Activity
From 05/17/2015 to 06/15/2015
06/15/2015
- 10:56 PM rgw Bug #12030 (Resolved): radosgw-agent: cannot specify ipv6 destination
- Cannot specify an ipv6 address as the destination for radosgw-agent.
- 10:55 PM Bug #11548 (Resolved): "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-bas...
- commit:c0e3f8f79c6d985a13776898f43664495920d9b0 in ceph-qa-suite and commit:348a3d3c9880e7d022e71a2faafe51c8f771406e ...
- 10:48 PM Revision 0ef0cfb9 (ceph): Merge branch 'next'
- 10:47 PM Revision c0e3f8f7 (ceph): upgrade-x: use compatible rados api tests
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 10:18 PM Revision 34ba3719 (ceph): qa: add compatibility filtered rados api tests for upgrades
- Post-9.0.1, the evict op returns success when an object doesn't exist
in the cache tier. Skip the tests that are inco... - 10:17 PM Revision ef0e8e77 (ceph): qa: add compatibility filtered rados api tests for upgrades
- Post-9.0.1, the evict op returns success when an object doesn't exist
in the cache tier. Skip the tests that are inco... - 10:16 PM Revision 348a3d3c (ceph): qa: add compatibility filtered rados api tests for upgrades
- Post-9.0.1, the evict op returns success when an object doesn't exist
in the cache tier. Skip the tests that are inco... - 09:54 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- For the record http://tracker.ceph.com/issues/12029
- 09:26 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- jdillaman suggests: might be good to get librbd debug logs (“debug rbd = 20”) from qemu. Can you get that please Mehdi ?
- 09:53 PM rbd Tasks #12029 (Resolved): add qemu erasure coded pool cache tier test
- In https://github.com/ceph/ceph-qa-suite/tree/master/suites/rbd/qemu/cachepool to help with diagnostic of problems su...
- 09:32 PM Backport #12027 (In Progress): mon: osd featuers aren't updated correctly
- 09:31 PM Backport #12027 (Resolved): mon: osd featuers aren't updated correctly
- https://github.com/ceph/ceph/pull/4960
- 09:02 PM Revision 1c6fed70 (ceph): Merge pull request #454 from ceph/wip-cdtests
- Single node ceph-deploy tests to exercise commonly used cli
Reviewed-by: Travis Rhoden <trhoden@redhat.com> - 07:40 PM Revision 81605bdd (ceph): Merge pull request #4959 from ceph/wip-crush-compat
- Add crush_compat.h to eliminate ad hoc diff between kernel and userspace
Reviewed-by: Sage Weil <sage@redhat.com> - 07:38 PM Revision d2b80966 (ceph): Merge pull request #4961 from ceph/wip-11493-hammer
- backport 11493 fixes, and test, prevetning ec cache pools
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:26 PM Revision f68bf94e (ceph): OSDMonitor: disallow ec pools as tiers
- Fixes: 11650
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 11b7801bb57cb25cd2d26d58722d496... - 07:25 PM Revision 13c8d58d (ceph): mon: prevent pool with snapshot state from being used as a tier
- If we add a pool with snap state as a tier the snap state gets clobbered
by OSDMap::Incremental::propogate_snaps_to_t... - 07:23 PM Revision 58e62662 (ceph): test/librados/tier.cc: destroy and recreate cache pool on every test
- Namespaces are not sufficient with the checks for 11493 in the mon.
Signed-off-by: Samuel Just <sjust@redhat.com>
(c... - 06:51 PM Bug #12025 (Resolved): rados mkpool/ pool_create should warn/error when pgp_num > pg_num
- Ran into a wierd case when our configuration management utility had only set @ceph_osd_default_pgp_num@ to a non defa...
- 06:37 PM Bug #10911 (Pending Backport): mon: osd featuers aren't updated correctly
- This was never backported. I've create wip-10911-firefly for testing.
- 06:00 PM rgw Bug #11795: "test_multipart_upload_small ... FAIL" in smoke-master-distro-basic-typica run
- Run: http://pulpito.ceph.com/teuthology-2015-06-14_05:00:05-smoke-master-distro-basic-multi/
Job: 933024 - 04:54 PM Revision ce86b0a2 (ceph): doc/messenger: Add doc for ceph_perf_server/client
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:28 PM Revision 80e29f19 (ceph): Merge pull request #4956 from oritwas/fix-cmake-2
- cmake: add missing RadosDump.cc, RadosImport.cc and PoolDump.cc
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:59 PM Revision 2e7c8e7f (ceph): libcephfs: add ceph_p{read,write}v
- Fix comments raised by John Spray
Signed-off-by: Jevon Qiao <qiaojianfeng@unitedstack.com> - 03:56 PM Bug #12021 (Resolved): hammer-x upgrade test.sh fails with ENOTEMPTY
- 2015-06-13T21:36:05.996 INFO:tasks.workunit.client.1.plana83.stdout:[ FAILED ] LibRadosTwoPoolsPP.PromoteSnapScrub
... - 03:26 PM Revision 70bba622 (ceph): Merge pull request #4846 from SUSE/wip-11862-hammer
- missing man pages for ceph-create-keys, ceph-disk-*
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Ken Dreye... - 03:23 PM Revision 254676b6 (ceph): osd,mon: explicitly specify OSD features in MOSDBoot
- We are using the connection features to populate the features field in the
OSDMap, but this is the *intersection* of ... - 03:13 PM Revision 1db1abc8 (ceph): crush: eliminate ad hoc diff between kernel and userspace
- - map->choose_tries is not in the kernel
- 64-bit/64-bit in the kernel needs a special helper for 32-bit
architectu... - 03:13 PM Revision 69316a93 (ceph): crush: add crush_compat.h
- Move all the cruft that is necessary to compile shared files both in
kernel and userspace into a new crush_compat.h. ... - 02:50 PM devops Bug #12005: yum crash: "ValueError: need more than 2 values to unpack"
- We talked about this last week. It's a bug in yum that breaks it entirely. You can see in the log you pasted that it'...
- 02:48 PM Revision c1761c0f (ceph): Merge pull request #4826 from xinxinsh/wip-fix
- os/DBObjectMap:move iterator to first record of object otherwise iter->valid is always false
Reviewed-by: Kefu Chai ... - 01:51 PM Revision 154f055f (ceph): ceph: fix up log rotation stopper
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 451c5ca79de14a8462a76dc8287be1f4fd72fa1b) - 01:46 PM rbd Bug #12017 (Need More Info): ERROR: test_rbd.TestImage.test_update_features
- Shambhu, under what condition did you encounter this issue? The Hammer branch does not have this test case [1], so e...
- 09:17 AM rbd Bug #12017 (Can't reproduce): ERROR: test_rbd.TestImage.test_update_features
- ERROR: test_rbd.TestImage.test_update_features fails on ceph 0.94
On execution of workunit.client.0/rbd/test_librb... - 01:44 PM Linux kernel client Feature #10585 (Fix Under Review): use new, more reliable version of watch/notify
- 01:17 PM Revision fb71bd9d (ceph): mds: add dirfrag split/merge asok commands
- Analogous to those from the old-style mds tell. Also
add an 'ls' that gives you the frags in the same format
that fr... - 11:26 AM Revision 9a8ed8b1 (ceph): crush: move safe arithmetic functions to buider.c
- Given that crush_{addition,multiplication}_is_unsafe() are only used
for compiling maps, they have no business in cru... - 11:26 AM Revision 9fde1864 (ceph): crush: fix style issues in shared files
- Fix some recently introduced style issues in crush_ln_table.h,
crush.[ch], hash.[ch], and mapper.[ch]. These files a... - 11:26 AM Revision ecee227b (ceph): crush: shared files should use kernel-doc
- This reverts mapper.c hunks of 830752a52841 ("doc: fix doxygen
warnings"). It is shared with the kernel and uses ker... - 11:20 AM Feature #11815: mon: allow injecting new crushmap
- per the discussion of Joao, Greg and Loïc,
we need to have a CLI tool which will be designed to add a new paxos co... - 09:26 AM Feature #11815: mon: allow injecting new crushmap
- Although the previous crushmap is likely to be correct, it is entirely possible that it is corrupt. For instance you ...
- 09:04 AM Feature #11815: mon: allow injecting new crushmap
- as per greg & joao this is not a good idea (--use-crushmap false)
- 07:20 AM Feature #11815: mon: allow injecting new crushmap
- What about the mon can start in --use-crushmap false and will start in a mode that makes sure the crushmap is not use...
- 11:16 AM Revision efd46d10 (ceph): libcephfs: add test for ceph_p{read,write}v
- Add test in src/test/libcephfs/test.cc for ceph_preadv and ceph_pwritev interfaces.
Signed-off-by: Jevon Qiao <qiaoj... - 10:44 AM Messengers Bug #9898 (Resolved): osd: fast dispatch deadlock in mark_down (giant)
- It was intended for giant which is now retired.
- 10:41 AM Bug #9418: mon: drop internal-purpose messages from clients without proper caps
- Assuming firefly backport is intended because it was set to pending backport prior to hammer release. But cloud not f...
- 09:56 AM CephFS Bug #12019 (Resolved): multiple_rsync failure
- Related to #11781?
This is running with the recent change to source files from a dir in /tmp instead of directly f... - 09:39 AM Revision 6ef40d7c (ceph): cmake: add missing RadosDump.cc, RadosImport.cc and PoolDump.cc
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:32 AM Linux kernel client Bug #11449: krbd: tripping over rbd_assert in rbd_img_obj_callback() on errors
- https://github.com/torvalds/linux/commit/082a75dad84d79d1c15ea9e50f31cb4bb4fa7fd6
- 09:17 AM rbd Bug #12018 (Resolved): rbd and pool quota do not go well together
- The pool "rbd" is already full, but I still flatten a clone successfully. After flatten, "rbd" has more objects, but ...
- 08:56 AM Backport #12016 (Resolved): osd cache full mode still skips young objects
- https://github.com/ceph/ceph/pull/5051
- 08:52 AM Backport #12015 (Resolved): LibRadosTwoPools[EC]PP.PromoteSnap failure
- https://github.com/ceph/ceph/pull/5050
- 08:16 AM Linux kernel client Bug #8979: GPF kernel panics - auth?
- https://github.com/torvalds/linux/commit/73c3d4812b4c755efeca0140f606f83772a39ce4
- 07:59 AM Backport #12014 (Resolved): osd: cache tier: avoid promotion on first read
- https://github.com/ceph/ceph/pull/5200
- 05:50 AM CephFS Bug #11989: Cephfs Kernel Client data corruption
- Zheng Yan wrote:
> are there any suspected message when this happens?
dmesg is silent, ceph logs in /var/log/ceph... - 01:57 AM CephFS Bug #11989: Cephfs Kernel Client data corruption
- are there any suspected message when this happens?
- 02:15 AM Revision f6bf6c2a (ceph): libcephfs: add ceph_p{read,write}v
- Add interfaces in libcephfs to enable users to read/write data via iovec structure.
Signed-off-by: Jevon Qiao <qiaoj... - 01:48 AM Revision 51862e3d (ceph): bug fix: librados segmentation fault, when two read ops share one AioCo...
- This is a serious BUG:
In librados, use two read ops to read one object twice
with the same completion will cause seg...
06/14/2015
- 06:46 PM Revision 05e95f75 (ceph): objectstore/store_test.cc : add tests for DBObjectMap::get_keys
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 06:45 PM Revision ce5ba43d (ceph): os/DBObjectMap : fix recurcive lock in get_keys
- 1. get_keys obtain header lock of oid
2. get iterator with get_iterator(oid), in get_iterator, it also want to get he... - 06:45 PM Revision 440ef3a2 (ceph): os/DBOjectMap : iter->valid is always false if we do not initialize the...
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 05:23 PM Revision ade36cf7 (ceph): in _zero() function, we should remove strips to minimize keyvalue DB up...
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 04:03 PM Revision ac447792 (ceph): Merge pull request #4690 from branch-predictor/wip-radosbench-memjuggle
- tools: improve the performance of rados and rest_bench
Don't delete, recreate and re-fill buffers in rados bench. Fi... - 03:20 PM Bug #12013 (Can't reproduce): assert(info->on_notify_finish) in Objecter::handle_watch_notify(MWa...
- http://pulpito.ceph.com/ubuntu-2015-06-12_21:23:04-rados-wip-kefu-testing---basic-multi/930883/
crashed in multi... - 03:07 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- I have also stopped one impacted VM, do a fsck with 'virt-rescue utility', and restart the VM, but I continue to get ...
- 02:42 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- kvm/qemu is 2.2 and have not changed before and after the upgrade. librbd is 0.94.2-1-ga11cca9
- 02:33 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- 02:31 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- We have not scrub since we upgrade to giant due to http://tracker.ceph.com/issues/8011, we upgrade to hammer to be ab...
- 02:29 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- joshd or jdillaman may have a suggestion on how to narrow the error down. Maybe "vdf, sector 4637237248" allows to fi...
- 02:24 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- Could you list the operations you did to upgrade ? Was it just a matter of apt-get install ? Or did you do other main...
- 02:22 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- The most recent deep-scrub is six month old...
- 02:17 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- When was the last time this pool had a deep-scrub ?
- 02:16 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- All PG are *active+clean* in the 80 and 81 pools...
- 02:01 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- ...
- 01:59 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- issue-12012-ceph-report-20150614.gz can be found in sftp cephdrop@ceph.com
- 01:36 PM Bug #12012: IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from 0.87.1 to ...
- Could you also show the tier configuration you have ?
- 01:09 PM Bug #12012 (Resolved): IO error on kvm/rbd with an erasure coded pool tier (after an upgrade from...
- issue-12012-ceph-report-20150614.gz can be found in sftp cephdrop@ceph.com
I have recently upgraded a giant (0.87.... - 11:08 AM Revision 5436c290 (ceph): mon: add an "osd crush tree" command
- * to print crush buckets/items in a tree
Fixes: #11833
Signed-off-by: Kefu Chai <kchai@redhat.com> - 10:35 AM Backport #12011 (Resolved): PG stuck with remapped
- https://github.com/ceph/ceph/pull/5044
- 10:34 AM Bug #9614: PG stuck with remapped
- Fixed in giant by two PRs:
* https://github.com/ceph/ceph/pull/2616
* https://github.com/ceph/ceph/pull/2711 - 08:03 AM Documentation #12010 (Closed): docker_test.sh is not documented
- Provide some basic documentation on ...
- 08:00 AM Documentation #12009 (Resolved): Developer Guide (Quick) should link to deeper explanation of vst...
- There is a deeper explanation of ...
- 07:57 AM Documentation #12008 (Closed): Mention docker_test.sh in Developer Guide (Quick)
- The Developer Guide (Quick) http://ceph.com/docs/next/dev/quick_guide/ describes how one can use ...
- 07:51 AM Backport #12007 (Resolved): Objecter: pg listing can deadlock when throttling is in use
- https://github.com/ceph/ceph/pull/5043
- 06:56 AM rbd Feature #11822: [rbd] support gb/tb units in rbd create/resize
- new commit : https://github.com/vumrao/ceph/commit/bb4924b453392956d05021bc0e7283d13013a07f
- 06:08 AM Revision 5187520e (ceph): osd_types.cc: drop commented-out asserts in add_next_event()
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 06:05 AM Revision 01b2e1fd (ceph): osd_types.cc: replace count with iterator in add_next_event function
- Performance optimization: count() and then operator[] duplicates the rbtree
lookup.
http://tracker.ceph.com/issues/4... - 12:51 AM Linux kernel client Bug #12006 (Closed): huge tickets test failure
- /var/lib/teuthworker/archive/teuthology-2015-06-09_23:06:01-krbd-master-testing-basic-multi/928130
2015-06-12T18:5...
06/13/2015
- 08:55 PM devops Bug #12005 (Won't Fix): yum crash: "ValueError: need more than 2 values to unpack"
- Lots of jobs failed, here is one example
Run: http://pulpito.ceph.redhat.com/teuthology-2015-06-12_18:06:01-krbd-h... - 06:59 PM Revision a756a32d (ceph): Merge pull request #4950 from SUSE/wip-osd-spelling
- osd_types.{cc,h}: fix three typos in comments
Reviewed-by: Sage Weil <sage@redhat.com> - 06:36 PM Revision 724c139c (ceph): osd_types.{cc,h}: fix three typos in comments
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 02:49 PM Revision e7c91c72 (ceph): Merge pull request #4758 from xinxinsh/wip-kv-dump-transaction
- dump keyvaluestore transaction to a file
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Varada Kari <v... - 12:53 PM devops Bug #12004 (Rejected): rpmlint complains bitterly about three shared library dependencies
- SUSE rpmlint complains bitterly about three shared library dependencies:...
- 11:22 AM devops Tasks #12002 (Resolved): Make custom query for Pending Backport tickets with empty backport field
- @dachary - All good from my side.
- 09:26 AM Revision aa8a5639 (ceph): Merge pull request #4940 from swamireddy/wip-v094-mailmap
- mailmap: Yuri Weinstein affiliation
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:32 AM rbd Feature #7923: Openstack: backup from in-use volume instead of from detached volume
- In case of ceph as a backup driver & ceph as a volume driver as well; backups work when forced (without the need for ...
- 05:11 AM rbd Feature #11822: [rbd] support gb/tb units in rbd create/resize
- Hi Josh,
I have sent a patch for it.
https://github.com/vumrao/ceph/commit/718c41c6ec77e703557de6d3d59d52a2a5cb... - 01:45 AM Revision df4d4b42 (ceph): Merge pull request #4947 from oritwas/fix-cmake
- cmake: Remove rados_sync.cc, rados_import.cc and rados_export.cc deleted files
Reviewed-by: Yehuda Sadeh <yehuda@red... - 01:25 AM Revision f620a8a6 (ceph): Remove rados_sync.cc, rados_import.cc and rados_export.cc deleted files
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
06/12/2015
- 08:46 PM Bug #12000: OSD: EC reads do not correctly validate checksums and data contents
- Whoever fixes this:
In CEPH_OSD_OP_READ, pass a boost::optional<uint32_t> checksum if present as well as &osd_op.r... - 07:44 PM Bug #12000: OSD: EC reads do not correctly validate checksums and data contents
- From the mailing list ("Pawe? Sadowski" <ceph@sadziu.pl>):
I'm testing erasure coded pools. Is there any protectio... - 07:42 PM Bug #12000 (Resolved): OSD: EC reads do not correctly validate checksums and data contents
- The checksum verification currently only happens in the syncronous read case in CEPH_OSD_OP_READ in do_osd_ops. In t...
- 08:21 PM Bug #12003: RHEL/Centos kernels should be configured for SELinux, not AppArmor
- need to grab a .config from fedora, probably!
- 08:13 PM Bug #12003 (Resolved): RHEL/Centos kernels should be configured for SELinux, not AppArmor
- This may or may not be all of the problem:...
- 08:18 PM Feature #11882 (Resolved): add 'PGs' column to 'ceph osd df'
- 08:13 PM devops Tasks #12002: Make custom query for Pending Backport tickets with empty backport field
- The devops project is not ideal for improvements related to the stable releases maintenance. It would be nice that th...
- 08:11 PM devops Tasks #12002 (In Progress): Make custom query for Pending Backport tickets with empty backport field
- 08:11 PM devops Tasks #12002: Make custom query for Pending Backport tickets with empty backport field
- What about http://tracker.ceph.com/projects/ceph-releases/wiki/HOWTO_triage_incoming_Pending_backport_issues/diff?utf...
- 08:09 PM devops Tasks #12002: Make custom query for Pending Backport tickets with empty backport field
- Ouch, nice catch ! Making a public custom query is going to make it visible everywhere and maybe confuse people ?
- 08:03 PM devops Tasks #12002 (Resolved): Make custom query for Pending Backport tickets with empty backport field
- This is another way that backport tasks "fall through the cracks" - since the *Backport* field is not filled in, the ...
- 08:00 PM Revision 55d9747e (ceph): mon: add 'PGs' column to 'ceph osd df'
- Fixes: #11882
Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 07:31 PM CephFS Backport #11999 (Resolved): cephfs Dumper tries to load whole journal into memory at once
- https://github.com/ceph/ceph/pull/5120
- 07:30 PM devops Backport #11998 (Resolved): /usr/bin/ceph from ceph-common is broken without installing ceph
- https://github.com/ceph/ceph/pull/5206
- 07:27 PM rgw Feature #10333 (Fix Under Review): rgw: support AWS4 authentication
- 04:00 PM rgw Feature #10333: rgw: support AWS4 authentication
- I've just created a pull request to merge a first version for supporting Amazon's S3 signature V4 (from now on, AWS4)...
- 07:26 PM rgw Feature #11858 (Duplicate): Support Amazon v4 Signatures
- 06:44 PM rgw Feature #11858: Support Amazon v4 Signatures
- Yes, you are right. It is.
- 04:05 PM rgw Feature #11858: Support Amazon v4 Signatures
- It looks one dupe of #10333
- 07:24 PM devops Backport #11997 (Resolved): ceph.spec.in: rpm: not possible to turn off Java
- https://github.com/ceph/ceph/pull/5203
- 07:23 PM devops Backport #11996 (Rejected): rpm: not possible to turn off Java
- 07:11 PM devops Bug #11991 (In Progress): rpm: cephfs_java not fully conditionalized
- 03:34 PM devops Bug #11991 (Resolved): rpm: cephfs_java not fully conditionalized
- The spec file has ...
- 07:07 PM Revision b455e4a7 (ceph): Single Node Ceph-deploy tests to exercise commonly used CLI and test in...
- - Add 1node tests to Smoke and include ceph-deploy test
- Review Comments , add rgw cli test
Signed-off-by: Vasu ... - 07:06 PM CephFS Bug #11989: Cephfs Kernel Client data corruption
- I imagine this is a result of some kind of memory exhaustion, but I'm not sure how best to diagnose it or if there ar...
- 01:22 PM CephFS Bug #11989 (Resolved): Cephfs Kernel Client data corruption
- Hi. i get random data corruption with the cephfs kernel client. i do streaming from a non-ceph machine using "cat <fi...
- 06:24 PM rgw Bug #11749 (Pending Backport): rgw: rados objects wronly deleted
- Merged in commit:69989ffa3cabe209404504edd24b1d2a53e33e15.
backporting to firefly will also require picking up fix f... - 06:20 PM Revision 3d935a36 (ceph): Merge pull request #460 from ceph/wip-logrotate-fix
- ceph: fix up log rotation stopper
Reviewed-by: John Spray <john.spray@redhat.com> - 06:19 PM CephFS Bug #11986: logs changing during tarball generation at end of job
- Actually this job doesn't have log rotation enabled at all.
- 12:34 PM CephFS Bug #11986 (Closed): logs changing during tarball generation at end of job
http://pulpito.ceph.com/teuthology-2015-06-08_23:04:01-fs-master---basic-multi/926320/...- 06:19 PM Revision 69989ffa (ceph): Merge pull request #4752 from wuxingyi/wip-11749
- rgw: fix data corruption when race condition
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:19 PM Revision 451c5ca7 (ceph): ceph: fix up log rotation stopper
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:17 PM Revision 21f850eb (ceph): Merge pull request #4900 from abhidixit/trans_id
- Transaction Id added in response for S3 and Swift requests
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:14 PM Linux kernel client Bug #11960: Kernel panic when deleting a pool, which contains a mapped RBD
- Ilya,
Thanks for getting back to me. I'm away for the weekend, but I can get back to you on Monday.
Have a good... - 09:34 AM Linux kernel client Bug #11960 (Need More Info): Kernel panic when deleting a pool, which contains a mapped RBD
- Hi Alex,
While deleting a pool with mapped rbd images is just asking for trouble, we shouldn't panic. Can you pro... - 04:50 PM Bug #11995 (Duplicate): "HEALTH_WARN 1 mons down, quorum 0,2 b,c" in upgrade:giant-x-next-distro-...
- Run: http://pulpito.ceph.com/teuthology-2015-06-11_17:05:04-upgrade:giant-x-next-distro-basic-vps/
Jobs: ['929547', ... - 04:47 PM Bug #11994 (Resolved): "unknown op append_excl" in upgrade:giant-x-next-distro-basic-vps run
- Run: http://pulpito.ceph.com/teuthology-2015-06-11_17:05:04-upgrade:giant-x-next-distro-basic-vps/
Jobs: 52 jobs
Lo... - 04:43 PM Bug #11993 (Duplicate): LibRadosTwoPoolsPP * tests failed in upgrade:giant-x-next-distro-basic-vp...
- NOTE: Could be a duplicate if #11548
Run: http://pulpito.ceph.com/teuthology-2015-06-11_17:05:04-upgrade:giant-x-n... - 04:30 PM devops Bug #11922: Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-distro-basic-vps...
- Run: http://pulpito.ceph.com/teuthology-2015-06-09_17:00:04-upgrade:firefly-firefly-distro-basic-vps/
- 12:25 AM devops Bug #11922: Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-distro-basic-vps...
- Any test that's queued against that d0f9c5f47024f53b4eccea2e0fde9b7844746362 sha1 is going to fail on centos6. You'll...
- 03:50 PM Revision 04e91bbd (ceph): rpm: add missing Java conditionals
- http://tracker.ceph.com/issues/11991 Fixes: #11991
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 03:42 PM devops Bug #11992 (Resolved): rpm: not possible to turn off Java
- It would be nice to enable packagers to turn off Java via a ...
- 02:49 PM Revision 45392a2d (ceph): mailmap: Yuri Weinstein affiliation
- Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
- 01:57 PM Stable releases Tasks #11990 (In Progress): hammer v0.94.3
- 01:51 PM Stable releases Tasks #11990 (Resolved): hammer v0.94.3
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 12:42 PM Fix #11987 (New): erasure-code: lrc k/m/l sanity check must apply to ruleset-failure-domain=osd
- When the layers are specified with...
- 12:31 PM CephFS Bug #11985 (Resolved): MDS asserts in objecter when transitioning from replay to DNE
Seen once:
http://pulpito.ceph.com/teuthology-2015-06-08_23:04:01-fs-master---basic-multi/926330/...- 11:17 AM rgw Bug #11984: Error with `radosgw-admin check --check-head-obj-locator --bucket=$bucket --fix` command
- Sorry I have forgotten to give some info about my environment. For each node of my cluster (2 "radosgw" servers, 2 "m...
- 11:10 AM rgw Bug #11984 (Duplicate): Error with `radosgw-admin check --check-head-obj-locator --bucket=$bucket...
- Hi,
I have a cluster in Hammer 0.94.1 which I have upgraded to 0.94.2. In my radosgw host, I wanted to fix the pro... - 09:31 AM Backport #11983 (Resolved): "FAILED assert(!old_value.deleted())" in upgrade:giant-x-hammer-distr...
- https://github.com/ceph/ceph/pull/5121
- 09:30 AM Backport #11982 (Resolved): ceph fails to compile with boost 1.58
- https://github.com/ceph/ceph/pull/5122
- 09:28 AM Backport #11981 (Rejected): chain_xattr: deal with 254 byte limit on inline xfs attrs
- https://github.com/ceph/ceph/pull/4973
- 09:27 AM Backport #11980 (Resolved): MDSMonitor: handle MDSBeacon messages properly
- https://github.com/ceph/ceph/pull/5199
- 09:26 AM Backport #11979 (Resolved): MDSMonitor: handle MDSBeacon messages properly
- https://github.com/ceph/ceph/pull/5123
- 08:45 AM devops Feature #11978: Tool that updates git-notes for backports
- A first step could be a script that:
* look for all commit with a Backport: field
* look for an issue in the comm... - 08:30 AM devops Feature #11978 (Closed): Tool that updates git-notes for backports
- The bot would create a json structure in the git notes of the ceph repository to be the authoritative state of the ba...
- 08:39 AM Bug #11793: test: rados.py does not do cache_(evict|flush|try_flush) since it leaves out the cache_
- This is what I see from the log for oid plana9327095-291:
1. At first, pool 2 is the cache pool of pool 1. For pla... - 08:28 AM Backport #11977 (Rejected): mon crashes when "ceph osd tree 85 --format json"
- 08:23 AM Backport #11975 (In Progress): mon crashes when "ceph osd tree 85 --format json"
- 08:17 AM Backport #11975: mon crashes when "ceph osd tree 85 --format json"
- https://github.com/ceph/ceph/pull/4936
- 07:23 AM Backport #11975: mon crashes when "ceph osd tree 85 --format json"
- -https://github.com/ceph/ceph/pull/4935-
- 07:20 AM Backport #11975 (Resolved): mon crashes when "ceph osd tree 85 --format json"
- https://github.com/ceph/ceph/pull/4936
- 07:56 AM Linux kernel client Bug #11976 (New): cephfs kernel driver overuses GFP_NOFS
- it should be ok to use GFP_KERNEL at lots of places
- 06:50 AM Bug #11576 (Pending Backport): ceph fails to compile with boost 1.58
- 05:39 AM Revision bf9a9a2d (ceph): Merge pull request #457 from ceph/wip-11913
- tasks/cephfs: fix race in test_full
Reviewed by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Greg Farnum <gfarnum@redh... - 03:33 AM rgw Bug #11974 (Resolved): Fix tool for #11442 does not correctly fix objects created via multipart u...
- @radosgw-admin bucket check --check-head-obj-locator --fix@ claims to successfully fix objects that were created via ...
- 01:41 AM Fix #11590 (Pending Backport): MDSMonitor: handle MDSBeacon messages properly
- 01:31 AM Bug #11680 (Pending Backport): mon crashes when "ceph osd tree 85 --format json"
- 01:19 AM Revision 95ba9677 (ceph): Merge pull request #4726 from tchaikov/wip-11680-check-empty-crushmap
- mon: check new crush for unknown name/type
Reviewed-by: Loic Dachary <ldachary@redhat.com>
06/11/2015
- 10:36 PM Bug #11548: "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-basic-multi run
- lots of jobs in
http://pulpito.ceph.com/teuthology-2015-06-09_17:05:01-upgrade:giant-x-next-distro-basic-vps/
http:... - 10:35 PM Revision 0698bde9 (ceph): Merge pull request #4932 from dzafman/wip-cot-import
- test, tools: Improve ceph-objectstore-tool import error handling and …
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:11 PM rgw Feature #11973 (New): rgw: create bootstrap admin commands
- A$ radosgw-admin realm bootstrap-master --realm=dho --zonegroup=us-west --zone=us-west-1
A$ radosgw --zone=us-west-1... - 10:10 PM rgw Feature #11972 (Resolved): rgw: implement zongroup create admin command
- radosgw-admin zonegroup add --zonegroup us-west --zone=foo --cluster-uuid=blah
- 10:09 PM rgw Feature #11971 (New): rgw: implement new zone join command
- radosgw-admin zone join --zone=foo --realm=dho
- 09:39 PM Stable releases Tasks #11492 (Resolved): hammer v0.94.2
- 08:54 PM Revision 3b6977b7 (ceph): Merge pull request #4934 from dachary/wip-releases-hammer
- doc/release-notes: v0.94.2
- 08:54 PM Revision f784db0b (ceph): Merge pull request #4933 from dachary/wip-releases
- doc: add v0.94.2 to the release timeline
Reviewed-by: Sage Weil <sage@redhat.com> - 08:52 PM devops Bug #11922: Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-distro-basic-vps...
- Run: http://pulpito.ceph.com/teuthology-2015-06-07_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps/
Jobs: 15
L... - 03:58 PM devops Bug #11922: Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-distro-basic-vps...
- The sha1 that Teuthology used here, d0f9c5f47024f53b4eccea2e0fde9b7844746362, is immediately prior to the change that...
- 03:46 PM devops Bug #11922: Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-distro-basic-vps...
- Run: http://pulpito.ceph.com/teuthology-2015-06-07_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps/
Jobs : 15
... - 08:50 PM rgw Feature #11933: rgw: create realm and period data structures
- 1. Term
$ radosgw-admin term prepare --parent=<parent> <uuid>
Creating a new term object in .rgw.root pool.
$ ... - 08:46 PM Revision 3db1026f (ceph): doc/release-notes: v0.94.2
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 306345b29c259ab04a58ed5d40f801645485b29d)
Conf... - 08:35 PM Revision 5b29a57b (ceph): doc: add v0.94.2 to the release timeline
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:57 PM Revision ddc4d527 (ceph): test, tools: Improve ceph-objectstore-tool import error handling and ad...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:56 PM Revision 0db3ba15 (ceph): Merge pull request #4926 from dzafman/wip-omaptool
- ceph-osdomap-tool: Fix argument handling
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:04 PM Revision 7618d869 (ceph): PerfMsgr: Add usage helper info
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:01 PM Revision 75949633 (ceph): Merge pull request #4914 from liewegas/wip-mon-pg-by-osd
- mon: fix pg_by_osd in PGMap
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:00 PM Revision d6f6ad03 (ceph): PerfMsgr: Make Server worker threads configurable
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:49 PM Bug #11969: chain_xattr: deal with 254 byte limit on inline xfs attrs
- https://github.com/ceph/ceph/pull/4070
- 04:44 PM Bug #11969 (Resolved): chain_xattr: deal with 254 byte limit on inline xfs attrs
- 04:32 PM Revision eba4eb2e (ceph): PerfMsgr: Add tips for running ceph_perf_msgr
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:27 PM Revision 97ff79d5 (ceph): debian, rpm: Add ceph_perf_msgr_* to build file
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:25 PM Revision 372eddf6 (ceph): PerfMsgr: Add messenger perf tools
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:22 PM Revision e27ed39b (ceph): Merge pull request #459 from dachary/wip-ceph-manager-log
- add the log object to ceph_manager
- 04:19 PM Revision 96bebc69 (ceph): add the log object to ceph_manager
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
(cherry picked from commit f7c1ca4a1e23b03ecf86d5e67d563f95b3a82f99)
... - 04:16 PM rgw Bug #11966 (Resolved): "SyntaxError (invalid syntax (test_s3.py, line 5792)) ... ERROR" in upgrad...
- Run: http://pulpito.ceph.com/teuthology-2015-06-08_16:05:02-upgrade:hammer-hammer-distro-basic-vps
Jobs: ['925330', ... - 02:56 PM Bug #11965: ceph_test_msgr --gtest_filter=*SyntheticInjectTest2/1* never ends
- nvm. it just took too long to finish.
but http://pulpito.ceph.redhat.com/kchai-2015-06-11_07:55:28-rados-master---... - 02:45 PM Bug #11965 (Can't reproduce): ceph_test_msgr --gtest_filter=*SyntheticInjectTest2/1* never ends
- see http://pulpito.ceph.com/ubuntu-2015-06-11_07:08:56-rados-master---basic-multi/929223/...
- 02:08 PM Backport #11964 (Resolved): systemd: Increase max files open limit for OSD daemon
- https://github.com/ceph/ceph/pull/5040
- 02:07 PM Backport #11963 (Rejected): REJECTED systemd: Increase max files open limit for OSD daemon
- Cherry-pick ebda4ba1c67172852587e47a8e6fb538809a1b1c to firefly
- 02:03 PM Bug #11962 (Resolved): systemd: Increase max files open limit for OSD daemon
- Owen Synge writes in https://github.com/ceph/ceph/commit/ebda4ba1c67172852587e47a8e6fb538809a1b1c
Under heavy load... - 01:56 PM CephFS Feature #3826 (Resolved): uclient: Be more aggressive about checking for pools we can't write to
- Zheng did this a few months ago; we now write to a test object in every newly-seen pool.
- 01:55 PM CephFS Feature #4885 (Resolved): dumper: do an incremental log dump
- https://github.com/ceph/ceph/pull/4835
- 01:53 PM rbd Backport #11769: librbd: aio calls may block
- Josh Durgin wrote:
> https://github.com/ceph/ceph/pull/4364 - DNM until it's been verified in master for a bit (**CL... - 01:52 PM CephFS Feature #11588 (Resolved): teuthology: set up log rotate for MDS logs
- https://github.com/ceph/ceph-qa-suite/pull/452
- 01:43 PM Backport #11961 (Resolved): Cleanup boost optionals for boost 1.56
- https://github.com/ceph/ceph/pull/5039
- 01:42 PM Bug #9983 (Pending Backport): Cleanup boost optionals for boost 1.56
- 01:41 PM Bug #9983 (Resolved): Cleanup boost optionals for boost 1.56
- This issue has already been resolved in master.
- 01:31 PM Bug #11470 (In Progress): mon: leaked Messenger, MLog on shutdown
- I believe I found where these come from while testing the optracker on my local machine \o/
Looks like these happe... - 01:28 PM CephFS Bug #11959 (Resolved): qa-suite: /usr copy needs more perms
- 10:13 AM CephFS Bug #11959 (Fix Under Review): qa-suite: /usr copy needs more perms
- That's kind of yucky of virtual box to put those in /usr/lib but whatever!
https://github.com/ceph/ceph/pull/4930 - 05:23 AM CephFS Bug #11959 (Resolved): qa-suite: /usr copy needs more perms
- /a/ubuntu-2015-06-10_10:18:19-fs-greg-fs-testing---basic-multi/928341/teuthology.log...
- 01:28 PM Revision 8b47a625 (ceph): Merge pull request #4930 from ceph/wip-11959
- qa: use "sudo cp" in multiple_rsync.sh
- 01:15 PM CephFS Bug #11913 (Fix Under Review): Failure in TestClusterFull.test_barrier
- https://github.com/ceph/ceph-qa-suite/pull/457
- 10:21 AM Revision 63a563d0 (ceph): tasks/cephfs: fix race in test_full
- Sometimes mount A would get a cap revoke when mount
B did its last IO, resulting in mount A's OSD epoch
getting updat... - 10:11 AM Revision 832f33ad (ceph): qa: use "sudo cp" in multiple_rsync.sh
- VirtualBox has some files with weird
permissions in its /usr/lib, which was
tripping up this usually-safe operation
w... - 10:04 AM Linux kernel client Bug #11960 (Closed): Kernel panic when deleting a pool, which contains a mapped RBD
- Hello all,
I've found a reproducible bug in Ceph relating to mapped RBD images.
Steps to reproduce:
1. Creat... - 08:54 AM Revision 290204d4 (ceph): common: make safe_splice return if return value is EAGAIN.
- If splice data from normal file into pipe and pipe has no enough
buffer(see fcntl), splice will block. If splice flag... - 08:48 AM Revision 82dc23a6 (ceph): erasure-code: lrc plugin workload
- Add a workload that uses the lrc erasure code plugin. Instead of adding
it to suites/rados/thrash-erasure-code/worklo... - 08:45 AM Revision d91808b7 (ceph): FileStore: For clone using splice to reduce memcopy.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 08:43 AM Bug #11952 (Resolved): ceph-disk tests silently fails on precise amd64
- 08:42 AM Revision 393c6241 (ceph): Merge pull request #4921 from dachary/wip-11952-test-ceph-disk
- tests: ceph-disk tests need to install pip > 6.1
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:41 AM Linux kernel client Bug #11841: umount stuck on NFS over RBD switch over by using Pacemaker
- Thanks for your reply.
I followed your suggestion to do some test again that don't involve pacemaker. I have tried t... - 08:12 AM Revision 7509a6ca (ceph): common/TrackedOp: checking in flight ops fix
- Return earlier if tracking is not enabled when checking in flight ops.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@i... - 08:12 AM Revision ec3c4095 (ceph): common/OpTracker: don't dump ops if tracking is not enabled
- If tracking is disabled, there is nothing to dump. No need to go through
each sharded list. This is true for both in ... - 08:11 AM Revision 5c7bacd5 (ceph): os/RocksDBStore:Drop buffer_list and key_list in transaction.
- We dont need to keep this inside the transaction.
Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com> - 08:10 AM Revision d9616d67 (ceph): common/TrackedOp: break out of loop when reaching log threshold
- When the number of warned ops reaches the log threshold, should break
out of the outer for loop as well.
Signed-off-... - 07:53 AM Revision 929e5932 (ceph): osd/ReplicatedPG: snapset is not persisted
- When the new_obs doesn't exist, and the old snapset obc does exist, we
need to update the snapdir object with the lat... - 07:25 AM Revision 1e4dc8d9 (ceph): FileStore: Call _do_copy_range in _do_spare_copy_range.
- For the real data copy, using _do_copy_range. Reduce the duplicated code.
Signed-off-by: Jianpeng Ma <jianpeng.ma@in... - 06:15 AM Revision 93d920e6 (ceph): doc: update rgw configuration doc on bucket index sharding feature
- Signed-off-by: Yuan Zhou <yuan.zhou@intel.com>
- 05:46 AM Revision 2fb380e9 (ceph): ECBackend:Only there are push, it queue transaction.
- For normal ec read, it don't need transaction.
In fact it only for MSG_OSD_PG_PUSH.
Signed-off-by: Jianpeng Ma <jian... - 01:49 AM Revision f23ff731 (ceph): ceph-osdomap-tool: Fix argument handling
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:41 AM Revision b4ad2601 (ceph): mon/PGMap: fix pgmap stat adjustment during map_pg_creates()
- PGMonitor::map_pg_creates() is the only caller that passes sumonly=true,
which is necessary to avoid modifying creati... - 12:32 AM devops Bug #11954 (Resolved): "Unable to locate package python-rados" in rados-firefly-distro-basic-magn...
- https://github.com/ceph/teuthology/commit/3f4a9dc763292a8e792fd5d9739376208f2d3dc5
06/10/2015
- 11:57 PM Revision 26717754 (ceph): Merge pull request #4863 from ceph/wip-9964-nosharding
- rados import/export (minus pgls sharding)
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: John Spray <jo... - 10:50 PM Revision d1d61963 (ceph): tools: better error message in objectstoretool
- ...for the case where someone exports a pool
with "rados export" and then tries to import
it into a PG.
Signed-off-b... - 10:50 PM Revision 14819507 (ceph): tools/rados: dry-run/no-overwrite args for import
- These were supported by the old objectstoretool
hook into RadosImport: wire them up here too.
Signed-off-by: John Sp... - 10:50 PM Revision c0c6efb9 (ceph): test: Add --dry-run and --no-overwrite testing of rados import
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 10:50 PM Revision 83a42203 (ceph): test: Switch ceph-objectstore-tool import-rados to rados import
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 10:44 PM Bug #11914: "Caught signal" in teuthology-2015-06-04_11:23:35-rados-firefly---basic-multi run
- A bit before the crash, ceph_objectstore_tool import 3.31s2 into osd 4.
2015-06-04T18:51:49.005 INFO:teuthology.or... - 10:40 PM devops Bug #11955: /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- To clarify - this fix is not needed in Hammer, master, or anywhere else. Just firefly.
- 10:07 PM devops Bug #11955 (Resolved): /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- Sage has merged the above PR just now, so this fix will be in the next Firefly release, v0.80.10.
- 10:05 PM devops Bug #11955: /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- Yuri Weinstein wrote:
> Is this related to #11922 ?
Quite possibly! I was wondering why the CentOS 6 gitbuilder d... - 10:03 PM devops Bug #11955: /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- Is this related to #11922 ?
- 09:56 PM devops Bug #11955 (Fix Under Review): /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- Firefly PR: https://github.com/ceph/ceph/pull/4924
Please note that this issue only affects Firefly, because mkcep... - 09:41 PM devops Bug #11955 (Resolved): /sbin/mkcephfs is not packaged on Firefly / CentOS 6
- https://github.com/ceph/ceph/commit/efbca0465c2946e113771966df08cf7cf37b1196 added mkcephfs to the files listing, but...
- 10:32 PM rgw Bug #11956: rgw: pool names need to be prefixed with a dot
- We need to clean this up.
- 10:31 PM rgw Bug #11956 (Resolved): rgw: pool names need to be prefixed with a dot
- 10:03 PM Revision d1f47820 (ceph): Merge pull request #4924 from ceph/wip-11955-firefly
- 11955: ceph.spec.in: package mkcephfs on EL6
Reviewed-by: Sage Weil <sage@redhat.com> - 09:51 PM Revision 7f1abd90 (ceph): ceph.spec.in: package mkcephfs on EL6
- Commit efbca0465c2946e113771966df08cf7cf37b1196 added mkcephfs to the
RPM %files listing, but this /usr/sbin path is ... - 09:37 PM Revision 28833146 (ceph): tools: remove old rados_sync code
- This is the code that used to sit behind the
old import/export commands that have been
disabled for some time.
Repla... - 09:37 PM Revision 460200c7 (ceph): tools: remove objectstoretool's rados-import
- Same functionality now exposed as "rados import".
This removes objectstoretool's librados dependency.
Signed-off-by... - 09:37 PM Revision d26086d3 (ceph): tools: refactor objectstore tool
- ...to expose the definitions of the object dump
format (RadosDump) for use in rados import/export.
The serialized->R... - 09:37 PM Revision 8e5594da (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... - 09:37 PM Revision f477b445 (ceph): tools: add support for pool exports in RadosImport
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:37 PM Revision 2991beeb (ceph): tools: remove RadosDump::debug in favour of dout
- This attribute was a hangover from objectstore-tool
Signed-off-by: John Spray <john.spray@redhat.com> - 09:37 PM Revision a45f8fe1 (ceph): tools: refactor RadosImport to pass ioctx
- Callers from rados.cc will already have an ioctx,
whereas objectstoretool passes in a pool name.
Signed-off-by: John... - 09:37 PM Revision 391c72f3 (ceph): tools: implement rados import/export
- New PoolDump (export) class to dump pool contents
in format compatible with ceph-objectstore-tool,
and wire up RadosI... - 09:02 PM Revision a5d9b49c (ceph): FileStore and blkdev: Collect device partition information
- Use blkid APIs to get device parition information into the metadata bundle, and leverage common/blkdev.* helpers to p...
- 08:57 PM devops Bug #11954 (Resolved): "Unable to locate package python-rados" in rados-firefly-distro-basic-magn...
- Run: http://pulpito.ceph.redhat.com/teuthology-2015-06-08_22:30:01-rados-firefly-distro-basic-magna/
Jobs: ['12703... - 08:34 PM CephFS Support #11923: MDS init script starts multiple instances when MDS is referenced in ceph.conf
- Can you attach the ceph.conf and an ls -al of the instance directory? This will happen if the section is in ceph.co...
- 07:59 PM Revision 64908500 (ceph): Merge pull request #4922 from dachary/wip-releases
- doc: add v9.0.1 to the release timeline
Reviewed-by: Sage Weil <sage@redhat.com> - 07:50 PM Revision 488c042f (ceph): doc: add v9.0.1 to the release timeline
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:48 PM Revision 306345b2 (ceph): doc/release-notes: v0.94.2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:42 PM Revision f5da2fc5 (ceph): doc/release-notes: v9.0.1
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM Fix #11953 (Rejected): tests: make check does pip install
- In ceph-detect-init/run-tox.sh and in ceph-disk.sh pip install pip >= 6.1 requires network access. If there is no net...
- 07:04 PM Bug #11952 (Fix Under Review): ceph-disk tests silently fails on precise amd64
- https://github.com/ceph/ceph/pull/4921
- 06:38 PM Bug #11952: ceph-disk tests silently fails on precise amd64
- ...
- 06:32 PM Bug #11952 (Resolved): ceph-disk tests silently fails on precise amd64
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-precise-amd64-basic/log.cgi?log=c06fd71a1a3c7ef78fdc718a063b...
- 07:00 PM Revision 1e77fcfd (ceph): tests: ceph-disk tests need to install pip > 6.1
- Otherwise it will not be able to use the wheelhouse.
http://tracker.ceph.com/issues/11952 Fixes: #11952
Signed-off-... - 06:28 PM Revision 9c6da3b0 (ceph): Merge pull request #4915 from ceph/wip-cot-list
- tools: For ec pools list objects in all shards if the pgid doesn't sp…
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:15 PM Revision dab2ae2e (ceph): Merge remote-tracking branch 'gh/next'
- 05:14 PM Revision c06fd71a (ceph): Merge remote-tracking branch 'gh/next'
- 04:11 PM rgw Bug #11795: "test_multipart_upload_small ... FAIL" in smoke-master-distro-basic-typica run
- Run: http://pulpito.ceph.com/teuthology-2015-06-09_05:00:04-smoke-master-distro-basic-multi/
Job: 926544
Logs: ... - 04:02 PM Revision 20e10486 (ceph): librbd: new rbd_non_blocking_aio config option
- Setting this option to false reverts librbd to legacy behavior
where AIO operations could potentially block.
Signed-... - 04:02 PM Revision ed5442b1 (ceph): tests: verify librbd blocking aio code path
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 4cf41486e9c9e1efcb863960a8f3e0326ffca7... - 04:02 PM Revision b4571b3e (ceph): PendingReleaseNotes: document changes to librbd's aio_read methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:00 PM Revision 9ea1edd0 (ceph): librbd: AioRequest::send no longer returns a result
- The librados calls used by AioRequest::send should always return
zero unless there is a bug.
Signed-off-by: Jason Di... - 03:59 PM Revision 272df2ae (ceph): tests: update librbd AIO tests to remove result code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 948b15eb52fd5d9ce842fa12ee0cecda17353b... - 03:55 PM Revision 7df6091a (ceph): librbd: add new fail method to AioCompletion
- Helper method to handle passing fatal errors generated within
librbd (not from the OSDs) back to the client.
Signed-... - 03:55 PM Revision dbd4e293 (ceph): Throttle: added pending_error method to SimpleThrottle
- Allow the client of SimpleThrottle to detect an async error
so that it can exit early.
Signed-off-by: Jason Dillaman... - 03:55 PM Revision dd2e4c13 (ceph): librbd: internal AIO methods no longer return result
- All failures should be returned via the AioCompletion.
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry p... - 03:55 PM Revision cf6e1f50 (ceph): librbd: avoid blocking AIO API methods
- Enqueue all AIO API methods within the new librbd thread pool to
reduce the possibility of any blocking operations. T... - 03:50 PM Revision e61974ae (ceph): librbd: add task pool / work queue for requests
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit afb896d91f886b647baf38f7ec94cc3739f6d2... - 03:48 PM Revision 4ab5b680 (ceph): Merge pull request #456 from ceph/wip-11937-firefly
- thrasher: Can't test ceph-objectstore-tool if nodes turned off (power…
Reviewed-by: Yuri Weinstein <yweinste@redhat.... - 03:48 PM Revision 14112110 (ceph): Merge pull request #455 from ceph/wip-11937
- thrasher: Can't test ceph-objectstore-tool if nodes turned off (power…
Reviewed-by: Yuri Weinstein <yweinste@redhat.... - 03:45 PM Bug #11949 (Resolved): erasure-code corpus verification fails on isa / i386
- 01:29 PM Bug #11949 (Fix Under Review): erasure-code corpus verification fails on isa / i386
- https://github.com/ceph/ceph/pull/4910
- 06:25 AM Bug #11949 (Resolved): erasure-code corpus verification fails on isa / i386
- The sanity check must take into account that it's normal for the isa plugin to not run on i386
http://gitbuilder.sep... - 03:44 PM Cleanup #11932 (Resolved): ceph_erasure_code_non_regression s/stipe/stripe/
- 03:43 PM Revision 1c1f2c32 (ceph): Merge pull request #4910 from dachary/wip-11932-non-regression-typo
- tests: ceph_erasure_code_non_regression s/stipe/stripe/
- 03:12 PM Revision 20f49348 (ceph): Merge pull request #4873 from liewegas/wip-rgw-civetweb-port
- rgw: strip off port from HTTP_HOST when determining bucket from URL
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 02:19 PM CephFS Bug #10950 (Resolved): Unable to remove MDS host: error handling
- Merged to master in commit:5441f89c022aa1f4df084a4280e45c5c5b278f00
- 02:18 PM Revision 5441f89c (ceph): Merge pull request #4838 from ceph/wip-10950
- #10950: Fix confusing errors using "mds rm"
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:18 PM CephFS Bug #11746 (Pending Backport): cephfs Dumper tries to load whole journal into memory at once
- Merged to master in commit:04a11f0f2f6d46091d6868ba1cc2fec7a4e7a99c
- 02:17 PM Revision 04a11f0f (ceph): Merge pull request #4835 from ceph/wip-11746
- tools: chunk reads in Dumper
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:15 PM Revision b408f009 (ceph): Merge pull request #4825 from tchaikov/wip-drop-ignored-mdsbeacon
- mon: drop ignored mdsbeacon
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 01:28 PM Bug #11896: ceph command hangs and calls repeatedly gettimeofday when rdtsc() in Cycles.h returns 0
- Just checked git/master and seems that Cycles.cc has a fix for this - have not tested it yet
- 01:26 PM Revision 2d76e2cb (ceph): tests: erasure-code non regression tests must skip isa on i386
- When the isa plugin is not present, the isa plugin payloads are not
tested. When that happens, remember that it was i... - 01:19 PM CephFS Feature #11950 (Resolved): Strays enqueued for purge cause MDCache to exceed size limit
If your purge operations are going slowly (either because of throttle or because of slow data pool), and you do lot...- 09:56 AM Revision 07eb03ac (ceph): tasks/cephfs: time out on ceph-fuses that don't die
- For cases where we have e.g. poked the fuse abort
file for a process, but it's still not dying. Because
this is a sp... - 09:53 AM Revision a1a83037 (ceph): Merge pull request #452 from ceph/wip-logrotate
- Logrotate
Reviewed-by: John Spray <john.spray@redhat.com> - 08:25 AM Revision e68ea2c9 (ceph): osdc: Make librbd cache handle NOCACHE fadvise flag.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:58 AM Revision ac1e729a (ceph): rgw: fix data corruption when race condition
- We should delete the object in the multipart namespace lastly to prevent a previous upload
wrongly deleting objects b... - 06:12 AM Bug #11948 (Can't reproduce): tests: test-erasure-code.sh osd out is racy
- In...
- 05:22 AM Revision 5a5dc5f0 (ceph): Merge pull request #4707 from stiopaa1/IosFwdNew
- Removed unnecessary inclusion of iostream in several files
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:57 AM Revision 42a3ab95 (ceph): os/LevelDBStore:Drop buffer_list and key_list in transaction.
- We dont need to keep this inside the transaction.
Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com> - 01:14 AM Revision 1aa9655f (ceph): tools: For ec pools list objects in all shards if the pgid doesn't specify
- Signed-off-by: David Zafman <dzafman@redhat.com>
06/09/2015
- 11:57 PM Bug #10317 (Can't reproduce): pg repair doesn't fix missing attr
- Can not reproduce on latest code in master branch nor in firefly "ceph version 0.80.9-255-gd0f9c5f (d0f9c5f47024f53b4...
- 11:16 PM Revision 6573e92f (ceph): ceph: update log rotation for review comments
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:00 PM Bug #10794 (Resolved): ceph_test_rados: incorrect buffer at pos ...
- 09:56 PM Revision fa048338 (ceph): mon/PGMap: fix pg_by_osd
- Broken since it was introduced in 7a04762fe09661cc2ac98a034626912ec0583116.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:56 PM Revision 98e77d59 (ceph): mon/PGMap: access num pgs by osd
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:38 PM rgw Feature #11945 (Resolved): rgw: radosgw-admin commands to control period - including commit
- ...
- 09:37 PM rgw Feature #11944 (Resolved): rgw: RESTful api for period operations
- ...
- 09:30 PM Linux kernel client Bug #11449: krbd: tripping over rbd_assert in rbd_img_obj_callback() on errors
- Made it into 4.0.3, 3.14.42, 3.10.78, 3.12.43, 3.18.14; Ubuntu 3.16.7-ckt12, 3.19.8-ckt1. Waiting for Ubuntu 3.13.
- 09:24 PM Revision b255db82 (ceph): thrasher: Can't test ceph-objectstore-tool if nodes turned off (powercy...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 09:21 PM Feature #11943 (New): erasure code plugin for tornado code
- https://en.wikipedia.org/wiki/Tornado_code
https://www.eigenmagic.com/2015/06/08/erasure-coding-for-fun-and-profit/
- 09:21 PM Revision cf01b53f (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 8a9bcd1eb7e8e7acb132b09574bb5bf6d6d52b10)... - 09:07 PM Linux kernel client Bug #11841 (Need More Info): umount stuck on NFS over RBD switch over by using Pacemaker
- 09:06 PM Linux kernel client Bug #11841: umount stuck on NFS over RBD switch over by using Pacemaker
- I'm not exactly sure what's going on here. Are there any stuck osd requests (you can check with cat /sys/kernel/debu...
- 08:52 PM Linux kernel client Bug #11615 (Need More Info): Memory Spike and page fault in slab allocator
- 08:45 PM Linux kernel client Bug #11615: Memory Spike and page fault in slab allocator
- Sorry I didn't see this earlier.
The panic is not in ceph_kvmalloc() but in the guts of slab memory allocator. It... - 08:35 PM Feature #11900: introduce and document single-command procedure to pull drive from cluster
- cephx key
crush heirarchy
osd rm - 08:33 PM Feature #11882 (Fix Under Review): add 'PGs' column to 'ceph osd df'
- 08:33 PM Feature #9981 (In Progress): osd: cache: proxy writes (instead of unconditionally promoting)
- 08:33 PM Feature #11773: mon: better scrub
- 08:32 PM Feature #11942 (Resolved): move recovery to the unified opwq
- 08:32 PM Feature #10507 (Fix Under Review): mon: have an OpTracker
- 08:32 PM Feature #11299 (In Progress): generic plugin loader framework
- 08:32 PM Feature #8635 (Resolved): add scrub, snap trimming, should be items in the OpWQ with cost/priority
- 08:31 PM Revision eabe37fb (ceph): Merge pull request #440 from ceph/wip-fs-clientnum
- Reduce fs test node usage
Reviewed-by: John Spray <john.spray@redhat.com> - 07:32 PM Revision 5fb85614 (ceph): 0.94.2
- 06:47 PM Bug #8498: udev rules not used on RHEL6/CentOS6
- > I see the same issue on one of the production host, rebooting the host deletes '/dev/disk/by-partuuid/'
this is ... - 06:29 PM Bug #8498: udev rules not used on RHEL6/CentOS6
- I see the same issue on one of the production host, rebooting the host deletes '/dev/disk/by-partuuid/'
Running "s... - 06:15 PM Revision abe4ec29 (ceph): rgw: remove trailing :port from host for purposes of subdomain matching
- Some clients (ahem, CrossFTP) include the :port in the HTTP_HOST header.
Strip it out.
Switch req_info field to a st... - 05:54 PM Revision 8d7024a2 (ceph): Merge pull request #4775 from yuyuyu101/wip-async-crc-decouple
- AsyncMessenger: Make send/receive logic independent
Reviewed-by: Sage Weil <sage@redhat.com> - 05:22 PM rbd Bug #11938 (Fix Under Review): Periodic failure of TestLibRBD.BlockingIO
- *master PR*: https://github.com/ceph/ceph/pull/4912
- 04:26 PM rbd Bug #11938 (Resolved): Periodic failure of TestLibRBD.BlockingIO
- ...
- 05:18 PM devops Bug #11927 (Closed): nuke stale failed on vps
- That was my mistake not passing "--unlock"
- 05:16 PM rgw Feature #11939 (Resolved): rgw: dynamic reconfiguration
- No need to restart rgw after changing configuration
- 04:31 PM Revision a3f9cba7 (ceph): config_opts: turn down default recovery tunables
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 03:17 PM Feature #9720 (Resolved): erasure-code: non regression should test jerasure variants
- 02:37 PM Cleanup #11932 (Fix Under Review): ceph_erasure_code_non_regression s/stipe/stripe/
- https://github.com/ceph/ceph/pull/4910
- 02:22 PM Cleanup #11932 (Resolved): ceph_erasure_code_non_regression s/stipe/stripe/
- the actual option being used is however correct and the payloads have been verified to be of the desired size / strip...
- 02:35 PM Revision e4011158 (ceph): tests: ceph_erasure_code_non_regression s/stipe/stripe/
- Synchronize withe the ceph-erasure-code-corpus submodule in which all
file names were modified to fix the typo.
http... - 02:32 PM rgw Feature #11935 (Fix Under Review): rgw: create immutable metadata objects
- When applying a metadata change, also create an immutable metadata object that represents this change. When applying ...
- 02:30 PM rgw Feature #11934 (Resolved): rgw: metadata log sync work
- We'll change the way we sync the metadata: instead of reading log on source zone and apply it on the metadata objects...
- 02:28 PM Revision 7e0536af (ceph): Merge pull request #4815 from dachary/wip-9720-erasure-code-corpus-vari...
- tests: sync ceph-erasure-code-corpus to verify jerasure variants
Reviewed-by: Andreas Peters <andreas.joachim.peters... - 02:25 PM rgw Feature #11933 (Resolved): rgw: create realm and period data structures
- - define data structures
- radosgw-admin commands to control - 01:50 PM Bug #11931 (Resolved): make -j4 check does not run more than one job on ubuntu precise
- 12:16 PM Bug #11931 (Fix Under Review): make -j4 check does not run more than one job on ubuntu precise
- https://github.com/ceph/ceph/pull/4908
- 11:34 AM Bug #11931: make -j4 check does not run more than one job on ubuntu precise
- http://lists.gnu.org/archive/html/automake/2012-12/msg00038.html...
- 11:33 AM Bug #11931 (Resolved): make -j4 check does not run more than one job on ubuntu precise
- ubuntu precise and centos 6.5 have automake 1.11. It runs more than one job on ubuntu trusty that has automake 1.14
... - 01:50 PM Revision b2399453 (ceph): Merge pull request #4908 from dachary/wip-11931-parallel-tests
- tests: automake 1.11 needs parallel-tests
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 12:56 PM Revision 9193afd3 (ceph): tests: automake 1.11 needs parallel-tests
- Prior to automake 1.13 the default behavior was serial-tests meaning
tests from make check were run one after the oth... - 12:02 PM rbd Cleanup #11906 (Rejected): reduce test verbosity
- it will be resolved as part of http://tracker.ceph.com/issues/11931 by enabling parallel test on automake 1.11 (it's ...
- 10:50 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- For completeness, here is how I am setting up the build environment:...
- 10:47 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- I ran run-make-check.sh again on a clean checkout of master. Again ceph_objectstore_tool.py is the only failing test,...
- 09:43 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- maybe the pid file does not exist for some reason: it's the only way kill_daemon could return without actually killin...
- 09:38 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- the machine running the tests does not have a SSD and make -j4 ( nproc == 8 ) and is therefore expected to be very sl...
- 09:34 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- 09:34 AM Bug #11930: test/ceph_objectstore_tool.py fails with OSD has the store locked
- (11:29:50) loicd: https://github.com/ceph/ceph/blob/master/src/init-ceph.in#L93
(11:31:17) loicd: https://github.c... - 09:32 AM Bug #11930 (Can't reproduce): test/ceph_objectstore_tool.py fails with OSD has the store locked
- When I run "run-make-check.sh" on master, all tests pass except ceph_objectstore_tool.py...
- 08:24 AM Feature #2305: Moving rbd images between pools
- I have to reopen this topic: why is it not possible to move a rbd image to another pool?
The reason why I reopen t... - 06:26 AM Revision 83f81987 (ceph): Removed unnecessary inclusion of iostream
- In several files the iostream wasn't being used, so it got removed.
In other files the iostream inclusion was replace... - 06:14 AM Revision 57eddf0f (ceph): osd: using is_omap instead of test_flag(pg_pool_t::FLAG_OMAP)
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:14 AM Revision 1ffced35 (ceph): osd: add bool supports_omap() in pg_pool_t.
- Using this func judge pg whether support omap operations.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 05:32 AM Revision bfb92bd1 (ceph): Merge pull request #4879 from SUSE/wip-master-specfile-cleanup
- ceph.spec.in: remove duplicate BuildRequires
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Kefu Chai ... - 03:16 AM Bug #11928 (Duplicate): osd: avoid multi set osd_op.outdata in tier pool
- There are two read op on the same object for ec pool. First op read
miss happend, call do_proxy_read and promote_obj... - 02:58 AM Revision 75465eb7 (ceph): osd/ReplicatedPG: Don't create objectcontext when remove tmp-obj for pr...
- If on objectcontext for tmp-obj dosen't find, there must be a bug.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 02:57 AM Revision cbf1d34f (ceph): osd/ReplicatedPG: For prmote object, if met error, delete the tmp obj.
- If promote large object, it need copy some times, if not the first time
met EIO, it should romove the tmp object
Sig... - 02:54 AM Revision e6334bdc (ceph): osd/ReplicatedPG: Only promote object success, it can requeue proxy-rea...
- For example, it promtoe object met data digest error, it still try
proxy-read continue.
Signed-off-by: Jianpeng Ma <... - 02:04 AM Revision 228ee47c (ceph): Merge pull request #4784 from ceph/wip-10794
- ceph-objectstore-tool improvements
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:37 AM Revision ba5b3bb9 (ceph): add log-rotate configs to the userspace suite
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 12:36 AM Revision 5935f86e (ceph): ceph: enable mds log rotation
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 12:36 AM Revision 96f3eb9d (ceph): ceph: support arbitrarily-named daemons in logrotate
- And make it more configurable in terms of sizes.
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 12:29 AM Revision 281058cb (ceph): suites/multimds: use 2-node clusters for pure userspace subsuites
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 12:29 AM Revision dd2fa897 (ceph): suites/fs: use a two-node layout for most userspace tests
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 12:20 AM Revision 01256c9b (ceph): suites/fs: switch standby-replay tests to use a smaller cluster
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
06/08/2015
- 11:55 PM devops Bug #11927 (Closed): nuke stale failed on vps
- ...
- 11:01 PM devops Bug #11581: "port 22: No route to host" errors in the labs
- Add http://tracker.ceph.com/issues/11925 #11925
- 09:55 PM CephFS Support #11923 (Resolved): MDS init script starts multiple instances when MDS is referenced in ce...
- MDS component init script does not seem to be able to properly differentiate between auto-detected instances and inst...
- 08:57 PM devops Bug #11922 (Won't Fix): Missing "ceph-release-1-0.el6.noarch.rpm" in upgrade:firefly-firefly-dist...
- firefly v0.80.10 validation
Run: http://pulpito.ceph.com/teuthology-2015-06-05_17:00:01-upgrade:firefly-firefly-di... - 08:57 PM rbd Bug #11895 (Duplicate): Core dump while trying to look at an image whose parent is in pool to whi...
- Thanks for checking!
- 07:57 PM rbd Bug #11895: Core dump while trying to look at an image whose parent is in pool to which the user ...
- I recreated this issue with RHEL 7.1 x86 ceph 0.80.7.
I then upgraded ceph to 0.80.9.
The issue did not reproduce... - 08:35 PM CephFS Bug #6613: samba is crashing in teuthology
- Seeing in release firefly v0.80.9 validation
Run: http://pulpito.ceph.com/ubuntu-2015-06-08_11:05:13-samba-firefly... - 07:36 PM Revision ebc38f4a (ceph): Merge pull request #4903 from theanalyst/doc/arch-watch-notify
- doc: architecture minor fixes in watch notify
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:51 PM Revision 437c9e1e (ceph): doc: architecture minor fixes in watch notify
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
- 06:11 PM Revision 21f9e1f6 (ceph): ceph.spec.in: remove duplicate BuildRequires
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 06:06 PM Bug #11461 (Resolved): arm64: crc32 macro not available on older kernel
- Resolved a8500ce981c563ece34e7171571b6b56663ae6b5
- 05:54 PM Backport #11908 (In Progress): Almost all OSDs in the cluster crashing at the same time, repeatedly
- 05:49 PM Revision c7b6a637 (ceph): ReplicatedPG::finish_ctx: take excl lock if operation is rw
- Fixes: #11677
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 5c2b795724423ed484ab451de855dd... - 05:49 PM Revision bfb14426 (ceph): ReplicatedPG::release_op_ctx_locks: requeue in scrub queue if blocked
- Otherwise we can reorder an op around another op which got blocked by a
scrub which started after the first blocked o... - 05:49 PM Revision 25c730bd (ceph): test/librados/snapshots.cc: add test for 11677
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit c2d17b927f8a222164b3bf2922a4ff337696f566) - 05:49 PM Revision 4cdc5f7d (ceph): RadosModel: assert exists on subsequent writes
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 121aa3bc612b86281535ac3bcfe98bc99bc99ace) - 05:49 PM Revision 1550a569 (ceph): RadosModel: randomly prefix delete with assert_exists
- Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 4fe7d2abdff2fce359e5e992206644cc03825ee0) - 05:33 PM Backport #11911 (In Progress): start_flush: filter out removed snaps before determining snapc's
- 05:30 PM Revision 3d74164d (ceph): ReplicatedPG::trim_object: write filtered snapset while we're at it
- If we trimmed an object, we might as well remove the obsolete snaps
as well.
Signed-off-by: Samuel Just <sjust@redha... - 05:30 PM Revision a1161540 (ceph): ReplicatedPG: start_flush: use filtered snapset
- Otherwise, we might send our deletes based on deleted snaps. This is
problematic since we may have trimmed the clone... - 05:29 PM Revision b711e312 (ceph): Transaction Id added in response
- Signed-off-by: Abhishek Dixit dixitabhi@gmail.com
- 04:27 PM Revision 142a6ce7 (ceph): Merge pull request #4880 from SUSE/wip-master-specfile-cleanup2
- ceph.spec.in: move specific BuildRequires to where they belong
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Revie... - 04:17 PM Bug #11914 (Can't reproduce): "Caught signal" in teuthology-2015-06-04_11:23:35-rados-firefly---b...
- This is part of firefly v0.80.10 validation.
NOTE: this test passed on rerun (http://pulpito.ceph.com/teuthology-2... - 03:33 PM rgw Bug #11795: "test_multipart_upload_small ... FAIL" in smoke-master-distro-basic-typica run
- Run: http://pulpito.ceph.com/teuthology-2015-06-05_05:00:02-smoke-master-distro-basic-multi/
Job: 921266
Logs: http... - 02:12 PM Revision 2c1f4d4a (ceph): Merge pull request #4893 from dachary/wip-11272-ceph-disk-false-negative
- tests: ceph-disk.sh test zap gitbuilder false negative
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:53 PM CephFS Bug #11913: Failure in TestClusterFull.test_barrier
- (Referring to ceph-qa-suite/tasks/cephfs/test_full.py::test_barrier().)
So mount.a is doing open_no_data("alpha") ... - 11:21 AM CephFS Bug #11913 (Resolved): Failure in TestClusterFull.test_barrier
http://pulpito.ceph.com/teuthology-2015-06-05_23:04:02-fs-master---basic-multi/922578/
mount_a is getting the ne...- 12:48 PM Feature #11904: ceph-cli: let "ceph report" support compressed json dump
- There has been discussion about making Formatter provide streaming output instead of composing everything into one bi...
- 09:10 AM Backport #11878 (In Progress): Clock skew causes missing summary and confuses Calamari
- 02:48 AM Revision b1ff7396 (ceph): osdc: add epoch_t last_force_resend in Op/LingerOp.
- Using this field record the pg_poo_t::last_force_op_resend to avoid op
endless when osd reply with redirect.
Fixes: ... - 02:39 AM Bug #11905 (Resolved): mon/osd-erasure-code-profile.sh assumes isa is available
- 02:38 AM Revision 66f3b192 (ceph): Merge pull request #4888 from dachary/wip-11905-test-isa
- tests: skip isa tests if the plugin is not available
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:06 AM Revision 26be86f6 (ceph): crush/CrushWrapper: fix adjust_subtree_weight debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:06 AM Revision b461dc2e (ceph): unittest_crush_wrapper: test adjust_subtree_weight
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:06 AM Revision 1da96ab8 (ceph): crush/CrushWrapper: adjust subtree base in adjust_subtree_weight
- We were correctly adjusting all the children, but the subtree root was
not being updated.
Fixes: #11855
Signed-off-b... - 12:06 AM Revision 551ab2d6 (ceph): crush/CrushWrapper: return changed from adjust_subtree_weight
- Signed-off-by: Sage Weil <sage@redhat.com>
06/07/2015
- 05:11 PM Backport #11862 (In Progress): missing man pages for ceph-create-keys, ceph-disk-*
- 05:10 PM Backport #11911 (Resolved): start_flush: filter out removed snaps before determining snapc's
- https://github.com/ceph/ceph/pull/4899
- 05:08 PM Backport #11910 (Resolved): mon: "pg ls" is broken
- https://github.com/ceph/ceph/pull/5160
- 04:32 PM Backport #11908 (Resolved): Almost all OSDs in the cluster crashing at the same time, repeatedly
- https://github.com/ceph/ceph/pull/4902
- 04:31 PM Bug #11484: OPT_INT option interprets "3221225472" as -1073741824, and crashes in Throttle::Throt...
- @loic sorry it was unintended.. Nathan informed me of the mistake I had done; basically if we use the script and feed...
- 11:22 AM Bug #11484: OPT_INT option interprets "3221225472" as -1073741824, and crashes in Throttle::Throt...
- @abhishek did you intend to edit the summary to include a link to the master pull request https://github.com/ceph/cep...
- 03:19 PM Bug #11905: mon/osd-erasure-code-profile.sh assumes isa is available
- https://github.com/ceph/ceph/pull/4888
- 08:30 AM Bug #11905 (Resolved): mon/osd-erasure-code-profile.sh assumes isa is available
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-i386-basic/log.cgi?log=29e3618f9852ce80d0f6699e5d3a5f...
- 02:54 PM RADOS Bug #11907 (Closed): crushmap validation must not block the monitor
- Not only does it fail if "the machine is slow":http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-precise-amd64...
- 02:31 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- master pull request: https://github.com/ceph/ceph/pull/4803
- 12:04 PM Backport #11824: implicit erasure code crush ruleset is not validated
- The upstream PR is not merged in master yet. Once that is merged we'll have a backport
- 11:58 AM rbd Cleanup #11906 (Rejected): reduce test verbosity
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-precise-amd64-basic/log.cgi?log=4d58c07490a1714fa65c8a79cb14...
- 11:52 AM Revision 3e128637 (ceph): tests: ceph-disk.sh test zap gitbuilder false negative
- When looking for an error message and testing ceph disk zap, use grep -q
to not display the error message that will b... - 09:25 AM Backport #11760 (In Progress): ceph-disk: get_partition_type fails on /dev/cciss...
- 09:22 AM Backport #11740 (In Progress): crush: take crashes due to invalid arg
- 09:22 AM Revision 82988d61 (ceph): ceph-disk: support NVMe device partitions
- Linux nvme kernel module v0.9 enumerate devices as following:
/dev/nvme0 - characted revice
/dev/nvme0n1 - whole blo... - 09:19 AM Revision 56565ee1 (ceph): crush: fix crash from invalid 'take' argument
- Verify that the 'take' argument is a valid device or bucket. Otherwise,
ignore it (do not add the value to the worki... - 09:19 AM Revision bd91fb02 (ceph): mon: prevent bucket deletion when referenced by a rule
- If a rule references a bucket with 'take', prevent deletion.
Fixes: #11602
Signed-off-by: Sage Weil <sage@redhat.com... - 09:15 AM Backport #11716 (In Progress): utf8 and old gcc breakage on RHEL6.5
- 09:07 AM Backport #11738 (In Progress): OPT_INT option interprets "3221225472" as -1073741824, and crashes...
- 09:02 AM Revision 9b947fa3 (ceph): common/config: detect overflow of int values
- * #include "strtol.h" in strtol.cc, to ensure the function defintions
are consistent.
* add a test accordingly
* fi... - 09:02 AM Revision 1440122d (ceph): common/config: detect overflow of float values
- Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 1ff409ef8d022a1a84d034bd3db976c4d769e993) - 09:01 AM Backport #11701: make the all osd/filestore thread pool suicide timeouts separately configurable
- Looks like this may need the corresponding dev to do the backport.
- 08:53 AM Revision 4d58c074 (ceph): tests: skip isa tests if the plugin is not available
- http://tracker.ceph.com/issues/11905 Fixes: #11905
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 08:52 AM Revision 90baef86 (ceph): tests: use erasure_code_plugin_exists from ceph-helpers.sh
- Instead of the local plugin_exists helper that does the same.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 08:51 AM Revision deb651b6 (ceph): tests: implement erasure_code_plugin_exists in ceph-helpers.sh
- Return 0 if the erasure code *plugin* is available, 1 otherwise.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 08:34 AM rgw Documentation #10184: rgw: document swift temp url functionality
- Fixed in https://github.com/ceph/ceph/pull/3648
- 08:33 AM rgw Documentation #10184 (Resolved): rgw: document swift temp url functionality
- 08:29 AM Backport #11736 (In Progress): ceph: cli interactive mode does not understand quotes
- 07:58 AM Bug #10358 (Resolved): ceph osd erasure-code-profile set myprofile k=1 should fail
- 07:58 AM Revision 2beba7c9 (ceph): Merge pull request #4713 from dachary/wip-10358-erasure-code-k-1-m-1
- ceph osd erasure-code-profile set myprofile k=1 should fail
Reviewed-by: Andreas Peters <andreas.joachim.peters@cern... - 07:45 AM CephFS Backport #11737 (In Progress): MDS is crashed (mds/CDir.cc: 1391: FAILED assert(!is_complete()))
- 07:40 AM Revision d723e115 (ceph): mds: clear CDir::STATE_REJOINUNDEF after fetching dirfrag
- Fixes: #11541
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit ab1e5394dc778f6799472bd79a4d9ba7... - 07:36 AM rbd Backport #11853 (In Progress): librbd: new config option for legacy blocking aio behavior
- 07:33 AM rgw Backport #11755 (In Progress): Object copy bug
- 07:29 AM Revision 54f4e7d4 (ceph): rgw: Use attrs from source bucket on copy
- On copy objects, when bucket source is the same as the destination, use attrs
from source bucket.
Fixes: #11639
Sig... - 06:54 AM Revision 9dfef600 (ceph): rgw: always check if token is expired
- Fixes: #11367
Currently token expiration is only checked by the token cache. With PKI
tokens no expiration check is ... - 06:34 AM rgw Backport #11722 (In Progress): Keystone PKI token expiration is not enforced
- 05:50 AM Revision fdb43ebe (ceph): ceph.spec.in: tweak ceph-common for SUSE/openSUSE
- ceph-common needs python-argparse in SUSE/openSUSE and
needs redhat-lsb-core only in RHEL/CentOS/Fedora.
http://trac... - 04:38 AM Feature #10098: wanted: command to clear 'incomplete' PGs
- I have this exact problem on my 0.94.1.2 cluster. It's production but the data is mostly-replaceable, so I'm willing ...
06/06/2015
- 10:43 PM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- I'm not making progress on this, unassigning.
- 10:23 PM Bug #11272 (Resolved): ceph-disk zap should ensure block device
- 10:22 PM Bug #11624 (Resolved): test/cephtool-test-mon.sh can fail due to timing issue
- 10:15 PM Revision 864e2007 (ceph): tests: add --{show_,}path to ceph_erasure_code_non_regression
- The directory in which the payload is stored is created from the plugin
parameters. The --show-path shows the directo... - 10:15 PM Revision fda586f5 (ceph): tests: sync ceph-erasure-code-corpus to verify jerasure variants
- http://tracker.ceph.com/issues/9720 Refs: #9720
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 10:12 PM Bug #11346 (Resolved): erasure-code: add non regression tests for isa-l with k=10, m=4
- 10:12 PM Revision 1d60786c (ceph): Merge pull request #4811 from dachary/wip-11346-isa
- ceph-erasure-code-corpus: isa: add k=10 m=4
Reviewed-by: Yuan Zhou <yuan.zhou@intel.com> - 10:05 PM Fix #11663 (Resolved): erasure-code-profile: verify profile content
- 10:02 PM devops Bug #11901 (Resolved): keyutils-devel no longer in buildrequires for centos7
- 08:29 AM devops Bug #11901 (Fix Under Review): keyutils-devel no longer in buildrequires for centos7
- https://github.com/ceph/ceph/pull/4878
- 07:58 AM devops Bug #11901 (Resolved): keyutils-devel no longer in buildrequires for centos7
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/5700/console
A large part of the build requires a... - 09:51 PM Revision 3ec41030 (ceph): erasure-code: add sanity check to guard against k=1
- Add a call to ErasureCode::sanity_check_k for the isa and jerasure
plugins, with associated tests.
http://tracker.ce... - 01:24 PM Revision efededa0 (ceph): Merge pull request #4882 from SUSE/wip-submitting-patches-clarification
- SubmittingPatches: clarify how Reviewed-by lines are added
Reviewed-by: Sage Weil <sage@redhat.com> - 01:16 PM Revision 85b327f8 (ceph): SubmittingPatches: clarify how Reviewed-by lines are added
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 12:37 PM Revision eefdeb6b (ceph): Merge pull request #4878 from dachary/wip-11901-spec
- ceph.spec.in: add missing BuildRequires from SUSE block
Reviewed-by: Nathan Cutler <ncutler@suse.cz> - 12:14 PM Revision e1cb7e51 (ceph): ceph.spec.in: move specific BuildRequires to where they belong
- Move distro-specific BuildRequires out of "common" section and
into the appropriate %if statement in the "specific" s... - 10:31 AM Revision 739ef0f9 (ceph): install-deps.sh: detect yum-builddep errors
- yum-builddep does not exit on error when an error happens: grep the
output for the error: string instead.
Signed-off... - 10:05 AM Revision 34e4dd9c (ceph): ceph.spec.in: add missing BuildRequires from SUSE block
- The %endif removed by f94f23297c05019db754ec53b4ceaea7706152c9 is restored.
The %else removed by 75e87a20dac05441b97c... - 09:56 AM Feature #11904 (New): ceph-cli: let "ceph report" support compressed json dump
- ceph report is very useful to monitor the status of ceph whatever io statistic or cluster status. But for a large clu...
- 09:52 AM CephFS Feature #11903 (Resolved): libcephfs: implement read/write interface support "struct iovec"
- Now if qemu virtfs directly call libcephfs api, it need to retranslate iov structure to continuous buffer. We should ...
- 08:06 AM Revision ba1a0167 (ceph): admin/build-doc: fix dependency checks
- http://tracker.ceph.com/issues/11857 Fixes: #11857
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked ... - 07:59 AM devops Backport #11902 (Resolved): admin/build-doc: script fails silently under certain circumstances
- https://github.com/ceph/ceph/pull/4877
- 07:58 AM devops Bug #11857 (Pending Backport): admin/build-doc: script fails silently under certain circumstances
- 07:43 AM Revision 37f73607 (ceph): erasure-code: implement ErasureCode::sanity_check_k
- Implement the ErasureCode::sanity_check_k helper for plugins
that need to verify k >= 2.
http://tracker.ceph.com/iss... - 06:30 AM Revision 5a60a034 (ceph): man/ceph-create-keys.8: add missing file
- This is the generated manpage, taken from a local build of master
Signed-off-by: Nathan Cutler <ncutler@suse.com>
(c... - 06:29 AM Revision 19305b89 (ceph): doc: add ceph-create-keys.8
- Fixes: #10725
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 27cee2f1f46a9f47cda9dfeb56ff1259...
06/05/2015
- 10:57 PM RADOS Bug #11855 (Fix Under Review): ceph osd crush reweight-subtree does not reweight parent node
- 03:24 PM RADOS Bug #11855 (In Progress): ceph osd crush reweight-subtree does not reweight parent node
- 09:39 PM Feature #11900 (Resolved): introduce and document single-command procedure to pull drive from clu...
- Description of problem:
User would like a command/script to manually remove a disk, and include in official docume... - 08:58 PM rbd Backport #11770 (In Progress): librbd: aio calls may block
- 08:19 PM rbd Backport #11770: librbd: aio calls may block
- *hammer PR*: https://github.com/ceph/ceph/pull/4875
- 08:50 PM Revision 7f8b8660 (ceph): Merge pull request #449 from ceph/wip-fsync
- tasks/cephfs: add TestClientRecovery.test_fsync
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:20 PM rbd Backport #11853: librbd: new config option for legacy blocking aio behavior
- *hammer PR*: last two commits from https://github.com/ceph/ceph/pull/4875
- 08:15 PM devops Feature #11881 (In Progress): ceph-disk support for multipath
- 08:11 PM Revision a28adfbd (ceph): WorkQueue: add new ContextWQ work queue
- The queue holds a collection of Context pointers that will
be completed by the thread pool.
Signed-off-by: Jason Dil... - 08:11 PM Revision ffd0933d (ceph): WorkQueue: added virtual destructor
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit b3f5a75332c058816dc39b71e9d2b36e752159f4) - 08:02 PM rbd Bug #11895: Core dump while trying to look at an image whose parent is in pool to which the user ...
- I tired putting 0.80.9 on RHEL 7.1 ppc64 using the Fedora RPMs above it pulled in too many package dependencies that ...
- 07:05 PM rbd Bug #11895: Core dump while trying to look at an image whose parent is in pool to which the user ...
- It's a client-only fix. I would skip v0.80.8, since it contained a performance regression for RBD, and test against ...
- 06:46 PM rbd Bug #11895: Core dump while trying to look at an image whose parent is in pool to which the user ...
- I'm currently on RHEL 7.0 ppc64 BE and I don't believe I can get v0.80.8 on there. I may try putting Fedora ppc64 0....
- 05:50 PM rbd Bug #11895 (Need More Info): Core dump while trying to look at an image whose parent is in pool t...
- I believe this issue has since been addressed by #10030 in the v0.80.8 release of Firefly. Do you still see the issu...
- 02:59 PM rbd Bug #11895 (Duplicate): Core dump while trying to look at an image whose parent is in pool to whi...
- Core dump while trying to look at an image whose parent is in pool to which the user does not have access.
Affected ... - 07:17 PM Revision a8351eb3 (ceph): unittest_crush_wrapper: attach buckets to root in adjust_item_weight test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:12 PM Revision 14c60b28 (ceph): unittest_crush_wrapper: parse env
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:12 PM Revision a8500ce9 (ceph): Merge pull request #4834 from liewegas/wip-11461
- fix build on arm w/ old kernels
Signed-off-by: Noah Watkins <nwatkins@redhat.com> - 06:25 PM Revision 905a8670 (ceph): Merge remote-tracking branch 'origin/wip-client-fsync'
- Conflicts:
src/client/Client.cc
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:23 PM CephFS Bug #11807 (Resolved): workunits: stop rsyncing with /usr as the source material
- 3f4dfb80e32fba86e9076a2915197487bf899906
We can reopen if we decide this needs a backport. - 06:22 PM Revision 3f4dfb80 (ceph): Merge pull request #4831 from ceph/wip-11807
- qa: fix multiple_rsync.sh to avoid using /usr/ directly
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: S... - 06:21 PM Revision 7dc602af (ceph): Merge pull request #4743 from ceph/wip-client-oldest-tid
- Wip client oldest tid
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:16 PM Revision 3673c8be (ceph): Merge pull request #4723 from ceph/wip-snap-misc
- Wip snap misc
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:15 PM Fix #11590 (Resolved): MDSMonitor: handle MDSBeacon messages properly
- commit:5e99022fc68ba5305f8d69d663746d6567168ff9
- 06:15 PM Revision 5e99022f (ceph): Merge pull request #4702 from tchaikov/wip-fix-11590
- mon: always reply mdsbeacon
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:14 PM CephFS Bug #11504 (Resolved): CephFS restriction on removing cache tiers is overly strict
- commit:5a3da7b891bf18e0f164352dd0010c7969233d72
- 06:13 PM Revision 5a3da7b8 (ceph): Merge pull request #4602 from ceph/wip-11504
- mon: refine check_remove_tier checks
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:07 PM Linux kernel client Bug #11898: Writing on forced umount causes silent data loss
- Is this in any way different from what happens against any other filesystem? This sounds more like something is bad i...
- 04:21 PM Linux kernel client Bug #11898 (Resolved): Writing on forced umount causes silent data loss
- Writing on a CephFS bind mount, (for example, inside a LXC container), for which the parent is umounted or broken, em...
- 05:59 PM Revision 997b3f99 (ceph): 9.0.1
- 05:40 PM devops Bug #11899 (Rejected): Build v0.87.2 (giant)
- This is needed for firefly release testing...
- 05:35 PM devops Bug #8160: multipath-tools does not co-exist with ceph
- Ian, I don't see a multipath issue associated with ceph-deploy, should I re-open this one ?
- 05:12 PM devops Bug #11887 (Resolved): rpm: unconditionally package rbd-replay-prep(8)
- 06:15 AM devops Bug #11887 (Resolved): rpm: unconditionally package rbd-replay-prep(8)
- https://github.com/ceph/autobuild-ceph/pull/40 verifies all files are packaged (~april 2015) and revealed
* master... - 05:12 PM devops Backport #11888 (Resolved): rpm: unconditionally package rbd-replay-prep(8)
- 06:25 AM devops Backport #11888: rpm: unconditionally package rbd-replay-prep(8)
- running in http://ceph.com/gitbuilder.cgi to verify it passes gitbuilder-ceph-rpm-centos7-amd64-basic
- 06:18 AM devops Backport #11888 (In Progress): rpm: unconditionally package rbd-replay-prep(8)
- 06:17 AM devops Backport #11888 (Resolved): rpm: unconditionally package rbd-replay-prep(8)
- https://github.com/ceph/ceph/pull/4865
- 04:53 PM rbd Documentation #11750 (New): Can't create image with format 2 with non-admin user
- 04:33 PM Revision f97ce46e (ceph): tests: new test for transitioning exclusive lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:33 PM Revision d9dd5c58 (ceph): librbd: don't cancel request lock early
- It's possible that a stale notice is received and will
be discarded after the request lock has been canceled.
This wi... - 04:33 PM Revision d2a1c226 (ceph): tests: verify that librbd will periodically resend lock request
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:33 PM Revision 1f130f32 (ceph): Merge pull request #4865 from dachary/wip-11888-giant
- rpm: unconditionally package rbd-replay-prep(8)
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 04:29 PM Revision 2b6d0633 (ceph): librbd: don't hold owner_lock for write during flush
- The various IO callback codepaths will attempt to take
the lock, which will result in deadlock since the flush
cannot... - 04:29 PM Revision 37c74e6e (ceph): librbd: retry lock requests periodically until acquired
- If the exclusive lock owner acks the lock release request but crashes
before it actually releases the lock, the reque... - 04:29 PM Revision 3e1e561c (ceph): librados_test_stub: watcher id should be the instance id (gid)
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:29 PM Revision b951a739 (ceph): librbd: improve debugging output for ImageWatcher
- Include the instance pointer so that different images
can be differentiated in the logs.
Signed-off-by: Jason Dillam... - 04:29 PM Revision 879b8a73 (ceph): common: Mutex shouldn't register w/ lockdep if disabled
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:24 PM Revision 43e0e3cd (ceph): librbd: avoid infinite loop if copyup fails
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:24 PM Revision 9055eb6c (ceph): librbd: hide ENOENT errors during copyup operations
- It's possible for this to occur when shrinking an image with
snapshots and a zeroed data block.
Signed-off-by: Jason... - 04:24 PM Revision 0766734a (ceph): librbd: don't attempt to (re-)update the object map for CoW
- The AbstractWrite state machine has already taken care of updating
the object map to the correct state.
Signed-off-b... - 04:24 PM Revision 1e0f1283 (ceph): librbd: CoR should copyup empty object to prevent future CoR attempts
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:24 PM Revision cd0fd833 (ceph): librbd: whole-object discards should copyup when snapshots exist
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:20 PM Bug #11856: osd - scrubbing slot leaked
- New PR - https://github.com/ceph/ceph/pull/4874
- 07:19 AM Bug #11856: osd - scrubbing slot leaked
- By going through the code, following seems a potential leak:
When there is map change to the PG, it relies on Repl... - 03:59 PM Revision 788542cc (ceph): Merge pull request #4781 from ceph/wip-librbd-perf-counters
- librbd: re-add missing discard perf counters
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:54 PM Revision d345061a (ceph): tests: verify copyup behavior during object discard
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:54 PM Revision f8c831e6 (ceph): librbd: trim operation should issue object copyups for overlap extent
- Now that child images can be disassociated from their parents even
when snapshots exist, trim operations need to copy... - 03:46 PM Revision 336c3bfb (ceph): librbd: include actual write op type in AbstractWrite debug output
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Conflicts:
src/librbd/AioRequest.cc - 03:46 PM Revision da5b565f (ceph): librbd: add new copyup helper method
- ImageCtx::get_copyup_snap_id returns the oldest snapshot
to be used when calculating parent image overlaps.
Signed-o... - 03:46 PM Revision 77343880 (ceph): tests: verify that copyup properly handle image shrinking
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:46 PM Revision 62f13066 (ceph): librbd: always use current parent overlap
- With deep-copyup, there is no longer a reason to shrink the
parent overlap for IO operations.
Signed-off-by: Jason D... - 03:46 PM Revision 1525ecbd (ceph): librados_test_stub: truncate should honor op snapshot context
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:46 PM Revision 325a066c (ceph): librbd: default to data_ctx for post-copyup operations
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:46 PM Revision 64f84182 (ceph): librbd: new AioTrim operation to force copyup on object removal
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:45 PM Revision 712b2da4 (ceph): librbd: removed unused ImageCtx::parent_io_len method
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:24 PM rgw Bug #11864: error in ext_mime_map_init() when /etc/mime.types is missing
- urgent until we know what the impact is
- 03:13 PM rbd Documentation #11897 (Resolved): Documentation on ceph auth caps is not specific enough.
- Please excuse me if this needs to be under Tracker: Documentation rather than Tracker: Bug. I don't know the semanti...
- 03:05 PM Bug #11896 (Resolved): ceph command hangs and calls repeatedly gettimeofday when rdtsc() in Cycle...
- Earlier version of Cycles.h aborted compilation when the OS/arch was not one of the defined ones. Now it only gives w...
- 01:22 PM Revision f2897886 (ceph): Merge pull request #4870 from joaquimrocha/extra_doc_info_for_debug_option
- build: Add info about tests to --with-debug option
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:17 PM Revision 63aa2e6a (ceph): build: Add info about tests to --with-debug option
- The configure's --with-debug option builds also some of the tests
so this should be mentioned in its doc string in or... - 09:56 AM Revision 3a562b44 (ceph): Merge pull request #4866 from ddiss/fix_test_ceph_disk_dmcrypt_uuid_only
- tests: fix test_activate_dmcrypt uuid usage
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:39 AM Revision 7bef2d88 (ceph): tests: fix test_activate_dmcrypt uuid usage
- 4601e10800a63cf0e03108e1da0bf11c19c33e26 introduced a regression in that
an empty (uninitialised) OSD uuid is passed ... - 08:56 AM devops Bug #11673 (Resolved): Debian: ceph-test and rest-bench debug packages should require their respe...
- 08:52 AM rgw Backport #11891: packaging: package ceph-disk and mkcephfs
- My guess is that the two commits that are related to packaging in https://github.com/ceph/ceph/pull/4851 have been ad...
- 08:47 AM rgw Backport #11891 (Resolved): packaging: package ceph-disk and mkcephfs
- https://github.com/ceph/ceph/pull/4851
- 08:41 AM rgw Backport #11871 (Resolved): RGW does not send Date HTTP header when civetweb frontend is used
- 08:26 AM rgw Bug #10295 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- 08:25 AM rgw Backport #11720 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- 08:19 AM rgw Backport #11890: rgw: don't allow negative / invalid content length
- Although this commit comes from https://github.com/ceph/ceph/pull/2272 which resolves http://tracker.ceph.com/issues/...
- 08:17 AM rgw Backport #11890 (Resolved): rgw: don't allow negative / invalid content length
- https://github.com/ceph/ceph/pull/4829
- 06:22 AM Revision d2e7ef54 (ceph): rpm: unconditionally package rbd-replay-prep(8)
- The build system will conditionally build and install the
rbd-replay-prep utility based on the presence of lttng.
Co... - 01:55 AM Revision 792e9482 (ceph): Merge pull request #4528 from ceph/wip-librbd-helgrind
- librbd: correct issues discovered via lockdep / helgrind
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:43 AM rbd Backport #11852: librbd: new config option for legacy blocking aio behavior
- Nathan Cutler wrote:
> If this backport is satisfied by the last two commits in https://github.com/ceph/ceph/pull/48... - 12:37 AM Revision c1b2783b (ceph): Merge pull request #4857 from jdurgin/wip-rbd-features-constants
- update rbd features constants for python usage
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
06/04/2015
- 10:26 PM Feature #11882: add 'PGs' column to 'ceph osd df'
- I can have a look at this
- 07:47 PM Feature #11882 (Resolved): add 'PGs' column to 'ceph osd df'
- The number of PGs per OSD is nearly as important as the number of bytes it's storing.
- 08:52 PM Revision c352bcdc (ceph): librbd: AsyncObjectThrottle should always hold owner_lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:52 PM Revision d6b733db (ceph): librbd: simplify state machine handling of exclusive lock
- It is expected that all IO is flushed and all async ops are cancelled
prior to releasing the exclusive lock. Therefo... - 08:52 PM Revision 1b57cc1d (ceph): librbd: fix recursive locking issues
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:52 PM Revision a38f9e51 (ceph): osdc: ObjectCacher flusher might needs additional locks
- librbd requires the ObjectCacher flusher thread to acquire
an additional lock in order to maintain lock ordering
cons... - 08:52 PM Revision c9142fe3 (ceph): librbd: owner_lock should be held during flush request
- Flush might result in the cache writing out dirty objects, which
would require that the owner_lock be held.
Signed-o... - 08:52 PM Revision 45cb9cb5 (ceph): tests: enable lockdep for librbd unit tests
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:52 PM Revision 742a85d6 (ceph): tests: fix possible deadlock in librbd ImageWatcher tests
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:52 PM Revision 3d5cef38 (ceph): librbd: flush pending ops while not holding lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:52 PM Revision 5f157f20 (ceph): librbd: execute flush completion outside of cache_lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:51 PM Revision 218bc2d0 (ceph): librbd: add AsyncRequest task enqueue helper method
- In order to support the invariant that all state machine
callbacks occur without holding locks, transitions that
don'... - 08:51 PM Revision 66e74641 (ceph): librbd: disable lockdep on AioCompletion
- It is only used by clients and it causes a large slowdown
in performance due to the rate at which the lock is constru... - 08:49 PM Revision 3ad19ae3 (ceph): librbd: AioCompletion shouldn't hold its lock during callback
- The callback routine most likely will attempt to retrieve the result
code, which will result in a recursive lock atte... - 08:49 PM Revision e5ffae57 (ceph): WorkQueue: ContextWQ can now accept a return code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision 21f990ef (ceph): librbd: add work queue for op completions
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision 650ad32d (ceph): common: add valgrind.h convenience wrapper
- Conditionally support helgrind annotations if valgrind support is
enabled during the build.
Signed-off-by: Jason Dil... - 08:49 PM Revision 7c7df2ce (ceph): common: lockdep now support unregistering once destructed
- librbd use of an image hierarchy resulted in lock names being
re-used and incorrectly analyzed. librbd now uses uniq... - 08:49 PM Revision 6e400b90 (ceph): librados_test_stub: add support for flushing watches
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision b65ae4bc (ceph): librados_test_stub: fix helgrind warnings
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision c1e14451 (ceph): log: fix helgrind warnings regarding possible data race
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision c474ee42 (ceph): librbd: give locks unique names to prevent false lockdep failures
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:49 PM Revision 0024677d (ceph): librbd: complete cache read in a new thread context
- The ObjectCacher complete the read callback while still holding
the cache lock. This introduces lock ordering issues... - 08:32 PM Revision eb6a1df8 (ceph): pybind/rbd.py: update with new features constants
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 08:32 PM Revision 8baaf514 (ceph): librbd: describe the purpose of features constants
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 08:06 PM Revision fbe328e2 (ceph): librbd: add a constant for single-client-only features
- This way it's easy to disable them if you want to access an image from
multiple clients.
Signed-off-by: Josh Durgin ... - 06:25 PM Revision b7abc398 (ceph): Merge pull request #4717 from athanatos/wip-8635
- Wip 8635 -- Move scrub, snap_trim into a unified queue
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage W... - 06:24 PM Revision e5b18903 (ceph): Merge pull request #4718 from athanatos/wip-sync-omap
- FileStore: sync object_map when we syncfs
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:43 PM devops Feature #11881 (Resolved): ceph-disk support for multipath
- h3. Need review
* ceph : https://github.com/ceph/ceph/pull/5699
* ceph-qa-suite : https://github.com/ceph/ceph-qa... - 05:07 PM Revision d0f9c5f4 (ceph): Merge pull request #4851 from ceph/wip-10873-firefly
- rgw: generate the "Date" HTTP header for civetweb.
- 04:46 PM Revision 5ff80564 (ceph): Merge pull request #4839 from ceph/wip-fix-arm-linking-issue
- common/Cycles.cc: skip initialization if rdtsc is not implemented
Reviewed-by: Boris Ranto <branto@redhat.com>
Revie... - 04:03 PM Revision 23a09790 (ceph): Merge pull request #4852 from ceph/wip-rgw-vstart
- make vstart + rgw more useful
- 04:02 PM Revision 61bad558 (ceph): vstart.sh: set rgw dns name = localhost
- So we can test buckets in the URL by adding entries in /etc/hosts
Signed-off-by: Sage Weil <sage@redhat.com> - 02:24 PM Tasks #11847: OSD crashes under cached cluster benchmark
- yeah, i have the same guess as Haomai. Mark, it looks like a dup of #10988 . probably we should find a way to throttl...
- 02:04 PM Tasks #11847: OSD crashes under cached cluster benchmark
- I guess it should be os thread limit. You need to increase thread limit for osd
- 02:14 PM Revision 2eb096a5 (ceph): FileJournal: Remove CEPH_PAGE_SIZE assumptions
- Ceph currently assumes a FileJournal block_size equal to a multiple of
CEPH_PAGE_SIZE. For x86, this will always be 4... - 01:43 PM rbd Backport #11852 (Fix Under Review): librbd: new config option for legacy blocking aio behavior
- 01:42 PM rbd Backport #11852: librbd: new config option for legacy blocking aio behavior
- If this backport is satisfied by the last two commits in https://github.com/ceph/ceph/pull/4854 then it really doesn'...
- 01:16 PM rbd Backport #11852: librbd: new config option for legacy blocking aio behavior
- *firefly PR*: last two commits from https://github.com/ceph/ceph/pull/4854
- 01:40 PM Bug #9732: ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
- we can simply change @ReplicatedPG::get_hit_set_current_object()@ and @ReplicatedPG::get_hit_set_archive_object()@, t...
- 01:38 PM rbd Backport #11769: librbd: aio calls may block
- not in firefly-backports yet
- 12:06 AM rbd Backport #11769: librbd: aio calls may block
- *firefly PR*: https://github.com/ceph/ceph/pull/4854 -- DNM until Josh provides +1
- 01:28 PM rgw Backport #11874 (In Progress): Bucket header is enclosed by quotes
- 11:48 AM rgw Backport #11874 (Resolved): Bucket header is enclosed by quotes
- https://github.com/ceph/ceph/pull/4862
- 01:27 PM rgw Backport #11873 (In Progress): Bucket header is enclosed by quotes
- 11:46 AM rgw Backport #11873 (Resolved): Bucket header is enclosed by quotes
- https://github.com/ceph/ceph/pull/5730
- 01:20 PM Bug #8752: firefly: scrub/repair stat mismatch
- * *"2015-05-30 05:52:03.706223 osd.1 10.214.134.124:6804/31007 234 : [ERR] 3.0s0 scrub stat mismatch, got 2005/2009 o...
- 01:08 PM Bug #11262: hit set miscount with wip-11177
- ...
- 12:52 PM Bug #11869 (Resolved): install-deps.sh failed to download missing wheels
- https://github.com/ceph/ceph/pull/4856
- 04:03 AM Bug #11869: install-deps.sh failed to download missing wheels
- Xinze Chi wrote:
> [...]
>
> @kefu as you said
> > find a pypi mirror in mainland china. and see if our script ... - 03:03 AM Bug #11869: install-deps.sh failed to download missing wheels
- ...
- 02:43 AM Bug #11869: install-deps.sh failed to download missing wheels
- >> so we have two issues here:
>>
>> 1) we should check if we really populate *all* required wheels in install-deps... - 02:38 AM Bug #11869 (Resolved): install-deps.sh failed to download missing wheels
- if wheelhouse directory exists but not all of the wheels are downloaded, install-deps.sh simply ignores all the requi...
- 12:51 PM Revision 1a321e47 (ceph): rgw: Do not enclose the Bucket header in quotes
- Fixes: #11860
Signed-off-by: Wido den Hollander <wido@42on.com>
(cherry picked from commit 8af25faed93fe02d3dad585b85... - 12:51 PM Bug #11870 (Resolved): testdir/test-erasure-code : TEST_rados_put_get_isa fails on i386
- https://github.com/ceph/ceph/pull/4859
- 09:51 AM Bug #11870: testdir/test-erasure-code : TEST_rados_put_get_isa fails on i386
- 09:08 AM Bug #11870 (Resolved): testdir/test-erasure-code : TEST_rados_put_get_isa fails on i386
- see http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-i386-basic/log.cgi?log=779360cd96c796aa1237dd474a...
- 12:10 PM Backport #11879 (Resolved): Clock skew causes missing summary and confuses Calamari
- https://github.com/ceph/ceph/pull/4868
- 12:09 PM Backport #11878 (Resolved): Clock skew causes missing summary and confuses Calamari
- https://github.com/ceph/ceph/pull/4867
- 12:08 PM Bug #11877: Clock skew causes missing summary and confuses Calamari
- https://github.com/ceph/ceph/pull/3659
- 12:08 PM Bug #11877 (Resolved): Clock skew causes missing summary and confuses Calamari
- Thorsten Behrens writes in https://github.com/SUSE/ceph/commit/eaf6e0cf48488fe604d0ef0db164d44948d4e8d4
Always pr... - 11:50 AM Backport #11876 (Resolved): ceph-post-file fails on rhel7
- https://github.com/ceph/ceph/pull/5038
- 11:50 AM Backport #11875 (Resolved): ceph-post-file fails on rhel7
- https://github.com/ceph/ceph/pull/5037
- 11:44 AM rgw Backport #11872 (Resolved): RGW does not send Date HTTP header when civetweb frontend is used
- https://github.com/ceph/ceph/pull/5228
- 11:43 AM rgw Backport #11871 (Resolved): RGW does not send Date HTTP header when civetweb frontend is used
- https://github.com/ceph/ceph/pull/4851
- 11:07 AM Revision b501c418 (ceph): Merge pull request #4858 from SUSE/wip_ceph.spec.in_remove_extra_else_s...
- ceph.spec.in: remove extra %else statement
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:14 AM Revision 9d8ae1ed (ceph): Merge pull request #4859 from ceph/wip-fix-i386-test-11870
- test: fix the plugin_exists()
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:51 AM Revision 6bd425b0 (ceph): test: fix the plugin_exists()
- in 8e61a99, we try to init the plugin when user set a profile using
"ceph osd erasure-code-profile set <profile-name>... - 08:52 AM Revision 1957c88c (ceph): Merge pull request #4856 from ceph/wip-install-deps-11869
- install-deps.sh: create virtualenv only if necessary
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:11 AM Revision 75e87a20 (ceph): ceph.spec.in: remove extra %else statement
- Remove extra conditional.
Signed-off-by: Owen Synge <osynge@suse.com> - 08:01 AM Revision b23fd403 (ceph): install-deps.sh: create virtualenv only if necessary
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:01 AM Revision 17a74ed2 (ceph): install-deps.sh: s/get_pip_and_wheel/populate_wheelhouse/
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:00 AM Revision f81f6516 (ceph): install-deps.sh: do not create "wheelhouse" unless it's ready
- * only create "wheelhouse" directory for tox when it is populated
with all packages in *requiresments.txt. before t... - 07:20 AM Bug #11840: avoid complicated cache tier, like cache loop and three level cache
- that's ok, multi-level cache is not wrong config, maybe pepole will take use of it, if they have three or more types ...
- 06:21 AM Bug #11840: avoid complicated cache tier, like cache loop and three level cache
- chuanhong wang wrote:
> there are three pool in ceph cluster, e.g, t1, t2 t3, and t2 is a cache of t1.
> 1, we can ... - 07:20 AM Revision 35c5fd00 (ceph): common/Cycles.cc: skip initialization if rdtsc is not implemented
- The Cycles initialization gets stuck in infinite loop if rdtsc is not
implemented. This patch fixes the issue by quit... - 05:52 AM Revision 0d845255 (ceph): install-deps.sh: refactor pip install a little bit
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:24 AM Revision 779360cd (ceph): Merge pull request #4855 from tchaikov/wip-man-page-fix
- man/create-create-keys: minor fixes
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com> - 03:27 AM Revision f04c8829 (ceph): man/create-create-keys: minor fixes
- to address the comments on https://github.com/ceph/ceph/pull/4846
Fixes: #10725
Signed-off-by: Kefu Chai <kchai@redh... - 03:21 AM Revision a308c113 (ceph): Merge pull request #4853 from ceph/wip-rpm-rm-endif
- ceph.spec.in: fix rpm build errors
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:02 AM Revision 99301384 (ceph): rgw: generate the "Date" HTTP header for civetweb.
- Fixes: #10873
Backport: hammer
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
(cherry picked from commit...
06/03/2015
- 11:48 PM Revision 0eabf27e (ceph): Revert "ceph.spec.in:ownership of dirs extension"
- This reverts commit 6f495974a8255ec4bbd4c7c85f1ed21b3f281f2b.
This needs more discussion, since "make install" does ... - 11:40 PM Revision f94f2329 (ceph): ceph.spec.in: rm stray %endif
- Commit d8abde3338b0c7df373b762e35099ad5123866bf introduced a stray
%endif. Remove it.
This fixes the build error:
... - 11:17 PM Revision 91dbc787 (ceph): vstart.sh: sudo radosgw for low port numbers
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:17 PM Revision f2a4c2ae (ceph): vstart.sh: show s3 creds at end
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:28 PM Revision 5feb8069 (ceph): Merge pull request #4793 from SUSE/wip_ceph_spec_directories_not_owned_...
- ceph.spec.in:ownership of dirs extension
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 10:24 PM Revision 7d5a8f74 (ceph): Merge pull request #4821 from SUSE/wip_libcephfs_jni_postun
- ceph.spec.in libcephfs_jni1 has no %post and %postun
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 10:22 PM Revision 683992d7 (ceph): Merge pull request #4670 from ceph/wip-11610-next
- ceph.spec.in: include SUSE in _with_systemd
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 10:19 PM Revision 799432ab (ceph): Merge pull request #4725 from SUSE/wip_suse_forward_conditionals
- Add rpm conditionals
- 10:14 PM Revision 0dbae1a8 (ceph): Merge pull request #4808 from liewegas/wip-make-dist
- make_dist_tarball.sh
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 09:49 PM rgw Bug #10873: RGW does not send Date HTTP header when civetweb frontend is used
- confirmed to fix multipart upload with crossftp (on hammer and firefly)
- 09:49 PM rgw Bug #10873 (Pending Backport): RGW does not send Date HTTP header when civetweb frontend is used
- 09:29 PM Revision 048a2263 (ceph): Merge pull request #4850 from ktdreyer/wip-readme-simplify-deps
- README: simplify build deps section
- 09:25 PM Revision fbb92797 (ceph): README: simplify build deps section
- The install-deps.sh step is the same for Debian and RPM-based systems.
Simplify the two README sections into a single... - 08:53 PM devops Bug #11798 (Resolved): upstart: configuration is too generous on restarts
- Merged in commit:172d3ac8744c876a0f6ed99f4d63d95ea899cf85 we do 3 restarts in 30 minutes on OSD, Mon, MDS.
- 08:51 PM Revision 172d3ac8 (ceph): Merge pull request #4828 from liewegas/wip-11798
- make upstart less aggressive with respawn (11798)
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:16 PM rgw Bug #11860 (Pending Backport): Bucket header is enclosed by quotes
- 06:43 PM rgw Bug #11860: Bucket header is enclosed by quotes
- How do I get this backported to Hammer and Firefly?
- 02:13 PM rgw Bug #11860: Bucket header is enclosed by quotes
- https://github.com/ceph/ceph/pull/4844
- 11:10 AM rgw Bug #11860 (Resolved): Bucket header is enclosed by quotes
- When "rgw_expose_bucket" is set to true the RGW will return the bucket name in the response header....
- 08:15 PM Bug #11856: osd - scrubbing slot leaked
- https://github.com/ceph/ceph/pull/4849
- 05:39 AM Bug #11856 (Can't reproduce): osd - scrubbing slot leaked
- ceph version: v0.80.4
platform: RHEL6
With our production cluster, we found that the 'pg repair' command was not ... - 08:15 PM Revision 0e66dae9 (ceph): Merge pull request #4844 from ceph/wip-11860
- rgw: Do not enclose the Bucket header in quotes
Reviewed-by: Sage Weil <sage@redhat.com> - 07:53 PM rgw Bug #11864 (Resolved): error in ext_mime_map_init() when /etc/mime.types is missing
- I'm testing 0.94.1. If @/etc/mime.types@ is not present on a system (eg, from the mailcap RPM), then RGW prints this ...
- 06:57 PM Revision eaff6cb2 (ceph): upstart: limit respawn to 3 in 30 mins (instead of 5 in 30s)
- It may take tens of seconds to restart each time, so 5 in 30s does not stop
the crash on startup respawn loop in many... - 06:20 PM Revision 8af25fae (ceph): rgw: Do not enclose the Bucket header in quotes
- Fixes: #11860
Signed-off-by: Wido den Hollander <wido@42on.com> - 06:17 PM Revision 601c2f7c (ceph): test: update argparse tests for "mds rm"
- This tests reflected the bogus old 'who' arg.
Signed-off-by: John Spray <john.spray@redhat.com> - 05:03 PM Revision efbca046 (ceph): ceph.spec: add mkcephfs to ceph.rpm
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:51 PM Revision 3fb1186d (ceph): Merge pull request #4836 from ceph/wip-11857
- admin/build-doc: fix dependency checks
Reviewed-by: Nathan Cutler <ncutler@suse.cz>
Reviewed-by: Kefu Chai <kchai@re... - 04:13 PM Linux kernel client Cleanup #11863 (New): osd_client: consolidate exported functions
- osd_client exports some functionality that could probably be refactored into osd_client itself (like set_request_ling...
- 03:11 PM Backport #11862 (Resolved): missing man pages for ceph-create-keys, ceph-disk-*
- https://github.com/ceph/ceph/pull/4846
- 03:00 PM Bug #10725: missing man pages for ceph-create-keys, ceph-disk-*
- Now I see this is for four manpages, not just one.
- 02:56 PM Bug #10725 (Pending Backport): missing man pages for ceph-create-keys, ceph-disk-*
- 02:39 PM rgw Bug #11563: RadosGW regression: COPY doesn't preserve Content-Type
- Any news on this ?
Given that COPY is used when renaming objects (like if you do a streaming upload but you want t... - 02:25 PM Bug #11836 (Pending Backport): ceph-post-file fails on rhel7
- 02:18 PM Revision 54e1d9d0 (ceph): Merge pull request #4818 from dachary/wip-11272-ceph-disk-zap
- ceph-disk: always check zap is applied on a full device
Reviewed-by: Travis Rhoden <trhoden@redhat.com> - 02:14 PM Revision 1f0d3ca0 (ceph): Merge pull request #4842 from liewegas/wip-install-deps
- make install-deps clean up
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:05 PM Revision db2d83cb (ceph): install-deps.sh: clean up after ourselves
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:01 PM Revision e785f1a2 (ceph): packaging: package ceph-disk(8)
- The ceph-disk man page was added in
a450cab2b8148cb8a9b043d629feccf89e5aabac, but this was not added to the
RPM or DE... - 01:57 PM Revision c6c3a3bc (ceph): Add rpm conditionals : libs_compat
- Extracted conditionals from SUSE rpm spec file to forward port.
Original work done by Thorsten Behrens <tbehrens@suse... - 01:57 PM Revision d8abde33 (ceph): Add rpm conditionals : tcmalloc
- Extracted conditionals from SUSE rpm spec file to forward port.
Original work done by Thorsten Behrens <tbehrens@suse... - 01:55 PM Revision 5747ea19 (ceph): Add rpm conditionals : tests
- Extracted conditionals from SUSE rpm spec file to forward port.
Original work done by Thorsten Behrens <tbehrens@suse... - 01:55 PM Revision c65538f4 (ceph): Add rpm conditionals : cephfs_java
- Extracted conditionals from SUSE rpm spec file to forward port.
Original work done by Thorsten Behrens <tbehrens@suse... - 11:48 AM Fix #11590: MDSMonitor: handle MDSBeacon messages properly
- the 2nd pull request for this issue
https://github.com/ceph/ceph/pull/4825 - 11:13 AM Feature #11833 (Fix Under Review): Method or utility to report OSDs in a particular bucket
- https://github.com/ceph/ceph/pull/4840
- 11:10 AM Feature #11833: Method or utility to report OSDs in a particular bucket
- to print all OSD ids under a bucket whose name is "default" and type is "root":...
- 10:51 AM CephFS Feature #11859 (Resolved): MDS "damage table" for recording scrub/fetch errors
Creating a ticket for this ongoing work in the interests of clarity.
The idea is that when we get an error in fe...- 10:13 AM rgw Feature #11858 (Duplicate): Support Amazon v4 Signatures
- Some tools (like s3cmd) are now trying v4 signatures and those are not working with RGW.
Amazon v4 signature: http... - 09:42 AM CephFS Bug #10950 (Fix Under Review): Unable to remove MDS host: error handling
- https://github.com/ceph/ceph/pull/4838
- 09:40 AM Revision 232ec887 (ceph): pybind: avoid spurious "too many values to unpack"
- When a user passes e.g. an IP address where
they should have passed a <service>.<id>,
the dots were causing us to rai... - 09:24 AM devops Bug #11857: admin/build-doc: script fails silently under certain circumstances
- Thanks, John. The issue I ran into when I ran admin/build-doc on my openSUSE system was that admin/build-doc looks fo...
- 09:10 AM devops Bug #11857 (Fix Under Review): admin/build-doc: script fails silently under certain circumstances
- As kefu says, we should just wait until after the dependency checks to enable -e
https://github.com/ceph/ceph/pull... - 07:32 AM devops Bug #11857 (Resolved): admin/build-doc: script fails silently under certain circumstances
- On openSUSE, admin/build-doc fails silently due to missing commands. Although the script has code for reporting which...
- 09:22 AM Revision e8e8b12c (ceph): mon: Remove spurious 'who' arg from mds rm
- This was never used, looks like a typo
from f26bd55e where the MonCommands.h
definitions were created.
Remove it bec... - 09:19 AM CephFS Bug #11835 (Fix Under Review): FuseMount.umount_wait can hang
- https://github.com/ceph/ceph-qa-suite/pull/453
- 09:09 AM Revision 539c1ba7 (ceph): admin/build-doc: fix dependency checks
- Fixes: #11857
Signed-off-by: John Spray <john.spray@redhat.com> - 09:07 AM CephFS Bug #11746 (Fix Under Review): cephfs Dumper tries to load whole journal into memory at once
- https://github.com/ceph/ceph/pull/4835
- 09:04 AM Revision e3ddcb89 (ceph): tools: chunk reads in Dumper
- Previously tried to read entire journal
into memory in one go, which was problematic
for large journals.
Fixes: #117... - 08:47 AM Revision 3ca1b509 (ceph): Merge pull request #4712 from dachary/wip-11663-verify-erasure-code-pro...
- normalize and verify the erasure code profile
Reviewed-by: Andreas Peters <andreas.joachim.peters@cern.ch> - 07:57 AM Revision 7aba9476 (ceph): Doc: add write back throttling stuff in document and test scripts
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 07:56 AM Revision fa000d0e (ceph): Osd: implement low speed flush
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 06:57 AM Bug #11505 (In Progress): "Invalid argument: osd_disk_thread_ioprio_class" while set to ""
- I don't remember this corner case was fixed. I'll take a look.
- 06:29 AM Feature #9589 (Resolved): erasure-code: query plugin for erasure-code-profile defaults
- 06:21 AM Revision b7eec9ab (ceph): Merge pull request #4590 from ceph/wip-da-SCA-20150427
- SCA and Coverity fixes
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:20 AM Revision f00ecb8b (ceph): mon/MDSMonitor: rename labels to a better name
- * s/ignore/reply/
* s/out/ignore/
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:14 AM Revision 72a37b3a (ceph): mon: send no_reply() to peon to drop ignored mdsbeacon
- so the peon can remove the ignored mdsbeacon request from the
routed_requets at seeing this reply, and hence no longe... - 05:54 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- We recently started seeing this crash in some of our OSDs, we applied the patch to firefly and did not fix the crash....
- 03:30 AM Revision 323918a3 (ceph): Merge pull request #4823 from liewegas/wip-ceph-post-file
- ceph-post-file: behave when sftp doesn't take -i
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:56 AM Bug #11695: keyvaluestore: can not overwrite object after snapshot is created
- i have started work on this bug, but i forget assign this bug to myself
- 12:28 AM Revision 17f73faf (ceph): Merge pull request #4816 from dachary/wip-11624-cephtools-test
- tests: cephtool/test.sh wait_for_clean after PG (re)mapping
Reviewed-by: David Zafman <dzafman@redhat.com>
06/02/2015
- 10:19 PM RADOS Bug #11235 (In Progress): test_rados.py test_aio_read is racy
- 09:59 PM RADOS Bug #11855 (Resolved): ceph osd crush reweight-subtree does not reweight parent node
- ...
- 09:55 PM devops Bug #11854 (Rejected): python-rados: packaging bug? "package is in a very bad inconsistent state"
- I am seeing this a lot right now.
After a failed @teuthology-nuke@:... - 09:34 PM Bug #11461 (Fix Under Review): arm64: crc32 macro not available on older kernel
- https://github.com/ceph/ceph/pull/4834
- 09:33 PM Revision fdcc0072 (ceph): arm: fix build on older kernels
- that don't define HWCAP_CRC32
Fixes: #11461
Signed-off-by: Sage Weil <sage@redhat.com> - 09:32 PM Bug #7068 (Can't reproduce): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset....
- 09:31 PM Bug #11016 (Can't reproduce): After restart OSD, another OSD crashes with error "FAILED assert(lo...
- 09:28 PM Bug #11511: FAILED assert(cursor.data_offset <= oi.size)
- Note, this case appears to involve a cache pool.
- 08:50 PM Bug #11511: FAILED assert(cursor.data_offset <= oi.size)
- Not sure from the logs what really happened. But I can infer from the code that objects_read_sync() returned a "resu...
- 09:23 PM rbd Backport #11853 (Resolved): librbd: new config option for legacy blocking aio behavior
- https://github.com/ceph/ceph/pull/4827
Just the first and last commit there, since rbd metadata is new in master.
... - 09:22 PM rbd Backport #11852 (Resolved): librbd: new config option for legacy blocking aio behavior
- https://github.com/ceph/ceph/pull/4854
- 09:21 PM Bug #11500 (Fix Under Review): Crush map cannot handle OSD weights smaller than 0.01
- https://github.com/ceph/ceph/pull/4833
- 09:20 PM Revision e9e68655 (ceph): init-ceph, ceph-osd-prestart: set osd weight with more precision
- Our fixed point weights can go down to .0001 -- allow that.
Fixes: #11500
Signed-off-by: Sage Weil <sage@redhat.com> - 09:18 PM Revision eb922540 (ceph): Merge pull request #4827 from ceph/wip-librbd-aio-submission
- librbd: new config option for legacy blocking aio behavior
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:16 PM Bug #11505: "Invalid argument: osd_disk_thread_ioprio_class" while set to ""
- i thought this was fixed a while back?
- 09:16 PM Bug #11526 (Resolved): MDS crashed in ceph::buffer::list::splice
- 09:13 PM Bug #11055 (Duplicate): firefly ceph-osd SEGV in tcmalloc testing wip-cot-firefly
- 09:13 PM Feature #10759 (Fix Under Review): rados command line gives no access to striper API
- 09:11 PM Bug #10901 (Duplicate): FAILED assert(weak_refs.empty()) (outstanding OSDMap ref at shutdown)
- 09:08 PM CephFS Bug #11758: kernel_untar_build fails on EL7
- let's update the tarball to use a newer kernel.
- 09:06 PM Bug #10794 (Fix Under Review): ceph_test_rados: incorrect buffer at pos ...
- 09:05 PM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
- 09:04 PM Bug #11848 (Duplicate): PG: don't check feature if connection isn't ready
- #11661
- 05:16 PM Bug #11848 (Duplicate): PG: don't check feature if connection isn't ready
- -4011> 2015-05-11 11:41:30.309734 7f91e19f7700 20 osd.4 pg_epoch: 1208
pg[0.41( empty local-les=1196 n=0 ec=1 les/c... - 09:02 PM Bug #11014 (Duplicate): "[ FAILED ] LibRadosTwoPoolsPP.EvictSnap2" in upgrade:firefly-firefly-d...
- this is fixed in a later version of firefly. dup of #11548
- 08:59 PM Bug #11586 (Rejected): RBD Data Corruption with Logging on Giant
- 08:56 PM Bug #11586: RBD Data Corruption with Logging on Giant
- David Burley wrote:
> Any other data I can collect on this to help?
sadly it's not the same bug we hit before tha... - 08:59 PM Bug #11569 (Pending Backport): mon: "pg ls" is broken
- 08:50 PM Bug #6955: ceph-disk should set the guid correctly when re-using a partition
- Loic Dachary wrote:
> Sage,
>
> If we set the typecode / uuid of an existing partition (something like https://g... - 08:46 PM Revision 79961bc3 (ceph): osd: Even in objects_read_sync() case don't read past oi.size
- Fixes: #11511
Signed-off-by: David Zafman <dzafman@redhat.com> - 08:38 PM Bug #11266 (Resolved): data digest mismatch 11177
- 08:38 PM Bug #11264 (Resolved): omap digest mismatch with wip-11177
- 08:32 PM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- Daniel: that assert can be triggered by many things. Can you paste the 100 lines above that?
- 08:31 PM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- ...
- 08:31 PM Bug #11512: "FAILED assert(0 == "unexpected error")" in upgrade:giant-x-hammer-distro-basic-vps run
- from the teuthology case
-12> 2015-04-30 01:17:33.351288 7f22e0231800 10 filestore(/var/lib/ceph/osd/ceph-4) _c... - 08:25 PM Bug #11211 (Resolved): osd/ReplicatedPG.cc: 2141: FAILED assert(op == prdop->op)
- the backport is 0ee022b1ae832c70a80e9d2cdf32403039f3f125 which was not present in that failed run.
- 08:23 PM Bug #11565 (Can't reproduce): "FAILED assert(r == -2)" in rados-firefly-distro-basic-magna run
- 08:19 PM Bug #7915 (Duplicate): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 08:17 PM Bug #11518 (Resolved): objectcacher stress test fails with command not found
- 08:16 PM Bug #11548: "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-basic-multi run
- same issue as before.. this test needs to be disabled.
- 07:26 PM rgw Bug #11851 (Resolved): Civetweb RGW appears to report full size of object as downloaded when only...
- Looking at the radosgw-admin usage show get_obj bytes_sent output for a user with 500MB to ~1.1GB objects being strea...
- 05:57 PM rbd Bug #11796: "rbd_get_flags() indicates object map is invalid" in smoke-master-distro-basic-typica...
- This looks like Ceph.
- 05:55 PM CephFS Bug #11807 (Fix Under Review): workunits: stop rsyncing with /usr as the source material
- https://github.com/ceph/ceph/pull/4831
- 01:49 PM CephFS Bug #11807: workunits: stop rsyncing with /usr as the source material
- John suggests we can grab /usr/doc instead, maybe.
- 05:54 PM rbd Bug #6630 (Resolved): fio tests against raw RBD volumes show strange results
- I think this was a symptom of #7385. Please reopen if you still see odd behavior after this fix.
- 05:53 PM Revision 0de68ebb (ceph): qa: fix multiple_rsync.sh to avoid using /usr/ directly
- While we're at it, take only /usr/lib instead of all of /usr
to keep the overall file count more modest.
Fixes: #118... - 05:51 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- For the upgrade test to work, the above needs to be enclosed in a loop over all buckets.. i assume 'radosgw-admin buc...
- 05:49 PM Linux kernel client Bug #11850 (Resolved): xfstests xfs/181 fails
- _check_xfs_filesystem: filesystem on /dev/rbd1 is inconsistent (r) (see /var/lib/xfstests/results//xfs/181.full)
- 05:47 PM Linux kernel client Bug #9147 (Closed): krbd: run_xfstests.sh fails
- 05:43 PM Linux kernel client Bug #9147 (In Progress): krbd: run_xfstests.sh fails
- 05:41 PM Bug #8598 (Can't reproduce): Monitor performance during intensive operations
- Loic Dachary wrote:
> Is this still active ?
Have not seen similar behavior since. - 05:17 PM devops Bug #11591 (Need More Info): "VersionNotFoundError: Failed to fetch package version" in rados-ham...
- This *should* be done now:
https://github.com/ceph/teuthology/commit/aa267edf8f65ed7d39aa6e36863fd39de51fabb6 - 04:53 PM Revision 819cf6dd (ceph): Merge pull request #4780 from oritwas/wip-10295-firefly
- rgw: civetweb should use unique request id
Reviewd-by: Yehuda Sadeh <yehuda@rehat.com> - 04:02 PM Revision e93711a4 (ceph): Merge pull request #4829 from oritwas/wip-negative_content_length-firefly
- rgw: don't allow negative / invalid content length
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:54 PM Revision 50e85797 (ceph): rgw: don't allow negative / invalid content length
- Certain frontends (e.g., civetweb) don't filter such requests.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cher... - 03:36 PM devops Bug #11798 (Fix Under Review): upstart: configuration is too generous on restarts
- https://github.com/ceph/ceph/pull/4828
- 03:34 PM Revision 3d39a9bc (ceph): Merge pull request #4701 from jdurgin/wip-nova-rbd-cache
- doc: add rbd cache settings to nova.conf
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:20 PM rbd Bug #11791 (In Progress): A client opening an image mid-resize can result in the object map being...
- 03:11 PM Bug #11836 (Fix Under Review): ceph-post-file fails on rhel7
- 03:02 PM Feature #11833 (In Progress): Method or utility to report OSDs in a particular bucket
- 08:52 AM Feature #11833: Method or utility to report OSDs in a particular bucket
- <vikhyat> kefu: Hey
<vikhyat> kefu: How are you doing ?
<kefu> vikhyat: hi
<kefu> i am replying on http://tracker... - 08:36 AM Feature #11833: Method or utility to report OSDs in a particular bucket
- > Thanks for your reply, is ceph node ls command is available from Hammer as in firefly it is not , am I right?
"c... - 07:21 AM Feature #11833: Method or utility to report OSDs in a particular bucket
- Hey Kefu,
Thanks for your reply, is ceph node ls command is available from Hammer as in firefly it is not , am I r... - 06:54 AM Feature #11833: Method or utility to report OSDs in a particular bucket
- > Method or utility to report OSDs in a particular bucket
Vikhyat, could you be more specific about what "report" ... - 02:33 PM Revision 4cf41486 (ceph): tests: verify librbd blocking aio code path
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 02:32 PM Revision 008a9c4f (ceph): librbd: add rbd_non_blocking_aio option to image metadata
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:54 PM CephFS Bug #11300 (Resolved): client-limits and mds-full failures on clog warning/errors
- We think we already did that...sorry, no commit refs handy.
- 01:44 PM CephFS Bug #10950: Unable to remove MDS host: error handling
- This is just unfriendly error handling. John says one of the other commands has a spurious argument that needs to get...
- 01:42 PM CephFS Bug #11784: ceph-fuse hang on unmount (stuck dentry refs)
- I copied the ceph-client log into that folder, although we're missing the server logs.
- 01:36 PM CephFS Bug #11294: samba: DISCONNECTED inode warning
- seems like dup of #11835
- 12:44 PM rgw Feature #10333: rgw: support AWS4 authentication
- Thanks Yehuda.
- 12:31 PM rgw Feature #10333: rgw: support AWS4 authentication
- Done. You should be able to modify these fields under the rgw project now.
- 11:53 AM rgw Feature #10333: rgw: support AWS4 authentication
- I started this feature and I have some initial bits working now but I don't have the right permissions to ask for ass...
- 12:43 PM Revision c2b06ab3 (ceph): Merge pull request #4643 from tchaikov/wip-fix-11569
- fix "pg ls" with states of "recovering" and/or "repair"
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: G... - 12:37 PM Revision aa3d2693 (ceph): Merge pull request #4760 from ketor/fix_mutex_memory_leak
- Mutex: fix memory leak in lockdep _register
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:36 PM Revision ddfc5899 (ceph): Merge pull request #4802 from isserrano/master
- doc: Fixed example sintax in Absolute Sizing
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:30 PM Revision de14093f (ceph): doc: s/osd pool hot-storage/osd pool set hot-storage/
- Signed-off-by: Ismael Serrano <ismael.serrano@gmail.com>
- 10:32 AM Tasks #11847 (New): OSD crashes under cached cluster benchmark
- I set up a cluster with around 204 OSDs. During continuous benchmarking (set up cache tier, move around hosts in crus...
- 08:55 AM Documentation #11845 (Resolved): Missing link in "Logging and Debugging" chapter
- In http://ceph.com/docs/master/rados/troubleshooting/log-and-debug/#subsystem-log-and-debug-settings there is a sente...
- 05:02 AM Revision 16e8e2cc (ceph): mon: remove unnecessary error handling
- msg.get_session() should always return a non-zero pointer in
Monitor.dispatch()
Signed-off-by: Kefu Chai <kchai@redh... - 04:31 AM Revision 64ec79f0 (ceph): Put new variable initialization in its own block
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 03:47 AM Linux kernel client Bug #11841 (Need More Info): umount stuck on NFS over RBD switch over by using Pacemaker
- I am testing NFS over RBD recently. I am trying to build the NFS HA environment under Ubuntu 14.04 for testing, and t...
- 02:56 AM Revision 769cad12 (ceph): librbd: new rbd_non_blocking_aio config option
- Setting this option to false reverts librbd to legacy behavior
where AIO operations could potentially block.
Signed-... - 02:05 AM Bug #11840 (Resolved): avoid complicated cache tier, like cache loop and three level cache
> there are three pool in ceph cluster, e.g, t1, t2 t3, and t2 is a cache of t1.
> 1, we can set t1 as a cache of ...- 01:59 AM Revision 1fb26e39 (ceph): Mon: add cache_target_dirty_high_ratio related configuration and commands
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 01:59 AM Revision 8f6056ae (ceph): Osd: revise agent_choose_mode() to track the flush mode
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 01:59 AM Revision 4c5f755f (ceph): Osd: add new field in pg_pool_t
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 12:41 AM Revision 23551dee (ceph): test/ceph-objectstore-tool: Show command that should have failed
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:41 AM Revision d7858c66 (ceph): test/ceph-objectstore-tool: Don't need stderr noise
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:41 AM Revision ce76f887 (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 ... - 12:41 AM Revision 90202a70 (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>
06/01/2015
- 11:02 PM Feature #11837 (New): mon: add ability to gradually remove an osd
- The problem is that when you are removing a single osd from a single host, almost all of that osd's pgs tend to shuff...
- 10:38 PM Revision ee170ead (ceph): ceph-post-file: improve check for a source install
- Signed-off-by: Joseph McDonald <joseph.mcdonald@alcatel-lucent.com>
- 10:38 PM Revision 106a1c30 (ceph): Makefile: install ceph-post-file keys with mode 600
- Otherwise ssh (may) prompt for a password.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:37 PM Revision b84031ed (ceph): ceph-post-file: behave when sftp doesn't take -i
- Fixes: #11836
Signed-off-by: Joseph McDonald <joseph.mcdonald@alcatel-lucent.com> - 10:18 PM Bug #11836 (Resolved): ceph-post-file fails on rhel7
- sftp doesn't like -i
see https://github.com/ceph/ceph/pull/4823 - 09:55 PM CephFS Bug #11835 (Resolved): FuseMount.umount_wait can hang
Currently code in FuseMount.umount assumes that the write to /sys/fuse/connections/X/abort causes the process to te...- 09:49 PM CephFS Bug #11784: ceph-fuse hang on unmount (stuck dentry refs)
- We saw this again today, and it's definitely inode refs this time:
http://pulpito-rdu.front.sepia.ceph.com/gregf-201... - 08:19 PM Revision bd2f6244 (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> - 08:19 PM Revision f1520061 (ceph): mds, include: Fix dump() numeric char array to include additional alpha...
- Caused by: c87f55b5a8b3e003726e1be22b9cb6894ef2f37d
Signed-off-by: David Zafman <dzafman@redhat.com> - 08:19 PM Revision 99d7663f (ceph): ceph-objectstore-tool: Add dump-super to show OSDSuperblock in format s...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 08:19 PM Revision 70316541 (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... - 08:19 PM Revision 51e27984 (ceph): ceph-objectstore-tool: Invalidate pg stats when objects were skipped du...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:52 PM Revision 8e61a99d (ceph): mon: normalize erasure-code profile for storage and comparison
- An erasure-code profile set by the user may be modified by the erasure
code plugin, most of the time to add default v... - 07:52 PM Revision e2e1f35f (ceph): erasure-code: verify the profile content matches get_profile()
- The profile stored by the plugin may be different from the one set by
the user: it includes defaults. When the plugin... - 07:52 PM Revision 77e5330d (ceph): erasure-code: implement get_profile for every plugins
- The ErasureCode::init function is implemented to store the profile and
is called by the init method of each plugin. T... - 06:28 PM devops Bug #11798: upstart: configuration is too generous on restarts
- how about 5 restarts in 10 minutes?
- 06:22 PM Bug #11224: crushtool --test --simulate not working correctly
- This is indeed a bug. I wrote this CRUSH rule and could not get the --test to appropriately assign four OSDs accordin...
- 06:20 PM Revision ab30921a (ceph): make_dist.sh: bz2 only
- faster and smaler. caller can convert to gz or xz if they need it.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:19 PM Revision 44f8bbb5 (ceph): make_dist.sh: improve version calc
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:16 PM Feature #11833 (Resolved): Method or utility to report OSDs in a particular bucket
- Description of New Feature:
Method or utility to report OSDs in a particular bucket
A CLI to report the OSD lis... - 06:11 PM Revision 0f997960 (ceph): osd/: convert scrub to use the OpWQ
- Fixes: 8635
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:01 PM Bug #11832 (Duplicate): ceph_test_msgr hung in rados suite
ubuntu@teuthology:/a/dzafman-2015-05-27_12:16:53-rados-wip-10794---basic-multi/911969
The end of log keeps repea...- 05:52 PM Revision 0f2c5567 (ceph): erasure-code: expect all plugins to implement get_profile
- Add the get_profile method to the interface and make it a pure virtual.
Each plugin is expected to return the profile... - 04:12 PM Revision a1de1fc2 (ceph): Merge pull request #4729 from SUSE/wip_suse_builddeps_and_deps
- ceph.spec.in: Forward port suse build deps and recomends
- 03:30 PM Tasks #11831 (New): erasure-code: add chance_test_backfill_full to ceph-qa-suite tests
- https://github.com/ceph/ceph-qa-suite/blob/master/tasks/thrashosds.py#L91
- 02:28 PM Revision e5222b7f (ceph): Merge pull request #4822 from SUSE/wip_rpm_summary_ended_with_dot
- ceph.spec.in summary-ended-with-dot
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:57 PM Revision 042e8ff4 (ceph): ceph.spec.in summary-ended-with-dot
- RPM spec files summary should not end with a dot.
This was inconsistent across the ceph rpm packages
and creates erro... - 01:45 PM Bug #11821 (Rejected): ceph-disk.sh should not call teardown_btrfs
- 01:26 PM Bug #11821: ceph-disk.sh should not call teardown_btrfs
- BtrfsFileStoreBackend::detect_features() can leave stale subvolumes behind on failure, so I think this bug should be ...
- 01:16 PM Revision 11e5faf3 (ceph): mon: forbid readonly cache tiers for CephFS
- For EC pools, we need a tier that is not just forwarding
writes, in order to provide the ops required
by CephFS.
Sig... - 01:16 PM Revision f9b11b0a (ceph): qa: update cephtool test for CephFS tier cases
- 1. Creating a filesystem using a
readonly tier on an EC pool (should be forbidden)
2. Removing a tier from a repli... - 01:16 PM Revision a50c8f1f (ceph): mon: refine check_remove_tier checks
- Fixes: #11504
Signed-off-by: John Spray <john.spray@redhat.com> - 01:00 PM Revision 8b7a6fde (ceph): Merge pull request #4710 from dachary/wip-9589-default-erasure-code-pro...
- erasure-code: query plugin for erasure-code-profile defaults
Reviewed-by: Andreas Peters <andreas.joachim.peters@cer... - 12:58 PM Revision 0742d82b (ceph): ceph.spec.in libcephfs_jni1 has no %post and %postun
- /usr/lib64/libcephfs_jni.so.1.0.0 requires /sbin/ldconfig to be
run after installing and after removing.
Signed-off-... - 09:57 AM Bug #11298: aio gets EPERM when update-grub runs
- Oh! I forgot, that a month ago or so, the same crash happens one more time.
Also on update-group. Unfortunanely the ... - 09:50 AM Bug #11298: aio gets EPERM when update-grub runs
- Loic Dachary wrote:
> Do you have a way to reproduce this problem ?
The way is quite simple - I got OSD crush whe... - 07:48 AM Revision 0be8c674 (ceph): AsyncConnection: Remove unusable status check
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 07:33 AM Bug #11827 (Resolved): git ls-files --exclude-standard --others complains about ceph_perf_local
- 07:04 AM Bug #11827 (Fix Under Review): git ls-files --exclude-standard --others complains about ceph_perf...
- 06:57 AM Bug #11827 (Pending Backport): git ls-files --exclude-standard --others complains about ceph_perf...
- haomai, sorry for grabbing this issue from you: i happened to read the comments from greg and thought that we'd bette...
- 07:33 AM Revision 0f024602 (ceph): Merge pull request #4820 from ceph/wip-fix-ceph-perf-local
- tools: fix ceph perf local build on i386
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 06:58 AM Revision 06e6c152 (ceph): test/perf_local: disable tests if not supported
- * pass appropriate "-m<machine>" args to compiler
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:58 AM Revision 63343cef (ceph): .gitignore: ignore /perf_perf_local
- Fixes: #11827
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:52 AM Revision 168354c6 (ceph): test_msgr: make available_conns only can own unique (server,client) mes...
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 06:50 AM Revision 55e7cb9c (ceph): Message: Make encode_payload can be reentrant
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 06:09 AM Revision 17b2c5b5 (ceph): mds: use helper functions to access/modify SnapRealm::open
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:09 AM Revision c3fa768d (ceph): mds: remove pruned parent snaprealm from snaprealm's open_past_parents
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:05 AM Revision 55063a9f (ceph): mds: fix CInode::pop_projected_snaprealm()
- CInode::pop_projected_snaprealm() was called after calling
CDentry::pop_projected_linkage(). So get_parent_inode()->f... - 06:02 AM Revision 6ed6a68e (ceph): mds: properly open parents of snaprealm
- make sure snaprealm's parents are opened before building
cached_snaps/cached_snap_context/cached_snap_trace
Signed-o... - 04:59 AM Revision 83cb6095 (ceph): mds/MDS.cc: silence coverity DIV_BY_ZERO
- Silence coverity: ls.empty() check should already imply that
ls.size() != 0.
CID 1295402 (#1 of 1): Division or modu... - 04:59 AM Revision af144371 (ceph): test/librbd/fsx.cc: reduce scope of variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:59 AM Revision 258b7b9a (ceph): rgw/rgw_rados.cc: remove dead code
- CID 1274290 (#1 of 1): Logically dead code (DEADCODE)
dead_error_line: Execution cannot reach this statement return r... - 04:59 AM Revision 42f93a64 (ceph): os/FileStore.cc: remove dead code
- Fix for coverity issue caused by 8811df3 (introduced a similar
check some lines earlier in the code causing the check... - 04:59 AM Revision 71df303a (ceph): mon/OSDMonitor.cc: suppress false positive MISSING_BREAK
- Suppress coverity issue:
CID 1193085 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This cas... - 04:59 AM Revision 3b720f5a (ceph): tools/rados/rados.cc: restore ostream format
- CID 717133 (#1 of 1): Not restoring ostream format (STREAM_FORMAT_STATE)
95. format_changed: fill changes the format... - 04:59 AM Revision 6ffec518 (ceph): tools/rados/rados.cc: restore ostream precision format
- CID 717134 (#1 of 1): Not restoring ostream format (STREAM_FORMAT_STATE)
4. format_changed: precision changes the fo... - 04:59 AM Revision bbeb37fc (ceph): tools/rados/rados.cc: restore ostream precision format
- CID 717135 (#1 of 1): Not restoring ostream format (STREAM_FORMAT_STATE)
1. format_changed: precision changes the for... - 04:59 AM Revision 0a45a7a1 (ceph): test/librbd/fsx.cc: fix BUFFER_SIZE_WARNING
- CID 1296375 (#1 of 1): Buffer not null terminated (BUFFER_SIZE_WARNING)
buffer_size_warning: Calling strncpy with a ... - 04:59 AM Revision f5ae56b5 (ceph): osd/ClassHandler.cc: fix STRING_OVERFLOW
- CID 1058792 (#1 of 1): Copy into fixed size buffer (STRING_OVERFLOW)
fixed_size_dest: You might overrun the 4097 byt... - 04:59 AM Revision 0ae8fcad (ceph): os/HashIndex.cc: add asserts to prevent BAD_SHIFT
- Fix for:
CID 1232599: Bad bit shift operation (BAD_SHIFT)
negative_shift: In expression i << (4 - split_bits) % 4, ... - 04:59 AM Revision 05b050f0 (ceph): mds/CInode.cc: fix FORWARD_NULL issue
- Don't check for the conditions used inside get_projected_parent_dn(),
simply check if the returned value is valid.
F... - 04:59 AM Revision cc1ff9b4 (ceph): test/librbd/fsx.cc: fix int/unsigned long conversion
- getnum() returns an integer while maxfilelen is a unsinged long.
Use a temp var to be able to check the result of the... - 04:59 AM Revision d3128473 (ceph): librbd/internal.cc: close resource leak
- Fix for:
CID 1295405 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable req_comp going out of scope ... - 04:59 AM Revision e60c9c22 (ceph): rgw/rgw_op.cc: prefer empty() over 'size() == 0' for emptiness check
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:59 AM Revision b705949a (ceph): test_internal.cc: prefer ++operator for non-primitive iter
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:59 AM Revision 958289b0 (ceph): test/librbd/fsx.cc: fix format specifier
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
05/31/2015
- 11:13 PM Revision f6e40005 (ceph): tests: reduce pg_num in test_mon_osd_pool_set
- No need for more than one pg to test get/set on pools: it also is faster
to become clean.
Signed-off-by: Loic Dachar... - 11:13 PM Revision 7e2a7a86 (ceph): tests: cephtool/test.sh wait_for_clean after PG (re)mapping
- A get/set command may fail with
Error EBUSY: currently creating pgs, wait
if issued before the PGs are clean. Ca... - 11:11 PM Revision d2cc2b18 (ceph): tests: use get_pg from ceph-helpers.sh
- The semantic and interface of get_pg are the same, that avoids
duplication and the ceph-helpers.sh version is tested ... - 10:49 PM Bug #9342: Different implementation for PGTransaction::get_bytes_written between RPGTransaction a...
- Will you take into account stuff written to omap ? If you don't have time right now I'll change the status accordingly.
- 10:25 PM Revision 7d6bef7c (ceph): COPYING: note git-archive-all.sh license
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:14 PM CephFS Bug #10248: messenger: failed Pipe;:connect::assert(m) in Hadoop client
- Yes — the related issue chain has been seen a few times, more recently.
- 06:05 PM CephFS Bug #10248: messenger: failed Pipe;:connect::assert(m) in Hadoop client
- is it still valid ?
- 10:11 PM Bug #8598: Monitor performance during intensive operations
- Is this still active ?
- 09:58 PM Revision 31e93908 (ceph): make_dist.sh: rename from bin/make_dist_tarball.sh
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:57 PM Revision f3fe18a6 (ceph): make_dist_tarball.sh: make gz and bz2 archives
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:09 PM Bug #10241 (Resolved): Incorrect OSD mapping with EC 6+2 setup in Giant
- It needs 8 and there are only 9 available, which may be a problem for crush, sometimes. It has been resolved (or made...
- 06:04 PM Bug #10824 (Won't Fix): giant: teuthology pool-snaps-few-objects.yaml: monitors fail to start or ...
- It did not show up in a long time and giant is retired.
- 06:03 PM Bug #10833 (Won't Fix): testdir/osd-config fails with ENXIO
- it did not show up in a long time
- 05:59 PM Fix #11081: ceph.conf - $host always expands to localhost instead of actual hostname
- 05:57 PM Bug #11220 (Rejected): Ceph Clis should return better error codes, by which one can identify the ...
- It looks like you suggest an extensive change that would be better discussed as a blueprint in the next CDS. Would yo...
- 05:53 PM Bug #11224 (Rejected): crushtool --test --simulate not working correctly
- I'm unclear what the problem is. Please comment if this is indeed a bug and not something you did wrong and the issue...
- 05:50 PM Bug #7401 (Resolved): rados bench takes into account second '0' for stddev calculation
- https://github.com/ceph/ceph/pull/4151
- 05:45 PM Bug #11272 (Fix Under Review): ceph-disk zap should ensure block device
- https://github.com/ceph/ceph/pull/4818
- 05:42 PM Revision 8e1bcf21 (ceph): ceph-disk: always check zap is applied on a full device
- zap only makes sense on a full device and this is verified for
ceph-disk prepare --zap-disk
but not for
ce... - 05:24 PM Revision b75384d7 (ceph): crush/CrushTester: add check_name_maps() method
- * check for dangling bucket name or type names referenced by the
buckets/items in the crush map.
* also check for t... - 05:24 PM Revision d6b46d4c (ceph): crushtool: add the "--check-names" option
- * so one is able to verify that the "ceph osd tree" won't chock on the
new crush map because of dangling name/type ... - 05:24 PM Revision a955f36a (ceph): mon: validate new crush for unknown names
- * the "osd tree dump" command enumerates all buckets/osds found in either the
crush map or the osd map. but the new... - 05:24 PM Revision e640d892 (ceph): crush/CrushTester: check if any item id is too large
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:24 PM Revision d0658dd3 (ceph): crushtool: enable check against max_id
- add an argument "max_id" for "--check-names" to check if any item
has an id greater or equal to given "max_id" in cru... - 05:24 PM Revision 22e6bd6e (ceph): mon: check the new crush map against osdmap.max_osd
- Fixes: #11680
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:24 PM Revision 9381d53a (ceph): crushtool: rename "--check-names" to "--check"
- * because "--check" also checks for the max_id
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:24 PM Revision c6e63487 (ceph): mon: add "--check" to CrushTester::test_with_crushtool()
- so we don't need to call CrushTester::check_name_maps() in OSDMonitor.cc
anymore.
Fixes: #11680
Signed-off-by: Kefu ... - 04:58 PM Bug #11298 (Need More Info): aio gets EPERM when update-grub runs
- Do you have a way to reproduce this problem ? Did the OSD restart ok after the crash ? It could very well be that the...
- 04:53 PM Bug #11488 (Duplicate): 2 OSD segfaults after some commit
- 04:43 PM Revision c8705e5a (ceph): Merge remote-tracking branch 'gh/next'
- 04:43 PM Revision f5a95804 (ceph): unittest_ceph_argparse: test float parsing
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:39 PM Bug #11620 (Resolved): osdc/stress_objectcacher.sh command failed
- commit:4487d13cc6a737d36f6cfafdf7c28ef6423e17c1
- 04:38 PM Revision 4487d13c (ceph): Allow float value by allowing . in input value
- Dont bail out if the input value happens to be .
Fixes: #11620
Signed-off-by: Rajesh Nambiar <rajesh.n@msystechnolog... - 04:33 PM Revision 64944d41 (ceph): tests: ceph-helpers.sh use expr instead of (( ))
- Because (( timer++ )) is mistaken by set -e to not be a successful
command, use expr instead.
Signed-off-by: Loic Da... - 04:33 PM Revision d2172b0e (ceph): tests: move ceph-helpers.sh to qa/workunits
- So that it can be used by scripts in qa/workunits that need it.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 02:13 PM Bug #11624 (Fix Under Review): test/cephtool-test-mon.sh can fail due to timing issue
- https://github.com/ceph/ceph/pull/4816
- 12:23 PM Bug #11757 (Duplicate): Failure to load the osdmap
- Duplicates #11680
- 11:42 AM Feature #9720 (Fix Under Review): erasure-code: non regression should test jerasure variants
- https://github.com/ceph/ceph/pull/4815
- 07:51 AM Feature #9720 (In Progress): erasure-code: non regression should test jerasure variants
- 07:50 AM Feature #10346 (Resolved): add ceph pg dump_stuck {degraded,undersized}
- 07:35 AM Bug #6955 (Need More Info): ceph-disk should set the guid correctly when re-using a partition
- Sage,
If we set the typecode / uuid of an existing partition (something like https://github.com/dachary/ceph/comm... - 07:16 AM Bug #11827 (Resolved): git ls-files --exclude-standard --others complains about ceph_perf_local
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-precise-amd64-basic/log.cgi?log=5652518cf87b35ac5e73ac8b24b3...
- 03:03 AM Revision b8954e6e (ceph): AsyncConnection: Make header insert when sending
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
05/30/2015
- 10:01 PM Revision 4b3ba2ab (ceph): erasure-code: ErasureCode default value is a string
- The to_int, to_bool prototypes are modified and the default values are
changed to string instead of int. If a default... - 10:01 PM Revision 6eaeb567 (ceph): erasure-code: ErasureCodeIsa update default values to string
- Update the ErasureCodeIsa::init function to use string default values
and update the profile accordingly.
Also fix a... - 10:01 PM Revision 14a59e5a (ceph): erasure-code: ErasureCodeJerasure update default values to string
- Update the ErasureCodeJerasure::init function to use string default values
and update the profile accordingly.
The E... - 10:01 PM Revision 17ecd6f9 (ceph): erasure-code: return ErasureCodeLrc::parse_kml error
- Instead of always returning 0
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 10:01 PM Revision 395eba9b (ceph): erasure-code: ErasureCodeLrc update default values to string
- Update the ErasureCodeLrc::init function to use string default values
and update the profile accordingly.
If the k,m... - 10:01 PM Revision a199ff9d (ceph): erasure-code: ErasureCodeShec update default values to string
- Update the ErasureCodeShec::init function to use string default
values. The default profile values for technique, rul... - 05:25 PM Revision 5652518c (ceph): Merge pull request #4810 from zaitcev/context_io_init_undup
- rgw: Drop a redundant context_io.init
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:19 PM Revision 55b9e4e2 (ceph): rgw: Drop a redundant context_io.init
- Interestingly enough, the function is not even entirely idempotent:
it prints debugging output, duplicated.
Signed-o... - 03:51 PM Bug #6955 (In Progress): ceph-disk should set the guid correctly when re-using a partition
- 03:27 PM Bug #11667 (Fix Under Review): erasure-code: test adding a new OSD
- https://github.com/ceph/ceph/pull/4813
- 02:29 PM Revision 80c3150d (ceph): AsyncConnection: Avoid "lock" acquire in message normal send flow
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 008d9cf5 (ceph): AsyncConnection: make can_write enum type
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 43ef09de (ceph): AsyncConnection: Avoid event creation leak when stopping
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision aa7674bd (ceph): Event: assert failure when failed to add/del event
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 27d24a84 (ceph): AsyncConnection: Use reference instead of value passing for try_send
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 19f681f7 (ceph): AsyncMessenger: Add perf counter for each async worker
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 947c39d2 (ceph): AsyncConnection: Allow msg encode without write_lock holding
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision 84b9088e (ceph): AsyncConnection: Avoid encoding message with lock holding
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:29 PM Revision a14b0e14 (ceph): Event: Avoid potential wakeup leak between set and read
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:27 PM Bug #11142: "Exception: ceph-objectstore-tool: import failure" in upgrade:firefly-x-hammer-distro...
- We have started running integration tests on the newly-reset firefly-backports branch (containing what will become 0....
- 02:18 PM Bug #11826 (Resolved): error: test/perf_local.cc:418:31: inconsistent operand constraints in an ‘...
- https://github.com/ceph/ceph/pull/4812
- 01:13 PM Bug #11826: error: test/perf_local.cc:418:31: inconsistent operand constraints in an ‘asm’
- https://github.com/ceph/ceph/pull/4812
- 12:37 PM Bug #11826 (Resolved): error: test/perf_local.cc:418:31: inconsistent operand constraints in an ‘...
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-i386-basic/log.cgi?log=830054b419be7f2a8097ae2856e9a0...
- 02:17 PM Revision a6479e4e (ceph): Merge pull request #4812 from yuyuyu101/fix-perf-incompatible
- PerfLocal: Doesnt' compile div64 for non-64 bits arch
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:13 PM Revision 6fcf162d (ceph): PerfLocal: Doesnt' compile div64 for non-64 bits arch
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 12:01 PM Fix #11666: erasure-code: add lrc to rados/thrash-erasure-code
- Shylesh, would you have time to review this test ?
- 11:58 AM Fix #11666 (Fix Under Review): erasure-code: add lrc to rados/thrash-erasure-code
- 11:50 AM Bug #11346 (Fix Under Review): erasure-code: add non regression tests for isa-l with k=10, m=4
- https://github.com/ceph/ceph/pull/4811
there was no need to wait for the 9.0.0 tag since the code is not modified.... - 11:44 AM Revision ceee695b (ceph): ceph-erasure-code-corpus: isa: add k=10 m=4
- To improve coverage.
http://tracker.ceph.com/issues/11346 Fixes: #11346
Signed-off-by: Loic Dachary <ldachary@redha... - 10:20 AM Bug #11665 (Resolved): erasure-code: test/osd/osd-scrub-repair.sh add lrc test case
- 10:19 AM Revision 830054b4 (ceph): Merge pull request #4797 from dachary/wip-11665-erasure-code-lrc
- tests: add lrc tests to osd-scrub-repair.sh
Reviewed-by: Shylesh Kumar <shmohan@redhat.com> - 09:47 AM Revision 17855b42 (ceph): Merge pull request #4799 from dachary/wip-install-deps
- install-deps.sh: robust pip and wheel installation
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:00 AM Revision 8199e006 (ceph): install-deps.sh: do not store pip cache outside of the tree
- Signed-off-by: Loic Dachary <ldachary@redhat.org>
- 01:29 AM Revision e8cc7a86 (ceph): bin/make_dist_tarball.sh
- This includes all submodules *except* ceph-object-corpus and
ceph-erasure-code-corpus.
This is a bit different that ... - 01:22 AM Revision 8bd27b61 (ceph): bin/git-all-archive.sh: add --ignore option
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:05 AM Revision 94b6661d (ceph): bin/git-archive-all.sh
- Thank you, internet: https://github.com/meitar/git-archive-all.sh
Signed-off-by: Sage Weil <sage@redhat.com> - 12:43 AM Revision 013f9af8 (ceph): Merge pull request #4727 from tchaikov/wip-osdmaptool-dump-tree-with-fo...
- osdmaptool: dump tree with given format
Reviewed-by: Sage Weil <sage@redhat.com>
05/29/2015
- 11:17 PM Backport #11824 (Resolved): implicit erasure code crush ruleset is not validated
- https://github.com/ceph/ceph/pull/5276
- 11:17 PM Bug #11814 (Fix Under Review): implicit erasure code crush ruleset is not validated
- * master https://github.com/ceph/ceph/pull/4807
- 02:41 PM Bug #11814: implicit erasure code crush ruleset is not validated
- The crush ruleset created as a side effect of an erasure coded pool creation is not validated via crushtool, but it s...
- 02:36 PM Bug #11814 (Resolved): implicit erasure code crush ruleset is not validated
- h3. Context
* RHEL6
* Hammer 0.94.1
* 3 Mons
* 315 OSDs
h3. Steps to reproduce... - 10:49 PM Bug #9408 (Resolved): erasure-code: misalignment
- 10:48 PM Backport #11704 (Rejected): erasure-code: misalignment
- the alignment problem has not manifested itself in over a year on firefly
- 10:17 PM Revision 5cb2631e (ceph): Merge pull request #451 from athanatos/wip-11677
- Wip 11677
Reviewed-by: Sage Weil <sage@redhat.com> - 09:55 PM Revision bbf75f81 (ceph): install-deps.sh: keep debian alternatives
- Instead of removing the | when an alternative is found in the control
file such as
cryptsetup-bin | cryptsetup
... - 09:54 PM Feature #11823 (New): Workqueue timeouts and the filestore sync_entry timeout should log somethin...
- Users currently see a rather unhelpful stacktrace for a mundane disk failure. I suggest that the WorkQueue base clas...
- 09:43 PM Revision cbc96a08 (ceph): install-deps.sh: robust pip and wheel installation
- The wheel and pip module must not only be installed in each wheelhouse
directory for tox to find. They must also be i... - 09:25 PM rbd Feature #11822: [rbd] support gb/tb units in rbd create/resize
- Yes, we should use the generic parsing introduced for units like this (and make it case insensitive if it still is).
- 09:21 PM rbd Feature #11822 (Resolved): [rbd] support gb/tb units in rbd create/resize
- Currently rbd create/resize uses mb as unit for size, its useful to provide g and t as well so that user can simply s...
- 09:24 PM Bug #11493 (Resolved): mon: adding exsting pool as tier with --force-nonempty clobbers removed_snaps
- 09:23 PM Bug #11296 (Pending Backport): "FAILED assert(!old_value.deleted())" in upgrade:giant-x-hammer-di...
- 09:23 PM Bug #11787 (Pending Backport): start_flush: filter out removed snaps before determining snapc's
- 09:21 PM Bug #11787 (Resolved): start_flush: filter out removed snaps before determining snapc's
- 09:21 PM Revision 64096b87 (ceph): Merge pull request #4805 from athanatos/wip-11787
- Wip 11787
Reviewed-by: Sage Weil <sage@redhat.com> - 09:20 PM Revision 33150c50 (ceph): Merge remote-tracking branch 'upstream/wip-txn-noappend-sam-rebased'
- Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:19 PM Revision d07100b6 (ceph): Merge pull request #4526 from athanatos/wip-11296
- Wip 11296
Reviewed-by: Sage Weil <sage@redhat.com> - 09:17 PM Revision 8a95f13a (ceph): Merge remote-tracking branch 'upstream/wip-11493'
- Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 09:15 PM Bug #11677 (Pending Backport): Almost all OSDs in the cluster crashing at the same time, repeatedly
- 09:11 PM Bug #11677 (Resolved): Almost all OSDs in the cluster crashing at the same time, repeatedly
- 09:11 PM Revision 315260a5 (ceph): Merge pull request #4803 from athanatos/wip-11677
- Wip 11677 -- fixes for rw rados ops with snaps
Reviewed-by: Sage Weil <sage@redhat.com> - 09:09 PM Revision be873eb8 (ceph): ReplicatedPG::release_op_ctx_locks: requeue in scrub queue if blocked
- Otherwise we can reorder an op around another op which got blocked by a
scrub which started after the first blocked o... - 09:09 PM Revision 5c2b7957 (ceph): ReplicatedPG::finish_ctx: take excl lock if operation is rw
- Fixes: #11677
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:03 PM Bug #11771 (Resolved): is_new_interval: size change should cause new interval
- 09:03 PM Revision f9ce2d78 (ceph): Merge pull request #4804 from athanatos/wip-11771
- osd_types::is_new_interval: size change triggers new interval
Reviewed-by: Sage Weil <sage@redhat.com> - 08:18 PM Bug #11821: ceph-disk.sh should not call teardown_btrfs
- This affects hammer as well as master.
- 08:17 PM Bug #11821 (Rejected): ceph-disk.sh should not call teardown_btrfs
- David Disseldorp writes in https://github.com/ceph/ceph/commit/38682f9a6a129e2f41a11476157ec6d0bd695b6c
If the tes... - 07:29 PM Bug #11809 (Won't Fix): ceph.spec.in fails on rhel7
- since it's supposed to not work, I'm good with it. Thanks for the workaround.
- 07:20 PM Bug #11809: ceph.spec.in fails on rhel7
- From a technical perspective the issue is that the downstream repos (@rhel-7-server-ceph-1.3-mon-test@ is a downstrea...
- 07:07 PM Bug #11809: ceph.spec.in fails on rhel7
- > In the above case it is going to conflict with downstream packages, maybe he can force install specific packages th...
- 06:14 PM Bug #11809: ceph.spec.in fails on rhel7
- In the above case it is going to conflict with downstream packages, maybe he can force install specific packages then.
- 05:59 PM Bug #11809: ceph.spec.in fails on rhel7
- for the purpose of testing a problem with LRC. we were trying to reproduce the conditions by using part of the tests ...
- 05:53 PM Bug #11809: ceph.spec.in fails on rhel7
- why is Shylesh running @./install-deps.sh@ there?
- 05:33 PM Bug #11809: ceph.spec.in fails on rhel7
- this is Shylesh Kumar machine, I'm not sure how it was configured. It is hp-ms-01-c02.moonshot1.lab.eng.rdu
- 05:31 PM Bug #11809: ceph.spec.in fails on rhel7
- Can you please tell the name of the hostname? , I think its due to someone having /etc/yum.repos.d/ceph.repo along wi...
- 04:50 PM Bug #11809: ceph.spec.in fails on rhel7
- I wonder if you locked a magna node that someone didn't clean up before they unlocked it and released it into the poo...
- 09:38 AM Bug #11809: ceph.spec.in fails on rhel7
- Ken: I've assigned this to you so you can triage it, there is no urgency ;-)
- 09:36 AM Bug #11809 (Won't Fix): ceph.spec.in fails on rhel7
- Steps to reproduce
* git clone http://github.com/ceph/ceph
* cd ceph
* ./install-deps.sh... - 06:42 PM Revision 3e4b8527 (ceph): osd/: convert snap trimming to use OpWQ
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:42 PM Revision e8cddf8e (ceph): OSD: add PGQueueable
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:25 PM Fix #11820 (In Progress): Show osd as NONE in "ceph osd map <pool> <object> " output
- 06:24 PM Fix #11820: Show osd as NONE in "ceph osd map <pool> <object> " output
- 06:16 PM Fix #11820 (Fix Under Review): Show osd as NONE in "ceph osd map <pool> <object> " output
- As of now ceph pg dump shows osd unavailability as something like [8,6,5,NONE,2,7,9,1] , where as ceph osd map shows...
- 06:25 PM Feature #11815: mon: allow injecting new crushmap
- How are you thinking of doing this? I imagine you mean this for a map which broke the monitor so it failed to propaga...
- 04:00 PM Feature #11815 (Resolved): mon: allow injecting new crushmap
- Whenever a crushmap is faulty and the monitor, for some reason, did not pick up on it, we may need to inject a new ve...
- 06:23 PM Revision 3f154583 (ceph): Merge pull request #450 from ceph/wip-fix-blacklist
- tasks/cephfs: fix typo in blacklist clearing
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:15 PM CephFS Bug #11792: mds: recursive statistics are either inaccurate or too "chunky"
- Well, they're delayed, yes. But the few times I've bothered to measure the delay is very short (a few seconds at most...
- 07:13 AM CephFS Bug #11792: mds: recursive statistics are either inaccurate or too "chunky"
- thanks to delay propagation, recursive statistics are never accurate
- 05:57 PM Revision d7fabebf (ceph): Merge pull request #4070 from ceph/wip-chain-xattr
- os/chain_xattr: cope with xfs limit of 254 bytes for inlined xattrs.
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>... - 05:53 PM Revision 517659b1 (ceph): FileStore: sync object_map when we syncfs
- This way, even if leveldb/rocksdb is on another filesystem/disk,
it will still be synced before trimming the journal.... - 05:41 PM Revision 2b281507 (ceph): Merge pull request #4059 from majianpeng/copyget-digest
- Replicated: For COPY_GET, only src has data/omap digest, the dst can do.
Reviewed-by: Sage Weil <sage@redhat.com>
Re... - 05:31 PM Revision 3e072c90 (ceph): Merge pull request #3253 from majianpeng/bug-fix
- cleanup code for wbthrottle.
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 04:59 PM Bug #11811 (Rejected): erasure-code: lrc chunks are not where they are supposed to be
- The confusion came from the fact that the content of some shards is full of NULL, as expected.
- 11:47 AM Bug #11811 (Need More Info): erasure-code: lrc chunks are not where they are supposed to be
- Shylesh, do you observe the same results when you run your tests ?
- 11:13 AM Bug #11811 (In Progress): erasure-code: lrc chunks are not where they are supposed to be
- 10:15 AM Bug #11811 (Rejected): erasure-code: lrc chunks are not where they are supposed to be
- * hammer
* MON=3 OSD=10 ./vstart.sh -X -n -l mon osd
* profile=ecprofile
* ceph osd erasure-code-profile set $prof... - 01:33 PM Revision 6d3b5c6b (ceph): tasks/cephfs: add TestClientRecovery.test_fsync
- To test that metadata written recently is
preserved across a client+server crash when
barriered with a directory fsyn... - 12:46 PM Revision df91f98e (ceph): tasks/cephfs: fix typo in blacklist clearing
- Broken in aa0ffb3
Signed-off-by: John Spray <john.spray@redhat.com> - 11:58 AM Bug #4282: auth: could not find secret_id=0
- Hi,
I got the same issue with a 6 node ceph cluster (giant 0.87.2) when booting servers via rbd from it.
The serv... - 10:39 AM Revision 891e9b17 (ceph): Merge pull request #4800 from hjwsm1989/journaler
- osdc/Journaler.h: fix ceph_file_layout dump error in journaler::dum…
Reviewed-by: John Spray <john.spray@redhat.com> - 08:56 AM Revision a10bd899 (ceph): Merge pull request #4794 from XinzeChi/wip-kill-sleep
- test: check daemon is alive or not agagin when sleep 60s
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Loic... - 08:11 AM Revision 8a6d626c (ceph): osdc/Journaler.h: fix ceph_file_layout dump error in journaler::dump().
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 07:51 AM devops Bug #11546 (Resolved): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- 07:50 AM devops Backport #11806 (Resolved): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test...
- http://pulpito.ceph.com/loic-2015-05-28_21:08:52-upgrade:firefly-x-wip-11806-hammer---basic-multi/ passed
- 07:49 AM Revision d967cecf (ceph): Merge pull request #4795 from dachary/wip-11806-hammer
- ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
Reviewed-by: Sage Weil <sage@redhat.com> - 07:27 AM Fix #11590: MDSMonitor: handle MDSBeacon messages properly
- see the discussions on https://github.com/ceph/ceph/pull/4702
per greg,
> So we need some kind of state message... - 07:21 AM Revision b3555e9c (ceph): mon: always reply mdsbeacon
- the MDS (Beacon) is always expecting the reply for the mdsbeacon messages from
the lead mon, and it uses the delay as... - 07:06 AM Revision 6f495974 (ceph): ceph.spec.in:ownership of dirs extension
- rpm lint says the following directories
/usr/share/ceph
/usr/lib/ceph
are un owned by any package and this causes
O... - 07:06 AM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- Boris Ranto wrote:
> btw: Do you see this behaviour also on rhel 7 and current range of fedoras?
I don't have a ... - 07:04 AM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- Ken Dreyer wrote:
> I'm not sure what "a while" is, though (seconds, minutes, etc)?
It depends on the number of ... - 03:29 AM Revision deb8ea44 (ceph): osd: check pending or active scrub before sched_scrub
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 02:03 AM Revision ce27ae4f (ceph): client: make fsync waits for single inode's flushing caps
- Client::_fsync() calls Client::wait_sync_caps(uint64_t), which
waits for all inodes' flush caps. It's suboptimal, thi... - 02:03 AM Revision 6883b829 (ceph): client: make fsync wait for unsafe directory operations
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:03 AM Revision b20ea430 (ceph): client: start flushing dirty caps in Client::_fsync()
- Client::flush_caps(Inode *, MetaSession *) does not start flushing
dirty caps. It only re-send caps message for caps ... - 02:03 AM Revision 6bb9e158 (ceph): client: don't update flushing_cap_seq when there are flushing caps
- Current code always updates flushing_cap_seq when marking dirty
caps as flushing. If there are old flushing caps, upd... - 01:45 AM Revision 2517ea99 (ceph): mds: don't add setfilelock requests to session's completed_requests
- setfilelock requests only modify states in MDS memory. The states get
lost when MDS fails. If a setfilelock reply get... - 01:45 AM Revision ae086388 (ceph): client: exclude setfilelock requests when calculating oldest tid
- setfilelock requests can block for a long time, which can prevent
client from advancing its oldest tid.
Signed-off-b... - 01:33 AM Revision 83f88e76 (ceph): commit: test: check daemon is alive or not agagin when sleep 60s
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
05/28/2015
- 11:26 PM Tasks #11797 (Rejected): does our log rotation do the right thing?
- Our log rotation does do the right thing. Running in debug mode makes clear that the compression happens after the po...
- 10:36 PM Revision 3127cda3 (ceph): rados: add write_excl and append_excl
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 10:36 PM Revision 91b300d1 (ceph): rados/thrash: add test for radosgw with snaps
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:25 PM Revision ddcbb66d (ceph): tests: add lrc tests to osd-scrub-repair.sh
- Create an lrc erasure coded pool and run corruption and repair tests on
it.
http://tracker.ceph.com/issues/11665 Fix... - 09:25 PM Revision 77f322b6 (ceph): tests: split osd-scrub-repair.sh erasure code test
- The erasure code repair test is split in two function:
* setup conditions specific to jerasure (4 osds, jerasure
... - 08:53 PM Bug #11665 (Fix Under Review): erasure-code: test/osd/osd-scrub-repair.sh add lrc test case
- https://github.com/ceph/ceph/pull/4797
- 08:38 PM Revision 70e069d2 (ceph): tests: cosmetic move of functions in osd-scrub-repair.sh
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 08:37 PM Bug #10901: FAILED assert(weak_refs.empty()) (outstanding OSDMap ref at shutdown)
- bah, just saw on wip-sam-testing: ubuntu@teuthology:/a/samuelj-2015-05-28_08:23:27-rados-wip-sam-testing-distro-basic...
- 08:35 PM Revision 28820d1c (ceph): erasure-code: s/unreocvery/unfound/
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 08:35 PM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
- ubuntu@teuthology:/a/samuelj-2015-05-28_08:23:27-rados-wip-sam-testing-distro-basic-multi/913520/remote
- 08:33 PM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
- ubuntu@teuthology:/a/samuelj-2015-05-28_08:23:27-rados-wip-sam-testing-distro-basic-multi/913465/remote
- 07:33 PM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- Milan, one of the things Boris and I discussed is that Dan's strace shows a lot of @stat()@ calls there. So even if t...
- 06:38 PM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- This is (well, will be) an intended behaviour, soon. We need to relabel the files for the SELinux policy to take effe...
- 05:48 PM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- That "fix" can make things worse later... It is probably good for quick workaround for some particular case though.
... - 04:08 PM Bug #9927: RHEL: selinux-policy-targeted rpm update triggers slow requests
- Milan, how can we implement a fix for this so it works out-of-the-box? Is selinux-policy-targeted the right place to ...
- 06:16 PM CephFS Bug #11781: multiple_rsync failure with fuse client
- #11807. I'm not actually sure what good options there are for replacement, but it won't get lost.
- 12:24 PM CephFS Bug #11781: multiple_rsync failure with fuse client
- Hmm, maybe using /usr/ as a source of workload files is something we just need to stop doing, there's no particular r...
- 12:12 PM CephFS Bug #11781 (Rejected): multiple_rsync failure with fuse client
- ...
- 06:15 PM CephFS Bug #11807 (Resolved): workunits: stop rsyncing with /usr as the source material
- We've had various issues with /usr. The permissions on it are fiddly, its size can vary, and apparently some times th...
- 06:02 PM Revision 7b4ee406 (ceph): Merge pull request #4796 from SUSE/wip-release-notes-fixup
- doc: release-notes.rst: fix typo and delete superfluous sentence
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:29 PM Revision 8b783718 (ceph): doc: release-notes.rst: fix typo and delete superfluous sentence
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 05:22 PM devops Bug #11546 (Pending Backport): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-t...
- 05:05 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- http://pulpito.ceph.com/loic-2015-05-28_17:16:30-upgrade:firefly-x-wip-11546-debian-packages---basic-multi/ successfu...
- 09:15 AM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- re-run a job known to fail ("upgrade:firefly-x/parallel/{0-cluster/start.yaml 1-firefly-install/firefly.yaml 2-worklo...
- 08:40 AM devops Bug #11546 (Fix Under Review): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-t...
- https://github.com/ceph/ceph/pull/4786
- 08:38 AM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- * https://www.debian.org/doc/debian-policy/ch-relationships.html#s-replaces
- 05:18 PM devops Backport #11806: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- same validation as http://tracker.ceph.com/issues/11546#note-22...
- 05:14 PM devops Backport #11806 (In Progress): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-t...
- 05:14 PM devops Backport #11806 (Resolved): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test...
- https://github.com/ceph/ceph/pull/4795
- 05:15 PM Revision 968573b8 (ceph): debian: ceph-dbg steals ceph-objectstore-tool from ceph-test-dbg
- When ceph-objectstore-tool was moved from ceph-test to
ceph by 61cf5da0b51e2d9578c7b4bca85184317e30f4ca, the ceph pac... - 05:11 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- Yehuda added to the v0.94.2 release notes: it's not a blocker https://github.com/ceph/ceph/pull/4789
- 10:02 AM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- I updated the release notes. Basically need to run for each affected bucket (without --fix it will be a dry run):
... - 05:09 PM Revision 98443203 (ceph): Merge pull request #4786 from dachary/wip-11546-debian-packages
- debian/control: ceph-dbg steals ceph-objectstore-tool from ceph-test-dbg
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 04:52 PM Backport #11700 (New): make the all osd/filestore thread pool suicide timeouts separately configu...
- 04:49 PM devops Backport #11734 (Resolved): Debian: ceph-test and rest-bench debug packages should require their ...
- 04:08 PM devops Backport #11734: Debian: ceph-test and rest-bench debug packages should require their respective ...
- changed target version to 0.80.10 as this commit got merged early
- 04:42 PM devops Bug #11591: "VersionNotFoundError: Failed to fetch package version" in rados-hammer-distro-basic-...
- In the smoke suite, no @os_type@ was provided so we don't have a way to check for packages up front.
In the upgrad... - 04:14 PM Stable releases Tasks #11090: firefly v0.80.10
- * changed "Branch to build from" to reflect last-minute backport
* changed Sam's rados approval to "YES" based on IR... - 04:08 PM Documentation #11503: [Docs] Placement Groups
- https://github.com/ceph/ceph/pull/4785
- 09:07 AM Documentation #11503 (Resolved): [Docs] Placement Groups
- 02:39 PM rgw Backport #11720 (In Progress): rgw deleting S3 objects leaves __shadow_ objects behind
- 01:50 PM Revision 6f11fbf4 (ceph): debian: ceph-dbg steals ceph-objectstore-tool from ceph-test-dbg
- When ceph-objectstore-tool was moved from ceph-test to
ceph by 61cf5da0b51e2d9578c7b4bca85184317e30f4ca, the ceph pac... - 01:31 PM Revision dbd9a87e (ceph): Merge pull request #4787 from yuyuyu101/fix-perf-i386
- PerfLocal: fix i386 compatible with perf_local
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:20 PM Revision 735abeaf (ceph): Osd: classify flush mode into low speed and high speed modes
- Signed-off-by: Mingxin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com>
Suggested-by: N... - 11:47 AM CephFS Bug #11789: knfs mount fails with "getfh failed: Function not implemented"
- I don't think this is likely to be a regression from previous hammer release, so not a blocker imho
- 11:45 AM rgw Feature #11804 (Resolved): rgw: configurable number of rados handles
- This was implemented by Pavan Rallabhandi <pavan.rallabhandi@sandisk.com> and was merged in commit:77e0084028b85feced...
- 11:43 AM rgw Feature #11804 (Resolved): rgw: configurable number of rados handles
- 11:41 AM Revision 77e00840 (ceph): Merge pull request #4309 from prallabh/master
- RGW: Make RADOS handles in RGW to be a configurable option
Passed rgw teuthology suite run.
Reviewed-by: Yehuda Sad... - 11:16 AM Bug #11334: osd: op with newer epoch stuck in optracker
- the only holder of TrackedOpRef is session.waiting_on_map. and once an updated osdmap is received, the request in wai...
- 10:28 AM Revision 729c5e1c (ceph): Merge pull request #4789 from yehudasa/wip-11442-notes
- rgw: update release notes with regard to issue #11442 recovery
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:13 AM devops Backport #11735 (In Progress): RGW init script needs to check /var/lib/ceph/radosgw
- > If not, I have resolved the conflicts on my wip branch, https://github.com/ceph/ceph/tree/wip-11686-rgw-init-hammer...
- 10:10 AM devops Bug #11686: RGW init script needs to check /var/lib/ceph/radosgw
- (setting sage as an assignee because he is the author of the original patches, not because an action is required of him)
- 10:07 AM Revision 926f2dfe (ceph): rgw: update release notes with regard to issue #11442 recovery
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:58 AM Backport #11801 (In Progress): Make it more difficult to delete pools in firefly
- 07:28 AM Backport #11801 (Resolved): Make it more difficult to delete pools in firefly
- https://github.com/ceph/ceph/pull/4788
- 09:56 AM rgw Bug #11802 (Duplicate): Key not found on some object after upgrade to Hammer
- Hello,
We have a problem regarding our Ceph upgrade. When we upgrade from Giant to Hammer, all objects beginning w... - 09:25 AM Revision 0b5944ae (ceph): PerfLocal: fix i386 compatible with perf_local
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 09:01 AM Revision b80e2144 (ceph): Merge pull request #4785 from tchaikov/wip-doc-fixes
- doc: typo fixes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:01 AM Revision a3199767 (ceph): Forward port suse build deps and recomends
- SUSE spec file got very out of sync with upstream master. This patch
helps resolve the build dependencies from suse c... - 08:40 AM rgw Bug #11753 (Resolved): rgw: missing test for issue #11639
- Merged in test into s3-tests, commit:cece4dd137ceae62925b9fd8199b668adfc70f7e
- 08:39 AM Revision aa62dcbe (ceph): osdmaptool: dump 'osd tree' in specified format
- * so we are able to dump more info from osdmap using this tool,
and this allows us to reproduce the behavior of "ce... - 08:39 AM Revision a808c814 (ceph): osdmap, mon: switch the params of print_tree()
- * change from
print_tree(ostream*, Formatter*)
to
print_tree(Formatter*, ostream*)
this is more consisten... - 07:44 AM Revision 9c8f8d27 (ceph): doc: fix a wrong quote in release.rst
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 07:44 AM Revision acdfd987 (ceph): doc: fix typo in placement-groups.rst
- s/osd pool set/osd pool create/ in the command line example.
Fixes: #11503
Signed-off-by: Kefu Chai <kchai@redhat.com> - 07:28 AM Backport #11799 (Closed): REJECTED mon/OSDMonitor: require mon_allow_pool_delete = true to remove...
- 07:15 AM Backport #11799 (Closed): REJECTED mon/OSDMonitor: require mon_allow_pool_delete = true to remove...
- Backport https://github.com/ceph/ceph/commit/6b982e4cc00f9f201d7fbffa0282f8f3295f2309 to firefly
- 07:27 AM Bug #11800 (Resolved): Make it more difficult to delete pools in firefly
- There is a commit entitled "mon/OSDMonitor: require mon_allow_pool_delete = true to remove pools" https://github.com/...
- 07:12 AM Revision 2cc7aee1 (ceph): mon: MonitorDBStore: get_next_key() only if prefix matches
- get_next_key() had a bug in which we would always return the first key
from the iterator, regardless of whether its p... - 07:12 AM Feature #9792: make it harder to remove cluster data pools
- This commit https://github.com/ceph/ceph/commit/6b982e4cc00f9f201d7fbffa0282f8f3295f2309 partially addresses the issue
- 06:17 AM CephFS Bug #11783 (In Progress): protocol: flushing caps on MDS restart can go bad
- this is a message ordering issue when MDS failover.
chown marks Ax dirty
client flushes and releases Ax cap
cho... - 01:06 AM devops Bug #11798 (Resolved): upstart: configuration is too generous on restarts
- See https://bugzilla.redhat.com/show_bug.cgi?id=1210871 for the investigation that prompted this.
Our current upst... - 01:02 AM CephFS Bug #11790 (Resolved): "cannot utime" errors in from tar in knfs workloads
- it's nfs bug in 4.1-rc2 kernel. now the testing branch has been rebased to 4.1-rc5, this issue should disappear
05/27/2015
- 11:32 PM devops Bug #11546 (In Progress): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- 04:24 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- There must be some additional Debian packaging changes that we need in order to make apt upgrade @ceph-test-dbg-0.80....
- 03:42 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- ...
- 03:30 PM devops Bug #11546 (New): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- Tests still failing
Run: http://pulpito.ceph.com/teuthology-2015-05-27_07:59:13-upgrade:firefly-x-hammer-distro-basi... - 12:57 PM devops Bug #11546 (Resolved): ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- 12:54 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- #11733 has been resolved
- 11:04 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- Run: http://pulpito.ceph.redhat.com/teuthology-2015-05-18_21:00:02-rados-hammer-distro-basic-magna/
Jobs: ['111030',... - 10:52 PM Bug #11786 (Fix Under Review): mon: MonitorDBStore iterator's get_next_key() returns wrong keys
- https://github.com/ceph/ceph/pull/4783
- 02:55 PM Bug #11786 (Resolved): mon: MonitorDBStore iterator's get_next_key() returns wrong keys
- specifically, the first key of the iterator is always returned first, regardless of it's prefix being passed on to th...
- 10:48 PM Revision 4b6d0819 (ceph): mon: Monitor: wait_for_paxos() before scrubbing
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 10:48 PM Revision ba4a2c1a (ceph): mon: Monitor: inject scrub failures
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 10:48 PM Revision 80ce9b0d (ceph): mon: Monitor: inject missing key failures during scrub
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 10:48 PM Revision e77b3f4d (ceph): mon: Monitor: allow scrub to timeout after a while
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 10:48 PM Revision 29349090 (ceph): mon: Monitor: allow updating scrub interval on demand
- The interval, by default, is 3600*60 seconds (1 day). When we start the
monitor we set the event to trigger a scrub ... - 10:48 PM Revision 0a19fd4a (ceph): mon: Monitor: rework scrub (2)
- Instead of hanging while scrubbing all the keys in the store, scrub just
a few keys each time and keep scrubbing unti... - 10:36 PM Revision 071c9438 (ceph): Merge pull request #4766 from SUSE/wip-11673-firefly
- Debian: ceph-test and rest-bench debug packages should require their respective binary packages
Reviewed-by: Sage We... - 10:32 PM Tasks #11797 (Rejected): does our log rotation do the right thing?
- Our logrotate.conf file uses the rotate, compress, and sharedscripts flags, and has a postrotate script which sends a...
- 10:29 PM Revision b2ccd9e3 (ceph): Merge pull request #4728 from branch-predictor/wip-radosbench-nomemcmp
- tools: add --no-verify option to rados bench
Reviewed-by: Sage Weil <sage@redhat.com> - 10:26 PM Revision 91d82515 (ceph): Merge pull request #4547 from yuyuyu101/wip-perf
- Perf: used to perf local hardware capacity
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:20 PM devops Bug #11591: "VersionNotFoundError: Failed to fetch package version" in rados-hammer-distro-basic-...
- Run: http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-24_17:05:01-upgrade:giant-giant-distro-basic-typica/
... - 10:04 PM devops Bug #11591 (New): "VersionNotFoundError: Failed to fetch package version" in rados-hammer-distro-...
- Run: http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-24_05:00:01-smoke-master-distro-basic-typica/
Jobs: ... - 10:13 PM rbd Bug #11796 (Resolved): "rbd_get_flags() indicates object map is invalid" in smoke-master-distro-b...
- Run: http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-24_05:00:01-smoke-master-distro-basic-typica/
Job: [... - 10:10 PM rgw Bug #11795 (Resolved): "test_multipart_upload_small ... FAIL" in smoke-master-distro-basic-typica...
- Run: http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-24_05:00:01-smoke-master-distro-basic-typica/
Job: [... - 10:07 PM CephFS Bug #11779 (Resolved): Intermittent failure in test_full
- 10:02 PM CephFS Bug #11779: Intermittent failure in test_full
- The breaker was...
- 09:18 PM CephFS Bug #11779 (Pending Backport): Intermittent failure in test_full
- Not sure when the change happened that broke this — do we need to backport to older qa branches?
- 12:53 PM CephFS Bug #11779 (Fix Under Review): Intermittent failure in test_full
- https://github.com/ceph/ceph-qa-suite/pull/447
- 11:16 AM CephFS Bug #11779 (Resolved): Intermittent failure in test_full
It isn't waiting long enough before writing the last chunk of data. This used to work because the osd report inter...- 10:00 PM rgw Bug #11794 (Can't reproduce): swift TestAccount tests failed in smoke-master-distro-basic-typica run
- Run: http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-24_05:00:01-smoke-master-distro-basic-typica/
Jobs: ... - 09:54 PM CephFS Bug #11781: multiple_rsync failure with fuse client
- #9884 was the case where it timed out b/c there were just so many files, whereas in this instance it's actually faili...
- 09:22 PM CephFS Bug #11781: multiple_rsync failure with fuse client
- Possibly a dup of #9884? :/ I'm not sure how accurate that "too many files" is as the actual bug cause, though...
- 12:46 PM CephFS Bug #11781: multiple_rsync failure with fuse client
- Wrong project, sorry.
- 12:28 PM CephFS Bug #11781 (Rejected): multiple_rsync failure with fuse client
The second rsync run is transferring some data, so either timestamps are going wrong, dentries are going missing, o...- 09:50 PM CephFS Bug #11790: "cannot utime" errors in from tar in knfs workloads
- It's the failure to set mtimes etc on an extracted file via utimensat.
I have a slightly fuzzy memory that we were... - 09:25 PM CephFS Bug #11790: "cannot utime" errors in from tar in knfs workloads
- ...
- 08:14 PM CephFS Bug #11790: "cannot utime" errors in from tar in knfs workloads
- hammer v0.94.2 release
do you think is this a blocker? - 07:21 PM CephFS Bug #11790 (Resolved): "cannot utime" errors in from tar in knfs workloads
- http://pulpito.ceph.com/teuthology-2015-05-18_13:43:17-knfs-hammer-testing-basic-multi/897933/
http://pulpito.ceph.c... - 09:31 PM Bug #11793 (Resolved): test: rados.py does not do cache_(evict|flush|try_flush) since it leaves o...
- Enabling it causes:
2015-05-27T12:23:17.122 INFO:tasks.rados.rados.0.plana93.stdout:update_object_version oid 489 ... - 09:29 PM CephFS Bug #11301 (Resolved): mds-full test occasionally fails due to blacklist expiry
- 09:29 PM Revision d9959b18 (ceph): Merge pull request #443 from ceph/wip-11301
- tasks/cephfs: reset osd blacklist between tests
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:25 PM Revision c6f62f51 (ceph): Merge remote-tracking branch 'gh/next'
- 09:23 PM CephFS Bug #11783: protocol: flushing caps on MDS restart can go bad
- Yep, this one looks unfamiliar to me. :( Do we have client logs from when it happened that we can reference?
- 01:04 PM CephFS Bug #11783 (Resolved): protocol: flushing caps on MDS restart can go bad
Not consistent, not happening on master.
http://pulpito.ceph.com/teuthology-2015-05-16_23:04:02-fs-next-testing-...- 09:22 PM Bug #11548: "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-basic-multi run
- Run: http://pulpito.ceph.com/teuthology-2015-05-26_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Jobs: almost all - 09:17 PM Revision 4a79c75d (ceph): Merge pull request #447 from ceph/wip-11779
- tasks/cephfs: fix timing in test_full
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:56 PM devops Backport #11734: Debian: ceph-test and rest-bench debug packages should require their respective ...
- Yuri: this is a Firefly backport. This issue has already been backported to hammer, see http://tracker.ceph.com/issue...
- 04:30 PM devops Backport #11734: Debian: ceph-test and rest-bench debug packages should require their respective ...
- I'm not 100% sure if this particular issue is blocking upgrade testing or not...
- 04:28 PM devops Backport #11734: Debian: ceph-test and rest-bench debug packages should require their respective ...
- Loic - we need to be backported for hammer v0.94.2
- 08:44 PM CephFS Bug #11792 (New): mds: recursive statistics are either inaccurate or too "chunky"
- https://www.mail-archive.com/ceph-users@lists.ceph.com/msg20005.html...
- 08:26 PM CephFS Bug #11784: ceph-fuse hang on unmount (stuck dentry refs)
- John, is this likely to have been a dup of #11294? We can tell by checking out the ceph-fuse log if it's still availa...
- 01:28 PM CephFS Bug #11784 (Can't reproduce): ceph-fuse hang on unmount (stuck dentry refs)
- http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-19_23:14:02-samba-master-testing-basic-typica/21446/
Th... - 08:14 PM CephFS Bug #11789: knfs mount fails with "getfh failed: Function not implemented"
- hammer v0.94.2 release
do you think is this a blocker? - 07:08 PM CephFS Bug #11789 (Can't reproduce): knfs mount fails with "getfh failed: Function not implemented"
See plana37 syslog on /a/teuthology-2015-05-18_13:43:17-knfs-hammer-testing-basic-multi/897936...- 08:07 PM rbd Bug #11791 (Resolved): A client opening an image mid-resize can result in the object map being in...
- There is a potential race where the object map size on disk does not match the image size on disk. This causes librb...
- 06:31 PM Revision 90eb7768 (ceph): ReplicatedPG::trim_object: write filtered snapset while we're at it
- If we trimmed an object, we might as well remove the obsolete snaps
as well.
Signed-off-by: Samuel Just <sjust@redha... - 06:30 PM Revision 6051e255 (ceph): ReplicatedPG: start_flush: use filtered snapset
- Otherwise, we might send our deletes based on deleted snaps. This is
problematic since we may have trimmed the clone... - 05:59 PM Bug #11787 (Resolved): start_flush: filter out removed snaps before determining snapc's
- 2015-05-24T17:33:00.778 INFO:tasks.rados.rados.0.plana86.stdout:2668: expect deleted
2015-05-24T17:33:00.811 INFO:t... - 05:05 PM Messengers Bug #5508 (Resolved): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
- ah, dup of #11381, fixed by commit:0ea0e011a6a6c6d6b40f5d97328bbad0e4568dd7
- 04:39 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- Yehuda, can you provide an example on how to add the repair tool to this test suite ?
- 03:46 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- I don't think it would be a blocker, but.. should we try to run the repair tool as part of this test suite?
- 03:08 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- Yehuda: is this a blocker for the hammer release ? If it was already in v0.94.1 it would not be a blocker, right ?
- 08:42 AM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- One suspect would be the broken objects starting with underscore on older hammer, so hammer to hammer upgrade means t...
- 04:25 PM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
- This is very rare and has been around for over a year.
- 04:03 PM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
- David, is this issue a blocker for hammer v0.94.2 release?
- 03:48 PM Revision 9ff69f64 (ceph): Merge pull request #4750 from vuhuong/wip-xio
- xio: several bug fixes
- 03:40 PM Revision f6c61dfc (ceph): Merge pull request #4782 from dachary/wip-doc-ceph-helpers
- tests: document ceph helpers
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:14 PM Revision 1eff4bc9 (ceph): Merge pull request #4700 from ceph/wip-crush-ruleset-name
- Validate default replicated ruleset config value
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Loic D... - 02:56 PM Revision 9e75d3b3 (ceph): Merge pull request #4759 from yuyuyu101/wip-kvstore-misc
- Wip kvstore misc
Reviewed-by: Varada Raja Kumar Kari <kariraja@yahoo.com> - 02:54 PM Revision 933df036 (ceph): tests: fix the main() documentation of ceph-helpers.sh
- It was incorrectly documented as calling the setup function. It was
also vague on how the environment was reset.
Sig... - 02:16 PM Revision a8e4b4fd (ceph): tests: remove unused CEPH_HELPER_VERBOSE in ceph-helpers.sh
- And undocumented. It may be useful for debugging but it would have to be
properly implemented instead of being half c... - 01:58 PM Bug #11334: osd: op with newer epoch stuck in optracker
- so it seems that, sometimes we failed to release OpRequestRef timely.
and hence didn't remove the finished op out ... - 01:29 PM CephFS Bug #11756 (Resolved): 'ls /sys/fs/fuse/connections' causes fuse mount fails
- 01:29 PM Revision 90b22c87 (ceph): Merge pull request #444 from ceph/wip-11756
- tasks/cephfs: mount fusectl before listing fuse connections
Reviewed-by: John Spray <john.spray@redhat.com> - 12:41 PM Revision 9c3040c0 (ceph): krbd: add unmap subsuite
- .. for testing various unmap scenarios, mostly unmap by spec, but also
unmap by device and device partition.
Signed-... - 12:41 PM Revision 633ab410 (ceph): ceph_deploy: no need to fetch overrides twice
- Looks like Sandon's and Sage's changes raced and there are now two
sites where we fetch overrides. One should be eno... - 12:11 PM Revision 665a8570 (ceph): rgw: civetweb should use unique request id
- max_req_id was moved to RGWRados and changed to atomic64_t.
The same request id resulted in gc giving the same idtag... - 12:06 PM Revision c00e3933 (ceph): OSDMonitor: fix prepare_pool_crush_ruleset() retval
- CrushWrapper::get_osd_pool_default_crush_replicated_ruleset() returns
-1 on error. Returning -EPERM for "No suitable... - 12:06 PM Revision eb9dbef2 (ceph): doc: fix crush-ruleset-name param description
- Specified crush-ruleset-name is required to exist, implicit creation is
going to happen only if crush-ruleset-name wa... - 12:05 PM Revision ea4f9421 (ceph): tests: a couple tweaks to osd-pool-create.sh
- In TEST_default_deprectated_*(), make expected/unexpected vars local
and actually check that rbd, being a default cre... - 12:05 PM Revision f032c409 (ceph): OSDMap: respect default replicated ruleset config opt in build_simple()
- Use id provided by osd_pool_default_crush_{replicated_ruleset,rule}
config options when creating a simple replicated ... - 12:05 PM Revision 29f11c7b (ceph): CrushWrapper: validate default replicated ruleset config opt
- Validate osd_pool_default_crush_{replicated_ruleset,rule} config
options, in particular when creating pools. Otherwi... - 11:40 AM Revision 5ff2743d (ceph): tasks/cephfs: fix timing in test_full
- The interval between writes was too short because
it was not taking account of the way OSDMap full
flags are set on t... - 11:21 AM Revision 770bd756 (ceph): Merge pull request #4777 from SUSE/wip-git_ignore_systemd_autotools_tem...
- .gitignore: systemd/ceph-osd@.service
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:03 AM Revision 81faac75 (ceph): debian/copyright: update copyright for test/perf*
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 09:54 AM Revision 93653f59 (ceph): Merge pull request #4779 from theanalyst/scripts/ceph-release-notes
- scripts: Add a helper to make release notes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:42 AM Revision cc92872b (ceph): scripts: Add a helper to make release notes
- First cut for a `ceph-release-notes` script added which looks at merge
commits and picks out issue numbers. Though th... - 09:42 AM rgw Bug #11639: Object copy bug
- Test available in #11753 (pull request asked)
- 09:38 AM rgw Bug #11753: rgw: missing test for issue #11639
- Test covering issue #11639 available.
Created pull request here...
https://github.com/ceph/s3-tests/pull/56 - 09:19 AM rgw Backport #11720: rgw deleting S3 objects leaves __shadow_ objects behind
- Orit has some concerns about the approach I took on this backport.
- 09:16 AM Backport #11700: make the all osd/filestore thread pool suicide timeouts separately configurable
- Agreed with Sam on IRC that he will do the backport.
- 08:25 AM Revision 2879b0cd (ceph): .gitignore: systemd/ceph-osd@.service
- systemd/ceph-osd@.service is now auto-generated by autotools.
This means the file should be added to gitignored list... - 07:40 AM devops Backport #11733 (Resolved): Debian: ceph-test and rest-bench debug packages should require their ...
- 04:51 AM Revision f8142980 (ceph): packaging: include ceph_perf_local
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:51 AM Revision 61d70db3 (ceph): ceph_perf_local: rename from ceph_perf
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:41 AM Revision 178484b8 (ceph): librbd: re-add missing discard perf counters
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:20 AM Revision a62c3aa1 (ceph): ceph.in: handle unknown Exception correctly
- * in case parse_cmdargs() throws
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 7789eefc01de... - 04:20 AM Revision eb26388c (ceph): ceph.in: parse quote correctly in interactive mode
- Fixes: #11279
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit bc7d8c99d2e16a141a8b575281ba12c6... - 04:20 AM Revision cc7f7441 (ceph): ceph.in: improve the interactive mode
- * if ceph is not reading from a tty, expect EOF instead of "quit"
as the end of input.
* do not panic at seeing the... - 02:58 AM Bug #11554 (Duplicate): Osds not start after upgrade
- 01:53 AM Revision eb69cf75 (ceph): Merge pull request #4773 from dachary/wip-11733-hammer
- Debian: ceph-test and rest-bench debug packages should require their respective binary packages
Reviewed-by: Ken Dre... - 01:29 AM Feature #11692 (Rejected): online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't...
- these options work as expected. so i am closing this issue. please feel free to reopen it if you think otherwise, tha...
- 01:27 AM Feature #11692: online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't take effect.
- Kefu Chai wrote:
> cory, you might want to try out
> [...]
>
> but i am not sure why we are using different set...
05/26/2015
- 11:43 PM Revision 344328de (ceph): debian: set rest-bench-dbg ceph-test-dbg dependencies
- Debian's debug packages ought to depend on their respective binary
packages. This was the case for many of our ceph p... - 11:17 PM Revision 9721d422 (ceph): Merge pull request #4708 from dachary/wip-erasure-code-profile
- erasure-code: fix error reporting
Reviewed-by: Takeshi Miyamae <miyamae.takeshi@jp.fujitsu.com> - 10:56 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Damn autocorrect. "at the top me we" => "at the time we".
- 10:54 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- We're aware that this is not atomic. We could accept that, because at the top me we do the snapshots we can be reason...
- 10:39 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- (removed, wrong bug)
- 08:29 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- It's not really a very good backup option not least because the snapshots are not synchronized across pools. Also, b...
- 03:58 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Follow up: after we had deleted the newly created snapshot from the RGW pools, the system has not crashed again. We a...
- 10:48 PM Bug #11660 (Duplicate): "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-b...
- 10:40 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- (03:36:43 PM) sjustwork: these two nodes are 3 hours off.
(03:37:03 PM) sjustwork: the utime_t->string calculation i... - 02:12 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- The log lines containing the OID *1/hit_set_2.1_archive_2015-05-20 18:21:56.078514_2015-05-20 18:22:58.416980/head/.c...
- 01:05 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- "rados/thrash/{0-size-min-size-overrides/2-size-1-min-size.yaml 1-pg-log-overrides/normal_pg_log.yaml clusters/fixed-...
- 10:48 PM Bug #9732: ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
- This...is not resolved! The utime_t->hobject_t mapping is timezone dependent. Needs to be not timezone dependent wh...
- 03:06 PM Bug #9732: ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
- I think I blamed this on the timezones, though I do not remember how.
- 10:37 PM Revision 5a216b14 (ceph): Merge pull request #4768 from SUSE/wip-systemd_autotools_template_syste...
- Template systemd/ceph-osd@.service with autotools,
Reviewed-by: Sage Weil <sage@redhat.com> - 10:12 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- Running here http://pulpito.ceph.com/teuthology-2015-05-26_15:11:31-upgrade:firefly-x-hammer-distro-basic-vps/
#11... - 10:06 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- When #11733 is fixed, does this problem still recur?
- 08:24 PM rbd Backport #11769 (In Progress): librbd: aio calls may block
- 08:22 PM rbd Backport #11769: librbd: aio calls may block
- https://github.com/ceph/ceph/pull/4364 - DNM until it's been verified in master for a bit
- 07:08 PM rbd Backport #11769 (Resolved): librbd: aio calls may block
- https://github.com/ceph/ceph/pull/4854 -- DNM until Josh provides +1
- 08:23 PM Bug #10612 (New): "[ FAILED ] LibRadosCmd.OSDCmd " in upgrade:dumpling-x-firefly-distro-basic-vps
- One more
Run: http://pulpito.ceph.com/teuthology-2015-05-24_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps/
J... - 08:21 PM Feature #11775 (Closed): change default port
- 08:20 PM Cleanup #11774 (In Progress): osd: finish wip-temp ObjectStore changes
- 08:12 PM Cleanup #11774 (Resolved): osd: finish wip-temp ObjectStore changes
- 08:11 PM Feature #11773 (In Progress): mon: better scrub
- 08:11 PM Feature #11773 (Resolved): mon: better scrub
- 08:08 PM Feature #10098: wanted: command to clear 'incomplete' PGs
- Probably ceph_objectstore_tool --[unsafe?]-mark-complete <pgid> on a down osd.
Definitely need to set:
info.last_... - 07:58 PM Revision ff79959c (ceph): osd_types::is_new_interval: size change triggers new interval
- Fixes: 11771
Signed-off-by: Samuel Just <sjust@redhat.com> - 07:38 PM Bug #11771 (Resolved): is_new_interval: size change should cause new interval
- 07:26 PM rbd Documentation #11750: Can't create image with format 2 with non-admin user
- Thanks, that fixed it.
I'd suggest to update the "User Management" documentation at http://ceph.com/docs/master/ra... - 02:21 PM rbd Documentation #11750 (Need More Info): Can't create image with format 2 with non-admin user
- RBD format 2 images require the execute capability on the OSD. Can you please retest and update the ticket with the ...
- 07:11 PM rgw Backport #11729: rgw: leak of bucket meta objects on bucket re-creation
- Non, car cette modification n'as pas encore été intégrée. No, because this commit has not yet been merged. I'm sure X...
- 06:43 PM rgw Backport #11729: rgw: leak of bucket meta objects on bucket re-creation
- The target version should be v0.80.10, n'est-ce pas?
- 07:09 PM rbd Backport #11770 (Resolved): librbd: aio calls may block
- https://github.com/ceph/ceph/pull/4875
- 07:07 PM Revision e2f392ef (ceph): Merge pull request #4761 from dachary/wip-doc-workflow
- doc: update the development workflow
Reviewed-by: Nathan Cutler <ncutler@suse.cz>
Reviewed-by: Abhishek Lekshmanan <... - 06:50 PM Revision 101287d8 (ceph): Merge pull request #4772 from theanalyst/doc/release/v0.94.2-updates
- doc: updates to v0.94.2 draft release notes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:43 PM rbd Fix #11056 (Pending Backport): librbd: aio calls may block
- 06:43 PM Revision d925aeb0 (ceph): Merge pull request #4318 from ceph/wip-11056
- librbd: avoid blocking AIO API methods
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:36 PM rgw Backport #11720 (Fix Under Review): rgw deleting S3 objects leaves __shadow_ objects behind
- 02:25 PM rgw Backport #11720: rgw deleting S3 objects leaves __shadow_ objects behind
- Waiting for Yehuda to review the pull request.
- 01:02 PM rgw Backport #11720 (In Progress): rgw deleting S3 objects leaves __shadow_ objects behind
- 06:34 PM rbd Feature #11286 (In Progress): add general journal
- 06:30 PM Revision 93af3829 (ceph): PendingReleaseNotes: document changes to librbd's aio_read methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:25 PM Revision 24a33e97 (ceph): WorkQueue: add new ContextWQ work queue
- The queue holds a collection of Context pointers that will
be completed by the thread pool.
Signed-off-by: Jason Dil... - 06:25 PM Revision b3f5a753 (ceph): WorkQueue: added virtual destructor
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:25 PM Revision afb896d9 (ceph): librbd: add task pool / work queue for requests / callbacks
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:25 PM Revision 3a7b5e30 (ceph): librbd: avoid blocking AIO API methods
- Enqueue all AIO API methods within the new librbd thread pool to
reduce the possibility of any blocking operations. T... - 06:25 PM Revision 6d1d0c86 (ceph): librbd: add new fail method to AioCompletion
- Helper method to handle passing fatal errors generated within
librbd (not from the OSDs) back to the client.
Signed-... - 06:25 PM Revision b88b88c5 (ceph): Throttle: added pending_error method to SimpleThrottle
- Allow the client of SimpleThrottle to detect an async error
so that it can exit early.
Signed-off-by: Jason Dillaman... - 06:25 PM Revision 9ab42d61 (ceph): librbd: internal AIO methods no longer return result
- All failures should be returned via the AioCompletion.
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 06:25 PM Revision c77bce33 (ceph): librbd: AioRequest::send no longer returns a result
- The librados calls used by AioRequest::send should always return
zero unless there is a bug.
Signed-off-by: Jason Di... - 06:25 PM Revision 948b15eb (ceph): tests: update librbd AIO tests to remove result code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:23 PM Revision a7bce203 (ceph): doc: updates to v0.94.2 draft release notes
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
- 06:02 PM Linux kernel client Fix #11767 (In Progress): qa: clean up krbd workunits and add any missing cases to qa suite
- Some older workunits were failing invisibly, by not exiting with an error status. There are other issues like too muc...
- 05:52 PM rgw Backport #11761 (Closed): REJECTED: rgw: fcgi connections are not closed when using mod-proxy-fcgi
- 02:08 PM rgw Backport #11761 (Rejected): REJECTED: rgw: fcgi connections are not closed when using mod-proxy-fcgi
- 01:54 PM rgw Backport #11761 (In Progress): REJECTED: rgw: fcgi connections are not closed when using mod-prox...
- 01:53 PM rgw Backport #11761 (Closed): REJECTED: rgw: fcgi connections are not closed when using mod-proxy-fcgi
- https://github.com/ceph/ceph/pull/4764
- 05:44 PM rbd Feature #11766 (Resolved): rbd-mirror: basic structure
- design discussion: http://pad.ceph.com/p/rbd_mirror_daemon (backup: http://fpaste.org/335877/raw/)
- 05:41 PM Backport #11759 (In Progress): ceph-disk: get_partition_type fails on /dev/cciss...
- 11:45 AM Backport #11759 (Resolved): ceph-disk: get_partition_type fails on /dev/cciss...
- https://github.com/ceph/ceph/pull/4771
- 05:39 PM Revision 90a1a758 (ceph): ceph-disk: support NVMe device partitions
- Linux nvme kernel module v0.9 enumerate devices as following:
/dev/nvme0 - characted revice
/dev/nvme0n1 - whole blo... - 05:28 PM rbd Feature #11405 (Resolved): qa: test rbd notify-based proxying across versions
- 05:27 PM Revision eb633911 (ceph): Merge pull request #438 from ceph/wip-11405
- client-upgrade: test librbd backwards compatibility
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:25 PM rbd Feature #7746 (Resolved): Capacity Management: rbd df
- 05:21 PM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 05:19 PM Bug #11665 (In Progress): erasure-code: test/osd/osd-scrub-repair.sh add lrc test case
- 05:19 PM Backport #11741 (In Progress): crush: take crashes due to invalid arg
- 05:17 PM Revision f93eadd7 (ceph): mon: prevent bucket deletion when referenced by a rule
- If a rule references a bucket with 'take', prevent deletion.
Fixes: #11602
Signed-off-by: Sage Weil <sage@redhat.com... - 05:11 PM Revision d7a23491 (ceph): doc: update the development workflow
- * use HOWTO_monitor_the_automated_tests_AKA_nightlies to explain the nightlies
* replace references to Serverity with... - 05:07 PM Revision 62b0f88e (ceph): Merge pull request #4756 from ceph/wip-mount-timeout-doc
- rbd: document mount_timeout in the man page
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:04 PM Revision ac347dc3 (ceph): Template systemd/ceph-osd@.service with autotools,
- The libexec path is different for different distributions.
systemd. This path is defined by a new variable on the
con... - 04:43 PM Backport #11700: make the all osd/filestore thread pool suicide timeouts separately configurable
- Waiting for Somnath to look at the pull request.
- 04:35 PM Backport #11700 (Fix Under Review): make the all osd/filestore thread pool suicide timeouts separ...
- 03:35 PM Bug #9218 (Resolved): FAILED assert(peering_queue.empty()) during OSD shutdown
- I was wrong. The backport is there: https://github.com/ceph/ceph/commit/f19162adc241e627ce20140360352ac96f809a6e
- 03:24 PM Bug #9218 (Pending Backport): FAILED assert(peering_queue.empty()) during OSD shutdown
- ...
- 03:32 PM Backport #11763 (Rejected): FAILED assert(peering_queue.empty()) during OSD shutdown
- 03:21 PM Backport #11763 (Rejected): FAILED assert(peering_queue.empty()) during OSD shutdown
- 03:11 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- Zack Cerza wrote:
> Well, maybe not; I don't define (or fully understand) our upstream testing strategy. What I do k... - 02:41 PM Revision 2b23327b (ceph): Mutex: fix leak of pthread_mutexattr
- Need pthread_mutexattr_destroy after pthread_mutexattr_init
Fixes: #111762
Signed-off-by: Ketor Meng <d.ketor@gmail.... - 02:38 PM Bug #11762 (Fix Under Review): Memory leak in Mutex.cc, pthread_mutexattr_init without pthread_mu...
- https://github.com/ceph/ceph/pull/4760
- 02:32 PM Bug #11762 (Resolved): Memory leak in Mutex.cc, pthread_mutexattr_init without pthread_mutexattr_...
- Leak in function Mutex::Mutex
in "else if (lockdep)" statement,
there is pthread_mutexattr_init(&attr) and withou... - 02:31 PM Revision c632ef13 (ceph): debian: set rest-bench-dbg ceph-test-dbg dependencies
- Debian's debug packages ought to depend on their respective binary
packages. This was the case for many of our ceph p... - 02:26 PM Bug #11582 (Can't reproduce): ceph-0.80.9 compile error
- cory, i am closing it, please feel free to reopen it once we have more info to move this issue forward. thanks.
- 02:18 PM Revision bd542353 (ceph): tasks/cephfs: mount fusectl before listing fuse connections
- Fixes: #11756
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:40 PM rgw Backport #11721 (In Progress): Keystone PKI token expiration is not enforced
- 01:34 PM Backport #11699: Objecter: resend linger ops on split
- The commit does not cherry-pick cleanly and it's not obvious how to resolve the conflicts in src/osdc/Objecter.cc so ...
- 01:26 PM Revision d4ef5566 (ceph): rgw: always check if token is expired
- Fixes: #11367
Currently token expiration is only checked by the token cache. With PKI
tokens no expiration check is ... - 01:00 PM Stable releases Tasks #11644 (In Progress): firefly v0.80.11
- 12:00 PM rgw Backport #11754 (In Progress): Object copy bug
- 11:56 AM Revision 2d5d8da3 (ceph): rgw: Use attrs from source bucket on copy
- On copy objects, when bucket source is the same as the destination, use attrs
from source bucket.
Fixes: #11639
Sig... - 11:47 AM Bug #11360 (Rejected): src/test/osd/osd-test-helpers.sh needs 240 sec timeouts
- osd-test-helpers.sh is deprecated
- 11:46 AM Backport #11760 (Resolved): ceph-disk: get_partition_type fails on /dev/cciss...
- https://github.com/ceph/ceph/pull/4892
- 11:45 AM Bug #11612 (Pending Backport): ceph-disk: get_partition_type fails on /dev/cciss...
- 11:43 AM Fix #11663 (Fix Under Review): erasure-code-profile: verify profile content
- * master https://github.com/ceph/ceph/pull/4712
- 11:41 AM Bug #11359 (Resolved): cephtool/test.sh:test_tiering intermittent failure
- did not show up again, let's assume it was a run that had a version of the tree without the patch resolving this issue
- 11:14 AM Revision b37807c8 (ceph): Merge pull request #4746 from ceph/wip-blacklist-json
- osd: fix blacklist field in OSDMap::dump
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:06 AM Bug #11757: Failure to load the osdmap
- > Multiple server disconnects the power supply, but there is no error in the FS
Do you mean the server on which OS... - 11:04 AM Bug #11757: Failure to load the osdmap
- Ok. Could you add to this issue as much details as possible regarding how this new OSD (osd.25) was installed ? Maybe...
- 09:57 AM Bug #11757: Failure to load the osdmap
- Loic Dachary wrote:
> it would be useful to know more about the history of this OSD. Was it upgraded from a previous... - 09:45 AM Bug #11757: Failure to load the osdmap
- it would be useful to know more about the history of this OSD. Was it upgraded from a previous version ? Is it a fres...
- 09:32 AM Bug #11757 (Duplicate): Failure to load the osdmap
- Compiling from source the latest active version Hammer....
- 10:36 AM CephFS Bug #11758 (Resolved): kernel_untar_build fails on EL7
Perhaps the more recent GCC is too strict to compile the old kernel tarball we use in the test?
http://magna002....- 09:58 AM Revision 8ef6f860 (ceph): osd: fix blacklist field in OSDMap::dump
- This was using an array_section so we were getting
a list of only the times, instead of an array
mapping addr to time... - 09:58 AM Revision 38a319d5 (ceph): qa/cephtool: add blacklist json output check
- ...not very elegantly because this is bash, but
at least check the expected value is somewhere
present in the JSON ou... - 09:33 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- #11757
- 09:20 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- The bug #11373 is a duplicate of this one and the trace shows it crashes in load_pgs. Your problem seems slightly dif...
- 07:44 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- Loic, Already there is also attached to the current task: #11373
- 07:36 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- Loic Dachary wrote:
> what you're having is different: it's a failure to load the osdmap because the epoch in the os... - 07:27 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- what you're having is different: it's a failure to load the osdmap because the epoch in the osd superblock is a refer...
- 07:09 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- Loic, This conclusion was already with the patch: https://github.com/ceph/ceph/pull/4559
Or you need to recreate the... - 07:04 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- From ceph-osd.25.log.tar.gz ...
- 06:45 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- ...
- 06:00 AM Bug #11429: OSD::load_pgs: we need to handle the case where an upgrade from earlier versions whic...
- Hi Loic,Samuel
The problem remains despite the patch.
Look at the attached log file.... - 08:47 AM Fix #11666 (In Progress): erasure-code: add lrc to rados/thrash-erasure-code
- 07:21 AM Feature #11692: online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't take effect.
- cory gu wrote:
> a few questions here:
> So those settings are in pg level, does this mean all pools have the uni... - 06:09 AM Stable releases Tasks #11492: hammer v0.94.2
Problems with patch #11429 remain..
http://tracker.ceph.com/issues/11429#note-18- 04:40 AM Revision 4cc0f2f4 (ceph): KeyValueStore: Add collect_metadata support
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:34 AM Revision 7b5fc500 (ceph): KeyValueStore: Avoid extra lookup for map
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 03:57 AM Revision e805b944 (ceph): Merge pull request #4757 from xinxinsh/wip-kv-cleanup
- os : remove GenericObjectMap::sync() function
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 03:12 AM CephFS Bug #11756: 'ls /sys/fs/fuse/connections' causes fuse mount fails
- http://pulpito.ceph.com/teuthology-2015-05-22_23:04:02-fs-master-testing-basic-multi/906267/
- 03:01 AM CephFS Bug #11756 (Fix Under Review): 'ls /sys/fs/fuse/connections' causes fuse mount fails
- https://github.com/ceph/ceph-qa-suite/pull/444
- 03:00 AM CephFS Bug #11756 (Resolved): 'ls /sys/fs/fuse/connections' causes fuse mount fails
- before list fuse connections, we should make sure fusectl is mounted on /sys/fs/fuse/connections
- 02:22 AM CephFS Bug #11752 (Resolved): valgrind InvalidRead
- 01:18 AM Revision 70198708 (ceph): Merge pull request #4755 from ceph/wip-11752
- mds: fix use-after-free in SessionMap::remove_session
05/25/2015
- 11:15 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- 20 runs did not repeat the failure...
- 11:07 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- * "rados/thrash/{0-size-min-size-overrides/2-size-1-min-size.yaml 1-pg-log-overrides/normal_pg_log.yaml clusters/fixe...
- 10:57 PM Bug #11660 (In Progress): "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro...
- 07:38 PM Revision 81130516 (ceph): os : remove unused GenericObjectMap::sync() funtion since no caller inv...
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 04:40 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- in http://tracker.ceph.com/attachments/download/1716/1029402.log.gz, we have ...
- 02:38 PM Bug #11680 (Fix Under Review): mon crashes when "ceph osd tree 85 --format json"
- https://github.com/ceph/ceph/pull/4726
- 03:16 PM Documentation #11503: [Docs] Placement Groups
- Peter Matulis wrote:
> The top of the PG page [1] is completely wrong.
>
>
> b) PG numbers are limited by 32 pe... - 02:59 PM Revision 6ca60061 (ceph): erasure-code: lrc size test depends on layer semantic
- When the lrc layers are defined, the semantic of the D,c and _
characters are defined, the rest is undefined. The tes... - 02:59 PM Revision 08229225 (ceph): erasure-code: do not leak shec instance on failure
- If the shec plugin fails to initialize the instance, it must be deleted
before returning to the caller, otherwise it ... - 02:59 PM Revision db7936ae (ceph): erasure-code: implement consistent error stream
- The error stream in the erasure code path is broken and the error
message is sometime not reported back to the user. ... - 02:49 PM Revision 21036cf0 (ceph): erasure-code: define the ErasureCodeProfile type
- Instead of map<string,string>. Make it a non const when initializing
an ErasureCodeInterface instance so that it can ... - 12:41 PM Revision 52440c4b (ceph): rbd: document mount_timeout in the man page
- With "rbd: timeout watch teardown on unmap with mount_timeout" going
into kernel 4.2, document its effect in the man ... - 08:28 AM Feature #11692: online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't take effect.
- Hi Kefu,
Thank you for your reply. Just tried your suggested input, and it works.
a few questions here:
So those s... - 06:58 AM Feature #11692: online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't take effect.
- cory, you might want to try out ...
- 07:48 AM rgw Backport #11755 (Resolved): Object copy bug
- https://github.com/ceph/ceph/pull/4885
- 07:48 AM rgw Backport #11754 (Resolved): Object copy bug
- https://github.com/ceph/ceph/pull/4762
- 07:08 AM rgw Bug #11639 (Pending Backport): Object copy bug
- Note: we need to create a test for this in s3-tests. Opened issue #11753.
- 07:08 AM rgw Bug #11753 (Resolved): rgw: missing test for issue #11639
- Need to have a test that covers issue #11639
- 07:05 AM Revision 51bf619b (ceph): Merge pull request #4745 from jmunhoz/object-copy-bug
- rgw: Use attrs from source bucket on copy
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:46 AM Bug #11693 (Resolved): pidfile is overwritten and removed if the ceph-osd with the specified pidf...
- 05:43 AM Feature #10973 (Resolved): randomize scrub times
- 03:56 AM CephFS Bug #11752 (Fix Under Review): valgrind InvalidRead
- https://github.com/ceph/ceph/pull/4755
- 03:38 AM CephFS Bug #11752 (Resolved): valgrind InvalidRead
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-05-20_23:04:01-fs-master-testing-basic-multi/902897/teuthology.log
- 03:46 AM Revision 2daaa61b (ceph): mds: fix use-after-free in SessionMap::remove_session
- Fixes: #11752
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 03:23 AM Revision 0a98b021 (ceph): dump keyvaluestore transaction to a file
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 03:19 AM Revision 2a1493ca (ceph): test/ceph_test_rados: consolidate ReadOps
- Consolidate the completions, retvals, and results into vectors.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
05/24/2015
- 11:20 PM Bug #11620: osdc/stress_objectcacher.sh command failed
- $ ./ceph_test_objectcacher_stress --ops 1000 --percent-read 0.90 --delay-ns 0 --objects 10 --max-op-size 4096 --clien...
- 11:06 PM Bug #11620: osdc/stress_objectcacher.sh command failed
- /a/teuthology-2015-05-20_21:00:01-rados-next-distro-basic-multi/902505
- 11:04 PM Bug #10901: FAILED assert(weak_refs.empty()) (outstanding OSDMap ref at shutdown)
- This bug is still there (or a new version of it is). Saw this on current next:
/a/teuthology-2015-05-20_21:00:01-... - 10:05 PM devops Bug #11751 (Rejected): Debian source deb indexes seem incomplete
- adding those lines to /etc/apt/source.list...
- 06:21 PM Revision 571d19f6 (ceph): ci: fetch dependencies
- This was apparently happening automatically and not now. I'm not sure what's going on.
- 06:16 PM Revision 19cf5ac0 (ceph): Merge pull request #21 from theanalyst/docker-ci
- Run local tests in a docker
- 12:25 PM rbd Documentation #11750 (Resolved): Can't create image with format 2 with non-admin user
- Hi,
we are trying to create an image in a pool as a non-admin user with --image-format 2:... - 08:13 AM Revision cec4e4d8 (ceph): Add a simple makefile
- Primarily allowing for testing via docker; and other simple stuff like
fmt
Signed-off-by: Abhishek Lekshmanan <abhis... - 05:42 AM Revision e38a5a25 (ceph): ci: Allow local tests to run in a docker
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
05/23/2015
- 04:05 PM rgw Bug #11749 (Fix Under Review): rgw: rados objects wronly deleted
- https://github.com/ceph/ceph/pull/4752
- 08:56 AM rgw Bug #11749 (Resolved): rgw: rados objects wronly deleted
- When testing rados gateway(giant v0.87), I found two bugs which would be dangerous enough to cause data corruption. T...
- 08:54 AM Revision d49d8166 (ceph): Merge pull request #4709 from dachary/wip-shec-corpus
- erasure-code: update ceph-erasure-code-corpus for shec
- 07:05 AM Revision 4507cb23 (ceph): Merge pull request #4751 from islepnev/wip-11612
- Support NVMe device partitions by ceph-disk
Reviewed-by: Loic Dachary <ldachary@redhat.com>
05/22/2015
- 09:51 PM Revision 9b62cf25 (ceph): ceph-disk: support NVMe device partitions
- Linux nvme kernel module v0.9 enumerate devices as following:
/dev/nvme0 - characted revice
/dev/nvme0n1 - whole blo... - 09:34 PM Revision 17812451 (ceph): rbd: use formatted output test from the hammer branch
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 07:56 PM Revision f36344f0 (ceph): Merge pull request #4736 from tchaikov/wip-11693-only-restart-crashed-osds
- test/test-erasure-code: spin off EIO tests to avoid lingering OSDs after tests finish
Reviewed-by: Loic Dachary <lda... - 07:52 PM CephFS Bug #11746 (Resolved): cephfs Dumper tries to load whole journal into memory at once
- It should be streaming instead.
(From http://lists.ceph.com/pipermail/ceph-users-ceph.com/2015-May/001622.html) - 07:51 PM rbd Bug #11562 (Resolved): docs: rbd-diff developer document lists image size as u64 instead of le64
- 03:19 PM rbd Bug #11562 (Fix Under Review): docs: rbd-diff developer document lists image size as u64 instead ...
- *master PR*: https://github.com/ceph/ceph/pull/4748
- 03:18 PM rbd Bug #11562 (In Progress): docs: rbd-diff developer document lists image size as u64 instead of le64
- 07:43 PM Revision 87ec95fb (ceph): Merge pull request #4748 from ceph/wip-11562
- dev/rbd-diff: clarify encoding of image size
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:22 PM Revision f417eda9 (ceph): tests/test-erasure-code: spin off eio tests into another testsuite
- * since the eio tests crashes some of the OSD nodes, before the
change, the tests try to undo the crash before movi... - 07:19 PM Revision 2230deff (ceph): tests: fix the get_config()
- * the "daemon" parameter was not respected.
* update the test_get_config() to check the overrided option instead of
... - 07:13 PM Backport #11745 (In Progress): object creation by write cannot use an offset on an erasure coded ...
- 07:13 PM Backport #11745 (Resolved): object creation by write cannot use an offset on an erasure coded pool
- https://github.com/ceph/ceph/pull/4632
- 07:12 PM Backport #11744 (Resolved): object creation by write cannot use an offset on an erasure coded pool
- 07:12 PM Backport #11744 (Resolved): object creation by write cannot use an offset on an erasure coded pool
- https://github.com/ceph/ceph/pull/4560
- 07:11 PM Bug #11507 (Pending Backport): object creation by write cannot use an offset on an erasure coded ...
- 06:45 PM Revision 09a64572 (ceph): Merge pull request #4749 from ddiss/ceph_disk_test_fix
- tests: don't choke on deleted losetup paths
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:40 PM rbd Bug #11743 (Resolved): Possible crash while concurrently writing and shrinking an image
- An image shrink will result in a flush and cache invalidation. If there is a pending write in the cache, the flush w...
- 06:09 PM Revision 33eae4ec (ceph): xio: fix reuse of outer loop index in inner loop
- Reported-by: Vu Pham <vuhuong@mellanox.com>
Signed-off-by: Casey Bodley <casey@cohortfs.com> - 06:09 PM Revision 367a5fcc (ceph): cmake: add missing source file to test_librbd
- Signed-off-by: Casey Bodley <casey@cohortfs.com>
- 06:09 PM Revision a8fca3c2 (ceph): cmake: add missing common/util.cc dependency
- Signed-off-by: Casey Bodley <casey@cohortfs.com>
- 06:09 PM Revision 15dd70cd (ceph): cmake: skip man/CMakeLists.txt
- man pages have to be preprocessed now, and can't be installed directly.
skip installing them until we add the cmake-f... - 05:48 PM devops Bug #11673: Debian: ceph-test and rest-bench debug packages should require their respective binar...
- Still in hammer release
Run:http://pulpito-rdu.front.sepia.ceph.com/teuthology-2015-05-19_23:20:01-upgrade:client-up... - 05:35 PM Bug #6366 (Closed): long TAT - due too long residence time in Ceph code
- "Latency is too high" isn't a very helpful bug. There are various things we can do about this; some of them are being...
- 12:37 PM Bug #6366 (New): long TAT - due too long residence time in Ceph code
- In 2013 the TAT for a single 4k IO was approx. 1600 micro-seconds (Client & OSDs).
In 2014 with our private timestam... - 04:40 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- The osd with the failed assert was running with valgrind.
- 04:28 PM Bug #11548: "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-basic-multi run
- Run: http://pulpito.ceph.com/teuthology-2015-05-21_17:05:01-upgrade:giant-x-next-distro-basic-vps/
Jobs: ~100
Log... - 04:24 PM Bug #11573: OSD assertion in erasure code environment
- xingyi, please see the "Related issues" above, it's #11507.
- 04:21 PM Backport #11741 (Resolved): crush: take crashes due to invalid arg
- https://github.com/ceph/ceph/pull/4769
- 04:20 PM Backport #11740 (Resolved): crush: take crashes due to invalid arg
- https://github.com/ceph/ceph/pull/4891
- 03:49 PM Bug #11602 (Pending Backport): crush: take crashes due to invalid arg
- 03:38 PM rgw Bug #11570: rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
- Run: http://pulpito.ceph.redhat.com/teuthology-2015-05-17_16:05:02-upgrade:hammer-hammer-distro-basic-magna/
Jobs: [... - 03:22 PM Revision 7c1bae56 (ceph): tests: don't choke on deleted losetup paths
- If a file has been deleted with a loopback device attached, then the
`losetup --all` output will carry:
/dev/loopX: [... - 03:18 PM Revision f9ba711c (ceph): dev/rbd-diff: clarify encoding of image size
- Fixes: #11562
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 03:01 PM rbd Bug #11593 (Fix Under Review): diff_iterate API call should use callback's return code
- *master PR*: https://github.com/ceph/ceph/pull/4744
- 03:01 PM rbd Feature #11625 (Fix Under Review): diff_iterate should utilize concurrent RADOS operations
- *master PR*: https://github.com/ceph/ceph/pull/4744
- 02:19 PM Revision 7defc069 (ceph): Merge pull request #4512 from hjwsm1989/init-ceph
- init-ceph.in: Create osd data dir if don't exists.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:53 PM Bug #9732: ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
- Is there a link to read more about how it was resolved ?
- 01:14 PM CephFS Bug #11301 (Fix Under Review): mds-full test occasionally fails due to blacklist expiry
- https://github.com/ceph/ceph/pull/4746
https://github.com/ceph/ceph-qa-suite/pull/443 - 12:32 PM Revision 9f0d2da7 (ceph): Merge pull request #4740 from ktdreyer/wip-11688-doc-firewall-ports
- #11688: doc: update OSD/MDS firewall port list
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:11 AM Bug #11618 (Resolved): test_mon_osd failed
- 10:04 AM Revision aa0ffb31 (ceph): tasks/cephfs: reset osd blacklist between tests
- ...to avoid OSDMap modifications happening in the
background due to blacklist expiry.
Fixes: #11301
Signed-off-by: ... - 09:57 AM Revision 6a7aa6c5 (ceph): Merge pull request #4734 from wonzhq/aio-completion
- test/aio: fix the leak of aio completion
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:55 AM Revision c2c36bc9 (ceph): Merge pull request #4738 from dachary/wip-11618-osd-create-dup
- tests: ceph create may consume more than one id
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai... - 08:36 AM rbd Backport #11731 (In Progress): Objectcacher setting max object counts too low
- 12:16 AM rbd Backport #11731 (Resolved): Objectcacher setting max object counts too low
- https://github.com/ceph/ceph/pull/4639
- 08:35 AM Backport #11703 (In Progress): objecter: can get stuck in redirect loop if osdmap epoch == last_f...
- 08:30 AM Backport #11705 (In Progress): PGLog: split divergent priors as well
- 08:29 AM Backport #11708 (In Progress): Malformed JSON command output when non-ASCII strings are present
- 08:29 AM Backport #11714 (In Progress): ceph_argparse_flag has no regular 3rd parameter
- 08:29 AM rgw Backport #11728 (In Progress): rgw: quota not respected in POST object
- 08:16 AM Revision ab8e9e39 (ceph): tests: CEPH_CLI_TEST_DUP_COMMAND=1 for qa/workunits/cephtool/test.sh
- Run cephtool-test-{mon,osd,mds}.sh with CEPH_CLI_TEST_DUP_COMMAND=1 to
detect idempotency related problems during mak... - 08:16 AM Revision 5c69f5e1 (ceph): tests: ceph create may consume more than one id
- When CEPH_CLI_TEST_DUP_COMMAND=1 is set, ceph osd create will consume
two osd id and return the later. Fix the test t... - 08:07 AM Backport #11738 (Resolved): OPT_INT option interprets "3221225472" as -1073741824, and crashes in...
- https://github.com/ceph/ceph/pull/4889
- 08:03 AM CephFS Backport #11737 (Resolved): MDS is crashed (mds/CDir.cc: 1391: FAILED assert(!is_complete()))
- https://github.com/ceph/ceph/pull/4886
- 08:02 AM Backport #11736 (Resolved): ceph: cli interactive mode does not understand quotes
- https://github.com/ceph/ceph/pull/4776
- 08:00 AM devops Backport #11735 (Resolved): RGW init script needs to check /var/lib/ceph/radosgw
- 07:58 AM devops Backport #11734 (Resolved): Debian: ceph-test and rest-bench debug packages should require their ...
- https://github.com/ceph/ceph/pull/4766
- 07:57 AM devops Backport #11733 (Resolved): Debian: ceph-test and rest-bench debug packages should require their ...
- https://github.com/ceph/ceph/pull/4773
- 07:56 AM devops Bug #11638 (In Progress): ceph.spec.in: ceph-common subpackage def needs tweaking for SUSE/openSUSE
- 07:55 AM devops Backport #11629 (In Progress): ceph.spec.in: SUSE/openSUSE builds need libbz2-devel
- 07:54 AM devops Backport #11611 (In Progress): ceph.spec: update OpenSUSE BuildRequires
- 07:50 AM devops Backport #11732 (Rejected): ceph.spec.in: include SUSE in _with_systemd
- https://github.com/ceph/ceph/pull/5788
- 07:41 AM Revision 1dac80df (ceph): rgw: Use attrs from source bucket on copy
- On copy objects, when bucket source is the same as the destination, use attrs
from source bucket.
Fixes: #11639
Sig... - 01:08 AM Revision 522b4957 (ceph): test/ceph_test_rados: add tests of pipeline reads
- Send pipelined reads in the ReadOp. This can help testing OSD's behavior
in some scenarios.
Signed-off-by: Zhiqiang ... - 12:15 AM rbd Backport #11730 (Resolved): Objectcacher setting max object counts too low
- 12:15 AM rbd Backport #11730 (Resolved): Objectcacher setting max object counts too low
- https://github.com/ceph/ceph/pull/4497
05/21/2015
- 11:59 PM rgw Backport #11729 (In Progress): rgw: leak of bucket meta objects on bucket re-creation
- 11:59 PM rgw Backport #11729 (Resolved): rgw: leak of bucket meta objects on bucket re-creation
- https://github.com/ceph/ceph/pull/4535
- 11:58 PM rgw Backport #11728 (Resolved): rgw: quota not respected in POST object
- https://github.com/ceph/ceph/pull/4642
- 11:57 PM rgw Backport #11727 (Resolved): rgw: quota not respected in POST object
- 11:57 PM rgw Backport #11727 (Resolved): rgw: quota not respected in POST object
- https://github.com/ceph/ceph/pull/4581
- 11:56 PM rgw Backport #11726 (In Progress): delete bucket does not remove .bucket.meta file
- 11:55 PM rgw Backport #11726 (Resolved): delete bucket does not remove .bucket.meta file
- https://github.com/ceph/ceph/pull/4641
- 11:55 PM rgw Backport #11725 (Resolved): delete bucket does not remove .bucket.meta file
- 11:54 PM rgw Backport #11725 (Resolved): delete bucket does not remove .bucket.meta file
- commit:85a68f9a8237f7e74f44a1d1fbbd6cb4ac50f8e8
- 11:53 PM rgw Bug #11125 (Resolved): rgw: keystone token cache does not work correctly
- 11:53 PM rgw Backport #11723 (Resolved): rgw: keystone token cache does not work correctly
- 11:50 PM rgw Backport #11723 (Resolved): rgw: keystone token cache does not work correctly
- https://github.com/ceph/ceph/pull/4573
- 11:52 PM rgw Backport #11724 (Resolved): rgw: keystone token cache does not work correctly
- 11:52 PM rgw Backport #11724 (Resolved): rgw: keystone token cache does not work correctly
- 11:48 PM rgw Backport #11722 (Resolved): Keystone PKI token expiration is not enforced
- https://github.com/ceph/ceph/pull/4884
- 11:47 PM rgw Backport #11721 (Resolved): Keystone PKI token expiration is not enforced
- https://github.com/ceph/ceph/pull/4765
- 11:42 PM rgw Backport #11720 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- https://github.com/ceph/ceph/pull/4780
- 11:41 PM rgw Backport #11719 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- 11:38 PM rgw Backport #11719 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- https://github.com/ceph/ceph/pull/4515
- 11:40 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- I'm seeing something different in that last run:...
- 11:03 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- Run: http://pulpito.ceph.com/teuthology-2015-05-21_15:22:19-upgrade:firefly-x-hammer-distro-basic-vps/
Jobs: all - 11:36 PM rgw Backport #11542 (In Progress): Change variable length array of std::strings (not legal in C++) to...
- 11:34 PM rgw Backport #11718 (In Progress): RGW doesn't return 'x-timestamp' in header which is used by 'View ...
- 11:33 PM rgw Backport #11718 (Resolved): RGW doesn't return 'x-timestamp' in header which is used by 'View Det...
- https://github.com/ceph/ceph/pull/4584
- 11:32 PM rgw Backport #11717 (Resolved): RGW doesn't return 'x-timestamp' in header which is used by 'View Det...
- 11:32 PM rgw Backport #11717 (Resolved): RGW doesn't return 'x-timestamp' in header which is used by 'View Det...
- giant commit:e230fab
- 11:30 PM Backport #11716 (Resolved): utf8 and old gcc breakage on RHEL6.5
- https://github.com/ceph/ceph/pull/4687
- 11:29 PM Backport #11715 (In Progress): utf8 and old gcc breakage on RHEL6.5
- 11:28 PM Backport #11715 (Resolved): utf8 and old gcc breakage on RHEL6.5
- https://github.com/ceph/ceph/pull/4635
- 11:26 PM Backport #11714 (Resolved): ceph_argparse_flag has no regular 3rd parameter
- https://github.com/ceph/ceph/pull/4582
- 11:25 PM Backport #11713 (In Progress): src/ceph-disk : "disk zap" sgdisk invocation
- 11:25 PM Backport #11713 (Resolved): src/ceph-disk : "disk zap" sgdisk invocation
- https://github.com/ceph/ceph/pull/4636
- 11:24 PM Backport #11712 (Resolved): src/ceph-disk : "disk zap" sgdisk invocation
- 11:23 PM Backport #11712 (Resolved): src/ceph-disk : "disk zap" sgdisk invocation
- https://github.com/ceph/ceph/pull/4561
- 11:22 PM Backport #11711 (In Progress): use a new disk as journal disk,ceph-disk prepare fail
- 11:21 PM Backport #11711 (Resolved): use a new disk as journal disk,ceph-disk prepare fail
- https://github.com/ceph/ceph/pull/4630
- 11:21 PM Backport #11710 (Resolved): use a new disk as journal disk,ceph-disk prepare fail
- 11:20 PM Backport #11710 (Resolved): use a new disk as journal disk,ceph-disk prepare fail
- https://github.com/ceph/ceph/pull/4503
- 11:19 PM Backport #11709 (In Progress): Malformed JSON command output when non-ASCII strings are present
- 11:18 PM Backport #11709 (Resolved): Malformed JSON command output when non-ASCII strings are present
- https://github.com/ceph/ceph/pull/4687
- 11:17 PM Backport #11708 (Resolved): Malformed JSON command output when non-ASCII strings are present
- https://github.com/ceph/ceph/pull/4635
- 11:15 PM Backport #11707 (In Progress): Client admin socket leaks file descriptors
- 11:15 PM Backport #11707 (Resolved): Client admin socket leaks file descriptors
- https://github.com/ceph/ceph/pull/4633
- 11:14 PM Backport #11706 (In Progress): Client admin socket leaks file descriptors
- 11:13 PM Backport #11706 (Resolved): Client admin socket leaks file descriptors
- https://github.com/ceph/ceph/pull/4657
- 11:09 PM Backport #11705: PGLog: split divergent priors as well
- 11:08 PM Backport #11705 (Resolved): PGLog: split divergent priors as well
- https://github.com/ceph/ceph/pull/4631
- 11:06 PM Backport #11704 (Rejected): erasure-code: misalignment
- commit:fdeeeb1b6be7a95f473ad33d3344a499a61106a1
- 11:04 PM Backport #11703 (Fix Under Review): objecter: can get stuck in redirect loop if osdmap epoch == l...
- 11:03 PM Backport #11703 (Resolved): objecter: can get stuck in redirect loop if osdmap epoch == last_forc...
- https://github.com/ceph/ceph/pull/4597
- 10:51 PM Backport #11702 (Resolved): objecter: can get stuck in redirect loop if osdmap epoch == last_forc...
- 10:50 PM Backport #11702 (Resolved): objecter: can get stuck in redirect loop if osdmap epoch == last_forc...
- https://github.com/ceph/ceph/pull/4502
- 10:46 PM Backport #11701 (Resolved): make the all osd/filestore thread pool suicide timeouts separately co...
- https://github.com/ceph/ceph/pull/5159
- 10:43 PM Backport #11700 (Resolved): make the all osd/filestore thread pool suicide timeouts separately co...
- https://github.com/ceph/ceph/pull/5823
- 10:05 PM rbd Bug #11593 (In Progress): diff_iterate API call should use callback's return code
- 09:32 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- Saw in run: http://pulpito.ceph.com/teuthology-2015-05-20_21:00:01-rados-next-distro-basic-multi/
Job: ['902503']
... - 09:20 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- Run: http://pulpito.ceph.redhat.com/teuthology-2015-05-20_17:15:43-rados-hammer-distro-basic-magna/
Jobs: ['112528',... - 09:09 PM rgw Bug #11367 (Pending Backport): Keystone PKI token expiration is not enforced
- 09:09 PM Revision 4be8e49e (ceph): Merge pull request #4617 from aakso/wip-11367-pki-token-expire
- rgw: always check if token is expired
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:36 PM Documentation #11688: OSDs and MDSs can use any ports in the entire ranges
- PR for master: https://github.com/ceph/ceph/pull/4740
- 08:36 PM Documentation #11688 (In Progress): OSDs and MDSs can use any ports in the entire ranges
- 08:31 PM Revision 11fef227 (ceph): doc: recommend opening entire 6800-7300 port range
- Prior to this commit, the Network Configuration Reference guide and
Troubleshooting guide recommended opening a numbe... - 07:14 PM Revision 121aa3bc (ceph): RadosModel: assert exists on subsequent writes
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:14 PM Revision 4fe7d2ab (ceph): RadosModel: randomly prefix delete with assert_exists
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:00 PM Revision b50cc947 (ceph): doc: update OSD port range to 6800-7300
- The upper limit for OSD/MDS ports changed from 7100 to 7300 in commit
f9ec5a7945518089ffae540649b77ac06f98df5f. Updat... - 06:56 PM Backport #11699 (Resolved): Objecter: resend linger ops on split
- https://github.com/ceph/ceph/pull/5062
- 06:29 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Jason, can you confirm whether https://github.com/athanatos/ceph/tree/wip-11677 fixes it? (Probably merge it into wha...
- 02:20 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- I can repeat this every time during a librbd fsx run on the wip-11579 branch:...
- 05:00 PM Revision 98cdf033 (ceph): Merge pull request #4391 from nilamdyuti/wip-doc-ceph-object-gateway
- doc: Removes references to s3gw.fcgi in simple gateway configuration file...
Reviewed-by: Yehuda Sadeh <yehuda@redha... - 03:46 PM devops Bug #11591 (Resolved): "VersionNotFoundError: Failed to fetch package version" in rados-hammer-di...
- My fix for #11645 should prevent this from happening; if it continues we can reopen.
- 03:11 PM Bug #11691: scrub vs rw lock ordering ooo op
- 03:08 PM Fix #11441 (Rejected): TEST_bench: 69: ./ceph tell osd.0 bench 3145728001 1048577
- Let's reopen if it shows again.
- 02:52 PM Bug #11618 (Fix Under Review): test_mon_osd failed
- * master https://github.com/ceph/ceph/pull/4738
- 01:07 PM Bug #11618 (In Progress): test_mon_osd failed
- Can be reproduced with...
- 12:53 PM Bug #11618: test_mon_osd failed
- CEPH_CLI_TEST_DUP_COMMAND=1 is set by "workunit.py":https://github.com/ceph/ceph-qa-suite/blob/master/tasks/workunit....
- 12:45 PM Bug #11618: test_mon_osd failed
- ...
- 12:42 PM Bug #11618: test_mon_osd failed
- When "a new osd is created":https://github.com/ceph/ceph/blob/f88275dd04b05fce9e4160872136e38453e232eb/qa/workunits/c...
- 12:17 PM Bug #11618: test_mon_osd failed
- When running locally it succeeds with...
- 11:55 AM Bug #11618: test_mon_osd failed
- http://pulpito.ceph.com/loic-2015-05-20_23:01:03-rados:singleton:all:cephtool.yaml-master---basic-multi/ has exactly ...
- 02:04 PM Revision 3dda5faf (ceph): xio: malloc if xio_mempool_alloc fails
- Signed-off-by: Casey Bodley <casey@cohortfs.com>
- 02:04 PM Revision 5c14a693 (ceph): xio: fix for xio_msg release after teardown
- The xio_msg pointers to be freed in XioPortal::release_xio_rsp() are no
longer valid after a call to xio_connection_d... - 02:00 PM Revision 16d1c1e9 (ceph): xio: use ceph clock for timestamps
- accelio is using rdtsc to generate xio_msg.timestamp, which can't be
reliably converted to a timeval. now uses ceph_c... - 01:59 PM Revision c2bba8eb (ceph): xio: save nonce for bind address
- A missing nonce in the osd addrs was preventing the monitor from
detecting osd restarts. XioMessenger::bind() now set... - 01:59 PM Revision 355aa0e4 (ceph): xio: check if connection is on list before erasing
- also removed the extra conditional put() in on_disconnect_event()
Signed-off-by: Casey Bodley <casey@cohortfs.com> - 01:59 PM Revision bb621b07 (ceph): xio: better way to assign connections to specific lane
- Better way to assign connections to a specific lane of a portal
Avoiding lane competition/hogging.
This change resolv... - 01:28 PM Bug #11695 (Won't Fix): keyvaluestore: can not overwrite object after snapshot is created
- recently i build a setup with key-value db back, but after snapshot is created, i overwrite one object, then OSD daem...
- 08:33 AM Bug #11693 (Fix Under Review): pidfile is overwritten and removed if the ceph-osd with the specif...
- https://github.com/ceph/ceph/pull/4736
- 05:56 AM Bug #11693 (Resolved): pidfile is overwritten and removed if the ceph-osd with the specified pidf...
-
If osd.5 is already up and running, following command will try to start osd.5 again.... - 07:42 AM Bug #9944 (Resolved): objecter: pool dne checks not correct
- giant is EOL
- 06:58 AM Revision 855a70d8 (ceph): test/aio: aio completion is not released
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 04:55 AM Feature #11692 (Resolved): online change of mon_osd_full_ratio and mon_osd_nearfull_ratio doesn't...
- > I want to verify the behavior of ceph cluster with full osd case, so I change the default full ratio with following...
- 04:40 AM Revision 39eb454e (ceph): test/ceph_test_rados: aio completion is not released for ReadOp
- Should release the completion when the ReadOp finishes.
Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com> - 04:38 AM Revision d118e56f (ceph): osd/ReplicatedPG: need to queue op when avoiding dup promotion in
- maybe_handle_cache
Need to queue the op before returning from maybe_handle_cache.
Otherwise, this op is lost.
Signe... - 12:53 AM Bug #11661: "FAILED assert(0 == "Running incompatible OSD")"
osd.3 and osd.5 are both running 0.94.1-111-gb69fb89 (a version of hammer).
2015-05-15 13:49:39.677006 7f41d9d5a...
05/20/2015
- 11:13 PM Bug #11661 (In Progress): "FAILED assert(0 == "Running incompatible OSD")"
- 11:13 PM Bug #10794: ceph_test_rados: incorrect buffer at pos ...
- 11:11 PM Bug #7451: updatedb will index /var/lib/ceph
- 11:10 PM Bug #7451: updatedb will index /var/lib/ceph
- As background info:
The original thread:
http://lists.ceph.com/pipermail/ceph-users-ceph.com/2014-February/037446... - 11:01 PM Bug #11691: scrub vs rw lock ordering ooo op
- Need to add an excl operation to ceph_test_rados writes.
- 11:00 PM Bug #11691 (Resolved): scrub vs rw lock ordering ooo op
- ubuntu@teuthology:/a/samuelj-2015-05-20_15:07:02-rados-wip-sam-testing-distro-basic-multi/902153/remote
Uncovered ... - 10:01 PM devops Bug #11388 (Pending Backport): /usr/bin/ceph from ceph-common is broken without installing ceph
- 09:54 PM Revision 783fdc7c (ceph): Merge pull request #4517 from ceph/wip-11388-debian-argparse
- #11388 debian: move ceph_argparse into ceph-common
Reviewed-by: Dan Mick <dmick@redhat.com> - 09:20 PM Revision 115545af (ceph): ceph-detect-init/debian/__init__: improved syntax
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 09:01 PM Bug #11618: test_mon_osd failed
- http://pulpito.ceph.com/loic-2015-05-20_23:01:03-rados:singleton:all:cephtool.yaml-master---basic-multi/
- 08:59 PM Bug #11618: test_mon_osd failed
- can probably be traced back to a commit with bisecting
- 08:58 PM Bug #11690 (Duplicate): cephtool/test.sh failing
- i'll assign the other one to myself
- 08:00 PM Bug #11690 (Duplicate): cephtool/test.sh failing
- 2015-05-19T19:08:52.853 INFO:tasks.workunit.client.0.plana59.stderr: test_mon_osd: 1047: uuidgen
2015-05-19T19:08:5... - 07:50 PM Feature #11689 (New): change ceph-mon TCP port to an IANA-registered port
- In April there was a ceph-devel mailing list thread subject "[IANA #821110] Application for a Port Number and/or Serv...
- 07:44 PM Documentation #11688 (Closed): OSDs and MDSs can use any ports in the entire ranges
- In talking with Sam about firewall rules the other day, he mentioned that the OSD TCP port selection is not really de...
- 07:42 PM rbd Bug #11579 (Fix Under Review): Copyup operation for deep flatten cannot use current parent extents
- *master PR*: https://github.com/ceph/ceph/pull/4730
- 06:19 PM Feature #11676: suite: extend the Product part of build_matrix to pass mincyclity properly
- Sam, what does it mean from the hightlies scheduling standpoint?
- 06:12 PM Bug #11687: stuck incomplete
- Related: 0712d8d90b4eb455ae56cce5eafdce3e50de39e0 and 9a2ff34d75cc69759584fb802f903068669f6233
- 06:01 PM Bug #11687: stuck incomplete
- 06:01 PM Bug #11687 (Resolved): stuck incomplete
- 2015-05-20 08:06:31.986367 7f6e76e53700 5 osd.5 pg_epoch: 556 pg[1.4e( empty local-les=0 n=0 ec=5 les/c 473/473 556/...
- 05:54 PM Revision 8190f44f (ceph): Merge pull request #4721 from ceph/wip-fix-concurrent.sh
- Fix ceph.conf path in concurrent.sh - krbd qa suite
Reviewed-by: Ilya Dryomov <idryomov@gmail.com> - 05:52 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- Well, maybe not; I don't define (or fully understand) our upstream testing strategy. What I do know is that Sage rele...
- 05:29 PM Revision 110608e5 (ceph): debian: move ceph_argparse into ceph-common
- Prior to this commit, if a user installed the "ceph-common" Debian
package without installing "ceph", then /usr/bin/c... - 01:28 PM Revision 8c65e2af (ceph): Merge pull request #4720 from athanatos/wip-clarify-DBObjectMap-sync
- DBObjectMap::sync: add comment clarifying locking
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:21 PM Revision 4e272e5e (ceph): Merge pull request #3946 from tchaikov/randomize-scrub-time
- osd: Randomize scrub time
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 01:08 PM Bug #11586: RBD Data Corruption with Logging on Giant
- Any other data I can collect on this to help?
- 10:41 AM Revision ca6abca6 (ceph): tools: add --no-verify option to rados bench
- When doing seq and rand read benchmarks using rados bench, a quite large
portion of cpu time is consumed by doing obj... - 10:23 AM Revision 2ab0e606 (ceph): osd: simplify OSD::scrub_load_below_threshold() a little bit
- avoid unnecessary comparison
Signed-off-by: Kefu Chai <kchai@redhat.com> - 10:23 AM Revision 0f7f3567 (ceph): osd: use __func__ in log messages
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 10:23 AM Revision 5e44040e (ceph): osd: randomize scrub times to avoid scrub wave
- - to avoid the scrub wave when the osd_scrub_max_interval reaches in a
high-load OSD, the scrub time is randomized.... - 10:23 AM Revision 6344fc83 (ceph): osd: use another name for randomize scrub option
- s/osd_scrub_interval_limit/osd_scrub_interval_randomize_ratio/
Fixes: #10973
Signed-off-by: Kefu Chai <kchai@redhat.... - 08:29 AM Revision 8ec7303b (ceph): Merge pull request #4691 from varadakari/wip-kvs-objheader
- KeyValueStore: optimize the object header writes
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 07:53 AM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- echoing joao...
- 07:43 AM Bug #11359: cephtool/test.sh:test_tiering intermittent failure
- ...
- 01:58 AM devops Bug #11686 (Pending Backport): RGW init script needs to check /var/lib/ceph/radosgw
- Note that there was another change on master, https://github.com/ceph/ceph/pull/4056 , corresponding to ticket #11140...
- 01:48 AM devops Bug #11686 (Resolved): RGW init script needs to check /var/lib/ceph/radosgw
- In order to support ceph-deploy's new RGW functionality, the RGW init script needs to check @/var/lib/ceph/radosgw@.
... - 01:12 AM Bug #11573: OSD assertion in erasure code environment
- Hi?Samuel? could you please show me the duplicated bug?
05/19/2015
- 10:53 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Actually, removing just the snapshots taken after you resumed taking snapshots might suffice.
- 06:09 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Testing a fix.
- 06:08 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Nevermind about the logging then. What caused it is an interaction between a radosgw operation and pool snapshotting...
- 05:52 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Just checked if I might have caught a crash in the short time I had the logging turned up earlier, but I wasn't lucky...
- 05:34 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- I have a unittest which reproduces it now. Logs would still be helpful to confirm.
- 03:31 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- My bad. Clicked the wrong line before copying the link. That's exactly what I was referring to. Thanks Florian.
- 02:09 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Note to reviewer:
Actual line (in hammer) is actually https://github.com/ceph/ceph/blob/hammer/src/osd/Replicated... - 12:41 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Seems we did not delete one of the test-snapshots last night after all.
So it kind of makes a little more sense -- g... - 09:47 AM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Downgraded to 0.94.1-trusty "official" packages to rule out we had compiled a somehow unstable intermediate state bet...
- 09:45 AM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Once the OSDs holding the blocked operations had crashed again, those were apparently processed.
- 05:58 AM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Several requests have been hanging since what appears to be the time of the crash:...
- 05:52 AM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- Up'ed debug_osd to 20 for OSDs on one node in anticipation of another crash.
3 on node01 crashed again about 2.5h la... - 10:20 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- Yeah, I noticed that a while ago. The annoying thing is that I can't find logs for the period when the osdmap moves ...
- 04:56 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- yes, "osd setcrushmap" was issued before we ran into this issue....
- 04:41 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- ...
- 04:34 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- Right now, the only way I can easily reproduce this is by setting an empty crushmap with 'ceph osd setcrushmap -i som...
- 04:30 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- kefu, we need logs from osdmap epoch 81 to 82. Last working crushmap is from epoch 81, all subsequent maps are broken.
- 02:34 PM Bug #11680: mon crashes when "ceph osd tree 85 --format json"
- and i am able to dump the osd map using ...
- 05:11 AM Bug #11680 (Can't reproduce): mon crashes when "ceph osd tree 85 --format json"
- ...
- 08:47 PM Revision 23caf526 (ceph): Added script to schedule 1/14th part of rados
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit a7064a7b3d8a865dead3800a4d97bd70da6dec33) - 08:46 PM Revision 7bc386e2 (ceph): Added script to schedule 1/14th part of rados
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit a7064a7b3d8a865dead3800a4d97bd70da6dec33) - 08:44 PM Revision a7064a7b (ceph): Added script to schedule 1/14th part of rados
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 08:26 PM Bug #11573 (Duplicate): OSD assertion in erasure code environment
- 08:15 PM Bug #11129 (Can't reproduce): coredump in upgrade:firefly-firefly-distro-basic-magna run
- 08:12 PM Bug #11238 (Duplicate): osd crash in upgrade:giant-x-hammer-distro-basic-multi run
- 08:11 PM Bug #11309 (Rejected): load_pgs very slow when use filestore_min_sync_interval = 60 in btrfs
- This seems like what the config is supposed to do?
- 08:10 PM Bug #11296: "FAILED assert(!old_value.deleted())" in upgrade:giant-x-hammer-distro-basic-multi run
- 08:08 PM Bug #11565: "FAILED assert(r == -2)" in rados-firefly-distro-basic-magna run
- Not actually the same as the other bug.
- 07:55 PM Revision f9e5b68b (ceph): qa: unbreak concurrent.sh workunit
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 06:33 PM Bug #11343 (Resolved): Need test written for bug 11184 fix
- 06:15 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- Do we really? Stretched thinner and thinner; should we be trying to test upstream on our primary downstream release ...
- 06:02 PM Revision c2d17b92 (ceph): test/librados/snapshots.cc: add test for 11677
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:58 PM Support #11681 (Closed): rbd copy failed return 90 Message too long
- No. You need to change the OSD max write size.
With a modern deployment this shouldn't cause any serious problems,... - 08:03 AM Support #11681 (Closed): rbd copy failed return 90 Message too long
- rbd order set to 27, so the object size is 128M each.
The osd max write size is default 90M.
I have a rbd image 1... - 02:46 PM devops Bug #11581: "port 22: No route to host" errors in the labs
- ...
- 02:30 PM devops Bug #11581: "port 22: No route to host" errors in the labs
- ...
- 11:44 AM Revision b894fc7a (ceph): tools: Don't delete, recreate and re-fill buffers in rados bench.
- Fixes the high CPU usage and corrects rados bench scores on fast SSDs
and ramdisks/memstore.
For bench run on SSD, on... - 11:43 AM Revision 55a6f9ef (ceph): bufferlist: implement bufferlist::invalidate_crc()
- This function iterates over all bufferlist internal buffers and calls
their invalidate_crc() method. Required for rad... - 11:23 AM rgw Bug #11682 (Resolved): Support Swift API '/healthcheck'
- curl -i http://172.16.45.101:8080/healthcheck
HTTP/1.1 404 Not Found
Date: Tue, 19 May 2015 11:20:59 GMT
Server: A... - 09:05 AM Bug #10411: PG stuck incomplete after failed node
- Hi Brian,
I face the same situation, and your solution fix our problem eventually. Huge Thanks to you!
I think ... - 08:31 AM CephFS Bug #11481 (Resolved): "mds/MDSTable.cc: 146: FAILED assert(is_undef())" on standby->replay trans...
- 08:05 AM CephFS Bug #10624 (Resolved): hung samba tests after lsof failure
- 08:04 AM CephFS Bug #11641 (Resolved): test_journal_repair failing on mds_verify_scatter
- 08:03 AM Revision e585ddf4 (ceph): Merge pull request #4658 from ceph/wip-11481
- #11481: MDS resilience to weird mdsmaps
- 07:47 AM Revision 55766865 (ceph): mds: unlink any stale remote snap dentry when evaluating stray inode
- Remote snap dentry may hold reference to the stray directory inode,
the reference prevent the stray inode from being ... - 07:47 AM Revision de8b9583 (ceph): mds: properly invalidate past child snaprealms
- After updating an existing snapshot or deleting an old snapshot,
we should invalidate past child snaprealms' cached s... - 07:47 AM Revision a13414da (ceph): mds: avoid calling StrayManager::eval_stray() recursively
- StrayManager::eval_stray() may close dirfrags and unlink remote
dentries. These operations drop inode's reference, wh... - 06:13 AM Revision 1b758c99 (ceph): Merge pull request #4722 from ceph/wip-rbd-xfstests-20150518
- rbd: expunge xfstests generic/078
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:52 AM Feature #11202 (Fix Under Review): add stop_scrub command for ceph
- 12:49 AM Feature #11319 (Resolved): ceph daemonperf: add 'interval' argument
- 12:45 AM Documentation #11490: http://ceph.com/docs/master/ bottom links are obsolete
- doc/_templates/layout.html is using ceph.js to dynamically generate the html layout. the ceph.js asks http://ayni.cep...
- 12:37 AM Revision bf40b9b5 (ceph): rbd: expunged xfstests generic/078
- This tests RENAME_WHITEOUT, which was enabled for xfs in kernel commit
7dcf5c3e4527cfa2807567b00387cf2ed5e07f00. At f... - 12:08 AM Feature #11459 (Resolved): cryptic error message in ceph interactive mode
- https://github.com/ceph/ceph/pull/4705 addresses this in a different way: it also accepts "exit" as a command to leav...
05/18/2015
- 11:13 PM Bug #11677: Almost all OSDs in the cluster crashing at the same time, repeatedly
- About every hour the crashes repeat. The calm that we saw after the initial round of crashes did not last long.
Here... - 08:42 PM Bug #11677 (Resolved): Almost all OSDs in the cluster crashing at the same time, repeatedly
- Tonight our Hammer cluster suffered a series of OSD crashes on all cluster nodes.
We are running Hammer (0.94.1-98-g... - 09:18 PM devops Bug #11673 (Pending Backport): Debian: ceph-test and rest-bench debug packages should require the...
- This bug is present in both Hammer and Firefly (although #11376 was only backported to Hammer, so Teuthology is only ...
- 04:59 PM devops Bug #11673: Debian: ceph-test and rest-bench debug packages should require their respective binar...
- (I wonder if lintian would have caught this. https://lintian.debian.org/tags/dbg-package-missing-depends.html)
- 04:55 PM devops Bug #11673 (Fix Under Review): Debian: ceph-test and rest-bench debug packages should require the...
- PR for "next" : https://github.com/ceph/ceph/pull/4716
- 04:41 PM devops Bug #11673 (Resolved): Debian: ceph-test and rest-bench debug packages should require their respe...
- I recently moved @ceph-objectstore-tool@ from the "ceph-test" package to the main "ceph" package,...
- 09:16 PM devops Bug #11376 (Resolved): ceph-objectstore-tool should be in the "ceph" server package
- 09:15 PM devops Bug #11376 (Pending Backport): ceph-objectstore-tool should be in the "ceph" server package
- 09:02 PM Revision 055c0c48 (ceph): Merge pull request #4716 from ceph/wip-11673-debian-dbg-depends
- debian: set rest-bench-dbg ceph-test-dbg dependencies
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:36 PM Feature #11676 (Resolved): suite: extend the Product part of build_matrix to pass mincyclity prop...
- We need this to support highly nested Product cases, for example, to add a distribution facet to the top level of the...
- 08:32 PM devops Bug #11581: "port 22: No route to host" errors in the labs
- ...
- 08:27 PM Revision 87433dab (ceph): Merge pull request #4705 from stiopaa1/exit
- cryptic error message in ceph interactive mode
Reviewed-by: David Zafman <dzafman@redhat.com> - 07:39 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- Perhaps these problems are similar: http://tracker.ceph.com/issues/11511
- 07:29 PM Revision 2eca5368 (ceph): DBObjectMap::sync: add comment clarifying locking
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:05 PM Revision 4b2e018d (ceph): Merge pull request #4659 from ceph/wip-11602
- mon: prevent deletion of bucket in use by rule; prevent subsequent crush crash
Reviewed-by: Loic Dachary <ldachary@r... - 05:23 PM devops Bug #11662: "error: Can't download https://pypi.python.org..." in ceph-deploy-hammer-distro-basic...
- Apparently PyPI does implement some rate-limiting: https://mail.python.org/pipermail/distutils-sig/2014-February/0238...
- 05:13 PM devops Bug #11675 (Can't reproduce): "error: Can't download https://pypi.python.org..." in ceph-deploy-h...
- hammer v0.94.2 release
Run:http://pulpito.ceph.com/teuthology-2015-05-17_10:05:19-ceph-deploy-hammer-distro-basic-vp... - 05:03 PM Revision f898ec1e (ceph): debian: set rest-bench-dbg ceph-test-dbg dependencies
- Debian's debug packages ought to depend on their respective binary
packages. This was the case for many of our ceph p... - 04:47 PM devops Bug #11546: ceph / ceph-dbg steal ceph-objecstore-tool from ceph-test / ceph-test-dbg
- There are a couple of separate issues going on.
-----
In the initial ticket description, the relevant lines are... - 04:44 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- Note to self: several RHEL 7.1 machines were released to the lab pool, but no ceph packages were built for it and th...
- 04:18 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- ... so we either need a 7.1 gitbuilder, or to keep such jobs from running on RHEL 7.1
- 04:14 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- If no specific distro is asked for, the job takes what it can get.
- 04:09 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- Seeing also in hammer v0.94.2 run
http://pulpito.ceph.redhat.com/teuthology-2015-05-15_18:20:01-upgrade:client-upgra... - 02:54 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- The problem is that there is no "http://gitbuilder.ceph.redhat.com/ceph-rpm-rhel7_1-x86_64-basic/" location. Do we ev...
- 04:28 PM Fix #11590 (Fix Under Review): MDSMonitor: handle MDSBeacon messages properly
- https://github.com/ceph/ceph/pull/4702
- 04:28 PM Revision 765ddaea (ceph): Merge pull request #4715 from ceph/wip-11641
- mds: fix handling missing mydir dirfrag
- 04:08 PM CephFS Bug #11641 (Fix Under Review): test_journal_repair failing on mds_verify_scatter
- https://github.com/ceph/ceph/pull/4715
- 12:53 PM CephFS Bug #11641 (In Progress): test_journal_repair failing on mds_verify_scatter
- 12:52 PM CephFS Bug #11641: test_journal_repair failing on mds_verify_scatter
- OK, turns out to be nothing to do with journaltool, this is a straight up bug in the change I made to populate_mydir....
- 04:01 PM Bug #11548: "[ FAILED ] LibRadosTwoPoolsPP.Evict" in upgrade:giant-x-next-distro-basic-multi run
- 97 failed jobs in run http://pulpito.ceph.com/teuthology-2015-05-17_17:05:02-upgrade:giant-x-next-distro-basic-vps/
- 03:48 PM Bug #11582: ceph-0.80.9 compile error
- cory, my best guess is that you are linking against a wrong boost version. if you are able to rebuild 0.80.9 or 0.94 ...
- 03:15 PM Revision 9ed49198 (ceph): mds: fix handling missing mydir dirfrag
- This was broken by 96992466 aka "mds: handle missing mydir dirfrag"
The previous code was mistakenly treating a not-... - 02:43 PM devops Bug #11453: run RGW as root
- What sort of problems do you picture occurring when switching from an unprivileged www UID to root in firefly?
- 01:58 PM Revision 2863163c (ceph): Merge pull request #4693 from varadakari/wip-kvdb-prefix
- KeyValueStore: Fix the prefix comparion to avoid object leaks.
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 01:56 PM Revision 0a087c1d (ceph): Merge pull request #4692 from varadakari/wip-kvs-iterator
- wip-kvs-iterator
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 12:36 PM rgw Bug #11604 (Resolved): rgw: broken multipart upload when retrying parts
- 12:26 PM rgw Bug #11622 (Resolved): rgw: broken manifest on multipart upload retry
- 12:26 PM Revision 63832d40 (ceph): Merge pull request #4696 from ceph/wip-11622-hammer
- Wip 11622 hammer
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:25 PM Revision 68211f69 (ceph): Merge pull request #4697 from ceph/wip-11622-firefly
- Wip 11622 firefly
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:57 AM Documentation #11669 (New): erasure-code: add cross datacenter example for lrc
- Add to http://ceph.com/docs/hammer/rados/operations/erasure-code-lrc/ a use case that shows how locality can be imple...
- 10:51 AM Feature #11668 (New): erasure-code: measure bandwidth usage
- Add a metrics that shows how much bandwidth is used during
* write
* read
* recovery
by each plugin, to highl... - 10:49 AM Bug #11667 (Resolved): erasure-code: test adding a new OSD
- * create an erasure coded pool with a few objects
* add a new osd
* wait until the cluster is healthy
* retrieve t... - 10:43 AM Fix #11666 (Resolved): erasure-code: add lrc to rados/thrash-erasure-code
- Add a workload using the LRC plugin
* master https://github.com/ceph/ceph-qa-suite/pull/445 - 10:33 AM Bug #11665 (Resolved): erasure-code: test/osd/osd-scrub-repair.sh add lrc test case
- The scenario for failure on erasure coded pool only verifies the behavior of the jerasure plugin. Add a minimal scena...
- 10:25 AM Bug #11573: OSD assertion in erasure code environment
- xingyi, i am not able to reproduce your crash on master. will try it on the firefly branch....
- 09:00 AM Bug #11211: osd/ReplicatedPG.cc: 2141: FAILED assert(op == prdop->op)
- http://pulpito.ceph.com/loic-2015-05-18_00:59:08-rgw-wip-11622-hammer---basic-multi/896515/...
- 08:45 AM devops Feature #11417 (Fix Under Review): build ceph with hardening flags
- https://github.com/ceph/ceph/pull/4683
- 02:14 AM Revision c1f4b7a2 (ceph): Merge pull request #4703 from dachary/wip-make-check-verbose
- tests: reduce make check verbosity
Reviewed-by: Kefu Chai <kchai@redhat.com>
05/17/2015
- 10:41 PM Revision e4ca4685 (ceph): tests: reduce make check verbosity
- Move check-local scripts
src/test/run-cli-tests
encode-decode-non-regression.sh
test/encoding/readable.sh
... - 10:35 PM Bug #10358 (Fix Under Review): ceph osd erasure-code-profile set myprofile k=1 should fail
- * master https://github.com/ceph/ceph/pull/4713
- 09:45 PM Feature #9589 (Fix Under Review): erasure-code: query plugin for erasure-code-profile defaults
- * master https://github.com/ceph/ceph/pull/4710
- 03:12 PM Feature #9589 (In Progress): erasure-code: query plugin for erasure-code-profile defaults
- 09:42 PM Fix #11663 (Resolved): erasure-code-profile: verify profile content
- The profile stored by the plugin may be different from the one set by the user: it includes defaults. When the plugin...
- 09:02 PM devops Bug #11662 (Can't reproduce): "error: Can't download https://pypi.python.org..." in ceph-deploy-h...
- hammer v0.94.2 release
Run:http://pulpito.ceph.com/teuthology-2015-05-17_10:05:19-ceph-deploy-hammer-distro-basic-vp... - 08:55 PM Revision a0eac3e4 (ceph): Merge pull request #4711 from dachary/wip-ceph-detect-init
- ceph-detect-init typo
Reviewed-by: Michal Jarzabek <stiopa@gmail.com> - 07:30 PM Revision 64f584a8 (ceph): ceph-detect-init: fix pep8 extra space
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:29 PM Revision 855aeee6 (ceph): ceph-detect-init: run-tox.sh always succeeds
- Because of the | grep, the status of tox is no longer the status of
run-tox.sh and errors are not reported as they sh... - 04:59 PM Revision 38e60deb (ceph): Perf: used to perf local hardware capacity
- This program contains a collection of low-level performance measurements
for Ceph, which can be run either individual... - 03:00 PM Revision d723de62 (ceph): erasure-code: update ceph-erasure-code-corpus for shec
- Update the ceph-erasure-code-corpus submodule to include the hammer shec
checks.
Signed-off-by: Loic Dachary <ldacha... - 02:25 PM Revision 8e7dfcd2 (ceph): Merge pull request #4704 from dachary/wip-ceph-helpers
- {mon,osd}-test-helpers.sh are deprecated
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:22 PM Revision 3cf3ac39 (ceph): cryptic error message in ceph interactive mode
- Fixes: #11459
Signed-off-by: Michal Jarzabek <stiopa@gmail.com> - 01:57 PM Revision 7e5336bf (ceph): Merge pull request #4706 from stiopaa1/cephdetectinit
- ceph_detect_init: added linux mint
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:18 PM Bug #11660: "osd/ReplicatedPG.cc: 10405: FAILED assert(obc)" in rados-hammer-distro-basic-magna
- Maybe related to http://tracker.ceph.com/issues/9732 ?
- 12:15 PM Bug #11386 (Duplicate): "osd/ReplicatedPG.cc: 11268: FAILED assert(obc)" in smoke-giant-distro-ba...
- 12:09 PM devops Bug #11659: Need a RHEL 7.1 gitbuilder
- The master builds were broken a few days ago. Although it was broken only during two or three hours, could it be the ...
- 11:50 AM Revision d688b0c3 (ceph): ceph_detect_init: added linux mint
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 11:31 AM Revision aa99929e (ceph): tests: test/erasure-code/test-erasure-code.sh uses ceph-helpers.sh
- The ceph-helpers.sh was already included, along with
mon/mon-test-helpers.sh and osd/osd-test-helpers.sh which create... - 11:31 AM Revision 4a26ca2e (ceph): tests: test/mon/misc.sh uses ceph-helpers.sh
- Fix grep that assume the pool has id 0, because it may be different
when rbd is redefined to have less PG by the run_... - 11:31 AM Revision c693ec10 (ceph): tests: test/vstart_wrapper.sh uses ceph-helpers.sh
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 11:31 AM Revision 0f565532 (ceph): tests: test/osd/osd-copy-from.sh uses ceph-helpers.sh
- The ceph-helpers.sh was already included, along with
mon/mon-test-helpers.sh and osd/osd-test-helpers.sh which create... - 11:31 AM Revision e3f03d83 (ceph): tests: test/osd/osd-config.sh uses ceph-helpers.sh
- The ceph-helpers.sh was already included, along with
mon/mon-test-helpers.sh and osd/osd-test-helpers.sh which create... - 11:31 AM Revision 88e954b0 (ceph): tests: test/osd/osd-bench.sh uses ceph-helpers.sh
- Remove useless inclusion of osd/osd-test-helpers.sh
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 11:31 AM Revision 12097865 (ceph): tests: test/mon/osd-pool-create.sh uses ceph-helpers.sh
- Use ceph-helpers.sh instead of mon/mon-test-helpers.sh.
* The expect_false() helper is replaced by a ! statement ... - 11:31 AM Revision e9859838 (ceph): tests: test/mon/mon-handle-forward.sh uses ceph-helpers.sh
- Use ceph-helpers.sh instead of mon/mon-test-helpers.sh.
* modifying the .asok and .log names to match the ceph-he... - 11:31 AM Revision ae2d489b (ceph): tests: ceph-helpers.sh remove redundant setup in main
- And add setup/teardown in tests that do not have it.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 11:31 AM Revision e5564a87 (ceph): tests: {mon,osd}-test-helpers.sh are deprecated
- Remove the helpers because they are not used any longer. They have been
deprecated by ceph-helpers.sh
Signed-off-by:... - 11:31 AM Revision 7aca4701 (ceph): tests: test/mon/osd-crush.sh uses ceph-helpers.sh
- It is just a conversion and the behavior is not changed. It involves:
* calling run_mon from inside each test inst... - 10:33 AM Revision b9447bce (ceph): tests: ceph-helpers.sh shows ceph report if not clean
- Instead of just pg dump and health detail, the wait_for_clean
function displays ceph report when it times out, to hel... - 10:33 AM Revision ea61c8ab (ceph): tests: ceph-helpers.sh do not hardcode id a in run_mon
- Fix hardcoding of id a in the run_mon function. The directory
in which the mon data is stored must be a sub-directory... - 10:33 AM Revision 66dcda9a (ceph): tests: kill mon-test-helpers.sh call_TEST_functions
- Remove call_TEST_functions because it is too complex and rarely used.
Replace the two instances where it was used by ... - 10:33 AM Revision f3cb870b (ceph): tests: test/mon/osd-erasure-code-profile.sh uses ceph-helpers.sh
- Instead of using mon-test-helpers.sh, primarily because the kill_daemon
function implemented in mon-test-helpers.sh i... - 10:10 AM Revision de20f615 (ceph): tests: ceph-helpers.sh implement wait_for_osd
- The wait_for_osd to wait for an osd to go up and down is needed
internally, after running an osd. Move the inline sni... - 01:09 AM rbd Bug #10116: Ceph vm guest disk lockup when using fio
- I haven't tested it yet, but its possible this kernel bug is what was biting me:
https://groups.google.com/forum/#!t...
Also available in: Atom