhat.com> Dan Mick
01:33 PM Revision 98b6d912 (ceph): test/osd: Relax the timing intervals in osd-markdown.sh
It's too easy for a busy system to violate the time intervals;
decouple the per-iteration sleeptime from the overall ...
Dan Mick
01:23 PM Revision 7a87625a (ceph): Merge remote-tracking branch 'gh/wip-file-layout'
Sage Weil
01:23 PM Revision 38904e92 (ceph): Merge remote-tracking branch 'gh/jewel'
Sage Weil
01:17 PM Revision a7a65e7a (ceph): cmake: add common/fs_types.cc to libcommon
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
01:07 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
h3. original description... Loïc Dachary
11:47 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Nevermind! I see now that's a totally different double-something issue. Nathan Cutler
11:42 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
In other words, we could close this as a duplicate of #14961 Nathan Cutler
11:41 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Loic, can we do the backport through #14958 which I have properly staged for backport to infernalis and hammer? Nathan Cutler
07:10 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
... Loïc Dachary
06:46 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
... Loïc Dachary
05:46 AM Backport #14873 (In Progress): hammer: rados bench seq crashes (v0.94.6)
Loïc Dachary
05:42 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
The faulty cherry pick comes from https://github.com/ceph/ceph/pull/6791 Loïc Dachary
01:02 PM Backport #14969 (In Progress): hammer: common/obj_bencher.cc: fix verification crashing when ther...
Loïc Dachary
12:59 PM Backport #14969 (Resolved): hammer: common/obj_bencher.cc: fix verification crashing when there's...
https://github.com/ceph/ceph/pull/7896 Loïc Dachary
12:59 PM Bug #14968 (Resolved): common/obj_bencher.cc: fix verification crashing when there's no objects
https://github.com/ceph/ceph/pull/5853 Loïc Dachary
12:36 PM Revision 6a6754f8 (ceph): hammer: tools: fix race condition in seq/rand bench (part 2)
Commit c2c6d02591519dfd15ddcb397ac440322a964deb which is intended to
cherry-pick 9bcf5f065c4ed4b10d8f98961d1f99493bcd...
Alexey Sheplyakov
12:32 PM Revision 3a5b1029 (ceph): hammer: tools: fix race condition in seq/rand bench (part 1)
src/common/obj_bencher.cc:601: the lock should be taken before calling completion_ret,
not after. Also note that if r...
Alexey Sheplyakov
12:30 PM Revision 562c0a96 (ceph): configure.ac: added autoconf check for getgrouplist
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 16b59c6cd68d532a47e8c0e7b1f088b41433f048)
Burkhard Linke
12:30 PM Revision b13ddc06 (ceph): client: added permission check based on getgrouplist
Fixes: #13268
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit f04c8da5432174874ca97d11a5b2fef5...
Burkhard Linke
12:30 PM Revision 16e3e2f0 (ceph): client/Client.cc: fix realloc memory leak
Fix handling of realloc. If realloc() fails it returns NULL, assigning
the return value of realloc() directly to the ...
Danny Al-Gaaf
12:30 PM Revision e7f299ac (ceph): client/Client.cc: remove only once used variable
Fix for:
[src/client/Client.cc:4555]: (style) The scope of the variable
'initial_group_count' can be reduced.
Signe...
Danny Al-Gaaf
12:30 PM Revision a84ed870 (ceph): client: use thread local data to track fuse request
When handling an operation, libcephfs code may want to access fuse
request for extra information. by tracking fuse re...
Yan, Zheng
12:30 PM Revision c4ba93a6 (ceph): client: use fuse_req_getgroups() to get group list
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 0eb6d0ba1b65ac0aaffc72a82f07857cc65a6b88)
Yan, Zheng
12:17 PM rgw Bug #13514: RGW Swift API: response for GET/HEAD on Swift's DLO returns wrong ETag
We also hitted by this bug.
Ceph 0.80.9-1~u14.04
Some progress to fix it?
Mike Almateia
12:10 PM devops Feature #14966 (New): add a jenkins job to run tox on paddles pull requests
Loïc Dachary
11:35 AM Backport #14964 (Rejected): infernalis: Objects promoted unnecessarily when deleting from cache
https://github.com/ceph/ceph/pull/7925 Nathan Cutler
11:30 AM Bug #14963 (Resolved): Objects promoted unnecessarily when deleting from cache
https://github.com/ceph/ceph/pull/7537 Nathan Cutler
11:06 AM Revision 45e16d0d (ceph): mon: Monitor: adaptative clock skew detection interval
When in the presence of a clock skew, adjust the checking interval
according to how many rounds have gone by since th...
Joao Eduardo Luis
11:06 AM Revision 17d8ff42 (ceph): mon: Monitor: get rid of weighted clock skew reports
By weighting the reports we were making it really hard to get rid of a
clock skew warning once the cause had been fix...
Joao Eduardo Luis
10:58 AM Revision b0b4b6de (ceph): os/bluestore/BlueStore: Fix bug when calc offset & end whether locate i...
Suppose: bluestore_overlay_max_length == bluestore_min_alloc_size
The orignal code which calc content of written whet...
Jianpeng Ma
10:22 AM Revision cd496158 (ceph): common/obj_bencher.cc: use more readable constant instead of magic number
When clean_up_slow() fails, it returns "-5" which is equal to -EIO.
Change it in source, so it's not confusing for so...
Piotr Dałek
09:17 AM rbd Subtask #13296 (In Progress): Mirroring API + rbd CLI updates for images
Ricardo Dias
01:34 AM rbd Subtask #13296: Mirroring API + rbd CLI updates for images
Correct, the description is from an old design. We are using http://pad.ceph.com/p/rbd_mirror_daemon to track the cu... Jason Dillaman
08:36 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
I created a tracker issue for PR#6698 - it is http://tracker.ceph.com/issues/14958 and it has been staged for backport. Nathan Cutler
03:54 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
Simple reproducer.
$ ceph-deploy new boxenX boxenY
$ ceph-deploy mon create-initial
Move to boxenY
$ sudo s...
Brad Hubbard
08:34 AM Backport #14957 (Rejected): infernalis: segfault from PrebufferedStreambuf::overflow
I created a tracker issue for PR#6698 - it is http://tracker.ceph.com/issues/14958 and it has been staged for backpor... Nathan Cutler
04:56 AM Backport #14957 (New): infernalis: segfault from PrebufferedStreambuf::overflow
Loïc Dachary
04:07 AM Backport #14957: infernalis: segfault from PrebufferedStreambuf::overflow
https://github.com/ceph/ceph/pull/6698 Brad Hubbard
04:02 AM Backport #14957 (Rejected): infernalis: segfault from PrebufferedStreambuf::overflow
Brad Hubbard
08:32 AM Backport #14956 (Rejected): hammer: segfault from PrebufferedStreambuf::overflow
I created a tracker issue for PR#6698 - it is http://tracker.ceph.com/issues/14958 and it has been staged for backpor... Nathan Cutler
04:56 AM Backport #14956 (New): hammer: segfault from PrebufferedStreambuf::overflow
Loïc Dachary
04:08 AM Backport #14956: hammer: segfault from PrebufferedStreambuf::overflow
https://github.com/ceph/ceph/pull/6698 Brad Hubbard
04:00 AM Backport #14956 (Rejected): hammer: segfault from PrebufferedStreambuf::overflow
Brad Hubbard
08:12 AM Revision e014ea88 (ceph): init-ceph: check if /lib/lsb/init-functions exists
On OSX/FreeBSD, /lib/lsb/init-functions does not exist
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked fr...
Yan, Zheng
06:30 AM rgw Bug #14215 (Resolved): rgw: radosgw-admin bucket check --fix not work
Loïc Dachary
06:30 AM rgw Bug #13824 (Resolved): orphans finish segfaults
Loïc Dachary
06:27 AM Bug #14883 (Resolved): osd, tools: various temp objects fixes
Loïc Dachary
06:27 AM Bug #14882 (Resolved): cot: interface fixes and new feature to access the meta collection
Loïc Dachary
06:27 AM Bug #14881 (Resolved): test: Fix failure test to find message anywhere in stderr
Loïc Dachary
06:27 AM Bug #14880 (Resolved): test, tools: Improve ceph-objectstore-tool import error handling and tests
Loïc Dachary
06:27 AM Bug #14879 (Resolved): tools: For ec pools list objects in all shards if the pgid doesn't specify
Loïc Dachary
06:27 AM Bug #14878 (Resolved): tools: clean up errors in ceph-objectstore-tool
Loïc Dachary
06:27 AM Feature #14877 (Resolved): ceph-objectstore-tool improvements
Loïc Dachary
06:27 AM Bug #14875 (Resolved): osd: write journal header by force when journal write close
Loïc Dachary
06:27 AM Bug #14876 (Resolved): Fix --dry-run for many ceph-objectstore-tool operations
Loïc Dachary
06:27 AM Feature #14874 (Resolved): crushtool: send --tree to stdout
Loïc Dachary
06:27 AM Bug #14428 (Resolved): Unable to bring up OSD's after dealing with FULL cluster (OSD assert with ...
Loïc Dachary
06:27 AM Bug #14748 (Resolved): OSD coredumps with leveldb compact on mount = true
Loïc Dachary
06:27 AM Feature #12740 (Resolved): ceph-objetstore-tool: add operations to remove clone ids from a head o...
Loïc Dachary
06:27 AM Bug #12738 (Resolved): scrub bogus results when missing a clone
Loïc Dachary
06:27 AM Feature #12193 (Resolved): OSD's are not updating osdmap properly after monitoring crash
Loïc Dachary
06:27 AM Feature #12038 (Resolved): make rgw_fronends more forgiving of whitespace
Loïc Dachary
06:27 AM Feature #11237 (Resolved): ceph-objectstore-tool needs to export and import the divergent_priors
Loïc Dachary
06:27 AM Feature #11135 (Resolved): ceph-objectstore-tool should let you dump a filestore journal
Loïc Dachary
06:27 AM Bug #10809 (Resolved): ceph-objectstore-tool can exit and lose logging output
Loïc Dachary
06:27 AM Feature #10290 (Resolved): ceph_objectstore_tool should support --dry-run option
Loïc Dachary
06:27 AM Feature #10098 (Resolved): wanted: command to clear 'incomplete' PGs
Loïc Dachary
06:25 AM Backport #14961 (Resolved): hammer: PK11_DestroyContext() is called twice if PK11_DigestFinal() f...
https://github.com/ceph/ceph/pull/7922 Loïc Dachary
06:25 AM Backport #14960 (Closed): infernalis: PK11_DestroyContext() is called twice if PK11_DigestFinal()...
https://github.com/ceph/ceph/pull/7920 Loïc Dachary
06:19 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
Since there is no satisfactory solution that would be both well tested and generic enough, I'm tempted to rule this a... Loïc Dachary
05:53 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
Original description
~# ceph-deploy osd prepare node-9:/dev/sdc3:/dev/disk/by-id/ata-INTEL_SSDSC2BW240A4_PHDA41030...
Loïc Dachary
05:39 AM Backport #14583 (Resolved): hammer: pid file that was deleted after ceph restart leads to osd pro...
Loïc Dachary
05:05 AM Revision 20b2a741 (ceph): Merge pull request #7671 from tchaikov/wip-14583-hammer
hammer: global/pidfile: do not start two daemons with a single pid-file
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
04:59 AM Revision e588f1d2 (ceph): Merge pull request #834 from ceph/wip-14077-hammer
add divergent priors tests
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
04:58 AM Backport #14076 (Resolved): hammer: ceph-objetstore-tool: add operations to remove clone ids from...
Loïc Dachary
04:58 AM Backport #14077 (Resolved): hammer: scrub bogus results when missing a clone
Loïc Dachary
04:57 AM Backport #14884 (Resolved): hammer: osd, tools: various temp objects fixes
Loïc Dachary
04:57 AM Backport #14885 (Resolved): hammer: cot: interface fixes and new feature to access the meta colle...
Loïc Dachary
04:57 AM Backport #14886 (Resolved): hammer: test: Fix failure test to find message anywhere in stderr
Loïc Dachary
04:56 AM Backport #14887 (Resolved): hammer: test, tools: Improve ceph-objectstore-tool import error handl...
Loïc Dachary
04:56 AM Backport #14888 (Resolved): hammer: tools: For ec pools list objects in all shards if the pgid do...
Loïc Dachary
04:56 AM Backport #14889 (Resolved): hammer: tools: clean up errors in ceph-objectstore-tool
Loïc Dachary
04:56 AM Backport #14890 (Resolved): hammer: ceph-objectstore-tool improvements
Loïc Dachary
04:56 AM Backport #14891 (Resolved): hammer: Fix --dry-run for many ceph-objectstore-tool operations
Loïc Dachary
04:56 AM Backport #14892 (Resolved): hammer: osd: write journal header by force when journal write close
Loïc Dachary
04:56 AM Backport #14893 (Resolved): hammer: crushtool: send --tree to stdout
Loïc Dachary
04:56 AM Backport #14894 (Resolved): hammer: OSD's are not updating osdmap properly after monitoring crash
Loïc Dachary
04:56 AM Backport #14895 (Resolved): hammer: ceph-objectstore-tool needs to export and import the divergen...
Loïc Dachary
04:56 AM Backport #14896 (Resolved): hammer: ceph-objectstore-tool should let you dump a filestore journal
Loïc Dachary
04:56 AM Backport #14897 (Resolved): hammer: ceph-objectstore-tool can exit and lose logging output
Loïc Dachary
04:55 AM Backport #14898 (Resolved): hammer: ceph_objectstore_tool should support --dry-run option
Loïc Dachary
04:55 AM Backport #14899 (Resolved): hammer: wanted: command to clear 'incomplete' PGs
Loïc Dachary
04:51 AM Revision c1bc048d (ceph): Merge pull request #7702 from ceph/wip-14077-hammer
hammer: scrub bogus results when missing a clone
Reviewed-by: Martin Palma <martin@palma.bz>
Reviewed-by: Wei-Chung ...
Loïc Dachary
04:39 AM Stable releases Tasks #14692: hammer v0.94.7
h3. upgrade... Loïc Dachary
04:36 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rbd... Loïc Dachary
04:34 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rados ... Loïc Dachary
04:29 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
04:14 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
http://pulpito.ceph.com/loic-2016-03-01_21:05:09-rados-hammer-backports---basic-multi/36771/ Loïc Dachary
04:10 AM Bug #13829 (Resolved): config set with negative value results in "error setting 'filestore_merge_...
Fixed in commit 389ecbbc2a9d7d4d334ea31a5c4120e9acc1b9aa Brad Hubbard
04:06 AM Bug #14958 (Resolved): PK11_DestroyContext() is called twice if PK11_DigestFinal() fails
Fixed in https://github.com/ceph/ceph/pull/6698 - specifically, https://github.com/ceph/ceph/commit/e9e05333ac7c64758... Nathan Cutler
03:53 AM devops Fix #14828: ceph Resource Agent does not work with systemd
*master PR*: https://github.com/ceph/ceph/pull/7894 Nathan Cutler
03:46 AM Revision acfc06d9 (ceph): ceph.spec.in: use %{_prefix} for ocf instead of hardcoding /usr
This patch aligns the spec file with src/ocf/Makefile.am, which
installs the resource agents in $(prefix)/lib/ocf.
S...
Nathan Cutler
03:46 AM Revision 9acb00ec (ceph): ceph.spec.in: do not install Ceph RA on systemd platforms
The Ceph Resource Agent (RA) wraps the Ceph init script and is incompatible
with systemd.
http://tracker.ceph.com/is...
Nathan Cutler
03:39 AM devops Bug #14785 (Rejected): rpm: %_with_ocf handling in configure broken in OBS
I was setting _with_ocf to "1" in the Project Config, whereas %configure was expecting it to be set to "--with-ocf" -... Nathan Cutler
03:15 AM Revision 22417925 (ceph): Merge pull request #7098 from liewegas/wip-file-layout
mds, client: add namespace to file_layout_t (previously ceph_file_layout)
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
03:03 AM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
@Yuri, so the test passes on latest jewel, but fails on wip-jewel-no-package-split? Weird.
Nathan Cutler
01:06 AM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
run on wip-jewel-no-package-split
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-02_19:34:51-upgrade:hamm...
Yuri Weinstein
03:03 AM Bug #9744: cephx: verify_reply couldn't decrypt with error: error decoding block for decryption
The crash associated with the duplicate bug is fixed by commit e9e05333ac7c64758bf14d80f6179e001c0fdbfd Brad Hubbard
03:02 AM Bug #13527: moniter segmentation fault
This crash is fixed by commit e9e05333ac7c64758bf14d80f6179e001c0fdbfd Brad Hubbard
02:48 AM Bug #14954: BlueStore: met assert when write size==bluestore_overlay_max_length
Fixed by this https://github.com/ceph/ceph/pull/7892 jianpeng ma
02:15 AM Bug #14954 (Rejected): BlueStore: met assert when write size==bluestore_overlay_max_length
Suppose set bluestore_overlay_max_length == bluestore_min_alloc_size && bluestore_overlay_max > 0.
write(bluestore_m...
jianpeng ma
02:38 AM CephFS Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
The file by default goes to a file called "cachedump.*", like it says. I think it tends to go in /, but I don't remem... Greg Farnum
01:17 AM Bug #14814: os/filestore: mkfs may return OK even if it encounters internal error.
https://github.com/ceph/ceph/pull/7704 xie xingguo
01:15 AM Bug #14827: os/filestore: copy_range may return OK if fail to verify src/dst offset
https://github.com/ceph/ceph/pull/7711 xie xingguo
01:15 AM Bug #14817: os/filestore: result code of fstat overwritten
https://github.com/ceph/ceph/pull/7711 xie xingguo
01:14 AM Bug #14872: OSD: wrong return-type of find_osd_on_ip()
https://github.com/ceph/ceph/pull/7812 xie xingguo
01:14 AM Bug #14921: OSD:wrong overload of "==" operator for pg_stat_t
https://github.com/ceph/ceph/pull/7842 xie xingguo
01:06 AM Revision c5bd4858 (ceph): Merge pull request #852 from ceph/wip-ceph-ansible
ceph-ansible: Add openstack hints for volumes Yuri Weinstein
12:36 AM Revision 33f68b88 (ceph): Revert "test/common/test_weighted_priority_queue Fix the unit tests sin...
This reverts commit 3a6d6279fe386f9591fdbd8c38fe2fb059dbc398.
Since we added round robin back into the queue, make s...
Robert LeBlanc
12:36 AM Revision e13a4b10 (ceph): test: common/test_weighted_priority_queue Add Some More Corner Cases
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com> Robert LeBlanc
12:36 AM Revision de001bd9 (ceph): osd: common/WeightedPriorityQueue.h Re-add Round Robin between classes
Fixes corner case where a single client can starve out other clients.
This enables round robin between all clients so...
Robert LeBlanc

03/02/2016

11:34 PM Revision b3bcf9d1 (ceph): ceph-ansible: Add openstack hints for volumes
3x20GB per instance
Signed-off-by: Zack Cerza <zack@redhat.com>
Zack Cerza
11:21 PM Bug #14810 (Resolved): "FileStore.cc: 2855: FAILED assert(0 == "unexpected error")" in powercycle...
Samuel Just
10:45 PM Bug #14952: New pools have bogus "stuck inactive/unclean" HEALTH_ERR messages until they are firs...
I think the pgs should be deemed stuck based on time since creation, that would make sense. Samuel Just
04:16 PM Bug #14952 (Resolved): New pools have bogus "stuck inactive/unclean" HEALTH_ERR messages until th...

(In master, on a vstart cluster but presumably happens on real clusters too)
Right after creating some pools:
...
John Spray
10:43 PM Bug #14933 (Resolved): osd/PGLog.cc: 569: FAILED assert(log.head >= olog.tail && olog.head >= log...
I see in the log a rados bench running in parallel with mark_all_unfound_lost calls. The latter eventually call shar... Samuel Just
10:41 PM Revision 26f9d694 (ceph): rgw: add support for overriding Content-Disposition in GET of Swift API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:41 PM Revision c857fcfe (ceph): rgw: ONLY refactor dump_object_metadata() of rgw_rest_swift.cc.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:41 PM Revision a2d58fc1 (ceph): rgw: TempURL of Swift URL does support Content-Disposition override.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:26 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
side-by-side runs before and after the split code, same test
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-201...
Yuri Weinstein
06:27 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
Last run on jewel: http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2016-03-02_02:52:36-upgrade:hammer-x-je... Yuri Weinstein
04:10 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
On pre-packadges split code tests passed http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-01_23:53:26-upgra... Yuri Weinstein
02:18 AM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
The ceph SHA1 for this job is "d6031c2 Merge pull request #7700 from SUSE/wip-14811"
As of that SHA1 the rados-cla...
Nathan Cutler
10:14 PM Revision 83e77cf1 (ceph): Bluestore.h:Added 'override' to virtual functions
Signed-off-by: Michal Jarzabek <stiopa@gmail.com> Michal Jarzabek
10:06 PM rbd Subtask #13296: Mirroring API + rbd CLI updates for images
Jason Dillaman wrote:
> A new "mirroring enabled" field should be added to the RBD image header. Mirroring should n...
Ricardo Dias
05:37 PM rbd Subtask #13296: Mirroring API + rbd CLI updates for images
Jason Dillaman
08:59 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Mon and osd logs uploaded to support case 01549888. They're too big to upload here. Steve Taylor
08:42 PM rgw Bug #12420: "[ FAILED ] cls_rgw.gc_defer"
How do we get to the logs produced by the failed test? Nathan Cutler
04:59 PM rgw Bug #12420: "[ FAILED ] cls_rgw.gc_defer"
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-02_10:02:04-upgrade:hammer-x-jewel-distro-basic-openst... Yuri Weinstein
08:42 PM Revision d793c6ab (ceph): test/rgw: add multisite test for meta sync across periods
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
08:00 PM Bug #13453 (Resolved): backfill pushes do not appear to increment the recovery rate counters
b04e17687fcb4609a8c6c3623bd0786116733465 Samuel Just
07:52 PM Bug #14498: cephx error: NSS AES final round failed: -8190 while bootstrapping containerised mon ...
2016-01-25 10:09:02.058557 7fef3c54f700 0 cephx server osd.25: couldn't find entity name: osd.25
That looks a lot ...
Samuel Just
07:48 PM Bug #14797: osd: add all backfill osd to backfill_targets
Hmm, I don't have 33ff281d60c825adf1889eb67c4fed280ba0ea6f. Can you push a branch corresponding to that commit? Samuel Just
07:41 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Hmm. Can you do the same for each from 5970 to 5981 and attach a .tar with those? Ilya Dryomov
05:48 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Hello
Ready, result in attachment
Ruslan Usifov
05:25 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Hi Ruslan,
Can you do
$ ceph osd getmap 5982 >osdmap.5982
and attach that file?
Ilya Dryomov
01:55 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
Ilya Dryomov
07:08 PM Revision 045ad3d2 (ceph): Merge pull request #7849 from ceph/wip-cmake
Wip cmake Casey Bodley
06:37 PM Revision d8cfef9d (ceph): cmake: simplified heap_profiler_objs dependencies
The heap_profiler object library only needs to be
added to mon,mds, and osd instead of the numerous
targets it is par...
Ali Maredia
05:43 PM rbd Bug #14953 (Rejected): can add 'rbd lock' to format 1 images
this is on hammer 0.94.5, i think its deprecated now recently but still want to document it
1) 2 node ceph cluste...
Vasu Kulkarni
05:37 PM rbd Subtask #14869 (In Progress): journal library should re-use thread pool and timer
Jason Dillaman
05:35 PM rbd Subtask #14413 (In Progress): Pull full image from remote peer when out-of-sync
Jason Dillaman
05:29 PM Revision 3e41cfde (ceph): client/Inode: fix has_dir_layout
Compare to default file_layout_t() -- not zeroed memory.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
05:26 PM Revision fb1b291e (ceph): Merge pull request #7867 from SUSE/wip-14940
RPM: move %post(un) ldconfig calls to ceph-base
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Reviewed-by: Boris Rant...
Boris Ranto
05:19 PM rbd Subtask #14663 (Fix Under Review): Integrate librbd with journal tag allocation
*PR*: https://github.com/ceph/ceph/pull/7884 Jason Dillaman
05:14 PM Revision 279826d3 (ceph): os/filestore/FileJournal: set block size via config option
We were setting the block_size as the MIN of the min size (4096) and the
block size reported for the journal file/dev...
Sage Weil
05:08 PM Revision e09863b4 (ceph): Merge pull request #7869 from rzarzynski/wip-rgw-aws4-puthash
rgw: calculate payload hash in RGWPutObj_ObjStore only when necessary.
Reviewed-by: Orit Wasserman <owasserm@redhat....
Orit Wasserman
04:47 PM Bug #14711 (Can't reproduce): OSD crashes with Suicide timeout due to timeout on FileStore::op_tp...
Samuel Just
04:17 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
> The bug is caused by a patch (mis)cherry-picked from master to Hammer.
For the record the patch in question is h...
Alexey Sheplyakov
02:54 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Nathan,
> Is this bug not present in master?
No. The bug is caused by a patch (mis)cherry-picked from master to...
Alexey Sheplyakov
04:16 PM Revision b3d5c39c (ceph): Merge pull request #851 from ceph/wip-ceph-ansible
ceph-ansible: Install ceph-test Yuri Weinstein
03:16 PM Backport #13288 (Fix Under Review): hammer: stuck recovering, unfound hit set due to removing it ...
* -https://github.com/ceph/ceph-qa-suite/pull/850-
* -https://github.com/ceph/ceph-qa-suite/pull/849-
* https://git...
Kefu Chai
01:40 PM Backport #13288: hammer: stuck recovering, unfound hit set due to removing it while !active
* mon.c v0.94, (e61c4f093f88e44961d157f65091733580cea79a)
* osd.1
* before upgrade v0.94, (e61c4f093f88e44961d15...
Kefu Chai
02:52 PM Bug #14934: common/config_opts.h: audit OPT_INT/OPT_UINT and handle incorrect signed uint
I can take a look into this Joao.
Daniel Oliveira
02:31 PM Bug #14856 (Resolved): Clang removes dead code....
Nathan Cutler
02:22 PM Revision 2786f0bf (ceph): Merge remote-tracking branch 'gh/jewel'
Sage Weil
02:06 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
Nathan Cutler wrote:
> @Peter - can you upgrade to 9.2.1 and try to reproduce again?
Most possibly I cannot, sinc...
Peter Gervai
01:31 PM Revision 67696f0b (ceph): Merge pull request #7612 from liewegas/wip-buffer-combined
buffer: raw_combined allocations buffer and ref count together
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Sage Weil
01:30 PM Bug #14804 (Resolved): Common/TrackedOp: inaccurate count for total slow requests
Sage Weil
01:30 PM Revision c4f68ade (ceph): Merge pull request #7690 from xiexingguo/xxg-wip-14804
common/TrackedOp: fix inaccurate counting for slow requests
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
01:30 PM Bug #14814 (Resolved): os/filestore: mkfs may return OK even if it encounters internal error.
Sage Weil
01:29 PM Revision b7a3217b (ceph): Merge pull request #7704 from xiexingguo/xxg-wip-14814
osd: filestore: fix wrong scope of result code for error cases during mkfs
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:29 PM Bug #14872 (Resolved): OSD: wrong return-type of find_osd_on_ip()
Sage Weil
01:29 PM Revision c25a8a22 (ceph): Merge pull request #7812 from xiexingguo/xxg-wip-14872
osd: fix wrong return type of find_osd_on_ip()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:28 PM Revision 8889d0c7 (ceph): Merge pull request #7815 from branch-predictor/bp-conditional-crc
msg/async: don't calculate msg header crc when not needed
Reviewed-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
01:28 PM Bug #14827 (Resolved): os/filestore: copy_range may return OK if fail to verify src/dst offset
Sage Weil
01:28 PM Bug #14817 (Resolved): os/filestore: result code of fstat overwritten
Sage Weil
01:28 PM Revision 1137c4ea (ceph): Merge pull request #7711 from xiexingguo/xxg-wip-14817
osd: filestore: fix result code overwritten for clone
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:27 PM Revision 9576b0c2 (ceph): Merge pull request #7790 from tchaikov/wip-log-segv
log: segv in a portable way
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Sage Weil
01:26 PM Bug #14921 (Resolved): OSD:wrong overload of "==" operator for pg_stat_t
Sage Weil
01:26 PM Revision e6fed056 (ceph): Merge pull request #7842 from xiexingguo/xxg-wip-14921
osd: fix overload of '==' operator for pg_stat_t
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:18 PM Bug #14950: keyring permisions for mon deamon
Note: the PR containing the above commit is https://github.com/ceph/ceph/pull/7880 Nathan Cutler
11:40 AM Bug #14950: keyring permisions for mon deamon
https://github.com/ceph/ceph/commit/c2f91a8ce46974a72b960b7cb25af3d089fbb80d Owen Synge
11:09 AM Bug #14950 (Resolved): keyring permisions for mon deamon
The command:
sudo ceph-mon --cluster ceph --mkfs -i ceph-node3 --keyring /var/lib/ceph/tmp/ceph-ceph-node3.mon.key...
Owen Synge
11:34 AM rgw Bug #14951 (Resolved): Misleading error message when you delete a zone from a zonegroup
Trying the new rgw multisite configuration.
$ radosgw-admin zone create --rgw-zonegroup=us --rgw-zone=us-1 --acces...
Shilpa MJ
11:31 AM Revision 71c4e525 (ceph): [MON] Fixed calculation of %USED. Now it is shows (space used by all re...
Signed-off-by: Adam Kupczyk akupczyk@mirantis.com Adam Kupczyk
11:27 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
Interesting :-) Are you using the patch that you proposed at https://github.com/ceph/ceph/pull/7123 ? Or another vers... Loïc Dachary
10:27 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
@Loic Dachary
> would you be so kind as to push said similar patch in a pull request?
Actually that patch is a ...
Alexey Sheplyakov
11:15 AM Revision c2f91a8c (ceph): keyring permissions for mon daemon
The command:
sudo ceph-mon --cluster ceph --mkfs -i $NODE_NAME --keyring $PATH_MON_KEYRING
Writes a new keyring wit...
Owen Synge
09:42 AM Bug #14844: rpm package building fails if the build machine has lttng and babeltrace development ...
Ken, thanks for your work! the packages install just fine in my centos7 box. 1 more karma needed for them. Kefu Chai
09:18 AM Revision cdf4486a (ceph): msg: async: fix result code
The set_nonblock() is not a standard system call, so
we don't have to reset the result code to errno on error.
Signe...
xie xingguo
09:10 AM Revision eb5f00a4 (ceph): msg: async: reset result code to errno for better tracing
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
09:06 AM Revision 2242988c (ceph): msg: async: fix wrong return code if out of memory
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
08:25 AM rgw Bug #14949 (Duplicate): radosgw-admin link failure
... Flex Gao
07:59 AM devops Backport #14945 (In Progress): infernalis: redhat-lsb-core dependency was dropped, but is still n...
Nathan Cutler
04:41 AM devops Backport #14945 (Rejected): infernalis: redhat-lsb-core dependency was dropped, but is still needed
https://github.com/ceph/ceph/pull/7877 Loïc Dachary
07:40 AM devops Backport #14946 (In Progress): hammer: redhat-lsb-core dependency was dropped, but is still needed
Nathan Cutler
04:41 AM devops Backport #14946 (Resolved): hammer: redhat-lsb-core dependency was dropped, but is still needed
https://github.com/ceph/ceph/pull/7876 Loïc Dachary
07:39 AM Revision 57264633 (ceph): packaging: lsb_release build and runtime dependency
The lsb_release executable is being run in multiple places, not least in
src/common/util.cc, which calls it via shell...
Nathan Cutler
06:40 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
My theory is that this error happens because something changed in the packages of centos 7.2. we know that tcmalloc c... Loïc Dachary
04:52 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
Loïc Dachary
04:51 AM Backport #14799 (New): hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.s...
Same occurrence exactly http://pulpito.ceph.com/loic-2016-02-28_21:51:29-rados-hammer-backports---basic-multi/32565 s... Loïc Dachary
04:50 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
Loïc Dachary
05:35 AM Backport #14948 (In Progress): hammer: mon: Enable Pg_prime By Default
Loïc Dachary
05:30 AM Backport #14948 (Rejected): hammer: mon: Enable Pg_prime By Default
https://github.com/ceph/ceph/pull/7848 Loïc Dachary
05:28 AM Feature #14947 (Resolved): mon: Enable Pg_prime By Default
https://github.com/ceph/ceph/pull/7838 Loïc Dachary
05:28 AM CephFS Bug #14805: Hadoop tests failing with EPERM
tests passed
http://pulpito.ceph.com/zyan-2016-03-01_20:05:19-hadoop-jewel-testing-basic-mira/
Zheng Yan
04:57 AM Bug #13563: "[ FAILED ] LibRadosAioEC.RoundTripSparseReadPP" in upgrade:hammer-x-infernalis-dis...
I thought I found the same bug but it turns out to be different http://tracker.ceph.com/issues/15009 Loïc Dachary
04:33 AM rbd Subtask #14414 (Fix Under Review): Add new "exclusive lock released" journal event to librbd
https://github.com/ceph/ceph/pull/7818 Josh Durgin
04:30 AM rbd Subtask #14161 (Resolved): Serialize snap create, snap rollback, and resize operations for journa...
https://github.com/ceph/ceph/pull/7019 Josh Durgin
04:23 AM rbd Subtask #14419 (Resolved): RBD mirroring settings should be moved to new pool object
https://github.com/ceph/ceph/pull/7620 Josh Durgin
04:21 AM rbd Feature #2468 (Resolved): librbd: provide a way for a user to flush and invalidate the cache
Josh Durgin
04:18 AM rbd Bug #14822 (Resolved): Journal replay needs to support replaying successful maintenance ops
Josh Durgin
04:18 AM rbd Cleanup #14809 (Resolved): ImageWatcher unwatch and flush should use async librados methods
Josh Durgin
04:17 AM rbd Tasks #14550 (Resolved): Deprecate format v1 RBD images
Josh Durgin
04:16 AM rbd Tasks #14551 (Resolved): Update RBD default features
Josh Durgin
03:22 AM Revision 389ecbbc (ceph): Merge pull request #7390 from badone/wip-13829
common: Allow OPT_INT settings with negative values
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Kefu Chai
03:14 AM Bug #14929: osd: can only reduce the weight of osd, the use of "ceph osd reweight-by-utilization"
https://github.com/ceph/ceph/pull/7853 huanwen ren
02:18 AM Revision 6e9f049b (ceph): Merge pull request #7854 from yehudasa/wip-authors-update
AUTHORS: update email
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
01:54 AM Bug #14837 (Resolved): OSD: race condition during update heartbeat_need_update
https://github.com/ceph/ceph/pull/7739 xie xingguo
01:53 AM devops Bug #14944 (Rejected): libtool: install: warning: `librados.la' has not been installed in `/usr/l...
As part of the build process, the following command is run:... Nathan Cutler
01:53 AM Bug #14786: OSD: potentially leave fuse_store hung if we fail to init osd
https://github.com/ceph/ceph/pull/7677 xie xingguo
01:18 AM Revision 0c965e76 (ceph): Merge pull request #7841 from dillaman/wip-14550
rbd: deprecate image format 1
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:18 AM Revision 2da7196b (ceph): Merge pull request #7839 from dillaman/wip-14809
librbd: remove last synchronous librados calls from open/close state machine
Reviewed-by: Josh Durgin <jdurgin@redha...
Josh Durgin
01:18 AM Revision a7470c80 (ceph): Merge pull request #7846 from dillaman/wip-14551
rbd: update default image features
Conflicts:
PendingReleaseNotes (trivial)
Josh Durgin
01:17 AM Revision 928c2e4d (ceph): Merge pull request #7785 from dillaman/wip-14822
librbd: journal replay needs to support re-executing maintenance ops
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:17 AM Revision 939984f7 (ceph): Merge pull request #7776 from dillaman/wip-librbd-journal-tweaks
journal: improve commit position tracking
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:00 AM Revision effcd77a (ceph): BlueStore.h:Remove unneeded includes
Signed-off-by: Michal Jarzabek <stiopa@gmail.com> Michal Jarzabek

03/01/2016

11:11 PM Revision 61026c87 (ceph): cmake: Turned LTTng OFF
This is temporary, until a way to stop repetitive
unecessary generation of headerfiles is figured out.
Signed-off-by...
Ali Maredia
10:53 PM Revision 597aaba4 (ceph): configure.ac: cython is used for more than librbd now
Signed-off-by: Josh Durgin <jdurgin@redhat.com> Josh Durgin
10:21 PM Bug #14942 (Won't Fix): centos packages issue for dumpling in upgrade:dumpling-firefly-x-hammer-d...
Can we stop running this suite?
As dumpling and firefly releases EOL
Run: http://pulpito.ovh.sepia.ceph.com:808...
Yuri Weinstein
09:58 PM Revision b9169538 (ceph): Merge pull request #848 from ceph/wip-ceph-ansible
ceph-ansible suite improvements Yuri Weinstein
09:58 PM Revision 83871147 (ceph): Install ceph-test
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
09:52 PM rbd Feature #14909 (New): Journal replay should support multiple tag class streams
Jason Dillaman
09:41 PM devops Bug #14941 (Resolved): ceph-{mds,mon,osd} packages need scriptlets with systemd code
Following the recent package split we now have separate packages for MDSs, MONs, and ODSs, and each daemon has its ow... Nathan Cutler
09:27 PM Revision 13a5aac6 (ceph): RPM: move scriptlets from ceph to ceph-base
This addresses the following RPMLINT error:
ceph-base.x86_64: E: library-without-ldconfig-postun (Badness:
300) /usr...
Nathan Cutler
09:07 PM Revision c6f317b4 (ceph): AUTHORS: update email
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
08:55 PM Revision 55eeee93 (ceph): rgw: calculate payload hash in RGWPutObj_ObjStore only when necessary.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:51 PM Revision c1e41afb (ceph): Merge pull request #7767 from athanatos/wip-sam-journal-throttle-4
osd: filestore: restructure journal and op queue throttling
Reviewed-by: Samuel Just <sjust@redhat.com>
Samuel Just
08:31 PM devops Bug #14940 (Resolved): Missing ldconfig in %post/%postun following package split
Following the package split, libraries requiring ldconfig in %post/%postun are now packaged in ceph-base, which has n... Nathan Cutler
07:49 PM Revision 4a450ca8 (ceph): Disable rbd_cli_tests for now
They don't seem to ever fail.
Signed-off-by: Zack Cerza <zack@redhat.com>
Zack Cerza
07:47 PM Revision 6df45fd5 (ceph): Add ceph-deploy_hello_world.sh
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
06:33 PM Bug #14844: rpm package building fails if the build machine has lttng and babeltrace development ...
I'd really like to get lttng and babeltrace into EPEL 7. This bug prompted me to go ahead and do builds for that.
...
Ken Dreyer
06:02 AM Bug #14844 (Fix Under Review): rpm package building fails if the build machine has lttng and babe...
https://github.com/ceph/ceph/pull/7857 Kefu Chai
06:29 PM Revision da84cbad (ceph): os/kstore: Latency breakdown in each stage of transaction for Kstore
Signed-off-by: James Liu <james.liu@ssi.samsung.com> James Liu
05:55 PM Revision 677d2906 (ceph): librados: race condition on aio_notify completion handling
Wait for both the notify_finish callback and the standard RADOS ack
callback before completing the associated AioComp...
Jason Dillaman
05:49 PM Bug #14939 (Resolved): "RefCountedObj.h: 31: FAILED assert(nref.read() == 0)" in smoke-master-dis...
3254e498864c0ee5ba4cbcacd97738d3e4bea29c Samuel Just
05:40 PM Bug #14939: "RefCountedObj.h: 31: FAILED assert(nref.read() == 0)" in smoke-master-distro-basic-o...
Also in run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-28_05:00:01-smoke-master-distro-basic-openstac... Yuri Weinstein
05:29 PM Bug #14939 (Resolved): "RefCountedObj.h: 31: FAILED assert(nref.read() == 0)" in smoke-master-dis...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-29_05:00:04-smoke-master-distro-basic-openstack/
Job:...
Yuri Weinstein
05:45 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
From IRC:... Yuri Weinstein
05:11 PM Bug #14927: "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-distro-basic-...
Also in run:
http://pulpito.ceph.com/teuthology-2016-02-28_02:10:01-upgrade:hammer-x-jewel-distro-basic-vps/31527/
...
Yuri Weinstein
05:27 PM Bug #14938 (Won't Fix): [hammer] repeated puts on an object can violate the pool quota
Actually, this is fixed in master. It's too complicated to backport imho. Marking won't fix. Samuel Just
05:21 PM Bug #14938 (Won't Fix): [hammer] repeated puts on an object can violate the pool quota
This is easy to reproduce in hammer. It seems that we don't throw out the cached obc object info and on the second p... Samuel Just
05:09 PM devops Bug #14936: "Sub-process /usr/bin/dpkg returned an error code" in e:infernalis-x-jewel-distro-bas...
Also in run: http://pulpito.ceph.com/teuthology-2016-02-28_02:10:01-upgrade:infernalis-x-jewel-distro-basic-vps/
Job...
Yuri Weinstein
04:32 PM devops Bug #14936 (Can't reproduce): "Sub-process /usr/bin/dpkg returned an error code" in e:infernalis-...
Run: http://pulpito.ceph.com/teuthology-2016-02-29_02:10:12-upgrade:infernalis-x-jewel-distro-basic-vps/
Jobs: ['340...
Yuri Weinstein
05:02 PM Bug #14935: "[ FAILED ] ClsHello.Filter" in upgrade:infernalis-x-jewel-distro-basic-vps
And in run:
http://pulpito.ceph.com/teuthology-2016-02-29_02:10:12-upgrade:hammer-x-jewel-distro-basic-vps/
Job: 34...
Yuri Weinstein
04:23 PM Bug #14935 (Duplicate): "[ FAILED ] ClsHello.Filter" in upgrade:infernalis-x-jewel-distro-basic...
Run: http://pulpito.ceph.com/teuthology-2016-02-29_02:10:12-upgrade:infernalis-x-jewel-distro-basic-vps/
Job: 34109
...
Yuri Weinstein
04:47 PM Revision 97d80690 (ceph): Merge pull request #843 from ceph/wip-list-inconsistent-obj
tasks/scrub_test: match the NOSNAP with "head"
Reviewed-by: Samuel Just <sjust@redhat.com>
Samuel Just
04:37 PM Revision ddf5c2b6 (ceph): osd: add sure and no-increasing options to reweight-by-*
Add a --no-increasing option to reweight-by-* which can be used to only decrease
OSD weights without increasing any. ...
Dan van der Ster
04:37 PM Revision 1a6ad505 (ceph): test: add simple test for new reweight-by-* options
Test validity of --no-increasing and --yes-i-really-mean-it.
Signed-off-by: Dan van der Ster <daniel.vanderster@cern...
Dan van der Ster
04:37 PM Revision 6f0a1fb6 (ceph): osd: add mon_reweight_max_change option which limits reweight-by-*
Add a configurable mon_reweight_max_change which limits be default
the reweight-by-* commands to only change an OSDs ...
Dan van der Ster
04:37 PM Revision 3aa0ccef (ceph): osd: add mon_reweight_max_osds to limit reweight-by-* commands
Add configurable mon_reweight_max_osds which limits the number
of OSDs modified each time reweight-by-* is called (by...
Dan van der Ster
04:33 PM rbd Subtask #14937 (Resolved): Cloned images must only be bootstrapped after parent image successfull...
Jason Dillaman
04:18 PM Revision 8e728fca (ceph): messages/MClientCaps: fix decoding
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
04:18 PM Revision a524df2f (ceph): mds: properly purge backtrace object
backtrace objects are always in default namespace
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
04:18 PM Revision 00a13942 (ceph): mds: fix inodestat size calculation
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
04:18 PM Revision 72ff3421 (ceph): mds: deny access to file with pool_ns layout if feature is missing
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
04:18 PM Revision c31e94d3 (ceph): qa/workunits/fs/misc/layout_vxattrs: test layout.pool_namespace
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:18 PM Revision efb4a83f (ceph): fs_types: file_layout_t: convert pool -1 (undefined) to 0 in legacy enc...
Old code assumes that fl_pg_pool == 0 means the pool is not defined, while
file_layout_t uses -1. Translate between ...
Sage Weil
04:18 PM Revision a2d42d55 (ceph): mds: don't break compatibility of MClientCaps/MClientReply
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
04:18 PM Revision 9c7669b9 (ceph): mon/MDSMonitor: prevent pool 0 from being used as a data pool
Pool 0 means no change or default in the legacy ceph_file_layout in the
layout ioctl and file create arguments. Preve...
Sage Weil
04:18 PM Revision 00850a67 (ceph): mds: deny access to directories with pool_ns layouts if feature is missing
If the client feature is missing, given them EIO. Change check_access to
return an error code to distinguish this fr...
Sage Weil
04:18 PM Revision 7f47cd76 (ceph): mds/MDSMap: add file layout v2 incompat feature
The existing MDSMonitor machinations already add this to the MDSMap to
boot out old MDS's.
Signed-off-by: Sage Weil ...
Sage Weil
04:18 PM Revision fafb1421 (ceph): fix init of new fields in MCLientCaps
Sage Weil
04:18 PM Revision e7ead6a5 (ceph): mds/Locker: fix Session leak on access denial
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:18 PM Revision 1de6e940 (ceph): mds/Server: fix whitespace
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:18 PM Revision 99f1f647 (ceph): struct ceph_file_layout -> file_layout_t
- drop the global
- do not memset!
- encode with features
- field names are different
- use get_period() method where...
Sage Weil
04:18 PM Revision 386d7c6b (ceph): mds: allow adjustment of layout.pool_namespace vxattr
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:18 PM Revision e0ad6517 (ceph): client: expose layout.pool_namespace vxattr
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:17 PM Revision e750f48c (ceph): messages/MClientCaps: avoid fixed struct for encoding
At least for new clients.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:17 PM Revision 2752eeef (ceph): mds: make inode_t, old_inode_t featureful
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:17 PM Revision 162ca5bc (ceph): libradosstriper: move default stripe parameters inline
The extern is going away.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:17 PM Revision 826e8d01 (ceph): mds/MDSMap: cache up_features; fix logic
& these, not | them.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:17 PM Revision 7dcf39f7 (ceph): mds: pass features to various CInode encoders and helpers
We'll need this shortly.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:17 PM Revision 0b1f7f59 (ceph): messages/MClientReply: stop using ceph_mds_reply_inode struct to unpack
Decode directly.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
04:17 PM Revision ff606bf4 (ceph): mds: encode inode reply information directly
Drop the ceph_mds_reply_inode struct and encode directly. Note
that we already decode directly to InodeStat in MClie...
Sage Weil
04:16 PM Revision 0cd1b941 (ceph): declare Formatter for everyone
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 98220813 (ceph): add fs_types.h, with file_layout_t
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 4ad8f725 (ceph): mds/MDSMap: add features to MDSMap's mds_info_t
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision e08dd70d (ceph): mds,mon: include features in beacon messages, MDSMap
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 358cce1e (ceph): mds: pass features to LogEvents, EMetaBlob
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 4cf4f8dd (ceph): ceph-dencoder: TYPE_FEATUREFUL_NOCOPY
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision bdae5bf3 (ceph): include/compact_map: featureful encoders, too
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 7b961ff1 (ceph): include/encoding: featureful encoder for list of shared_ptrs
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:16 PM Revision 58a00e01 (ceph): qa/workunits/fs/misc/layout_vxattr.sh: detect data pool name
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
04:07 PM Revision 86b7a830 (ceph): os/bluestore: for _clone, first check source-object whether has extents.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
03:57 PM Revision b0f692d7 (ceph): os/bluestore: print Enode::hash w/ hex format.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
03:53 PM Revision 7c4f37dc (ceph): os/bluestore: make _clone work when object has overlay data.
Don't forget copy overlay data when do _clone.
Because bluestore_overlay_max_length & bluestore_overmay_max maybe
cha...
Jianpeng Ma
03:40 PM devops Bug #14906 (Pending Backport): redhat-lsb-core dependency was dropped, but is still needed
Nathan Cutler
03:35 PM Revision cc7f9ec6 (ceph): Merge pull request #7823 from SUSE/wip-14906
packaging: add lsb-release dependency for SUSE and Debian
Reviewed-by: David Disseldorp <ddiss@suse.de>
Reviewed-by:...
Boris Ranto
03:26 PM Revision 533b6177 (ceph): rgw: send proper ETag value during GET on DLO/SLO through S3 API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
03:10 PM Bug #14934 (Won't Fix): common/config_opts.h: audit OPT_INT/OPT_UINT and handle incorrect signed ...
The fix for #13829 uncovered something that concerns me deeply: all the options that are marked as 'OPT_INT' when the... Joao Eduardo Luis
02:45 PM Revision 8ffc4e80 (ceph): msg: async: start over after failing to bind a port in specified range
The original report associated with this fix can be found at
http://tracker.ceph.com/issues/13002. I reopen one in ca...
xie xingguo
02:27 PM Revision bb2f5755 (ceph): tasks/cephfs/filesystem: ceph_file_layout -> file_layout_t
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:27 PM Revision 14211ba2 (ceph): suites/fs/verify: debug mon too
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:27 PM Revision efd7625f (ceph): Merge pull request #7837 from rldleblanc/wpq-documentation
doc: osd-config Add Configuration Options for op queue. Sage Weil
02:25 PM Revision 805e37cf (ceph): Merge pull request #7851 from jupiturliu/obj-bencher-bug
rados: fix bug for write bench
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
02:18 PM Revision 48e2a65b (ceph): Merge pull request #7729 from yuyuyu101/wip-spdk2
osd: bluestore: Revert NVMEDevice task cstor and refresh interface changes Sage Weil
02:14 PM Revision b87f4efb (ceph): packaging: lsb_release build and runtime dependency
The lsb_release executable is being run in multiple places, not least in
src/common/util.cc, which calls it via shell...
Nathan Cutler
02:09 PM Revision aa2b8911 (ceph): buffer: use alignof for raw_combined allocation arithmetic
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:09 PM Revision f2c0d5cd (ceph): rbd-replay: s/CEPH_BUFFER_APPEND_SIZE/CEPH_PAGE_SIZE/
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
02:09 PM Revision b6ed4d3e (ceph): buffer: size append_buffer so that it fits into page-multiple allocations
We drop some unittest assertions about alloc buffer size. Sorry!
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
02:09 PM Revision ef806906 (ceph): buffer: clean up raw_combined construction
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
01:47 PM Revision 73dcd26f (ceph): buffer: use raw_combined for certain allocations
If the alignment is on a page boundary, or the allocation is big,
a separate buffer::raw goes faster. The rest of th...
Sage Weil
01:47 PM Revision ce3e5a33 (ceph): buffer: alloc right-sized buffer from read_fd
This may as well fit the input; this doesn't relate to the
append buffer.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
01:47 PM Revision 7723d294 (ceph): unittest_bufferlist: fix ptr move test
Do not assume there is a trailing null the terminate the string.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
01:47 PM Revision 08c0d98b (ceph): unittest_bufferlist: fix append_bench
- fix source
- include larger sizes
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
01:47 PM Revision 69bcbe10 (ceph): unittest_bufferlist: benchmark some allocations
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
01:47 PM Revision 04482ae9 (ceph): buffer: add front(), back(), get_num_buffers() methods
These eliminate most callers of buffers(), which exposes the
internal list<ptr>.
Signed-off-by: Sage Weil <sage@redh...
Sage Weil
01:47 PM Revision 724a493a (ceph): buffer: combine data and buffer::raw into single allocation
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
01:47 PM Revision 6be3b99d (ceph): buffer: align unspecified allocations to a word
This will let us put policy create_aligned.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
01:46 PM Revision 149f01f3 (ceph): Merge pull request #7739 from xiexingguo/xxg-wip-14387
osd: fix race condition for heartbeat_need_update
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:45 PM Revision ef597332 (ceph): Merge pull request #7703 from xiexingguo/xxg-wip-statfs
osd: filestore: fast abort if statfs encounters ENOENT
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:45 PM Revision 57b838f4 (ceph): Merge pull request #7766 from adamemerson/wip-portable-mutex
common: Do not use non-portable constants in mutex_debug
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Sage Weil
01:44 PM Revision 5f429178 (ceph): Merge pull request #7799 from xiexingguo/xxg-wip-fixnvme
osd: bluestore: NVMEDevice: fix error handling
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:43 PM Revision 46bd7bbb (ceph): Merge pull request #7804 from jjhuo/fixes
osd: kstore: fix a race condition in _txc_finish()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
01:43 PM Revision 46641a9b (ceph): osd: probabilistic promotion throttling
Global tunables osd_tier_promote_max_{objects,bytes}_sec adjust a
probability that any given promotion we might other...
Sage Weil
01:43 PM Revision 07507694 (ceph): osd: set per-interval cap on promotions
This will help mitigate stampedes by capping the number of
promotes within a single tick interval.
Signed-off-by: Sa...
Sage Weil
01:43 PM Revision 0a03b792 (ceph): osd: set conservative (low) promotion throttling values
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
01:43 PM Revision 0edaae63 (ceph): Merge pull request #7816 from marcan/build-fixes
configure.ac: boost_iostreams is required, not optional
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
01:42 PM Bug #14933 (Resolved): osd/PGLog.cc: 569: FAILED assert(log.head >= olog.tail && olog.head >= log...
... Sage Weil
01:42 PM Revision a7642825 (ceph): osd/ReplicatedPG: fix promote obc setup when recency > 1
Pass promote_obc like the other call sites.
This was broken by d36d7f24fb001c136ec5a0c8bf9e52411d6c0947.
Signed-off...
Sage Weil
01:36 PM Revision eac7e7a1 (ceph): librados_test_stub: added aio_watch/aio_unwatch/aio_watch_flush
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
01:36 PM Revision 34dd39c0 (ceph): librbd: use aio watch/unwatch during open/close state machines
Removed the place holders in the open/close async state machines with
the newly added aio watch/unwatch methods.
Sig...
Jason Dillaman
01:32 PM Revision feb2fc02 (ceph): test: adjust rbd test case guards to handle new defaults
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
01:09 PM Revision e5ac9d08 (ceph): Merge pull request #844 from ceph/wip-rbd-cli-features
rbd/cli: add older default features
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
12:55 PM Revision ed839759 (ceph): librbd: permit deep-flatten to be dynamically disabled
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:55 PM Revision 0b2847e6 (ceph): test: use default RBD features in test cases
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:55 PM Revision d24883e4 (ceph): rbd: update default image features
Exclusive lock, object map, fast-diff, and deep-flatten have been
enabled by default for all new images.
Signed-off-...
Jason Dillaman
12:48 PM Revision 6eff39af (ceph): qa/workunits/cephtool/test.sh: wait longer in ceph_watch_start()
"ceph --watch-debug" and "ceph tell mon.foo version" could connect
to different monitors, and there is chance that "c...
Kefu Chai
12:47 PM Revision 42d81bff (ceph): common/obj_bencher.cc: faster object name generation
generate_object_name() uses std::ostringstream to build object name
and calls generate_object_prefix() (which uses an...
Piotr Dałek
12:39 PM Revision e4f73b3b (ceph): librbd: apply orphaned maintenance ops after journal replay
If a client recorded a maintenance op to the journal but crashed
before writing the op finish event, the image will b...
Jason Dillaman
12:39 PM Revision c4387301 (ceph): librbd: only cancel replay of journal op events upon error
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:38 PM Revision 9c996371 (ceph): librbd: delay commit of op start event
If the start event is flagged as committed before the op is
actually executed, librbd won't be able to replay the eve...
Jason Dillaman
12:38 PM Revision ed9de5fc (ceph): librbd: support replay of maintenance ops
Ignore errors that are to be expected when replaying
a maintenance op two or more times.
Fixes: #14822
Signed-off-by...
Jason Dillaman
12:38 PM Revision b0dc047e (ceph): journal: permit fire-and-forget aio commit position flush
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:28 PM Backport #13288 (In Progress): hammer: stuck recovering, unfound hit set due to removing it while...
Kefu Chai
12:28 PM Backport #13288: hammer: stuck recovering, unfound hit set due to removing it while !active
pushed to wip-12848-hammer.
running
teuthology-suite --priority 10 --suite upgrade --suite-branch jewel --emai...
Kefu Chai
12:19 PM Fix #14932: Improve ceph-disk error message when there is not enough space to create journal part...
See https://github.com/ceph/ceph/pull/5057 Nathan Cutler
12:15 PM Fix #14932: Improve ceph-disk error message when there is not enough space to create journal part...
Loïc Dachary
12:13 PM Fix #14932 (In Progress): Improve ceph-disk error message when there is not enough space to creat...
Owen Synge writes:
When using ceph-disk to create a journal partiton in the next available partition and their is ...
Nathan Cutler
12:03 PM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
@Alexey Sheplyakov or maybe the similar patch you're refering to is https://github.com/ceph/ceph/pull/7123/files ? Loïc Dachary
10:27 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
@Alexey Sheplyakov would you be so kind as to push said similar patch in a pull request ? That would be most helpful :-) Loïc Dachary
10:16 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
> I think handling those with regexps is very error prone (and even more intrusive than the suggested patch).
On t...
Alexey Sheplyakov
10:14 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
> We don't have good enough test coverage in hammer
We (Mirantis) have been using a similar patch for 2 months wit...
Alexey Sheplyakov
11:49 AM Revision ea9cb4ff (ceph): doc: rgw explain keystone's verify ssl switch
Adding info about `rgw keystone verify ssl` to configuration reference,
also adding a note in rgw keystone to explain...
Abhishek Lekshmanan
11:05 AM Bug #14864 (Resolved): ceph-detect-init requires python-setuptools at runtime
Nathan Cutler
10:58 AM Revision e5641115 (ceph): doc: add notes about upgrading cephfs
This is part of the run-up to removing all
TMAP code in the Jewel+1 cycle.
Signed-off-by: John Spray <john.spray@red...
John Spray
10:58 AM Revision d5c9349e (ceph): Merge pull request #7858 from jdurgin/wip-rbd-formatted-output-progress
test/cli-integration/rbd: disable progress output
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
10:57 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Nathan and Alexey, probably we should backport https://github.com/ceph/ceph/pull/5853 also? Kefu Chai
10:40 AM Revision 3d8fc943 (ceph): Merge pull request #7745 from sileht/sileht/rados-cython
pybind: move cephfs to Cython
Reviewed-by: John Spray <john.spray@redhat.com>
John Spray
10:13 AM Bug #14928 (Resolved): AsyncMessenger: shall start over after fails to bind a port in specified r...
https://github.com/ceph/ceph/pull/7852 xie xingguo
02:51 AM Bug #14928 (Resolved): AsyncMessenger: shall start over after fails to bind a port in specified r...
See
http://tracker.ceph.com/issues/13002
xie xingguo
09:57 AM Bug #14925 (Resolved): async messenger assert failure
Haomai Wang
09:56 AM Bug #14912 (Resolved): msg/async: bad RESETSESSION
Kefu Chai
09:54 AM Revision 4ea3d683 (ceph): Merge pull request #7831 from yuyuyu101/wip-14912
AsyncMessenger: fix several bugs Haomai Wang
09:53 AM Revision 48a5f2d8 (ceph): Merge pull request #7852 from xiexingguo/xxg-wip-14928
msg: async: start over after failing to bind a port in specified range
Reviewed-by: Haomai Wang <haomai@xsky.com>
Re...
Haomai Wang
09:48 AM Bug #14910 (Fix Under Review): cephtool/test.sh: test_mon_tell test unreliable
https://github.com/ceph/ceph/pull/7861 Kefu Chai
09:26 AM Bug #14910: cephtool/test.sh: test_mon_tell test unreliable
as a fix, we might need to wait until the "ceph --watch-debug" prints something ("cluster" maybe) before calling "cep... Kefu Chai
09:00 AM Bug #14910: cephtool/test.sh: test_mon_tell test unreliable
in @test_mon_tell()@, we try to verify that @ceph tell mon.foo version@ is always handled by mon.foo. and ceph cli al... Kefu Chai
09:16 AM Linux kernel client Bug #14232: Kernel NULL pointer dereference in __dcache_readdir
Thanks for the patch! I will let you know, if the bug hits again. Markus Blank-Burian
08:22 AM Revision 843564f1 (ceph): Merge pull request #845 from dachary/wip-14931-cram-hammer
cram: pin to version 0.6 because 0.7 handles \r differently Loïc Dachary
07:57 AM Revision eb631a08 (ceph): cram: pin to version 0.6 because 0.7 handles \r differently
http://tracker.ceph.com/issues/14931 Fixes: #14931
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro...
Loic Dachary
07:50 AM Revision d6ae11d1 (ceph): Merge pull request #846 from dachary/wip-14931-cram
cram: pin to version 0.6 because 0.7 handles \r differently
Reviewed-by: Xiaoxi Chen <xiaoxchen@ebay.com>
Reviewed-b...
Loïc Dachary
07:17 AM Revision 70fb7493 (ceph): cram: pin to version 0.6 because 0.7 handles \r differently
http://tracker.ceph.com/issues/14931 Fixes: #14931
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary
06:57 AM Revision acc64054 (ceph): test/cli-integration/rbd: disable progress output
This test is intended to check machine-readable output and usage, not
human-readable output.
Fixes: #14931
Signed-of...
Josh Durgin
06:48 AM Revision 4f98ba25 (ceph): Merge pull request #7778 from marcan/pybind-fixes
pybind/rados: fix object lifetime issues and other bugs in aio
Reviewed-by: Mehdi Abaakouk <sileht@redhat.com>
Revie...
Josh Durgin
06:40 AM Bug #14930 (Resolved): test/osd/TestPGLog.cc fails to compile
Kefu Chai
06:27 AM Bug #14930 (Fix Under Review): test/osd/TestPGLog.cc fails to compile
https://github.com/ceph/ceph/pull/7855 Kefu Chai
05:02 AM Bug #14930 (Resolved): test/osd/TestPGLog.cc fails to compile
This is making make check fail:
http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-amd64-basic/log.cg...
Josh Durgin
06:39 AM Revision cbe8dfbd (ceph): Merge pull request #7855 from tchaikov/wip-fix-ftbfs
test/TestPGLog: fix the FTBFS
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Kefu Chai
06:30 AM Bug #13826 (Duplicate): segfault from PrebufferedStreambuf::overflow
Kefu Chai
04:47 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
@Peter - can you upgrade to 9.2.1 and try to reproduce again? Nathan Cutler
04:46 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
The infernalis backport is http://tracker.ceph.com/issues/13589 - https://github.com/ceph/ceph/pull/6392. It is inclu... Nathan Cutler
06:09 AM Revision 3a6bf7d2 (ceph): tasks/scrub_test: match the NOSNAP with "head"
* rados cli prints "head" at seeing CEPH_NOSNAP, so update the test
accordingly
* print inconsistent objs before te...
Kefu Chai
05:55 AM Revision b82fe3d6 (ceph): rbd/cli: add older default features
Explicitly set features and default format so they don't become out of
date. Remove none.yaml, since default.yaml is ...
Josh Durgin
05:20 AM Revision 20398733 (ceph): test/TestPGLog: fix the FTBFS
the new pure virtual method was introduced by e7edf20.
Fixes: #14930
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
05:09 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
thanks in advance! Kefu Chai
03:58 AM Bug #14924 (Fix Under Review): scrub_test failure
https://github.com/ceph/ceph-qa-suite/pull/843 Kefu Chai
03:17 AM Bug #14924 (In Progress): scrub_test failure
the last minute change of rados cli broke the test suite. just updated the scrub_test.py, testing now at http://pulpi... Kefu Chai
03:17 AM Bug #14929 (Resolved): osd: can only reduce the weight of osd, the use of "ceph osd reweight-by-u...
The osd on the node181 weight has been reduced when use "ceph osd reweight-by-utilization 101"... huanwen ren
02:26 AM Revision 1594ec09 (ceph): Merge pull request #842 from ceph/wip-rbd-features
rbd: updated tests to use new rbd default feature set
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
02:20 AM Revision febc307d (ceph): Merge pull request #841 from ceph/wip-krbd-default-features
krbd: override rbd defaults features to 1
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
02:18 AM Revision 03e6627d (ceph): Merge pull request #821 from ceph/wip-fsx-journal
rbd: add fsx journal replay test case
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:35 AM Revision 0bd82d3d (ceph): [rgw] RGWLib::env is not used so remove it
Coverity complains about RGWLib::env.port being uninitialised but
RGWLib::env is not used at all so just remove it.
...
Brad Hubbard
01:30 AM Revision abd708d8 (ceph): Merge pull request #7781 from ceph/wip-fix-rbd-cli-tests
rbd/run_cli_tests.sh: Reflect test failures
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:25 AM Revision 6cd5e204 (ceph): fixed a bug for write bench with rados
Signed-off-by: James Liu <james.liu@ssi.samsung.com> James Liu
12:20 AM Revision 86e67cd0 (ceph): Rename mon.0 to mon.a
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
12:20 AM Revision 6305415c (ceph): Make the keyring world-readable
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
12:20 AM Revision 7dd350e7 (ceph): Run 'ceph health' after deployment
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza

02/29/2016

11:57 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
9085c820491f25a04ec02accc5098c1ab9b57311 I guess fixed it. Samuel Just
11:47 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
Ok, bug seems to be in Monitor::ms_verify_authorizer. It treats the return value from cephx_verify_authorizer as an ... Samuel Just
11:39 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
Samuel Just
11:38 PM Bug #13826 (Duplicate): segfault from PrebufferedStreambuf::overflow
Samuel Just
11:53 PM Revision e70a633b (ceph): Merge pull request #832 from athanatos/wip-lost
Wip lost
Reviewed-by: Sage Weil <sage@redhat.com>
Samuel Just
11:43 PM Bug #14927 (Resolved): "[ FAILED ] ClsLock.Test*" (4 tests) failed in upgrade:hammer-x-jewel-di...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-29_10:02:04-upgrade:hammer-x-jewel-distro-basic-openst... Yuri Weinstein
11:25 PM Revision 1a84b8c4 (ceph): Merge pull request #7826 from SUSE/wip-move-requires
RPM: move runtime dependencies to ceph-base and fix other packaging issues
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Ken Dreyer
11:19 PM Revision cf812ead (ceph): rgw: aggregate usage by payer
If bucket has requester-payer property set, aggregate the usage data
on it by the user that did the operation.
Signe...
Yehuda Sadeh
11:19 PM Revision ff8305a9 (ceph): rgw: fix permission check for request payer
If request_payer auth check returns false, we need to abort.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
11:04 PM Revision 440e9b5d (ceph): Merge pull request #7769 from somnathr/wip-make-shared
Use make_shared while creating shared_ptr
Reviewed-by: Samuel Just <sjust@redhat.com>
Samuel Just
09:17 PM Revision ecae0549 (ceph): Merge pull request #839 from ceph/wip-ceph-ansible
Add ceph-ansible suite Yuri Weinstein
08:06 PM Bug #14244: "SELinux denials found" in rados-jewel-distro-basic-smithi
Is anyone tracking the actual @chrony@ bug/fix? Zack Cerza
07:23 PM Revision 554b643a (ceph): test_filejournal: reserve throttle as needed
This is awkward, if there are later users other than this test
and JournalingObjectStore, it'll be worth making it a ...
Samuel Just
07:12 PM Revision 2856cf5a (ceph): osd: replicatedpg: remove redundant semicolon
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
07:06 PM Revision 201e1742 (ceph): osd: replicatedpg: break out if we encounter error during do_pg_op()
Otherwise:
1. The error result may be overwritten and hidden.
2. There may be potential memory leak.
Fixes: #14922
S...
xie xingguo
06:55 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I noticed the mon log was a day off when I made my last update. Sorry about that. Unfortunately this test was old eno... Steve Taylor
06:52 PM Revision 30f548e9 (ceph): config_opts: make filestore_queue_max_(ops|bytes) U64
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:42 PM Revision 306c7bf4 (ceph): Merge pull request #7765 from athanatos/wip-lost-unfound-repop
Repop and lost-unfound overhaul
Reviewed-by: Sage Weil <sage@redhat.com>
Samuel Just
06:26 PM Revision bcc2866e (ceph): doc: fix typo, indention etc.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
06:24 PM rbd Tasks #14551 (Fix Under Review): Update RBD default features
*PR*: https://github.com/ceph/ceph/pull/7846
*PR*: https://github.com/ceph/ceph-qa-suite/pull/841
*PR*: https://git...
Jason Dillaman
04:28 PM rbd Tasks #14551 (In Progress): Update RBD default features
Jason Dillaman
06:22 PM Revision 622748ae (ceph): rbd: deprecate image format 1
The rbd cli will warn about the deprecation when attempting to create
image format 1 images. librbd will log an erro...
Jason Dillaman
06:20 PM Revision 49c76d6a (ceph): Updated mirroring script to mirror Ceph
It adds new mirror locations which exist for Ceph
Signed-off-by: Wido den Hollander <wido@42on.com>
Wido den Hollander
06:20 PM Revision ece5b9e5 (ceph): Add new mirrors to overview file
Signed-off-by: Wido den Hollander <wido@42on.com> Wido den Hollander
05:52 PM Revision 0c0e8a0f (ceph): AsyncConnection: log cleanup, remove redundant state display
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
05:44 PM Bug #14925: async messenger assert failure
https://github.com/ceph/ceph/pull/7831 Haomai Wang
03:46 PM Bug #14925 (Resolved): async messenger assert failure
2016-02-27T05:56:55.094 INFO:teuthology.orchestra.run.smithi045.stderr:2016-02-27 13:56:55.084479 7f90442c0700 1 Eve... Samuel Just
05:42 PM Revision 324145b7 (ceph): Event: complete all pending events
Fix #14925
Signed-off-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
05:26 PM rbd Backport #13757: rbd: pure virtual method called
It was rejected because firefly is EOL. Loïc Dachary
05:22 PM rbd Backport #13757: rbd: pure virtual method called
This problem was reported in the OpenStack gate for ceph:
https://bugs.launchpad.net/ubuntu/+source/ceph/+bug/1551...
James Page
04:36 PM Revision 275b5f28 (ceph): RPM: drop duplicate udev rules from ceph-base
The udev rules should be packaged in ceph-osd only.
Signed-off-by: Nathan Cutler <ncutler@suse.com>
Nathan Cutler
04:36 PM Revision 4de86bf3 (ceph): RPM: drop duplicate /var/lib/ceph/* directories
As of a recent commit, we had /var/lib/ceph/{mds,mon,osd} directories
packaged twice, once with %attr and once withou...
Nathan Cutler
04:36 PM Revision 5083980f (ceph): packaging: rados-classes libraries in ceph-base
Drop duplicate rados-classes libraries from ceph-osd and align the RPM
packaging with Debian by using a wildcard to p...
Nathan Cutler
04:28 PM Revision bd592c0f (ceph): AsyncConnection: dispatch write handler when accept done
Fix #12912
Signed-off-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
04:01 PM Bug #14911 (Rejected): rados: unrecognized command list-inconsistent-pg; -h or --help for usage
thanks for sorting this one out! Sage Weil
03:53 PM Revision bcff5be4 (ceph): osd: fix typo
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
03:50 PM Revision 90d4afff (ceph): osd: fix overload of '==' operator for pg_stat_t
The newly added fields -- 'last_peered' and 'last_became_peered'
are not compared.
Fixes: #14921
Signed-off-by: xie ...
xie xingguo
03:42 PM Revision 5f82cbe0 (ceph): Merge pull request #7824 from dillaman/wip-aio-watch-notify
librados: fix test failure with new aio watch/unwatch API
Reviewed-by: Samuel Just <sjust@redhat.com>
Samuel Just
03:40 PM Bug #14924 (Resolved): scrub_test failure
I have seen this in runs for two disjoint sets of PRs.
File "/var/lib/teuthworker/src/ceph-qa-suite_master/tasks...
Samuel Just
02:16 PM Revision d1c211dd (ceph): rbd: updated tests to use new rbd default feature set
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
01:53 PM Revision 4b0ff1c7 (ceph): Merge pull request #7832 from trociny/wip-journal-register-async
journal: async methods to (un)register and update client
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
01:42 PM Revision f9a69022 (ceph): krbd: override rbd defaults features to 1
Jewel will update the default feature set to features
unsupported by krbd.
Signed-off-by: Jason Dillaman <dillaman@r...
Jason Dillaman
01:13 PM Revision 7bc42aaa (ceph): Merge pull request #7829 from xiexingguo/xxg-wip-doc
doc: fix typo, indention etc.
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Reviewed-by: Kefu Chai <kchai@red...
Kefu Chai
12:35 PM Bug #14923 (Duplicate): osd/ReplicatedPG: break out loop if we encounter error during do_pg_op()
http://tracker.ceph.com/issues/14922 xie xingguo
10:47 AM Bug #14923 (Duplicate): osd/ReplicatedPG: break out loop if we encounter error during do_pg_op()
Otherwise the error code will be overwritten and may cause potential memory leak. xie xingguo
12:15 PM Revision 0952f35e (ceph): tools/cephfs: add tmap_upgrade
Because TMAP support will go away in Jewel+1,
we need a way to ensure anyone upgrading
an ancient CephFS filesystem c...
John Spray
12:05 PM Revision f22a0970 (ceph): Bugfix: set thread name will fail, when running as differnt user.
When using setuid/setgid, main thread don't have access to
/proc/self/task/[tid]/comm, which is owned by newly create...
Igor Podoski
11:52 AM CephFS Bug #14685: dbench hang on native cifs mount
http://qa-proxy.ceph.com/teuthology/teuthology-2016-02-26_19:14:10-samba-jewel---basic-mira/29964/teuthology.log Zheng Yan
11:16 AM Revision c27d2792 (ceph): rgw: culculate etag for DLOs of Swift API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
11:16 AM Revision 44b87bdb (ceph): rgw: calculate etag for SLOs of Swift API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
11:16 AM Revision dcd6c4ad (ceph): rgw: ONLY code refactoring in RGWGetObj::handle_slo_manifest.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
11:16 AM Revision d4282967 (ceph): rgw: return proper etag in response for PUT on Swift's SLO.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
11:16 AM Revision 6fb1ceb8 (ceph): rgw: do not enforce Content-Length in response for DELETE on Swift's SLO.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:37 AM Bug #14922 (Resolved): osd/ReplicatedPG: break out loop if we encounter error during do_pg_op()
Otherwise the error code will be overwritten. xie xingguo
10:36 AM Revision 4b172fd2 (ceph): pybind: update ceph_volume_client for cython
No need to explicitly touch the (no-longer-existing)
load_libcephfs method during module load, as with
the cython ver...
John Spray
10:36 AM Revision 7f03c0e5 (ceph): pybind: fix error handling on getxattr
The ctypes bindings returned empty string
instead of raising exception. This was a bug,
because it made it impossibl...
John Spray
09:58 AM Revision 10f125f7 (ceph): pybind: move cephfs to Cython
This change moves cephfs binding to Cython.
Closes-bug: #14818
Signed-off-by: Mehdi Abaakouk <sileht@redhat.com>
Mehdi Abaakouk
08:03 AM Revision 70f32f99 (ceph): rgw: adjust the request_uri to support absoluteURI of http request
http://tracker.ceph.com/issues/12917 Fixes: #12917
The requestURI transferred from the frontend can be abs_path or a...
wenjunhuang
07:43 AM Bug #14921 (Resolved): OSD:wrong overload of "==" operator for pg_stat_t
Fields "last_peered" and "last_became_peered" are not compared xie xingguo
06:21 AM Bug #14920 (Resolved): If bluestore_sync_submit_transaction == true, make ceph don't work.
If bluestore_sync_submit_transaction = true; it submit transaction in _txc_state_proc.
For the extent alloca/release...
jianpeng ma
06:04 AM Revision 1ab5fcdb (ceph): doc: mon-config Add information about pg_prime
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com> Robert LeBlanc
05:34 AM Bug #14918: [BlueStore]If bluestore_sync_transaction == true, make bluestore deadlock
https://github.com/ceph/ceph/pull/7674 jianpeng ma
05:28 AM Bug #14918 (Resolved): [BlueStore]If bluestore_sync_transaction == true, make bluestore deadlock
In _txc_finish_io, it get the lock of osr and call _txc_state_proc.
If bluestore_sync_transaction == true adn txd->w...
jianpeng ma
02:43 AM Revision c914f28d (ceph): utime.h: fix timezone issue in round_to_* funcs.
gmtime_r converts local time to UTC, however mktime only takes an
argument as local time. Use localtime_r instead of ...
Chao Zhao
02:09 AM rbd Tasks #14550 (In Progress): Deprecate format v1 RBD images
Jason Dillaman

02/28/2016

09:04 PM Bug #12967: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
Shinobu Kinjo wrote:
> Hm, not sure what's best - the "duplicated" bug mentions error messages I'm not seeing (handl...
Aaron T
10:11 AM Bug #12967: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
Hm, not sure what's best - the "duplicated" bug mentions error messages I'm not seeing (handle_sub_read: Bash hash)
...
Shinobu Kinjo
09:06 AM Bug #12967: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
Aaron Ten Clay wrote:
> I'm encountering an issue that looks very similar. Four OSDs are crashing almost immediately...
Aaron T
09:03 AM Bug #12967: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
I'm encountering an issue that looks very similar. Four OSDs are crashing almost immediately after startup, both with... Aaron T
08:34 PM rbd Cleanup #14809: ImageWatcher unwatch and flush should use async librados methods
*PR*: https://github.com/ceph/ceph/pull/7839 Jason Dillaman
05:47 PM rbd Cleanup #14809 (In Progress): ImageWatcher unwatch and flush should use async librados methods
Jason Dillaman
07:34 PM Bug #14911: rados: unrecognized command list-inconsistent-pg; -h or --help for usage
I took a look at this. The testing branch is wip-sage-testing, which contains 4c3270692 (the commit where Kefu implem... Nathan Cutler
06:35 PM Revision 2784c653 (ceph): mon: Enable pg_prime by Default
Although this does not completely resolve the start up issues, it looks
like this really helps with the memory usage ...
Robert LeBlanc
06:09 PM CephFS Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
We're also running into this with the latest versions of ceph and CentOS 7 kernel. Message on the mds is:... Richard Hesse
05:46 PM rbd Feature #14909 (In Progress): Journal replay should support multiple tag class streams
Jason Dillaman
05:06 PM Revision 8aa159be (ceph): doc: osd-config Add Configuration Options for op queue.
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com> Robert LeBlanc
09:23 AM devops Bug #14906: redhat-lsb-core dependency was dropped, but is still needed
@Ken, @Boris - the lsb_release executable is run in many places:... Nathan Cutler
09:15 AM Backport #14916 (In Progress): infernalis: librados (C++) linker error (undefined reference)
Nathan Cutler
09:07 AM Backport #14916 (Rejected): infernalis: librados (C++) linker error (undefined reference)
https://github.com/ceph/ceph/pull/7835 Nathan Cutler
09:04 AM CephFS Backport #14761 (In Progress): infernalis: ceph-fuse does not mount at boot on Debian Jessie
Nathan Cutler
07:45 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Hi Alexey! Is this bug not present in master? (The usual process is to fix in master first and then backport.) Nathan Cutler
07:44 AM Backport #14873 (Fix Under Review): hammer: rados bench seq crashes (v0.94.6)
Nathan Cutler
04:50 AM Revision 65a096be (ceph): IoCtxImpl: delete WatchCtx when it's internal alloc
Fix #14907
Signed-off-by: Haomai Wang <haomai@xsky.com>
Haomai Wang

02/27/2016

11:02 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
We found follow warn in osd logs when we make massive rsync... Ruslan Usifov
09:42 AM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
our dmsg log is clean, and doens't have any suspicious records(only boot log, thats all). When rbd erros happens last... Ruslan Usifov
06:45 PM Bug #14864 (Fix Under Review): ceph-detect-init requires python-setuptools at runtime
This issue is fixed in https://github.com/ceph/ceph/commit/cba211dfa8875194691c11411bbde9f04166d4c4 which is a part o... Nathan Cutler
01:42 PM Bug #14864 (In Progress): ceph-detect-init requires python-setuptools at runtime
Nathan Cutler
05:16 PM Revision b4f19352 (ceph): Python-argparse is a virtual package which stretch wants you to pick
a real package to satisfy the dependency.
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com>
Robert LeBlanc
04:01 PM Revision 8c054f74 (ceph): Merge pull request #7747 from vsjulu/master
xio: fix incorrect ip being assigned in case of multiple RDMA ports
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
02:22 PM Revision 894738f8 (ceph): Merge pull request #7630 from rzarzynski/wip-rgw-admin-token-cache
rgw: add support for caching of Keystone admin token.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
02:17 PM Revision 04884be9 (ceph): Merge pull request #7825 from ceph/wip-rgw-openssl
rgw: link civetweb with openssl (Sage, Marcus Watts)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
01:59 PM Revision 608dd287 (ceph): RPM: align runtime dependencies with Debian packaging
The ceph package is now a metapackage, so move all its runtime dependencies
to ceph-base as we already have done in t...
Nathan Cutler
01:59 PM Revision 1a0bb0f6 (ceph): packaging: move python-flask runtime dependency to ceph-mon, radosgw
Flask is used by MON (in the Ceph REST API) and by RGW (powerdns).
Therefore, it only needs to be in the ceph-mon and...
Nathan Cutler
01:59 PM Revision 8b04c2b4 (ceph): ceph.spec.in: drop support for ancient SUSE versions
In Jewel, there is no reason to support anything less than openSUSE 13.
Signed-off-by: Nathan Cutler <ncutler@suse.com>
Nathan Cutler
01:59 PM Revision 45ede095 (ceph): ceph.spec.in: move ceph-disk runtime dependency to ceph-osd
ceph-disk uses sgdisk, which resides in the gdisk and gptfdisk packages on
RHEL and SUSE derivatives, respectively.
...
Nathan Cutler
01:59 PM Revision cba211df (ceph): packaging: pkg_resources.py runtime dependency
ceph-detect-init uses pkg_resources.py
http://tracker.ceph.com/issues/14864 Fixes: #14864
Signed-off-by: Nathan Cut...
Nathan Cutler
01:28 PM Revision 083a0064 (ceph): osd: update sprintf() to snprintf()
Which is safer. Also enlarge length of name to 32, which shall be
big enough to hold a int64_t value.
Signed-off-by:...
xie xingguo
01:28 PM Revision 8101df00 (ceph): osd: fix typo
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:27 PM Revision 0d4be187 (ceph): osd: improve get_net_marked_out() a little bit
For the sake of performance.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
01:27 PM Revision 73784f0b (ceph): osd: fix wrong return type of find_osd_on_ip()
Fixes: #14872
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
12:59 PM Revision 9453967f (ceph): test: add tests to (un)register and update journal client
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
12:57 PM Bug #14912: msg/async: bad RESETSESSION
I think this is a safe revert. Because from #12912 described, initiate side will never send message to peer, this sho... Haomai Wang
12:53 PM Bug #14912 (Fix Under Review): msg/async: bad RESETSESSION
https://github.com/ceph/ceph/pull/7831 Haomai Wang
12:47 PM Bug #14912: msg/async: bad RESETSESSION
From the log message, we can infer the sequence:
1. osd.2 connect to osd.0
2. osd.0 connect to osd.2
3. osd.2 ge...
Haomai Wang
12:50 PM Revision 3e18f564 (ceph): Revert "AsyncConnection: Close connection when unregistered connection ...
This reverts commit 9cc1055eb6e18d55084d5af2b2f93eb8da5ab7da.
Fix #14912
Signed-off-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
11:51 AM Bug #14862 (Fix Under Review): utime.h: fix timezone issue in round_to_* funcs.
Nathan Cutler
10:33 AM Revision a4527c3c (ceph): journal: async methods to (un)register and update client
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
10:33 AM Revision 378f4c73 (ceph): cls::journal: async client_unregister
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
09:03 AM Bug #14766 (In Progress): OSD reporting ENOTEMPTY and crashing
Loïc Dachary
07:34 AM Revision 86718592 (ceph): cmake fix: build civetweb with the right include path.
In an earlier commit, civetweb.c got moved into a separate cmake 'object'
library civetweb_common_objs so that it cou...
Marcus Watts
05:45 AM Bug #14907 (Fix Under Review): rados_watch2 and rados_aio_watch memory leak
https://github.com/ceph/ceph/pull/7830 Haomai Wang
04:10 AM Revision 130b12b6 (ceph): Fix old and new pep8 issues
Signed-off-by: Vasu Kulkarni <vasu@redhat.com> Vasu Kulkarni
02:05 AM Bug #14913 (Resolved): ceph-disk-test.py::TestCephDisk::test_destroy_osd_by_id FAILED
http://qa-proxy.ceph.com/teuthology/teuthology-2016-02-25_23:13:11-ceph-disk-jewel-distro-basic-mira/28295/... Loïc Dachary
12:07 AM Revision ea2e24fd (ceph): rgw: fixes and adjustments following rebase
Also, use ldout instead of cerr in rgw_op.cc
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:07 AM Revision 23785d32 (ceph): rgw: remove usage from signed resources
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh

02/26/2016

11:58 PM Revision 74d698a4 (ceph): Merge pull request #7650 from avnerbh/fix1_rand
msg: add thread safety for "random" Messenger + fix wrong usage of random functions
Reviewed-by: Haomai Wang <haomai...
Sage Weil
11:57 PM Revision 0499ca89 (ceph): Merge pull request #7651 from xiexingguo/xxg-wip-fixtypecheck
osd: bluestore: improve fs-type verification and tidy up
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
11:36 PM Revision 6e497e07 (ceph): Merge pull request #7654 from rldleblanc/wip-wpq-optimization
osd: WeightedPriorityQueue: move to intrusive containers Sage Weil
11:33 PM devops Bug #14811 (Resolved): RPM: yasm complains when building with %{with lowmem_builder}
Sage Weil
11:33 PM Revision d6031c26 (ceph): Merge pull request #7700 from SUSE/wip-14811
src/yasm-wrapper: ignore parameters starting with ggc-min
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Sage Weil
11:28 PM Bug #14912 (Resolved): msg/async: bad RESETSESSION
2016-02-26 19:07:53.618211 7f876efc1700 0 -- 172.21.15.37:6805/3358 >> 172.21.15.37:6801/3355 conn(0x7f8782b7c000 sd... Sage Weil
11:22 PM Bug #14911 (Rejected): rados: unrecognized command list-inconsistent-pg; -h or --help for usage
/a/sage-2016-02-26_07:11:10-rados-wip-sage-testing---basic-smithi/28864 Sage Weil
11:21 PM Bug #14910 (Resolved): cephtool/test.sh: test_mon_tell test unreliable
ceph tell mon.foo may get redirected to another mon
/a/sage-2016-02-26_07:11:10-rados-wip-sage-testing---basic-smi...
Sage Weil
10:55 PM Bug #14438: "FAILED assert(pg->info.history.same_interval_since == p.same_interval_since)" in upg...
Unfortunately, I added the diagnostics to jewel branch so it didn't add anything in this last case of Infernalis. David Zafman
09:40 PM Bug #14438: "FAILED assert(pg->info.history.same_interval_since == p.same_interval_since)" in upg...
Also in run:
http://pulpito.ceph.com/teuthology-2016-02-25_17:10:10-upgrade:hammer-x-infernalis-distro-basic-vps/
L...
Yuri Weinstein
10:45 PM Revision 1a1a9397 (ceph): Merge pull request #838 from ceph/wip-14905-hammer
Added v0.94.6 to stable upgrade suite Yuri Weinstein
09:37 PM Revision 88802118 (ceph): Merge pull request #7821 from rzarzynski/wip-rgw-14903
rgw: fix wrong handling of limit=0 during listing of Swift account.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
09:20 PM Revision 155f0791 (ceph): rgw: change naming of utility functions in rgw_keystone.cc.
Slightly improve code formatting and const-correctness as well.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirant...
Radoslaw Zarzynski
08:59 PM Revision a710dcca (ceph): Merge pull request #7807 from ceph/wip-debian-fixes
debian: packaging fixes for jewel
Reviewed-by: Dan Mick <dmick@redhat.com>
Dan Mick
08:45 PM Revision 4a8448a5 (ceph): Add ceph-ansible suite
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
08:36 PM Revision aaa0f6fa (ceph): Use fixed version of civetweb to avoid warning.
The warning about SSLv23_client_method is because when using dynamic
linking, this should always be non-zero. That's...
Marcus Watts
08:30 PM Revision f3925ec5 (ceph): Fix ssl link error.
When linking against -lssl, should also include -lcrypto.
// fixup merge with previous
Signed-off-by: Marcus Watts ...
Marcus Watts
08:29 PM Revision b451cbb3 (ceph): Use ld.so to link in ssl crypto (cmake changes).
Using dlopen() to load in ssl crypto makes me cringe.
Also it requires either installing the devel package,
or append...
Marcus Watts
08:18 PM Revision ec186f4c (ceph): rgw: fix wrong handling of limit=0 during listing of Swift account.
Fixes: #14903
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
Radoslaw Zarzynski
07:22 PM rbd Feature #14909 (New): Journal replay should support multiple tag class streams
Assume an journal layout like:
Object 0: Object 1:
tag=0 (class 0), entry=0 tag=2 (class 0...
Jason Dillaman
07:18 PM Revision d7b47c26 (ceph): Merge pull request #7777 from theanalyst/rgw/insecure-keystone
rgw: allow authentication keystone with self signed certs
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
07:15 PM rbd Bug #14908 (Resolved): Journal replay needs to conditionally refresh the image between events
If a previously replayed maintenance operation requires an image refresh, perform the refresh before processing more ... Jason Dillaman
06:50 PM Revision 381411e3 (ceph): Merge pull request #7809 from cbodley/wip-rgw-includes
rgw: use pimpl pattern for RGWPeriodHistory
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:44 PM Revision 62a21277 (ceph): Merge pull request #7822 from rzarzynski/wip-rgw-keystone-proper-parse-...
rgw: try to parse Keystone token in order appropriate to configuration.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:38 PM Revision 0e3e7bca (ceph): Merge pull request #7803 from oritwas/wip-14826
rgw: reset return code in when iterating over the bucket the objects
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:23 PM Bug #14907 (Resolved): rados_watch2 and rados_aio_watch memory leak
These two methods allocate a C_WatchCB2 proxy class which is never freed upon unwatch. Jason Dillaman
06:19 PM Revision 3254e498 (ceph): test: remove doubled unwatch API call
This error was unmasked by the fix included in commit 8caa2e4.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
06:19 PM Revision 82f547f1 (ceph): librados: aio watch/unwatch/notify now uses completion objver
A local variable was used for an async callback operation,
resulting in the potential for memory corruption.
Signed-...
Jason Dillaman
06:17 PM Revision d4dd0f49 (ceph): debian: remove ceph-dbg package and any traces of it
Signed-off-by: Ali Maredia <amaredia@redhat.com> Ali Maredia
06:01 PM Revision 837dcc59 (ceph): XIO: Changes to fix incorrect ip being assigned in case of multiple RDM...
Signed-off-by: Subramanyam Varanasi <s.varanasi@ssi.samsung.com> vsjulu
05:56 PM devops Bug #14906: redhat-lsb-core dependency was dropped, but is still needed
+ adding branto to the CC
Why does the OSD have a lsb_release_parse function at all? That seems odd.
We really ...
Ken Dreyer
05:42 PM devops Bug #14906: redhat-lsb-core dependency was dropped, but is still needed
*jewel PR*: https://github.com/ceph/ceph/pull/7823 Nathan Cutler
05:41 PM devops Bug #14906 (Fix Under Review): redhat-lsb-core dependency was dropped, but is still needed
Nathan Cutler
05:27 PM devops Bug #14906: redhat-lsb-core dependency was dropped, but is still needed
It looks like collect_sys_info() is called by OSDs, MONs, and MDSs. Nathan Cutler
04:58 PM devops Bug #14906 (Resolved): redhat-lsb-core dependency was dropped, but is still needed
The redhat-lsb-core dependency was removed in https://github.com/ceph/ceph/pull/6363 but it appears to still be neede... Nathan Cutler
05:51 PM Revision 3fc7fdba (ceph): debian: remove ceph-base's dependency on -mon and -osd
The ceph-base package contains files shared between the -mon, -osd, and
-mds. In other words, the MON, OSD, and MDS s...
Ken Dreyer
04:54 PM Revision 44d25fd5 (ceph): journal: track commit position for each object splay offset
It's possible, when delaying appends to the journal, that the
current commit position might be in object set X while ...
Jason Dillaman
04:54 PM Revision 56973870 (ceph): journal: update JournalMetadata to support new commit handling
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:54 PM Revision 91ea6da8 (ceph): journal: update JournalPlayer to support new commit tracking
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:54 PM Revision df258675 (ceph): journal: active and minimum set should always grow
Prevent async reload from canceling out an in-flight update.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
04:54 PM Revision 7906737a (ceph): journal: update JournalTrimmer to support new commit tracking
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:54 PM Revision 107e1145 (ceph): journal: fix delimiter in ObjectSetPosition formater
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:54 PM Revision 41e54221 (ceph): tests: update rbd-mirror tests for updated commit handling
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
04:50 PM Revision 92f24095 (ceph): journal: differentiate corruption vs missing entry errors
librbd should treat the corruption of the journal differently from
missing journal entries. If entries are missing, ...
Jason Dillaman
04:42 PM rbd Subtask #13298 (Resolved): Journal registered client entry should store bufferlist payload
Jason Dillaman
04:41 PM Revision 80f34dcb (ceph): rgw: try to parse Keystone token in order appropriate to configuration.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
04:41 PM rgw Bug #14903 (Fix Under Review): rgw: limit=0 parameter is wrongly handled during Swift acccount li...
Pull request: https://github.com/ceph/ceph/pull/7821. Radoslaw Zarzynski
03:58 PM rgw Bug #14903 (In Progress): rgw: limit=0 parameter is wrongly handled during Swift acccount listing
Radoslaw Zarzynski
03:57 PM rgw Bug #14903 (Resolved): rgw: limit=0 parameter is wrongly handled during Swift acccount listing
Swift:
$ curl -i "$publicURL/?limit=0" -X GET -H "X-Auth-Token: $token"
> HTTP/1.1 204 No Content
> Content-Length...
Radoslaw Zarzynski
04:40 PM Revision ad7f4a59 (ceph): Added v0.94.6 to stable upgrade suite
Fixed #14905
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
Yuri Weinstein
04:20 PM Revision 5d417354 (ceph): rgw: add insecure option to the http client
This allows the http client to turn off ssl certificate peer checking,
which is turned on by default. This is useful ...
Abhishek Lekshmanan
03:54 PM Revision dff62e47 (ceph): rgw: use pimpl pattern for RGWPeriodHistory
this removes the dependency on RGWPeriod from rgw_rados.h, which breaks
a circular dependency between rgw_rados.h -> ...
Casey Bodley
03:51 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
The revised patch (https://github.com/ceph/ceph/pull/7817) fixes the problem. Alexey Sheplyakov
03:04 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
The fix is incomplete, there are more locking errors. I'll keep digging. Alexey Sheplyakov
12:10 PM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Fix (not tested yet): https://github.com/ceph/ceph/pull/7817 Alexey Sheplyakov
10:10 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
I guess it's due to the new --no-verify option: https://github.com/ceph/ceph/commit/a619b621b0a7c670eeaf163d9e2b742d1... Dan van der Ster
09:54 AM Backport #14873: hammer: rados bench seq crashes (v0.94.6)
Same here, only after upgrading clients (OSDs still running 0.94.5).
Full traceback here: http://pastebin.com/HXfVKKFB
Dan van der Ster
06:42 AM Backport #14873 (Resolved): hammer: rados bench seq crashes (v0.94.6)
https://github.com/ceph/ceph/pull/7817 Christian Balzer
03:38 PM Revision 0441f100 (ceph): Merge pull request #837 from ceph/wip-valgrind
suites: debuginfo: true for valgrind Zack Cerza
03:25 PM Revision ca50f423 (ceph): doc: batch small fixes, including typo, syntax etc.
Signed-off-by: xiexingguo <xie.xingguo@zte.com.cn> xie xingguo
03:24 PM Revision 39671f1f (ceph): doc: final v9.2.1 release notes
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:24 PM Revision 8689a615 (ceph): Merge pull request #7694 from Abhishekvrshny/wip-infernalis-release-notes
release-notes: draft v9.2.1 release notes Sage Weil
03:01 PM Revision 0436306c (ceph): Merge pull request #833 from ceph/wip-async
Revert "basic/msgr: remove async and random for now" Sage Weil
03:01 PM Revision 2a800427 (ceph): rbd/run_cli_tests.sh: Reflect test failures
Signed-off-by: Zack Cerza <zack@redhat.com> Zack Cerza
02:55 PM Revision 614597b9 (ceph): AsyncMessenger: remove experiment feature
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
02:54 PM Revision d3db533a (ceph): Merge pull request #7813 from xiexingguo/xxg-wip-doc
doc: small fixes Sage Weil
02:53 PM Bug #14788 (Pending Backport): librados (C++) linker error (undefined reference)
Kefu Chai
02:52 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
oh, i see. Steve, could you help send me the mon log and osd log collected in the same time period?
* the mon log ...
Kefu Chai
02:46 PM Revision f274737d (ceph): suites: debuginfo: true for valgrind
This lets us get line numbers in the valgrind xml output.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil
02:39 PM Revision dc7e027e (ceph): doc: fix typo
Signed-off-by: xiexingguo <xie.xingguo@zte.com.cn> xie xingguo
02:13 PM Linux kernel client Bug #14901: misdirected requests on 4.2 during rebalancing
... Ilya Dryomov
10:45 AM Linux kernel client Bug #14901 (Resolved): misdirected requests on 4.2 during rebalancing
On ceph version 9.2.0 (bb2ecea240f3a1d525bcb35670cb07bd1f0ca299) Linux server4 4.2.0-27-generic #32~14.04.1-Ubuntu SM... Ruslan Usifov
02:04 PM CephFS Backport #14761: infernalis: ceph-fuse does not mount at boot on Debian Jessie
Is there a reason why this was not backported to Infernalis before 9.2.1 release ? Florent B
02:04 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
Is there a reason why this was not backported to Infernalis before 9.2.1 release ? Florent B
01:24 PM Linux kernel client Bug #8226: 0.80~rc1: RBD read errors (ENXIO)
Hello
We create new issue http://tracker.ceph.com/issues/14901
We increase pg_count from 512 to 1024, and see r...
Ruslan Usifov
01:23 PM Revision 5eb2d6cf (ceph): Merge remote-tracking branch 'gh/infernalis' into infernalis
Alfredo Deza
12:56 PM Revision 0cee333e (ceph): mds: remove stray dentry from delayed eval list after calling eval_stray()
MDCache::trim_inode() calls StrayManager.eval_stray() when trimming a
a stray dentry. After calling StrayManager.eval...
Yan, Zheng
11:06 AM Revision 8abffb9a (ceph): os/bluestore/NVMEDevice: fix error handling for try_get()
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
11:06 AM Revision b33984b4 (ceph): os/bluestore/NVMEDevice: remove unused variables ref
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
11:03 AM Revision e2bbce79 (ceph): os/bluestore/NVMEDevice: fix error handling for open()
According to Linux man page, the system call read() may return zero to indicate
that end of file reached on success. ...
xie xingguo
10:50 AM Bug #14902 (Closed): Backport #7604
We should backport PR #7604 (selinux policy update for radosgw) to jewel. Boris Ranto
10:16 AM Revision 2cf7c4a9 (ceph): configure.ac: boost_iostreams is required, not optional
Signed-off-by: Hector Martin <marcan@marcan.st> Hector Martin
09:31 AM Bug #14900: hammer: A massive crush OSD daemons in cache tier pool
If any additional log is needed - just ask. Mike Almateia
09:30 AM Bug #14900 (Rejected): hammer: A massive crush OSD daemons in cache tier pool
Cluster:
* 5 servers
* Centos 7.2 with last updates
* Ceph 0.94.6 from Intank repo
* 4 SSD and 12 HDD on each ser...
Mike Almateia
09:30 AM Backport #14899 (In Progress): hammer: wanted: command to clear 'incomplete' PGs
Loïc Dachary
09:22 AM Backport #14899 (Resolved): hammer: wanted: command to clear 'incomplete' PGs
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:30 AM Backport #14894 (In Progress): hammer: OSD's are not updating osdmap properly after monitoring crash
Loïc Dachary
09:12 AM Backport #14894 (Resolved): hammer: OSD's are not updating osdmap properly after monitoring crash
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:29 AM Backport #14885 (In Progress): hammer: cot: interface fixes and new feature to access the meta co...
Loïc Dachary
09:08 AM Backport #14885 (Resolved): hammer: cot: interface fixes and new feature to access the meta colle...
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:29 AM Backport #14884 (In Progress): hammer: osd, tools: various temp objects fixes
Loïc Dachary
09:08 AM Backport #14884 (Resolved): hammer: osd, tools: various temp objects fixes
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:29 AM Backport #14887 (In Progress): hammer: test, tools: Improve ceph-objectstore-tool import error ha...
Loïc Dachary
09:09 AM Backport #14887 (Resolved): hammer: test, tools: Improve ceph-objectstore-tool import error handl...
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:28 AM Backport #14888 (In Progress): hammer: tools: For ec pools list objects in all shards if the pgid...
Loïc Dachary
09:09 AM Backport #14888 (Resolved): hammer: tools: For ec pools list objects in all shards if the pgid do...
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:28 AM Backport #14889 (In Progress): hammer: tools: clean up errors in ceph-objectstore-tool
Loïc Dachary
09:09 AM Backport #14889 (Resolved): hammer: tools: clean up errors in ceph-objectstore-tool
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:27 AM Backport #14890 (In Progress): hammer: ceph-objectstore-tool improvements
Loïc Dachary
09:09 AM Backport #14890 (Resolved): hammer: ceph-objectstore-tool improvements
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:27 AM Backport #14895 (In Progress): hammer: ceph-objectstore-tool needs to export and import the diver...
Loïc Dachary
09:13 AM Backport #14895 (Resolved): hammer: ceph-objectstore-tool needs to export and import the divergen...
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:26 AM Backport #14898 (In Progress): hammer: ceph_objectstore_tool should support --dry-run option
Loïc Dachary
09:13 AM Backport #14898 (Resolved): hammer: ceph_objectstore_tool should support --dry-run option
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:26 AM Backport #14896 (In Progress): hammer: ceph-objectstore-tool should let you dump a filestore journal
Loïc Dachary
09:13 AM Backport #14896 (Resolved): hammer: ceph-objectstore-tool should let you dump a filestore journal
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:26 AM Backport #14897 (In Progress): hammer: ceph-objectstore-tool can exit and lose logging output
Loïc Dachary
09:13 AM Backport #14897 (Resolved): hammer: ceph-objectstore-tool can exit and lose logging output
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:25 AM Backport #14892 (In Progress): hammer: osd: write journal header by force when journal write close
Loïc Dachary
09:09 AM Backport #14892 (Resolved): hammer: osd: write journal header by force when journal write close
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:25 AM Backport #14893 (In Progress): hammer: crushtool: send --tree to stdout
Loïc Dachary
09:09 AM Backport #14893 (Resolved): hammer: crushtool: send --tree to stdout
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:24 AM Backport #14886 (In Progress): hammer: test: Fix failure test to find message anywhere in stderr
Loïc Dachary
09:09 AM Backport #14886 (Resolved): hammer: test: Fix failure test to find message anywhere in stderr
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:24 AM Backport #14891 (In Progress): hammer: Fix --dry-run for many ceph-objectstore-tool operations
Loïc Dachary
09:09 AM Backport #14891 (Resolved): hammer: Fix --dry-run for many ceph-objectstore-tool operations
https://github.com/ceph/ceph/pull/7702 Loïc Dachary
09:18 AM Feature #10098 (Pending Backport): wanted: command to clear 'incomplete' PGs
Loïc Dachary
09:18 AM Revision c9a40adf (ceph): msg/async: don't calculate msg header crc when not needed
There was a missing condition that caused to calculate outgoing message
header CRC even if CRC checking was disabled ...
Piotr Dałek
09:05 AM Bug #14882 (Pending Backport): cot: interface fixes and new feature to access the meta collection
Loïc Dachary
09:05 AM Bug #14882 (New): cot: interface fixes and new feature to access the meta collection
Loïc Dachary
09:05 AM Bug #14882 (Pending Backport): cot: interface fixes and new feature to access the meta collection
Wei-Chung Cheng
08:58 AM Bug #14882 (Resolved): cot: interface fixes and new feature to access the meta collection
https://github.com/ceph/ceph/pull/5197 Wei-Chung Cheng
09:04 AM Bug #14881 (Pending Backport): test: Fix failure test to find message anywhere in stderr
Wei-Chung Cheng
08:57 AM Bug #14881 (Resolved): test: Fix failure test to find message anywhere in stderr
https://github.com/ceph/ceph/pull/5842 Wei-Chung Cheng
08:59 AM Bug #14883 (Resolved): osd, tools: various temp objects fixes
https://github.com/ceph/ceph/commit/fb22a9fa2fd6d268914d73f018c31760d22afa29
https://github.com/ceph/ceph/commit/4fc...
Loïc Dachary
08:54 AM Bug #14880 (Resolved): test, tools: Improve ceph-objectstore-tool import error handling and tests
https://github.com/ceph/ceph/pull/4932 Loïc Dachary
08:52 AM Bug #14879 (Resolved): tools: For ec pools list objects in all shards if the pgid doesn't specify
https://github.com/ceph/ceph/pull/4915 Loïc Dachary
08:49 AM Bug #14878 (Resolved): tools: clean up errors in ceph-objectstore-tool
https://github.com/ceph/ceph/commit/8e5594da29e782b6efd046ed03f313599dafa1c5 Loïc Dachary
08:46 AM Feature #14877 (Resolved): ceph-objectstore-tool improvements
All commits from https://github.com/ceph/ceph/pull/4784 except the one fixing issue #10794 https://github.com/ceph/ce... Loïc Dachary
08:41 AM Bug #14876 (Pending Backport): Fix --dry-run for many ceph-objectstore-tool operations
Loïc Dachary
08:39 AM Bug #14876 (Resolved): Fix --dry-run for many ceph-objectstore-tool operations
https://github.com/ceph/ceph/pull/6545 Wei-Chung Cheng
08:39 AM Feature #12193 (Pending Backport): OSD's are not updating osdmap properly after monitoring crash
Loïc Dachary
08:36 AM Feature #11237 (Pending Backport): ceph-objectstore-tool needs to export and import the divergent...
Loïc Dachary
08:36 AM Feature #10290 (Pending Backport): ceph_objectstore_tool should support --dry-run option
Loïc Dachary
08:35 AM Feature #11135 (Pending Backport): ceph-objectstore-tool should let you dump a filestore journal
Loïc Dachary
08:34 AM Bug #10809 (Pending Backport): ceph-objectstore-tool can exit and lose logging output
Loïc Dachary
08:30 AM Bug #14875 (Resolved): osd: write journal header by force when journal write close
https://github.com/ceph/ceph/pull/3860 Loïc Dachary
08:15 AM Revision 8ce96308 (ceph): S3 rest api extend for usage show
This api is used to let every S3 user know
their total usage.
Before this, only cluster manager can use
radosgw-admin...
Ji Chen
08:14 AM Feature #14874 (Resolved): crushtool: send --tree to stdout
https://github.com/ceph/ceph/commit/dca345280e4f6124a8b5aea73e6219488111c356 Loïc Dachary
08:09 AM Linux kernel client Bug #14232: Kernel NULL pointer dereference in __dcache_readdir
I found an bug in the fill cache code, could you please try the attached patch Zheng Yan
07:46 AM CephFS Bug #14732 (Duplicate): open returns EACCES when O_TRUNC is specified and write permission is den...
@Yan, marking it as a duplicate of http://tracker.ceph.com/issues/13809 because it's only caused by this incomplete b... Loïc Dachary
07:09 AM CephFS Bug #14732 (Fix Under Review): open returns EACCES when O_TRUNC is specified and write permission...
Zheng Yan
07:19 AM Revision c05300b1 (ceph): log: segv in a portable way
this piece of code creates a SEGV from logging code to verify a
bug fix at e3fe18a.
clang will delete the null-refer...
Kefu Chai
06:03 AM rbd Backport #14863 (Resolved): hammer: test/crypto.cc:161:43: error: ‘ceph_clock_now’ was not declar...
Loïc Dachary
06:00 AM Stable releases Tasks #14692: hammer v0.94.7
h3. fs... Loïc Dachary
06:00 AM Stable releases Tasks #14692: hammer v0.94.7
h3. powercycle... Loïc Dachary
05:57 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rbd... Loïc Dachary
05:56 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rgw... Loïc Dachary
05:56 AM Stable releases Tasks #14692: hammer v0.94.7
h3. upgrade... Loïc Dachary
05:55 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rados... Loïc Dachary
05:54 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
04:34 AM Revision 86e2987f (ceph): Merge pull request #7805 from ErwanAliasr1/evelu-check-btrfs
Fixing BTFS issue at 'make check'
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:54 AM rbd Feature #14264 (Resolved): async rbd_open() option
Haomai Wang
02:49 AM Revision c63baebb (ceph): global: do not start two daemons with a single pid-file (part 2)
Fixes the following bugs:
* the fd is open(O_WRONLY) and cannot be read from, safe_read
always fails and never rem...
Loic Dachary
02:45 AM Revision e236ebdc (ceph): Merge pull request #7802 from branch-predictor/bp-increase-async-threads
config: increase default async op threads
Reviewed-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
02:20 AM Bug #14872 (Resolved): OSD: wrong return-type of find_osd_on_ip()
bool OSDMap::find_osd_on_ip(const entity_addr_t& ip) const
{
for (int i=0; i<max_osd; i++)
if (exists(...
xie xingguo

02/25/2016

11:57 PM Bug #14871: selinux: handle lock files better
The '/run/lock/ceph-disk' path is actually a '/var/lock/ceph-disk' in the source code. The '/var/lock' directory is a... Boris Ranto
10:42 PM Bug #14871 (Resolved): selinux: handle lock files better
We are hitting a couple of denials like these. This suggests that our policy does not label the lock files properly a... Boris Ranto
11:24 PM Bug #14766: OSD reporting ENOTEMPTY and crashing
With quite reasonable statistics, now I can say that its these files which are left behind in collections....although... Jeffrey McDonald
05:05 PM Bug #14766: OSD reporting ENOTEMPTY and crashing
Loic, can you take a look at this one? Samuel Just
04:12 PM Bug #14766: OSD reporting ENOTEMPTY and crashing
In the collections, there typically seems to be one type of file left aside from the directory structure:
I can giv...
Jeffrey McDonald
10:25 PM Revision 28d42dc8 (ceph): Merge backport pull request #6545 into wip-14077-hammer
A commit skipped because remove_coll() still needed in Hammer David Zafman
10:25 PM Revision 9144c383 (ceph): Merge backport pull request #5783 into wip-14077-hammer
David Zafman
10:25 PM Revision fd74fbf0 (ceph): Merge backport pull request #5031 into wip-14077-hammer
David Zafman
10:24 PM Revision 4309fa87 (ceph): Merge backport pull request #5842 into wip-14077-hammer
David Zafman
10:24 PM Revision de5e11ec (ceph): Merge backport pull request #5127 into wip-14077-hammer
David Zafman
10:23 PM Revision 7698e6c5 (ceph): Merge backport 6 commits from pull request #5197 into wip-14077-hammer
Excludes the ceph-objectstore-tool meta-list op David Zafman
10:22 PM Revision c8057c69 (ceph): Merge backport branch 'wip-temp' into wip-14077-hammer
David Zafman
10:21 PM Revision ecbf6d28 (ceph): Merge backport pull request #4932 into wip-14077-hammer
David Zafman
10:20 PM Revision 34153127 (ceph): Merge backport pull request #4915 into wip-14077-hammer
David Zafman
10:20 PM Revision e022b5b5 (ceph): Merge backport 1 commit from pull request #4863 into wip-14077-hammer
David Zafman
10:18 PM Revision 4ed44e1e (ceph): Merge backport 8 commits from pull request #4784 into wip-14077-hammer
Only excludes actual fix for #10794 David Zafman
10:15 PM Revision 3f0fc84c (ceph): Merge backport 41 commits from pull request #4473 into wip-14077-hammer
David Zafman
10:13 PM Revision db68c6cb (ceph): Merge backport branch 'wip-journal-header' of git://github.com/XinzeChi...
Includes a change to the code in the original merge commit itself David Zafman
10:13 PM Revision c3d938d8 (ceph): Merge backport 1 commit of pull request #3686 into wip-14077-hammer
David Zafman
09:46 PM Bug #14870 (Resolved): selinux 'dac_override' denials
We are hitting a couple of denials like these. This suggests that we are accessing files owned by a regular ceph user... Boris Ranto
09:01 PM devops Fix #14828 (Fix Under Review): ceph Resource Agent does not work with systemd
-*jewel PR*: https://github.com/ceph/ceph/pull/7810- Nathan Cutler
08:50 PM Revision efc2183b (ceph): test: Remove redundant test output
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e6f1bdcd310bd6417f0f695fba3430fd0edba43d)
David Zafman
08:50 PM Revision 9282c1d0 (ceph): ceph-objectstore-tool: Add dry-run checking to ops missing it
Update test to check most operations
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e89...
David Zafman
08:50 PM Revision 7b800b7c (ceph): ceph-objectstore-tool: Add undocumented clear-snapset command for testing
Add test cases using new feature to corrupt SnapSet
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked ...
David Zafman
08:50 PM Revision 78b13f5d (ceph): ceph-objectstore-tool: Improve object spec error handling
Add test cases
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit caf2d5970b0a3e3ce4ef941d1...
David Zafman
08:50 PM Revision 8f88b442 (ceph): osd: Fix trim_object() to not crash on corrupt snapset
Add test case to check for trim_object() osd crash
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked f...
David Zafman
08:50 PM Revision e92505be (ceph): ceph-objectstore-tool: Add new remove-clone-metadata object op
Fixes: #12740
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit c6d283f0f16347a13418d8a0ed...
David Zafman
08:50 PM Revision 6c51e483 (ceph): test: Eliminate check for bogus "obj13/head snaps empty" error
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 8227b4b75c24b632e637decbe4b818606e8589ee)
David Zafman
08:50 PM Revision 37be9599 (ceph): rados: Minor output changes for consistency across operations
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 016ed34ce85fa111f54857a8ca1002ae32b52b8e)
David Zafman
08:50 PM Revision 0988b123 (ceph): osd, test: Keep missing count and log number of missing clones
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 2e0bb0ae9498fd9a0c49f1b81bf0c86f7a7cac42)...
David Zafman
08:50 PM Revision 59fee8a6 (ceph): test: Add test cases for xattr and omap ceph-objectstore-tool operations
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit cbaed6a8c737f77e68a0eb7f1fca32ec4155f045)
David Zafman
08:50 PM Revision b8c9507f (ceph): osd, test: When head missing a snapset, clones not an error
Fix log message for this case and make into "info"
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked f...
David Zafman
08:50 PM Revision 750f8173 (ceph): test: Fix verify() used after import to also check xattr and omap
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 92d00f22805599c519806c6ff6164847b5c33931)
David Zafman
08:50 PM Revision 6afb5d3b (ceph): osd: Use boost::optional instead of snap 0 for "all_clones"
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 310bf784b7cd8d75f2ab7ee431bc764f5b312aa2)
David Zafman
08:50 PM Revision 995a0042 (ceph): test: Verify replicated PG beyond just data after vstart
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 9a29c5983cd392e4b479b6b685fb0c3797c10cd2)
David Zafman
08:50 PM Revision 32266154 (ceph): test: osd-scrub-snaps.sh uses ceph-helpers.sh and added to make check
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d712737be1aadb38ecc3882200999d79d748cdb8)...
David Zafman
08:50 PM Revision 3a1b5883 (ceph): osd: Fix log message name of ceph-objectstore-tool
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 545e4b2c582625f8b93502266ca59ee40e0d0e5f)
David Zafman
08:50 PM Revision 18af852a (ceph): osd: Make the _scrub routine produce good output and detect errors prop...
Catch decode errors so osd doesn't crash on corrupt OI_ATTR or SS_ATTR
Use boost::optional<> to make current state cl...
David Zafman
08:50 PM Revision 7103e74e (ceph): osd: Better SnapSet scrub checking (find issues instead of asserting)
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 3b381caaad20c683a330e8b7a4e1c017abcb60df)
David Zafman
08:50 PM Revision 3af8f9e8 (ceph): osd: Additional _scrub() check for snapset inconsistency
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 9e48e1801ea1a10ce495b3947da06676c2f5f72f)
David Zafman
08:50 PM Revision 113d5c75 (ceph): osd: Don't crash if OI_ATTR attribute is missing or corrupt
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e0b39650028205e9d9e314b75c444cc8cf055a31)
David Zafman
08:50 PM Revision c8e27725 (ceph): test: Test scrubbing of snapshot problems
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e5ad33ec07ee9fffe862d84955a566261d101713)
David Zafman
08:50 PM Revision 0f785646 (ceph): tools/rados: Improve xattr import handling so future internal xattrs ig...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 9222f56403cf52ec161a38fc437a3f04c24d1625)...
David Zafman
08:50 PM Revision 26cbf14e (ceph): ceph-objectstore-tool: White space fixes
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 0564f398269d920d90f6d6ecb008ebcd6609d611)
David Zafman
08:50 PM Revision ad7825a4 (ceph): ceph-objectstore-tool: Improve some error messages
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit b0c884ba8b51eedf9def093c61f0f06398101ecc)
David Zafman
08:50 PM Revision fd518e70 (ceph): ceph-objectstore-tool: For corrupt objectstores, don't abort listing on...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d276d3286504ea702ae561b91dff4121c99feb9a)...
David Zafman
08:50 PM Revision a46fc661 (ceph): test: Add some clones to ceph-objectstore-tool test
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit b4ba3e66548a5dee58553df071b916c85d701caf)
David Zafman
08:50 PM Revision 53dc87f8 (ceph): ceph-objectstore-tool: Enhanced dump command replaces dump-info
Show object stat information from objectstore
Show SnapSet if present
Add --head for search by object name
Signed-of...
David Zafman
08:50 PM Revision 7f398bd2 (ceph): ceph-objectstore-tool: Add set-size command for objects
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 138a33b8946e6fea1e09527b8bc45b7aa4bee1d6)...
David Zafman
08:50 PM Revision cfe7d47d (ceph): tools: Check and specify commands that require the pgid specification
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 5534bc864813d96a0d20791d79151c4f6695a013)
David Zafman
08:50 PM Revision c60eee1d (ceph): tools/ceph-objectstore-tool: add "set-osdmap" command
Fixes: #12193
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 3e30c1746fb8d90b04e4776849069db0...
Kefu Chai
08:50 PM Revision 3f9e4677 (ceph): tools: Fix dump-super which doesn't require pgid
A valid pgid had to be specified in order for superblock to be displayed,
but it was otherwise ignored.
Fix message t...
David Zafman
08:50 PM Revision e44c042c (ceph): tools/ceph-objectstore-tool: add "get-osdmap" command
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit f0c130d6b1bc2a8a0cce6d78a6e69995fe00a427)
Con...
Kefu Chai
08:50 PM Revision 06dcf743 (ceph): tools: Fix newlines in output of --op list
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 6aec38b51f0c14684912b5ee28fb5b1375cb8f8a)
David Zafman
08:50 PM Revision be24c50b (ceph): tools/ceph-objectstore-tool: add set-inc-osdmap command
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 95344d07c3a1a9a6b1246e5eca3f7daeb062dd06)
Con...
Kefu Chai
08:50 PM Revision c7d0fda0 (ceph): tools: Check for valid --op earlier so we can get a better error message
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d8460714fab61d0a3092b3e7b290c0c19ad58beb)...
David Zafman
08:50 PM Revision cfabcc10 (ceph): tools/ceph-objectstore-tool: add get-inc-osdmap command
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 7801bb20d23ce83fc4093c23331bcb75e43c878f)
Con...
Kefu Chai
08:50 PM Revision 3276258b (ceph): tools, test: Some ceph-objectstore-tool error handling fixes
Improve various error messages generated with invalid syntax
Add test cases for most of these error messages
Signed-...
David Zafman
08:50 PM Revision 5ba86494 (ceph): test: add test for {get,set}-osdmap commands
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 0257c150fe552300c0d9f5a22a27aaa49fb6cc64)
Con...
Kefu Chai
08:50 PM Revision 0643797c (ceph): rados: Fix usage for "notify" command
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit b968fb3bcefb0cdafb1e84d7c679b61a201a940f)
David Zafman
08:50 PM Revision de80bbf4 (ceph): test: Add debug argument to the ceph-objectstore-tool test
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit a3b14ede9e829ec85c49980ecbff11f584ca70ae)
David Zafman
08:50 PM Revision 6ff42173 (ceph): test: add test for {get,set}-inc-osdmap commands.
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 818de1a2c89272d98610328a958fea06d1cc41cc)
Con...
Kefu Chai
08:50 PM Revision 1bc88827 (ceph): test: Fix failure test to find message anywhere in stderr
Consolidate test_failure() and test_failure_tty()
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked fr...
David Zafman
08:50 PM Revision 0fe3dfe8 (ceph): ceph-objectstore-tool: add mark-complete operation
It is supposed to be used as a last resort to fix a cluster that has
PGs in 'incomplete' state, using the following p...
Mykola Golub
08:50 PM Revision feecacfb (ceph): ceph-objectstore-tool: Add dump-journal as not requiring --pgid in usage
Additional comment describes --pgid requirement checking
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry pi...
David Zafman
08:50 PM Revision 4dcf15bc (ceph): mds, include: Fix dump() numeric char array to include additional alpha...
Caused by: c87f55b5a8b3e003726e1be22b9cb6894ef2f37d
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked ...
David Zafman
08:50 PM Revision af3f8ae1 (ceph): ceph-objectstore-tool: Add dump-super to show OSDSuperblock in format s...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 99d7663f870abfa82711dbf0451334f7d6c883d8)
David Zafman
08:50 PM Revision aed1c49e (ceph): ceph-objectstore-tool: Invalidate pg stats when objects were skipped du...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 51e27984ec131fd21bbc26411ae1540b9047eb37)
David Zafman
08:50 PM Revision 444ce0ac (ceph): ceph-objectstore-tool: Allow --pgid specified on import (for post split)
Revamp split import testing to use --pgid option post split
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry...
David Zafman
08:50 PM Revision 13360d3a (ceph): test/ceph_objectstore_tool: Improve dump-journal testing
Fix false failure when journal has no entries
Test dump-journal on all osds in 2 places
Signed-off-by: David Zafman ...
David Zafman
08:50 PM Revision 3d99ecd6 (ceph): tools: Don't export temporary objects until we have persistent-temp obj...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 4fcf5dd370e8cfac75fadbf709a785053eb26ad9)...
David Zafman
08:50 PM Revision 88ac5198 (ceph): test: Add config changes to all tests to avoid order dependency
ReplayCorrupt was crashing because journal_ignore_corruption wasn't set true
Improve ReplayCorrupt by checking settin...
David Zafman
08:50 PM Revision efc402ea (ceph): test/ceph-objectstore-tool: Show command that should have failed
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 23551deea66673c35d7183d18b63b5a8438ebf00)
David Zafman
08:50 PM Revision d58793d1 (ceph): osd, tools: Always filter temp objects since not being exported
Can't use object_locator_to_pg() directly with a temp object
because the pool is negative.
Signed-off-by: David Zafm...
David Zafman
08:50 PM Revision eab0f240 (ceph): osd: Show number of divergent_priors in log message
Report dirty_divergent_priors as true or false
Use dout(5) so tests can verify divergent_priors created
Signed-off-b...
David Zafman
08:50 PM Revision 78a59f8b (ceph): test/ceph-objectstore-tool: Don't need stderr noise
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d7858c66454093dd6f2fab60e33e5b2472bcd80a)
David Zafman
08:50 PM Revision 9ca2f35d (ceph): tools: clean up errors in ceph-objectstore-tool
We use negative error codes everywhere else, should
use them here too. Also add a couple of strategically
placed pri...
John Spray
08:50 PM Revision 87a7f991 (ceph): tools: For ec pools list objects in all shards if the pgid doesn't specify
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 1aa9655f10b0fcc42cb5114681b8b24a2ccb68f4)
David Zafman
08:50 PM Revision 6c8884b1 (ceph): test, tools: Improve ceph-objectstore-tool import error handling and ad...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit ddc4d52782a04d99a4293c9fc278894dfe328515)
David Zafman
08:50 PM Revision df0e11e7 (ceph): hobject_t: modify operator<<
Put the most significant fields to the left so that it matches the sort
order. Also use unambiguous separator when t...
Sage Weil
08:50 PM Revision 99d3e17f (ceph): osd: Add simple_dump() to FileJournal for unit testing
Allow a dump when entries aren't ObjectStore::Transaction's
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry...
David Zafman
08:50 PM Revision f7ab316b (ceph): osd: FileJournal: Add _fdump() that takes Formatter instead of ostream
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 130eba48495d0e6acd8a472cbf0c47ebbc7a038c)
David Zafman
08:50 PM Revision 33813b66 (ceph): test: Fix ceph-objectstore-tool test, overwrite OTHERFILE so second che...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 1b9f85befa1efff3b05b2af0e62d568eea37d790)
David Zafman
08:50 PM Revision 729abf5a (ceph): test: Pep8 fixes for ceph-objectstore-tool test
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit b0141108c0596b535d25792a9102787b1cd3eca3)
David Zafman
08:50 PM Revision b4ac42be (ceph): test: Test ceph-objectstore-tool --op dump-journal output
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 9b08bcf95caf77fb7f9bd293559534ed8ff3eded)...
David Zafman
08:50 PM Revision 09cb8a41 (ceph): test: Add optional arg to vstart() to provide additional args to vstart
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit dff17a800c9cc1cf0cc23d70479c031aa8e9cbfc)
David Zafman
08:50 PM Revision b337d677 (ceph): test: Limit how long ceph-objectstore-tool test will wait for health
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 868cf457a3990ba9989aef55823630e3189acf4a)
David Zafman
08:50 PM Revision 4f387b1e (ceph): test: Use CEPH_DIR where appropriate
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 1e18e8a88f88809081684b09f36691cd724720b5)
David Zafman
08:50 PM Revision 771dcd94 (ceph): test: ceph-objectstore-tool import after split testing
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d80ce6668c1aa3c9898ab49e847c4dadafe256f0)
David Zafman
08:50 PM Revision 848822db (ceph): test: ceph-objectstore-tool: Remove duplicate debug messages, keep cmd/...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 94b3d7632f2548c19beca5a2e024c95f601b61f3)
David Zafman
08:50 PM Revision b5f2ccd5 (ceph): test: Fix ceph-objectstore-tool test error message
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 11c13eb7c182870727fbcb25a83f3348ac0bad13)
David Zafman
08:50 PM Revision ab893d76 (ceph): test: Fix ceph-objectstore-tool test missing fd.close()
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit ece630d5a741ba8c82f55f964f1887cb7fcaa493)
David Zafman
08:50 PM Revision 2078f639 (ceph): test: ceph_test_filejournal Add check of journalq in WriteTrim test
Commit all journal entries and check for empty journalq
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry pic...
David Zafman
08:50 PM Revision 06d3f512 (ceph): test: ceph_test_filejournal fix missing argument to FileJournal constru...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit c94fe8db36e7d54227edde94a99bc1aa236b8ec8)
David Zafman
08:50 PM Revision c161cbf8 (ceph): test: ceph_test_filejournal need to force aio because testing with a file
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit d540dde1faee47d01ee358ae384fa301fa59f00f)
David Zafman
08:50 PM Revision 5e8fbb18 (ceph): test: ceph_test_filejournal: Conform to test infrastructure requirements
Only call RUN_ALL_TESTS() once
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit e30efe6c1...
David Zafman
08:50 PM Revision 83de86e4 (ceph): ceph-objectstore-tool: Create section around log/missing/divergent_prio...
Remove extra new lines in the output
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 548...
David Zafman
08:50 PM Revision 7947f4f7 (ceph): ceph-objectstore-tool: Clean up error handling
Use negative errors throughout and positive error to specify exit status
cpp_strerror() handles negative errors
Clean...
David Zafman
08:50 PM Revision 3a533d76 (ceph): ceph-objectstore-tool: Add a couple of strategically placed prints
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit fdb1a4b676765c5d3ca5d436f34230dd6996d7a7)
John Spray
08:50 PM Revision 2d764c54 (ceph): ceph-objectstore-tool: Use empty string for <object> to specify pgmeta ...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit c00290b836adba12212e8a57f13b0c9193ac0ef8)
David Zafman
08:50 PM Revision 05d3b73a (ceph): ceph-objectstore-tool: Add dump-info command to show object info
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 244092d034781d2e980f9de7c6f9eea227967c5a)
David Zafman
08:50 PM Revision 35991747 (ceph): ceph-objectstore-tool: Add --dry-run option
Fixes: #10290
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 2795161f470ab87cf4a82f4557...
David Zafman
08:50 PM Revision 2dbf8435 (ceph): ceph-objectstore-tool: Remove list-lost because now we have --dry-run flag
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 3e7fe7e85716f80e055ffbc5305f406b3e020608)
David Zafman
08:50 PM Revision d8ae1a9b (ceph): ceph-objectstore-tool: Add --no-overwrite flag for import-rados
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 35cdcabbdad7dc7249029630c64022c822c67ddc)
David Zafman
08:50 PM Revision cc5fa68c (ceph): ceph-objectstore-tool: If object re-appears after removal, just skip it
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit c6e41663e7434b4dcbb1abbe62ac008388da268a)
David Zafman
08:50 PM Revision 4ae3f88c (ceph): ceph-objectstore-tool: For import/export --debug dump the log
Move log dumping code to common function dump_log()
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked ...
David Zafman
08:50 PM Revision a935ce50 (ceph): osd: Add admin socket feature set_recovery_delay
Set the value of osd_recovery_delay_start to specified seconds
Signed-off-by: David Zafman <dzafman@redhat.com>
(che...
David Zafman
08:50 PM Revision 288902fe (ceph): osd: Fix flushing in FileJournal::dump()
Use ostream arg since caller is specifying
Move flush after last section close
Signed-off-by: David Zafman <dzafman@...
David Zafman
08:50 PM Revision 21c3c18c (ceph): osd: FileJournal::read_entry() can't use a zero seq to check for corrup...
Seen when using dump() on a journal which has all entries committed
Signed-off-by: David Zafman <dzafman@redhat.com>...
David Zafman
08:50 PM Revision b8f4ea17 (ceph): osd: Dump header in FileJournal::dump()
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 3c97b32131e83c934b3d340eeb75284e898380c4)
David Zafman
08:50 PM Revision 80fc57f7 (ceph): osd: FileJournal clean-up
Move aio / directio adjustments to constructor
Indicate functions which only operate before journal is active
Make fu...
David Zafman
08:50 PM Revision c5ac7ce0 (ceph): ceph-objectstore-tool: Check pgid validity earlier like we did before
This code was not doing the umount() even though it was moved after mount()
Signed-off-by: David Zafman <dzafman@red...
David Zafman
08:50 PM Revision 9da6c01b (ceph): ceph-objectstore-tool: Eliminate obscure "Invalid params" error
Will fail later with "No such file or directory" for an empty data-path
because we've already checked for vm.count("d...
David Zafman
08:50 PM Revision 7445cf5a (ceph): ceph-objectstore-tool: Check for keyvaluestore experimental feature
Don't list keyvaluestore as a valid type if feature not enabled
Signed-off-by: David Zafman <dzafman@redhat.com>
(ch...
David Zafman
08:50 PM Revision aaff4d7b (ceph): ceph-objectstore-tool: On any exit release CephContext so logging can f...
Add myexit() which will put() the g_ceph_context if present before exit
Must umount() once the objectstore has been m...
David Zafman
08:50 PM Revision 3e68825e (ceph): ceph-objectstore-tool: Add dump-journal op
Have dump-journal op directly dump a filestore journal without
mounting or try to dump after mounting.
Fixes: #11135...
David Zafman
08:50 PM Revision f3327489 (ceph): ceph-objectstore-tool: Fix pgid scan to skip snapdirs
Long standing bug where it wasn't skipping snapdirs if !debug
For debug output use stderr like all other cases
Signe...
David Zafman
08:50 PM Revision add937c4 (ceph): ceph-objectstore-tool: Add --force option which is used for import only
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 2f4090daaea715b896e49f678933abb8a13b5c98)
David Zafman
08:50 PM Revision ddfaa70a (ceph): ceph-objectstore-tool: Add divergent_priors handling
Add to --op log output
Add to metadata_section for export
Add filtering of divergent_priors in case of splits
Fixes:...
David Zafman
08:36 PM Linux kernel client Bug #14232: Kernel NULL pointer dereference in __dcache_readdir
Took a while, but found a very similar one with 4.4.1 using only a few patches:... Markus Blank-Burian
08:33 PM Revision 18c49b64 (ceph): Backport the merge commit of branch 'wip-journal-header' of git://githu...
(cherry picked from commit 8d596bfa24c9c3e2aadbb87494284cb5fd824e55)
Conflicts:
src/os/FileJournal.cc (trivial)
sr...
Sage Weil
08:09 PM Revision 5f935455 (ceph): Merge pull request #7808 from cbodley/wip-cmake-jerasure
cmake: add ErasureCode.cc to jerasure plugins Ali Maredia
08:04 PM rbd Subtask #14869 (Resolved): journal library should re-use thread pool and timer
This will allow the RBD mirror daemon to not need to allocate two threads per image. Jason Dillaman
07:58 PM Revision 753221e2 (ceph): cmake: add ErasureCode.cc to jerasure plugins
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
07:44 PM Revision aa92f9df (ceph): rgw: link against system openssl (instead of dlopen at runtime)
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
07:13 PM Revision 88ee4e75 (ceph): osd/,messages/: add MOSDPGUpdateLogMissing[Reply]
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
07:13 PM Revision e7edf20f (ceph): osd/: Use MOSDPGUpdateLogMissing to implement mark_unfound_lost_delete ...
Using a MOSDPGLog was unsafe since it is not ordered with
respect to repops. Instead, use a new message sent through...
Samuel Just
07:13 PM Revision b8e58431 (ceph): os/: add try_rename
Similar to collection_move_rename, except we ignore ENOENT and
don't allow different collections.
Signed-off-by: Sam...
Samuel Just
07:11 PM Revision a00bed34 (ceph): FileStore: use BackoffThrottle for the op queue
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
07:11 PM Revision 83baa1f8 (ceph): FileJournal: use queue size explicitely in aio backoff
Using the throttle here is sketchy, mainly because we won't wake
up if something new is queued. Let's do it explicit...
Samuel Just
07:11 PM Revision f54e563c (ceph): Journal: replace the journal throttle with fullness backoff throttle
The existing FileJournal::throttle_(ops|bytes) throttles overlap with
the FileStore op queue throttles. It doesn't s...
Samuel Just
07:11 PM Revision c9861a0f (ceph): doc/.../throttles*: update the docs to reflect the throttle changes
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
07:11 PM Revision 9f4cba31 (ceph): Throttle: add BackoffThrottle unit tests
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
07:11 PM Revision b0a8b1ce (ceph): throttle: add a BackoffThrottle implementation
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
07:09 PM Bug #14796 (Fix Under Review): test/osd/osd-markdown.sh has too-aggressive timing restrictions
Dan Mick
07:06 PM Revision 0dd061c3 (ceph): Merge pull request #7748 from ceph/wip-cmake-2-22-16
cmake: fix paths to various EC source files Casey Bodley
07:02 PM Revision 83b4aab3 (ceph): cmake: installing _tp libraries into lib
Signed-off-by: Ali Maredia <amaredia@redhat.com> Ali Maredia
06:56 PM Revision 612fd334 (ceph): ReplicatedPG::RepGather: remove on_finish, no more users
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 0a5b4c1d (ceph): src/osd: use unique_ptr for backend trasaction, move into submit_transa...
submit_transaction takes ownership of the transaction implicitely. Make
this implicit using an rvalue ref to force u...
Samuel Just
06:56 PM Revision 7ae52fcf (ceph): osd_types: add ObcLockManager
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 82896f2c (ceph): ReplicatedPG::close_op_ctx: the err argument is unused
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision e68b5507 (ceph): ReplicatedPG: refactor OpContext to use ObcLockManager
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 43f3d829 (ceph): ReplicatedPG: s/release_op_ctx_locks/release_object_locks, don't use op...
This gets us one step closer to removing OpContext from Repop.
Signed-off-by: Samuel Just <sjust@redhat.com>
Samuel Just
06:56 PM Revision 257225d3 (ceph): ReplicatedPG: remove OpContext from Repop
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision b1151c4b (ceph): ECBackend: send subop writes and reads at normal priority
We want these to be processed ahead of new client ops since
there are resources being held.
Fixes: 14313
Backport: h...
Samuel Just
06:56 PM Revision d3eac8fe (ceph): ECBackend: use CEPH_MSG_PRIO_HIGH for write replies
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision b33dd14e (ceph): dout.h: add a DoutPrefixProvider and macro to allow passing of prefixes
This way, we can get proper logging within static functions.
Signed-off-by: Samuel Just <sjust@redhat.com>
Samuel Just
06:56 PM Revision 50e4e2c7 (ceph): PG,PGLog: convert to DoutPrefixProviders
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 7eadf88b (ceph): PGLog::merge_log: update missing, after removing divergent
This should not change behavior at all. It'll be useful in
the next few commits.
Signed-off-by: Samuel Just <sjust@...
Samuel Just
06:56 PM Revision 430027f7 (ceph): PGLog: factor out claim_log_entries_update_missing
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 6db7fe7d (ceph): introduce CEPH_FEATURE_SERVER_JEWEL feature bit
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 51102143 (ceph): osd/: replace simple_repop_.* with simple_opc_.*
This way, we don't expose the RepGather structure
up into the users (which pretty much exclusively
use the repop->ctx...
Samuel Just
06:56 PM Revision cc1b2c6f (ceph): ReplicatedPG: move client reply handling out of eval_repop
execute_ctx is the only path which actually has a client op,
let's clarify eval_repop by moving that logic inline the...
Samuel Just
06:56 PM Revision e4c53560 (ceph): ReplicatedPG: break out complete_disconnect_watches helper
We'll need this shortly when we remove do_osd_op_effects from
eval_repop.
Signed-off-by: Samuel Just <sjust@redhat.com>
Samuel Just
06:56 PM Revision 90a5359b (ceph): ReplicatedPG: move do_osd_op_effects out of eval_repop
This is better anyway, do_osd_op_effects on a non-client op was somewhat
silly without an op (even if you filled in t...
Samuel Just
06:56 PM Revision 8e82deaf (ceph): ReplicatedPG::scrub: use register_on_commit rather than on_finish
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:56 PM Revision 1ef04ddf (ceph): ReplicatedPG: use register_on_finish rather than on_finish for flush/evict
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
06:48 PM Revision 2e4ad9ea (ceph): cmake: Removed _tp libraries from linking
Signed-off-by: Ali Maredia <amaredia@redhat.com> Ali Maredia
05:45 PM Bug #11930 (Can't reproduce): test/ceph_objectstore_tool.py fails with OSD has the store locked
I bet this has been fixed, but if not reopen. David Zafman
05:44 PM Revision dc54a856 (ceph): debian: fix logrotate conf handling
Fixes a failure to build from source; fallout from the server split
change (0cbe3dea69604730bc7dba7bc3844294f4c9ac5a)...
Ken Dreyer
05:44 PM Revision 9a66bf00 (ceph): debian: put libexec files in /usr/lib
SUSE does not allow the use of /usr/libexec, so commit
69291f872e7dd20e88c052cfc220e02d59826c0f changed the RPM
packa...
Ken Dreyer
05:42 PM devops Backport #14769 (Resolved): hammer: Fix message on attempt to use tell in interactive mode
David Zafman
05:34 PM Revision 18da92f3 (ceph): rgw: add support for caching of Keystone admin token.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
05:28 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
mon-eng-05-03 is 10.3.20.169. This is a test cluster with only 1 mon. Steve Taylor
08:41 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
i received the mon log from Steve.
the monitor was holding 20 osdmaps (856-876), right before the log is collected...
Kefu Chai
05:14 PM Revision c2e61029 (ceph): test/ceph_objectstore_tool: Deleting btrfs subvolumes before exiting
When running the ceph_objectstore_tool test suite, we shall delete the btrfs
subvolumes that have been created before...
Erwan Velu
04:40 PM rbd Feature #14867 (Resolved): add object map verifier to RBD CLI
Add rbd object-map verify to the RBD CLI that reads the object map and compares it with a rebuilt one from the availa... Douglas Fuller
03:54 PM Backport #14765 (Resolved): hammer: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
Kefu Chai
03:54 PM Bug #13748 (Resolved): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
Kefu Chai
03:46 PM Revision 9ae89269 (ceph): ceph-helpers: Delete remaining subvolumes on destroy_osd()
Before deleting $dir/$id, we have to delete the associated subvolumes unless the
rm will fail.
Signed-off-by: Erwan ...
Erwan Velu
03:39 PM Revision 546a7b98 (ceph): Merge pull request #7656 from dzafman/wip-14769-hammer
ceph.in: Notify user that 'tell' can't be used in interactive mode
Reviewed-by: Loic Dachary <ldachary@redhat.com>
R...
Loïc Dachary
03:37 PM Revision 6b7660c9 (ceph): Merge pull request #7648 from tchaikov/wip-13783-hammer
mon/LogMonitor: use the configured facility if log to syslog
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:35 PM rbd Bug #14822 (Fix Under Review): Journal replay needs to support replaying successful maintenance ops
*PR*: https://github.com/ceph/ceph/pull/7785 Jason Dillaman
03:33 PM Revision 0c44f20a (ceph): Merge pull request #7793 from tchaikov/wip-fix-dencoder-MirrorImage
cls_rbd: fix the test for ceph-dencoder
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
03:24 PM Revision 9dbac6c3 (ceph): os/kstore: fix a race condition in _txc_finish()
{} was missed, which limits the scope of the lock_guard.
osr->qlock has to be unlocked before calling _osr_reap_done(...
Jianjian Huo
03:16 PM rgw Bug #14826: rgw: bucket listing following object delete is partial
https://github.com/ceph/ceph/pull/7803 Orit Wasserman
03:11 PM Revision e23fdcbb (ceph): rgw: reset return code in when iterating over the bucket the objects
Fixes: #14826
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
03:07 PM Revision a7042702 (ceph): cls_rbd: fix the test for ceph-dencoder
initialize MirrorImage::state to a certain value, otherwise the
generated test instances would be undetermined, and h...
Kefu Chai
03:06 PM RADOS Feature #14865 (New): Permit cache eviction of watched object
If all watchers are using the non-legacy watch interface, permit the cache to evict a watched object on-demand. The ... Jason Dillaman
03:04 PM Revision 7131c977 (ceph): Merge pull request #7792 from tchaikov/wip-13505
fix FTBFS introduced by d0af316
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:58 PM Bug #14864 (Resolved): ceph-detect-init requires python-setuptools at runtime
Testing a reasonably recent ceph-10.0.2 on openSUSE Leap 42.1, my OSDs weren't mounting. I tracked this back to /usr... Tim Serong
02:33 PM Revision cd0389dd (ceph): ceph-helpers.sh: Deleting forgoten btrfs subvolumes
While running a make check on a btrfs system, many subvolumes are let at the end
of the build. It's pretty common to ...
Erwan Velu
02:26 PM Revision cf433bac (ceph): global/pidfile: do not start two daemons with a single pid-file
add functions named pidfile_open and pidfile_verify to avoid starting two daemons by a single pid-file
Fixes: #13422...
shun song
02:12 PM Revision ba70bdb3 (ceph): config: increase default async op threads
Default value of two async threads is enough for light workloads,
but is insufficient for heavy ones, reducing maximu...
Piotr Dałek
02:03 PM Revision 61ab9e8e (ceph): Merge pull request #7731 from SUSE/wip-shebang
ceph_detect_init/__init__.py: remove shebang
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
01:47 PM Revision b0b40219 (ceph): pybind: fix the FTBFS introduced by d0af316
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
01:47 PM Revision 557c3bfe (ceph): osd: always cleanup the scrub results
the destructor of Scrub::Store asserts that `this->results` should
always be empty when it is free'd. before this cha...
Kefu Chai
12:54 PM CephFS Bug #14732: open returns EACCES when O_TRUNC is specified and write permission is denied (hammer)
Sorry, it's my fault.
I added two extra commits to https://github.com/ceph/ceph/pull/6604
Zheng Yan
12:39 PM Revision e34c2094 (ceph): Merge pull request #7801 from dachary/wip-14863-hammer
hammer: unittest_crypto: benchmark 100,000 CryptoKey::encrypt() calls
Reviewed-by: Nathan Cutler <ncutler@suse.cz>
Loïc Dachary
12:07 PM Revision b43c5b20 (ceph): unittest_crypto: benchmark 100,000 CryptoKey::encrypt() calls
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit fb4b6c52d8e31e8dedfa8aecc16c389f0e7d86cf)
Conf...
Sage Weil
12:06 PM rbd Backport #14863: hammer: test/crypto.cc:161:43: error: ‘ceph_clock_now’ was not declared in this ...
https://github.com/ceph/ceph/commit/fb4b6c52d8e31e8dedfa8aecc16c389f0e7d86cf was partially included as part of https:... Loïc Dachary
12:04 PM rbd Backport #14863 (Resolved): hammer: test/crypto.cc:161:43: error: ‘ceph_clock_now’ was not declar...
https://github.com/ceph/ceph/pull/7801 Loïc Dachary
11:07 AM Revision 23f3d309 (ceph): qa/workunits: add test for setting scrub priority
Signed-off-by: Zhiqiang Wang <zhiqiang@xsky.com> Zhiqiang Wang
11:06 AM Revision 3241011c (ceph): osd: add the support of per pool scrub priority
ceph osd pool get pool_name scrub_priority
ceph osd pool set pool_name scrub_priority x
Signed-off-by: Zhiqiang Wang...
Zhiqiang Wang
10:55 AM Backport #14231: hammer: ceph-disk fails to work with udev generated symlinks
We don't have good enough test coverage in hammer for me to feel comfortable with the proposed change. It may introdu... Loïc Dachary
10:38 AM Bug #14862: utime.h: fix timezone issue in round_to_* funcs.
https://github.com/ceph/ceph/pull/7789 Chao Zhao
10:36 AM Bug #14862 (Resolved): utime.h: fix timezone issue in round_to_* funcs.
gmtime_r converts local time to UTC, however mktime only takes an argument as local time. Use localtime_r instead of ... Chao Zhao
09:18 AM Revision a7f3a658 (ceph): mds: avoid creating unnecessary snap dentry/inode
When COW dentry/inode, if there is no snapshot between 'first' and
'follow', updating dentry/inode 's first should be...
Yan, Zheng
09:18 AM Revision 798ad64a (ceph): mds: set multiversion inode's first
For multiversion inode, inode's 'first' can be different to its
parent dentry's 'first'. But when encoding a primary ...
Yan, Zheng
09:17 AM Revision f7fb2cb5 (ceph): mds: fix open snap parents tracking
We may move an inode into its past snap_parent, then move the
inode out again. So there can be multiple entries in sn...
Yan, Zheng
09:12 AM devops Backport #14861 (In Progress): hammer: ceph init script unconditionally sources /lib/lsb/init-fun...
Nathan Cutler
08:35 AM devops Backport #14861 (Resolved): hammer: ceph init script unconditionally sources /lib/lsb/init-functions
https://github.com/ceph/ceph/pull/7797 Nathan Cutler
08:35 AM devops Bug #14402 (Pending Backport): ceph init script unconditionally sources /lib/lsb/init-functions
Nathan Cutler
08:19 AM Revision 67aa66ee (ceph): Merge pull request #7734 from dachary/wip-14834-pidfile-test
tests: test_pidfile.sh lingering processes
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
07:16 AM devops Bug #14756 (Resolved): EC testing plugins are being versioned and installed even though they are ...
Nathan Cutler
06:39 AM Revision ac7d11ad (ceph): librados: add missing tracpoint for scrub APIs
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
06:27 AM Bug #12814: flipping the overlay from forward to seems to reorder writes

Seen again in my hammer backport testing:
description: rados:singleton:all/thrash_cache_writeback_forward_none.y...
David Zafman
06:07 AM rbd Feature #14264: async rbd_open() option
I think the status can be changed to resolved. Mykola Golub
05:41 AM Revision fe5aff3b (ceph): Merge pull request #7637 from SUSE/wip-14756
Refrain from versioning and packaging EC testing plugins
Reviewed-by: Boris Ranto <branto@redhat.com>
Reviewed-by: K...
Loïc Dachary
05:24 AM Revision c1e1c8d1 (ceph): tests: test_pidfile.sh lingering processes
For the mon, using ps aux to find the process will only show part of the
command line and the $RUNID may be missing. ...
Loic Dachary
05:20 AM Feature #14860 (Duplicate): scrub/repair: persist scrub results (do not overwrite deep scrub resu...
this is a spin-off of #13505
> note to myself, in the last discussion with david, he advised that we should not ov...
Kefu Chai
05:10 AM Feature #13506 (In Progress): scrub/repair: add librados APIs
* @get_inconsistent_pgs()@ has been exposed as C API and pybind APIs, but they are not tested by the integration test... Kefu Chai
04:51 AM Revision 2efd4c63 (ceph): Merge pull request #795 from ceph/wip-list-inconsistent-obj
task/scrub_test: tests for list inconsistent obj APIs
Reviewed-by: Samuel Just <sjust@redhat.com>
Kefu Chai
04:48 AM Revision ce1169d2 (ceph): Merge pull request #6898 from tchaikov/wip-13505
add scrub persist/query API
Reviewed-by: Samuel Just <sjust@redhat.com>
Kefu Chai
04:41 AM Revision fb956b74 (ceph): osd: persist inconsistent objs using omap
persist inconsistent objects found when comparing the ScrubMaps
collected from replica/shards. the discrepancies betw...
Kefu Chai
04:41 AM Revision 8ed62772 (ceph): osd/: clear scrub store safetly
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
04:41 AM Revision c828c398 (ceph): librados: add `inconsistent_snapset_t` type
for presenting the inconsistent snapsets found in scrub
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
04:41 AM Revision 2009ed27 (ceph): osd: persist inconsistent snapsets using omap
the inconsistent snapsets are identified in ReplicatedPG::_scrub()
after we compared the authorized objects with thei...
Kefu Chai
04:41 AM Revision 3dea4f1f (ceph): osd: add CEPH_OSD_OP_SCRUBLS pg op
it is a new pg op which returns the encoded objects stored when
scrubbing.
Fixes: #13505
Signed-off-by: Kefu Chai <k...
Kefu Chai
04:41 AM Revision dfc2f482 (ceph): librados: add get_inconsistent_objects() API
Fixes: #13505
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
04:41 AM Revision c9b593d2 (ceph): librados: add get_inconsistent_snapsets() API
Fixes: #13505
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
04:41 AM Revision 8018eab3 (ceph): rados: add "list-inconsistent-obj" cmd
to list inconsistent objects of a given PG, this command exposes
get_inconsistent_objects() rados API to user.
Signe...
Kefu Chai
04:41 AM Revision e2374c43 (ceph): rados: add "list-inconsistent-snapset" cmd
to list inconsistent snapsets of a given PG, this command exposes
get_inconsistent_snapsets() rados API to user.
Fix...
Kefu Chai
04:40 AM Revision 50bbf7f9 (ceph): tools/rados: support more --format options
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
04:40 AM Revision cb4efbd7 (ceph): librados: add get_inconsistent_pgs() to librados
to list the inconsistent PGs of given pool, it's a wrapper
around the "ceph pg ls" command.
Fixes: #13505
Signed-off...
Kefu Chai
04:40 AM Revision d0af316c (ceph): pybind: add Rados.get_inconsistent_pgs method
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
04:40 AM Revision 4c327069 (ceph): rados: add "list-inconsistent-pg" command
to list inconsistent PGs of a given pool. this command exposes
the underlying get_inconsistent_pgs() API to user.
Si...
Kefu Chai
04:40 AM Revision b43d4809 (ceph): librados: add `inconsistent_obj_t` types
which present the inconsistent objects found in scrub
Fixes: #13505
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
04:40 AM Revision f236b7d7 (ceph): osd: more constness to spg_t
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
04:39 AM rgw Backport #13799 (Resolved): hammer: rgw: default quota params
Loïc Dachary
04:39 AM rgw Backport #13887 (Resolved): infernalis: orphans finish segfaults
Loïc Dachary
04:39 AM rgw Backport #14324 (Resolved): infernalis: rgw: radosgw-admin bucket check --fix not work
Loïc Dachary
04:39 AM rgw Backport #14325 (Resolved): hammer: rgw: radosgw-admin bucket check --fix not work
Loïc Dachary
04:39 AM Backport #14493 (Resolved): hammer: make rgw_fronends more forgiving of whitespace
Loïc Dachary
04:38 AM Backport #14579 (Resolved): hammer: mon sync does not copy config-key
Loïc Dachary
04:38 AM RADOS Bug #14858 (New): ceph_test_rados failure due to objectstore tool removing only copy -- need to s...
ubuntu@teuthology:/a/samuelj-2016-02-24_11:43:42-rados-wip-sam-testing-distro-basic-smithi/24832/remote$ Samuel Just
04:28 AM Bug #14856 (Fix Under Review): Clang removes dead code....
https://github.com/ceph/ceph/pull/7790 Kefu Chai
04:27 AM Revision 34c33688 (ceph): rados/singleton/all/pg-removal-interruption: ensure osd.0 is marked down
We were waiting for teh dameon to fail, not for the mons to notice,
which meant that after we restart the daemon the ...
Sage Weil
04:09 AM Revision ec33aec3 (ceph): Merge pull request #7185 from dachary/wip-14325-hammer
hammer: rgw: radosgw-admin bucket check --fix not work
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com>
Loïc Dachary
04:09 AM Revision 4b461829 (ceph): Merge pull request #7188 from dachary/wip-13799-hammer
hammer: rgw: default quota params
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com>
Loïc Dachary
04:08 AM Revision d148ed64 (ceph): Merge pull request #7423 from Abhishekvrshny/wip-14324-infernalis
infernalis: rgw: radosgw-admin bucket check --fix not work
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com>
Loïc Dachary
04:07 AM Revision d9e3ffb2 (ceph): Merge pull request #7424 from Abhishekvrshny/wip-13887-infernalis
infernalis: rgw: orphans finish segfaults
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com>
Loïc Dachary
04:04 AM Revision 722ca62e (ceph): Merge pull request #7414 from dachary/wip-14493-hammer
hammer: make rgw_fronends more forgiving of whitespace
Reviewed-by: Yehuda Sadeh <ysadehwe@redhat.com>
Loïc Dachary
04:01 AM CephFS Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
Christopher Nelson wrote:
> It turns out the main files are too large. Is there any other way I can upload them?
...
Zheng Yan
03:53 AM Revision 2368c98e (ceph): Merge pull request #7746 from ceph/wip-10587-split-servers
debian/rpm split servers
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Ken Dreyer
03:50 AM rgw Bug #14857 (Closed): Multi object delete using HTTP POST does not update bucket metadata
When we perform multiple object delete using HTTP POST where the object key list is sent in XML, response shows that ... Karthik Sathyanarayana
02:36 AM Revision 0c27417d (ceph): librbd: Truncate of non-existent object results in object map flagged a...
Fixes: #14789
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
xinxin shu
02:25 AM Bug #14844: rpm package building fails if the build machine has lttng and babeltrace development ...
@Kefu Chai
Would you mind having a look at this?
xie xingguo

02/24/2016

11:51 PM Linux kernel client Bug #8226: 0.80~rc1: RBD read errors (ENXIO)
Hi Ruslan,
The issue this ticket is for is fixed. Please open a new ticket.
Is there anything else in dmesg? ...
Ilya Dryomov
11:29 PM Linux kernel client Bug #8226: 0.80~rc1: RBD read errors (ENXIO)
Our crash, and osd maps in attachments. Also we see that this happens alltime when rebalance happens. In our cluster ... Ruslan Usifov
11:22 PM Linux kernel client Bug #8226: 0.80~rc1: RBD read errors (ENXIO)
Perhaps we have simular problems when cluster rebalance happens(we change placement groups count).
We run on
...
Ruslan Usifov
11:32 PM Backport #14076 (In Progress): hammer: ceph-objetstore-tool: add operations to remove clone ids f...
Backporting with 12740.
See pull request: https://github.com/ceph/ceph/pull/7702
David Zafman
10:40 PM Revision 1c4ccfe3 (ceph): Merge pull request #7597 from rzarzynski/wip-rgw-keystone-proper-fail
rgw: improve error handling in S3/Keystone integration
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:33 PM Bug #14856 (Resolved): Clang removes dead code....
log/Log.cc:193:5: warning: indirection of non-volatile null pointer will be deleted, not trap [-Wnull-dereference]
...
Willem Jan Withagen
10:19 PM Bug #13992: LibRadosMiscConnectFailure.ConnectFailure (not so intermittent) failure in upgrade/ha...
also in http://qa-proxy.ceph.com/teuthology/teuthology-2016-02-23_17:10:01-upgrade:hammer-x-infernalis-distro-basic-v... Yuri Weinstein
10:07 PM Revision 752b6a30 (ceph): 9.2.1
Jenkins Build Slave User
09:47 PM Revision 0cbe3dea (ceph): debian/rpm: split mon/osd/mds server packages
Split up the "ceph" package into four new packages:
1. ceph-mon
2. ceph-osd
3. ceph-mds (already done on Debia...
Ali Maredia
09:37 PM Revision 52704d3b (ceph): Reduced runtime for radosbench to 600
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit a72bba29103cd287131eb7b56953c417649fed5d)
Yuri Weinstein
09:35 PM Revision eead031d (ceph): Reduced runtime for radosbench to 600
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit a72bba29103cd287131eb7b56953c417649fed5d)
Yuri Weinstein
09:31 PM Bug #14810: "FileStore.cc: 2855: FAILED assert(0 == "unexpected error")" in powercycle-infernalis...
reduced runtime per Sage - https://github.com/ceph/ceph-qa-suite/pull/835 Yuri Weinstein
06:53 PM Bug #14810: "FileStore.cc: 2855: FAILED assert(0 == "unexpected error")" in powercycle-infernalis...
we can ignore this (for hte purposes of release), just a full disk.
to fix the test, we should change powercycle/o...
Sage Weil
04:18 PM Bug #14810: "FileStore.cc: 2855: FAILED assert(0 == "unexpected error")" in powercycle-infernalis...
Rerun om smithi failed http://pulpito.ceph.com/teuthology-2016-02-23_13:44:13-powercycle-infernalis-testing-basic-smi... Yuri Weinstein
09:31 PM Revision 31a8d168 (ceph): Merge pull request #835 from ceph/wip-14810-master-2
Reduced runtime for radosbench to 600 Yuri Weinstein
09:28 PM Revision a72bba29 (ceph): Reduced runtime for radosbench to 600
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> Yuri Weinstein
08:44 PM devops Bug #14854 (Resolved): ceph-fuse requires "ceph"
In https://bugzilla.redhat.com/show_bug.cgi?id=1303546 it was uncovered that the "ceph-fuse" package depends on the "... Ken Dreyer
08:10 PM Revision bffbe9cc (ceph): tasks/divergent_priors2: wait for osd to start before tell
Otherwise we can get
2015-09-24T19:22:15.191 INFO:teuthology.orchestra.run.mira080.stderr:Error ENXIO: problem getti...
Sage Weil
08:10 PM Revision b05ecd27 (ceph): divergent_priors2: give divergent time to come up
Fixes: #13322
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit c0b0ec2831f410d89b695a1d081223...
Samuel Just
07:35 PM Revision f053e3e7 (ceph): Merge pull request #7051 from wonzhq/scrub-cmp-map
osd: avoid FORCE updating digest been overwritten by MAYBE when comparing scrub map
Reviewed-by: Kefu Chai <kchai@re...
Sage Weil
07:09 PM rgw Bug #14853 (Fix Under Review): radosgw has no option to work with "insecure" ssl from keystone
https://github.com/ceph/ceph/pull/7777 Abhishek Lekshmanan
09:14 AM rgw Bug #14853 (In Progress): radosgw has no option to work with "insecure" ssl from keystone
Abhishek Lekshmanan
09:14 AM rgw Bug #14853: radosgw has no option to work with "insecure" ssl from keystone
Basically all openstack services have clients with a `--insecure` switch, which allow deployments with self signed ss... Abhishek Lekshmanan
09:01 AM rgw Bug #14853 (Resolved): radosgw has no option to work with "insecure" ssl from keystone
Anonymous
06:45 PM Revision 48d007f6 (ceph): Merge pull request #7617 from liewegas/wip-14745
osd: fix forced prmootion for CALL ops
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:42 PM Revision e67b70e7 (ceph): Merge pull request #7286 from ktdreyer/wip-10587-init-ceph-disk
init-ceph.in: skip ceph-disk if it is not present
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
06:42 PM Bug #14707 (Resolved): log: segv during _flush on very big long lines
Sage Weil
06:42 PM Revision ccfbca42 (ceph): Merge pull request #7599 from ifed01/wip-14707
log: fix stack overflow when flushing large log lines
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:41 PM Revision c10f6287 (ceph): Merge pull request #7643 from jazeltq/add_count_github
osd: filejournal: report journal entry count
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:40 PM Revision fa8ba08b (ceph): Merge pull request #7658 from majianpeng/bluestore
osd: bluestore: misc fixes
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:39 PM Bug #14786 (Resolved): OSD: potentially leave fuse_store hung if we fail to init osd
Sage Weil
06:39 PM Revision 6aa9a473 (ceph): Merge pull request #7677 from xiexingguo/xxg-wip-14786
osd: fix fusestore hanging during stop/quit
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:38 PM Revision 4229cd43 (ceph): Merge pull request #7680 from ceph/wip-da-SCA-20160203
common: various fixes from SCA runs
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Jason Dillaman <jdillama@...
Sage Weil
06:37 PM Revision b3141ce1 (ceph): Merge pull request #7681 from jjhuo/kstore-updates
osd: kstore: sync up kstore with recent bluestore updates
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
06:15 PM Backport #14554 (Resolved): hammer: Unable to bring up OSD's after dealing with FULL cluster (OSD...
Sage Weil
06:15 PM Revision 3c1e2d42 (ceph): Merge pull request #7415 from dachary/wip-14554-hammer
hammer: Unable to bring up OSD's after dealing with FULL cluster (OSD assert with /include/interval_set.h: 386: FAILE... Sage Weil
06:15 PM Revision b73a93d8 (ceph): Merge pull request #7576 from dachary/wip-14579-hammer
hammer: mon sync does not copy config-key Sage Weil
06:14 PM Backport #14689 (Resolved): hammer: consume_maps clearing of waiting_for_pg needs to check the sp...
Sage Weil
06:14 PM Revision b3eac8e3 (ceph): Merge pull request #7577 from dachary/wip-14689-hammer
hammer: consume_maps clearing of waiting_for_pg needs to check the spg_t shard for acting set membership Sage Weil
06:04 PM Backport #14720 (Resolved): hammer: OSDMap: reset osd_primary_affinity shared_ptr when deepish_co...
Sage Weil
06:03 PM Revision bf6dcc7c (ceph): Merge pull request #7590 from SUSE/wip-14720-hammer
hammer: OSDMap: reset osd_primary_affinity shared_ptr when deepish_copy_from Sage Weil
06:03 PM Backport #14760 (Resolved): hammer: OSD coredumps with leveldb compact on mount = true
Sage Weil
06:03 PM Revision 293e8c7b (ceph): Merge pull request #7645 from dachary/wip-14760-hammer
hammer: OSD coredumps with leveldb compact on mount = true Sage Weil
04:40 PM Revision 8ff1a8df (ceph): Merge pull request #7759 from trociny/wip-rbd-mirror-image-replayer-imp...
rbd-mirror: ImageReplayer improvements
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
04:23 PM rbd Bug #14822 (In Progress): Journal replay needs to support replaying successful maintenance ops
Jason Dillaman
04:07 PM Revision 53d87e17 (ceph): Merge pull request #7736 from trociny/fix-librbd-asok-empty-name
librbd: retrieve image name when opening by id
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
04:07 PM devops Bug #14851 (Duplicate): RPM: Missing dependency "redhat-lsb-core"
Dup of #14402 Ken Dreyer
03:35 PM Revision f0e428ad (ceph): Merge pull request #7620 from jdurgin/wip-14419
cls_rbd: mirroring directory
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
03:34 PM Revision da9b36a7 (ceph): librbd: rename rbd_pool_settings object to rbd_mirroring
We'll use this object only for mirroring-related purposes, not generic
settings on a pool.
Refs: #14419
Signed-off-b...
Josh Durgin
03:34 PM Revision 28e2d1bc (ceph): cls_rbd: add methods for keeping track of mirrored images
These will track whether local images should be mirrored, and map them
to a unique global id. There's a state field f...
Josh Durgin
03:30 PM Revision 2104df82 (ceph): test/objectstore: add test for GetNumBytes
Since new, fast implementation relies on results of encoded_size()
methods which may be invalidated once someone modi...
Piotr Dałek
03:10 PM Revision 6e901bac (ceph): pybind/rados: track completions before calling aio functions
Tracking completions is critical for memory safety - if the
aio function succeeds, the completion must be tracked. Ho...
Hector Martin
03:10 PM Revision 3c767ab8 (ceph): pybind/rados: Fix error handling and leaks in aio
aio_read:
The reference to ret_s begins existing at PyBytes_FromStringAndSize and
is handed over to the callback if r...
Hector Martin
02:51 PM Feature #14669: ceph-disk: support indirect dmcrypt key retrieval
... Loïc Dachary
02:42 PM Revision 894b3b7c (ceph): Merge pull request #7762 from ErwanAliasr1/evelu-check
Improving 'make check' for ceph-disk
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
02:28 PM Revision 80656b11 (ceph): librbd: get image name on open if it is opened by id
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:28 PM Revision 5360d861 (ceph): librbd: init asok_hook on open so name is always known
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:23 PM rbd Bug #14847 (Resolved): teuthology: test_librbd_python crashes
Jason Dillaman
01:57 PM Revision 1ee8c13f (ceph): Merge pull request #7743 from JiYou/open-test-for-bug-2339
test: enable test for bug #2339 which has been resolved.
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
01:54 PM Revision fae912c3 (ceph): ObjectCacher: don't loop the extents of OSDRead in map_read
Looping the extents of OSDRead is done in _readx. The looping in
map_read is not needed.
Signed-off-by: Zhiqiang Wan...
Zhiqiang Wang
01:53 PM Linux kernel client Bug #14717 (Closed): "Failures: xfs" in krbd-hammer-testing-basic-smithi
Linked to #11850, as another data point. Ilya Dryomov
01:49 PM Revision ca6f1681 (ceph): ObjectCacher: fix the bytes_written in writex
The BufferHead returned after map_write may include other dirty data to
the left and/or right. The actual length of d...
Zhiqiang Wang
01:49 PM Revision 281b1e37 (ceph): Merge pull request #7773 from roidayan/xio_remove_redundant_magic_methods
xio: remove redundant magic methods
Reviewed-by: Haomai Wang<haomai@xsky.com>
Haomai Wang
01:45 PM Revision 322f1059 (ceph): osdc: don't loop the extents of OSDWrite in map_write
We are looping all the extents of the OSDWrite in writex. The looping in
map_write is not needed. And if there are sa...
Zhiqiang Wang
01:35 PM Revision 5c5ca11b (ceph): Merge pull request #7771 from xiexingguo/xxg-wip-fixawatch
librados: do not clear handle for aio_watch()
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
12:31 PM Revision 325963b2 (ceph): os/ObjectStore: implement more efficient get_encoded_bytes()
Previous version explicitly encoded entire transaction just to get
its length, which resulted in encoding it twice. N...
Piotr Dałek
12:00 PM Revision af12582b (ceph): xio: remove redundant magic methods
The same methods are inherited from Messenger.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Roi Dayan
11:10 AM rbd Bug #14789: Truncate of non-existent object results in object map flagged as exists
https://github.com/ceph/ceph/pull/7772 Xinxin Shu
11:09 AM rbd Bug #14789 (Fix Under Review): Truncate of non-existent object results in object map flagged as e...
Xinxin Shu
08:59 AM Revision 3cfb83d1 (ceph): librados: remove unused local variables
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
08:56 AM Revision 8caa2e45 (ceph): librados: do not clear handle for aio_watch()
which is needed for aio_unwatch() to work.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
08:56 AM Revision 48af4bec (ceph): tests/ceph-disk: Let teardown clearing data
When running the ceph-disk check suite, 'test_mark_init' & 'test_activate_dir' had a
permission denied of the freshly...
Erwan Velu
08:55 AM Revision 57f31e95 (ceph): tests/ceph-disk: Using dummy device mappers
When doing a make test, if your local setup was running a "dm-0" or "dm-1",
the make check was failing.
The detectio...
Erwan Velu
08:55 AM Revision ba05b7e7 (ceph): tests/ceph-disk: Creating missing working dir
When running run-tox.sh in a very simple env,
the test will fail if '/var/lib/ceph/tmp' doesn't exist.
This patch ad...
Erwan Velu
06:42 AM devops Bug #14811: RPM: yasm complains when building with %{with lowmem_builder}
Nathan Cutler
06:13 AM devops Bug #14687 (Resolved): RPM: no /usr/libexec directory on SUSE
Nathan Cutler
06:11 AM Revision 7bd95b59 (ceph): os/filestore: FALLOC_FL_PUNCH_HOLE must be used with FALLOC_FL_KEEP_SIZE
Signed-off-by: xinxin shu <xinxin.shu@intel.com> xinxin shu
06:10 AM Bug #14586 (Resolved): qa/workunits/post-file.sh: sudo
Loïc Dachary
06:10 AM rbd Bug #14483 (Resolved): Flattening an rbd image with a running Qemu instances causes librbd worker...
Loïc Dachary
06:08 AM rbd Backport #14611 (Resolved): hammer: Flattening an rbd image with a running Qemu instances causes ...
Loïc Dachary
06:03 AM rbd Backport #14611 (In Progress): hammer: Flattening an rbd image with a running Qemu instances caus...
Loïc Dachary
06:08 AM rbd Backport #14620 (Resolved): hammer: unsafe use of libnss PK11_GetBestSlot()
Loïc Dachary
06:03 AM rbd Backport #14620 (In Progress): hammer: unsafe use of libnss PK11_GetBestSlot()
Loïc Dachary
06:05 AM CephFS Backport #12350 (Resolved): Provided logrotate setup does not handle ceph-fuse correctly
Loïc Dachary
06:04 AM Backport #14087 (Resolved): FAILED assert(old_size == total_chunk_size) in 0.94.5 / strange file ...
Loïc Dachary
06:03 AM Backport #14587 (Resolved): hammer: qa/workunits/post-file.sh: sudo
Loïc Dachary
06:03 AM Backport #14602 (Resolved): hammer: ceph-disk: use blkid instead of sgdisk -i
Loïc Dachary
05:56 AM Revision 5b724fcc (ceph): Merge pull request #7485 from dillaman/wip-14611-hammer
librbd: flattening an rbd image with active IO can lead to hang
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:55 AM Revision bb84692e (ceph): Merge pull request #7488 from ceph/wip-auth-hammer
hammer: auth: use libnss more safely
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:48 AM Revision ee014d80 (ceph): Merge pull request #7475 from dachary/wip-14602-hammer
hammer: ceph-disk: use blkid instead of sgdisk -i
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:47 AM Revision 576225d6 (ceph): Merge pull request #7456 from dachary/wip-14587-hammer
hammer: qa/workunits/post-file.sh: sudo
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:38 AM Revision a6f7a2f1 (ceph): Merge pull request #6946 from dachary/wip-14087-shard-size
osd: log inconsistent shard sizes
Reviewed-by: David Zafman <dzafman@redhat.com>
Loïc Dachary
05:37 AM Revision 74cfe5c5 (ceph): Merge pull request #7110 from david-z/wip-hammer-fix-logrotate-ceph-fuse
[ceph-fuse] fix ceph-fuse writing to stale log file after log rotation
Reviewed-by: Sage Weil <sage@redhat.com>
Revi...
Loïc Dachary
05:22 AM CephFS Bug #14732: open returns EACCES when O_TRUNC is specified and write permission is denied (hammer)
More runs with the same failure : http://pulpito.ceph.com/loic-2016-02-22_22:08:47-fs-hammer-backports---basic-multi/ Loïc Dachary
04:41 AM Revision dc5a9053 (ceph): Merge pull request #7649 from yuyuyu101/wip-async-watch
librados: implement async watch/unwatch
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
03:41 AM Bug #14766: OSD reporting ENOTEMPTY and crashing

Hi,
Not sure if these are related or not. Here's an instance where the OSD crashes, then on restart, I receive ...
Jeffrey McDonald
03:36 AM Revision f59c872d (ceph): test: enable test for bug #2339 which has been resolved.
Signed-off-by: You Ji <jiyou09@gmail.com> You Ji
02:07 AM Revision 0b56c5e5 (ceph): Merge pull request #7761 from dillaman/wip-14847
librbd: fix state machine race conditions during shut down
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:50 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
thank you for your reproducer.
I have already known the root cause, but fixing it requires refactor internal locki...
Zheng Yan
01:24 AM Linux kernel client Bug #14360: Cephfs kernel client ceph_send_cap_releases hung task
i've got a simple reproducer for CoreOS 899.7.0 with the 4.3.3 kernel.
in this instance selinux is in permissive m...
Nick Owens
01:29 AM Revision 7109de7b (ceph): RadosClient: call watch_flush before finisher stop
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
01:19 AM Feature #14852 (New): Make SOCKET_BACKLOG configurable
/src/rgw/rgw_main.cc has a #define for SOCKET_BACKLOG = 1024. Please consider this for a configurable option.in my c... Diluga Salome
12:30 AM Revision dfe538d5 (ceph): Merge pull request #7636 from SUSE/wip-systemd-paths
build: move libexec scripts to standardize across distros
Reviewed-by: Boris Ranto <branto@redhat.com>
Reviewed-by: ...
Sage Weil

02/23/2016

11:44 PM Bug #14660: selinux denials during rbd test run
That sounds interesting, The system is not restarted nor relabelled, other than whatever ceph-deploy does internally... Vasu Kulkarni
10:27 PM Bug #14660: selinux denials during rbd test run
Vasu,
yep, I plan to fix these (at least the /run/lock and dac_override issue). I do have some clues as to have to...
Boris Ranto
06:40 PM Bug #14660: selinux denials during rbd test run
Boris,
Other than the dac_overide and /run/lock/ceph-disk, this is one additional thing that should be fixed, let ...
Vasu Kulkarni
09:55 PM devops Bug #14851: RPM: Missing dependency "redhat-lsb-core"
I further hunted it down to the following commit: https://github.com/ceph/ceph/commit/f972f38445bc7a6efe122a5f9fc2ba7... Martin Palma
09:35 PM devops Bug #14851: RPM: Missing dependency "redhat-lsb-core"
By comparing the two version 0.94.5 with 0.94.6 on Github we can see that the dependency of *redhat-lsb-core* was rem... Martin Palma
09:00 PM devops Bug #14851 (Duplicate): RPM: Missing dependency "redhat-lsb-core"
It seems that the *ceph-common* RPM package is missing the *redhat-lsb-core* dependency?
I tried to deploy a new c...
Martin Palma
08:42 PM Revision 3a6d6279 (ceph): test/common/test_weighted_priority_queue Fix the unit tests since the
changes to WeightedPriorityQueue there is no strict round robin
dequeueing of classes. Removed that test from the uni...
Robert LeBlanc
08:42 PM Revision f03de8e2 (ceph): common/WeightedPriorityQueue Rewrote the queue to use intrusive contian...
show 60-70% of execution time compared to before.
Signed-off-by: Robert LeBlanc <robert.leblanc@endurance.com>
Robert LeBlanc
08:23 PM Revision e688a44e (ceph): cls_rbd: async version of dir_get_name
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
08:11 PM Revision d48536c5 (ceph): common: Do not use non-portable constants in mutex_debug
The mutex initializers in Linux are non-portable, as evidenced by their
names ending with _NP.
Use the POSIX complia...
Adam Emerson
08:09 PM Revision cc990729 (ceph): cmake: fix paths & make object libs of various EC files
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
08:06 PM Revision 442be027 (ceph): osd: Replace snprintf with faster implementation in eversion_t::get_key...
Signed-off-by: Evgeniy Firsov <evgeniy.firsov@sandisk.com> Evgeniy Firsov
07:44 PM Revision 635ae88a (ceph): Merge pull request #7632 from zaitcev/cleanup-dead-code-3
rgw: Drop unused usage_exit from rgw_admin.cc
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
07:25 PM Revision 06681edd (ceph): Merge pull request #7285 from magicrobotmonkey/patch-1
Increase verbosity level on RGWObjManifest line
Reviewed-by: Yehuda Saeh <yehuda@redhat.com>
Yehuda Sadeh
07:23 PM Revision a6538d40 (ceph): Merge pull request #7618 from zaitcev/wip-5073-subuser-bis
rgw: Fix subuser harder with tenants
Reviewed-y: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
06:18 PM Revision 933ae4ca (ceph): Merge pull request #7763 from dachary/wip-releases
doc: fix 0.94.4 and 0.94.5 ordering Sage Weil
06:17 PM Revision a1a0e96c (ceph): Merge pull request #7364 from javenwu/master
common: default cluster name to config file prefix
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
06:15 PM Revision 89878e8f (ceph): Merge pull request #7548 from yuyuyu101/librbd-avoid-memcpy
librbd: reduce mem copies to user-buffer during read
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
06:14 PM Revision 76dc4471 (ceph): Merge pull request #7667 from jdurgin/wip-14780
Revert "librbd: use task finisher per CephContext"
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
05:50 PM Bug #14849 (Duplicate): (infernalis) [ FAILED ] LibRadosAioEC.ReturnValuePP in rados-infernalis...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-23_02:00:02-rados-infernalis-distro-basic-openstack/
...
Yuri Weinstein
05:30 PM Revision 7b3334ac (ceph): Merge pull request #7625 from branch-predictor/bp-async-more
msg/async: smarter MSG_MORE
Reviewed-by: Haomai Wang <haomai@xsky.com>
Haomai Wang
05:13 PM Revision dafe0d97 (ceph): doc: fix 0.94.4 and 0.94.5 ordering
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
04:53 PM rbd Bug #14595 (Resolved): Race between releasing exclusive lock and incoming write ops
This is not an issue within jewel due to the new block-writes ability and exclusive lock state machine. Jason Dillaman
04:30 PM rbd Bug #14846 (In Progress): teuthology: helgrind warnings
Jason Dillaman
01:14 PM rbd Bug #14846 (Closed): teuthology: helgrind warnings
http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2016-02-22_16:00:01-rbd-master---basic-openstack/3178/teut... Jason Dillaman
04:29 PM rbd Bug #14847 (Fix Under Review): teuthology: test_librbd_python crashes
*PR*: https://github.com/ceph/ceph/pull/7761 Jason Dillaman
01:15 PM rbd Bug #14847 (Resolved): teuthology: test_librbd_python crashes
http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2016-02-22_16:00:01-rbd-master---basic-openstack/3200/teut... Jason Dillaman
04:23 PM Bug #13098 (Resolved): OSD crashed when reached pool's max_bytes quota
Loïc Dachary
04:15 PM Stable releases Tasks #13356 (Resolved): hammer v0.94.6
Loïc Dachary
04:02 PM Revision 479366a5 (ceph): Merge pull request #7760 from theanalyst/fix/rgw-fcgi-build
rgw: fcgi should include acconfig Casey Bodley
03:59 PM Revision e67099d0 (ceph): librbd: deterministically unblock writes on snap set
Previously this was handled in the state machine's destructor,
but that can lead to nondeterministic behavior due to ...
Jason Dillaman
03:53 PM Revision 514519a6 (ceph): librbd: avoid close race-condition within ImageState
The lock was previously unlocked/locked to avoid lock cycles. This
creates an issue when closing the image because th...
Jason Dillaman
03:39 PM Revision f3fc6b15 (ceph): rgw: fcgi should include acconfig
As it references FASTCGI_INCLUDE_DIR which is referenced from it
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
Abhishek Lekshmanan
03:35 PM Revision c7c1d281 (ceph): doc/release-notes: v0.94.6 final notes
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
03:29 PM Revision de0be8af (ceph): Merge pull request #7689 from dachary/wip-release-notes
release-notes: draft v0.94.6 release notes Sage Weil
02:52 PM Revision c5a6b6a5 (ceph): msg/async: cut the middle-man
Get rid of complete_bl and let messenger write directly to outcoming_bl of
a connection. Also, if message bufferlist ...
Piotr Dałek
02:37 PM CephFS Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
It turns out the main files are too large. Is there any other way I can upload them? Christopher Nelson
02:36 PM CephFS Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
Apparently my institution blocks outbound scp, so I had to post the files here. Sorry for the delay. Christopher Nelson
02:19 PM Revision bd893438 (ceph): Merge pull request #7725 from ceph/wip-fix-async-valgrind
AsyncMessenger: fix valgrind leak Haomai Wang
01:11 PM Revision dd17b513 (ceph): Merge pull request #7758 from dachary/wip-ceph-disk-prepare-help
ceph-disk: fix prepare --help
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
11:56 AM Revision 4a61793c (ceph): ceph-disk: fix prepare --help
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
11:12 AM Revision 0ae120db (ceph): Merge pull request #7756 from dachary/wip-ceph-disk-args
ceph-disk: deactivate / destroy PATH arg are optional
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
09:21 AM CephFS Bug #13640 (Resolved): CephFS and page cache handling
Zheng Yan
09:16 AM Revision ac241ab4 (ceph): ceph-disk: deactivate / destroy PATH arg are optional
And the mandatory positional arguments need not be == 1, it is enough to
leave the nargs parameter out.
Signed-off-b...
Loic Dachary
09:15 AM CephFS Bug #14684 (Fix Under Review): test_scrub_checks fails
... Zheng Yan
09:11 AM Revision dff71a5d (ceph): mon/MDSMonitor.cc: properly note beacon when health metrics changes
Fixes: #14684
Signed-off-by: Yan, Zheng <zyan@redhat.com>
Yan, Zheng
07:35 AM Bug #14845 (Resolved): OSD: wrong counter for remove dir
Check bool remove_dir() for detail information and a patch is on the way. xie xingguo
07:25 AM Revision 103eee4d (ceph): test: image_replay: use flush to speedup commit position update
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:25 AM Revision 9572d27a (ceph): rbd-mirror: add asok commands to get image replyer status and flush
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:25 AM Revision 1a6dfa46 (ceph): rbd-mirror: store sync snapshot name in registered client
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:25 AM Revision 79dcef27 (ceph): librbd: add field to MirrorPeerClientMeta to store snap name
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:25 AM Revision e92b4527 (ceph): rbd-mirror: ImageReplayer: pass registered client ID as external param
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
07:09 AM Feature #14669: ceph-disk: support indirect dmcrypt key retrieval
osd dm-crypt key management scheme
----------------------------------
- create new partition type OSD_LOCKBOX (or...
Loïc Dachary
06:29 AM Bug #14844 (Resolved): rpm package building fails if the build machine has lttng and babeltrace d...
OS:... runsisi hust
06:15 AM devops Bug #14839: systemctl stop ceph.target doesn't stop ceph
Few more notes:
This was probably introduced by [1]. We should probably consider using some new dependency layout ...
Boris Ranto
06:09 AM Stable releases Tasks #14692: hammer v0.94.7
h3. fs... Loïc Dachary
06:07 AM Stable releases Tasks #14692: hammer v0.94.7
h3. powercycle... Loïc Dachary
06:06 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rbd... Loïc Dachary
06:05 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rgw... Loïc Dachary
06:04 AM Stable releases Tasks #14692: hammer v0.94.7
h3. upgrade... Loïc Dachary
06:02 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rados... Loïc Dachary
05:57 AM CephFS Backport #14843 (Rejected): infernalis: test_object_deletion fails (tasks.cephfs.test_damage.Test...
Loïc Dachary
05:50 AM Bug #14842: ceph-disk: /sys/block/<device>/queue/physical_block_size is not obeyed
IIRC there are cases where sgdisk is not able to create a partition aligned as recommended (but parted could). I don... Loïc Dachary
05:48 AM Bug #14842 (Closed): ceph-disk: /sys/block/<device>/queue/physical_block_size is not obeyed
ceph-disk is creating data partition from sector 1 ignoring what sgdisk is recommending (256 in my disk). Basically, ... Loïc Dachary
05:08 AM Revision 4bb184f1 (ceph): Merge pull request #7687 from yangdongsheng/ceph-disk_nargs
ceph-disk: make some arguments as required if necessary
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:07 AM devops Fix #9666 (Resolved): ceph-disk error when activate is missing an argument is cryptic
https://github.com/ceph/ceph/pull/7687 and https://github.com/ceph/ceph/pull/7756 Loïc Dachary
04:47 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Steve Taylor wrote:
> I already have the corresponding mon log with --debug-paxos 10. I didn't send it because I cou...
Vikhyat Umrao
03:37 AM CephFS Bug #14759: ovh: failed snaptest-git-ceph.sh test
might be duplicate of #10436 Zheng Yan
03:20 AM CephFS Bug #14196: test_object_deletion fails (tasks.cephfs.test_damage.TestDamage)
https://github.com/ceph/ceph-qa-suite/pull/829 Zheng Yan
03:12 AM CephFS Bug #14798 (Fix Under Review): free fds being exhausted eventually because freed fds are never pu...
Zheng Yan
02:59 AM Revision e9a4cd13 (ceph): Merge pull request #7640 from batrick/vstart-btrfs-missing
vstart.sh: silence a harmless msg where btrfs is not found
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
02:35 AM Revision dc9aba1c (ceph): BlueStore: fix type mismatch for openat syscall
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
02:35 AM Revision 9be35bca (ceph): BlueStore: add sanity check for type during mount
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
02:35 AM Revision 468b64a0 (ceph): BlueStore: remove unused local variables
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
02:35 AM Revision 204a96ca (ceph): BlueStore: add sanity check for attr removal
So we don't bother to start a real trans if it is a noop.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
02:21 AM Revision 4f88f5fb (ceph): hadoop: disable client_permissions for tasks
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
01:26 AM Revision 26db0588 (ceph): BlueStore: simplify put logic a little
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision d01a39e2 (ceph): BlueStore: optimize head check logic
For the sake of performance.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
01:26 AM Revision 73d86b36 (ceph): BlueStore: simplify cow allocation for head and tail a little
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision a906019d (ceph): BlueStore: set existence for new onode in a proper way during write
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 98b2d83b (ceph): BlueStore: add result check logic for _do_truncate
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 0f8bf7d0 (ceph): BlueStore: add result check for _do_remove
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision bc320eba (ceph): BlueStore: remove unused member fs
We use internal blue-fs for such support.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
xie xingguo
01:26 AM Revision f99bf344 (ceph): BlueStore: fix obsolete comment
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision a8435690 (ceph): BlueStore: fix typo
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 1e53e5b8 (ceph): BlueStore: remove redundant continue
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 5e55c133 (ceph): BlueStore: remove unused member dirty of onode
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 00d40e24 (ceph): BlueStore: avoid create the dest onode in advance
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 73f35f11 (ceph): BlueStore: fix return type of _txc_add_transaction
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
01:26 AM Revision 4b673ee2 (ceph): KStore: fix return type of _txc_add_transaction
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
12:57 AM Revision 30db35cd (ceph): osdmaptool: allow add --pg-num to osdmaptool --test-map-pgs to override...
Fixes: #14701
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
xinxin shu
12:55 AM Revision 46da33bd (ceph): OSD: update heartbeat peers if unable to statfs
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
12:53 AM Revision 144fa29d (ceph): os/filestore: fast abort when basedir no more exists
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo

02/22/2016

09:10 PM Revision e832001f (ceph): 0.94.6
Jenkins Build Slave User
08:17 PM Bug #13421: ceph-osd Segmentation fault in pthread_join
That most recent one was triggered by user SIGABRT, so it's not a reproduction of any genuine bugs. :) Greg Farnum
08:00 PM devops Bug #14839: systemctl stop ceph.target doesn't stop ceph
Boris told me try below which worked
<branto> workaround is to run 'systemctl stop ceph-mon.target ceph-osd.target c...
Vasu Kulkarni
07:46 PM devops Bug #14839: systemctl stop ceph.target doesn't stop ceph
This is on master, but same seen in testing on infernalis/jewel and ceph-deploy tests logs on centos show this issue ... Vasu Kulkarni
07:40 PM devops Bug #14839 (Resolved): systemctl stop ceph.target doesn't stop ceph
This is on centos 7.2 and easy to recreate... Vasu Kulkarni
07:47 PM Bug #12025 (Resolved): rados mkpool/ pool_create should warn/error when pgp_num > pg_num
PR Merged into master Abhishek Lekshmanan
06:46 PM Revision 30bddc45 (ceph): Makefile: workaround an automake bug for "make check"
override the automake variable of am__is_gnu_make. it is a workaround
for http://debbugs.gnu.org/cgi/bugreport.cgi?bu...
Kefu Chai
05:37 PM Revision 89764124 (ceph): Merge pull request #7737 from trociny/wip-librados_test_stub-debug
test: more debug logging for TestWatchNotify
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
05:36 PM Revision b9a4b977 (ceph): Merge pull request #7714 from SUSE/wip-qa-typo
doc: standardize @param (not @parma, @parmam, @params)
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Sage Weil
05:36 PM Revision 289403df (ceph): Merge pull request #7738 from trociny/test-librbd-poolname
test: create pools for rbd tests with different prefix
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
05:30 PM devops Bug #14829 (Resolved): Error launching rgw via vstart.sh
Sage Weil
05:29 PM Revision dd478ffe (ceph): Merge pull request #7727 from jmunhoz/ceph-fix-14829
vstart.sh: avoid race condition starting rgw via vstart.sh
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
04:47 PM Revision 93f255c9 (ceph): Merge pull request #7614 from trociny/wip-rbd-mirroring-image-reply
rbd-mirror: implement ImageReplayer
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
04:07 PM Bug #14838 (Resolved): Spelling error in ceph_disk/main.py
Loïc Dachary
04:05 PM Bug #14838 (Fix Under Review): Spelling error in ceph_disk/main.py
Loïc Dachary
04:04 PM Bug #14838: Spelling error in ceph_disk/main.py
https://github.com/ceph/ceph/pull/7744 good catch ! Loïc Dachary
03:31 PM Bug #14838 (Resolved): Spelling error in ceph_disk/main.py
With Ceph version 10.0.3-2171-gb8131f8 (b8131f893ae6f631debb8ca59e470ff919da7ec1):
root@compute01:/var/log/ceph# /...
Frode Sandholtbraaten
04:07 PM Revision ebc7a92f (ceph): Merge pull request #7744 from dachary/wip-14838-ceph-disk-dmcrypt
ceph-disk: s/dmcrpyt/dmcrypt/
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Loïc Dachary
04:02 PM Revision ef6aafa8 (ceph): ceph-disk: s/dmcrpyt/dmcrypt/
http://tracker.ceph.com/issues/14838 Fixes: #14838
Signed-off-by: Frode Sandholtbraaten <fsa@basefarm.no>
Signed-off...
Loic Dachary
03:37 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I already have the corresponding mon log with --debug-paxos 10. I didn't send it because I couldn't get the osd log t... Steve Taylor
01:46 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
> My understanding of the purpose of this test is either to verify the fix you made as working in our environment or ... Kefu Chai
03:24 PM Revision 19843ce2 (ceph): rgw: enable users of RGWHTTPClient to get HTTP status code.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
03:24 PM Revision a7a5cf2b (ceph): rgw: return proper error codes in S3/Keystone auth.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
03:20 PM RADOS Feature #14527 (Fix Under Review): Lookup monitors through DNS
https://github.com/ceph/ceph/pull/7741 Kefu Chai
03:16 PM Revision 7186d1cb (ceph): rgw: improve debugs around S3/Keystone auth mechanism.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
02:42 PM Revision 838b3675 (ceph): Merge pull request #7688 from tchaikov/wip-14788
buffer: hide iterator_impl symbols
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Kefu Chai
02:06 PM Revision 74b92163 (ceph): tasks/cephfs: add test case for scrub repair
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
01:34 PM CephFS Bug #14732: open returns EACCES when O_TRUNC is specified and write permission is denied (hammer)
strange, I can't find O_TRUNC in tests/open/06.t Zheng Yan
12:19 PM CephFS Bug #14800 (Fix Under Review): [ceph-fuse] Fh ref might leak at umounting
Zheng Yan
12:11 PM CephFS Bug #14805 (Fix Under Review): Hadoop tests failing with EPERM
I have trouble to run the test on local machine, let's try disable client_permissions
https://github.com/ceph/ceph...
Zheng Yan
11:41 AM Feature #14701 (Fix Under Review): allow add --pg-num to osdmaptool --test-map-pgs to override th...
https://github.com/ceph/ceph/pull/7733 Kefu Chai
10:52 AM Revision edf8152c (ceph): rgw: ONLY move PKI-related things from rgw_swift to rgw_keystone.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:35 AM Revision 9a3252c1 (ceph): tasks/scrub_test: add test for get-inconsistent-* commands
Signed-off-by: Kefu Chai <kchai@redhat.com> Kefu Chai
10:17 AM Revision 09142463 (ceph): OSD: fix race condition for heartbeat_need_update
The heartbeat_need_update member can be accessed by both OSD tick thread and
PG relevant threads, that is why the hea...
xie xingguo
09:55 AM Revision 804c6159 (ceph): osd/ReplicatedPG: remove unused bufferlist
This bufferlist isn't used, so just get rid of it.
Signed-off-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com>
Piotr Dałek
09:52 AM Bug #14837 (Resolved): OSD: race condition during update heartbeat_need_update
Mutex::Locker l(heartbeat_lock);
if (!heartbeat_peers_need_update())
return;
heartbeat_need_update = false;
xie xingguo
09:38 AM CephFS Bug #14684: test_scrub_checks fails

http://pulpito.ceph.com/teuthology-2016-02-19_14:03:01-fs-jewel---basic-smithi/17838/...
Zheng Yan
09:23 AM CephFS Bug #14196 (Pending Backport): test_object_deletion fails (tasks.cephfs.test_damage.TestDamage)
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-19_17:43:52-fs-infernalis---basic-openstack/559/
need ba...
Zheng Yan
07:57 AM Revision bdf998c8 (ceph): tasks/scrub_test: restore the changes to omap after the test
because the repair for digest mismatch will rewrite the omap digest
in the corresponding OI attribute with the one ca...
Kefu Chai
07:37 AM Revision 83da0936 (ceph): test: create pools for rbd tests with different prefix
This makes easier to find out what test fails to cleanup.
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub
07:23 AM Revision 4d26000b (ceph): OSD: put a guard for updating heartbeat peers
As get_next_up_osd_after() and get_previous_up_osd_before() may refer to the same
osd, so we need to put a guard in c...
xie xingguo
06:35 AM Revision 67b2744b (ceph): OSD: fix typo
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
05:44 AM rgw Bug #14835 (Resolved): src/test/cli/radosgw-admin/help.t: failed
Loïc Dachary
05:43 AM rgw Bug #14835 (Fix Under Review): src/test/cli/radosgw-admin/help.t: failed
Loïc Dachary
03:26 AM rgw Bug #14835: src/test/cli/radosgw-admin/help.t: failed
@Loic
A patch is already on the way, check below:
https://github.com/ceph/ceph/pull/7723
xie xingguo
03:12 AM rgw Bug #14835 (Resolved): src/test/cli/radosgw-admin/help.t: failed
https://jenkins.ceph.com/job/ceph-pull-requests/1868/console
Marking as urgent as it creates false negatives durin...
Loïc Dachary
05:44 AM Revision b8131f89 (ceph): Merge pull request #7723 from tchaikov/wip-rgw-test
test/radosgw-admin: update the expected usage outputs
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:10 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
04:43 AM Bug #14834 (Fix Under Review): test_pidfile.sh leave two osd daemon running after unittest
https://github.com/ceph/ceph/pull/7734 Loïc Dachary
02:46 AM Bug #14834 (Resolved): test_pidfile.sh leave two osd daemon running after unittest
not killed two daemons comes out at line 90 and line 73 in test_pidfile.sh. The detail description is seen at https:/... shun song
02:34 AM Revision 7987e545 (ceph): qa/workunits/fs/misc: Add workunit for file lock deadlock detection
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
01:27 AM Revision ad44b5ea (ceph): test_rados_watch_notify: add async_watch_flush tests
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
01:11 AM Revision e17a0c04 (ceph): OSD: shutdown OSDService in a more graceful way
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo

02/21/2016

10:15 PM rgw Bug #14806 (Fix Under Review): rgw: TempURL authentication of Swift API doesn't work
Pull request: https://github.com/ceph/ceph/pull/7697. Radoslaw Zarzynski
08:06 PM Revision a1f20db5 (ceph): ceph_detect_init/__init__.py: remove shebang
This file is installed with permissions 644, making the shebang
redundant and causing RPMLINT to complain.
Signed-of...
Nathan Cutler
05:34 PM Cleanup #14833 (New): move rados-classes from /usr/lib to /usr/lib/ceph
rados-classes is currently installed to /usr/lib/rados-classes/
while erasure-code and compressor is installed under...
Bjørnar Ness
02:44 PM Linux kernel client Bug #14715 (Resolved): "rbd: sysfs write failed" in krbd-hammer-testing-basic-smithi
Pulled "[DO NOT MERGE] rbd: bump RBD_MAX_PARENT_CHAIN_LEN to 128" into testing. Yuri - you shouldn't see any more pr... Ilya Dryomov
01:01 PM Revision d20936fc (ceph): Revert "NVMEDevice: add default constructor for Task and clean up"
This reverts commit feaa4573366cce27b5523d2838ca09708c4c0b35. Haomai Wang
12:57 PM Revision 8513e001 (ceph): NVMEDevice: use wakeup instead of direct call
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
12:17 PM Revision b09b80ed (ceph): NVMEDevice: accept spdk structure name changes
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
11:42 AM Bug #14832 (Won't Fix): configure flag dependencies/inconsistensies
I am working on a buildroot package (using 10.0.3 atm), and have found
some problems with configure flag dependencie...
Bjørnar Ness
11:30 AM Revision 847c3eba (ceph): Merge pull request #7647 from yuyuyu101/wip-spdk
NVMEDevice: refactor probe/attach codes and support zero command
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
11:10 AM Revision 8d27e99b (ceph): test: more debug for TestWatchNotify
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
10:51 AM Bug #14831 (Resolved): build with --with-rocksdb (shared) fails
ar is passed -lrocksdb when building --with-librocksdb:
ar cru libkv.a kv/libkv_a-KeyValueDB.o kv/libkv_a-LevelDBS...
Bjørnar Ness
10:48 AM Bug #14830 (Resolved): rocksdb extects to be passed build environment
build environment passed to ceph configure is not propagated
to the rocksdb build, and cross compiles fails.
when...
Bjørnar Ness
10:43 AM Revision 4c0f6a3b (ceph): NVMEDevice: accept spdk api name changes
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:38 AM Revision 4602f1ba (ceph): spdk: update spdk submodule to accept new interface changes
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:33 AM Revision feaa4573 (ceph): NVMEDevice: add default constructor for Task and clean up
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:30 AM Revision 7ef2f4aa (ceph): NVMEDevice: only activate zero command when backend supported
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:27 AM Revision b5cdc332 (ceph): BlockDevice: detect symbol file basename
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:23 AM Revision d208668d (ceph): BlueStore: fix spdk link file create failed
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:23 AM Revision 84a36a0a (ceph): NVMEDevice: fix atomic and lock changes
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:22 AM Revision 4f868ee4 (ceph): NVMEDevice: use nvme_probe to simply init
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:18 AM Revision 61ef7d4e (ceph): spdk: update spdk submodule
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:18 AM Revision 52592704 (ceph): NVMEDevice: use nvme zero command instead of writing zero
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
10:16 AM Revision 398e331e (ceph): NVMEDevice: cleanup task iterator process
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang

02/20/2016

06:00 PM Bug #14244 (Fix Under Review): "SELinux denials found" in rados-jewel-distro-basic-smithi
https://github.com/ceph/teuthology/pull/790 Vasu Kulkarni
05:48 PM devops Bug #14829: Error launching rgw via vstart.sh
It seems a race condition on the rados lock. Delaying the rgw server booting is good enough and all things work as ex... Javier M. Mellid
05:32 PM devops Bug #14829 (Resolved): Error launching rgw via vstart.sh
Running the next command:
MON=1 MDS=1 ./vstart.sh -d -n -x -r
...raises several error in the logs. The vstart.s...
Javier M. Mellid
05:33 PM Revision 809189b4 (ceph): vstart.sh: avoid race condition starting rgw via vstart.sh
In slow environments running vstart.sh hits a race condition setting up
the rgw server. Creating the S3 and Swift use...
Javier M. Mellid
03:51 PM devops Fix #14828: ceph Resource Agent does not work with systemd
Yeah. With the systemd unit files, there's no point bothering with the wrapper RAs - pacemaker is quite capable of m... Tim Serong
09:39 AM devops Fix #14828 (Resolved): ceph Resource Agent does not work with systemd
I have been told by people more knowledgeable than myself that the ceph Resource Agent (RA), which we are currently p... Nathan Cutler
08:58 AM Revision cf8483f9 (ceph): test/radosgw-admin: update the expected usage outputs
to match with the latest radosgw-admin changes.
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
08:42 AM Revision b2ae384e (ceph): RPM: refrain from packaging EC testing plugins
Since these plugins are only used in "make check", there is no
reason to package them and doing so causes RPMLINT to ...
Nathan Cutler
08:42 AM Revision 1b6faf68 (ceph): Refrain from versioning EC testing plugins
Since these plugins are only used in "make check", there is no
point in versioning them.
http://tracker.ceph.com/iss...
Nathan Cutler
08:05 AM Revision b3990a15 (ceph): rbd-mirror: implement ImageReplayer
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
08:05 AM Revision f8291867 (ceph): test: rbd-mirror: add ImageReplayer tests
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
08:05 AM Revision cc4b73b3 (ceph): test: rbd-mirror: add tool to test ImageReplayer
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
08:03 AM Revision 9644df6d (ceph): os/filestore: fix result code if sanity check failed during copy_range
According to Linux Man Page, the lseek() system call returns -1 and
sets errno only if it indeed encouters some error...
xie xingguo
07:30 AM Bug #14827 (Resolved): os/filestore: copy_range may return OK if fail to verify src/dst offset
xie xingguo
07:27 AM Revision da0f6608 (ceph): test/time: no need to abs(uint64_t) for comparing
fixes
```
/home/kefu/dev/ceph/src/test/common/test_time.cc: In instantiation of
‘void system_clock_conversions() [wit...
Kefu Chai
06:37 AM Revision afdc3ccd (ceph): librados: add async_watch_flush api
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:37 AM Revision b651dd7e (ceph): RadosClient: add async watch_flush version
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:37 AM Revision f5d8da62 (ceph): Objecter: make linger_callback_flush accept context instead of blocking
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision 569b1213 (ceph): librados: add unittest for rados aio watch
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision 28ac2638 (ceph): librados: support aio_unwatch api
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision 2be574af (ceph): test: add aio_unwatch unittest
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision f04c96cd (ceph): librados: remove unused variables
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision f977f0ab (ceph): librados: add C api impl and tracing codes
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:22 AM Revision 87e715c5 (ceph): librados: add async watch api
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:19 AM Revision 9e1cf70e (ceph): cls::journal: don't print client data
It makes `rbd journal status` output look ugly.
It is a temporary solution and is going to be improved in
the future...
Mykola Golub
06:19 AM Revision 0aaaf367 (ceph): librbd: allow to use journal replay externally
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
06:19 AM Revision 886e28ab (ceph): journal: wrappers to get journal metadata
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
06:15 AM Revision f250f4ea (ceph): osdc/objectCacher: Remove the unsed field.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
06:15 AM Revision a8793010 (ceph): Striper: Add total_intended_len in StripedReadResult
Using this field record the total len which we wanted.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Jianpeng Ma
06:15 AM Revision 9867804c (ceph): Striper: Add function 'assemble_result(CephContext *cct, char *buffer, ...
For sparse read, it can avoid copying zero around.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Jianpeng Ma
06:15 AM Revision c68d00ce (ceph): test/bufferlist:Add test case for bufferlist::is_provided_buffer.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
06:15 AM Revision ed54420e (ceph): bufferlist: Add new func is_provided_buffer(const char *dst)
Using this function to judge whether copy data from bufferlist to
dst. It mainly used librados C interface to avoid c...
Jianpeng Ma
05:33 AM Stable releases Tasks #13356: hammer v0.94.6
For the record, in a mail sent today by Yuri:
The following suites were in scope of this point release testing:
...
Loïc Dachary
05:29 AM rbd Backport #14824: hammer: rbd and pool quota do not go well together
Original description: A partial backport to fix the OSD crash was completed already (#13335). This ticket is to adapt... Loïc Dachary
05:26 AM rbd Bug #12018 (Pending Backport): rbd and pool quota do not go well together
Loïc Dachary
05:16 AM Revision 52c04b81 (ceph): common/TrackedOp: avoid implicitly cast for return value
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> xie xingguo
05:16 AM Revision b2bfd6cc (ceph): common/TrackedOp: fix inaccurate counting for total slow requests
In the original design there are two counters in charge of collecting
potentially problematic requests, namely 'slow'...
xie xingguo
03:42 AM CephFS Bug #9679: Ceph hadoop terasort job failure
I'm testing ceph version 10.0.3-1325-g98fba62 on hadoop 3.0.0 and I see the same error in hadoop terasort.
I'm not s...
Dmitry Buzz
02:50 AM rgw Bug #14826 (Resolved): rgw: bucket listing following object delete is partial
I noticed a weird behavior in current master:
- create bucket
- put a few objects in bucket
- try to delete obj...
Yehuda Sadeh
12:56 AM Revision 4fb688d1 (ceph): osd: write journal header by force when journal write close
osd update the journal header when ceph call FileStore::sync_entry(
ApplyManager::commit_finish -> FileJournal::commi...
Xinze Chi
12:56 AM Revision a1fc1010 (ceph): crushtool: send --tree to stdout
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit dca345280e4f6124a8b5aea73e6219488111c356)
Conf...
Sage Weil
12:51 AM Revision b89ba998 (ceph): Merge pull request #7627 from dillaman/wip-librbd-read-replay
librbd: block read requests until journal replayed
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:50 AM Revision ff82fd16 (ceph): Merge pull request #7718 from dillaman/wip-librbd-mirror-peer
librbd: update of mirror pool mode and mirror peer handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:50 AM Revision 44d7819c (ceph): Merge pull request #7698 from dillaman/wip-librbd-replay-flush
librbd: differentiate journal replay flush vs shut down
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
12:14 AM Revision c8858019 (ceph): Merge pull request #7720 from ceph/wip-rgw-aws4
rgw support for aws authentication v4 (Javier M. Mellid) Yehuda Sadeh

02/19/2016

11:28 PM Bug #13421 (Need More Info): ceph-osd Segmentation fault in pthread_join
This has been seen in a mon on Hammer.
0> 2016-02-12 23:23:28.169430 7f88a84f97c0 -1 *** Caught signal (Abort...
Brad Hubbard
10:34 PM Revision 55271599 (ceph): Merge remote-tracking branch 'jmunhoz/wip-aws4' into wip-aws4
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/rgw/rgw_auth_s3.h
src/rgw/rgw_client_io.cc
src/rgw...
Yehuda Sadeh
09:42 PM Revision a646103e (ceph): Merge pull request #7719 from ceph/wip-rgw-keystone-v3
rgw keystone v3 (Mark Barnes, Radoslaw Zarzynski)
support for keystone v3
Reviewed-by: Matt Benjamin <mbenjamin@red...
Yehuda Sadeh
09:14 PM Linux kernel client Bug #14715: "rbd: sysfs write failed" in krbd-hammer-testing-basic-smithi
Heh, I never finished it, because it seemed wrong ;) I'd rather we carry a patch in the testing branch, disabling th... Ilya Dryomov
09:12 PM Revision 0ec038ab (ceph): librbd: support image and pool-level mirroring modes
If pool-level mirroring is enabled, all journaled images within
the pool are eligible for mirroring. If image-level ...
Jason Dillaman
09:12 PM Revision 700c3dc2 (ceph): librbd: update mirror peer data structure
Replace cluster uuid with mirror peer uuid and support an
optional pool id within a peer (when using internal APIs
fo...
Jason Dillaman
09:01 PM rbd Bug #14085 (Can't reproduce): TestInternal.ShrinkFlushesCache librbd/test_internal.cc:686: Value ...
Jason Dillaman
08:58 PM rbd Subtask #14412 (Resolved): Track epoch and period for mirrored images
Jason Dillaman
08:28 PM Revision 7e0fb5dd (ceph): rados/singleton: use xfs instead
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
08:28 PM Revision 8cf25611 (ceph): ceph_manager: use time before mon command for timeout
Slow mon commands can cause a false failure.
Signed-off-by: Samuel Just <sjust@redhat.com>
Samuel Just
08:28 PM Revision b2a08efe (ceph): tasks/*unfound*.py: run rados bench in parallel
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
08:28 PM Revision ef75c897 (ceph): rados: add lost-unfound upgrade tests
Signed-off-by: Samuel Just <sjust@redhat.com> Samuel Just
08:28 PM Revision af3af304 (ceph): divergent_priors: add sleep after reviving divergent
Basically same thing as
c0b0ec2831f410d89b695a1d08122334d8ee907a
client is getting ENXIO when trying to do osd tell b...
Samuel Just
08:22 PM devops Bug #14785 (Fix Under Review): rpm: %_with_ocf handling in configure broken in OBS
Nathan Cutler
08:16 PM Revision 92764d42 (ceph): rgw: handle Keystone API version with dedicated enum.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision bc6d7c30 (ceph): rgw: ONLY formatting improvements for Keystone-related code.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision 90e1f394 (ceph): rgw: improve debugs in RGWPostHTTPData.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision 2f190fdc (ceph): rgw: Keystone token parsing should fail on misformed JSONs.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision abbd9129 (ceph): rgw: S3 always must use token format of Keystone v2.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision 55cbc60d (ceph): rgw: Keystone token parsing doesn't need to know API version.
This patch targets an issue with S3Extension in Keystone:
requested tokens always conform to Keystone API v2 - regard...
Radoslaw Zarzynski
08:16 PM Revision a622e3f9 (ceph): rgw: rework serialization in token retrieval for Keystone's admin.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision 8e906868 (ceph): rgw: fix wrong format of admin token request in Keystone v3.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision 84bcb506 (ceph): rgw: fix Keystone v2 regression in role's JSON parsing
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
08:16 PM Revision d3299b0f (ceph): rgw: accommodate Keystone v3 in S3-related auth mechanisms.
This patch is based on changes proposed by Mark Barnes
<mark.barnes@ocado.com> (lperiquito) in commit
af71f6a518529ea...
Radoslaw Zarzynski
08:16 PM Revision c5b114bb (ceph): rgw: accommodate Keystone v3 in RGWSwift class.
This patch is based on changes proposed by Mark Barnes
<mark.barnes@ocado.com> (lperiquito) in commit
af71f6a518529ea...
Radoslaw Zarzynski
08:16 PM Revision 46a48813 (ceph): rgw: unify RGWValidateKeystoneToken with RGWPostHTTPData.
The change has been extracted from changeset proposed
in commit af71f6a518529ea6cccb25bd46da2b6d1458c1da by
Mark Barn...
Luis Periquito
08:16 PM Revision 38ee6614 (ceph): rgw: basic data structures for Keystone v3.
The change has been extracted from changeset proposed
in commit af71f6a518529ea6cccb25bd46da2b6d1458c1da by
Mark Barn...
Radoslaw Zarzynski
08:16 PM Revision a868e598 (ceph): rgw: make RGWPostHTTPData able to extract X-Subject-Token.
The change has been extracted from changeset proposed
in commit af71f6a518529ea6cccb25bd46da2b6d1458c1da by
Mark Barn...
Radoslaw Zarzynski
08:00 PM devops Bug #14687 (Fix Under Review): RPM: no /usr/libexec directory on SUSE
*jewel PR*: https://github.com/ceph/ceph/pull/7636 Nathan Cutler
07:40 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
corresponding issue #14824 Yuri Weinstein
04:49 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Next try commit 951339103d35bc8ee2de880f77aada40d15b592a
passed
http://pulpito.ceph.com/teuthology-2016-02-19_1...
Yuri Weinstein
04:01 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Tests on 2817ffcf4e57f92551b86388681fc0fe70c386ec in ReplicatedPG commit failed all in similar way => .... Yuri Weinstein
07:29 PM devops Bug #14756 (Fix Under Review): EC testing plugins are being versioned and installed even though t...
Nathan Cutler
07:29 PM Bug #13098 (Pending Backport): OSD crashed when reached pool's max_bytes quota
Josh Durgin
07:28 PM rbd Backport #14824 (Rejected): hammer: rbd and pool quota do not go well together
Josh Durgin
07:22 PM Revision 3c5bc079 (ceph): Makefile: workaround an automake bug for "make check"
override the automake variable of am__is_gnu_make. it is a workaround
for http://debbugs.gnu.org/cgi/bugreport.cgi?bu...
Kefu Chai
06:33 PM Revision ad56c201 (ceph): tasks/divergent_prior[2]: fix rados get syntax
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 6064443ad1e0dd87801a4508025906d5e26c02c5)
Sage Weil
05:51 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
I just sent you the new osd log via email.
What I did for this test was write a bunch of RBD data and take lots of...
Steve Taylor
01:32 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
Steve, you can either send it over to me (tchaikov@gmail.com), or post it here. but before that, i want to confirm wi... Kefu Chai
05:36 PM rgw Bug #13448: /etc/init.d/radosgw-agent: configuration file default.conf not found
See if below info resolves this restart service issue :
To use complete file path instead of just filename i.e...
Sriharsha YD
05:15 PM Revision 6c645780 (ceph): buffer: hide iterator_impl symbols
buffer::list::iterator_impl symbols are referenced by const_iterator
and iterator, and are exposed as weak symbols. i...
Kefu Chai
05:15 PM Revision 694f92f3 (ceph): PendingReleaseNotes: document the dropped buffer symbols
the symbols of buffer::list::iterator_impl<> were wrongly exposed
in previous infernalis release, and the clients lin...
Kefu Chai
05:05 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
The sequence of events as far as I can tell is
1) Cluster happy
2) gqac022 reimaged to serve as mon in smaller clus...
Samuel Just
05:02 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
Backtraces from another node as well, still no sign of the call into handle_auth. Samuel Just
04:56 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
Replaced with slightly more complete version. Samuel Just
04:50 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
Attached backtraces from one of the nodes, no mention of MonClient::handle_auth. Not sure whether that torpedoes my ... Samuel Just
04:36 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
<bennyturns> sjusthm, its feasible the OS install would be done by then
<sjusthm> bennyturns: I think you reimaged t...
Samuel Just
04:28 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
On one mon node:
[global]
rbd cache writethrough until flush = false
osd crush chooseleaf type = 0
osd crush up...
Samuel Just
04:20 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
Is there anything which actually protects from a race between the monc->auth access in OSD::ms_get_authorizor and the... Samuel Just
04:15 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
145 (in the summary) also has the same pattern
Thread 1459 (Thread 0x7fa3eb833700 (LWP 604327)):
#0 0x00007fa4...
Samuel Just
04:13 PM Bug #14821: OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4bfad3a3c51054df7e5...
From another osd, two threads actually ran into trouble in that method:
Thread 1209 (Thread 0x7f66d74a4700 (LWP 60...
Samuel Just
03:47 PM Bug #14821 (Can't reproduce): OSD segfault in ms_get_authorizer -- hammer ceph version 0.94.1 (e4...
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/lib64/libthread_db.so.1".
bCore was...
Samuel Just
04:34 PM Revision 7249a5cf (ceph): librbd: read ops require journal replay
When journaling is enabled, a read op should acquire the exclusive
lock and replay the journal in case uncommitted wr...
Jason Dillaman
04:33 PM Revision 6582b7d5 (ceph): Merge pull request #7717 from cbodley/wip-cmake-rbd-image-watcher
cmake: add missing librbd image_watcher sources
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
04:18 PM Revision b61f4676 (ceph): cmake: add missing librbd image_watcher sources
Fixes: #14823
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
04:17 PM Bug #14823 (Resolved): cmake: targets fail to link against librbd.so with missing librbd::image_w...
The targets smalliobenchrbd, test_librbd_fsx and test_cls_rbd fail to link in cmake with the following errors:
../...
Casey Bodley
04:07 PM rbd Bug #14822 (Resolved): Journal replay needs to support replaying successful maintenance ops
For example:
journal snap create start
snap create
journal snap create finish
<crash>
-- on replay --
snap cr...
Jason Dillaman
03:22 PM Revision 0f45d589 (ceph): Merge pull request #7709 from ceph/wip-rgw-new-multisite-merge
rgw multisite v2 (Yehuda Sadeh, Orit Wasserman, Casey Bodley)
- rename region to zonegroup
- new zone and zonegroup...
Yehuda Sadeh
03:00 PM rgw Bug #14820 (Duplicate): s3cmd rb --recursive doesn't decrease total_entries in stats
Hello,
When you use s3cmd with 'rb --recursive', the stats informations about user total_entries is not well decre...
Quentin Perez
02:37 PM Revision 9d25202a (ceph): Makefile: workaround an automake bug for "make check"
override the automake variable of am__is_gnu_make. it is a workaround
for http://debbugs.gnu.org/cgi/bugreport.cgi?bu...
Kefu Chai
02:36 PM Revision c7eba2aa (ceph): src/yasm-wrapper: ignore parameters starting with ggc-min
When the "with lowmem_builder" bcond is active, the string "--param
ggc-min-expand=20 --param ggc-min-heapsize=32768"...
Nathan Cutler
02:32 PM Revision 882066d6 (ceph): doc: standardize @param (not @parma, @parmam, @params)
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
01:40 PM Linux kernel client Bug #13905 (Closed): "BUG: held lock freed!"
This indeed turned out to be a regression in the networking layer, see http://www.spinics.net/lists/ceph-devel/msg286... Ilya Dryomov
01:02 PM rgw Bug #14816 (Fix Under Review): rgw: failed to use s3 bucket since commit 2f706ef
Nathan Cutler
08:27 AM rgw Bug #14816: rgw: failed to use s3 bucket since commit 2f706ef
fixed by https://github.com/ceph/ceph/pull/7710 Dunrong Huang
08:04 AM rgw Bug #14816 (Resolved): rgw: failed to use s3 bucket since commit 2f706ef
*Description*
Since commit 2f706ef, failed to operate bucket using s3 api
[root@ceph1 obs]# s3cmd ls
ERROR: S3...
Dunrong Huang
11:51 AM Revision d71df261 (ceph): test_Replay.cc: prefer ++operator for non-primitive iterators
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 91a8b1b2 (ceph): journal/JournalMetadata.cc: compare size of lhs instead of rhs to rhs
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 61698545 (ceph): compressor/zlib/CompressionZlib.cc: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 00af2a27 (ceph): compressor/zlib/CompressionPluginZlib.cc: use explicit for ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision c51ada3b (ceph): ErasureCodeJerasure.h: init packetsize member var in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 60b61b45 (ceph): librbd/AioImageRequest.cc: reduce scope of var
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision a37ae6a3 (ceph): log/Graylog.h: make ctor explicit
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision e5c9694a (ceph): msg/async/Event.cc: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision e6d3a0f9 (ceph): msg/async/EventKqueue.cc: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 1f0c1b1a (ceph): librbd/ImageCtx.cc: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision c645bd9c (ceph): librbd/DiffIterate.cc: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision a55f8c21 (ceph): librbd/operation/RebuildObjectMapRequest.cc: init m_snap_list_ret in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:51 AM Revision 4213b869 (ceph): msg/xio/XioConnection.h: init some member variables in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision c08435cf (ceph): client/Client.cc: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision aef72abe (ceph): mds/mdstypes.h: init fnode_t::damage_flags in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision a5d78c22 (ceph): rgw/rgw_admin.cc: remove unused variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision 822eecf8 (ceph): rgw/rgw_op.cc: remove unused variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision d407faa2 (ceph): rgw/rgw_rados.cc: remove unused variable locator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision 2b603064 (ceph): client/Client.cc: init owner_uid and owner_gid vars in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision cfd07653 (ceph): client/SyntheticClient.cc: remove unused code
Removed since 2007 unused code and fixed indentation.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf
11:50 AM Revision 729117f9 (ceph): client/SyntheticClient.cc: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision 8793921c (ceph): mds/Server.cc: replace inefficient string::find() w/ compare()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision fc443474 (ceph): cls/rbd/cls_rbd.cc: reuse existing variable with same name
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision 44e028f9 (ceph): HTMLFormatter: reuse m_header_done from parent class
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision b906041a (ceph): common/Graylog.h: make constructor explicit
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:50 AM Revision 11bfc6df (ceph): common/PluginRegistry.h: init Plugin::library in ctor
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:49 AM rgw Bug #14819 (New): RadosGW and OpenStack Kilo Keystone's integration fails
RadosGW is working fine with swift cli client. When tries to integrate with Keystone(1.2.0 version), rgw fails with a... Yogesh Deshmukh
11:12 AM Bug #14797: osd: add all backfill osd to backfill_targets
For pg 1.7d
In timestamp 2016-02-11 23:40:51.235507 osd.2 is auth_log_shard and it's log_tail is 191'185, the last...
Xinze Chi
10:48 AM Revision 56dd09fc (ceph): mds: Add posix file lock deadlock detection
Signed-off-by: Yan, Zheng <zyan@redhat.com> Yan, Zheng
10:18 AM CephFS Bug #14818 (Resolved): Cython librados broke libcephfs/ceph_volume_client
Specifically, the create_with_rados libcephfs function is no longer happy.... John Spray
10:10 AM Revision 877eae85 (ceph): os/filestore: fix result code overwritten for clone
During the clone process, the result code of syscall-fstat which is intend for
getting the source size for copying is...
xie xingguo
09:56 AM Revision f6692a42 (ceph): Merge pull request #7371 from theanalyst/mon/quota-msg-cleanup
mon: cleanup set-quota error msg
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
09:48 AM Bug #14817 (Resolved): os/filestore: result code of fstat overwritten
xie xingguo
08:37 AM rgw Bug #14812: s3test failure in rados suite
I also met this bug, see
http://tracker.ceph.com/issues/14816
and wrote a patch to fix:
https://github.com/ceph...
Dunrong Huang
08:34 AM Revision 49a7ef50 (ceph): Merge pull request #7708 from jdurgin/wip-cython-cleanup
pybind: replace __del__ with __dealloc__ for rbd
Reviewed-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Mehdi Ab...
Josh Durgin
08:29 AM Revision a917ccfc (ceph): mon: cleanup set-quota error msg
When we send in an unrecognized field for set-quota, specify that the
options should be `max_bytes` or `max_objects`....
Abhishek Lekshmanan
08:15 AM Revision b556b24a (ceph): Merge pull request #7668 from dillaman/wip-librbd-replay-locks
librbd: use async librados notifications
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:58 AM Feature #14454: mon: report pool deletion in "ceph -w"
what do we want?
may be we want the ceph -w can display the results of rados tool, admin socket or via librados pyb...
Anonymous
07:50 AM Revision 9695a0b4 (ceph): rgw: avoid empty object names
Don't try to sync an object with empty name (shouldn't happen, but
bugs may happen). Also, don't try to write_meta() ...
Yehuda Sadeh
07:49 AM Revision 3d391546 (ceph): .gitignore: include recently added rgw programs
Signed-off-by: Josh Durgin <jdurgin@redhat.com> Josh Durgin
07:49 AM Revision 3f525f40 (ceph): rgw: fix s3 list bucket (affects format=json)
another merge casualty. The section wasn't opened properly.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
07:47 AM Revision 0a988f95 (ceph): pybind: replace __del__ with __dealloc__ for rbd
Cython extension types like these don't call __del__, but use
__dealloc__ instead:
http://docs.cython.org/src/usergu...
Josh Durgin
07:46 AM Revision 5489ad3a (ceph): Merge pull request #7706 from sileht/sileht/rados-cython
pybind: remove next() on iterators
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
07:29 AM Revision 7be19c28 (ceph): os/filestore: fix wrong scope of result code for error cases during mount
This pr is similar to https://github.com/ceph/ceph/pull/7704
but I feel like making a new one in case they need to be...
xie xingguo
07:24 AM Bug #14815 (Resolved): os/filestore: mount may return OK even if it encounters internal error.
This bug is much alike as
http://tracker.ceph.com/issues/14814
But I make a new one in case they need to be treat...
xie xingguo
07:09 AM Revision 1e472685 (ceph): rgw: only validate bucket name if not empty
This got broken due to code movement
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
07:07 AM Revision 804e6c8f (ceph): rgw: resurrect lost code
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
06:59 AM Revision f98b4855 (ceph): pybind: remove next() on iterator
Cython recommends to implement only __next__() methods.
http://docs.cython.org/src/userguide/special_methods.html#th...
Mehdi Abaakouk
06:56 AM Revision 024caa72 (ceph): mon/pgmonitor: use appropriate forced conversions in get_rule_avail
use appropriate forced conversions in get_rule_avail
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
renhwztetecs
06:55 AM Revision 36af4802 (ceph): common: default cluster name to config file prefix
Signed-off-by: Javen Wu <javen.wu@xtaotech.com> Javen Wu
06:45 AM Revision 68f300dd (ceph): os/filestore: fix wrong scope of result code for error cases during mkfs
During the mkfs process, if we fail to read and sometimes rewrite the
op_seq, the mkfs process is abnormally terminat...
xie xingguo
06:25 AM Revision 78b3c40c (ceph): Merge pull request #7641 from batrick/vstart-usage
Clarify usage on starting single osd/mds/mon.
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
06:16 AM Revision 8243d180 (ceph): Event: replace fileevent array to vector
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:15 AM Revision d5463d76 (ceph): Event: delete leak event callback
Signed-off-by: Haomai Wang <haomai@xsky.com> Haomai Wang
06:09 AM Bug #14814 (Resolved): os/filestore: mkfs may return OK even if it encounters internal error.
@ uint64_t initial_seq = 0;
int fd = read_op_seq(&initial_seq);
if (fd < 0) {
derr << "mkfs: fail...
xie xingguo
04:49 AM Revision 72b03330 (ceph): test/Makefile-client.am: adjustment following merge
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
04:42 AM Backport #14077 (In Progress): hammer: scrub bogus results when missing a clone
Loïc Dachary
03:53 AM Revision eee7d9e0 (ceph): librbd: helper method for flushing journal commit positions
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
03:53 AM Revision 999a319d (ceph): journal: added interface to flush pending commit position updates
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:00 AM Revision a1fcb53e (ceph): tasks/reg11184.py: fix rados get syntax
no -o
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 7b3ea31efeb0da81b3a5ed486cebce72edbf2fec)
Sage Weil
01:42 AM Revision 398c493f (ceph): Merge pull request #7692 from sileht/sileht/rados-cython
pybind/rados: use __dealloc__ since __del__ is ignored by cython
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:14 AM Revision 4d494d5b (ceph): Merge remote-tracking branch 'origin/master' into wip-rgw-new-multisite
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Conflicts:
src/CMakeLists.txt
src/rgw/Makefile.am
src/rgw/rgw_adm...
Yehuda Sadeh
01:09 AM rgw Bug #14585 (Resolved): rgw_main.cc: fuction main should not ignore the return value when call fe-...
https://github.com/ceph/ceph/pull/7457 xie xingguo
12:58 AM Revision 1cfd9658 (ceph): librbd: differentiate journal replay flush vs shut down
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
12:21 AM Revision f07540ea (ceph): Thrasher: Fix log message
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit ca04dc65c197f54fd6f71806059c4323cc8ee86c)
David Zafman
12:21 AM Revision 137e18ef (ceph): divergent_priors: Fix divergent_priors task
Flake8 fixes
Use new set_recovery_delay admin socket command
Fix bad value set for filestore_blackhole
Make sure log ...
David Zafman
12:21 AM Revision 578a113e (ceph): divergent_priors2: Do divergent priors and ceph-objectstore-tool export...
Based on tasks/divergent_priors.py but also do simple export/remove/import on
same osd.
Add yaml file to run the dive...
David Zafman
12:21 AM Revision 70c149f7 (ceph): reg11184: Add regression test for 11184
Create divergent priors and a split and then move a pg using
ceph-objectstore-tool export/import
Add yaml file to run...
David Zafman
12:21 AM Revision 69988bd3 (ceph): thrasher: Can't test ceph-objectstore-tool if nodes turned off (powercy...
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit b255db820ffd1d3e1253a9a60c7192696c226490)
David Zafman
12:08 AM devops Bug #14811 (Fix Under Review): RPM: yasm complains when building with %{with lowmem_builder}
Nathan Cutler
12:07 AM devops Bug #14811: RPM: yasm complains when building with %{with lowmem_builder}
*jewel PR*: https://github.com/ceph/ceph/pull/7700 Nathan Cutler

02/18/2016

11:38 PM rgw Bug #14812 (Resolved): s3test failure in rados suite
2016-02-18T14:52:44.683 INFO:teuthology.orchestra.run.smithi028.stdout:Using /home/ubuntu/cephtest/s3-tests/virtualen... Samuel Just
11:36 PM Bug #14797: osd: add all backfill osd to backfill_targets
I don't understand how this can happen. When we start backfilling, we set pi.last_update to info.last_update (as part... Samuel Just
01:30 AM Bug #14797 (Can't reproduce): osd: add all backfill osd to backfill_targets
if pg_log.get_tail() > pi.last_update return true, it is possible that the peer is not in backfill_targets.
I am not...
Xinze Chi
11:25 PM Revision ac168e3f (ceph): rgw: add drain_all() before exiting a cr
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
11:20 PM Revision d95fcfa5 (ceph): rgw: silence compilation #warnings
these are now FIXMEs
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
11:18 PM Revision 996e6e9a (ceph): rgw: more error reporting
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
11:18 PM Revision ac726c6d (ceph): rgw: data sync error handling (for sync init)
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
11:14 PM devops Bug #14811 (Resolved): RPM: yasm complains when building with %{with lowmem_builder}
When the "with lowmem_builder" bcond is active, the string "--param ggc-min-expand=20 --param ggc-min-heapsize=32768"... Nathan Cutler
11:11 PM Revision d2d0f847 (ceph): rgw: a bit better hashing
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
10:58 PM Revision 4f15332d (ceph): librbd: don't hold owner lock while refreshing image synchronously
The write lock will be taken when the new state is applied.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
10:56 PM Revision 4ecdf066 (ceph): librbd: need owner write lock when disabling exclusive lock
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
10:46 PM Revision 922072ae (ceph): librbd: correct memory leaks discovered via valgrind
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
10:46 PM Revision 7e09cb13 (ceph): librbd: notifications should be flushed between exclusive lock states
Avoid leaving in-flight notification messages when transitioning lock
states.
Signed-off-by: Jason Dillaman <dillama...
Jason Dillaman
10:31 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Greg the test passed on that commit.
http://pulpito.ceph.com/teuthology-2016-02-18_13:42:45-fs-wip-test-14716-2---...
Yuri Weinstein
01:11 AM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Well at least it's consistent. Can you also try commit:2c8e57934284dae0ae92d1aa0839a87092ec7c51 against smithi/mira?
...
Greg Farnum
10:17 PM Bug #14810 (Resolved): "FileStore.cc: 2855: FAILED assert(0 == "unexpected error")" in powercycle...
infernalis v9.2.1 testing
Run: http://pulpito.ceph.com/teuthology-2016-02-18_09:34:39-powercycle-infernalis-testing-...
Yuri Weinstein
10:11 PM Linux kernel client Bug #13905: "BUG: held lock freed!"
infernalis v9.2.1 testing
Run: http://pulpito.ceph.com/teuthology-2016-02-18_09:34:39-powercycle-infernalis-testing-...
Yuri Weinstein
10:04 PM Revision 6b6625e2 (ceph): rgw: get period history cursor when starting sync
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision eebe61a5 (ceph): rgw: RGWMetaSyncCR loops through period history
RGWMetaSyncCR uses a period history Cursor to track its position. it
uses this to get the max sync markers for each s...
Casey Bodley
10:04 PM Revision 34ea6bcc (ceph): rgw: add map of period_id -> RGWMetadataLog
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 02edcdd9 (ceph): rgw-admin: update callers of get_log
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision adab1e18 (ceph): rgw: add period id to rgw_rest_log operations
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 98813301 (ceph): rgw: factor get_log_shard_id() out of RGWMetadataLog
by using RGWRados::key_to_shard_id(), we can avoid the dependency on
RGWMetadataLog's prefix (and period)
Signed-off...
Casey Bodley
10:04 PM Revision f10a6d4f (ceph): rgw: add first log period to mdlog info response
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision be5c263f (ceph): rgw: rados coroutines take bucket by const ref
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 12cae9e7 (ceph): rgw: remove RGWMetadataManager::store_md_log_entries
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 1ebb55b2 (ceph): rgw: remove RemoteMetaLog::fetch() and admin command
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision fe681503 (ceph): cmake: remove duplicate rgw source files
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision ea9f0fc3 (ceph): rgw: use std::move for strings in RGWFetchAllMetaCR
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 3c990d22 (ceph): rgw: include period id in rgw_meta_sync_info
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 25771efa (ceph): rgw: move sync_status into RGWRemoteMetaLog
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 699809e1 (ceph): rgw: RGWRemoteMetaLog passes period id with requests to master
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 5b12ec0b (ceph): rgw: add period id to metadata log oids
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 10cda14b (ceph): rgw-admin: command to list sync error logs
$ radosgw-admin sync error list
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:04 PM Revision 3cb199a4 (ceph): rgw: we need to clear the id in create_default in case of a race
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
10:04 PM Revision 1999c57d (ceph): rgw: remove unneeded RGWRados arg for RGWMetadataLog
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision 10cdb886 (ceph): rgw: remove unused clone_shards() in metadata sync
clone_shards() was an exact duplicate for fetch()
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
10:04 PM Revision c13e7ee7 (ceph): rgw: remove unused class RGWReadMDLogShardInfo
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
10:04 PM Revision be06128b (ceph): rgw: remove unused RGWRemoteMetaLog::list_shards
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
09:56 PM Revision 28850142 (ceph): rgw: set quota when converting regionmap
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:45 PM rbd Cleanup #14809 (Resolved): ImageWatcher unwatch and flush should use async librados methods
See https://github.com/ceph/ceph/pull/7649 for new API Jason Dillaman
09:43 PM CephFS Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
I was not aware of any issues prior to the upgrade. I am posting the files now, and I'll let you know the tag when it... Christopher Nelson
08:57 PM CephFS Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
Do you have the MDS log from when this first started happening, and can you please upload it? (ceph-post-file will le... Greg Farnum
03:44 PM CephFS Bug #14807 (Can't reproduce): MDS crashes repeatedly after upgrade to Infernalis from Hammer
I have a small cluster (1xMON 1xMDS 2xOSD). It has been very stable for the last year.
However, after the upgrade ...
Christopher Nelson
08:48 PM Revision 2530d622 (ceph): Merge pull request #823 from ceph/wip-dir-rstats
add test for norstats functionality Greg Farnum
08:47 PM Revision 957c77d5 (ceph): Merge pull request #7323 from ukernel/wip-client-dirsize
client: add option to control how directory size is calculated
This lets you disable rstats if your workload is unha...
Greg Farnum
08:45 PM Revision 9d0b5b9e (ceph): librbd: cleanup header update notifications
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
08:45 PM Revision bc2ae0ef (ceph): librbd: use AIO notifications to prevent blocking ops
If two or more images share the same CephContext, notifications
from one image can block the work queue which will po...
Jason Dillaman
08:45 PM Revision e01b4067 (ceph): librbd: journal replay should execute ops in clean context
lockdep will complain about loop cycles that won't cause an
issue in reality as replay and record are two different
j...
Jason Dillaman
08:45 PM Revision ad78558a (ceph): librbd: missing owner lock on snap rollback cache invalidation
Signed-off-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
08:45 PM Revision 3d8d9da3 (ceph): librbd: update image name upon rename operations
Previously the image could not have been renamed twice without
re-opening the image.
Signed-off-by: Jason Dillaman <...
Jason Dillaman
08:45 PM Revision dd5c9e55 (ceph): librbd: support for AIO notifications
The header update and lock notifications might be invoked
from the librados AIO thread. Update the close state
machi...
Jason Dillaman
08:45 PM Revision 2c656171 (ceph): Revert "librbd: lock notifications should be executed outside librados ...
This reverts commit d898995b0e3ea301b1325f68a0532d57afa3c816.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman
08:44 PM Revision 12a55d6b (ceph): rstats: enable by default on client; move test workunit to its own dir
Signed-off-by: Greg Farnum <gfarnum@redhat.com> Greg Farnum
06:09 PM rgw Bug #14652 (Resolved): "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-bas...
Yuri Weinstein
04:24 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
https://github.com/ceph/ceph-qa-suite/pull/825
tests:
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02...
Yuri Weinstein
05:27 PM Stable releases Tasks #13750: infernalis v9.2.1
h3. QE VALIDATION (STARTED 2/18/16)
*re-runs command lines and filters are captured in http://pad.ceph.com/p/infer...
Yuri Weinstein
05:05 PM Revision d7564c11 (ceph): Merge pull request #825 from ceph/wip-14652-hammer
Fixes #14652 (moved rbd and rgw tests on separate clients, forced s3tests branch)
Reviewed-by: Josh Durgin <jdurgin@...
Josh Durgin
04:16 PM Revision 3687a0d9 (ceph): Merge pull request #7457 from weiqiaomiao/w1
Rgw: check the return value when call fe->run()
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
04:08 PM Revision 210b075d (ceph): Merge pull request #7666 from rzarzynski/wip-rgw-sysreq-over-swift
rgw: add support for system requests over Swift API
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
04:04 PM Revision 55689f9b (ceph): Merge pull request #7678 from linuxbox2/rgw-sigusr1
rgw: move signal.h dependency from rgw_front.h
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
03:40 PM CephFS Bug #14672: MDS crashes with FAILED assert(inode_map.count(in->vino()) == 0) in 9.2.0
I have this same problem, and I did not do a newfs. I simply upgraded from Hammer to Infernalis:... Christopher Nelson
03:35 PM CephFS Bug #14641: don't let users specify 0 on stripe count or object size
It was a brand new 9.2 cluster. Haven't yet seen the issue again.. Kenneth Waegeman
03:15 PM Revision ff9f9288 (ceph): Merge pull request #7 from Abhishekvrshny/fix-release-notes-unicode
Fix unicode encoding for non-ASCII characters in title and author names
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:08 PM Revision 284075cc (ceph): Fix unicode encoding for non-ASCII characters in title and author names
Signed-off-by: Abhishek Varshney <abhishek.varshney@flipkart.com>
Reviewed-by: Loic Dachary <loic@dachary.org>
Abhishek Varshney
02:46 PM Revision 73e02e8e (ceph): Merge pull request #776 from ceph/wip-sharded-scan
tasks/cephfs: test sharded cephfs-data-scan Greg Farnum
02:45 PM CephFS Feature #12144 (Resolved): cephfs-data-scan: integrated with sharded pgls
https://github.com/ceph/ceph/pull/7034 Greg Farnum
02:41 PM Revision bf24e351 (ceph): Merge branch 'greg-pr-7034'
Greg Farnum
01:58 PM Revision 138d7718 (ceph): Merge pull request #7679 from linuxbox2/rgw-ssconst
sstring.hh: return type from str_len(...) need not be const
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
01:58 PM rgw Bug #14806 (In Progress): rgw: TempURL authentication of Swift API doesn't work
I'm working on that. Radoslaw Zarzynski
01:57 PM rgw Bug #14806 (Resolved): rgw: TempURL authentication of Swift API doesn't work
_authenticate_temp_url()_ has a check at the beginning to ensure that _s->bucket_name_ is non-empty. Otherwise it ret... Radoslaw Zarzynski
01:38 PM Revision cded77d0 (ceph): release-notes: draft v9.2.1 release notes
Signed-off-by: Abhishek Varshney <abhishek.varshney@flipkart.com> Abhishek Varshney
11:19 AM Revision 69291f87 (ceph): packaging: move ceph_common.sh and ceph-osd-prestart.sh to /usr/lib/ceph
First, it makes sense for both ceph_common.sh and ceph-osd-prestart.sh to
reside in the same directory: make it so.
...
Nathan Cutler
10:45 AM Revision f0dcd32b (ceph): [ceph-fuse] Fh ref might leak at umounting
Signed-off-by: Zhi Zhang <zhangz.david@outlook.com> Zhi Zhang
10:44 AM CephFS Bug #14805 (Resolved): Hadoop tests failing with EPERM

Most recent instance:
http://pulpito.ceph.com/teuthology-2016-02-17_18:12:06-hadoop-jewel---basic-mira/
Here's ...
John Spray
10:39 AM Bug #14804 (Fix Under Review): Common/TrackedOp: inaccurate count for total slow requests
https://github.com/ceph/ceph/pull/7690 Kefu Chai
07:20 AM Bug #14804 (Resolved): Common/TrackedOp: inaccurate count for total slow requests
Check bool OpTracker::check_ops_in_flight for detail information. xie xingguo
10:26 AM Revision 0fb387fa (ceph): pybind: rados cleanup
This change uses:
* a pystring to store ioctx state like other state attributes and like
previous binding
* use __d...
Mehdi Abaakouk
08:10 AM Bug #14788 (Fix Under Review): librados (C++) linker error (undefined reference)
https://github.com/ceph/ceph/pull/7688 Kefu Chai
07:09 AM Bug #14788: librados (C++) linker error (undefined reference)
if that's the case which Jesse ran into. it's because the new buffer.h is referencing the symbols of @buffer::list::i... Kefu Chai
03:26 AM Bug #14788 (New): librados (C++) linker error (undefined reference)
this reminds me of #13429.
turns out i was compiling with the header in my source repo, while linking against the ...
Kefu Chai
02:42 AM Bug #14788: librados (C++) linker error (undefined reference)
What version is this?
That missing semicolon was fixed last year.
I can't reproduce this behaviour on master, c...
Brad Hubbard
08:10 AM Revision b3f8dd8c (ceph): scripts: ceph-release-notes fixes --strict
When --strict,
* Do not take into account the merge message. This is is not used
for backports
* Avoid duplicates ...
Loic Dachary
08:09 AM Revision b7524c0a (ceph): release-notes: draft v0.94.6 release notes
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
06:55 AM Backport #14803 (Resolved): hammer: osd: smaller object_info_t xattrs
https://github.com/ceph/ceph/pull/6544 Loïc Dachary
06:47 AM Backport #14802 (Resolved): hammer: build/ops: pass tcmalloc env through to ceph-os
https://github.com/ceph/ceph/pull/7365 Loïc Dachary
06:45 AM Backport #14801 (Resolved): hammer: build/ops: deb: strip tracepoint libraries from Wheezy/Precis...
https://github.com/ceph/ceph/pull/7316 Loïc Dachary
06:38 AM Revision 64c469ab (ceph): Merge pull request #789 from ceph/wip-14146
tasks/cephfs: check status asok output while in reconnect Greg Farnum
06:37 AM Revision 88eb2e73 (ceph): Merge pull request #787 from ceph/wip-13903
Wip 13903 tests Greg Farnum
06:15 AM Bug #12442: how to use the command “ceph ping mon.ID”?
I had the same issue and I used this solution to fix it:
1. In [global] section
remove the line : mon_host
2. Cr...
Phat Le Ton
05:55 AM rbd Bug #10773: dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
http://pulpito.ceph.com/loic-2016-02-16_22:05:19-rbd-hammer-backports---basic-multi/12638/... Loïc Dachary
05:54 AM Revision 7ee99689 (ceph): ceph-disk: make some arguments as required if necessary
There is no default value for these arguments, and they are
necessary. Then make them as required.
Fixes 9666
Signe...
Yang Dongsheng
05:37 AM Bug #14244: "SELinux denials found" in rados-jewel-distro-basic-smithi
http://pulpito.ceph.com/loic-2016-02-16_22:00:52-rados-hammer-backports---basic-multi/12412 Loïc Dachary
05:24 AM CephFS Bug #14800: [ceph-fuse] Fh ref might leak at umounting
https://github.com/ceph/ceph/pull/7686 Zhi Zhang
05:22 AM CephFS Bug #14800 (Resolved): [ceph-fuse] Fh ref might leak at umounting
Recently we meet ceph-fuse hanging issue and have to kill ceph-fuse process to continue. This issue is caused by forc... Zhi Zhang
05:17 AM Backport #14799: hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread-mt.so.1.53
http://pulpito.ceph.com/loic-2016-02-16_22:00:52-rados-hammer-backports---basic-multi/12373/
http://qa-proxy.ceph.co...
Loïc Dachary
05:12 AM Backport #14799 (Resolved): hammer: CentOS 7 tcmalloc::ThreadCache valgrind error libboost_thread...
https://github.com/ceph/ceph/pull/10750
libboost_thread-mt.so.1.53 uses tcmalloc::ThreadCache which triggers a val...
Loïc Dachary
04:55 AM Bug #14461 (Need More Info): test hung "joining thrashosds" in hammer tests
http://pulpito.ceph.com/loic-2016-02-16_22:00:52-rados-hammer-backports---basic-multi/12298/... Loïc Dachary
04:49 AM Bug #14015 (New): osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.history.last_epoc...
Loïc Dachary
04:48 AM Bug #14015 (Pending Backport): osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.hist...
Loïc Dachary
04:47 AM Bug #14015 (New): osd/PG.cc: 288: FAILED assert(info.last_epoch_started >= info.history.last_epoc...
@david: could this be a regression introduced by this fix ?
http://pulpito.ceph.com/loic-2016-02-16_22:00:52-rados...
Loïc Dachary
03:40 AM Revision 06806f70 (ceph): [ceph-fuse] Fh ref might leak at umounting
Signed-off-by: Zhi Zhang <zhangz.david@outlook.com> Zhi Zhang
03:22 AM CephFS Bug #14798: free fds being exhausted eventually because freed fds are never put back
https://github.com/ceph/ceph/pull/7685 Zhi Zhang
03:18 AM CephFS Bug #14798: free fds being exhausted eventually because freed fds are never put back
The open and create operation in libcephfs will get a free fd from the free_fd_set. This free fd will be erased from ... Zhi Zhang
03:12 AM CephFS Bug #14798 (Resolved): free fds being exhausted eventually because freed fds are never put back
Zhi Zhang
03:07 AM Revision ee077706 (ceph): [cephfs] fix free fds being exhausted eventually because freed fds are ...
Signed-off-by: Zhi Zhang <zhangz.david@outlook.com> Zhi Zhang
02:36 AM Revision 2b15e2b3 (ceph): create and check omap fsid
1. write osd_uuid to omap dir when doing filestore mkfs
2. check if omap fsid matches osd fsid when doing filestore m...
Chendi.Xue
02:24 AM Revision 0441e7d5 (ceph): Added option to deploy omap to a separate device(path)
In the HDD as OSD, SSD as journal test, we saw a great
throughput improvement if moving omap to a SSD device at
randw...
Chendi Xue
02:15 AM Bug #14796: test/osd/osd-markdown.sh has too-aggressive timing restrictions
test/osd/osd-markdown.sh's tests try to set the OSD markdown count and period to 5 and 40s, and then mark the OSD dow... Dan Mick
01:24 AM Bug #14796 (Resolved): test/osd/osd-markdown.sh has too-aggressive timing restrictions
Dan Mick
01:16 AM Revision 331e90f4 (ceph): Use make_shared while creating shared_ptr
make_shared() will get rid of one extra 'new' call during shared_ptr
creation.It is also 20-30% faster than creating ...
Somnath Roy
01:13 AM rgw Bug #14795 (New): test_librgw: build fails on i386
From http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-i386-basic/log.cgi?log=c8b9a79bbd48e0339a6a5146d... Josh Durgin
12:56 AM Bug #14794 (Resolved): Objecter: valgrind unclean
http://pulpito.ceph.com/gregf-2016-02-15_18:08:49-fs-greg-fs-testing-215-1---basic-smithi/10830/
Looks like our un...
Greg Farnum
12:45 AM Revision 037852ea (ceph): Merge pull request #7684 from ceph/wip-pybind-install
pybind: use correct subdir for rados install-exec rule
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
12:41 AM rgw Bug #14105: adminops subuser specify S3 keys
The behavior of the radosgw-admin CLI does allow this see this example (hammer). The issue is that the Admin REST AP... Derek Yarnell
12:27 AM Revision 0e6f6d89 (ceph): Fixes #14652
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> Yuri Weinstein

02/17/2016

11:49 PM Revision 493a073e (ceph): Merge branch 'wip-sharded-scan' of git://github.com/jcsp/ceph into greg...
Conflicts:
src/osdc/Objecter.cc
Greg Farnum
11:45 PM Bug #14606: rest.py fails
Run: http://pulpito.ceph.com/teuthology-2016-02-16_22:00:02-rados-jewel-distro-basic-smithi/
Jobs: ['12123', '12272']
Yuri Weinstein
11:44 PM Revision c8b9a79b (ceph): pybind: use correct subdir for rados install-exec rule
This fixes package builds and 'make install'
Signed-off-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
11:09 PM CephFS Bug #14684: test_scrub_checks fails
And again: http://pulpito.ceph.com/gregf-2016-02-15_18:08:49-fs-greg-fs-testing-215-1---basic-smithi/10771/
It doe...
Greg Farnum
10:11 PM Bug #13835: on_flushed: object 1/f9b8d3f7/burnupi0951139-337/head obc still alive
Looks similar in run:
http://pulpito.ceph.com/teuthology-2016-02-16_09:00:01-rados-hammer-distro-basic-vps/
Job: 11...
Yuri Weinstein
09:53 PM Bug #14793 (Rejected): "Error ENXIO: problem getting command descriptions from osd.0" in rados-in...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-17_02:00:01-rados-infernalis-distro-basic-openstack/
...
Yuri Weinstein
09:46 PM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-17_02:00:01-rados-infernalis-distro-basic-openstack/
...
Yuri Weinstein
09:08 PM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
The log setting change worked. No more mon segfaults. I have a new osd log for you too, but I'm unable to upload it. ... Steve Taylor
06:33 PM Bug #14792 (Rejected): s3tests failed in smoke-master-distro-basic-openstack
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-17_05:00:01-smoke-master-distro-basic-openstack/
Jobs...
Yuri Weinstein
06:30 PM Bug #14791 (Can't reproduce): "boost: mutex lock failed in pthread_mutex_lock: Invalid argument" ...
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-17_05:00:01-smoke-master-distro-basic-openstack/
Job:...
Yuri Weinstein
06:23 PM rgw Feature #13478 (Resolved): rgw: new admin command to control setting/clearing master zone and zon...
Yehuda Sadeh
06:23 PM rgw Feature #13479: rgw: configuration backward compatibility
Yehuda Sadeh
06:23 PM rgw Feature #11944 (Resolved): rgw: RESTful api for period operations
Yehuda Sadeh
06:21 PM rgw Feature #13102 (Resolved): rgw: multisite: copy-if-newer option for data copy
Yehuda Sadeh
06:21 PM rgw Feature #13101 (Resolved): rgw: multisite: data sync: incremental
Yehuda Sadeh
06:21 PM rgw Feature #13100 (Resolved): rgw: multisite: data sync: full data sync
Yehuda Sadeh
06:21 PM rgw Feature #13099 (Resolved): rgw: multisite: data sync - init
Yehuda Sadeh
06:21 PM rgw Feature #12905 (Resolved): rgw: multisite: per-shard incremental sync stage
Yehuda Sadeh
06:21 PM rgw Feature #12608 (Resolved): rgw: multisite: per-shard full sync stage
Yehuda Sadeh
06:21 PM rgw Feature #12606 (Resolved): rgw: multisite: keep metadata zone sync state
Yehuda Sadeh
06:21 PM rgw Feature #11945 (Resolved): rgw: radosgw-admin commands to control period - including commit
Yehuda Sadeh
06:21 PM rgw Feature #11972 (Resolved): rgw: implement zongroup create admin command
Yehuda Sadeh
06:21 PM rgw Feature #11934 (Resolved): rgw: metadata log sync work
Yehuda Sadeh
06:19 PM rgw Feature #11412 (Resolved): rgw: tie ganesha fsal to librgw object interface
Yehuda Sadeh
06:19 PM rgw Feature #11410 (Resolved): rgw: implement object api to use with ganesha fsal (librgw)
Yehuda Sadeh
06:19 PM rgw Feature #11411 (Resolved): rgw: tie ganesha fsal to librgw bucket interface
Yehuda Sadeh
06:19 PM rgw Feature #11409 (Resolved): rgw: implement bucket api to use with ganesha fsal (librgw)
Yehuda Sadeh
06:18 PM rgw Feature #11939 (Resolved): rgw: dynamic reconfiguration
Yehuda Sadeh
06:17 PM rgw Feature #4097 (Resolved): rgw: s3 static website
Yehuda Sadeh
06:14 PM rgw Feature #940 (Closed): obsync: use COPY optimization
Yehuda Sadeh
06:05 PM Revision 196d324b (ceph): Merge pull request #7621 from sileht/sileht/rados-cython
python binding of librados with cython
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
05:43 PM Backport #14077: hammer: scrub bogus results when missing a clone
I'm attempting this tricky backport so it can get into a Hammer point release. David Zafman
05:30 PM Revision aa87becb (ceph): rgw: remove unnecessary overloads in RGWHTTPArgs.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
05:24 PM rgw Bug #14652 (New): "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-op...
I was wrong above the fix above, it did not apply to rgw test, so reopening. Yuri Weinstein
12:44 AM rgw Bug #14652 (Resolved): "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-bas...
Yuri Weinstein
04:52 PM Revision cb928f5f (ceph): mds: don't crash because of bad ms-type in ceph.conf (or missing enable...
missing nullity check will cause the process to crash in the following cases:
a. bad ms-type is configured in ceph.c...
Avner BenHanoch
04:48 PM Revision b9a4ad86 (ceph): mon: don't crash because of bad ms-type in ceph.conf (or missing enable...
missing nullity check will cause the process to crash in the following cases:
a. bad ms-type is configured in ceph.c...
Avner BenHanoch
04:42 PM Revision 027edc3a (ceph): osd: don't crash because of bad ms-type in ceph.conf (or missing enable...
missing nullity check will cause the process to crash in the following cases:
a. bad ms-type is configured in ceph.c...
Avner BenHanoch
04:37 PM rbd Bug #14789 (Resolved): Truncate of non-existent object results in object map flagged as exists
This won't affect the proper read of data but it will incorrectly affect the disk usage calculations (and it introduc... Jason Dillaman
04:36 PM Revision c58fc206 (ceph): os/kstore: default Onode::true to false
This patch is mostly a wash, except that _rename now avoids doing the
_do_remove() work in the case where the object ...
Jianjian Huo
04:24 PM Revision 180a12a0 (ceph): os/kstore: fix onode_t attr leak in _setattrs()
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
04:17 PM Revision 27b991a5 (ceph): sstring.hh: return type from str_len(...) need not be const
Removes a compile warning.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:08 PM Revision eeaf8b8e (ceph): os/kstore: remove unused OnodeMap::remove
We install negative entries instead.
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com>
Jianjian Huo
04:05 PM Revision 206c3e8a (ceph): os/kstore: use std::mutex et al
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
03:46 PM Revision ebfc6bfd (ceph): rgw: move signal.h dependency from rgw_front.h
Missed in refactoring of rgw_main.cc.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
03:36 PM rgw Bug #10606: civetweb keeps receiving data after client canceled download
This is now fixed in 9.2 Infernalis, thank you, please close this bug. Mustafa Muhammad
03:28 PM Bug #14788: librados (C++) linker error (undefined reference)
so it sounds like a regression after introducing the @buffer::list::const_iterator@. Kefu Chai
03:03 PM Bug #14788 (Resolved): librados (C++) linker error (undefined reference)

When compiling a patched librados C++ example (or other C++ programs-- see included patchfile), pointing to the hea...
Jesse Williamson
03:20 PM devops Bug #14785 (In Progress): rpm: %_with_ocf handling in configure broken in OBS
*jewel PR*: https://github.com/ceph/ceph/pull/7676 Nathan Cutler
09:42 AM devops Bug #14785 (Rejected): rpm: %_with_ocf handling in configure broken in OBS
In the OBS, the ocf bcond is enabled by setting _with_ocf to any value (for
example, "1"). When %_with_ocf is used, ...
Nathan Cutler
03:17 PM Revision 58fe65f2 (ceph): os/kstore: add transaction dump msg in _txc_add_transaction
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
03:12 PM Revision bce0bc0b (ceph): os/kstore: wr lock collection in _txc_add_transaction
Do this in the caller to simplify the callees slightly.
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com>
Jianjian Huo
02:33 PM rgw Bug #14787 (Won't Fix): Bug using bootstrap deployment mechasim with radosgw
hi,
we are using ceph on Debian jessy and are running into issues when using the bootstrap mechanism.
When we gen...
Rainer Goldmann
02:16 PM Revision 67f95c8f (ceph): Update the documentation
Signed-off-by: Mehdi Abaakouk <sileht@redhat.com> Mehdi Abaakouk
01:34 PM Revision 362abf7e (ceph): tasks/scrub_test: refactor this test
prepare for the scrub API tests
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
11:32 AM Revision c4162b59 (ceph): librbdpy: Use new rados lib
Signed-off-by: Mehdi Abaakouk <sileht@redhat.com> Mehdi Abaakouk
11:32 AM Revision 9997b32d (ceph): Cython Rados module
Notable changes:
* run_in_thread have disapeared
* timeout argument of some methods are ignored
* rados_create_write...
Mehdi Abaakouk
11:32 AM Revision 3c405240 (ceph): Remove old rados pybinding
Signed-off-by: Mehdi Abaakouk <sileht@redhat.com> Mehdi Abaakouk
11:32 AM Revision 82869f00 (ceph): Fix rpm/deb packaging
Signed-off-by: Mehdi Abaakouk <sileht@redhat.com> Mehdi Abaakouk
11:32 AM Revision 7216b06b (ceph): ceph.in: Use new python rados module
This implements run_in_thread inside the ceph command itself.
And fixes the ceph command bootstrap when it run insid...
Mehdi Abaakouk
10:35 AM rgw Feature #11858: Support Amazon v4 Signatures
Kindly let me know if there is an update on the same. It seems I'm also stuck with the same issue. If there is a work... Raunak Kumar
10:34 AM rgw Bug #10195: s3 java jdk conn.getobject(...) (get s3 object) method fails with latest version of a...
Hi Team
I am using a Go SDK in my Go Client to access the Radosgw but am getting errors and it is due to authenticat...
Raunak Kumar
10:28 AM Revision 4c8f320a (ceph): OSD: fix fusestore hanging during stop/quit
If both 'stop' and 'osd_objectstore_fuse' are set to true, then the
fuse_store will be stopped first and then restart...
xie xingguo
10:26 AM Bug #14786 (Resolved): OSD: potentially leave fuse_store hung if we fail to init osd
Check int OSD::enable_disable_fuse(bool stop) for detailed information. xie xingguo
09:21 AM Revision 22c6d354 (ceph): Merge pull request #7603 from roidayan/xio_fixes
Xio fixes
Reviewed-by: Matt Benjamin <mbenjamin@redhat.com>
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Kefu Chai
07:18 AM Bug #14784 (Can't reproduce): Ceph deploymentinto prefix breaks some operations
When installing ceph from git sources into non-default prefix:
./install-deps.sh
./autogen.sh
./configure --enab...
Dmitry Buzz
06:18 AM Backport #14782 (In Progress): infernalis: test_bit_vector.cc uses magic numbers against #defines...
Loïc Dachary
06:07 AM Backport #14782 (Rejected): infernalis: test_bit_vector.cc uses magic numbers against #defines th...
https://github.com/ceph/ceph/pull/7673 Loïc Dachary
06:17 AM Backport #14783 (In Progress): hammer: test_bit_vector.cc uses magic numbers against #defines tha...
Loïc Dachary
06:08 AM Backport #14783 (Resolved): hammer: test_bit_vector.cc uses magic numbers against #defines that vary
https://github.com/ceph/ceph/pull/7672 Loïc Dachary
06:16 AM Revision 31a2fc47 (ceph): common/bit_vector: use hard-coded value for block size
The CEPH_PAGE_SIZE is not actually a constant. On aarch64 platforms
the page size is 64K instead of the assumed 4K. ...
Jason Dillaman
06:07 AM Stable releases Tasks #14692: hammer v0.94.7
h3. upgrade... Loïc Dachary
06:05 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rbd... Loïc Dachary
06:01 AM Stable releases Tasks #14692: hammer v0.94.7
h3. rados... Loïc Dachary
05:36 AM Revision c03ab962 (ceph): os/kstore: use std::atomic
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
05:20 AM Revision d457ff00 (ceph): os/kstore: load OnodeRef in _txc_add_transaction
Get OnodeRef ready in the caller, and keep it in a vector so that it
can be reused for any subsequent operations in t...
Jianjian Huo
05:17 AM Cleanup #14202 (In Progress): the method 'Message::decode_message' is too long
https://github.com/ceph/ceph/pull/7669 Kefu Chai
05:08 AM Backport #14583 (In Progress): hammer: pid file that was deleted after ceph restart leads to osd ...
Kefu Chai
05:06 AM Backport #14583: hammer: pid file that was deleted after ceph restart leads to osd process lose c...
https://github.com/ceph/ceph/pull/7671 Kefu Chai
04:51 AM Backport #14583 (Fix Under Review): hammer: pid file that was deleted after ceph restart leads to...
Kefu Chai
03:55 AM Backport #14583 (New): hammer: pid file that was deleted after ceph restart leads to osd process ...
Kefu Chai
02:55 AM rgw Bug #14764: RGW: swift API 'swift stat' double counts objects
Yeah - looks like the same issue! (Ahem - I did search 1st but clearly missed 13140, apologies) Mark Kirkwood
02:45 AM rgw Bug #14764: RGW: swift API 'swift stat' double counts objects
Probably a known issue, you may want to take a look at http://tracker.ceph.com/issues/13140
Sandy Xu
02:54 AM rbd Cleanup #14781 (New): Reuse ImageCtx::op_work_queue for TaskFinisher's finisher thread
Convert any remaining tasks to be fully async so that the extra thread can be removed from librbd. Jason Dillaman
01:19 AM rbd Bug #14780 (Fix Under Review): librbd: TaskFinisher lifetime no longer matches ImageWatcher
https://github.com/ceph/ceph/pull/7667 Josh Durgin
01:13 AM rbd Bug #14780 (Resolved): librbd: TaskFinisher lifetime no longer matches ImageWatcher
Since notify handling was made async from the librados threads in commit:d898995b0e3ea301b1325f68a0532d57afa3c816 tes... Josh Durgin
01:12 AM Revision a2c90b51 (ceph): Revert "librbd: use task finisher per CephContext"
Since notify handling was made async from the librados threads in
d898995b0e3ea301b1325f68a0532d57afa3c816 tests can ...
Josh Durgin

02/16/2016

11:58 PM Bug #14521: Failure on restart after repairing corrupted PG
The problem is that corruption is silent, scrub and repair doesn't report any errors. After a year of run all replica... Evgeniy Firsov
11:13 PM rgw Bug #14349 (Need More Info): radosgw-admin --log-to-stderr --format json -n client.1 user info -...
Yuri Weinstein
10:54 PM Revision cd357b6a (ceph): rgw: enable access to system arguments of RGWHTTPArgs.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:54 PM Revision 52b7f1d6 (ceph): rgw: support system requests over Swift API.
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> Radoslaw Zarzynski
10:50 PM rgw Bug #14652: "Segmentation fault" (radosgw-admin()) in upgrade:hammer-hammer-distro-basic-openstack
Testing http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-16_22:50:12-upgrade:hammer-hammer-distro-basic-open... Yuri Weinstein
10:39 PM Bug #14244: "SELinux denials found" in rados-jewel-distro-basic-smithi
Run: http://pulpito.ceph.com/teuthology-2016-02-15_22:00:05-rados-jewel-distro-basic-smithi/
Job: ['11051']
Yuri Weinstein
10:26 PM Bug #14777 (Resolved): "RadosModel.h: 1223: FAILED assert(old_value.header == header)" in rados-j...
Run: http://pulpito.ceph.com/teuthology-2016-02-15_22:00:05-rados-jewel-distro-basic-smithi/
Job: 11194
Logs: http:...
Yuri Weinstein
09:54 PM CephFS Bug #14714: three jobs in samba suite failing for hammer v0.94.6 QE validation
same tests on v0.94.4 failed same way !?
Although they did passed during QE validation http://tracker.ceph.com/issue...
Yuri Weinstein
07:40 PM Revision 4b9413f0 (ceph): os/kstore: drop unused TransContext mutex and cond
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
07:16 PM Revision 926eb776 (ceph): os/kstore: fix valgrind warning on fsid read
Signed-off-by: Jianjian Huo <samuel.huo@gmail.com> Jianjian Huo
06:43 PM Revision 1c0406ae (ceph): pybind: Ensure correct python flags are passed
Cython should use the cflags and ldflags provided by
python-config; add checks, population and use of:
PYTHON_CFLA...
James Page
05:41 PM Revision d3ac713d (ceph): Move pybind rbd module into it own directory
To allow to create a autonomous rados module with cython.
We move the current librbdpy to the rbd sub directory.
Sig...
Mehdi Abaakouk
05:31 PM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Tried on diff machines all failed in similar fashion:
http://pulpito.ceph.com/teuthology-2016-02-15_16:52:37-fs-hamm...
Yuri Weinstein
04:59 PM Revision 1badcdd4 (ceph): os/bluestore: change bluestore_backend to bluestore_kvbackend.
In fact, bluestore_backend is kvbackend. So change it to
bluestore_kvbackend looks better.
Signed-off-by: Jianpeng M...
Jianpeng Ma
04:38 PM Bug #14776 (Can't reproduce): "FAILED assert(0 == "old msgs despite reconnect_seq feature")" in r...
Run: http://pulpito.ceph.com/teuthology-2016-02-15_09:00:01-rados-hammer-distro-basic-vps/
Job: 9742
Logs: http://q...
Yuri Weinstein
03:45 PM Revision 7b57f295 (ceph): os/bluestore: If bluestore_bluefs == false, only rocksdb_separate_wal_d...
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
03:33 PM Revision dbfee624 (ceph): os/bluestore: Only enable bluestore_bluefs, symlink or create db or db....
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> Jianpeng Ma
02:58 PM Bug #14766: OSD reporting ENOTEMPTY and crashing
It would help if you could post the contents of one of the pg directories where this happened. Samuel Just
02:57 PM Bug #14711: OSD crashes with Suicide timeout due to timeout on FileStore::op_tp thread
This usually means the fs hung during a call. Please restart the osd with
debug osd = 20
debug filestore = 20
d...
Samuel Just
02:04 PM Revision 64c1d543 (ceph): Merge pull request #7520 from renhwsky/renhw-wip-mon-monitor
mon/monitor: some clean up
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
01:17 PM Revision e6f39680 (ceph): msg: add thread safety for "random" Messenger + fix wrong usage of rand...
1. srand() and rand() functions are not thread safe => for extra robustness: use rand_r with a thread_local variable
...
Avner BenHanoch
01:00 PM Bug #14710 (Duplicate): Bad output from 'ceph df' causes problems for cinder
dup with #13930 Kefu Chai
12:45 PM Bug #14710: Bad output from 'ceph df' causes problems for cinder
reproducible in hammer, but not in master. Kefu Chai
11:16 AM devops Backport #14774 (In Progress): infernalis: Fix message on attempt to use tell in interactive mode
Nathan Cutler
10:47 AM devops Backport #14774 (Rejected): infernalis: Fix message on attempt to use tell in interactive mode
https://github.com/ceph/ceph/pull/7660 Nathan Cutler
10:47 AM devops Backport #14769: hammer: Fix message on attempt to use tell in interactive mode
h3. Original description
This fix originally went in without a corresponding tracker issue. It is only 1 of the c...
Nathan Cutler
10:44 AM devops Bug #14773 (Pending Backport): Fix message on attempt to use tell in interactive mode
Nathan Cutler
10:44 AM devops Bug #14773 (Resolved): Fix message on attempt to use tell in interactive mode
This is the broken behavior:... Nathan Cutler
04:44 AM CephFS Bug #14754 (Duplicate): test_barrier (tasks.cephfs.test_full.TestClusterFull) fails on osdmap epo...
I hope this was #14750 manifesting differently? Greg Farnum
04:43 AM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
#14750 Greg Farnum
04:42 AM CephFS Bug #14698 (Duplicate): Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
Greg Farnum
04:43 AM CephFS Bug #14258 (Duplicate): qa: failed test_full_fsync
#14750 Greg Farnum
04:40 AM Bug #14750 (Resolved): Objecter: do not mark OSD ops as laggy based on osd_timeout value
Greg Farnum
04:39 AM Revision fd4d97c0 (ceph): Merge pull request #7629 from ceph/wip-14750-op-timeouts
Objecter: detect laggy ops with objecter_timeout, not osd_timeout
Reviewed-by: Adam C. Emerson <aemerson@redhat.com>
Greg Farnum
04:36 AM Revision 02840904 (ceph): Merge pull request #7655 from gregsfortytwo/wip-metarequest-lock
client: removed unused Mutex from MetaRequest
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Greg Farnum
04:35 AM CephFS Bug #14697 (Resolved): mds: assert in SafeTimer while suiciding
Greg Farnum
04:35 AM Revision 42afb5b5 (ceph): Merge pull request #7616 from gregsfortytwo/wip-timer-14697
mds: don't double-shutdown the timer when suiciding
Reviewed-by: John Spray <john.spray@redhat.com>
Greg Farnum
04:34 AM Revision da834412 (ceph): Merge pull request #7490 from x11562/mds_mdstype_ref
mds: function parameter 'df' should be passed by reference
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
03:49 AM CephFS Bug #14684: test_scrub_checks fails
gregf-2016-02-15_13:33:12-fs-greg-fs-testing-215-sure---basic-smithi/10011/
original; and here we have it on maste...
Greg Farnum
03:24 AM Linux kernel client Bug #14736: Kernel cephfs bind-mounts break if parent dir modified elsewhere
Nick Mailer wrote:
> Greg, we're talking about --bind mounting, not mounting a whole new filesystem.
>
> So, moun...
Zheng Yan
01:55 AM Linux kernel client Bug #14736: Kernel cephfs bind-mounts break if parent dir modified elsewhere
Greg Farnum wrote:
> Just to be clear, you mean don't use a cephfs directory as the location for mounting another FS...
Zheng Yan
02:17 AM rgw Bug #14772 (Can't reproduce): test_abort_multipart_upload_not_found
2016-02-15T16:45:02.881 INFO:teuthology.orchestra.run.plana14.stderr:s3tests.functional.test_s3.test_multipart_upload... Zezhu Zhang
01:25 AM Bug #14747 (Pending Backport): test_bit_vector.cc uses magic numbers against #defines that vary
Dan Mick
01:18 AM Bug #14747 (Resolved): test_bit_vector.cc uses magic numbers against #defines that vary
Dan Mick
01:24 AM Bug #14771 (Rejected): test_bit_vector.cc uses magic numbers against #defines that vary
understood process wrong Dan Mick
01:18 AM Bug #14771 (Rejected): test_bit_vector.cc uses magic numbers against #defines that vary
test_bit_vector's partial_decode_encode test allocates a 9161-element bit vector, and then tests with ranges based on... Dan Mick
01:07 AM Revision 9d2c7869 (ceph): Merge pull request #7610 from dillaman/wip-bit-vector
common/bit_vector: use hard-coded value for block size
Reviewed-by: Dan Mick <dmick@redhat.com>
Dan Mick

02/15/2016

11:25 PM Revision 9d3e6dcb (ceph): Merge pull request #7653 from dillaman/wip-librbd-race-conditions
librbd: several race conditions discovered under single CPU environment
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
11:16 PM Revision 1b6ec189 (ceph): rgw: cleanup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
11:07 PM Revision 3c28f198 (ceph): rgw: don't try to parse some forwarded requests
Not every forwarded requests are expected to get a json response,
don't pass the parser when not needed.
Signed-off-...
Yehuda Sadeh
10:50 PM Revision 842140b3 (ceph): rgw: adjust data sync async notification locking
This is a workaround to avoid issues related to the way lockdep works
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:48 PM Revision fe14a267 (ceph): ceph.spec.in: declare /usr/share/ceph properly
Signed-off-by: Nathan Cutler <ncutler@suse.com> Nathan Cutler
10:30 PM devops Bug #14757: ceph-rpm (el7,v10.0.3): missing dependency: ceph-detect-init requires python-setuptools
One way to deal with this would be to package ceph-detect-init separately. Nathan Cutler
09:12 PM Revision bdb035ce (ceph): Merge pull request #7408 from ceph/wip-14549
rgw: don't use s->bucket for metadata api path entry
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
09:04 PM Revision 3352b144 (ceph): ceph.in: Notify user that 'tell' can't be used in interactive mode
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit a341d977d42a3010267b64e15cebae3085507297)...
David Zafman
08:57 PM Revision 76e42f09 (ceph): Merge pull request #7633 from zaitcev/cleanup-various-1
rgw: cleanups to comments and messages
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
08:32 PM devops Backport #14769 (Resolved): hammer: Fix message on attempt to use tell in interactive mode
https://github.com/ceph/ceph/pull/7656
David Zafman
08:03 PM Bug #14438 (Need More Info): "FAILED assert(pg->info.history.same_interval_since == p.same_interv...
David Zafman
05:36 PM Bug #14438: "FAILED assert(pg->info.history.same_interval_since == p.same_interval_since)" in upg...
db3dc4d3e2a74cfd366cd2ef4d0c9c4581269113 was merged to jewel branch to get further diagnostics if this problem recurs. David Zafman
07:09 PM Revision edefcafb (ceph): vstart.sh: clarify usage on single osd/mds/mon.
vstart.sh expects the literal string "osd"/"mds"/"mon". To me, it was confusing
as I interpreted the usage hint as an...
Patrick Donnelly
07:06 PM Revision 912fe8e2 (ceph): vstart.sh: silence a msg where btrfs is not found.
The error was:
./vstart.sh: line 603: btrfs: command not found
Signed-off-by: Patrick Donnelly <batrick@batbytes.com>
Patrick Donnelly
06:54 PM Revision a6cc8ea5 (ceph): rpm: drop systemd_libexec_dir template variable
General cleanup. Actual use of the template variable was discontinued in
7c9fdf44f2c18659a0bcc03f7b98dafdf9f54448.
S...
Nathan Cutler
06:52 PM Revision 3c76c570 (ceph): cephfs/test_full: add some gratuitous debugging
Signed-off-by: Greg Farnum <gfarnum@redhat.com> Greg Farnum
06:52 PM Revision e54ad3ba (ceph): Merge remote-tracking branch 'origin/wip-14365' into greg-fs-testing
https://github.com/ceph/ceph-qa-suite/pull/805 Greg Farnum
06:44 PM Revision 5c09a3e4 (ceph): rpm: drop user_rgw and group_rgw template variables
These were originally used to template RGW tmpfiles.d, which was eliminated
by 8e13d89f0f136f5be8ab869190062abfcca0e2...
Nathan Cutler
06:41 PM devops Bug #14687 (In Progress): RPM: no /usr/libexec directory on SUSE
Nathan Cutler
06:38 PM devops Bug #14687: RPM: no /usr/libexec directory on SUSE
Changing issue title to reflect narrower scope. Nathan Cutler
06:37 PM devops Bug #14687: RPM: no /usr/libexec directory on SUSE
It seems that the only path that is actually causing trouble now (at least on SUSE) is /usr/libexec. Nathan Cutler
06:36 PM devops Cleanup #14705 (Closed): Reinstate ceph-osd@.service.in
Agreed to put the ceph-osd-prestart.sh script in /usr/lib instead of reinstating the autotools template. Nathan Cutler
05:36 PM Revision 84e9f3f1 (ceph): librados_test_stub: watch_flush should block until notifies complete
It shouldn't block until all the acks are received as that is not
how librados handles the method.
Signed-off-by: Ja...
Jason Dillaman
05:35 PM Revision f5dfebc0 (ceph): librbd: potential deadlock during AIO image re-open
The AIO image open might complete under the librados AIO callback.
Attempting to close the old image handle under tha...
Jason Dillaman
05:35 PM Revision 7ae774b8 (ceph): librbd: potential race on image close
If multiple states are pending, it's possible for an image to
be closed while the state lock is unlocked during the c...
Jason Dillaman
05:35 PM Revision d898995b (ceph): librbd: lock notifications should be executed outside librados thread
Otherwise it's possible that the notification will be blocked if
the librados AIO thread isn't available to invoke th...
Jason Dillaman
05:33 PM Revision 8756e808 (ceph): librados_test_stub: ensure AIO callback is also flushed
There are sporadic librbd unit test failures due to the
mock being destroyed while an active librados_test_stub
AIO c...
Jason Dillaman
03:08 PM Linux kernel client Bug #14736: Kernel cephfs bind-mounts break if parent dir modified elsewhere
Greg, we're talking about --bind mounting, not mounting a whole new filesystem.
So, mount --bind /ceph/some/direct...
Nick Mailer
03:03 PM Linux kernel client Bug #14736: Kernel cephfs bind-mounts break if parent dir modified elsewhere
Just to be clear, you mean don't use a cephfs directory as the location for mounting another FS, right? And it's perf... Greg Farnum
08:41 AM Linux kernel client Bug #14736: Kernel cephfs bind-mounts break if parent dir modified elsewhere
when creating /data/target/file_in_parent on server 2, MDS revokes directory (/data/target) inode's Fs capability fro... Zheng Yan
02:42 PM Revision 98fba627 (ceph): Merge branch 'wip-commit_position-tests' of git://github.com/trociny/ceph
Reviewed-by: Jason Dillaman <dillaman@redhat.com> Jason Dillaman
02:38 PM Revision a418182e (ceph): tests: librbd: commit position updated after journal replay
Signed-off-by: Mykola Golub <mgolub@mirantis.com> Mykola Golub
02:23 PM Bug #14766 (Resolved): OSD reporting ENOTEMPTY and crashing
mail thread "inconsistent PG -> unfound objects on an erasure coded system":http://www.spinics.net/lists/ceph-users/m... Jeffrey McDonald
01:59 PM Linux kernel client Feature #14198: rbd: renaming a pool does not update the pool names in /dev/rbd or /sys/bus/rbd
... and then to unmap, if you want to use the spec syntax, you have to specify the old pool name. Ilya Dryomov
01:50 PM Bug #14747 (Fix Under Review): test_bit_vector.cc uses magic numbers against #defines that vary
*PR*: https://github.com/ceph/ceph/pull/7610 Jason Dillaman
01:49 PM Revision ba2e6ce4 (ceph): common/bit_vector: use hard-coded value for block size
The CEPH_PAGE_SIZE is not actually a constant. On aarch64 platforms
the page size is 64K instead of the assumed 4K. ...
Jason Dillaman
01:45 PM Revision 37a3728d (ceph): Make variable count usefull
Basicly the variable count is used as the
total number of op_seq for journal replay.
But it is not added as the op tr...
tianqing
10:58 AM Revision 7469ef3c (ceph): FileJournal::_open: return the correct error code
.. and print a more helpful error message. Unlike most of IO routines
(open, creat, write*, read, close) io_setup doe...
Alexey Sheplyakov
10:38 AM Backport #14765 (In Progress): hammer: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
Loïc Dachary
10:05 AM Backport #14765: hammer: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
https://github.com/ceph/ceph/pull/7648 Kefu Chai
10:03 AM Backport #14765 (Resolved): hammer: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
https://github.com/ceph/ceph/pull/7648 Loïc Dachary
10:02 AM Revision 14b5feab (ceph): mon/LogMonitor: use the configured facility if log to syslog
Fixes: #13748
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 4d2ca37d3b8f067d0cf0f7cfea24964a...
Kefu Chai
09:58 AM Bug #13748 (Pending Backport): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
Loïc Dachary
09:28 AM Bug #13748 (Fix Under Review): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
https://github.com/ceph/ceph/pull/7648 Kefu Chai
09:23 AM Bug #13748 (In Progress): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
this issue was addressed by https://github.com/ceph/ceph/pull/5148 . should have backported it to hammer... Kefu Chai
07:35 AM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
the mon crash is also observed in e1b92081c9e4b21eb30cc873c239083a08fce12f
> that's that we see the mon segfault ...
Kefu Chai
09:46 AM Bug #13990: Hammer (0.94.3) OSD does not delete old OSD Maps in a timely fashion (maybe at all?)
> the assumption is that we're seeing that same issue. Every 0.94.5 deployment we've tested has exhibited that segfau... Kefu Chai
09:05 AM Revision a1e6dcdb (ceph): osd: rewrite digest only when the digest exists on auth obj
Signed-off-by: Zhiqiang Wang <wonzhq@hotmail.com> Zhiqiang Wang
07:19 AM Revision 9540769d (ceph): Merge pull request #7646 from dachary/wip-ceph-disk-flake8
ceph-disk: flake8 fixes
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
06:29 AM rgw Bug #14764: RGW: swift API 'swift stat' double counts objects
Sorry that example is utterly unreadable, trying again:
$ swift stat
Account: v1
...
Mark Kirkwood
06:27 AM rgw Bug #14764 (Duplicate): RGW: swift API 'swift stat' double counts objects
Performing an account 'stat' results in double the expected number of objects and bytes.
The replication level in ...
Mark Kirkwood
05:43 AM Revision d476ff65 (ceph): ceph-disk: flake8 fixes
Signed-off-by: Loic Dachary <loic@dachary.org> Loic Dachary
05:28 AM Stable releases Tasks #14692: hammer v0.94.7
... Loïc Dachary
05:01 AM Backport #14762 (In Progress): hammer: No longer able to host rbd images on cache-tier backed by ...
Loïc Dachary
05:00 AM Backport #14762 (Closed): hammer: No longer able to host rbd images on cache-tier backed by EC pool
https://github.com/ceph/ceph/pull/7622 Loïc Dachary
05:01 AM Revision 678e2bbe (ceph): rgw: cleanups to comments and messages
These are minor cleanups that do not affect the code in a
material way:
- Forgot to add --tenant to usage message
- M...
Pete Zaitcev
04:57 AM Bug #12903 (Pending Backport): No longer able to host rbd images on cache-tier backed by EC pool
Loïc Dachary
04:53 AM Backport #14760 (In Progress): hammer: OSD coredumps with leveldb compact on mount = true
Loïc Dachary
04:46 AM Backport #14760 (Resolved): hammer: OSD coredumps with leveldb compact on mount = true
https://github.com/ceph/ceph/pull/7645 Loïc Dachary
04:52 AM Revision 10d29dab (ceph): os/LevelDBStore:fix bug when compact_on_mount
Initialize the performance counter(l_rocksdb_compact)
before use it in compact().
Signed-off-by: Xiaoxi Chen <xiaoxi...
Xiaoxi Chen
04:46 AM CephFS Backport #14761 (Rejected): infernalis: ceph-fuse does not mount at boot on Debian Jessie
https://github.com/ceph/ceph/pull/7834 Loïc Dachary
02:53 AM Bug #13902 (Closed): OSD:project_pg_history may not return the latest same_interval_since.
xie xingguo

02/14/2016

08:22 PM CephFS Bug #14684: test_scrub_checks fails
http://pulpito.ceph.com/teuthology-2016-02-05_14:03:02-fs-jewel---basic-smithi/8806/
Same as the original case
Greg Farnum
07:54 PM CephFS Bug #14684: test_scrub_checks fails
http://pulpito.ceph.com/teuthology-2016-02-12_14:03:01-fs-jewel---basic-smithi/8245/... Greg Farnum
08:04 PM CephFS Bug #14759 (Closed): ovh: failed snaptest-git-ceph.sh test
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-02-06_18:04:02-fs-master---basic-openstack/17910/... Greg Farnum
07:51 PM CephFS Bug #14758 (Resolved): failed TestJournalRepair test on smithi
http://pulpito.ceph.com/teuthology-2016-02-12_14:03:01-fs-jewel---basic-smithi/8218/... Greg Farnum
06:38 PM devops Bug #14757: ceph-rpm (el7,v10.0.3): missing dependency: ceph-detect-init requires python-setuptools
influences other commands
ceph-disk activate will fail without "--mark-init ..."
systemd job ceph-disk@.service...
Anonymous
06:34 PM devops Bug #14757: ceph-rpm (el7,v10.0.3): missing dependency: ceph-detect-init requires python-setuptools
somehow related to http://tracker.ceph.com/issues/13057, which fixed it for debian ??? Anonymous
06:31 PM devops Bug #14757 (Rejected): ceph-rpm (el7,v10.0.3): missing dependency: ceph-detect-init requires pyth...
> ceph-detect-init
Traceback (most recent call last):
File "/usr/bin/ceph-detect-init", line 5, in <module>
...
Anonymous
12:26 PM Revision ce421725 (ceph): rgw: catch up aws4 with the new features
Fix pending conflicts after massive merging. It catches up with SLO, bucket
website, bulk deletes and payment request...
Javier M. Mellid

02/13/2016

02:57 PM devops Bug #14756 (In Progress): EC testing plugins are being versioned and installed even though they a...
*jewel PR*: https://github.com/ceph/ceph/pull/7637 Nathan Cutler
02:43 PM devops Bug #14756: EC testing plugins are being versioned and installed even though they are only used i...
Note that the OBS implements a "devel-file-in-non-devel-package" RPMLINT check that this is tripping. For details on ... Nathan Cutler
02:19 PM devops Bug #14756 (Resolved): EC testing plugins are being versioned and installed even though they are ...
The following shared libraries in src/erasure-code result in the following shared objects that need to be packaged (i... Nathan Cutler
02:56 PM devops Cleanup #14705 (In Progress): Reinstate ceph-osd@.service.in
*jewel PR*: https://github.com/ceph/ceph/pull/7636 Nathan Cutler
12:53 PM Revision 8a4f8e89 (ceph): rgw: escape aws4 query string
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:53 PM Revision 84bd2af1 (ceph): rgw: add x-amz-expires support
Provides the time period, in seconds, for which the generated presigned URL is
valid. For example, 86400 (24 hours). ...
Javier M. Mellid
12:53 PM Revision 16646c3b (ceph): rgw: add aws4 auth grace period
Protect against reuse of the signed portions of the request. In AWS, the signed
portions (using AWS Signatures) of re...
Javier M. Mellid
12:53 PM Revision cc8f31b8 (ceph): rgw: fix bug encoding percentage char in X-Amz-Credential
The X-Amz-Credential value in the URL shows the "/" character only for
readability. In practice, it should be encoded...
Javier M. Mellid
12:53 PM Revision e9917a66 (ceph): rgw: fix host field in canonical headers under qs
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:51 PM Revision b052b0d2 (ceph): rgw: implement missing handlers for aws4 signatures
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:49 PM Revision e183009b (ceph): rgw: raise error on not implemented AWS4 completions
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:49 PM Revision f851cbcd (ceph): rgw: implement RGWOp_Metadata_Put::get_type()
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:43 PM Revision e28072e3 (ceph): rgw: add AWS4 completion support for RGW_OP_PUT_OBJ
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:43 PM Revision 8e1048d1 (ceph): rgw: add AWS4 completion support for RGW_OP_PUT_ACLS
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:41 PM Revision e533917d (ceph): rgw: verify X-Amz-Date
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:41 PM Revision 55477546 (ceph): rgw: return -EINVAL on unknow authorization
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:41 PM Revision 537e5493 (ceph): Revert "rgw: avoid re-encoding already encoded query strings in AWS4 auth"
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:41 PM Revision f7f21984 (ceph): rgw: do not encode key/val when computing canonical qs
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com> Javier M. Mellid
12:39 PM Revision 52e601b3 (ceph): rgw: multiple fixes and adjustments following aws4 code review
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:35 PM devops Bug #14755 (Rejected): OBS needs ceph-rpmlintrc file
The openSUSE Build Service[1] implements RPMLINT checks, and failures in some of them cause the OBS to mark the build... Nathan Cutler
12:33 PM Revision 2de292ac (ceph): rgw: validate x-amz-sha256
Verify content's sha256 sum matches the expected value.
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igal...
Javier M. Mellid
12:33 PM Revision 4da85395 (ceph): rgw: achieve same error behaviour in S3 and RGW when processing signedh...
This patch gets the same error response in S3 and RGW when the error is related
to the signedheaders processing.
Fix...
Javier M. Mellid
12:31 PM Revision 3210cd8a (ceph): rgw: AWS4 auth support for positive content-length
Handle AWS4 auth on requests with positive content-length. It splits the
auth process along several steps to process ...
Javier M. Mellid
12:31 PM Revision b7772cac (ceph): rgw: initialize aws4_auth_complete
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
12:31 PM Revision c32e5eaa (ceph): rgw: verify Content-MD5 is a valid base64 value
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
12:31 PM Revision 79b6b4f1 (ceph): rgw: check if x-amz-date has a value
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
12:25 PM Revision 483ad815 (ceph): rgw: avoid re-encoding already encoded query strings in AWS4 auth
When computing V4 signature, we need to encode the query string. But it
could come already encoded, at least partiall...
Javier M. Mellid
12:25 PM Revision 466cb81c (ceph): rgw: UNSIGNED-PAYLOAD support in AWS4 auth
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
12:22 PM Revision 9a0de484 (ceph): rgw: AWS4 authentication minimal support
Amazon S3 supports Signature Version 4. This patch contains the minimal
implementation supporting AWS4 in RGW. It imp...
Javier M. Mellid
12:22 PM Revision cbfc4af6 (ceph): rgw: handle AWS4 auth case when query string exists
Crafts the canonical query string. URI-encode each parameter name and
value properly.
Fixes: #10333
Signed-off-by: ...
Javier M. Mellid
12:22 PM Revision a15abe46 (ceph): rgw: add proper AWSv4 and AWSv2 auth detection
Adds a new authorize function to identify/handle AWSv4 and AWSv2 auth
properly, handling common code, etc.
Fixes: #1...
Javier M. Mellid
12:22 PM Revision 49856eb7 (ceph): rgw: AWS4 auth support when using request params
Fixes: #10333
Signed-off-by: Javier M. Mellid <jmunhoz@igalia.com>
Javier M. Mellid
07:08 AM CephFS Bug #14714: three jobs in samba suite failing for hammer v0.94.6 QE validation
Hmm, we've got 3 failures in teuthology-2016-02-07_21:14:02-samba-infernalis---basic-openstack as well, but they're d... Greg Farnum
06:10 AM CephFS Bug #14754 (Duplicate): test_barrier (tasks.cephfs.test_full.TestClusterFull) fails on osdmap epo...
In an integration branch which might have messed it up, but this is a first appearance:
http://pulpito.ceph.com/greg...
Greg Farnum
03:55 AM Bug #14723 (Resolved): make check bot broken: execvp: /bin/sh: Argument list too long
Kefu Chai
12:06 AM Revision 1ce0c771 (ceph): client: removed unused Mutex from MetaRequest
Signed-off-by: Greg Farnum <gfarnum@redhat.com> Greg Farnum

02/12/2016

11:29 PM Bug #14753: lokdep: uses lock name as the lock identity
I don't think we want to change this by default. Locks that share the same name almost always have to follow the same... Greg Farnum
11:19 PM Bug #14753 (Rejected): lokdep: uses lock name as the lock identity
This is problematic if having multiple lock instances that share the same name. Yehuda Sadeh
10:51 PM Revision 5542c6e5 (ceph): Merge pull request #7634 from ceph/rgw-nfs-5
nfs for rgw (Matt Benjamin, Orit Wasserman)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
10:35 PM Revision 892c1448 (ceph): Objecter: detect laggy ops with objecter_timeout, not osd_timeout
Fixes: 14750
Signed-off-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum
10:16 PM Bug #14660: selinux denials during rbd test run
Boris,
you can ignore the unlabeled in the above logs for now, I will run this on non vm' system to check what pat...
Vasu Kulkarni
10:04 PM Revision a7d4e424 (ceph): rgw: Drop unused usage_exit from rgw_admin.cc
Signed-off-by: Pete Zaitcev <zaitcev@redhat.com> Pete Zaitcev
10:03 PM Revision 00d396e3 (ceph): rgw: don't use s->bucket for metadata api path entry
Fixes #14549
s->bucket is only initialized at the object store handler (post auth
callback). We don't want to initia...
Yehuda Sadeh
09:03 PM Revision 447c8061 (ceph): rgw: adjust interfaces following rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:03 PM Revision 865c76c3 (ceph): rgw: add drain_all() after collect() in sync crs
this fixes a segfault caused by parent stacks completing while there are
child stacks outstanding
Signed-off-by: Cas...
Casey Bodley
09:03 PM Revision 2d52ab31 (ceph): rgw: data sync env cleanup
pass RGWDataSyncEnv container object instead of passing around multiple
params. (incomplete)
Signed-off-by: Yehuda S...
Yehuda Sadeh
09:03 PM Revision 7bbbec02 (ceph): rgw: add error_logger to sync env
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:03 PM Revision 0a0d437b (ceph): rgw: fail when trying to commit period if no master zone configured
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
09:03 PM Revision 9abb8e62 (ceph): rgw: more error handling
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
08:50 PM Revision caa73ba3 (ceph): os/filestore/FileJournal: simplify alignment asserts
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
08:45 PM Revision a8807641 (ceph): Merge pull request #7350 from ddiss/tracker14499_enotconn_rados_monitor...
librados: check connection state in rados_monitor_log
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
08:40 PM Bug #14511 (Resolved): cache-flush-evict-all causes OSD stuck ops on unevictable objects
Sage Weil
01:04 AM Bug #14511: cache-flush-evict-all causes OSD stuck ops on unevictable objects
Sage Weil
08:40 PM Revision 56d3e94b (ceph): Merge pull request #7584 from ifed01/wip-14511
osd: fix lack of object unblock when flush fails
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
08:39 PM Revision 50b45ccf (ceph): Merge pull request #7593 from ifed01/wip-no-blockedpromote-return-fix
osd: fix return value from maybe_handle_cache_detail()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
08:39 PM Revision bd17b5f4 (ceph): Merge pull request #7587 from cbodley/wip-pageset-align
osd: memstore: fix alignment of Page for test_pageset
Reviewed-by: Dan Mick <dmick@redhat.com>
Sage Weil
08:38 PM Revision a00e8358 (ceph): Merge pull request #7595 from liewegas/wip-hobject-stringify
osd: ghobject_t: use ! instead of @ as a separator Sage Weil
08:37 PM Revision 9be30dbe (ceph): Merge pull request #7596 from dachary/wip-erasure-code-corpus
tests: sync ceph-erasure-code-corpus for mktemp -d
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil
08:36 PM Revision eec65d03 (ceph): Merge pull request #7608 from liewegas/wip-warnings
tests: fix a few build warnings
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil
08:23 PM Revision 613457f9 (ceph): osd: consider high/low mode when putting agent to sleep
If we are in low flush mode, we may only get up to max_low_ops in flight,
in which case we may never go to sleep here...
Sage Weil
08:22 PM Bug #14752 (Resolved): osd: agent can spin if in low flush mode and no evict work
if there isn't evict work, we will only start the low flush max ops, but won't go to sleep if we're below the high li... Sage Weil
07:53 PM Revision c8048ce4 (ceph): os/filestore/FileJournal: set block size via config option
We were setting the block_size as the MIN of the min size (4096) and the
block size reported for the journal file/dev...
Sage Weil
07:28 PM CephFS Bug #14684: test_scrub_checks fails
http://pulpito.ceph.com/teuthology-2016-02-10_14:03:02-fs-jewel---basic-smithi/4160/... Greg Farnum
07:05 PM Bug #14750: Objecter: do not mark OSD ops as laggy based on osd_timeout value
https://github.com/ceph/ceph/pull/7629 Greg Farnum
06:58 PM Bug #14750 (Resolved): Objecter: do not mark OSD ops as laggy based on osd_timeout value
We are currently looking at Objecter::osd_timeout when determining if OSD ops are laggy in Objecter::tick(). This hap... Greg Farnum
07:00 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
John Spray wrote:
> The output is
> [...]
>
> (it's hard to see because it comes out at the point the command ac...
Greg Farnum
01:35 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
aaaand here's why:... John Spray
01:30 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
The weirdness here is that the error is coming from os.write() rather than os.fsync().
The test expects that the c...
John Spray
01:24 PM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
The output is... John Spray
06:43 AM CephFS Bug #14698: Test failure: test_full_fsync (tasks.cephfs.test_full.TestQuotaFull)
I'm confused — the log doesn't seem to include any of the output from the remote python script. Which makes me think ... Greg Farnum
06:07 PM Revision cb9cfb72 (ceph): librgw: fix rpm packaging
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
06:07 PM Revision 85e4febb (ceph): librgw: fix new Debian control entries
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
06:07 PM Revision e18c6890 (ceph): librgw: remove junk files
Files accidentally added.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
06:07 PM Revision 5f0fcdba (ceph): librgw: don't compare a string_ref with "" (use empty())
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
06:07 PM Revision 244ad79f (ceph): librgw: fix boost::basic_string_ref template instantiation
The commit adding Seastar sstring.h replaced a part of the interface
which used an internal string-view type, with an...
Matt Benjamin
06:07 PM Revision de0f8669 (ceph): librgw: add debian and rpm packaging
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
06:07 PM Revision 2f706ef0 (ceph): librgw: consolidate S3 bucket name validation
There is more cleanup potential here, but it is intrusive, as the
validators for bucket and object names have been fa...
Matt Benjamin
05:33 PM Revision 7496dd9f (ceph): Merge pull request #7626 from tchaikov/wip-fix-automake
Makefile: workaround an automake bug for "make check"
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Kefu Chai
05:08 PM Revision cfb8c81e (ceph): librgw: fix copyright in src/include/rados/rgw_file.h
This file originated at Red Hat.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:08 PM Revision 195185d4 (ceph): librgw: initialize RGWLib pointer members
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Yehuda Sadeh
05:08 PM Revision a293c529 (ceph): librgw: remove slo, dlo, and supplied-md5 logic in RGWWriteRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 3d7fa4f7 (ceph): librgw: remove RGWLibRequest "magic" numbers added for debugging
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 303f5420 (ceph): librgw: comment rgw_nfs config_ops.h tunables
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 48c0f5b4 (ceph): cohort_lru: remove #if 0 section
The declaration being skipped was meant as a placeholder for future
optimization work, moved to a comment.
Signed-of...
Matt Benjamin
05:08 PM Revision 165079de (ceph): {rgw,common}/Makefile.am: add a few more missing .h files
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Yehuda Sadeh
05:08 PM Revision acadd09b (ceph): common: add xxhash.h to Makefile.am
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Yehuda Sadeh
05:08 PM Revision 47a5c0cf (ceph): rgw: fix null dereference
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Yehuda Sadeh
05:08 PM Revision 1f6799df (ceph): librgw/rgw: fix librgw.la linkage
Ensure that key symbols from global are satisfied in the library.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:08 PM Revision c38e3cbb (ceph): librgw/rgw: reorganize autotools linkage
Adds the RGW-NFS library to the radosgw build, with unit tests.
Adds -fPIC to compile flags to satisfy the linker, bu...
Matt Benjamin
05:08 PM Revision 269d90a4 (ceph): librgw: call obj_rec::sync() on dirs1_b
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 77a40397 (ceph): librgw_file_nfsns: create readf_out_name, if needed
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision fa9cd660 (ceph): librgw: remove deprecated/unused librgw personality
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 4b42c57b (ceph): librgw: properly detect RGWRados init failure
Unit tests correctly see fail result from librgw_create.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:08 PM Revision aa969585 (ceph): librgw: remove deprecated librgw methods
Remove unused routines:
* librgw_acl_bin2xml
* librgw_free_xml
* librgw_acl_xml2bin
* librgw_free_bin(librgw_t r...
Matt Benjamin
05:08 PM Revision e43eb4d6 (ceph): librgw: temporary fix RGWWrite
The current behavior of put_data_and_throttle leads to data
curruption, because the supplied buffer is apparently sti...
Matt Benjamin
05:08 PM Revision 8aa43781 (ceph): librgw: cleanup rgw_write
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:08 PM Revision 6b9b3d8f (ceph): librgw: add new rgw_write unit test
WRITEF1 writes back data wread in READF1.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:08 PM Revision 0eda995c (ceph): librgw: fix RGWReadRequest send_response_data
In hindsight, it seems clear how to consume the available bytes and
account for the bytes written into the caller's b...
Matt Benjamin
05:08 PM Revision 06aff873 (ceph): librgw: add cross-bucket rgw_rename test
It passes.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:08 PM Revision b35de479 (ceph): librgw: fix intra-bucket rename
Avoid hopeless fail due to binding const::std::string& to a
temporary.
Signed-off-by: Matt Benjamin <mbenjamin@redha...
Matt Benjamin
05:08 PM Revision ca6e93bb (ceph): librgw: add support for rgw_rename tests
Implements intra-bucket rgw_rename test, which unfortunately fails
currently.
Signed-off-by: Matt Benjamin <mbenjami...
Matt Benjamin
05:08 PM Revision 2e109ec3 (ceph): librgw: fix rgw_unlink and delete atomicity
Move internal unlink logic into new RGWLibFS::unlink method, fix
logic for files and directories.
Use RGWFileHandle:...
Matt Benjamin
05:08 PM Revision ad3a22da (ceph): librgw: implement object rename
The implementation uses currently does a copy, followed by a
delete operation (if successful).
Signed-off-by: Matt B...
Matt Benjamin
05:08 PM Revision 2a860f42 (ceph): librgw: fix timestamp on create (another case)
In the rgw_create regular file case, the timestamp and size update
logic (though present) was being bypassed because ...
Matt Benjamin
05:08 PM Revision e68600be (ceph): librgw: cleanup, move 3 prints to log channel
Save a pointer to CephContext in RGWProcess for use by logger--
using the existing pointer in ThreadPool would be an ...
Matt Benjamin
05:08 PM Revision 7ef64851 (ceph): librgw: add missing RGWFileHandle::stat in rgw_mkdir
The lack of stat here induced a serious memory corruption, due to
the organization of Ganesha file attributes (and th...
Matt Benjamin
05:07 PM Revision 35445cf7 (ceph): librgw: fix leading-slash special case, again
Fix boilerplate to sanitize relative_object_name() in rgw_create
as well as the RGWStatObjRequest case of RGWLibFS::s...
Matt Benjamin
05:07 PM Revision 4f8e7652 (ceph): librgw: disable name-cache lookups w/CREATE
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision b57f51bf (ceph): librgw: fix a prefix bug and bucket timestamp bug
The fix for missing bucket.creation_time in RGWStatBucket is not
complete--we're not carrying all the info over.
Sig...
Matt Benjamin
05:07 PM Revision 998ed65d (ceph): librgw: ignore "/" as a common_prefix
This happens commonly, apparently when a parent object name ends
with '/' (as all explicit directories do).
Signed-o...
Matt Benjamin
05:07 PM Revision 441bff73 (ceph): librgw: rgw_getattr refactor, RGWLibFS::stat_leaf (object)
Rewrite rgw_getattr to just dispatch into RGWLibFS::getattr, where
we can better use RGWFileHandle and RGWLibFS inter...
Matt Benjamin
05:07 PM Revision ce62d805 (ceph): librgw: fix rgw_read, add unit test
rgw_read had been trivially broken by the relative path change,
fixed.
Signed-off-by: Matt Benjamin <mbenjamin@redha...
Matt Benjamin
05:07 PM Revision 1b797a72 (ceph): librgw: add rgw_getattr tests
Re-implement rgw_getattr to just dispatch into RGWFileHandle::stat,
we expect all objects to stat correctly for their...
Matt Benjamin
05:07 PM Revision 117208c7 (ceph): librgw: re-implement rgw_create
rgw_create hadn't been re-implemented for NFS namespace behavior,
where we expect it to create empty file objects.
I...
Matt Benjamin
05:07 PM Revision ec924b66 (ceph): librgw: update rgw_* api calls so that all take a flags arg
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 4f2dd467 (ceph): librgw: normalize obj_rec::sync calls, fix signedness of refcnt asserts
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision a50416bc (ceph): librgw: partial getattrs/gc checks
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 402a76f2 (ceph): librgw: fix handle type in rgw_mkdir, finish dirs1 create tests
Fixes handle type after rgw_mkdir.
Add handle type checks to nfsns unit tests. Adds tests to create
files and direc...
Matt Benjamin
05:07 PM Revision d18fe86b (ceph): librgw: set directory ctime and mtime
Adds method to RGWStatBucketRequest to access the creation_time of
the returned bucket.
(For now, that's the only ti...
Matt Benjamin
05:07 PM Revision d8175918 (ceph): librgw: refactor nfsns dirs1 and fix a "bad unlink" case
Fix the error returns from rgw_unlink. This is sufficient to
catch the errors that arise from operation failure.
We...
Matt Benjamin
05:07 PM Revision 558c2115 (ceph): librgw: incremental bucket-object 2-level tests
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 12fd3faa (ceph): librgw: enforce S3 object name restrictions
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 66b6b1fd (ceph): librgw: enforce S3 bucket name restrictions
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 54149b06 (ceph): librgw: FLAG_CREATE cleanup
Split the transiently-creating concept (CREATING) from the request
to create objects used in lookup_fh.
Signed-off-b...
Matt Benjamin
05:07 PM Revision c1d1e15d (ceph): librgw: nfsns dirs1 delete, make hier1 conditional
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 41b2357a (ceph): librgw: incr. fix various nfs ops (REBASEME)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision b008fe52 (ceph): librgw: reorg SETUP_ENUMERATE test
Stat nfsroot bucket, create it only if !exist && do_create.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:07 PM Revision b7730c0a (ceph): librgw: conditionally send '.' and '..' (rgw_readdir)
Ganesha traditionally does not expect them, but they may be needed
when bypassing the MDCACHE (2.4).
Signed-off-by: ...
Matt Benjamin
05:07 PM Revision 5e75c183 (ceph): librgw: stop abusing parents
Also make sure that root file handle has directory as its variant
type.
Signed-off-by: Matt Benjamin <mbenjamin@redh...
Matt Benjamin
05:07 PM Revision 7cc6a6db (ceph): librgw: likely correct marker handling
New logic propagates is_truncated traveral-finished indicator up
from bucket and object list operations in all cases,...
Matt Benjamin
05:07 PM Revision 446d92c4 (ceph): librgw: is_truncated experiments
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision bd07c2ad (ceph): librgw nfsns: create/delete updates
Add ability to delete marker objs, and create (but not yet delete)
nfs_hier objects.
Signed-off-by: Matt Benjamin <m...
Matt Benjamin
05:07 PM Revision adfb96a5 (ceph): librgw: don't early terminate readdirs (in progress)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 9a6944c7 (ceph): librgw: remove unused st
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 603f245e (ceph): librgw: split nfsns bucket and object create blocks
Helps to see the respective timings.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:07 PM Revision 82aababc (ceph): librgw_file_nfsns: bugfix MARKER1_SETUP
Successfully creates 5*1024 objects at /nfsroot/nfs_marker/, verifies
externally.
Follow-up rgw_readdir shows 999 re...
Matt Benjamin
05:07 PM Revision e6b3be3c (ceph): librgw: consolidate dup'd librgw, rgwlib
There can be only one. Fixes crash on shutdown.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:07 PM Revision 103b9dde (ceph): librgw: remove search_prefix()
Since it turns out this is a synonym for relative_object_name().
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:07 PM Revision 5b6af8a1 (ceph): incremental marker
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 80d5201a (ceph): librgw: omit always-false depth test.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision bd4b9844 (ceph): librgw: rework full_object_name() and friends
Flex RGWFileHandle::full_object_name() to build either a search
prefix (omits leading "/" and bucket name) or else th...
Matt Benjamin
05:07 PM Revision 41587210 (ceph): librgw: add continued readdir test
Verify that files created in a single, large directory are correctly
enumerated through a sequence of rgw_readdir() c...
Matt Benjamin
05:07 PM Revision 1097ed4c (ceph): marker
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision a557c898 (ceph): Fix copyright statements on new test driver files (Red Hat, Inc.)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 597f69d9 (ceph): librgw: dir traversal state GC added
To minimize overhead, traversal events are modeled as a linear
sequence of fh_key, timestamp tuples. GC operates out...
Matt Benjamin
05:07 PM Revision b970fd00 (ceph): librgw: restore readdir prints (move to dout)
They are useful for checking the exact strings being produced,
and in which sequence (object or common prefix).
Sign...
Matt Benjamin
05:07 PM Revision 7acb20d8 (ceph): librgw: move readdir operations into RGWFileHandle::readdir
The motivation here is to localize state updates to the class,
e.g., to hide consistency logic.
Signed-off-by: Matt ...
Matt Benjamin
05:07 PM Revision 453219cb (ceph): librgw: implement small-directory name cache
Augment the existing marker cache with cache of name->type
mappings for up to 128 dirents (appx. 4x the common upper-...
Matt Benjamin
05:07 PM Revision e8fc2b75 (ceph): librgw: remote redundnat prints in RGWReaddirRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 49a034af (ceph): librgw: don't increment offset at rcb (it is no longer a counter)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision bd068089 (ceph): librgw: fill in dirent cache
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 33856c19 (ceph): librgw: implement framework for fs periodic work
This can be used for, e.g., gc of stale handles and directory
traversals.
Signed-off-by: Matt Benjamin <mbenjamin@re...
Matt Benjamin
05:07 PM Revision 3237f0b9 (ceph): librgw: add intrusive refcnt to RGWLibFS
Ensures that file system instances cannot be disposed while (e.g.)
background processing is ongoing.
Signed-off-by: ...
Matt Benjamin
05:07 PM Revision baffb146 (ceph): librgw: header and namespace reorganization
Move RGWLibProcess and RGWLibFrontend into new rgw_lib_frontend.h
header, which can include rgw_lib.h and rgw_file.h....
Matt Benjamin
05:07 PM Revision e448c4eb (ceph): librgw: use string_ref remove_prefix
Save a few cycles over re-assigning a string_ref suffix substring
to itself.
Signed-off-by: Matt Benjamin <mbenjamin...
Matt Benjamin
05:07 PM Revision 8db2c6a9 (ceph): librgw: fix initialization of string_ref from temporary
Found by valgrind. The good news: amounts to proof that the
sref notation works.
Signed-off-by: Matt Benjamin <mbe...
Matt Benjamin
05:07 PM Revision b19912c9 (ceph): cohort_lru: use correct new/delete operator pair
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision eaf15639 (ceph): librgw: move ObjUnref trace print ahead of...unref
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision 1f2ec092 (ceph): librgw: cleanup add_marker and handlers
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:07 PM Revision e6eee9fa (ceph): librgw: rename RGWGetObjRequest, RGWListBucketRequest
The behavior of these requests is basically specific to the
needs of NFS READDIR and READ. (RGWWriteRequest already ...
Matt Benjamin
05:07 PM Revision ef6367fc (ceph): common: add (tweaked) sstring.h
Add sstring.h from Seastar, slightly adapted for c++2011 and
boost::string_ref.
An sstring resembles std::string, bu...
Matt Benjamin
05:07 PM Revision 6147c3e5 (ceph): librgw: fix RGWLibFS::stat_leaf ex-ref
Found verifying refcounts at RGWLibFS::close.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:06 PM Revision 9cf66708 (ceph): lirgw: call RGWLibFS::close in rgw_umount
Also remove an unused warning in currently-disabled rgw_readv.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:06 PM Revision 562ebcbe (ceph): librgw: implement LRU lifecycle for handles
This re-uses intrusive lane LRU and co-resident intrusive b-tree
for lookups (formerly, we were using just the dictio...
Matt Benjamin
05:06 PM Revision 066c2e8d (ceph): librgw: remove dead code (rgw_readdir)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 00571a51 (ceph): librgw: use correct finish path for RGWWriteRequest (logging and stats)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision e4b0c2be (ceph): librgw: update posix-style read path
Update RGWGetObj to take ulp buffer rather than transferring the
elements of a buffer::list and re-traversing it.
Th...
Matt Benjamin
05:06 PM Revision 49a47d1d (ceph): librgw: set iov->iov_len to nread (get)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision ea51474a (ceph): librgw: sequential rgw_write works
This commit finishes hooking up RGWWriteRequest, and its supporting
RGWLibContinuedRequest.
The rgw_read call now fa...
Matt Benjamin
05:06 PM Revision 5d9e395c (ceph): librgw: update mtime on write finish
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision e08b8d67 (ceph): librgw: -EISDIR
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 0090da6d (ceph): librgw: check variant type, fix reversed check for write trans
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 3b795c1c (ceph): librgw: finish write transactions in rgw_close path
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision a8f8c1a6 (ceph): librgw: block in RGWWriteRequest::exec_continue
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 6e630d69 (ceph): librgw: block in RGWWriteRequest::exec_start
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 1c722bbc (ceph): librgw: wire up more of continuation
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 80bac657 (ceph): librgw: dont forget to call exec_start
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 6b798deb (ceph): librgw: partial implementation of continued request framework
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision e3be0743 (ceph): librgw_file_aw: re-enable write sequence
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision a27a4070 (ceph): librgw: fix some incorrect uses of string temporary
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 5fe01703 (ceph): librgw: add initial atomic write unit test
Tests are focused on open-write-close, open-read-close sequences.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:06 PM Revision 4e5aef61 (ceph): librgw: don't allow open on directories (externally)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision eb99b448 (ceph): librgw: restrict objects to single-open
this is the simplest consistent model for an open-write-close
transaction (and it reads stable)
Signed-off-by: Matt ...
Matt Benjamin
05:06 PM Revision 57938d8c (ceph): librgw: fix last enumeration bug, move tracing to debug
The last issue with enumeration was caused by inserting objects
into handle cache with their key-ified full_object_na...
Matt Benjamin
05:06 PM Revision a4207842 (ceph): librgw: fix and unify full-name assembly and hashing
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 46f82d7a (ceph): librgw: incremental listing fixes
* remove path in RGWStatLeafRequest--use bool is_dir instead
* remove unused uri in RGWListBucketRequest
* more dbg p...
Matt Benjamin
05:06 PM Revision b83ac0d9 (ceph): librgw: incremental enumeration progress
As of this change, enumeration is -almost- correct, but the
rules for name, object_name(), and full_object_name() nee...
Matt Benjamin
05:06 PM Revision 6dba6924 (ceph): librgw: remove unused string uri
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 589af39b (ceph): librgw: namespace bugfixes
1. stat_leaf() and stat_bucket() require RGWFileHandle::FLAG_CREATE
2. refactor RGWStatLeafRequest on the model of RG...
Matt Benjamin
05:06 PM Revision 821c562f (ceph): librgw_file_nfsns: stage namespace traversal (fails)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 27c9a360 (ceph): librgw: initial librgw_file_nfsns.cc test
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision ba82ff80 (ceph): librgw: add missing include deps (rgw_file.h)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 54dcf30c (ceph): librgw: fix parent chasing in make_fhk
Avoid an...infinite loop.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:06 PM Revision f9173e89 (ceph): librgw: fix last-of marker detection
Add the count of common_prefixes to the existing listing size, rather
than overwriting it, else size cannot be compar...
Matt Benjamin
05:06 PM Revision 4e9116ae (ceph): librgw: unify result cases in rgw_mkdir
In both paths, instantiate a file handle iff the remote op
succeeded.
If this operation lost a race to create an obj...
Matt Benjamin
05:06 PM Revision 33539db7 (ceph): librgw: RGWListBucketRequest and related bugfixes
1. instantiate handles as required in RGWLibFS::stat_bucket
2. fix bucket_name() when bucket
3. fix full_object_name(...
Matt Benjamin
05:06 PM Revision e53eb38c (ceph): librgw: implement stat_bucket, call from rgw_lookup
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 21bf2776 (ceph): librgw: annotate unlink's rgw_lookup
An rgw_lookup w/RGW_LOOKUP_FLAG_NONE will return an existing (hence
validated, modulo CREATE races) handle, but fail ...
Matt Benjamin
05:06 PM Revision b9f30657 (ceph): librgw: add lookup step in rgw_unlink
Implement the required check for underlying leaf object, since with
the current signature it is not known.
(Is that ...
Matt Benjamin
05:06 PM Revision 1d17dcd9 (ceph): librgw: hide uri in RGWListBucketRequest, use full_objectname()
Really would like to remove the requirement to format a URI for these
requests, since it is merely taken apart in par...
Matt Benjamin
05:06 PM Revision 06e2dad5 (ceph): librgw: add marker processing to RGWListBucket(s)Request
Ignores object instances, for now. Not verified.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:06 PM Revision 6e70b6de (ceph): librgw: reimplement RGWLibFS::stat_leaf
Now the code attempts to read an object header (which may be cached),
and if this fails, uses RGWStatLeafRequest to f...
Matt Benjamin
05:06 PM Revision 3ac44f91 (ceph): librgw: variant handle subtype and marker cache
RGWFileHandle gets a type-specific variant part. For the directory
variant, define a flat_map of cookie to marker. ...
Matt Benjamin
05:06 PM Revision fcd43203 (ceph): librgw: create dir file handles w/correct type
RGW objects which happen to represent directories will always end
in '/', but the trailing slash will not be present ...
Matt Benjamin
05:06 PM Revision 103eda1c (ceph): librgw: implement RGWLibFS::stat_leaf
Stats one of <object>, <object/>. Additional control over handle
creation has been added to RGWLibFS::lookup_fh.
S...
Matt Benjamin
05:06 PM Revision 5725721f (ceph): librgw: incr rework stat
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 37810275 (ceph): librgw: fix uninitialized rgw_fh
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 196ef769 (ceph): cohort_lru: fix a maybe uninitialized warning (that seems invalid)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 4a23f4c0 (ceph): librgw: create explicit directory leaf objects in rgw_mkdir
There is some asymmetry here, since directories are also inferred
from object names containing embedded "/."
The obv...
Matt Benjamin
05:06 PM Revision b94b51f9 (ceph): librgw: consolidate RGWLib RGWOps into RGWRequest
The intermediate derivation mirrored that in RGWRest, but we
don't seem to need it.
Signed-off-by: Matt Benjamin <mb...
Matt Benjamin
05:06 PM Revision 42fc51a4 (ceph): librgw: don't discard lookup result, fix signedness of min_size
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 13bc25a1 (ceph): librgw: make_fhk put base name, object_name in wrong order
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 3e6e4ed2 (ceph): librgw: add pseudo() accessor
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision fc505f4a (ceph): librgw: add pseudofs awareness to lookup_fh
And then allow rgw_mkdir() to create pseudofs vnodes, when parent
is not the root.
Signed-off-by: Matt Benjamin <mbe...
Matt Benjamin
05:06 PM Revision 33ee6d27 (ceph): librgw: make_fhk, compute object hashes path-wise
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:06 PM Revision 6691da04 (ceph): librgw: add depth and make_path to RGWFileHandle
This just (mostly) efficiently builds a full path from its segments
on demand.
Signed-off-by: Matt Benjamin <mbenjam...
Matt Benjamin
05:06 PM Revision 443e9c9c (ceph): librgw: compress RGWFileHandle stat data
Just save the state we actually mutate, and fill stat structures
on demand.
Signed-off-by: Matt Benjamin <mbenjamin@...
Matt Benjamin
05:06 PM Revision cfc7a4f5 (ceph): librgw: fix abuse of std::string& in RGWDeleteObjRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 80c85738 (ceph): librgw: fix rgw_unlink
Fix handling of bucket namespace, remove bogus RGWLibFS::is_root()
logic. Also remove a stray debug check.
Signed-o...
Matt Benjamin
05:05 PM Revision fbfafb3e (ceph): librgw: ok, make RGW vnodes cache Unix attrs
Ganesa ULP needs to see a sane progression of attrs in the CREATE
path.
With this change shell actions like
$ echo ...
Matt Benjamin
05:05 PM Revision 5f4ef7ed (ceph): librgw: forge Unix attrs in rgw_create
Possibly RGW vnodes should cache Unix attrs, it would reduce the
latency of (frequent) getattr calls, and eventually ...
Matt Benjamin
05:05 PM Revision c480472f (ceph): librgw: fix Unix file modes
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 4fd6511c (ceph): librgw: implement rgw_create + bugfixes
Incremental work to support CREATE,OPEN,WRITE*,CLOSE transactions.
Adds a new tuple-based signature for RGWFileHandle...
Matt Benjamin
05:05 PM Revision 6db1f9dd (ceph): librgw: fix size computation in RGWStatObjRequest
Overrides RGWGetObj::execute(), calls the parent method and then
saves obj_size from the manifest.
Signed-off-by: Ma...
Matt Benjamin
05:05 PM Revision bf6bee61 (ceph): librgw: fix many rgw_file return codes
This should all be -(POSIX), or at any rate negative.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:05 PM Revision 66823a06 (ceph): librgw: don't abuse fs_private
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 857aa1e3 (ceph): librgw: introduce RGW_LOOKUP_FLAG_CREATE
The current API relies on rgw_lookup and rgw_lookup_filehandle to
return file handle instances, and like POSIX, needs...
Matt Benjamin
05:05 PM Revision 7f482c05 (ceph): librgw: add getattr unit tests, restructure
The fids1, fids2 vectors were confusing, as fids2 mapped the
objects in the union of all buckets.
Now there's a matr...
Matt Benjamin
05:05 PM Revision 3c94a95b (ceph): librgw: handle a 3 cases in rgw_getattr
Only the object case is mostly correct.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:05 PM Revision 885a603a (ceph): librgw: handle rgw_lookup in the root (minimally)
In addition, check real return code from RGWStatRequest.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:05 PM Revision fd8f20e8 (ceph): librgw: change validity check for rgw_lookup
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 71590b8b (ceph): librgw: add RGWStatObjRequest and use it
* implement a stat operation over RGWGetObj (returning early)
* use stat to validate rgw_lookup
* use stat to impleme...
Matt Benjamin
05:05 PM Revision 0e5f5e2b (ceph): librgw: add diagnostic dump_buckets() call.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision a5e6d559 (ceph): librgw: fail RGWLibFS::authorize() on user-by-id lookup failure
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 0175a3d3 (ceph): librgw: implement rgw_vfsstat
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 74e4c5ab (ceph): librgw: rgw_mkdir and rgw_create return addresses
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 507ecab9 (ceph): librgw: pass struct rgw_fh_hk by reference
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 056c0cb8 (ceph): librgw: always add struct before rgw_file_handle in rgw_file.h
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 8417a788 (ceph): librgw: bring back lookup_handle()
Now as a member of RGWLibFS, and exposed via rgw_lookup_handle()
for use by library clients.
Signed-off-by: Matt Ben...
Matt Benjamin
05:05 PM Revision 455d9d5c (ceph): librgw_file_gp: check test state before closing null fh handle
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 9821d6fb (ceph): librgw: implement intrusive filehandle cache
The cache is keyed on a hash of bucket name, plus a hash of the
object name.
Signed-off-by: Matt Benjamin <mbenjamin...
Matt Benjamin
05:05 PM Revision d6e171a7 (ceph): librgw: add common/cohort_lru.h
This a cache-line-friendly set of primitives for
a) shareded, intrusive maps based on boost::intrusive
b) an LRU sys...
Matt Benjamin
05:05 PM Revision e1b4fc7e (ceph): librgw_file: release file handles
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 73b19a91 (ceph): librgw_file_gp: don't leak a buffer::list
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision ab377b18 (ceph): librgw: checksum verify writev/readv read-after-write
The changes to GET_OBJECT and PUT_OBJECT test options are needed,
since they are (re) writing the same object.
Sadly...
Matt Benjamin
05:05 PM Revision b9137e47 (ceph): librgw: really make hexdump optional, set resid in readv unit test
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 5e0b6e4d (ceph): librgw: fix 2 dout problems
* rgw_file.cc needed to include include/assert.h AFTER all rgw
includes, for some reason
* use *_dout syntax as ta...
Matt Benjamin
05:05 PM Revision 5139c312 (ceph): librgw: try-implement rgw_readv/rgw_writev
The model in the rgw_readv call is the caller owns the struct rgw_uio,
and uses it to pass uio_offset.
The caller re...
Matt Benjamin
05:05 PM Revision 540ce769 (ceph): librgw: improve rgw_write and add WRITE_READ_VERIFY
Update rgw_write to return bytes written as an OUT argument,
use and verify in PUT test.
A new WRITE_READ_VERIFY tes...
Matt Benjamin
05:05 PM Revision 421f5ecc (ceph): librgw: remove junk prints
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 50abb8cb (ceph): librgw: set RGWGetObj::get_data = true, for great justice
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 290b06a9 (ceph): librgw: rework library CephContext* and init
Remove duplicated init step. Just reference the global
Ceph context for the library instance(s).
The immediate effe...
Matt Benjamin
05:05 PM Revision 72fb1ad6 (ceph): librgw: dispatch RGWDeleteRequest in object branch in rgw_unlink().
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 88c2d028 (ceph): librgw: implement RGWGetObjRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision b6521266 (ceph): librgw: declare RGWDeleteObjRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 0ec522bc (ceph): librgw: declare RGWGetObjRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 21e6ff37 (ceph): librgw: fix RGWPutObj s->content_length
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 24da131d (ceph): RGWPutObjRequest: fix get_data()
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision b3150b0f (ceph): rgw log: disambiguate 'Read AccessControlPolicy' (logs)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision c352d4b2 (ceph): librgw: add --prelist to gp to prime cache
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 7f981b10 (ceph): librgw: fix rgw_open param names and invocation
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 9429cb13 (ceph): librgw: avoid illegal rele()
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision ec89aafd (ceph): librgw: don't create/delete in librgw_file.cc (unit test)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision adcba208 (ceph): librgw: fs->root_fh is a pointer (and assign it)
Assign and expose the expanded root_fh indirectly from the mounted
root filesystem structure.
Signed-off-by: Matt Be...
Matt Benjamin
05:05 PM Revision 522c9588 (ceph): librgw: bucket names can be const
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision e562357b (ceph): librgw: reify root handles
Reify root handle, remove traces of legacy (counter) handles.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:05 PM Revision 1e7539be (ceph): librgw: incremental RGWPutObj work and almost-complete RGWFH refactor.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision a50bc13d (ceph): xxHash: build internally
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 1254f34f (ceph): librgw: add ZPage/ZPageSet abstraction (gp unit tests)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision 020aee93 (ceph): xxHash: add as submodule
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision fc0a895a (ceph): librgw: rgw_file_handle refactor, plus get/put
Implement encapsulation of RGWFileHandle in rgw_file_handle,
so return these from rgw_lookup(), add new rgw_fh_rele()...
Matt Benjamin
05:05 PM Revision 03b66159 (ceph): librgw: add options for bucket name, multi create, delete
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:05 PM Revision abcec540 (ceph): librgw: fix acl assignment in RGWCreateBucket_OS_Lib
The logic to create a default S3 policy in
RGWCreateBucket_OS_Lib::get_params() was essentially correct, but
failed t...
Matt Benjamin
05:04 PM Revision 29942221 (ceph): librgw: don't fake hostname (real hostname isn't used yet)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision cca325e1 (ceph): librgw: don't allow running rgwfile tests as anon
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision 3fcdd946 (ceph): librgw: partial delete/unlink support
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision 9fb454ac (ceph): librgw: return result code from execute_request
Update rgw_mkdir and rgw_readdir to use it.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:04 PM Revision c43384c0 (ceph): librgw: fix uri, read_permissions virtual for create-bucket
* set uri in rgw_mkdir (duh)
* RGWCreateBucketRequest should override RGWHandler::read_permissions
to return 0
Sig...
Matt Benjamin
05:04 PM Revision 460794ef (ceph): librgw: block in create bucket, rgw_mkdir
Unit test runs, doesn't...seem to create a bucket.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:04 PM Revision ceb2b0e9 (ceph): librgw: re-derive rgw_os_lib family
* shorten names to match files
* remove derivation through rgw_rest intermediates
Signed-off-by: Matt Benjamin <mben...
Matt Benjamin
05:04 PM Revision 83bed47f (ceph): librgw: s/rgw_rest_lib.{h,cc}/rgw_os_lib.{h,cc}
There is no longer an explicit (e.g., inherited) dependency on REST
implementations.
The remaining coupling (via RGW...
Matt Benjamin
05:04 PM Revision cbcb641e (ceph): lirgw: call RGWHanlder_Lib::init_from_header
Call this from the general RGWLibRequest init() method, after
descendant header_init() has run.
Signed-off-by: Matt ...
Matt Benjamin
05:04 PM Revision 6dae209c (ceph): librgw: cleanups, incremental ListBuckets fixes
1. remove unused RGWLibRequestEnv code marked to delete
2. restore call to RGWHandler::authorize
3. provide RGWLibReq...
Matt Benjamin
05:04 PM Revision e2956295 (ceph): librgw: forward cmdline args to librgw_create
Verified w/-d.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:04 PM Revision 55bb8d34 (ceph): librgw: remove disabled RGWLib RGWREST::get_handler()
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision ed7dc88e (ceph): librgw: cleanups in process_request
* remove disabled S3 authorize step (user authorized on mount)
* re-enable op->verify_permission()
Skipping the latt...
Matt Benjamin
05:04 PM Revision ec96809c (ceph): librgw: pull RGWUserinfo user into RGWLibRequest
Also, return result from process_request(req, io) to caller.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:04 PM Revision 7e21e238 (ceph): librgw: cache RGWUserInfo in rgw_fs private handle
The private RGWLibFS type holds a RGWUserInfo, and
calls rgw_get_user_info_by_access_key and verifies the returned
se...
Matt Benjamin
05:04 PM Revision 6688bc1c (ceph): librgw: split RGWUserInfo from struct req_state
The immediate purpose is to permit auth caching in RGWLib, but
it seems likely that this will be useful for general r...
Matt Benjamin
05:04 PM Revision 290e7881 (ceph): librgw: RGWFileHandle and RGWLibFS
Experimentally reframe the C interface objects as subobjects in
private internal types.
Signed-off-by: Matt Benjamin...
Matt Benjamin
05:04 PM Revision f9382815 (ceph): librgw: fixes for RGWListBucketRequest callback
The cached req_state is still not correct at RGWOp::execute().
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
05:04 PM Revision 9c4de578 (ceph): librgw: untested RGWLibListBucketsRequest and caller.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision 80a56f20 (ceph): librgw: fix 2 bugs in RGWListBuckets, remove scaffolding
1. the prior commit had authorize cognate with S3
1.1 which may be right
1.2 but maybe not for each request
1.3 and l...
Matt Benjamin
05:04 PM Revision c44f19c4 (ceph): librgw: process_request prologue fixups
* initialize RGWEnv with required HTTP_HOST (incorrectly!)
* assign req_state::cio (not really correctly)
* remove in...
Matt Benjamin
05:04 PM Revision 0b614a1b (ceph): librgw: reprocess process_request
Refactor RGWLib variant of process_request(...) as a (actually 2,
one which puts an RGWLibIO on the stack) member fun...
Matt Benjamin
05:04 PM Revision 143bd14f (ceph): librgw: wire up RGWLibFrontend enqueue and exec operations
Adds the missing bits of RGWLibProcess and RGWLibFrontend, and
calls them from rgw_readdir().
Clients can call enque...
Matt Benjamin
05:04 PM Revision 84fd9aa8 (ceph): librgw: remove RGWLibRequestEnv
The REST cognates of this class largely deal with HTTP, and is 1-1
w/request, client-io, op, etc. At worst, its func...
Matt Benjamin
05:04 PM Revision 48671485 (ceph): librgw: wire up request initializers
There's some tricky overloading induced by multiple inheritance,
also this design makes repeatedly shared handles in ...
Matt Benjamin
05:04 PM Revision 259be80c (ceph): librgw: re-derive RGWLibRequest
Derive RGWLibRequest from RGWRequest, RGWHandler.
This strategy defines the dialect of ops following the derivation
...
Matt Benjamin
05:04 PM Revision d1d4535d (ceph): librgw: rename RGWHandler_REST_Lib (sic), inherit from RGWHandler
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:04 PM Revision ac379419 (ceph): librgw: remove dead code, add comments in RGWLib
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
05:02 PM Revision 4af5aeac (ceph): librgw: refactor RGWHandler HTTP/REST methods into _REST
This change renames RGWHandler_ObjStore to RGWHandler_REST, and
moves the following protected, virtual, RESTful metho...
Matt Benjamin
04:58 PM Revision bf104629 (ceph): librgw: call rcb in RGWListBucketsRequest operator()
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:58 PM Revision 748a6e56 (ceph): librgw: add user_id to RGWListBucketsRequest
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:58 PM Revision adade479 (ceph): librgw: header inclusion fix, actually call callbacks
Fix public header inclusion from rgw_file.h internal header, which
of course needs to see the public interface.
Fini...
Matt Benjamin
04:58 PM Revision 85087300 (ceph): librgw: incremental
* move RGWLibRequest decls into rgw_file.h
* revise include guard token in rados/rgw_file.h (avoid conflict)
* save C...
Matt Benjamin
04:58 PM Revision 987821c7 (ceph): librgw: s/gen_request/enqueue_req/;
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:58 PM Revision 9d6c78ff (ceph): librgw: replace RGWHandler::put_op() in RGWLib path
The method just called delete on the RGWOp pointer.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:58 PM Revision ab2349c4 (ceph): librgw: move authorize() and read_permissions()
all RGW_Auth_S3::authorize() from process_request(). Add a
read_permissions() primitive replacing RGWHandler's versi...
Matt Benjamin
04:58 PM Revision 7e8ecc58 (ceph): librgw: pre-assign req->op (as self), avoid dynamic_cast
It would be nice to have some compile-type assistance w/the
dual RGWOp & RGWLibRequest boilerplate.
Signed-off-by: M...
Matt Benjamin
04:58 PM Revision f4994c84 (ceph): librgw: breakthrough cleanups (I think)
* RGWLib bucket ops prototyped
* progress made on RGWOp+RGWRequest unification (RGWLib only)
* mostly-harmlessness of...
Matt Benjamin
04:58 PM Revision f1720d88 (ceph): librgw: incremental rgw_rest_lib internals
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:58 PM Revision 35a5e501 (ceph): librgw: include rgw_lib.h from rgw_rest.cc
RGWLibIO is forward declared in rgw_rest.h.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:58 PM Revision 5cc096d0 (ceph): librgw: tweaks to RGWREST::preprocess and fix a typo in RGWHandler_ObjS...
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:58 PM Revision df8f3920 (ceph): refactor RGWClientIO
In order to support direct/library clients, we want to
more fully decouple RGWOp processing from client HTTP
processi...
Matt Benjamin
04:57 PM Revision 79d3879c (ceph): librgw: comments
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision 2903d754 (ceph): librgw: widen rgw_mount, open-code list buckets
Widen rgw_mount(...) to take the library context, which from
there on follows struct rgw_fs.
Implement an open-coded...
Matt Benjamin
04:57 PM Revision a719a0bd (ceph): librgw: add LOOKUP_BUCKETS and LIST_OBJECTS
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision f6a95fc1 (ceph): librgw: add list bucket test
The operation on store is missing, but interface works.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:57 PM Revision 5521c7ab (ceph): librgw: test rgw_(u)mount(...)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision 84e21660 (ceph): librgw: take keys in test
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision 9eeba4fb (ceph): librgw: fe::init must create RGWLibProcess
All evidence suggests RGWLibFrontend::init needs to create
an RGWLibProcess, and assign to pprocess.
Signed-off-by: ...
Matt Benjamin
04:57 PM Revision d1bbfe94 (ceph): librgw: introduce struct rgw_fs
Pretending for a moment that we can definitely use the "mount"
based model, rgw_file like libcephfs requires a contex...
Matt Benjamin
04:57 PM Revision fae842d2 (ceph): librgw: remove classes from extern, argv
Remove class definitions from extern "C" block, which was
illogical.
Block in support for passing a C-style argument...
Matt Benjamin
04:57 PM Revision eb2ac51c (ceph): librgw: fix type of rgw_readdir eof argument (C-11 bool)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision 2035fcc1 (ceph): librgw: revise rgw_* method signatures
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision e7d0300c (ceph): librgw: update rgw_rename signature
Currently unimplemented.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:57 PM Revision 8fb8f002 (ceph): librgw: define an rgw_setattr
Currently, this operation has no effect. It may be unsafe to
assume that NFS clients can tolerate errors or inconsis...
Matt Benjamin
04:57 PM Revision 763f434b (ceph): librgw: make rgw_readdir take a bool* for eof
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision 5dd73b91 (ceph): librgw: update rgw_readdir interface (stub impl)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision c4262b29 (ceph): librgw: add hypothetical rgw_statfs call
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision c81b85d2 (ceph): librgw: stub implement rgw_getattr
This method returns Unix attributes for an object, represented
by an rgw_file_handle.
Signed-off-by: Matt Benjamin <...
Matt Benjamin
04:57 PM Revision 27e066de (ceph): librgw: add a library version (1.0.0)
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:57 PM Revision c52a9fad (ceph): librgw: rgw shared library
Refactor rgw_a and radosgw_srcs, and add librgw_srcs, permitting
librgw to contain a smaller subset of objects, and i...
Matt Benjamin
04:56 PM Revision ce5ba5d6 (ceph): librgw: compile and implement more of rgw_file
The rgw_file body wasn't being built, so had some impossible
constructs. More had been added by the commit which ren...
Matt Benjamin
04:56 PM Revision e7696554 (ceph): librgw: the external type of librgw_t must be void*
The C interface cannot contain a C++ forward declaration of
class CephContext.
Signed-off-by: Matt Benjamin <mbenjam...
Matt Benjamin
04:55 PM Revision f23cd03b (ceph): librgw: install librgw.h
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> Matt Benjamin
04:55 PM Revision 3f603007 (ceph): librgw: s/nfs_file_handle/rgw_file_handle/;
The interface is in rgw_file.h, so make it match.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:55 PM Revision 98309417 (ceph): rgw_file.h: preserve cosnt correctness
/s
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
Matt Benjamin
04:55 PM Revision 2aa79deb (ceph): librgw: fix some return warnings (and cosmetic)
Fix return codes for several exported functions in the rgw_file
interface.
Fix spacing and pointer, reference type n...
Matt Benjamin
04:55 PM Revision 08b89a5f (ceph): rgw: introduce libradosgw
This change exposes the radosgw service as a dynamic
library, and also introduces a file-oriented view of the
RGW cor...
Orit Wasserman
04:54 PM Revision 76f1dcaf (ceph): rgw: refactor rgw_main
This change is an extended version of work by Orit Wasserman
moving some request-processing class headers and definit...
Matt Benjamin
04:10 PM Revision b709f7ce (ceph): Merge pull request #7351 from fmeppo/master
Add --setuser and --setgroup options for ceph-disk
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
03:58 PM Bug #14723 (Fix Under Review): make check bot broken: execvp: /bin/sh: Argument list too long
https://github.com/ceph/ceph/pull/7626 Kefu Chai
03:47 PM Bug #14723 (In Progress): make check bot broken: execvp: /bin/sh: Argument list too long
Kefu Chai
03:21 PM Bug #14723: make check bot broken: execvp: /bin/sh: Argument list too long
turns out, @MAKEFILE_LIST@ is too long to be passed as a parameter for sh... Kefu Chai
01:11 PM Bug #14723: make check bot broken: execvp: /bin/sh: Argument list too long
https://jenkins.ceph.com/job/ceph-pull-requests/1378/consoleFull Kefu Chai
03:56 PM Revision 19391b71 (ceph): Makefile: workaround an automake bug for "make check"
override the automake variable of am__is_gnu_make. it is a workaround
for http://debbugs.gnu.org/cgi/bugreport.cgi?bu...
Kefu Chai
02:11 PM CephFS Bug #14735 (Pending Backport): ceph-fuse does not mount at boot on Debian Jessie
Nathan Cutler
01:40 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
Nathan Cutler wrote:
> Should this be backported to Infernalis?
Yes, please.
Florent B
01:31 PM CephFS Bug #14735: ceph-fuse does not mount at boot on Debian Jessie
Should this be backported to Infernalis? Nathan Cutler
01:47 PM Bug #14748 (Pending Backport): OSD coredumps with leveldb compact on mount = true
Nathan Cutler
01:01 PM Bug #14748: OSD coredumps with leveldb compact on mount = true
Seems this was fixed in master by https://github.com/ceph/ceph/pull/4372, still waiting for a backport to hammer, tho... Jens Harbott
12:56 PM Bug #14748 (Resolved): OSD coredumps with leveldb compact on mount = true
... Jens Harbott
01:42 PM Backport #14746 (In Progress): infernalis: systemd escaping of block devices in ceph-disk incorrect
Nathan Cutler
05:46 AM Backport #14746 (Rejected): infernalis: systemd escaping of block devices in ceph-disk incorrect
https://github.com/ceph/ceph/pull/7624 Loïc Dachary
01:37 PM rbd Bug #14373 (Resolved): Cannot reliably create snapshot after freezing QEMU IO
Nathan Cutler
01:37 PM rbd Bug #14030 (Resolved): rbd merge-diff doesn't properly handle >2GB diffs
Nathan Cutler
01:35 PM rbd Bug #13491 (Resolved): misdirected op in rbd balance-reads test
Nathan Cutler
01:25 PM Revision 153f7190 (ceph): msg/async: set MSG_MORE intelligently
In write_message, set "more" flag according to ack queue, if there are
messages to acknowledge, set it. Unset it othe...
Piotr Dałek
01:25 PM Revision a07aea6d (ceph): msg/async: delay bufferlist construction
We're using this bl only when removing *some* of data in front of
outcoming_bl, so there's no need to construct it ea...
Piotr Dałek
12:17 PM Revision 7d804cfa (ceph): osd/ReplicatedPG: fix whitespace
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
12:17 PM Revision bab48c2c (ceph): ceph_test_rados_api_tier: verify class op forces promotion
A class op should force a promotion to the base tier. If it
doesn't, well get EOPNOSUPP from the base EC tier, which...
Sage Weil
12:17 PM Revision a0858a58 (ceph): osd/ReplicatedPG: respect must_promote in READFORWARD and READPROXY
Signed-off-by: Sage Weil <sage@redhat.com> Sage Weil
12:17 PM Revision 7dbce5ba (ceph): osd/ReplicatedPG: respect must_promote in WRITEBACK cache mode
Force a promotion of the op requires it. This bug was easily masked
because the defaultish cache parameters would of...
Sage Weil
11:59 AM Revision fb727143 (ceph): Merge pull request #7605 from dachary/wip-python-wheelhouse
python: use pip instead of python setup.py
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai
10:10 AM Revision c1d8faad (ceph): python: use pip instead of python setup.py
python setup.py develop may try to pull dependencies from the net and
has no way to collect them from the wheelhouse ...
Loic Dachary
10:10 AM Revision cd87bd48 (ceph): ceph-disk,ceph-detect-init: clean the build directory
b030d8fc113736b479e84246b6b36d5f698a2da3 should have kept the build
directory in .gitignore and the clean target. Re-...
Loic Dachary
10:00 AM Bug #14095: FreeBSD testsuite generates traps on os/FileJournal.cc:1043
This error was gone until very recently when I again rebased.
Now it is back again.
Probably due to changes for the...
Willem Jan Withagen
06:58 AM CephFS Bug #14714 (Won't Fix): three jobs in samba suite failing for hammer v0.94.6 QE validation
I'm not sure exactly what's going on here, but I'm pretty convinced it's a configuration issue not worth our time to ... Greg Farnum
06:14 AM Revision 18e64820 (ceph): Merge pull request #7528 from objoo/YD-jewel-mailmap-updates-take2
mailmap updates
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Loïc Dachary
05:54 AM Bug #14747 (Resolved): test_bit_vector.cc uses magic numbers against #defines that vary
test_bit_vector's partial_decode_encode test allocates a 9161-element bit vector, and then tests with ranges based on... Dan Mick
05:42 AM rbd Backport #14610 (Resolved): infernalis: Flattening an rbd image with a running Qemu instances cau...
Loïc Dachary
05:38 AM rbd Backport #14610 (In Progress): infernalis: Flattening an rbd image with a running Qemu instances ...
Loïc Dachary
05:40 AM rbd Backport #14062 (Resolved): infernalis: rbd merge-diff doesn't properly handle >2GB diffs
Loïc Dachary
05:38 AM rbd Backport #14062 (In Progress): infernalis: rbd merge-diff doesn't properly handle >2GB diffs
Loïc Dachary
05:40 AM rbd Backport #14542 (Resolved): infernalis: Cannot reliably create snapshot after freezing QEMU IO
Loïc Dachary
05:38 AM rbd Backport #14542 (In Progress): infernalis: Cannot reliably create snapshot after freezing QEMU IO
Loïc Dachary
05:36 AM rbd Backport #13733 (Resolved): misdirected op in rbd balance-reads test
Loïc Dachary
05:10 AM Revision a2888e0a (ceph): Merge pull request #7609 from dillaman/wip-librbd-flatten-test
test: new librbd flatten test case
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
05:09 AM Revision bc22c0f3 (ceph): Merge pull request #7583 from dillaman/wip-librbd-journal-fsx
librbd: integrate journal replay with fsx testing
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin
01:07 AM Bug #14745: osd: call doesn't force promotion from ec base tier
https://github.com/ceph/ceph/pull/7617 Sage Weil
01:05 AM Bug #14745 (Resolved): osd: call doesn't force promotion from ec base tier
reproduce with:... Sage Weil
01:01 AM Revision f88c8522 (ceph): rgw: Fix subuser harder with tenants
We have several ways to set the tenant and user in the operation
state now:
radosgw-admin --uid=user <command> # de...
Pete Zaitcev
12:17 AM CephFS Bug #14716: "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
Nope, that's not it directly, we only propagate one at a time thanks to Journaler::handle_write_error().
This is a...
Greg Farnum
12:13 AM Revision b2f7438d (ceph): rgw: fix create_default to handle EEXIST
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 5c2b519d (ceph): rgw: fix do_curl_wait() if curl_multi_wait() not defined
needed for older systems
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 7a78b0ef (ceph): rgw: replace #warning with a comment
not going to fix it now
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 744f3844 (ceph): rgw: add a timelog add operation cr
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 22faa002 (ceph): rgw: link_pending_requests() fixes
set aside the list of reqs we need to finish, and only then iterate
through that list and finish. Otherwise we corrup...
Yehuda Sadeh
12:13 AM Revision fd46b2d9 (ceph): rgw: hold reference to req_completion while calling aio_operate()
This is a workaround to fix issue with aio_operate() racing with the
request completion. This way we make sure comple...
Yehuda Sadeh
12:13 AM Revision 33489473 (ceph): rgw: use exclusive flag for store_name in RGWSystemMetaObj::create
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 67fccabc (ceph): radosgw-admin: realm pull should not fail if the realm exists
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 4342bd6b (ceph): rgw: add error messages to realm::create
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2360e165 (ceph): rgw: fix RGWSystemMetaObj::init to handle perdefined name correctly
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 79d6952f (ceph): rgw: metadata and data sync share RGWAsyncRadosProcessor
each RGWAsyncRadosProcessor creates 32 worker threads by default, so we
should only create one instance and share it ...
Casey Bodley
12:13 AM Revision defb4d3f (ceph): rgw: shorten name of RGWAsyncRadosProcessor thread pool
threads now call pthread_setname_np(), and have to enforce a
16-character limit on the names. this fixes the assertio...
Casey Bodley
12:13 AM Revision 45c53277 (ceph): rgw: safe disposal of async processors
the async processor might out its container cr, need to refcount.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision b243075a (ceph): rgw: fix a few more leaks
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 847ec960 (ceph): radosgw-admin: add missing break in key rm command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 51eb2fad (ceph): rgw: in create_default read zone_params in case we raced with another
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 0ce5bc5a (ceph): rgw: fix a typo
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision ee9f2065 (ceph): rgw: more of dropping async ops reference
instead of deleting. This was missing from a previous commit.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision d52bf638 (ceph): rgw: forward meta changes to master
(initial work)
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 9ffa3e20 (ceph): rgw: fix a few leaks
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 46f1ee54 (ceph): rgw: more leak fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 9e2569e2 (ceph): rgw: clear stack ops when unwinding last op
So that we don't drop the last one's reference twice
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 5363017e (ceph): rgw: reorder RGWRados shutdown
dependency order fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 47db646f (ceph): rgw: minor cleanup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision efc2dfcc (ceph): rgw: more leak fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8bcdb77d (ceph): rgw: stop meta sync handler when going down
it needed to check internally whether it was going down
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision e53fbe31 (ceph): rgw: split RGWPeriod::reflect out of set_latest_epoch
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 60c9798b (ceph): rgw: add exclusive param to RGWPeriod::set_latest_epoch
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision d89d2247 (ceph): rgw: add RGWPeriodPuller for RGWPeriodHistory
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision f420bd2a (ceph): rgw: add period history and puller to RGWRados
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 71dd4085 (ceph): rgw: 'period push' handler uses RGWPeriodHistory
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision b0630d50 (ceph): rocksdb: set to master
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 813c021f (ceph): rgw: update datalog also when unlinking object instance
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 426e3fc4 (ceph): rgw: period commit updates sync status before writing the object
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision b72530bc (ceph): rgw: start pushing current period on startup
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 423719ba (ceph): rgw: RGWRealm::set_current_period takes RGWPeriod
set_current_period() doesn't need to set the predecessor;
RGWPeriod::commit() takes care of that
Signed-off-by: Case...
Casey Bodley
12:13 AM Revision b37739a2 (ceph): rgw: add realm epoch to RGWRealm and RGWPeriod
RGWRealm::epoch is incremented on each new period, and
RGWPeriod::realm_epoch tracks the realm epoch when it was crea...
Casey Bodley
12:13 AM Revision 1ee26eda (ceph): rgw: use realm epoch to choose most recent period to push
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 7469fc28 (ceph): rgw: fix documentation of RGWRealmWatcher
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 470595b0 (ceph): rgw: RGWPeriodHistory to track period history
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 69c1d9f2 (ceph): rgw: data sync, handle delete marker removal
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8821d065 (ceph): rgw: init_zg_from_period() fixes
Reported-by: fangchen sun <sunspot0105@gmail.com>
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 5e708a96 (ceph): rgw: fix RGWZoneGroup ctor and check period update return code
Add more debug messages
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:13 AM Revision 0ef1fae4 (ceph): radosgw-admin: zonegroup set and zone set should set the realm id
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e911e14c (ceph): rgw: use refrence in read_clear_modified
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2d90f858 (ceph): rgw: 'realm pull' uses realm's current_period for do_period_pull
instead of using period_id/period_epoch, which are radosgw-admin
arguments that are unused by 'realm pull', use the p...
Casey Bodley
12:13 AM Revision 71797cdb (ceph): radosgw-admin: add mdlog and datalog status to help.t
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 18f6853d (ceph): rgw: set_date_header should use header_name
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d26ebb0a (ceph): rgw: update datalog when creating delete marker
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision c78cb250 (ceph): mrgw.sh: modify log file name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision a104062d (ceph): cls/rgw: log owner, display name when creating delete marker
In the case of delete marker, we need to log the owner and the owner
display name so that we can create it correctly ...
Yehuda Sadeh
12:13 AM Revision 850dd42c (ceph): rgw: handle delete marker when doing incremental data sync
Still need to handle the full sync, and to make sure we apply it
only if-newer (as with the other data sync operation...
Yehuda Sadeh
12:13 AM Revision 5e93a686 (ceph): rgw: guard versioned object removal from circular sync
check if marker instance already exists, only apply (and update bi log)
if does not exist. Propagate the versioning f...
Yehuda Sadeh
12:13 AM Revision c5990873 (ceph): rgw: some debug info
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 6476c4e7 (ceph): rgw: data sync, update high marker when skipping duplicate sync entries
Need to update the high marker when skipping an entry, so that when the processing
entry finishes we set the markers ...
Yehuda Sadeh
12:13 AM Revision 6052d4b0 (ceph): test-rgw-call.sh: add missing file
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d2e41e8f (ceph): rgw: store obj pg version in the object's head
this is done atomically when object is written, will allow us
to determine whether object is newer or not.
Signed-of...
Yehuda Sadeh
12:13 AM Revision b50b3bb9 (ceph): rgw: keep pg ver on obj state, and send it in HEAD request
send it in HEAD request if it was done by the system user
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision de129aaa (ceph): rgw: create a short (32bit) zone id, keep it on the period map
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b37503ab (ceph): rgw: keep source zone attr on head object
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b9da8db7 (ceph): rgw: fetch remote obj depends on zone id and pg ver
This provides a consistent objects view on zones when changes happen on
the same objects at the same time. The zone i...
Yehuda Sadeh
12:13 AM Revision a38a3ae8 (ceph): rgw-admin: add datalog status command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 673abbe7 (ceph): test_multi: test object sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 7a25c639 (ceph): test_multi: buckets and objects comparison
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision fb3dd942 (ceph): rgw: clear 'null' object instance when fetching remote obj
otherwise the objclass code will handle it as a versioned object
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision f9b94071 (ceph): rgw/test_multy.py: improve test_object_sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 21e108bb (ceph): rgw/test_multi.py: meta checkpoint uses zones, not clusters
The unit we need to care about is the zone, not the cluster
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 0cc621c9 (ceph): rgw/test_multi.py: add log level for saner output
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 76807064 (ceph): test_multi.py: generate boto connection per zone
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 38cefb41 (ceph): test_multi.py: can run through python nose
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8b8f91a5 (ceph): tests_multi.py: test bucket creation, fix meta checkpoint
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision aa5de3b2 (ceph): rgw: test_multi: start radosgw with debug logs, asok
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision a2583c50 (ceph): rgw: meta sync, handle ENOENT, ECANCELED
retry when canceled, continue when entry does not exist.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 671f3196 (ceph): test_multi: add more bucket related tests
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 61de0364 (ceph): rgw: clone mdlog updates marker in any case
Need to set the new_marker even if no new entries fetched.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 0e9f2e44 (ceph): rgw: meta sync can remove entries
and also skip non complete entries
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 22129ec0 (ceph): radosgw-admin: fix help.t
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 44d0d3f4 (ceph): test/rgw: more test work
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 99da3393 (ceph): test_multi.py: finer control for bringing up system
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 7fd15284 (ceph): test_multi.py: wait for meta sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 6f544074 (ceph): test_multi.py: generate random key
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 82b5f3ae (ceph): test_multi.py: move meta checkpoint inside, add configurables
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b170343a (ceph): test_python.py: call radosgw-admin with cache disabled where applicable
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision aee4e85e (ceph): test_multi.py: create a test user
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8d4fbc09 (ceph): test/rgw: wait for metadata sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b4193211 (ceph): radosgw-admin: use realm current period master_zonegroup as remote for ...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e206c022 (ceph): rgw: cleanup remove realm unused master_zonegroup and zonegroups
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 845bf22e (ceph): rgw: create_default cannot set as default
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 1827781a (ceph): rgw: default zonegroup per realm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2ec85ef6 (ceph): rgw: default zone per realm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision afc900bd (ceph): radosgw-admin: zone list should print default zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 69a395f6 (ceph): rgw: remove error message from read_default
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 74fdef41 (ceph): rgw: bucket sync, don't drain_all() before shutting down lease cr
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b991ff70 (ceph): rgw: more log info on realm reloading
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 346343ed (ceph): rgw: http client lock related fix
need to call _finish_request() under the lock.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 94bd292d (ceph): rgw: fix period pull of first epoch
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8f34600b (ceph): rgw: option to set realm, zonegroup, zone as default
when modifying / creating the entity. This is in addition to the explicit
command.
Signed-off-by: Yehuda Sadeh <yehu...
Yehuda Sadeh
12:13 AM Revision 4571f729 (ceph): test/rgw: initial work on multi site test framework
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 673b28c3 (ceph): test/rgw: basic meta sync status test util
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1105cff6 (ceph): rgw-admin: add mdlog status command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b91e4511 (ceph): rgw: reflect period when setting as current period
reflect period into local objects when setting it as current.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 684d8130 (ceph): rgw: report error
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d1d93860 (ceph): rgw: rearrange zonegroup and zone initialization
move into helpers, don't keep distinct structures for zonegroup local and period
zonegroup, we end up using the one w...
Yehuda Sadeh
12:13 AM Revision e8f148ee (ceph): rgw: adding more reflection where needed
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1975310d (ceph): rgw: make realm pull a raw storage operation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision f81eb8e5 (ceph): rgw: switch to local zonegroup config if zone is not found
We might be just creating a zone that is not in the period config yet,
if we can't find it in period config switch to...
Yehuda Sadeh
12:13 AM Revision 36861353 (ceph): rgw: fix data sync notification
should send zone id, not zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 4720662d (ceph): rgw: update bucket index marker before skipping entries
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision dd490b67 (ceph): rgw: merge related fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 0b5cdc31 (ceph): rgw: take a lease before syncing bucket shard
This is needed for having multiple rgws running on the same zone
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 5c96534a (ceph): rgw: data shard sync locking
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 6494347d (ceph): rgw: realm pull also pulls period
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b8dcb667 (ceph): rgw: avoid unneeded yield
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision b9fbe050 (ceph): rgw: keep track of how busy a cr stack is
this can give indication about crs that aren't structured correctly.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 52486a96 (ceph): rgw: data sync, don't yield when spawning
this enables us to filter out duplicate keys without worrying about races, since
spawned crs will only be executed on...
Yehuda Sadeh
12:13 AM Revision 8b9cd668 (ceph): rgw: forward bucket creation removal if it's not meta master
We can be in the master zonegroup, but not the meta master -- in which case
we still need to forward the request to t...
Yehuda Sadeh
12:13 AM Revision f00585f0 (ceph): rgw: incremental sync, skip non-complete entries early
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 2108b2d1 (ceph): rgw: remove incorrect conn assignment
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 36e5ded2 (ceph): rgw: fix call to index_key_to_marker()
was passing variables in the wrong order
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision e08eb9c1 (ceph): rgw: don't spawn multiple concurrent object sync for same object
Either mark the current running operation to retry, or wait for it to finish
(if it's not doing the same operation).
...
Yehuda Sadeh
12:13 AM Revision 3b41d87f (ceph): rgw: create a unique zone pool names
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision efe8d9d4 (ceph): radosgw-admin: zone set add a check for zone name in json
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision eca0bb84 (ceph): rgw: use zonegroup id for location constrain
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9dccf6e4 (ceph): radosgw-admin: clean backward support for region in the cli
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 6a31379f (ceph): rgw: fix setting of rgw_zonegroup from rgw_region
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 706a194d (ceph): rgw: remove run context when finished running
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 44194c01 (ceph): rgw: keep status and history in coroutine
will replace the report container stuff
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 637bd560 (ceph): rgw: remove sync reporting
will use the cr reporting framework instead
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision fa5b36c9 (ceph): rgw: start annotating coroutines status and description
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 0efd1ff3 (ceph): rgw: more coroutines annotation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 67fa54fd (ceph): rgw: data sync, only use complete log entries
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 94ad24ae (ceph): rgw: rework set_description(), set_status()
make it easier to construct description, status info
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision d6597be6 (ceph): rgw: cancel index operation if delete got ENOENT
Should mark the operation as canceled, so that sync followers don't try to
apply it.
Signed-off-by: Yehuda Sadeh <ye...
Yehuda Sadeh
12:13 AM Revision 968cc6b4 (ceph): rgw: start moving report into coroutines
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d920dab8 (ceph): rgw: add locking to coroutines reporting
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1e0ac526 (ceph): rgw: hook cr managers to admin socket
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 21eaefac (ceph): rgw: admin socket related fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 28308458 (ceph): radosgw-admin: allow region use for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 24e1a4e9 (ceph): rgw: handle the case of non exisiting zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision b8eb5bd0 (ceph): rgw: more on fix for g_ceph_context shutdown
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 085ee732 (ceph): rgw: track all stacks, not just scheduled
And don't expand spawned stacks out of existing cr. This flattens the
admin socket output.
Signed-off-by: Yehuda Sad...
Yehuda Sadeh
12:13 AM Revision 124cf065 (ceph): rgw: remove epoch and duplicates from list_periods
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision edc24bf1 (ceph): rgw: fix assert on shutdown by keeping g_ceph_context around longer
RGWRealmWatcher and friends are on the stack in main(), so we can't drop
the last ref on g_ceph_context until their d...
Casey Bodley
12:13 AM Revision 7f439b1b (ceph): radosgw-admin: replace region with zonegroup in the help file
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 5aa81b97 (ceph): ceph_json: add deque encode/decode
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1c6ac7bb (ceph): rgw: framework for per-rgw sync status reporting
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 961e602d (ceph): rgw: start hooking sync report
also multiple fixes around the report tool
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision f5f05ba7 (ceph): rgw: more metadata sync reporting
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 9ecd08fd (ceph): rgw: RGWRealmWatcher supports multiple watch types
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 22fca7eb (ceph): rgw: RGWPeriodPusher shares periods between zones/groups
RGWPeriodPusher implements the RGWRealmWatcher interface to get
notifications for new periods. when it discovers tha...
Casey Bodley
12:13 AM Revision 87ef103e (ceph): rgw: register RGWPeriodPusher with RGWRealmWatcher
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision cd1b46da (ceph): rgw: allocate a larger buffer for full sync omap oid
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision aa8a1ebd (ceph): rgw: call drain_all() before returning from some crs
spawned crs are still using marker_tracker, need to drain_all() as
we destroy it in the destructor.
Signed-off-by: Y...
Yehuda Sadeh
12:13 AM Revision c54a99ff (ceph): rgw: fix compilation error on i386
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision f20c0ac8 (ceph): rgw: fix compilation error in RGWPeriodPusher::handle_notify
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9122fab4 (ceph): rgw: fix for decode of ZoneGroup id
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision abec368e (ceph): rgw: fix typo in RGWPeriod::update
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 5adae5b8 (ceph): rgw: add RGWRealm::notify_new_period()
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision ac18d0ce (ceph): rgw: keep Context for reconfig timer cancellation
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 76f811b7 (ceph): rgw: refactor reconfigure out of RGWRealmWatcher
add a RGWRealmReloader class to handle reconfiguration, and use a
Watcher interface to get notifications from RGWReal...
Casey Bodley
12:13 AM Revision cf8b1b2f (ceph): rgw: period push succeeds even if it isn't a new period
when pushing periods between zones, we need a successful result to
signal that we can stop sending the period
Signed...
Casey Bodley
12:13 AM Revision e836b368 (ceph): rgw: rename RGWRealmReloader::FrontendPauser to Pauser
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 1297b373 (ceph): radosgw-admin: add --zone-new-name to usage
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d065ef49 (ceph): rgw: fix RGWSystemMetaObj::rename
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 396bbb47 (ceph): rgw: we need to rename the zone inside the zonegroup too
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 521fb06a (ceph): rgw: data sync marker tracker, don't assert
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 155ab741 (ceph): rgw: cr call() doesn't return a value
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision f75388a9 (ceph): rgw: data sync fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 10171dcf (ceph): rgw: fetch bucket instance info if doesn't exist
when doing data sync. This handles a race in which we try to sync data
of bucket instance before fetched its metadata...
Yehuda Sadeh
12:13 AM Revision 29496f0f (ceph): rgw: clarify log message
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8c11019b (ceph): rgw: start marker tracker sync entry can fail
We might hit duplicate entry, just skip it, don't assert.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 4f17bbb5 (ceph): rgw: translate source_zone param into source zone id
operations are done using the zone id, not the zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 9fc032f4 (ceph): rgw: use correct connection for certain data sync operations
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1aabaafe (ceph): rgw: init num shards if sync status did not exist
in data sync process
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 0cf3c913 (ceph): rgw: special handling of 'null' object version
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision fdbb9681 (ceph): rgw: full data sync, pass correct op
Need to specify appropriate op (depending on whether object is
versioned or not versioned).
Signed-off-by: Yehuda Sa...
Yehuda Sadeh
12:13 AM Revision dcac9ba4 (ceph): rgw: initialize data sync if needed
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision dac0ed9e (ceph): rgw: data sync CR retry after specific errors
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision f5a07532 (ceph): rgw: backoff mechanism for data sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 77072341 (ceph): rgw: move code around
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 35ffcff1 (ceph): rgw: more backoff related changes and fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 8166ac43 (ceph): rgw: don't force pool names to start with periods
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 2bfd66ea (ceph): rgw: remove include to <boost/asio/coroutine.h>
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 209608a9 (ceph): rgw: remove include to <boost/asio/coroutine.h>
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 7942c937 (ceph): rgw: fix compilation with older boost versions that don't have asio cor...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision a958be00 (ceph): rgw: coroutine manager returns ECANCELED when going down
RGWRemoteMetaLog::run_sync() was getting stuck in an infinite loop after
a call to RGWCoroutinesManager::stop(). ins...
Casey Bodley
12:13 AM Revision d79fe697 (ceph): rgw: init REST connection by zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 21347a5c (ceph): rgw: keep timestamp stats in incremental sync position data
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision fcc6b8e9 (ceph): rgw: initialize data member
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 62681589 (ceph): rgw: add make_param_list() helper
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision e81c1ac9 (ceph): rgw: RGWRESTPostResource takes param_list_t for RGWPostRESTResourceCR
RGWPostRESTResourceCR needs to make a copy of the parameters given to
its constructor, because it doesn't use them un...
Casey Bodley
12:13 AM Revision 03282533 (ceph): rgw: apply RGWRESTReadResource::wait_bl() fix to PostResource as well
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 1a0e74bb (ceph): rgw: use boost::intrusive_ptr for http_op ref counting
this fixes a segfault in the RGWPostRESTResourceCR::request_complete()
error path, which accessed http_op after calli...
Casey Bodley
12:13 AM Revision 86148c47 (ceph): rgw: shutdown lease CR on mdlog inc sync failure
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 28ba9af0 (ceph): rgw: update the correct shards when doing full sync
The shard we use for each entry (either meta, or data) needs to be selected
correctly to match the different logs we ...
Yehuda Sadeh
12:13 AM Revision 7c435548 (ceph): rgw: keep sync progress info for full sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 49bf8ba1 (ceph): rgw: show data full sync stats
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 0c0c9960 (ceph): rgw: fix bucket creation and deletion when there is no realm or period ...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2a22b2b7 (ceph): rgw: realm watcher locks mutex for SafeTimer::shutdown()
this fixes an assert() on shutdown
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
12:13 AM Revision 1f485dd7 (ceph): rgw: bucket ops, obj create and obj delete should check to see if bucke...
rgw_build_policies set the bucket_exists flag
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:13 AM Revision 91de9b51 (ceph): rgw: workaround to clear location constrain when using default zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 384df8d1 (ceph): rgw: RGWRestConn uses vector instead of map
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision d585436d (ceph): rgw: move RGWPostRESTResourceCR to rgw_cr_rest.h
for use by RGWRealmPusher
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
12:13 AM Revision a1816d97 (ceph): rgw: use insert to copy containers in rgw_rest_conn
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 6c1f3761 (ceph): rgw: add typedef for rest parameter lists
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 953086a2 (ceph): rgw: handle transient error in md full sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d047763f (ceph): rgw: move children collection to other method
and call it again instead of just draining at the end
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 105f8a07 (ceph): rgw: rework incremental md sync error handling
similar to what we do with the full md sync. Identify transient
errors, and if so return -EAGAIN so that caller would...
Yehuda Sadeh
12:13 AM Revision 3fa1cc7b (ceph): rgw: move data sync init into the processing thread
that way we don't depend on remote peer to be available
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 111cb41c (ceph): rgw: fix data sync initialization
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 9acb6296 (ceph): rgw: allow creating a bucket without current period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d12da625 (ceph): rgw: use default zonegroup and zone in init_complete
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 41bbe95a (ceph): rgw: cleanup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 50fd0bd0 (ceph): rgw: return -EAGAIN on a connection related http failure
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision c8cd83c2 (ceph): rgw: multiple sync initialization and error handling fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision fbdd3ad2 (ceph): rgw: get some errors from req_data
When reading request status, we need to check with req_data first,
since it might have failed before we even got the ...
Yehuda Sadeh
12:13 AM Revision 4bbfe637 (ceph): rgw: rework error handling when syncing a single md entry
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 91761d1d (ceph): rgw: a coroutine util function to collect a single stack
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 1a92c4b2 (ceph): rgw: RGWCoroutine::spawn() returns stack
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision a4cec387 (ceph): rgw: coroutine drain fixes
Init drain_cr() before draining, otherwise we wouldn't be able to
call it a second time
Signed-off-by: Yehuda Sadeh ...
Yehuda Sadeh
12:13 AM Revision 31913902 (ceph): rgw: RGWPeriod stores sync_status as vector of strings
rgw_meta_sync_status keeps the shards in a std::map, but a std::vector
is more appropriate when all keys are present....
Casey Bodley
12:13 AM Revision ca5e00b1 (ceph): rgw: create RGWMetaSyncEnv, use it as container to sync env
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d8dcf9b3 (ceph): rgw: move sync_oid() and shard_object_name() to sync env
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 96e38506 (ceph): rgw: mdlog full sync, yield for each entry
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 7be92686 (ceph): rgw: init sync env
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 97029664 (ceph): rgw: error out if failed to build md sync index
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 09112f25 (ceph): rgw: fix the mdlog sync lock control flow
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision e99da775 (ceph): rgw: add backoff and restart to meta sync
also fix lease cr lifecycle
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 580e017d (ceph): rgw: account total number of metadata entries for sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 55a5addb (ceph): rgw: add missing rgw_meta_sync_status.h to the Makefile
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 790eeb5d (ceph): rgw: add rgw_rest_realm.h to the Makefile
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision de748e53 (ceph): make: fix link of ceph_test_cls_rgw_meta
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 99ef6fc5 (ceph): rgw: store metadata sync status on period commit
store the new master zone's sync status with each new period
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
12:13 AM Revision f2424a16 (ceph): rgw: update realm_id when converting a region to zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ac6dcc78 (ceph): rgw: add RGWRegionMap for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2650b3b0 (ceph): rgw: update current_period after adding converted zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 6d65dac2 (ceph): rgw: add support for region format in RGWOp_ZoneGroupMap_Get
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e92c9155 (ceph): rgw: create a realm in case of pervious regions configuration
The realm name is concatanation of master region and master zone and its
id is the mds sume of the name
Signed-off-b...
Orit Wasserman
12:13 AM Revision 261e6436 (ceph): rgw: md full sync backoff
Still need to work this out correctly
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 2991ffb1 (ceph): rgw: use set_cr_error() and set_cr_done() instead of set_state()
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision afc3194b (ceph): radosgw-admin: remove period activate in favor of commit
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision f81e72fe (ceph): rgw: RGWHTTPManager dtor stops background thread
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision c010a3c0 (ceph): rwlock: add prioritize_write flag to prevent write starvation
RWLock's constructor takes an additional 'prioritize_write' flag, which
defaults to false. when enabled, this adds t...
Casey Bodley
12:13 AM Revision 30f74854 (ceph): rgw: add pause/unpause to RGWFrontend interface
RGWProcessFrontend implements pause/unpause through the ThreadPool
interface. RGWMongooseFrontend implements them wit...
Casey Bodley
12:13 AM Revision 4d72adce (ceph): rgw: add realm control object for watch/notify
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 40608a5f (ceph): rgw: period commit calls notify_zone
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision ab6c9213 (ceph): rgw: RGWRealmWatcher to reload RGWRados on changes
adds RGWRealmWatcher, which watches the RGWRealm control object for
changes. in a separate thread, all frontends are...
Casey Bodley
12:13 AM Revision ae729aa7 (ceph): rgw: add converted regions into the current period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 29779964 (ceph): radosgw-admin: add realm pull command
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 51133f1f (ceph): rgw: RGWPeriod accessors are const
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 25c14c8c (ceph): rgw: period push handler updates current period/epoch
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision d9a19c75 (ceph): rgw: add RGWPeriod::commit()
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision c38a7812 (ceph): rgw: period push handler supports commit
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 132c2a18 (ceph): radosgw-admin: add 'period commit' command
on the master zone, store the new period locally and notify the zone for
restart. on other zones, send a 'period pus...
Casey Bodley
12:13 AM Revision 6b1cb5dc (ceph): radosgw-admin: add --commit flag for period update
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 3b019faf (ceph): radosgw-admin: add 'period update' to usage
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 55dfc851 (ceph): rgw: omit epoch in oid for staging period
there should only be one staging period object, so the epoch is
an unnecessary part of its oid. and for period commit...
Casey Bodley
12:13 AM Revision fc483c82 (ceph): rgw: period allows setting id, epoch, latest_epoch
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision a69e69aa (ceph): rgw: move period Ops to rgw_rest_realm.cc
this removes the handling of /admin/config?type=period
Signed-off-by: Casey Bodley <cbodley@redhat.com>
Casey Bodley
12:13 AM Revision 7623e437 (ceph): rgw: add realm params to period pull
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 5704bcd1 (ceph): rgw: add op for GET /admin/realm
this is for the radosgw-admin 'realm pull' command, which gets the realm
object by name or id
Signed-off-by: Casey B...
Casey Bodley
12:13 AM Revision ee6d76f4 (ceph): radosgw-admin: add send_to_remote_or_url() helper
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 70a2b935 (ceph): rgw: multiple init metadata sync locking fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 76bfd7b0 (ceph): rgw: initialize rest connection if no period
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 092303ab (ceph): rgw: a bit better coroutine related logging
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision f055fae8 (ceph): rgw: guard metadata sync initialization step
Guard the fetch-meta stage
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 899ff3dd (ceph): rgw: guard metadata full/incremental sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision c7f77c66 (ceph): rgw: RGWHandler_Config should assume empty type is zonegroupmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d3b3ddae (ceph): rgw: fix comparison typo in RGWRados::init_complete
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 0174086d (ceph): rgw: RGWRemoteMetaLog ctor sets async_rados=nullptr
RGWRemoteMetaLog::init() is not called in all error paths, so we need to
start with nullptr
Signed-off-by: Casey Bod...
Casey Bodley
12:13 AM Revision ea60f7e2 (ceph): rgw: RGWRados internal zone should be protected and not accessed directly
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e9044fc0 (ceph): rgw: RGWRados zonegroup and zone_public_config should not be accessed d...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ae807420 (ceph): rgw: use default zone in case there is no period or zone name
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision db6647d0 (ceph): radosgw-admin: fix zone get command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c16caa01 (ceph): rgw: update new name after converting region to zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 697753a0 (ceph): rgw: backward compatability update_name for existing zones
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 3263c2e6 (ceph): cmake: move link dependencies to rgw_a
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:13 AM Revision 8e77fa6f (ceph): rgw: remove zonegroup_map from RGWRados
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision f5857c72 (ceph): rgw: no need to store or update zonegroupmap
Structure and command will be kept for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:13 AM Revision 4c6a01af (ceph): radosgw-admin: zonegroupmap get should no error if no realm or period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2441b7cd (ceph): rgw: add support to zonegroupmap set
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c11a5a50 (ceph): rgw: convert regionmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 3468dd6d (ceph): rgw: fix RGWSystemMetaObj::init by passing old_format flag
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision bba68536 (ceph): rgw: use current_period zonegroup and zone when exists
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 4195f8b0 (ceph): rgw: read local zonegroup and zone only when needed
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision fb2b8f2f (ceph): rgw: update rest connections from the current period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 8d323925 (ceph): rgw: can set zone read-only, can set zonegroup id
and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 680e58e6 (ceph): rgw: fix log message
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 6a403507 (ceph): rgw: don't read/init sync status if meta master
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision d97718d4 (ceph): CMake - add check for libcurl
Signed-off-by: Daniel Gryniewicz <dang@fprintf.net> Daniel Gryniewicz
12:13 AM Revision 78294dd1 (ceph): radosgw-admin: zone add command should be zonegroup add
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d2109c73 (ceph): rgw_admin: update zone set
zone set was broken, now it can update the zone params correctly. Also
inheriting the id from the current zone if exi...
Yehuda Sadeh
12:13 AM Revision d1e32a87 (ceph): rgw: can override master zone config
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 4a5d77aa (ceph): rgw: get_predefined_name should get the ceph context
so it can be called before object init
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:13 AM Revision 4733ccba (ceph): rgw: zonegroup and zone should not be accessed directly
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision fa2dc6a1 (ceph): rgw: read current period during init
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 93bddf9f (ceph): rgw: create default zonegroup for first time run of the gateway
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 46b268cd (ceph): rgw: auto create placement target params
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 4d484019 (ceph): rgw_admin: period update command
A command that creates staging period data out of current local data
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 78f53f3f (ceph): rgw: stuff more info into the period
and don't update the current period when adding zone, this
will be done through the staging period.
Signed-off-by: Y...
Yehuda Sadeh
12:13 AM Revision a2e7cd58 (ceph): rgw: update master zone
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 526421ac (ceph): rgw: run sync thread only when number of zones > 2 and master is config...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 8e8f13d1 (ceph): rgw: set first created realm as default
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 448674b6 (ceph): rgw: prefix default pools with zone name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision c497facd (ceph): rgw: set first created zone as default
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 12239dd5 (ceph): rgw_admin: can update zonegroup endpoints, is_master
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 56bbadf2 (ceph): rgw_admin: can set zonegroup api name
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 2ae0f41e (ceph): rgw_admin: can config access/secret key for zone
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 66041ae8 (ceph): rgw: --rgw-zone and --rgw-zonegroup use names not id
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision eeaf75da (ceph): rgw_admin: don't require zonegroup id on some commands
should be able to get the default one
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 212d8f48 (ceph): rgw_admin: zone name need to be provided on zone create
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision ee29f62b (ceph): rgw_admin: zone delete doesn't require zonegroup
iterates through all the zonegroups and remove it
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 5f774a1d (ceph): rgw_admin: realm set-default -> realm default
to be in line with the other default commands
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision a325dd5e (ceph): rgw: use --rgw-realm instead of --realm
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 702d5b05 (ceph): rgw: period get does not require specifying period id
Can return the current period
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision 369e484e (ceph): rgw: period oid doesn't include realm id
So that realm id is not a dependency for reading period.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision fa12a072 (ceph): radosgw-admin: zone get and rename commands should work without zonegro...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ba629cdb (ceph): rgw: update rest_conn_master when adding a new master zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision fc3df345 (ceph): rgw: update zone endpoints when creating a new zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision fd315d9b (ceph): rgw: update zonegroup endpoints when creating it
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 65775645 (ceph): rgw_admin: don't use --zone, use --rgw-zone
--rgw-zone is tied to ceph.conf, and what we've always been using
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:13 AM Revision a12ec59f (ceph): rgw_admin: a zone default command, and other changes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 962eb3cd (ceph): rgw: don't use --zonegroup, use --rgw-zonegroup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision f267df2f (ceph): radosgw-admin: check legal input for zone modify command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e79171cf (ceph): radosgw-admin: check for legal input for zonegroup default command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 01e342fe (ceph): radosgw-admin: check for valid input for zonegroup modify command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 2a947bfe (ceph): radosgw-admin: check for valid input in zone add command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9638a4ee (ceph): radosgw-admin: check for valid input in zone delete command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c9269031 (ceph): rgw: print zone name and id in the begining of the dump
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ef641572 (ceph): rgw: remove is_master flag from zoneparams
make it easier to change master zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:13 AM Revision 452c8eed (ceph): radosgw-admin: fix zonegroup and master usage text
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e65afc56 (ceph): rgw: add zonegroup modify command to allow setting/clearing zonegroup m...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9954bb5c (ceph): rgw: add zone modify command to change master zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 4517bf77 (ceph): rgw: fix RGWZone::dump
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 824a05bf (ceph): radosgw-admin: use realm_id from zonegroup if not provided
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9dfbae6d (ceph): rgw: fix compilation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision 3bd29b4e (ceph): rgw: zone config related changes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:13 AM Revision bc70d67f (ceph): rgw: move dump functions into rgw_json_enc.cc
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 189c1b13 (ceph): rgw: move rgw_meta_sync_status, rgw_meta_sync_marker and rgw_meta_sync_...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 98178094 (ceph): rgw: add decode_json method to rgw_meta_sync_status structures
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 58065620 (ceph): rgw: store latest sync status when activating a period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c05e6321 (ceph): radosgw-admin: fix zone create to check for zonegroup name
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c1e1f12f (ceph): rgw: remove debug message from decode_zones
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision bded7eb7 (ceph): rgw: add RGWRegionMap for backward support
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 220e8e86 (ceph): rgw: add backward support for old regionmap format
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 852ead59 (ceph): rgw: fix whitespace and remove debug messages
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9272d7ef (ceph): rgw: add period_map to period dump and encode_json
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e18b72f7 (ceph): rgw: add bucket_quota to RGWRegionMap::encode_json
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 208a3873 (ceph): rgw: don't try to unregister request on destructor
We already unregister the request earlier, and the locking here
was weird and wrong anyway.
Signed-off-by: Yehuda Sa...
Yehuda Sadeh
12:13 AM Revision d12836d0 (ceph): radosgw-admin: fix zonegroup default
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision dbd70b04 (ceph): radosgw-admin: zone create should update zonegroupmap for non standalon...
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 57cb5184 (ceph): rgw: add id to RGWZone dump and decode_json functions
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision e020790a (ceph): radosgw-admin: zone set should handle old format json (without name or id)
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 6c45a2ad (ceph): rgw: systemmetaobj::create don't generate random id if id is provided
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 6705fe73 (ceph): rgw: rgwzone decode_json should handle empty id for backward compatabiltiy
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 1882243b (ceph): radosgw-admin: remove extra print from zonegroup set command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 3d9eb7f3 (ceph): radosgw-admin: add --rgw-zone for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 117bb62d (ceph): rgw: backward compatabilty for zone set command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c3907af4 (ceph): radosgw-admin: fix zonegroupmap update
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 674087ec (ceph): radosgw-admin: zonegroup set needs to update zonegroupmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision a320a442 (ceph): radosgw-admin: realm set should update zonegroup map
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9082ed6c (ceph): radosgw-admin: zone set command should update zonegroupmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 922721cc (ceph): radosgw-admin: add --rgw-zonegroup for backward compatability
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 23cafb0e (ceph): rgw: use encode_map for zonegroups
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 0e4cdb65 (ceph): radosgw-admin: update zonegroupmap when adding a zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 76df9117 (ceph): rgw: add realm_id to zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision cd120d84 (ceph): radosgw-admin: use zonegroup realm id in zone add command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision eb6fe357 (ceph): radosgw-admin: use the correct realm id when creating a new zonegroup
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d6d57aeb (ceph): rgw: use realm provided in the command line
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 695b48be (ceph): rgw: fix zonegroupmap initialization in init_complete
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 265e0933 (ceph): radosgw-admin: update zonegroupmap when activating a period
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 6f80c92b (ceph): rgw: fix realm create
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d178f99b (ceph): rgw: fix zonegroup create
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ae7f8042 (ceph): rgw: add zonegroup_map period update
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 88515686 (ceph): rgw: add period_map to encode/decode
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 84f9a26c (ceph): rgw: update zonegroupmap when creating new realm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision fe8c3440 (ceph): rgw: fix zonegroup update
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 60f948d1 (ceph): radosgw-admin: fix error messages for zonegroup create
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 3c45e433 (ceph): rgw: fix init_complete when there is no realm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 993481a7 (ceph): rgw: cleanup period init
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision c04e688f (ceph): rgw: move zonegroup data into rgwperiodmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 10adb672 (ceph): rgw: zonegroup map contains a map of periods
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision b8b237a8 (ceph): rgw: add realms to zonegroupmap
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9af5152d (ceph): rgw: fix encoding and decoding of realms and periods
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 11500473 (ceph): rgw: add zonegroupmap realm update
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 66eb0200 (ceph): rgw: Rename Region to ZoneGroup only internal structures and class
User visuable are not changed: admin commands, jsons and rados objects names
Signed-off-by: Orit Wasserman <owasserm...
Orit Wasserman
12:13 AM Revision 9451af69 (ceph): cmake: fix erasure-code
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision d4b58baa (ceph): rgw: RGWZoneGroup should inheirt from RGWSystemMetaObj
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 9a0d4170 (ceph): rgw: RGWZoneParams should inherit from RGWSystemMetaObj
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision ea0a4202 (ceph): radosgw-admin: add zone create, delete and rename commands
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 0d83cfe3 (ceph): rgw: add use_next_epoch method
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:13 AM Revision 660fc7ca (ceph): rgw: use RGWZoneGroupMap in RGWPeriod
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 966dd3ee (ceph): rgw: propagate olh_epoch for obj sync correctly
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 3c6e5e7b (ceph): cls/rgw: rgw_bi_log_entry::decode_json(), decode ver
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision beac57f2 (ceph): rgw: don't require system pools to start with a period
Make sure cache operations are being done on system objects.
Separate calls where needed to make sure that separate p...
Yehuda Sadeh
12:12 AM Revision 9744de72 (ceph): rgw: add new class to create resource request
RGWRESTReadResource holds the request input and output. Previously
we were using stack variables that couldn't be use...
Yehuda Sadeh
12:12 AM Revision 94db324c (ceph): rgw: async rados requests through a work queue
Tie in the async rados requests to the async framework.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision daaf7b41 (ceph): rgw: Add RGWNameToId and RGWDefaultSystemMetaObjInfo
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 1680bb75 (ceph): rgw: Add RGWSystemMetaObj class
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc
Orit Wasserman
12:12 AM Revision a8d765d2 (ceph): rgw: Add period admin commands and rest api to handle period
the new commands are prepare,delete, get, activate, pull and push
Signed-off-by: Orit Wasserman <owasserm@redhat.com...
Orit Wasserman
12:12 AM Revision 0bdf1505 (ceph): rgw: don't create connection object for zone without endpoints
warn about it though
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 01608a84 (ceph): rgw: minor cleanup
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision beba94bc (ceph): rgw: data sync locking fixes
and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision ddfb0193 (ceph): rgw: tie incremental data sync
and other fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 9c6a962f (ceph): rgw: handle object removal in incremental data sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 5e368857 (ceph): rgw: fetch_remote_obj() uses correct version_id
This fixes one aspect of the versioned objects sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 6e243c34 (ceph): cls_rgw: reset dirent flag appropriately
Need to mark dirent as versioned if it has instance.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 8ff39798 (ceph): rgw: incremental data sync
still needs some more work, but basic structure is there.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 579bd3a1 (ceph): rgw: incremental data sync adjustments
update marker, close a race
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision c43f7362 (ceph): rgw: only account actual io for coroutine io window
stacks that are put in interval_wait shouldn't be accounted.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 35d48c04 (ceph): rgw: eliminate window for data sync marker
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision b334c03b (ceph): rgw: work towards datalog sync notification
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 5a7e4e32 (ceph): rgw: async data changes notifications
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision f6788b75 (ceph): rgw: multiple fixes related to coroutines draining
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 390f64a0 (ceph): rgw: data sync work
Instead of just keeping map of bucket instances, keep map of all the shards.
Also prepare the CRs that will call into...
Yehuda Sadeh
12:12 AM Revision 1403b23c (ceph): rgw: move top level data sync function into coroutine
So that it can be called from a coroutine
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 04cd5921 (ceph): rgw: data sync, spawn sync on all shards
full sync should work now
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 3dff6252 (ceph): rgw: revive io window
and several other fixes. Don't send unbounded number of IO requests,
send back http related errors (that didn't have ...
Yehuda Sadeh
12:12 AM Revision cf3bbddc (ceph): rgw: reduce the use of obj_ctx
Should really get rid of all the obj_ctx use, unless it's really needed. It's
not thread safe.
Signed-off-by: Yehuda...
Yehuda Sadeh
12:12 AM Revision aefa0884 (ceph): rgw: add rwlock to RGWObjectCtx
It can be used from multiple threads now.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision a8dc84e9 (ceph): rgw: fix data sync init
Need to wait for shards' status.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 9422936d (ceph): rgw: no need to yield while collecting
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision b8d57a22 (ceph): rgw: add RGWCoroutine::wait_for_child()
Will yield until one of the spawned stacks finished execution.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision c4cdb396 (ceph): rgw: finish execution when done with bucket sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 649b6723 (ceph): rgw: simplify unblocked by stack state change
If blocked by another stack that is finished, just schedule, not waiting
on IO.
Signed-off-by: Yehuda Sadeh <yehuda@...
Yehuda Sadeh
12:12 AM Revision aa829e39 (ceph): rgw: clean up child draining a bit
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 27450d72 (ceph): Revert "rgw: simplify unblocked by stack state change"
This reverts commit 8509ef5034818e163bebc8fd2de039a96b4a8f1a. Yehuda Sadeh
12:12 AM Revision cd1ad88d (ceph): rgw: move bucket shard full sync to its own coroutine
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 23e083ab (ceph): rgw: fix shard_id use
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 6b2df0e1 (ceph): rgw: init shard_id param for bucket listing
shard_id can now be specified in the bucket instance http param
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 800f391c (ceph): rgw: add rgw_bi_log_entry::decode_json
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 7cc81c47 (ceph): rgw: skeleton for bucket index incremental sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 092cf681 (ceph): rgw: url_encode http params in requests that we send
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 0f42103c (ceph): rgw: collect spawned requests before completing coroutine
Need to finish all processing before we return
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 65308b51 (ceph): rgw: fix pending operations accounting
create RGWCoroutine::num_pending() to get the number of
pending spawned coroutines.
Signed-off-by: Yehuda Sadeh <yeh...
Yehuda Sadeh
12:12 AM Revision df001d8b (ceph): rgw: can read attrs when reading system obj
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 0ffbd84f (ceph): rgw: keep bucket sync markers in object attrs
This allows to set the status separately for each of the
different stages (full, incremental), while allowing also
to...
Yehuda Sadeh
12:12 AM Revision 24373fd7 (ceph): radosgw-admin: bucket sync commands don't require bucket id
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 82db4777 (ceph): rgw: silence some verbose logs
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision e833021a (ceph): rgw: fix iteration over bucket entries in full sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 6d6cdc70 (ceph): rgw: switch sync state when done with full bucket sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 442edc82 (ceph): rgw: list bucket instance shard entries for data sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 07f3754b (ceph): rgw: fix signing for generated requests
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 4d69b8fa (ceph): rgw: extend list bucket versions api
System user can now provide 'objs-container=true' in conjuction
with 'format=json' so that response is json and entri...
Yehuda Sadeh
12:12 AM Revision cd20ec84 (ceph): rgw: bucket sync, send marker when listing bucket shard
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 8659ff19 (ceph): rgw: bucket sync fetches remote objects
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 9f63b15b (ceph): rgw: fix identification of canceled operation
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 868dccf2 (ceph): rgw: api adjustment following rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 727db686 (ceph): rgw: window of full sync operations per bucket
also store marker periodically, reuse marker logic from md sync.
Marker still needs some work.
Signed-off-by: Yehuda...
Yehuda Sadeh
12:12 AM Revision fa96d4e4 (ceph): rgw-admin: skeleton for data sync commands
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 29db3ce6 (ceph): rgw: initial data sync work
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 3d49dced (ceph): rgw-admin: data sync status command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 5fb66152 (ceph): rgw-admin: implement data sync init
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 2b4de2d2 (ceph): rgw: initial work on data sync run
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision f0e351d4 (ceph): rgw: per-bucket instance shard state
add 'radosgw-admin bucket sync init' command
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision f5a27f9d (ceph): rgw: read bucket sync status
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision c90d7cb5 (ceph): cls/rgw: add an objclass method to check obj mtime
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 0f7e3e0a (ceph): rgw: add mtime check to object removal if needed
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 9751d612 (ceph): rgw: add no-precondition-error http param for object delete
In case we don't want to get an error response when a precondition
failed.
Signed-off-by: Yehuda Sadeh <yehuda@redha...
Yehuda Sadeh
12:12 AM Revision a3b0d200 (ceph): rgw: fix time parsing for delete precondition
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 14cb57a0 (ceph): rgw: propagate rgwx-bucket-instance for copying objects
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 15c530b4 (ceph): build: add cls_timeindex_client to DENCODER_DEPS
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision 2aa6fd94 (ceph): radosgw-admin: switch mdlog sync commands to metadata sync
radosgw-admin mdlog sync init -> metadata sync init
etc.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 8813a440 (ceph): rgw: add rgwx-copy-if-newer http header
Similar to IF_MOD_SINCE, but does not take a time argument, and should
protected against races (not there yet).
Sign...
Yehuda Sadeh
12:12 AM Revision 27946e8b (ceph): rgw: fix if-modified-since boundary
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 20d24e96 (ceph): rgw: translate http error 304 to appropriate status
So that we can return the appropriate response on a conditioinal multi
zone copy operation.
Signed-off-by: Yehuda Sa...
Yehuda Sadeh
12:12 AM Revision fe9c64b7 (ceph): rgw: identify racing writes when using copy-if-newer
When copying an object from a different zone, and copy-if-newer is
specified, if the final meta write is canceled che...
Yehuda Sadeh
12:12 AM Revision babbf672 (ceph): rgw: adjust calls
as part of a rebase work
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision e36db984 (ceph): rgw: more api adjustments
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision fc01f16f (ceph): rgw: add DELETE_IF_UNMODIFIED_SINCE header to obj delete
Will delete object only if not modified after the specified time. Still
need to close a race where object is modified...
Yehuda Sadeh
12:12 AM Revision 413ac34b (ceph): rgw: fix uninitialized variable
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 654f203a (ceph): rgw: bilog info can get shard id
We would like to be able to get bilog info by shard if needed.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 9cb1d6f6 (ceph): rgw: get_bucket_stats() returns a plain marker if shard specified
E.g, will return 00001234 vs. 2#00001234 if shard 2 specified.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 359325b5 (ceph): rgw: system user can list bucket shard
By setting the HTTP-Rgwx-Shard-Id header to the shard id.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 22f766eb (ceph): rgw: dump internal object tag when system user lists bucket
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 142c5a83 (ceph): rgw: access zone.name, zonegroup_name through accessor
fix as part of a rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 5d924904 (ceph): rgw: make rgw_user::empty() const
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision e6548ecd (ceph): rgw: rearrange full metadata sync order
Users need to exist before their buckets, better have bucket instances
before bucket entry points
Signed-off-by: Yeh...
Yehuda Sadeh
12:12 AM Revision f2eb0d75 (ceph): rgw: move code around
move code from rgw_sync.cc to rgw_cr_rados.{h,cc}
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 9ca266a1 (ceph): rgw: move more code around
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 07feb134 (ceph): rgw: coroutine stack wait util
Instead of using a separate coroutine for waiting on
a condition.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision be3e2727 (ceph): rgw: use internal wait instead of special coroutine
Instead of using a special coroutine that spawns a separate thread
and waits on a condition, use the internal corouti...
Yehuda Sadeh
12:12 AM Revision 9ab02a8c (ceph): rgw: trivial fix
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 73a21475 (ceph): rgw: move more code
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision a848353e (ceph): rgw: simple thread base class
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision f7ac1222 (ceph): rgw: run and stop sync thread
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 18a9a436 (ceph): rgw: a few sync thread init/finalization fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 3e7b86e6 (ceph): rgw: wake up appropriate shard sync handler
When receiving notification about modified shard, wake up the appropriate handler
Signed-off-by: Yehuda Sadeh <yehud...
Yehuda Sadeh
12:12 AM Revision 4b80edb1 (ceph): rgw: http client req handling fixes
The error buffer for the async requests was on the stack, and not
on the request structure. Some other use after free...
Yehuda Sadeh
12:12 AM Revision 5cc80b0e (ceph): rgw: fix shutdown
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 6adf75c2 (ceph): rgw: trivial fixes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 766d52ae (ceph): rgw: keep track of modified mdlog shards
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 30bf776a (ceph): rgw: handle mdlog post request
with 'notify' subresource. Will be used later for handling notifications
about modified mdlog shards.
Signed-off-by:...
Yehuda Sadeh
12:12 AM Revision 4ce51091 (ceph): rgw: periodical thread that tracks mdlog changes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 0f65f565 (ceph): ceph_json: add json encoder / decoder for std::set
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision c26ff96a (ceph): rgw: add simple POST requests interfaces
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision a7a9ca70 (ceph): rgw: send mdlog changes notifications to zones
Will probably need to rework this, as it is now zones may interfere
with each other which is not optimal.
Signed-off...
Yehuda Sadeh
12:12 AM Revision 11dd2b86 (ceph): rgw: decode mdlog notification shards
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 669b9fc5 (ceph): rgw: RGWRESTSimpleRequest::forward_request params
forward_request() uses new_info.build_from(info) to initialize the new
request info. but this doesn't copy the RGWHTT...
Casey Bodley
12:12 AM Revision 7a760fe7 (ceph): radosgw-admin: fixes for period push/pull
for send_to_remote_gateway() to work, the push and pull commands had to
be moved to the not-raw-storage section, beca...
Casey Bodley
12:12 AM Revision 9da07070 (ceph): radosgw-admin: period pull supports --url
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision c6be10df (ceph): rgw: add master flag to zonegroup create command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision c4795043 (ceph): radosgw-admin: allow creating a zone without a zone group
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 1f0c2c57 (ceph): rgw: Add zone add command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 390e1e1f (ceph): rgw: create the first period when creating a new realm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision b9e51fc0 (ceph): rgw: fix period init and activate
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 7b81c27d (ceph): radosgw-admin: add json output to create commands
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision 68232485 (ceph): radosgw-admin: add realm set command
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision a0d76ec5 (ceph): rgw: fixes for RGWZoneGroupMap::decode_json
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision dfadc9f7 (ceph): rgw: add handler for /admin/realm/period
the handler returns the existing RGWOp_Period_Get/Post ops from
rgw_rest_config.h
Signed-off-by: Casey Bodley <cbodl...
Casey Bodley
12:12 AM Revision be17da5e (ceph): rgw: delay allocation of RGWPeriod
RGWOp_Period_Get and _Post don't have a valid RGWRados pointer until
they get the init() call, so the constructors we...
Casey Bodley
12:12 AM Revision 6693737f (ceph): rgw: POST /admin/realm/period reads in json data
Signed-off-by: Casey Bodley <cbodley@redhat.com> Casey Bodley
12:12 AM Revision 4a2f1681 (ceph): common: expose Formatter::flush to derived classes
class Formatter declares both a 'virtual void flush(ostream&)' and a
'void flush(bufferlist&)'. however, because its ...
Casey Bodley
12:12 AM Revision 750074b2 (ceph): radosgw-admin: Add period list command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 589fe2ed (ceph): radosgw-admin: Add master_zonegroup and master_zone to period prepare
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 92504ddc (ceph): rgw: Add realm list-periods command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 27fda3aa (ceph): rgw: realm id and epoch should be part of period oid
fixes period get and activate command
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Orit Wasserman
12:12 AM Revision d259066f (ceph): rgw: fix realm list-periods
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 7f683ed4 (ceph): rgw: update period predecessor when it is activated
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 297de47e (ceph): rgw: use id for master zone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 550d84f6 (ceph): rgw: RGWZoneParams should inherit from RGWSystemMetaObj
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 12ce5128 (ceph): radosgw-admin: add zone create, delete and rename commands
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision ef5544fd (ceph): rgw: default zone should not be master
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 27af8930 (ceph): rgw: remove debug messages
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 3fc65d14 (ceph): rgw: fix zone set command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 8190047f (ceph): radosgw-admin: print new perion in period perpare command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 7a1cb789 (ceph): rgw: fix typo
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 10b3fe76 (ceph): rgw-admin: fix realms list
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 1adf6a5d (ceph): rgw: pass const string reference
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision f5a05674 (ceph): rgw-admin: use default realm on realm get
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 199ee222 (ceph): rgw-admin: adjustments to period get-current output
Make it output through the formatter
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 5fa07644 (ceph): rgw: Add RGWSystemMetaObj class
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
Conflicts:
src/rgw/rgw_rados.cc
Orit Wasserman
12:12 AM Revision a6acb1a0 (ceph): rgw: add id to RGWZoneParams
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision dc3feb6a (ceph): Add zone create admin command - wip
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 814fe66b (ceph): rgw: wake up wait coroutine thread on destruction
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision fe113730 (ceph): rgw: sync local mdlog if needed
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision e332d17c (ceph): rgw: fix busy wait in RGWHTTPManager
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 311c105c (ceph): rgw: don't force wait on blocked coroutines
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision fe38269b (ceph): rgw: track mdlog marker
sync entries if the sync marker is < mdlog marker, otherwise
try to fetch more entries.
Signed-off-by: Yehuda Sadeh ...
Yehuda Sadeh
12:12 AM Revision 764dc5b3 (ceph): rgw: do the actual incremental metadata sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision bd5a6b37 (ceph): rgw: update meta sync markers during full sync operation
update marker per shard, keep a window so that we don't update after each change
Signed-off-by: Yehuda Sadeh <yehuda...
Yehuda Sadeh
12:12 AM Revision 46445a65 (ceph): rgw: update global sync state after building meta indexes
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 528aff10 (ceph): rgw: switch to incremental sync when done full meta sync
each shard need to collect the coroutines it spawned before continuing.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh
12:12 AM Revision 3db4e98e (ceph): rgw: hash full sync keys to shards
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 12926239 (ceph): rgw: get remote mdlog status when initializing
Use that as the lowerbound for the meta marker when we start
the incremental sync.
Signed-off-by: Yehuda Sadeh <yehu...
Yehuda Sadeh
12:12 AM Revision 6bf77a7e (ceph): rgw: read mdlog entries for incremental sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision 8f7b6712 (ceph): rgw: poll mdlog for incremental sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> Yehuda Sadeh
12:12 AM Revision c169b75f (ceph): rgw: add id to RGWZone
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 95f71261 (ceph): rgw: RGWZoneGroup should inheirt from RGWSystemMetaObj
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision 242f2c88 (ceph): rgw: add current_period to RGWRealm
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision d07306cc (ceph): rgw: add period activate admin command and fix get current command
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision f4be2693 (ceph): rgw: Add zonegroup create, delete and rename admin commands
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
12:12 AM Revision f176c587 (ceph): rgw: add zonegroup name or id to zonegroup get and set commands
Signed-off-by: Orit Wasserman <owasserm@redhat.com> Orit Wasserman
 

Also available in: Atom