Activity
From 03/05/2014 to 04/03/2014
04/03/2014
- 11:47 PM CephFS Bug #7980 (Resolved): 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- MDS crashes (segmentation fault) when I wake-up machine with CephFS (mounted using kernel client) from suspend:
<p... - 10:54 PM Bug #7922 (Fix Under Review): osd: multi-backfill reservation does not release on reject
- 06:08 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- ...
- 03:29 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- i reproduced this on my first try with the patch in wip-7922....
- 10:15 PM Revision 0552ecba (ceph): rgw: only look at next placement rule if we're not at the last rule
- Fixes: #7978
We tried to move to the next placement rule, but we were already at the
last one, so we ended up looping... - 10:11 PM Revision 0f6c92f0 (ceph): Merge pull request #23 from ceph/wip-7771-wusui
- FIxed dumpling - emperor upgrade suites
- 09:22 PM Revision 39166b2d (ceph): upgrade/dumpling-x: run dumpling version of s3tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:04 PM Revision eb23ac46 (ceph): ReplicatedPG::agent_choose_mode: use num_user_objects for target_max_by...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:04 PM Revision cc9ca67a (ceph): ReplicatedPG::agent_choose_mode: exclude omap objects for ec base pool
- Fixes: #7831
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:04 PM Revision a130a445 (ceph): osd/: track num_objects_omap in pg stats
- Fixes: #7831
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:03 PM Revision 9894a55d (ceph): ReplicatedPG: handle FLAG_OMAP on promote and copyfrom
- Fixes: #7967
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:02 PM Revision a60b50d6 (ceph): FIxed dumpling - emperor upgrade suites
- Reformatted many of the yaml files.
Fixed duplication of workunit definitions.
Do not do install.upgrade on clients.
... - 07:53 PM Revision 78e9813c (ceph): ReplicatedPG: do not create snapdir on head eviction
- Head eviction implies that no clones are present. Also, add
an exists flag to SnapSetContext in order prevent an ssc... - 07:53 PM Revision a11b3e8d (ceph): ReplicatedPG::do_op: use get_object_context for list-snaps
- find_object_context provides some niceties which we don't need since we know
the oid of the clones. Problematically,... - 07:20 PM Revision c66b61f9 (ceph): rbd: return 0 and an empty list when pool is entirely empty
- rbd_list will return -ENOENT when no rbd_directory object
exists. Handle this in the cli tool and interpret it as suc... - 07:06 PM Revision 31df91e0 (ceph): osd: add 'osd debug reject backfill probability' option
- This will make the OSD randomly reject backfill reservation requests. This
exercises the failure code paths but does... - 06:45 PM Revision 90c4540b (ceph): Merge pull request #1598 from ceph/wip-test-alloc-hint-ec-fix
- qa: test_alloc_hint: set ec ruleset-failure-domain to osd
Reviewed-by: Sage Weil <sage@inktank.com> - 06:44 PM Revision 9f41975c (ceph): Merge pull request #1581 from ceph/wip-init
- a few deb changes
- 06:42 PM Revision 267307e6 (ceph): upgrade/dumpling-emperor-x: do not warn about tunables
- We do the same for dumpling-x.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:42 PM Revision a5a5ba3c (ceph): upgrade/dumpling-emperor-x: ignore 'scrub mismatch' from mon
- The encoded full osdmaps can differ due to a series of issues that were
fixed well after emperor. We also whitelist ... - 06:30 PM Bug #7977 (Pending Backport): cephx has embedded byte-order dependency
- 01:56 PM Bug #7977 (Resolved): cephx has embedded byte-order dependency
- Calculation of the original session key is byte-order-dependent; cephx_calc_client_server_challenge gets a message di...
- 05:49 PM Bug #7964: ceph_test_rados with snaps and caching stat errors
- 01:04 PM Bug #7964 (Rejected): ceph_test_rados with snaps and caching stat errors
- 05:43 PM rgw Bug #7978 (Resolved): rgw: infinite loop when iterating multipart object
- 03:17 PM rgw Bug #7978 (Fix Under Review): rgw: infinite loop when iterating multipart object
- 03:13 PM rgw Bug #7978 (Resolved): rgw: infinite loop when iterating multipart object
- This happens when the object created has a final placement rule with part_size > 0, e.g.,...
- 05:16 PM Revision d3236340 (ceph): qa: test_alloc_hint: set ec ruleset-failure-domain to osd
- Create a custom profile with ruleset-failure-domain=osd. (The default
ruleset-failure-domain=host won't do because t... - 04:57 PM Revision 60d19756 (ceph): Merge pull request #1593 from dachary/wip-vstart-erasure-code-default
- vstart: set a sensible default for ruleset-failure-domain
Reviewed-by: Ilya Dryomov <ilya.dryomov@inktank.com> - 04:57 PM Revision cdcd8368 (ceph): Merge pull request #1596 from ceph/wip-vstop-unmap
- Unmap rbd images when stopping the whole cluster
Reviewed-by: Sage Weil <sage@inktank.com> - 02:14 PM Revision afc5dc53 (ceph): stop.sh: do not trace commands
- Command tracing here doesn't bring any value and simply pollutes the
terminal, as the script always runs to completio... - 02:14 PM Revision 8e46fe00 (ceph): stop.sh: unmap rbd images when stopping the whole cluster
- Unmap rbd images when stopping the whole cluster. Not doing so results
in images that cannot be unmapped until the s... - 02:03 PM Revision 0110a19b (ceph): stop.sh: indent 4 spaces universally
- Currently there is a mix between tabs and 4 spaces indent. Switch to
4 spaces indent.
Signed-off-by: Ilya Dryomov <... - 01:55 PM Bug #7976 (Duplicate): 4.8 missing primary copy of ..., unfound (dumpling)
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-02_22:35:24-upgrade:dumpling-x:stress-split-firefl...
- 01:38 PM rbd Bug #7973 (Resolved): rbd ls returns error code of 1 on empty pool
- This is the same as #6693. Backported the fix to the dumpling branch in commit:c66b61f9dcad217429e4876d27881d9fb2e7666f
- 11:55 AM rbd Bug #7973 (Resolved): rbd ls returns error code of 1 on empty pool
- Using version 0.67.7 rbd ls is returning an error code of 1 on an empty pool. This is causing OpenStack Havana proble...
- 01:28 PM Bug #7975 (Resolved): osd: handle inconsistent stats in the osd post split
- 01:01 PM Bug #7967: finish_promote needs to handle the omap flag
- 12:07 PM Revision e4a8535a (ceph): vstart: set a sensible default for ruleset-failure-domain
- Set ruleset-failure-domain=osd so that
./ceph osd pool create ecpool 12 12 erasure
./rados --pool ecpool put SOM... - 10:24 AM Fix #7919 (Fix Under Review): mon: prevent clients with a read cap from reading the full keyring
- pull request 1597 https://github.com/ceph/ceph/pull/1597
- 06:53 AM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- 05:32 AM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- I guess it's introduce by commit f1c7b4ef0 (client: pin Inode during readahead). Readahead raced with truncate. Objec...
- 12:43 AM Bug #7968 (Won't Fix): ImportError occurred when run command 'ceph -v'
- I. How to reproduce:
1. Clone the latest ceph master code from github
2. From my laptop, install the pre-require... - 12:13 AM Revision 552f9d8d (ceph): multimds: test ceph-fuse and kclient
- Add client as a variable on the basic collection. Move the other stuff
(libcephfs plus a weird restart test) to libc... - 12:03 AM Revision 89f38c09 (ceph): Merge pull request #1592 from ceph/wip-7965
- lockdep: fix when instantiated multiple times (bug 7965)
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
04/02/2014
- 11:46 PM Revision c43822cd (ceph): lockdep: reset state on shutdown
- If we shut down, clear out all of the lockdep state. This ensures that if
we start up again on another cct, we will ... - 11:46 PM Revision 7a49f3da (ceph): lockdep: do not initialize if already started
- If we have already registered a cct for lockdep, do not accept another one.
We already check that the cct matches whe... - 11:13 PM Revision eae5a377 (ceph): Merge pull request #1591 from ceph/wip-7915
- mon: bump snap_epoch when adding a tier (fixes 7915)
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:03 PM Revision 6bf46e23 (ceph): OSDMap: bump snap_epoch when adding a tier
- When we make an existing pool a tier, we start copying the snap metadata
from the base tier. That includes removed_s... - 10:15 PM Revision 27e353cc (ceph): Merge pull request #1580 from ceph/wip-7937
- osd: fix scrub logic for snapdir object
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage... - 10:12 PM Revision 01445d5c (ceph): ReplicatedPG::_scrub: don't bail early for snapdir
- Fixes: #7937
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:10 PM Revision 0815140f (ceph): test: use older names for module setup/teardown
- setUp and tearDown require nosetests 0.11, but 0.10.4 is the latest on
centos. Rename to use the older aliases, which... - 10:00 PM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_23:00:33-fs-firefly-distro-basic-plana/160589
- 10:23 AM CephFS Bug #7958 (Resolved): ceph-fuse+fsx umount hang on leaked inode reference
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-31_23:00:36-fs-master-testing-basic-plana/157636
... - 09:56 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- logs on flab:/more2/t/7922
on osd.9, we see:... - 03:21 PM Bug #7922 (In Progress): osd: multi-backfill reservation does not release on reject
- 01:19 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- All highly-verbose logfiles have been uploaded at Sage's request (4.3GiB): http://www.aarontc.com/logs/ceph-logs-chek...
- 09:22 PM Revision 5f680f90 (ceph): ReplicatedPG::_verify_no_head_clones: missing implies that the clone ex...
- Fixes: #7659
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:57 PM Revision b405bfa4 (ceph): OSD: don't clear peering_wait_for_split in advance_map()
- I really don't know why I added this... Ops can be discarded from the
waiting_for_pg queue if we aren't primary simp... - 08:54 PM Revision 60b7aa96 (ceph): test: use older names for module setup/teardown
- setUp and tearDown require nosetests 0.11, but 0.10.4 is the latest on
centos. Rename to use the older aliases, which... - 08:07 PM Bug #7965 (Resolved): osd: SEGV in handle_recovery_read_complete
- 04:47 PM Bug #7965: osd: SEGV in handle_recovery_read_complete
- reliably reproduced with lockdep enabled with ceph_test_rados_api_tier. appears to be due to multiple initialization...
- 04:46 PM Bug #7965 (Fix Under Review): osd: SEGV in handle_recovery_read_complete
- 04:08 PM Bug #7965 (Resolved): osd: SEGV in handle_recovery_read_complete
- ...
- 07:57 PM Revision a498c940 (ceph): Merge remote-tracking branch 'gh/wip-7888-dumpling' into dumpling
- 07:34 PM Bug #4185: Python multiprocessing exhibiting odd behaviour with librados
- Some notes for the Next guy that comes across this issue:
You can use the multiprocessing managers to push all the... - 06:29 PM Revision 7909262f (ceph): debian: fix control to allow upgrades
- Signed-off-by: Mohammad Salehe <salehe+dev@gmail.com>
- 05:52 PM Revision 250a1029 (ceph): Merge pull request #1590 from ceph/wip-7939
- PG: set role for replicated even if role != shard
Reviewed-by: Sage Weil <sage@inktank.com> - 05:44 PM Revision b6c70534 (ceph): Merge pull request #1589 from ceph/wip-7805-emperor
- PG: only complete replicas should count toward min_size
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:35 PM Revision d6258b63 (ceph): Merge pull request #1579 from ceph/wip-7907
- osd/ReplicatedPG: mark_unrollbackable when _rollback_to head
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:29 PM Revision 17732dc0 (ceph): debian: move rbdmap config and sysvinit/upstart scripts into ceph-common
- Fixes: #7171
Signed-off-by: Sage Weil <sage@inktank.com> - 05:28 PM Bug #7967 (Resolved): finish_promote needs to handle the omap flag
- 05:22 PM Bug #7689 (Duplicate): librados: ENOENT on ioctx create
- 05:21 PM Bug #7689: librados: ENOENT on ioctx create
- oh, i think this is a dup of #7736
- 05:19 PM Bug #6429 (Can't reproduce): msg/Pipe.cc: 1029: FAILED assert(m)
- 05:17 PM Bug #7776 (Resolved): client lockdep crash
- 04:28 PM Bug #7776 (In Progress): client lockdep crash
- 03:33 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_02:30:19-rados-firefly-distro-basic-plana/158403...
- 03:32 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_02:30:19-rados-firefly-distro-basic-plana/158409...
- 04:13 PM Bug #7915 (Resolved): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 04:04 PM Bug #7915 (Fix Under Review): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 11:55 AM Bug #7915 (Need More Info): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- we've added more debug to master/firefly
- 04:12 PM CephFS Bug #7966 (Resolved): ceph-mds respawn doesn't always work
- ...
- 03:55 PM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- @Yehuda: That code change looks good. I'll try to test by monday and get back to you with confirmation of it working.
- 07:31 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- I pushed some work into wip-7450. It takes care of the default access key generation in the case of subusers, and som...
- 03:54 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Compiled TestErasureCodeJerasure.cc with m=1 https://github.com/ceph/ceph/blob/master/src/test/erasure-code/TestErasu...
- 02:23 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 10:57 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- mira087 has the fisrst 2 failures, mira089 has the earlier one. they all see to crash in teh same place:...
- 10:19 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 09:38 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Ran test for both gf-complete and jerasure and they are valgrind clean ( https://bitbucket.org/jimplank/jerasure/pull...
- 09:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- /a/teuthology-2014-03-31_02:30:03-rados-master-testing-basic-plana/155875/teuthology.log is the only ec_pool test tha...
- 09:10 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- also happened on ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154379 on commi...
- 03:44 PM Revision 86a032f2 (ceph): Merge pull request #1586 from ceph/wip-dirfrag
- mds: fix check for merging/spliting dirfrag
Reviewed-by: Sage Weil <sage@inktank.com> - 03:43 PM Revision 84e62e9f (ceph): Merge pull request #1587 from onlyjob/debian
- init.d: correcting rbdmap LSB header / init order:
Reviewed-by: Sage Weil <sage@inktank.com> - 03:31 PM Bug #7964 (Resolved): ceph_test_rados with snaps and caching stat errors
- 03:21 PM Bug #6681 (Resolved): osd recovery hung
- backported to dumpling
- 01:52 PM Bug #6681 (Pending Backport): osd recovery hung
- /var/lib/teuthworker/archive/teuthology-2014-04-01_19:00:30-rados-dumpling-testing-basic-plana/159217
- 03:15 PM Bug #7576 (In Progress): osd: large skew in pg epochs (dumpling)
- wip-7576
- 03:07 PM Bug #7917 (Resolved): "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Just needed to cherry-pick the fix for #6368 to dumpling.
- 02:25 PM Revision 1d42de54 (ceph): init.d: correcting rbdmap init order:
- * Require "$remote_fs" since it guarantees /usr availability
(rbd executable is in /usr/bin/rbd)
* Speed-up init.... - 01:38 PM RADOS Feature #7962 (New): allow the user to query inconsistent object status and specify repair strategy
- 12:56 PM Messengers Bug #7888 (Resolved): msgr: keepalive is insufficient
- 10:56 AM devops Feature #7960 (Resolved): backport rpm creation of /usr/lib64/qemu/librbd.so.1 symlink to dumpling
- Backport #7293 to dumpling so it works seamlessly with rhev and rhel-osp as well.
- 10:51 AM Bug #7939 (Resolved): pg role wrong for replicated pools
- 10:42 AM Bug #7805 (Pending Backport): emperor can go active with < min_size non-incomplete peers since we...
- 08:50 AM Bug #7805 (Fix Under Review): emperor can go active with < min_size non-incomplete peers since we...
- 10:41 AM Bug #7907 (Resolved): osd: rollback to head didn't mark_unrollbackable
- 09:45 AM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- ...
- 09:36 AM Bug #7949 (Duplicate): "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefl...
- Dup of 7935
- 09:33 AM Bug #7951 (Duplicate): "test_rbd."* tests failed in upgrade:dumpling-x:parallel-firefly-distro-ba...
- 09:07 AM Bug #7957 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-emperor-x:parallel-firefly-testi...
- Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-04-02_01:54:27-upgrade:dumpling-emperor-x:parallel-firefly...
- 07:53 AM RADOS Feature #7956 (New): osd: implement posix_fadvise/POSIX_FADV_DONTNEED to prevent data caching
- Running Ceph OSDs on commodity hardware often means that servers are not used exclusively for OSDs and may have other...
- 07:32 AM Revision 771e88a4 (ceph): mds: fix check for merging/spliting dirfrag
- check actual number of items instead of number of cached items
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 07:24 AM Bug #7931 (Can't reproduce): setcrushmap crashing monitor
- 06:36 AM Bug #7931: setcrushmap crashing monitor
- Hi Greg,
I don't think that was the issue, however it has since been working. The crushmap I've uploaded was the r... - 04:47 AM Revision edb8a596 (ceph): Merge pull request #1583 from ceph/wip-largedir
- Wip largedir
Reviewed-by: Sage Weil <sage@inktank.com> - 04:19 AM Revision 5a9b99aa (ceph): mds: initialize bloom filter according to dirfrag size
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 04:19 AM Revision 43bc39be (ceph): mds: ignore CDir::check_rstats() when debug_scatterstat is off
- It uses lots of CPU when dirfrag is large
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 04:19 AM Revision 16af25fb (ceph): mds: add dentries in dirfrag to LRU in reverse order
- Files in a dirfrag are usually processed in the order of readdir
results. Files at the beginning of are more likely t... - 04:01 AM Revision d351e5fb (ceph): Merge pull request #1584 from ceph/wip-multimds
- Wip multimds
Reviewed-by: Sage Weil <sage@inktank.com> - 03:03 AM Revision 06ecb2c7 (ceph): mds: handle freeze authpin race
- For across authority rename, the MDS first freezes the source inode's
authpin. It happens while the source dentry isn... - 03:03 AM Revision b65a8184 (ceph): mds: don't start new segment while finishing disambiguate imports
- This avoid inserting ESubtreeMap among EImportFinish events that
finish disambiguate imports. Because the ESubtreeMap... - 03:03 AM Revision d1967f32 (ceph): mds: treat cluster as degraded when there is clientreplay MDS
- This forbids exporting subtrees and fragmenting dirfrags when there
is MDS in clientreplay state. During replaying cl... - 03:03 AM Revision ff44a99a (ceph): mds: trim non-auth subtree more aggressively
- When a non-auth dirfrag is pinned by uncommitted slave update,
there still can be non-auth child dirfrags that are tr...
04/01/2014
- 11:02 PM Revision c09f58ef (ceph): radosgw-admin: don't always generate access key for subusers
- Only generate key for subuser if one was not specified for it, and only
when creating a subuser.
Signed-off-by: Yehu... - 11:01 PM Revision 0d5d3d1a (ceph): PG: only complete replicas should count toward min_size
- Backport: emperor,dumpling,cuttlefish
Fixes: #7805
Signed-off-by: Samuel Just <sam.just@inktank.com>
Signed-off-by: S... - 11:01 PM Revision 9ef5e4ab (ceph): Revert "PG: only complete replicas should count toward min_size"
- This reverts commit b097a237e11b48c47d3fd5484f3449e683e95db0.
This causes us to crash, probably because whoami is no... - 10:43 PM Revision e1783a62 (ceph): rgw: subuser creation can be idempotent
- No real reason to check for existing subuser before (re)creating it.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:40 PM Revision f54c6846 (ceph): radosgw-admin: fix subuser modify
- Shouldn't check for empty access key when modifying swift user, also
set correct fields when updating swift keys.
Si... - 09:46 PM Bug #7952: After aio_read() completes a call to return_value() doesn't return bytes read
- This might be the issue underlying #7822
- 06:02 PM Bug #7952 (Resolved): After aio_read() completes a call to return_value() doesn't return bytes read
When using the rados_aio_read() interface the c.bl bufferlist stores the read data. So the code below will set rva...- 09:42 PM Revision e095b1d4 (ceph): debian: make ceph-common own etc/ceph, var/log/ceph
- Clients can make use of these directories, and ceph-common is required by
ceph, so nothing should break here.
Change... - 09:38 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- Here's a partial log from osd.3 around the problematic time: http://www.aarontc.com/logs/ceph-osd.3.log.bz2
Please... - 09:22 PM Bug #7922 (Need More Info): osd: multi-backfill reservation does not release on reject
- it would help to see the log from the primary sending the dup backfill request. it is not entirely trivial to determ...
- 09:18 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- We got a duplicate backfill reservation request from osd.3:...
- 09:27 PM Revision d4d39a01 (ceph): osd/ReplicatedPG: mark_unrollbackable when _rollback_to head
- We fell into the case in _rollback_to where we just set ctx->modify = true
and don't explicitly mark the ctx and unro... - 08:58 PM Revision f0978a82 (ceph): Merge pull request #1578 from ceph/wip-7437
- wip-7437
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:44 PM Linux kernel client Bug #7954 (Resolved): misdirected op
- Test Run: teuthology-2014-03-31_23:02:09-kcephfs-master-testing-basic-plana
======================================... - 08:07 PM Revision 1acd547a (ceph): debian: move ceph-rest-api from ceph-common to ceph
- ceph-rest-api is a 'server' thing that runs persistently; 'ceph' is a
better match.
Signed-off-by: Sage Weil <sage@i... - 07:38 PM Revision a926cd38 (ceph): Merge pull request #1577 from ceph/wip-7935
- rgw: reverse logic to identify next part
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:19 PM Revision a76a129f (ceph): PG: set role for replicated even if role != shard
- Fixes: #7939
Signed-off-by: Samuel Just <sam.just@inktank.com> - 07:02 PM Revision 26eeab43 (ceph): PGLog::rewind_divergent_log: log may not contain newhead
- Due to split, there may be a hole at newhead.
Fixes: #6722
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewe... - 07:02 PM Revision 225fc97f (ceph): PG: fix operator<<,log_wierdness log bound warning
- Split may cause holes such that head != tail and yet
log.empty().
Fixes: #6722
Signed-off-by: Samuel Just <sam.just@... - 06:59 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- I found another source of race conditions, and hopefully fixed them in the wip-6480-0.67.7 branch. I'm running tests ...
- 06:53 PM Revision 759878c1 (ceph): test: Add EC testing to ceph_test_rados_api_tier
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 1871fe79 (ceph): test: Add EC testing to ceph_test_rados_api_lock
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision ef94fcd7 (ceph): test: Add EC testing to ceph_test_rados_api_snaphots
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 2d7da1d5 (ceph): librados: Add missing rados_wait_for_latest_osdmap()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision c106976f (ceph): librados: Add missing C variants for alignment
- Add rados_ioctx_pool_requires_alignment()
Add rados_ioctx_pool_required_alignment()
Signed-off-by: David Zafman <dav... - 06:53 PM Revision 74ed4489 (ceph): test: Cleanup pools when FlushWriteRaces is done
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 966480b2 (ceph): test: Fix ceph_test_rados_api_aio to clean up all test pools
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision a4da24d3 (ceph): test: Fix ceph_test_rados_list_parallel to clean up test pool
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 9bd5821a (ceph): test: Add EC test classes RadosTestEC and RadosTestECPP
- Fixes: #7437
Signed-off-by: David Zafman <david.zafman@inktank.com> - 06:53 PM Revision ea26e13b (ceph): test: Add EC testing to ceph_test_rados_api_io
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 7ccf4129 (ceph): test: Add EC testing to ceph_test_rados_api_list
- Fixes: #7437
Signed-off-by: David Zafman <david.zafman@inktank.com> - 06:53 PM Revision 6cedfacd (ceph): test: Add EC testing to ceph_test_rados_api_stat
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:53 PM Revision 38b9fe7c (ceph): test: Add EC to ceph_test_rados_api_watch_notify
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:04 PM Revision dde1c916 (ceph): osd/ReplicatedPG: continue scrub logic when snapset.head_exists doesn't...
- The 'continue' will cause more damange/noise than continuing because the
next_clone value won't be updated properly.
... - 06:04 PM Revision c2e5a428 (ceph): osd/ReplicatedPG: handle snapdir properly during scrub
- Handle snapdir similarly to how head is treated when updating the
next_clone info. Also, add a warning when we have ... - 05:52 PM Revision ed5a5e07 (ceph): rgw: reverse logic to identify next part
- Fixes: #7935
The check that identifies whether we need to move to the next part when
iterating over an object was rev... - 05:45 PM Revision 48fbce98 (ceph): ReplicatedPG: improve get_object_context debugging
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:40 PM Bug #7941: caching needs to be able to enforce snap context on flush even with pool snaps
- 01:11 PM Bug #7941 (Resolved): caching needs to be able to enforce snap context on flush even with pool snaps
- 04:40 PM Bug #7942: promote uses cloneid, but backend may have a different cloneid
- 01:12 PM Bug #7942 (Resolved): promote uses cloneid, but backend may have a different cloneid
- 04:20 PM Bug #7949: "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefly-distro-bas...
- A pretty good chance that this is #7935.
- 03:28 PM Bug #7949 (Duplicate): "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 04:17 PM Bug #7950 (Duplicate): "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgra...
- Duplicate of #7935, failed due to a new test added.
- 03:46 PM Bug #7950: "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgrade:dumpling-...
- May be a duplicate of 7949
- 03:45 PM Bug #7950 (Duplicate): "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgra...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 03:59 PM Bug #7805: emperor can go active with < min_size non-incomplete peers since we check acting size
- wip-7805-emperor
- 03:59 PM Bug #7938 (Resolved): Coredump generated by upgrade test
- this was a broken commit:b097a237e11b48c47d3fd5484f3449e683e95db0. reverted.
- 11:23 AM Bug #7938 (Resolved): Coredump generated by upgrade test
- The following yaml consistently generates coredumps....
- 03:55 PM Bug #7951 (Duplicate): "test_rbd."* tests failed in upgrade:dumpling-x:parallel-firefly-distro-ba...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 03:29 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- The only difference is that ext4 is used in teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491 an...
- 03:15 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Running 30 more, sequentially.
- 03:09 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Contrary to what I thought (reading the wrong number), plana have SSE3 indeed and the jerasure plugin including SSE4 ...
- 02:59 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ran through 20 iterations of the above yaml and did not reproduce.
- 09:35 AM Bug #7914 (In Progress): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer lengt...
- I will run the workload many times, hoping to reproduce the crash.
- 08:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Another run with success, complete logs in attachment:run2.txt
- 06:49 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- I don't see why not locking the erasure-code plugin registry could be a problem in practice but it is a problem in th...
- 06:26 AM Bug #7914 (Can't reproduce): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer l...
- The above teuthology workload ran on two plana machines and did not create a core dump.
- 06:05 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 05:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Trying to trigger the problem again with:...
- 05:16 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- /a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491...
- 03:29 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- both errors show with "thrashers/pggrow.yaml" (one with btrfs, the other with ext4)
- 02:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- the /a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491 radosbench completed successfully
<pre... - 02:18 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Trying to reproduce the problem from the source tree on the current master with...
- 01:49 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- cpuinfo on plana17 (the machine on which the core dump occured) shows:...
- 01:43 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- *-msse3* was not used although it should have and this was fixed "march 30th":https://github.com/ceph/ceph/commit/1c9...
- 01:39 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- "latest jerasure / gf-complete":https://github.com/ceph/ceph/commit/1c92453f748aea48084e57c9c721ee8080caeeb6 submodul...
- 01:23 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 12:57 AM Bug #7914 (In Progress): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer lengt...
- 02:46 PM Bug #7937: [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 11:05 AM Bug #7937 (Fix Under Review): [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected c...
- 10:48 AM Bug #7937: [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 038e94b51e4945380c4ba771c88c953b6628d0f7 (wip-sam-testing)
- 10:46 AM Bug #7937 (Resolved): [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 2014-03-31 17:00:27,792.792 INFO:teuthology.task.internal:Removing archive directory...
2014-03-31 17:00:27,840.840 ... - 02:46 PM rgw Bug #7935 (Resolved): rgw: multipart upload failure with s3cmd
- commit:ed5a5e075544662a12d94e472da55aeb2f0efe5d
- 12:31 PM rgw Bug #7935: rgw: multipart upload failure with s3cmd
- This issue happens when not all parts are the same size. Extended the s3 functional test to check this.
- 10:55 AM rgw Bug #7935 (Fix Under Review): rgw: multipart upload failure with s3cmd
- 10:05 AM rgw Bug #7935 (Resolved): rgw: multipart upload failure with s3cmd
- From ceph-users mailing list:...
- 02:44 PM devops Feature #7171 (Fix Under Review): rbdmap should be part of ceph-common
- https://github.com/ceph/ceph/pull/1581
- 02:25 PM Bug #7907: osd: rollback to head didn't mark_unrollbackable
- the original modify:...
- 02:14 PM devops Feature #7947 (Duplicate): Create separate ceph and ceph-common packages for EL6 and EL7 builds
- No reason why rpm builds shouldn't be the same as for debs...
- 02:07 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- My guess is that this behavior kicked in when we started matching client caps with the expected caps on a per-command...
- 01:27 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- That sounds like the best solution to me. Somebody on the mailing list reported that Dumpling is not exposing user da...
- 01:25 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- My vote is to make 'auth' special and require * to access it (or an explcit grant of auth rw or something). This is ...
- 01:23 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- Here's the thing: obviously, allowing anyone with read permission to simply grab the whole keyring is not a good thin...
- 01:10 PM Fix #7919 (In Progress): mon: prevent clients with a read cap from reading the full keyring
- Okay, I was the one at fault here. Was missing to provide a keyring with the client's key thus getting permission de...
- 09:12 AM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- Hum, I didn't validate the issue so maybe it was user error. Should probably poke him on the mailing list to check. *...
- 05:26 AM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- doesn't seem to happen on latest emperor. checking if anything changed in between 0.72.2 and latest emperor, or if I...
- 01:26 PM Feature #7459 (Rejected): ceph-rest-api: sysvinit and upstart scripts
- 01:06 PM Feature #7459 (Fix Under Review): ceph-rest-api: sysvinit and upstart scripts
- 01:09 PM Feature #7940 (Resolved): add pool snaps to ceph_test_rados
- 01:00 PM Bug #7939: pg role wrong for replicated pools
- 12:16 PM Bug #7939 (Resolved): pg role wrong for replicated pools
- 10:30 AM Bug #7892 (New): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.length()...
- 10:23 AM Bug #7892 (Duplicate): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.le...
- probably dups #7916
- 10:29 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- We looked at this in standup today. There is a queue_null on every PG in OSD::consume_map(), so they should be gettin...
- 10:24 AM Bug #7588 (Can't reproduce): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_co...
- 10:23 AM Bug #7936 (Can't reproduce): "failed: rados" in upgrade:dumpling-x:parallel-firefly-distro-basic-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 10:21 AM Bug #7916 (In Progress): ceph_test_rados got ENOENT on ec pool + thrashing
- 09:43 AM Bug #7934 (Resolved): ceph_test_rados_watch_notify doesn't clean-up all pools it creates
$ ./rados lspools
data
metadata
rbd
$ ./ceph_test_rados_watch_notify
...
$ ./rados lspools
data
metadata
r...- 09:41 AM Bug #7519 (Can't reproduce): upgrade: osd crash on cuttlefish -> v0.67.1 -> emperor
- 09:35 AM devops Bug #7918: Mon hangs at start after upgrading to leveldb-1.12.0-3.fc18.x86_64 from the ceph-extra...
- We've pulled those packages until we can figure what's causing this.
- 09:34 AM Bug #7926 (Resolved): "[ERR] scrub 45.0" in upgrade:dumpling-x:parallel-firefly-distro-basic-vps ...
- commit:e672c52b4f8b945a516f2eec006e33665a08f045
- 09:31 AM rbd Bug #6257 (Resolved): rbd: cp on sparse image allocates objects in dest
- 09:21 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- Also need to ensure that code is backported to Icehouse-based distro (Ubuntu, RDO, RHEL-OSP) products.
- 09:19 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- 09:15 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- 09:21 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- Also need to ensure that code is backported to Icehouse-based distro (Ubuntu, RDO, RHEL-OSP) products.
- 09:18 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- 09:14 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- 09:15 AM rbd Feature #7924: Openstack: make long-running operations async in cinder
- 09:15 AM rbd Feature #7923: Openstack: backup from in-use volume instead of from detached volume
- 09:14 AM Bug #7931: setcrushmap crashing monitor
- You should do this with "debug mon = 20" set, but it appears to be crashing because your crush map is somehow invalid...
- 08:08 AM Bug #7931 (Can't reproduce): setcrushmap crashing monitor
- Following the guides I've created a new crushmap. When I submit this new crushmap the monitor crashes with some infor...
- 09:14 AM rbd Feature #7895: krbd: test cloning, discard, plus regular I/O via fsx
- 09:14 AM Linux kernel client Feature #190: krbd: DISCARD support
- 09:10 AM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
- 09:05 AM rgw Feature #7932 (Resolved): Create design for object versioning, including subtasks and estimates
- 04:12 AM Revision 2e997aa7 (ceph): Report job updated time
- When reading job information from archive files, use the mtime of
teuthology.log as the job updated time
Signed-off-... - 03:47 AM Revision 48c36dc3 (ceph): Merge pull request #21 from ceph/wip-thrash-affinity
- krbd, kcephfs: trash osd primary-affinity
- 03:46 AM Revision 06cab8b0 (ceph): Merge pull request #22 from ceph/wip-fuse-permission
- multimds: fuse_default_permissions = 0 for kernel build test
- 02:09 AM Feature #7928 (Rejected): erasure-code : no SSE3 specific code
- Is it worth compiling with *-msse3* and detecting it at runtime when no HAVE_SSE3 code is being compiled conditionall...
- 02:07 AM Revision 796af560 (ceph): Handle jobs with no targets
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:30 AM Revision 2e283ce6 (ceph): multimds: fuse_default_permissions = 0 for kernel build test
- This can reduce the test time becuase it avoids sending getattr
request whenever the kernel checks inode permission.
... - 01:15 AM Revision 87b08b23 (ceph): Merge pull request #1575 from jdurgin/wip-librbd-cp-sparse
- librbd: skip zeroes when copying an image
Reviewed-by: Sage Weil <sage@inktank.com> - 12:39 AM Revision 5c9b8a27 (ceph): osd/PG: debug cached_removed_snaps changes
- See #7915.
Signed-off-by: Sage Weil <sage@inktank.com>
03/31/2014
- 10:46 PM Revision addfed2d (ceph): When ignoring a raised exception, at least log it
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:19 PM Revision a4dc6f2b (ceph): Merge pull request #1574 from mikenel/master
- Add ceph-client-debug and jerasure shared objects to RPM spec file.
Reviewed-by: Sage Weil <sage@inktank.com> - 10:04 PM Revision 824da202 (ceph): librbd: skip zeroes when copying an image
- This is the simple coarse-grained solution, but it works well in
common cases like a small base image resized with a ... - 09:59 PM Revision 70d2e135 (ceph): Merge pull request #1573 from ceph/wip-7912
- mon/PGMap: clear pool sum when last pg is deleted
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:57 PM Revision 51326991 (ceph): Merge pull request #1556 from ceph/wip-7888
- msgr: add new ping/ping reply to use in place of keepalive
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:56 PM Revision a8eb9b5f (ceph): Merge pull request #1566 from ceph/wip-fuse-access
- fuse: implement 'access' low level function
Reviewed-by: Sage Weil <sage@inktank.com> - 09:44 PM devops Bug #7879 (Resolved): sentry-db is down
- Migration complete!
- 09:38 PM Bug #7927 (Duplicate): Removed pools still show up in "ceph pg dump" output
- Duplicate #7912
This should be fixed as of commit 70d2e1353ecb9d31a394fdac333dbb0de93339d3. - 09:32 PM Bug #7927 (Duplicate): Removed pools still show up in "ceph pg dump" output
Creating new pools 3 and 4 then removing them leaves them behind in ceph pg dump output. Minutes later it is still...- 09:12 PM Revision e44f85ce (ceph): qa/workunits/cephtool/test.sh: test 'osd pg-temp ...'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:12 PM Revision 2d4ec6a1 (ceph): mon/OSDMonitor: clear primary_temp on osd pg_temp updates
- Until the OSD and the MOSDPGTemp messages encode primary_temp updates,
assume that any pg_temp update will clear prim... - 09:12 PM Revision 255f8404 (ceph): OSDMonitor: add 'mon osd allow primary temp' bool option
- By default, we don't send out maps with primary_temp mappings because
there is no infrastructure in place that would ... - 09:12 PM Revision 63ac0793 (ceph): OSDMonitor: add 'osd primary-temp ...' command
- ceph osd primary-temp <pgid> [<osd>]
Examples:
ceph osd primary-temp 0.2 4 # set primary_temp mapping for 0.2 to os... - 09:11 PM Revision 07dcffa1 (ceph): OSDMonitor: add 'osd pg-temp ...' command
- ceph osd pg-temp <pgid> [<osd1> [<osd2> ...]]
Examples:
ceph osd pg-temp 0.2 0 1 2 # set pg_temp mapping for 0.2 to... - 09:05 PM Revision d3183e31 (ceph): java/test: ceph.file.layout xattr is still not there now
- b8ea65694faf59f12f285a65dc21753dab20ba11 tried to fix this, but
missed a spot.
Signed-off-by: Greg Farnum <greg@inkt... - 07:40 PM Revision 880e6ea3 (ceph): Merge pull request #1567 from ceph/wip-7849
- ceph-conf: don't create log files
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:36 PM Revision d474332e (ceph): Merge pull request #1570 from dachary/wip-gitignore
- .gitignore: add examples/librados files
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:35 PM Revision cd1a9c49 (ceph): Add ceph-client-debug and jerasure shared objects to RPM spec file.
- 05:42 PM Revision 81853c61 (ceph): mon/PGMap: clear pool sum when last pg is deleted
- Use the x.0 pg as a sentinel for the existence of the pool. Note that we
have to clean in up two paths: apply_incrme... - 05:18 PM Revision b3ffce87 (ceph): Merge pull request #1572 from ceph/wip-ec-profile-idempotent
- mon: make 'ceph osd erasure-code-profile set ...' idempotent
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:01 PM Revision 8c761c47 (ceph): mon: make 'ceph osd erasure-code-profile set ...' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:54 PM Revision d258fcce (ceph): osd: do not send peering messages during init
- Do not send any peering messages while we are still working our way
through init().
Fixes: #7093
Signed-off-by: Sage... - 04:34 PM Revision a536fd13 (ceph): krbd, kcephfs: trash osd primary-affinity
- libceph.ko support is in testing and should be in 3.15. This commit
effectively reverts commit 66ffaa65657b ("kcephf... - 04:16 PM rbd Bug #6257 (Fix Under Review): rbd: cp on sparse image allocates objects in dest
- Flatten ignores empty objects since commit:bfa106694dc4db97f58c623eafc3c2d0f9a8bff1, which is in dumpling and emperor...
- 04:14 PM Revision 7d321d8a (ceph): qa/workunits/rados/test_alloc_hint: fix erasure syntax
- This changed recently.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:55 PM Bug #7917: "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Looks like the same issue on
os_type: rhel
os_version: '6.5'
Los are in http://qa-proxy.ceph.com/teuthology/teuth... - 09:15 AM Bug #7917 (Resolved): "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 03:19 PM Bug #7926 (Resolved): "[ERR] scrub 45.0" in upgrade:dumpling-x:parallel-firefly-distro-basic-vps ...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 02:59 PM Bug #7912 (Resolved): Wrong pool count when using "ceph -s" and "ceph -w"
- 05:36 AM Bug #7912 (Resolved): Wrong pool count when using "ceph -s" and "ceph -w"
- Hi,
running ceph version 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
I created a bunch of pools and delet... - 02:58 PM devops Feature #7925 (Rejected): Feature: create new download.ceph.com site
- See https://docs.google.com/a/inktank.com/document/d/1K8pUEZpN5-t1wd0t81MXgooB1Xz_Cgi4jkvo25dysiU/edit
- 02:57 PM Revision 4efb57d3 (ceph): Provide real error messages for unfound (sub)tasks
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:57 PM Messengers Bug #7888 (Pending Backport): msgr: keepalive is insufficient
- 02:27 PM Revision 995e055b (ceph): Merge pull request #1571 from kotnik/docufix
- Small glossary typo fix
Reviewed-by: Loic Dachary <loic@dachary.org> - 02:24 PM Revision 2826fdad (ceph): doc: fix typos in glossary
- 02:21 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- After the additional logging directives were added and osd.0 was restarted, it quickly crashed again. Here is the log...
- 01:55 PM Bug #7922 (Resolved): osd: multi-backfill reservation does not release on reject
- Several OSDs are crashing quite frequently with this error, at least on version 0.77 and 0.78 (possibly earlier as we...
- 02:15 PM rbd Bug #7577 (Resolved): rbd info displays extra random char in block prefix
- 02:03 PM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- Looking at the first failure:
- PGPool::cached_removed_snaps is empty
- info.purged_snaps = 1~1
hence the fail... - 09:10 AM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154663
- 09:07 AM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154509
- 09:06 AM Bug #7915 (Duplicate): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154635...
- 01:56 PM rbd Feature #7924 (Closed): Openstack: make long-running operations async in cinder
- - deleting an image takes a long time, and blocks cinder-volume
from doing anything else during that time
... - 01:55 PM rbd Feature #7923 (Resolved): Openstack: backup from in-use volume instead of from detached volume
- Currently, you can take a backup of a detached volume and send to a Swift/RBD backend.
We want to be able to take ba... - 01:55 PM Bug #7804 (Duplicate): backfill racing with a hitset object remove
- 01:55 PM Bug #7893 (Duplicate): osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- 09:16 AM Bug #7893: osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154529
- 01:55 PM Bug #7894 (Duplicate): osd: missing hitset object in cluster log
- 01:51 PM rbd Feature #7921 (Resolved): Openstack: live migration for ephemeral volumes
- - live migration for rbd ephemeral disks
- live migration can easily be truly live with shared storage
- easier mai... - 01:50 PM rbd Feature #7920 (Resolved): Openstack: cloning for rbd ephemeral disks
- As per https://blueprints.launchpad.net/nova/+spec/rbd-clone-image-handler
- 12:42 PM Bug #7849 (Resolved): ceph-conf create empty log files
- commit:fc1a424e837bee139726eec333c9efd65e2abb6a
- 09:39 AM Bug #7849: ceph-conf create empty log files
- Josh - please review the wip branch
- 11:58 AM Linux kernel client Feature #3837: krbd: support format 2 striping
- 10:54 AM Bug #7875: osd: pg_pool_t hitset fields incompat
- If you have a mix of OSDs tracking hitsets in the cluster, your data tracking isn't going to make any sense...what di...
- 10:39 AM Fix #7919 (Resolved): mon: prevent clients with a read cap from reading the full keyring
- From the mailing list thread "[ceph-users] Security Hole?"...
- 09:45 AM Bug #7626 (Closed): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- as far as I can tell, Sage is right. Nothing else seems off. Closing the ticket.
- 02:11 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Jasper Siero wrote:
> I updated all nodes to -0.88- 0.78 and removed the monitor and created a new one ;-)
- 02:10 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- I updated all nodes to 0.88 and removed the monitor and created a new one
- 09:36 AM devops Bug #7918 (Won't Fix): Mon hangs at start after upgrading to leveldb-1.12.0-3.fc18.x86_64 from th...
- I had a working 0.72.2 installation using the standard Fedora 18 RPMs.
I upgraded leveldb from 1.7.0-4.fc18 to 1.1... - 09:33 AM Bug #7908 (Resolved): "osd.3 ... [ERR] scrub" in upgrade:dumpling-x:parallel-firefly-distro-basic...
- 09:30 AM Revision 7fa025e3 (ceph): .gitignore: add examples/librados files
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:09 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491
- 09:03 AM Bug #7914 (Resolved): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length f...
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154379...
- 09:09 AM Bug #7916 (Can't reproduce): ceph_test_rados got ENOENT on ec pool + thrashing
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154424
- 08:58 AM Bug #7776: client lockdep crash
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154676
03/30/2014
- 04:20 PM Revision f89e992f (ceph): Merge pull request #1564 from dachary/wip-erasure-code-doc
- doc: updates to the erasure code development docs
Reviewed-by: Sage Weil <sage@inktank.com> - 04:17 PM Revision f60ce297 (ceph): Merge pull request #1568 from dachary/wip-jerasure-warnings
- erasure-code: update jerasure / gf-complete submodules
Reviewed-by: Sage Weil <sage@inktank.com> - 04:16 PM Revision ffcbeb46 (ceph): Merge pull request #1569 from dachary/wip-ssse3
- autotools: s/ssse3/sse3/ typo
Reviewed-by: Sage Weil <sage@inktank.com> - 03:57 PM Revision 14418a29 (ceph): autotools: s/ssse3/sse3/ typo
- Reported-by: Justin Erenkrantz <justin@erenkrantz.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:33 AM Revision 1c92453f (ceph): erasure-code: update jerasure / gf-complete submodules
- For compilation warning patches.
http://tracker.ceph.com/issues/7909 Fixes #7909
Signed-off-by: Loic Dachary <loic@... - 09:17 AM Bug #7909 (Resolved): warnings during gf-complete/jerasure build
- 04:33 AM Bug #7909: warnings during gf-complete/jerasure build
- "work in progress":https://github.com/ceph/ceph/pull/1568 cherry pick of the above pending pull requests
- 01:25 AM Bug #7909 (In Progress): warnings during gf-complete/jerasure build
- * https://bitbucket.org/jimplank/gf-complete/pull-request/12/fix-void-arithmetic-compilation-warning
* https://bitbu... - 08:31 AM Revision d5973aaf (ceph): doc: update jerasure plugin
- * The parameters come from the erasure code profile
* Add a note about the upstream submodules gf-complete / jerasure... - 08:31 AM Revision ff51d3ff (ceph): doc: pgbackend dev doc outdated notice
- * Warn the reader that the implementation is ahead and may differ
* Update the links to the Firefly branch
* Remove l... - 08:31 AM Revision 402e1047 (ceph): doc: erasure code developer notes updates
- Update the introduction to explain erasure code profiles. Remove
obsolete explanations about partial writes etc. Remo... - 05:40 AM Revision 74fa3a78 (ceph): fuse: implement 'access' low level function
- Add an empty 'access' function to fuse low level functions. This
allow us to use ceph-fuse with fuse_default_permissi... - 05:28 AM Revision e672c52b (ceph): osd/ReplicatedPG: fix cache tier scrub again
- This condition was flipped from commit eb71924ea27e78d97bd45674ef5e6a7f
and the test case in c3292e48483d861148322590... - 05:27 AM Revision ea47b4a8 (ceph): ceph_test_rados_api_tier: improve promote+scrub test
- We need to have multiple clones with some different patterns of
missing-ness.
Signed-off-by: Sage Weil <sage@inktank... - 05:00 AM Revision 98551fc7 (ceph): global: separate first half of global_init into global_pre_init
- The pre_init now captures enough to create the g_ceph_context and parse
and initialize the in-memory config. However... - 05:00 AM Revision fc1a424e (ceph): ceph-conf: use global_pre_init to avoid starting logging
- This avoids starting up logging, which is not appropriate when we are
examining the config state and not actually sta... - 04:27 AM Revision 5019a151 (ceph): Merge pull request #1520 from ceph/wip-multimds
- Wip multimds
Reviewed-by: Sage Weil <sage@inktank.com> - 12:28 AM Revision 90e1e719 (ceph): Merge pull request #1563 from dachary/wip-sse-i386
- erasure-code: do not attempt to compile SSE4 on i386
Reviewed-by: Sage Weil <sage@inktank.com>
03/29/2014
- 11:58 PM Revision c3292e48 (ceph): ceph_test_rados_api_tier: improve cache tier + scrub test
- Create lots of objects and make *some* of them be missing clones but not
all.
Signed-off-by: Sage Weil <sage@inktank... - 11:57 PM Revision cfd6f23a (ceph): osd/ReplicatedPG: tolerate trailing missing clones on cache tiers
- I missed this case in eb71924ea27e78d97bd45674ef5e6a7fce30932f.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:52 PM Bug #7849 (Fix Under Review): ceph-conf create empty log files
- 09:39 PM Bug #7909 (Resolved): warnings during gf-complete/jerasure build
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-saucy-amd64-basic/log.cgi?log=c3292e48483d861148322590ea1f05...
- 09:27 PM Revision 040abd75 (ceph): qa/workunits/fs/misc/layout_vxattrs: ceph.file.layout is not listed
- As of 08a3d6bd428c5e78dd4a10e6ee97540f66f9729c. A similar change was made
in the kernel.
Signed-off-by: Sage Weil <... - 09:25 PM Revision b8ea6569 (ceph): java/test: ceph.file.layout xattr is not there now
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:23 PM Revision 4f9f7f87 (ceph): qa/workunits/fs/misc/layout_vxattrs: ceph.file.layout is not listed
- As of 08a3d6bd428c5e78dd4a10e6ee97540f66f9729c. A similar change was made
in the kernel.
Signed-off-by: Sage Weil <... - 09:12 PM Bug #7908 (Resolved): "osd.3 ... [ERR] scrub" in upgrade:dumpling-x:parallel-firefly-distro-basic...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 04:59 PM Bug #7907 (Resolved): osd: rollback to head didn't mark_unrollbackable
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-28_22:35:22-upgrade:dumpling-x:stress-split-firefl...
- 04:39 PM Revision f895d16c (ceph): valgrind.supp: be less picky about library versions
- ...so that this works on trusty
Signed-off-by: Sage Weil <sage@inktank.com> - 04:20 PM Revision 74f3827f (ceph): Merge pull request #1548 from ceph/wip-7880
- mds: properly propagate dirty dirstat to auth inode
Reviewed-by: Sage Weil <sage@inktank.com> - 04:18 PM Bug #7744: osd: assert(last_e.version.version < e.version.version)
- Two of my osds are crashing with the same signature:
osd/PGLog.cc: 672: FAILED assert(last_e.version.version < e.v... - 01:41 PM Revision b71e64dd (ceph): mds: find approximal bounds when adjusting subtree auth
- When finishing exporting a subtree, the exporter MDS drops locks and
sends MExportDirFinish message to the importer M... - 10:25 AM Revision fd28ad55 (ceph): doc: erasure-code development complete
- remove the note explaining that it is not yet available.
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:34 AM Revision 399de24e (ceph): erasure-code: do not attempt to compile SSE4 on i386
- SSE4 are only not availabe on older CPUs. Although the compiler could
probably generate the code, there is no point i... - 09:19 AM CephFS Bug #7880 (Resolved): multimds: directory gets rsynced twice
- 05:28 AM Subtask #7548 (Resolved): Basic docs for Erasure Coding
- 01:25 AM Revision 07ccc4e7 (ceph): mds: commit new dirfrag before splitting it
- Commit 6e013cd6 (properly set COMPLETE flag when merging dirfrags)
tries solving the issue that new dirfrag's COMPLET... - 01:13 AM Revision 8f5e92dd (ceph): Merge pull request #1562 from onlyjob/debian
- init: fix OSD startup issue
Reviewed-by: Sage Weil <sage@inktank.com> - 01:11 AM Revision 780fa91c (ceph): Revert "ceph-conf: do not log"
- This reverts commit acc31e75a3e7115c00f9980609948455e3b2d49e.
- 01:11 AM Revision b5a63207 (ceph): Revert "ceph-conf: no admin_socket"
- This reverts commit 72715b235a0daee7ab8e5cd3ab6e415de2939df9.
This breaks the ceph cli, which uses ceph-conf --show-... - 01:06 AM Revision 44afc233 (ceph): init: fix OSD startup issue
- On machines with MON and OSDs (on boot) OSDs started shortly after MON startup
but MON needs time to become opration... - 01:01 AM Revision f5aa492a (ceph): Merge pull request #1519 from ceph/wip-6951-dumpling
- rgw: reset objv tracker on bucket recreation
- 12:56 AM Revision fd76fec5 (ceph): rbd.cc: tolerate lack of NUL-termination on block_name_prefix
- Fixes: #7577
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:20 AM Revision bd6e35c1 (ceph): rbd.cc: yes, cover formatted output as well. sigh.
- Fixes: #7577
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:19 AM Revision fab374b0 (ceph): Merge pull request #1552 from ceph/wip-7902
- osd/PG: fix choose_acting revert to up case
Reviewed-by: Samuel Just <sam.just@inktank.com> - 12:02 AM Revision fef70cbb (ceph): Merge pull request #1559 from ceph/wip-7881-dumpling
- Wip 7881 dumpling
Reviewed-by: Sage Weil <sage@inktank.com>
03/28/2014
- 11:59 PM Revision 66c1ef45 (ceph): Merge pull request #1560 from ceph/wip-7903
- Wip 7903
Reviewed-by: Sage Weil <sage@inktank.com> - 11:49 PM Revision 80e0a0a8 (ceph): mon/MonClient: use keepalive2 to verify the mon session is live
- Verify that the mon is responding by checking the keepalive2 reply
timestamp. We cannot rely solely on TCP timing ou... - 11:49 PM Revision 87232183 (ceph): msgr: add KEEPALIVE2 feature
- This is similar to KEEPALIVE, except a timestamp is also exchanged. It is
sent with the KEEPALIVE, and then returned... - 11:49 PM Revision a2f0974f (ceph): Pipe: rename keepalive->send_keepalive
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit 38d4c71a456c1cc9a5044dbcae5378836a34484d) - 11:17 PM Revision cb699f6a (ceph): rados/monthrash: shorten mon pings so that freezing triggers reconnects
- This exercises (tho it doesn't necessarily verify) the mon ping reconnect
code when the thrasher freezes the mons.
S... - 11:09 PM Revision d747d79f (ceph): msgr: add KEEPALIVE2 feature
- This is similar to KEEPALIVE, except a timestamp is also exchanged. It is
sent with the KEEPALIVE, and then returned... - 11:09 PM Revision 056151a6 (ceph): mon/MonClient: use keepalive2 to verify the mon session is live
- Verify that the mon is responding by checking the keepalive2 reply
timestamp. We cannot rely solely on TCP timing ou... - 11:01 PM Revision 3a66e291 (ceph): Merge pull request #1558 from ceph/wip-7837
- ReplicatedPG: include pending_attrs when reseting attrs in WRITEFULL
Reviewed-by: Sage Weil <sage@inktank.com> - 10:57 PM Revision 1aa1d938 (ceph): ReplicatedPG: hit_set_setup, agent_setup, skip if !active
- We call these in on_activate and on_pool_change. In the former, we are
necessarily active. In the latter, we only w... - 10:56 PM Revision 881bd36a (ceph): client: pin Inode during readahead
- Make sure the Inode does not go away while a readahead is in progress. In
particular:
- read_async
- start a re... - 10:56 PM Revision dbfb993c (ceph): osdc/ObjectCacher: call read completion even when no target buffer
- If we do no assemble a target bl, we still want to return a valid return
code with the number of bytes read-ahead so ... - 10:48 PM Revision 9bfbce30 (ceph): client: pin Inode during readahead
- Make sure the Inode does not go away while a readahead is in progress. In
particular:
- read_async
- start a re... - 10:48 PM Revision 23244557 (ceph): osdc/ObjectCacher: call read completion even when no target buffer
- If we do no assemble a target bl, we still want to return a valid return
code with the number of bytes read-ahead so ... - 10:34 PM Revision f443ff30 (ceph): PGLog: remove obsolete assert in merge_log
- This assert assumes that if olog.head != log.head, olog contains
a log entry at log.head, which may not be true since... - 10:34 PM Revision 636e53c0 (ceph): PGLog: on split, leave log head alone
- This way last_update doesn't go backwards.
Fixes: 6447
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry pic... - 10:08 PM Revision 1af95e7b (ceph): Merge pull request #1557 from ceph/wip-7867
- client: fix assert(!unclean) due to readahead vs close race
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:55 PM Revision f1c7b4ef (ceph): client: pin Inode during readahead
- Make sure the Inode does not go away while a readahead is in progress. In
particular:
- read_async
- start a re... - 09:55 PM Revision 032d4ec5 (ceph): osdc/ObjectCacher: call read completion even when no target buffer
- If we do no assemble a target bl, we still want to return a valid return
code with the number of bytes read-ahead so ... - 09:07 PM Revision c166215d (ceph): Merge pull request #1553 from ceph/wip-7874
- ReplicatedPG: disable clone subsets for cache pools
Reviewed-by: Sage Weil <sage@inktank.com> - 09:06 PM Revision 3c18fad4 (ceph): Merge pull request #1554 from ceph/wip-7828
- ReplicatedPG:: s/_delete_head/_delete_oid, adjust head_exists iff is_hea...
Reviewed-by: Sage Weil <sage@inktank.com> - 09:05 PM Revision decbe2c0 (ceph): Merge pull request #1555 from ceph/wip-7835
- ReplicatedPG::make_writeable: fill in ssc on clone
Reviewed-by: Sage Weil <sage@inktank.com> - 09:05 PM Revision 68dc0c6b (ceph): rgw: move max_chunk_size initialization
- RGWRados::initialize() is not called when doing
RGWRados::get_raw_storage_provider(). This was the culprit for issue
... - 08:27 PM Revision a6be1d67 (ceph): PG: always clear agent_state in clear_primary_state
- We aren't actually active between activate() and all_activated_committed().
We'd have to suspend agent_work during th... - 08:25 PM Revision dfd3cb51 (ceph): rgw: only look at prefetched data if we actually prefetched
- Fixes: #7903
Since we didn't prefetch data then we couldn't rely on the data to
actually exist there. In that case ju... - 08:25 PM Revision 80c5b4ce (ceph): Merge pull request #1517 from ceph/wip-7805
- PG: only complete replicas should count toward min_size
Reviewed-by: Sage Weil <sage@inktank.com> - 08:10 PM Revision d78e6788 (ceph): osd/PG: fix choose_acting revert to up case
- If we decide to revert back to up, we need to
1- return false, so that we go into the NeedActingChange state, and
2-... - 07:11 PM rbd Bug #6480 (In Progress): librbd crashed qemu-system-x86_64
- Mike provided a core dump in which structures appear to be normal, though it's hard to tell with the ceph::buffer::ra...
- 06:31 PM Bug #7849: ceph-conf create empty log files
- Socket part was introduced later -- perhaps only socket part shall be reversed?
Log-related change seems safe...
- 06:05 PM Bug #7849 (In Progress): ceph-conf create empty log files
- oops, the previous fix breaks ceph.py, which does ceph-conf --show-config-value to get admin_socket.
- 06:08 PM Revision 71fa779e (ceph): mds: don't clear scatter dirty when cache rejoin ack is received
- The auth mds has received dirty scatterlock state. But it hasn't
journaled the dirty state yet. The log segment that ... - 06:08 PM Revision ce936161 (ceph): mds: fix stack overflow caused by nested dispatch
- Commit bc3325b37 fixes a stack overflow bug happens when replaying
client requests. Similar stack overflow can happen... - 06:08 PM Revision 34ef91a2 (ceph): mds: fix negative dirstat assertion
- When splitting dirfrag, delta dirstat is always added to the first new
dirfrag. Before the delta dirstat is propagate... - 06:08 PM Revision 79aa26ff (ceph): mds: allow sending MMDSFindIno to MDS who is in clientreplay state
- Because MDCache::kick_find_ino_peers() is called when a MDS enters
clientreplay state.
Signed-off-by: Yan, Zheng <zh... - 06:08 PM Revision 367987fa (ceph): mds: don't increase nlink when rollback stray reintegration
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision 90b4e53c (ceph): mds: include authority of the overwrited inode in rename witnesses
- Rename operation needs to adjust the overwrited inode's link count.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 06:08 PM Revision 0bb911c6 (ceph): mds: don't trim non-auth root inode/dirfrag
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision 6963a8f9 (ceph): mds: handle interaction between slave rollback and fragmenting
- For slave rename and rmdir events, the MDS needs to preserve non-auth
dirfrag where the renamed inode originally live... - 06:08 PM Revision ffcbcdd6 (ceph): mds: handle race between cache rejoin and fragmenting
- MDCache::handle_cache_expire() ignores mismatched dirfrags. this is
OK during normal operation because MDS doesn't tr... - 06:08 PM Revision e535f7f2 (ceph): mds: avoid journaling non-auth opened inode
- Exporting inode has AUTH bit set while EExport event is being
journaled.
Signed-off-by: Yan, Zheng <zheng.z.yan@inte... - 06:08 PM Revision 6a548a97 (ceph): mds: fix CDir::WAIT_ANY_MASK
- make sure CDir::WAIT_ANY_MASK include MDSCacheObject::WAIT_UNFREEZE
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 06:08 PM Revision e811b07e (ceph): mds: properly journal fragment rollback
- If dirfrags are subtree roots, mark the dirfragtreelock as scattered
dirty, otherwise journal the dirfragtree change.... - 06:08 PM Revision 3c6c7124 (ceph): mds: trim non-auth inode with remote parents
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision 598c5f18 (ceph): mds: trim empty non-auth dirfrags
- Fragmenting a non-auth dirfrag results several smaller dirfrags. Some
of the resulting dirfrags can be empty, which a... - 06:08 PM Revision a1f5c645 (ceph): mds: don't trim ambiguous import dirfrags
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision 1bd575e2 (ceph): mds: fix CInode::get_approx_dirfrag
- return NULL if there is no opened dirfrag
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 06:08 PM Revision ed49d5ef (ceph): mds: journal EFragment::OP_COMMIT before drop locks
- Dropping locks can dispatch other requests. These request can submit
log entry.
Signed-off-by: Yan, Zheng <zheng.z.y... - 06:08 PM Revision fb19100f (ceph): mds: fix null pointer dereference in MDCache::rejoin_send_rejoins()
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision d14ec95e (ceph): mds: skip non-opened session when flushing client sessions
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:08 PM Revision fbf4fbc3 (ceph): mds: explicitly set nonce for imported dirfrag
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:28 PM Revision 9f3a6644 (ceph): rgw_pool_type: remove accidentally added empty file
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 05:23 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Yes, I'm pretty sure it is.. this bug affected 0.77 and was fixed for 0.78. If I remember correctly, the full osdmap...
- 05:20 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- This sounds like it could be commit:14ea8157eb2883b9f53c234044fe002153212ef8
- 10:18 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- The store attached to the ticket shows the latest 7 full osdmaps as being unable to be decoded, which would explain t...
- 05:18 PM Bug #7902 (Pending Backport): osd/PG.cc: 6803: FAILED assert(!pg->actingbackfill.empty())
- 12:54 PM Bug #7902 (Resolved): osd/PG.cc: 6803: FAILED assert(!pg->actingbackfill.empty())
- this a split dumpling/firefly cluster
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-27_22:35:2... - 05:17 PM Bug #7881 (Resolved): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info...
- 03:37 PM Bug #7881: osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info.last_update))
- 03:16 PM Bug #7881 (In Progress): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == i...
- 09:52 AM Bug #7881: osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info.last_update))
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-27_22:35:20-upgrade:dumpling-x:stress-split-firefly...
- 04:58 PM rgw Bug #7903 (Resolved): radosgw-admin: failing to set default region
- 01:27 PM rgw Bug #7903 (Fix Under Review): radosgw-admin: failing to set default region
- 12:59 PM rgw Bug #7903 (Resolved): radosgw-admin: failing to set default region
- http://pulpito.ceph.com/teuthology-2014-03-27_23:00:17-rgw-firefly-distro-basic-plana/149617/
- 04:00 PM rgw Bug #7837 (Resolved): s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- 03:56 PM CephFS Bug #7867 (Resolved): client/Client.cc: 2087: FAILED assert(!unclean)
- 03:47 PM CephFS Bug #7867 (Pending Backport): client/Client.cc: 2087: FAILED assert(!unclean)
- 03:52 PM Bug #7906 (Duplicate): "adjust-ulimits ... --rgw-region zero'''" filed in rgw-firefly-distro-basi...
- Duplicates #7903
- 03:36 PM Bug #7906 (Duplicate): "adjust-ulimits ... --rgw-region zero'''" filed in rgw-firefly-distro-basi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-27_23:00:17-rgw-firefly-distro-basic-plana/149644/...
- 03:23 PM Revision 0dcb54f7 (ceph): Merge pull request #1549 from dachary/wip-doc
- doc: fix typos in tiering dev doc
- 02:07 PM Bug #7874 (Resolved): clone_range from clone on recovery fails if clone has been evicted
- 02:05 PM Bug #7828 (Resolved): osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_sn...
- 02:05 PM Bug #7835 (Resolved): make_writeable needs to fill in ssc on new clone
- 01:25 PM Bug #7805 (Resolved): emperor can go active with < min_size non-incomplete peers since we check a...
- 01:21 PM Bug #7904 (Resolved): osd/ReplicatedPG.cc: 10661: FAILED assert(is_active())
- We need to dump agent_state even on primary->primary
-69> 2014-03-28 13:07:10.884747 7fdc1660b700 15 journal pr... - 01:02 PM Revision 72eaa5e8 (ceph): doc: fix typos in tiering dev doc
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:43 AM Fix #7890: erasure-code: last stripe is not truncated
- At present, this is by design.
- 01:05 AM Fix #7890 (New): erasure-code: last stripe is not truncated
- When encoding a 10 bytes object with osd_pool_erasure_code_stripe_width = 2048 and k=2 + m=1, the last strip should b...
- 10:05 AM rbd Feature #7895 (Resolved): krbd: test cloning, discard, plus regular I/O via fsx
- This could be another fork of src/test/librbd/fsx.c in ceph.git, or modifications to it to abstract out the I/O more ...
- 09:21 AM Bug #7894 (Duplicate): osd: missing hitset object in cluster log
- failure_reason: '"2014-03-27 16:02:47.849800 osd.4 10.214.131.17:6800/13622 33 : [ERR]
4.0 shard (4,255) missing 0... - 09:20 AM Bug #7893 (Duplicate): osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- ...
- 09:19 AM Bug #7892 (Duplicate): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.le...
- ...
- 09:18 AM Bug #7891 (Resolved): osd: leaked pg refs on shutdown
- ...
- 08:53 AM Bug #5884: negative num_objects_degraded in pool stats
- Oops, replace 1.3 with 1.30 in previous message....
- 08:50 AM Bug #5884: negative num_objects_degraded in pool stats
Seen on a cluster that's been running for the past 2 weeks on the firefly branch.
Potentially noteworthy things ...- 08:25 AM CephFS Bug #7780 (Resolved): When full flag is set, even MDS writes are blocked
- Fix was merged at c647a03fffb2e1e997dbdb0ff128eeb6efc47deb
- 05:24 AM Revision 1b5e8f43 (ceph): mds: properly propagate dirty dirstat to auth inode
- Propagate dirty dirstat to freezing auth inode if the inode is
already auth pinned by the Mutation. Otherwiese the di... - 12:58 AM Revision 5651ee81 (ceph): upgrade/dumpling-x/parallel: restart after cuttlefish->dumpling upgrade
- Fixes: #7824
Signed-off-by: Sage Weil <sage@inktank.com> - 12:22 AM Revision dfdeb5c3 (ceph): radosgw-agent: coerce max-entries config to a string
- This is necessary to pass it as a command line argument.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 12:14 AM Revision 7f4be9e9 (ceph): Merge pull request #1547 from ceph/wip-cache-scrub
- osd: improve scrub checks on clones; tolerate missing clones on cache pools
Fixes: #7885
Reviewed-by: Samuel Just <s...
03/27/2014
- 11:45 PM Revision 38d4c71a (ceph): Pipe: rename keepalive->send_keepalive
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:39 PM Revision 7a1990b6 (ceph): Merge branch 'wip-7875'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 11:39 PM Revision c64d03d0 (ceph): mon/OSDMonitor: require OSD_CACHEPOOL feature before using tiering feat...
- The OSDs need to support this feature before we allow users to turn it
on. This is similar to what the erasure pool ... - 11:38 PM Revision 69321bf5 (ceph): mon/OSDMonitor: prevent setting hit_set unless all OSDs support it
- We are using OSD_CACHEPOOL as a proxy for the support for the tiering
OSDMap infrastructure.
Signed-off-by: Sage Wei... - 10:26 PM CephFS Bug #7880: multimds: directory gets rsynced twice
- 06:54 AM CephFS Bug #7880 (Resolved): multimds: directory gets rsynced twice
- probalby the mtime doesn't get set properly teh first time?...
- 10:12 PM Revision eb71924e (ceph): osd/ReplicatedPG: tolerate missing clones in cache pools
- A few cases:
- As we are working through the list, if we see a clone that is lower than
the next one we were expec... - 10:00 PM Revision 6508d5ef (ceph): osd/ReplicatedPG: improve clone vs head checking
- - notice when we are missing a clone (that isn't at the end of the list)
- notice when we are missing a clone on the ... - 09:31 PM Messengers Bug #7888: msgr: keepalive is insufficient
- wip-7888 handles this for MonClient. We can do the same with Objecter, but this is less critical because we will fin...
- 09:24 PM Messengers Bug #7888 (Fix Under Review): msgr: keepalive is insufficient
- 06:01 PM Messengers Bug #7888 (In Progress): msgr: keepalive is insufficient
- 04:44 PM Messengers Bug #7888 (Resolved): msgr: keepalive is insufficient
- the current keepalive behavior relies on writes triggering a tcp timeout/error, which does not actually happy in many...
- 08:48 PM Revision 9e2cd5fe (ceph): osd/ReplicatedPG: do not assert on clone_size mismatch
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:28 PM Revision 7f026ba6 (ceph): ceph_test_rados_api_tier: scrub while cache tier is missing clones
- Trigger a scrub to verify that we can handle a cache tier that is missing
some clones. We rely on the test harness t... - 08:01 PM Revision c5682e78 (ceph): Merge pull request #1546 from ceph/wip-fix-pools
- fix pool ops test
- 07:57 PM Revision 7cb1d3a4 (ceph): qa/workunits/mon/pool_ops.sh: fix test
- The pool create command doesn't take k/v pairs any more.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:56 PM Revision 233801c6 (ceph): qa/workunits/mon/pool_ops.sh: use expect_false
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:35 PM Revision ce59760a (ceph): Merge pull request #1545 from ceph/wip-7849-b
- ceph-conf: do not log
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:30 PM Revision 72715b23 (ceph): ceph-conf: no admin_socket
- We don't need to worry about pidfile because that is done by the fork
functions, which ceph-conf doesn't call.
Signe... - 07:03 PM Revision e91f5c8c (ceph): Merge pull request #1522 from themgt/patch-1
- document adding dev key for custom Apache/FCGI install
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:51 PM Revision 68343ee1 (ceph): rados/thrash/workloads: make cache-agent-big use an ec base pool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:41 PM Revision fb208237 (ceph): jerasure: fix up .gitignore
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:36 PM Revision acc31e75 (ceph): ceph-conf: do not log
- If you are querying the conf for an osd and it has a log configured, we
should not generate any log activity.
This i... - 06:33 PM Revision 3f1417a8 (ceph): Merge pull request #1542 from onlyjob/debian
- logrotate: do not rotate empty logs (2nd logrotate file)
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:15 PM Revision e21561e7 (ceph): Merge pull request #1544 from ceph/wip-7876
- rgw: use s->content_length instead of s->length
Reviewed-by: Sage Weil <sage@inktank.com> - 06:14 PM Revision 9f313109 (ceph): Merge pull request #1534 from dachary/wip-sse-fix
- erasure code sse optimized jerasure plugin
Reviewed-by: Sage Weil <sage@inktank.com> - 06:09 PM Revision 3bbea517 (ceph): Merge pull request #234 from ceph/wip-priority
- schedule_suite: ugly hack to set priority when scheduling
- 05:58 PM Bug #7824 (Resolved): LibRadosList.ListObjectsNS failure
- ugh, the test wasn't restarting after the cuttlefish->dumpling upgrade step.
ceph-qa-suite.git commit 5651ee813170... - 05:53 PM Revision ffd69ab3 (ceph): rgw: use s->content_length instead of s->length
- Fixes: #7876
Need to use the actual content length, not the pointer to the string.
This was probably working because ... - 05:40 PM devops Bug #7889: IPv6 support with ceph-deploy
- socket.gethostbyname supports only ipv4 and should be replaced with socket.getaddrinfo
next the inet_aton is also ... - 05:36 PM devops Bug #7889 (Resolved): IPv6 support with ceph-deploy
- In ceph-deploy/util/arg_validators.py the hostname function fails "hostname: X is not resolvable" if using ipv6
- 05:24 PM Revision b6ad5c6c (ceph): rgw: idle timeout config moves to the external server line
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:21 PM Revision 0935bb61 (ceph): Merge pull request #1540 from ceph/wip-7860
- test: Wait for tier removal before next test starts
Reviewed-by: Sage Weil <sage@inktank.com> - 05:14 PM Bug #7885 (Resolved): scrub must not take offence if evicted/unpromoted clones are missing on a c...
- 11:54 AM Bug #7885: scrub must not take offence if evicted/unpromoted clones are missing on a cache pool
- 11:41 AM Bug #7885 (Resolved): scrub must not take offence if evicted/unpromoted clones are missing on a c...
- 05:13 PM Revision fd6056be (ceph): schedule_suite: ugly hack to set priority when scheduling
- I don't want to add another arg at the end of the very long list of
optional args, so I'll use an environment variabl... - 04:42 PM Revision 501e31d9 (ceph): logrotate: do not rotate empty logs (2nd logrotate file)
- Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
- 04:41 PM Bug #7887 (Resolved): W: shlib-with-executable-stack
- Lintian produced the following warnings after building Debian packages of ceph-0.78:...
- 04:35 PM Revision 158f9ba1 (ceph): Revert "Lines formerly of the form '(remote,) = ctx.cluster.only(role)....
- This reverts commit d693b3f8950ffd1f2492a4db0f8234fee31f00f0.
- 04:35 PM Revision fac452ae (ceph): Revert "Lines formerly of the form '(remote,) = ctx.cluster.only(role)....
- This reverts commit d693b3f8950ffd1f2492a4db0f8234fee31f00f0.
- 04:29 PM Bug #7875 (Resolved): osd: pg_pool_t hitset fields incompat
- 10:40 AM Bug #7875 (In Progress): osd: pg_pool_t hitset fields incompat
- 02:48 PM Documentation #7886 (New): What's the policy on URL stability for public documentation?
- We're trying to decide whether to include links to documentation on ceph.com within the UI of the Calamari product. W...
- 02:02 PM Revision 2d553161 (ceph): Merge pull request #1541 from onlyjob/debian
- logrotate improvement: do not rotate empty logs
Reviewed-by: Sage Weil <sage@inktank.com> - 01:27 PM Revision 91176f14 (ceph): erasure-code: test encode/decode of SSE optimized jerasure plugins
- If the machine running make check has the required CPU features
available, load the SSE optimized plugin and check th... - 01:27 PM Revision cc0cc152 (ceph): erasure-code: gf-complete / jerasure modules updates
- To avoid confusion, the jerasure v1 branch that contains commits pending
review upstream is named v2-ceph and the gf-... - 01:27 PM Revision c07aedb6 (ceph): autotools: intel cpu features detection
- Rename SIMD to INTEL for clarity.
Instead of agregating all flags in INTEL_FLAGS, create individual flags
for each f... - 01:27 PM Revision e9878db2 (ceph): arch: add SSE3, SSSE3, SSSE41 and PCLMUL intel features
- And add a note about valgrind forcing a fake cpuid.
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:27 PM Revision 10fd6b31 (ceph): erasure-code: SSE optimized jerasure plugins
- The jerasure plugin is compiled with three sets of flags:
* jerasure_generic with no SSE optimization
* jerasure_sse... - 01:27 PM Revision 30e71405 (ceph): osd: increase osd verbosity during functional tests
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:27 PM Revision b76ad972 (ceph): erasure-code: test jerasure SSE optimized plugins selection
- Test the selection of the plugin depending on the CPU features. The
prefix of the plugin is "jerasure" by default (je... - 01:26 PM Revision 12d4f382 (ceph): erasure-code: allow loading a plugin from factory()
- The Mutex scope is restricted to only protect the load() method and not
the factory() method. This allows a plugin to... - 01:24 PM Bug #7805 (Fix Under Review): emperor can go active with < min_size non-incomplete peers since we...
- 01:24 PM Bug #7858: agent with snaps ceph_test_rados error
- 12:37 PM Bug #7849 (Resolved): ceph-conf create empty log files
- commit:acc31e75a3e7115c00f9980609948455e3b2d49e
- 11:36 AM Bug #7849 (Fix Under Review): ceph-conf create empty log files
- 11:16 AM Bug #7849: ceph-conf create empty log files
- This should be just a matter of passing the right flags to common_init or global_init
- 11:34 AM Feature #7884 (New): investigate having the messenger (or dispatch q?) in the osd limit the numbe...
- 11:14 AM rgw Bug #7876 (Resolved): rgw: > on char* in rgw_rest_user
- 11:13 AM rgw Bug #7876 (Fix Under Review): rgw: > on char* in rgw_rest_user
- 11:13 AM Bug #7826 (Resolved): osd: illegal instruction in jerasure
- 03:23 AM Bug #7826 (Fix Under Review): osd: illegal instruction in jerasure
- 10:40 AM CephFS Bug #7867: client/Client.cc: 2087: FAILED assert(!unclean)
- 10:37 AM Fix #7560 (Closed): mon: add compat set feature to mark an upgraded pg format in order to disallo...
- The feature was introduced for Dumpling. The only version that does not support it is Cuttlefish, and it will assert...
- 10:20 AM Bug #7860 (Resolved): LibRadosTwoPoolsPP.PromoteSnap failed at line 311
- 08:54 AM Bug #7881 (Resolved): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info...
- mixed dumpling/firefly cluster:...
- 08:54 AM rbd Bug #6628: krbd: BUG during ceph_osdc_stop() sometimes when rbd_add() fails
- 07:18 AM devops Bug #7879: sentry-db is down
- Let's get these services moved over today.
- 06:48 AM devops Bug #7879 (Resolved): sentry-db is down
- 04:44 AM Revision d9a2dea7 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:01 AM Revision b454bd6c (ceph): rgw: add erasure coded data pool variant
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 01:43 AM Revision d693b3f8 (ceph): Lines formerly of the form '(remote,) = ctx.cluster.only(role).remotes....
- and '(remote,) = ctx.cluster.only(role).remotes.iterkeys()' would fail with
ValueError and no message if there were l... - 01:43 AM Revision e98b1073 (ceph): Lines formerly of the form '(remote,) = ctx.cluster.only(role).remotes....
- and '(remote,) = ctx.cluster.only(role).remotes.iterkeys()' would fail with
ValueError and no message if there were l... - 01:12 AM Revision 506d2bba (ceph): logrotate improvement: do not rotate empty logs
- Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
- 12:47 AM Revision dc3ce58a (ceph): osd: do not make pg_pool_t incompat when hit_sets are enabled
- If we enable HitSet tracking, the OSD needs to know this, but clients do
not care. Setting the compat version is too... - 12:43 AM Revision 92859ed6 (ceph): ReplicatedPG: include pending_attrs when reseting attrs in WRITEFULL
- This is necessary for ops like:
2014-03-25 11:48:20.354168 7f0df0ff9700 1 -- 192.168.106.226:0/1016231
--> 192.168.... - 12:24 AM Revision b6a431b1 (ceph): ReplicatedPG: disable clone subsets for cache pools
- To do this properly, we need to take appropriate read
locks on clone sources and handle evicted clones.
Fixes: #7874... - 12:18 AM Revision e84ac3aa (ceph): Merge pull request #1538 from ceph/wip-6910-emperor
- PG: don't query unfound on empty pgs
- 12:18 AM Revision a0a560a9 (ceph): Merge pull request #1539 from ceph/wip-6910-dumpling
- PG: don't query unfound on empty pgs
- 12:16 AM Revision b5702640 (ceph): Merge pull request #1537 from ceph/wip-7871
- RadosModel: allow --no-omap to be specified seperately from --ec-pool
Reviewed-by: Sage Weil <sage@inktank.com> - 12:14 AM Revision ec40196f (ceph): Merge pull request #1536 from ceph/wip-7870
- ReplicatedPG::do_osd_ops: only return ENOTSUP on OMAP write ops
Reviewed-by: Sage Weil <sage@inktank.com>
03/26/2014
- 11:04 PM Revision 56974b91 (ceph): test: Wait for tier removal before next test starts
- Fixes: #7860
Signed-off-by: David Zafman <david.zafman@inktank.com> - 10:51 PM Revision 7999bc9e (ceph): ReplicatedPG:: s/_delete_head/_delete_oid, adjust head_exists iff is_head
- Fixes: #7872
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:49 PM Revision 98654092 (ceph): rgw: configurable chunk size
- Fixes: #7589
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:55 PM Bug #7824 (In Progress): LibRadosList.ListObjectsNS failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-25_19:33:06-upgrade:dumpling-x:parallel-firefly---b...
- 08:24 PM Revision 41d5e9ab (ceph): PG: don't query unfound on empty pgs
- When the replica responds, it responds with a notify
rather than a log, which the primary then ignores since
it is al... - 08:23 PM Revision c6f754c5 (ceph): PG: don't query unfound on empty pgs
- When the replica responds, it responds with a notify
rather than a log, which the primary then ignores since
it is al... - 07:38 PM Feature #7437 (In Progress): EC: add adapt unittest teuthology task and add to nightly
- 07:00 PM CephFS Bug #5787 (Duplicate): client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- 07:00 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- dup #7867
- 06:48 PM Revision f171c93f (ceph): Merge pull request #1535 from ceph/wip-7823
- osd: trim copy-get backend read to object size
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:44 PM Revision 832c007d (ceph): RadosModel: allow --no-omap to be specified seperately from --ec-pool
- Fixes: #7871
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:42 PM Revision 555ae125 (ceph): ReplicatedPG::do_osd_ops: only return ENOTSUP on OMAP write ops
- This way, redirected omap reads will work correctly by returning
empty maps and buffers.
Fixes: #7870
Signed-off-by:... - 06:39 PM Revision 6cb85955 (ceph): ReplicatedPG::make_writeable: fill in ssc on clone
- ssc should always be filled in on live ObjectContexts.
Fixes: #7835
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:37 PM Revision 21fc535e (ceph): osd: trim copy-get backend read to object size
- We are passing a big number to the backend to read and it is trimming it
to the stripe boundary, and then setting the... - 06:09 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- 05:44 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- wip-7837
- 05:28 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- looking
- 06:05 PM rgw Bug #7876 (Resolved): rgw: > on char* in rgw_rest_user
- ...
- 05:57 PM CephFS Bug #7867: client/Client.cc: 2087: FAILED assert(!unclean)
- pushed a simpler version, wip-7867-b, that just pins the Inode* for the duration of the readahead. This avoids a pos...
- 09:13 AM CephFS Bug #7867 (Resolved): client/Client.cc: 2087: FAILED assert(!unclean)
- here is the lsat bit of log, starting with the incomplete readahead that caused the crash...
- 05:54 PM Bug #7875 (Resolved): osd: pg_pool_t hitset fields incompat
- If the hitset fields get used in pg_pool_t the encoding is marked as incompatible. This breaks old clients that don'...
- 05:33 PM Revision 5aa5566b (ceph): Don't explode when finding an empty job
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:27 PM Bug #7874: clone_range from clone on recovery fails if clone has been evicted
- wip-7874 disables clone subsets for cache pools. Testing
- 05:26 PM Bug #7874: clone_range from clone on recovery fails if clone has been evicted
- 05:13 PM Bug #7874 (Resolved): clone_range from clone on recovery fails if clone has been evicted
- Options
1) don't allow clone_range from clone on recovery if cache pool
2) detect when the clone has been evicted a... - 05:26 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- 05:25 PM Feature #7831: OSD: track objects with omap entries and don't count toward caps
- 05:18 PM Bug #6910 (Resolved): don't query empty osds for unfound
- 05:16 PM Revision 859e66b3 (ceph): Merge pull request #232 from ceph/wip-suite-priority
- suite: allow priority to be set
- 05:15 PM Feature #7871 (Resolved): ceph_test_rados: allow no-omap to be specified seperately from ec-pool
- 11:43 AM Feature #7871 (Resolved): ceph_test_rados: allow no-omap to be specified seperately from ec-pool
- 05:13 PM Bug #7870 (Resolved): only return ENOTSUP on omap write ops for EC pools
- 02:04 PM Bug #7870 (Fix Under Review): only return ENOTSUP on omap write ops for EC pools
- 11:39 AM Bug #7870 (Resolved): only return ENOTSUP on omap write ops for EC pools
- This way redirected ops on objects without omap entries will work.
- 05:09 PM Revision 67844e0e (ceph): suite: allow priority to be specified when scheduling
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:59 PM rgw Feature #7589 (Resolved): rgw: configurable chunk size
- commit:98654092fc5a18ef542d294d5696cac86d96229f
- 04:10 PM Bug #7860: LibRadosTwoPoolsPP.PromoteSnap failed at line 311
- 03:47 PM Revision ee217952 (ceph): Merge pull request #1518 from dachary/wip-mailmap
- mailmap updates
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 03:33 PM Bug #7826: osd: illegal instruction in jerasure
- For the record, the illegal instruction was on an AVX instruction. It was part of the flags being set at compile time...
- 09:53 AM Bug #7826: osd: illegal instruction in jerasure
- 03:32 AM Bug #7826 (In Progress): osd: illegal instruction in jerasure
- "work in progress":https://github.com/ceph/ceph/pull/1534
- 02:17 PM Feature #7873 (Resolved): pg query: dump peer_info, peer_missing in all states
- This debug info is useful for recovering from incomplete situations.
- 01:21 PM Bug #7872 (Duplicate): PG: all_unfound_are_queried_or_lost must skip dne replicas
- 01:21 PM Bug #7872: PG: all_unfound_are_queried_or_lost must skip dne replicas
- actually, 6910
- 01:17 PM Bug #7872 (Duplicate): PG: all_unfound_are_queried_or_lost must skip dne replicas
- 11:48 AM Bug #7823 (Resolved): osd: copy-get from ec pool returns wrong size
- 11:22 AM Cleanup #7869 (Resolved): arch: use cpuid.h when possible
- Milosz Tanski <milosz@adfin.com>:
Instead of doing cpuid manually you can use builtins provided in gcc
(and in... - 09:47 AM Bug #7868 (Can't reproduce): "failed to recover before timeout expired" in powercycle-firefly---b...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-23_23:55:02-powercycle-firefly---basic-plana/14419...
- 05:39 AM Revision f1a1ac82 (ceph): Merge remote-tracking branch 'gh/firefly'
- 05:38 AM Revision 29f74202 (ceph): Revert "osd: create the erasure-code ruleset in OSDMap::build_simple"
- This reverts commit b85330eb1d62632a1c3f2025b1f309816d54bd5a.
We can't have this in the OSDMap by default or else al... - 05:38 AM Revision 18c3e9ec (ceph): osd: fix tests due to no default erasure-code ruleset
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:44 AM Revision fbbdbf0a (ceph): Merge pull request #1530 from onlyjob/fix-defaultweight
- fix bug in 'defaultweight' calculation on OSD start.
Reviewed-by: Sage Weil <sage@inktank.com> - 01:32 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Thanks!
- 01:04 AM Revision b2cf052a (ceph): rgw: allow overriding options
- This is mainly useful for toggling ec/replicated pools right now.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 12:15 AM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- We did not get to the bottom of this and the hardware is still available. It's cold but not dead ;-)
03/25/2014
- 11:51 PM RADOS Cleanup #7865 (New): erasure-code: fine grain SSE support
- make use of "ifunc":http://gcc.gnu.org/onlinedocs/gcc-4.7.2/gcc/Function-Attributes.html#index-g_t_0040code_007bifunc...
- 11:48 PM Revision 4cf9a73b (ceph): fix bug in 'defaultweight' calculation on OSD start.
- awk: cmd. line:1: { d=$2/1073741824 ; r = sprintf(\"%.2f\", d); print r }
awk: cmd. line:1: ... - 11:40 PM Revision f57cf56a (ceph): Merge branch 'wip-7676-firefly' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 11:36 PM Revision 3f47f9e7 (ceph): Merge pull request #1533 from ceph/wip-7863-wusui
- Make sure s3_utilities are found.
- 11:30 PM Revision 2779e2ab (ceph): Make sure s3_utilities are found.
- Add FindBin code to rgw/s3 tests to include s3_utilites.pm properly.
Fixes: 7863
Signed-off-by: Warren Usui <warren.... - 10:29 PM Revision b9e29caf (ceph): Merge pull request #1527 from ceph/wip-6465
- be nitpicky about missing references
Reviewed-by: Sage Weil <sage@inktank.com> - 09:59 PM Revision 1234f768 (ceph): Merge pull request #1531 from onlyjob/debian
- minor corrections from Debian
Reviewed-by: Sage Weil <sage@inktank.com> - 09:57 PM Revision f89c0d59 (ceph): rgw: fix ec-data-pool config
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:57 PM Revision 812e48a1 (ceph): radosgw-admin: skip data sync tests when only metadata is configured
- Fixes http://tracker.ceph.com/issues/7818
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:50 PM Revision f250da84 (ceph): Add log statement to find_run_info()
- Sometimes it takes a while.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 08:40 PM Revision b3d0c19f (ceph): Exit gracefully on KeyboardInterrupt
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:38 PM Revision 03974bf5 (ceph): Add --description flag
- Default to not printing job descriptions. Add -d/--description flag to
control that behavior. Change --delete's short... - 08:31 PM Revision a6658fd8 (ceph): s/JOB/PATTERN/
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:29 PM Revision cfe4c8be (ceph): Tweak usage
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:28 PM Revision 4bedc548 (ceph): Correct help text
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:27 PM Revision 381ecea8 (ceph): Fix lots of linter errors
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:11 PM Revision 38bcd3cf (ceph): osd: start_flush() should check for missing clones and return if requested
- Fixes: #7659
Signed-off-by: David Zafman <david.zafman@inktank.com> - 06:11 PM Revision d1d99df2 (ceph): osd: Improve logging output including pg_shard_t as osd#(shard)
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:11 PM Revision ed43aa01 (ceph): osd: Add logging of missed l_osd_agent_skip cases
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:11 PM Revision bf875629 (ceph): osd: Error from start_flush() not checked in agent_maybe_flush()
- This caused a very minor memory leak since ctx was allocated
Include logging of l_osd_agent_skip
Signed-off-by: Davi... - 05:49 PM Revision 83661c27 (ceph): Merge pull request #1363 from ceph/wip-3863
- Add ceph-client-debug inode lookup
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:48 PM rgw Bug #7676 (Resolved): rgw: multi-part upload incompatible with EC backend
- commit:7989cbd418ed8d51348851a39ffa84ac2224f4fe
- 05:17 PM RADOS Feature #7770: "ceph osd crush set" should handle ingestion of non-compiled crush maps
- Stating the obvious: If a user is going to manually modify the crush map, there is always a chance of botching it and...
- 01:11 PM RADOS Feature #7770: "ceph osd crush set" should handle ingestion of non-compiled crush maps
- We probably want a better idea of what they are trying to accomplish.
- 05:03 PM Tasks #7864 (New): please clarify copyright and the license
- Please confirm the licensing information for the following files:
Files: src/test/librbd/fsx.c
Copyright: ??1991,... - 04:44 PM rgw Bug #7818 (Resolved): syncdaemon: error geting op state: list index out of range
- fixed by commit:812e48a14837cc0173a15aafa6fa563bf9fdd6d4 in teuthology.git
- 02:44 PM rgw Bug #7818: syncdaemon: error geting op state: list index out of range
- this actually looks like a test issue after all - trying to run some of the data sync tests across regions
- 04:43 PM rgw Bug #7820 (Resolved): "AssertionError: 404 != 301" in rgw-firefly-distro-basic-plana suite
- fixed by commit:0cb00b1fb9bf6c59d787f340dd50ae16b1473f82 in teuthology.git
- 04:23 PM rgw Bug #7099 (Pending Backport): Strange Comportments with media files
- This one was also already merged, in commit:0427f61544529ab4e0792b6afbb23379fe722de1
- 04:11 PM rgw Bug #7271 (Resolved): container create via swift doesn't register ACL
- This was merged a while ago as commit:bf38bfb2e6511217eaa720811af826fe5498a461
- 04:10 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- One more:...
- 09:05 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- 04:03 PM Feature #7862 (Resolved): allow backfill/recovery while below min_size
- 04:03 PM Feature #7861 (Closed): osd: allow writes on degraded objects
- 03:57 PM Bug #7860 (Resolved): LibRadosTwoPoolsPP.PromoteSnap failed at line 311
This is even before setting up the tiering doing the following sequence:
Create/write "hi there" to object "baz"...- 03:45 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- nvm
- 02:31 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- finish_ctx incorrectly sets head_exists for a clone evict operation.
- 03:36 PM Bug #7858 (Resolved): agent with snaps ceph_test_rados error
- 2014-03-25 15:04:11,699.699 INFO:teuthology.run:Summary data:
{duration: 474.998064994812, failure_reason: 'Command ... - 03:22 PM Bug #7824: LibRadosList.ListObjectsNS failure
- And it looks like majority of upgrade:dumpling-x:parallel-firefly tests failed like this
- 02:59 PM Bug #7824: LibRadosList.ListObjectsNS failure
- Still an issue, if you need fresh logs log to yw box (via teuthology), logs are in /home/ubuntu/logs/142441
- 01:14 PM Bug #7824: LibRadosList.ListObjectsNS failure
- Is this the one we are backporting?
- 03:18 PM Revision 70ab6e03 (ceph): Add --preserve-queue to teuthology-kill
- For any cases where we just want to kill the running jobs and not delete
any scheduled jobs. This only applies to kil... - 03:07 PM Revision c404be61 (ceph): Postpone creation of logger object
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:42 PM rgw Bug #7821 (Duplicate): 'S3ResponseError: 301 Moved Permanently' in rgw-firefly-distro-basic-plana...
- 02:31 PM Bug #7843: OSD fails to start
- this is the trace when it fails
ceph version 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
1: /usr/bin/ceph... - 09:57 AM Bug #7843: OSD fails to start
- #6101 has nothing to do with this. :)
Looks like something has gone wrong with the OSD classes or some data passed t... - 07:04 AM Bug #7843 (Can't reproduce): OSD fails to start
- one of our OSD suddenly crashed, after that it no longer starts. the osd was new to the cluster so it was recovering....
- 02:14 PM devops Bug #7645 (Resolved): mira020 is having problems
- It had a hardware issue and has since been long fixed.
- 02:13 PM devops Bug #4887: ceph-disk list: Doesn't list properly devices using dm-mapper
- Alfredo - please confirm this issue no longer exists in current ceph-disk
- 02:11 PM devops Bug #5306: Xen based OSDs fail to start ceph-osd process
- Yan is this still an issue?
- 02:10 PM devops Bug #5811 (Resolved): gperftools-{devel,libs}-2.0.11.el6 appears to be broken (centos6/rhel6)
- 02:09 PM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- Loic - is this still "In Progress"?
- 02:07 PM devops Bug #5193: RHEL6 does not ship with xfsprogs
- Should eventually live in http://www.ceph.com/rpm/rhel6/x86_64/
- 02:05 PM devops Bug #5193: RHEL6 does not ship with xfsprogs
- Build and package xfsprogs.
- 02:04 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- I've got osd and rgw logs on metropolis:/home/joshd/teuthology/archive/rgw-ec-pool-7837
- 11:54 AM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- This looks like an EC related regression, was working before.
The test first creates an object + xattrs. Then over... - 02:01 PM devops Bug #5479: Append our built packages with some sort of inktank/ceph identifier
- 02:01 PM devops Bug #7312 (Resolved): ERROR: Running exception handlers
- This was a temporary issue that has not repeated.
- 01:41 PM Bug #7804: backfill racing with a hitset object remove
- This appears to have been caused by a backfill racing with a hitset object remove -- probably easiest to block hitset...
- 01:27 PM Bug #7781 (Duplicate): "FAILED assert" in rados-firefly-distro-basic-plana suite
- 11:55 AM Bug #7781: "FAILED assert" in rados-firefly-distro-basic-plana suite
- Looks like Ceph issue.
- 01:21 PM Bug #7495 (Resolved): ENOTEMPTY on collection remove
- 01:20 PM Bug #6003: journal Unable to read past sequence 406 ...
- 01:19 PM Bug #7728 (Resolved): osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- 01:04 PM Bug #7706: osd: PrioritizedQueue can starve
- ms pq max tokens per priority: 16777216 is a good work around
- 12:34 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- As a performance patch that only impacts splitting, I don't think this is really appropriate for a backport.
- 11:43 AM Bug #7849 (Resolved): ceph-conf create empty log files
- `ceph-conf` creates empty log files in "/var/log/ceph". This is unexpected, undesireable (and undocumented) behaviour...
- 11:23 AM Revision 4ac78087 (ceph): minor corrections to package descriptions
- 11:10 AM Revision 012bb5fb (ceph): minor init.d scripts lintianisation:
- * init.d-script-does-not-source-init-functions
* init.d-script-does-not-implement-required-option
* init.d-script-m... - 10:50 AM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
- Merged into master in commit:83661c273e759837816d5cd7ba27233ded898455
- 10:00 AM Bug #7822: examples/librados/hello_world.cc broken on master
- The read isn't supposed to be null terminated; it's a bufferlist. I was sloppy in giving that to an ostream, but doin...
- 09:57 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 09:47 AM Bug #7826: osd: illegal instruction in jerasure
- ceph/src/unittest_erasure_code_jerasure fails consistently...
- 09:32 AM Bug #7826: osd: illegal instruction in jerasure
- reproduced on https://github.com/dachary/ceph/tree/wip-sse-fix
- 08:01 AM Bug #7826: osd: illegal instruction in jerasure
- Reproduced the bug on master in a kvm without SSE instructions :-)...
- 07:40 AM Bug #7826: osd: illegal instruction in jerasure
- I thought that maybe ...
- 05:27 AM Bug #7826: osd: illegal instruction in jerasure
- On master ( afcf016a8a814167ced178d8a4275fa2a6f94a4d ) it fails in the same way using the set of command above, with ...
- 02:32 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 02:29 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 09:25 AM rbd Bug #5876 (In Progress): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_re...
- 09:24 AM rbd Bug #7282 (Resolved): Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connect...
- Marking resolved since Wido's patches landed upstream. Thanks!
- 09:24 AM rbd Bug #7577 (In Progress): rbd info displays extra random char in block prefix
- 09:21 AM rgw Bug #7526 (Resolved): "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-di...
- 09:21 AM rgw Bug #6889: rgw: usage log: don't log system user operations
- commit:42ef8ba543c7bf13c5aa3b6b4deaaf8a0f9c58b6
- 09:11 AM rgw Feature #6678 (Pending Backport): rgw: reject writes to secondary zones
- 09:08 AM rgw Bug #7502 (Rejected): S3 API - deleting object always returns 204 regardless of object is existin...
- 06:46 AM CephFS Feature #7761 (In Progress): journal-tool: forwards-search through corrupt regions
- 06:45 AM CephFS Feature #7759 (In Progress): journal-tool: roll in resetter/dumper from MDS
- 06:35 AM devops Feature #7239 (Closed): ceph-deploy: install cephfs java bindings
- Noah, ceph-deploy does have the ability to install a package on remote nodes:...
- 06:25 AM rbd Bug #7790: Kernel panic when creating ZFS pools on CEPH RBD devices
- Steps to reproduce bug:
- create a zpool with default options (@zpool create mypool /dev/rbd/rbdpool/rbddev@)
- w... - 01:19 AM Revision 47ba1711 (ceph): rgw: add option to use erasure coding instead of replication
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
03/24/2014
- 10:05 PM Revision bf90414a (ceph): rgw: set max-entries to 10 for data sync test
- This way it tests the agent generating more than max-intries writes to
a bucket.
Signed-off-by: Josh Durgin <josh.du... - 09:59 PM Revision 14b743ba (ceph): rgw: don't modify rgw_bucket for data extra pool
- This cleans up the interface, as we don't have this ugly implicit
structure modification when we deal with object tha... - 09:58 PM Revision 3677076b (ceph): rgw: add data_extra pool to bucket
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:58 PM Revision f023f900 (ceph): rgw: zone placement info includes extra data pool
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:58 PM Revision 7989cbd4 (ceph): rgw: multipart meta object uses extra data pool
- Fixes: #7676
We need the extra data pool since EC backends cannot handle the omap
operations that are needed for the ... - 09:54 PM Revision 0cb00b1f (ceph): radosgw-agent: default to 1000 max entries
- Using a small number of max entries is only needed for one test, so
make it configurable. Setting it too low makes s3... - 09:26 PM Revision 3e168306 (ceph): internal: cleaner fix for binary gibberish in logs
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:18 PM Revision e5a4f5ed (ceph): Merge pull request #1528 from ceph/wip-dz-watch-test
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 09:17 PM Revision 14921c70 (ceph): mailmap: James Ryan Cresawn affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:17 PM Revision a310ea20 (ceph): mailmap: Guang Yang affiliation
- and name normalization
Reviewed-by: Guang Yang <yguang@yahoo-inc.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:17 PM Revision 0160d19a (ceph): mailmap: Tyler Brekke name normalization
- Reviewed-by: Tyler Brekke <tyler.brekke@inktank.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:17 PM Revision 286131e3 (ceph): mailmap: Huang Jun name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:17 PM Revision 58ef0dab (ceph): mailmap: Inktank jenkins bot
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:17 PM Revision 27c28ad2 (ceph): mailmap: Sharif Olorin affiliation
- Reviewed-by: Sharif Olorin <sio@tesser.org>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:17 PM Revision 2faf271a (ceph): mailmap: Mohammad Salehe affiliation
- Reviewed-by: Mohammad Salehe <salehe+dev@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:17 PM Revision 9fd61c7a (ceph): mailmap: Stephan Renatus affiliation
- Reviewed-by: Stephan Renatus <s.renatus@x-ion.de>
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:14 PM Revision 190d8183 (ceph): ceph: ignore daemon types that aren't configured
- not every cluster needs an mds
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 09:14 PM Revision b677bdd1 (ceph): internal: ignore binary junk in kernel logs
- NUL bytes can show up here after powercycle testing
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 09:04 PM Revision 01b99668 (ceph): qa: Add ceph_multi_stress_watch for rep and ec
- Fixes: #7438
Signed-off-by: David Zafman <david.zafman@inktank.com> - 08:54 PM Revision b1819fcb (ceph): Merge pull request #1525 from ceph/wip-listxattr
- client: don't include ceph.{file,dir}.layout vxattr in listxattr()
Reviwed-by: Sage Weil <sage@inktank.com> - 07:59 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- What we'll actually need to repair these objects will involve pulling the rgw xattrs out as well as the RADOS ones — ...
- 05:31 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- actually, the salvage tool is useless. since we are throwing out the rados user attrs, we can just do...
- 05:23 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- wip-7779 has a reproducer program, and a 'salvage' target that will copy the known important ceph xattrs to a replace...
- 04:41 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- good news: scrub on a pg with an object with too many xattrs:...
- 06:52 PM Revision 6ec28fd9 (ceph): ensure pybind is in the PYTHONPATH
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
- 06:43 PM Revision 9c0ae632 (ceph): build: add gf-complete/jerasure to gitmodule_mirrors
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:43 PM Revision 078e58c4 (ceph): Add file to store mirror location of module's.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 06:23 PM rgw Bug #7837 (Resolved): s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- Using this configuration:...
- 05:03 PM Revision afcf016a (ceph): Merge pull request #1523 from ceph/wip-7827
- msg: set recv stamp for local delivery
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:01 PM Revision 37899fa5 (ceph): be nitpicky about missing references
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
- 04:56 PM Revision 230dfc62 (ceph): Merge pull request #1526 from ceph/wip-status-function-names
- mon: Monitor: change 'status' function names for clarity's sake
Reviewed-by: Sage Weil <sage@inktank.com> - 04:21 PM Revision 4186916c (ceph): Revert "erasure-code: gf-complete detects SSE at runtime"
- This reverts commit dbcf4471838fbf5dce2ee06fc73493f513dbf9f0.
- 03:36 PM Bug #7835 (Resolved): make_writeable needs to fill in ssc on new clone
- -1> 2014-03-24 15:29:50.770570 7fac0522e700 10 filestore(/var/lib/ceph/osd/ceph-4) _finish_op 0x5ac6a00 seq 4456 ...
- 03:32 PM Revision b79ab0d8 (ceph): Merge pull request #1524 from dachary/wip-sse
- erasure-code: deactivate SSE optimizations
- 02:55 PM rgw Bug #7742 (Resolved): FAIL: s3tests.functional.test_s3.test_region_bucket_create_master_access_re...
- commit:0cb00b1fb9bf6c59d787f340dd50ae16b1473f82 in teuthology.git
- 02:43 PM Revision 3f014dad (ceph): mon: Monitor: s/_mon_status()/get_mon_status()/
- 'Monitor::_mon_status()' provides status specific to the monitor being
poked. This is information that does not nece... - 02:41 PM Revision ed780adb (ceph): mon: Monitor: s/get_status()/get_cluster_status()/
- Monitor::get_status() is actually used to obtain 'cluster status' (i.e.,
status about *all* the monitors, maps, IO, o... - 02:41 PM Bug #7826: osd: illegal instruction in jerasure
- running this teuthology workload on http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-deb-precise-amd64-basic/log.cgi?...
- 08:34 AM Bug #7826: osd: illegal instruction in jerasure
- this is what i triggered it with. note that yo uneed to adjust the branch to be something that doesn't include the w...
- 08:05 AM Bug #7826: osd: illegal instruction in jerasure
- fixed a "few things in gf_complete":https://bitbucket.org/jimplank/gf-complete/pull-request/4/defer-the-decision-to-u...
- 07:40 AM Bug #7826: osd: illegal instruction in jerasure
- "work in progress":https://github.com/ceph/ceph/tree/wip-sse-fix to run teuthology workloads
- 02:09 AM Bug #7826: osd: illegal instruction in jerasure
- It would be helpful to have the config yaml used to trigger this...
- 01:15 AM Bug #7826: osd: illegal instruction in jerasure
- "workaround":https://github.com/ceph/ceph/pull/1524
- 02:21 PM RADOS Fix #7832: PG: do not double-queue pg log entries
- Okay, that code diagnosis is probably not correct, since append_log doesn't set the dirty_from member which _write_lo...
- 02:10 PM RADOS Fix #7832 (New): PG: do not double-queue pg log entries
- PG::_write_log() sends each of the entries in the pg log to the omap. (obviously) Irritatingly, PG::append_log does t...
- 02:20 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
- Two commits resolve this issue:
01b99668abd9aaa65e8864c2dad392d35dd892e1
5a3f6c7c8a01c002e9ff7ad5b49afaf3ae041ead - 02:17 PM Bug #6789: cannot remove the leader when there only are two monitors
- This doesn't currently happen on latest. Haven't tested yet with latest dumpling and latest emperor.
- 12:14 PM Feature #7831 (Resolved): OSD: track objects with omap entries and don't count toward caps
- 11:35 AM Revision 08a3d6bd (ceph): client: don't include ceph.{file,dir}.layout vxattr in listxattr()
- This avoids 'cp -a' modifying layout of new files/directories.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 10:03 AM Bug #7827 (Resolved): osd: weird slow request warnings
- Merged into master in commit:afcf016a8a814167ced178d8a4275fa2a6f94a4d
- 08:27 AM Bug #7626 (In Progress): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 08:14 AM Revision 1bc680eb (ceph): erasure-code: deactivate SSE optimizations
- Workaround until the bug is diagnosed and fixed
http://tracker.ceph.com/issues/7826 refs #7826
Signed-off-by: Loic ... - 07:34 AM Bug #6850 (Closed): mon: 'ceph health detail' with formatted output doesn't report low space on d...
- As of today this is no longer valid.
- 07:06 AM Feature #6732 (Rejected): mon: 'mon_status' should provide as much insight as 'ping'
- 'mon_status' has a different scope than that of 'ping'.
'mon_status' reports on monitor's status, via the ceph too... - 04:50 AM Revision 904c870c (ceph): Merge pull request #1521 from ceph/wip-7810
- mds: reset connection priv after connection's session is removed
Reviewed-by: Sage Weil <sage@inktank.com> - 04:32 AM Revision 81163948 (ceph): msg: set recv stamp for local delivery
- Fixes: #7827
Signed-off-by: Sage Weil <sage@inktank.com>
03/23/2014
- 10:33 PM Bug #7826: osd: illegal instruction in jerasure
- 10:32 PM Bug #7826 (Fix Under Review): osd: illegal instruction in jerasure
- 06:38 PM Bug #7826 (Resolved): osd: illegal instruction in jerasure
- ...
- 10:12 PM Bug #7828 (Resolved): osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_sn...
- ...
- 09:34 PM Bug #7827 (Fix Under Review): osd: weird slow request warnings
- 09:27 PM Bug #7827 (Resolved): osd: weird slow request warnings
- ...
- 02:06 PM Revision 3ebeb8e9 (ceph): mailmap: Allen Samuels affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 02:06 PM Revision a217cd67 (ceph): mailmap: Warren Usui is with Inktank
- Reviewed-by: Warren Usui <warren.usui@inktank.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:48 AM rgw Feature #6513 (Resolved): rgw: dr: Service scripts for meta/data sync agents
- Added to radosgw-agent.git commit:c8d243f503b39e67a8daec6df40b58fb993cc6e6 and the following few to fix up packaging.
- 05:25 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
- Also, for those who are ailed by this bug, best solution for them is to remove the affected monitor from the cluster ...
- 05:23 AM Bug #5804 (Resolved): mon: binds to 0.0.0.0:6800something port
- My suspicions were right, at least as far as the VMs are concerned. Whereas using 0.67.2 or 0.72.2 would hit this ev...
- 04:58 AM Revision a4c652c5 (ceph): document adding dev key for custom Apache/FCGI install
- following the docs will only get you the release key and the install of custom Apache/FCGI fails w/ key error
- 02:47 AM Revision fb72330f (ceph): mds: reset connection priv after connection's session is removed
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
03/22/2014
- 08:44 PM Bug #7824 (Resolved): LibRadosList.ListObjectsNS failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-22_19:33:22-upgrade:dumpling-x:parallel-firefly---b...
- 05:24 PM Revision 361b251e (ceph): Merge tag 'v0.78'
- v0.78
- 03:41 PM Bug #7823: osd: copy-get from ec pool returns wrong size
- wip-ec-copy-get
- 03:19 PM Bug #7823 (Resolved): osd: copy-get from ec pool returns wrong size
- reproduced w/ replicated cache in front of an ec pool and ceph_test_rados
03/21/2014
- 11:57 PM Revision e4f2d9fe (ceph): doc/release-notes: 0.78 final notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:32 PM Revision b742f94e (ceph): Merge pull request #1515 from ceph/wip-rgw-less-alloc
- Wip rgw less alloc
Reviewed-by: Sage Weil <sage@inktank.com> - 10:59 PM Revision b097a237 (ceph): PG: only complete replicas should count toward min_size
- Backport: emperor,dumpling,cuttlefish
Fixes: #7805
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:43 PM Revision 185bcc42 (ceph): doc/release-notes: final 0.78
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:16 PM Revision 1e7cd10d (ceph): rgw: remove memory allocation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:16 PM Revision 1817c23c (ceph): rgw: get rid of a memory allocation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:05 PM Revision f6c746c3 (ceph): 0.78
- 09:53 PM Revision 466cd536 (ceph): Merge pull request #1313 from ceph/dumpling-osd-subscribe
- Dumpling backport: clean up osd subscriptions
- 09:52 PM Revision 2ef0d6a2 (ceph): Merge pull request #1485 from ceph/wip-7212.dumpling
- backport 7212 fixes to dumpling
- 09:52 PM Revision dfc11104 (ceph): Merge pull request #1484 from ceph/wip-7212.emperor
- backport 7212 fixes to emperor
- 09:51 PM Revision e4e8dc50 (ceph): Merge pull request #1512 from dachary/wip-jerasure-sse
- erasure-code: gf-complete detects SSE at runtime
Reviewed-by: Sage Weil <sage@inktank.com> - 09:50 PM Bug #7822 (Resolved): examples/librados/hello_world.cc broken on master
- Using the example program to test librados ports, I notice that it's currently failing (slightly) on master:...
- 09:06 PM Revision fed2ed1a (ceph): Merge pull request #1513 from ceph/wip-7438
- Reviewed-by: Loic Dachary <loic@dachary.org>
- 08:50 PM Revision 752a76fb (ceph): radosgw-agent: use our mirror instead of github
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:39 PM Revision a8f59a38 (ceph): Merge pull request #1510 from ceph/wip-pq
- osd: some PrioritizedQueue cleanups; dump locking fix; debug pqueue state at high debug level
Reviewed-by: Samuel Ju... - 07:30 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- I propose the following:
1. Ubuntu LTS (12.04, 14.04, etc) can (should) stop at the Inktank-supported Ceph release... - 05:11 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Been waiting for a while, one more weekend won't hurt ;)
Don't know about the others but I'll be very happy with e... - 05:01 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Builds take quite a while and we are actually doing a release today so at the very least this will need to wait until...
- 12:01 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Ok, i was able to sucessfully build for saucy on jenkins. Trusty is giving me trouble as the machines I was using are...
- 06:57 PM Revision 28d8e7f5 (ceph): Revert "ReplicatedPG: disallow trans which atomically create and remove...
- This reverts commit 9ee108428176c93fe48ae5ae95b160eadabca9b6.
This appears to break rgw in its current state; test a... - 05:22 PM rgw Bug #7821 (Duplicate): 'S3ResponseError: 301 Moved Permanently' in rgw-firefly-distro-basic-plana...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-21_14:31:01-rgw-firefly-distro-basic-plana/140962/...
- 05:16 PM rgw Bug #7820 (Resolved): "AssertionError: 404 != 301" in rgw-firefly-distro-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-21_14:31:01-rgw-firefly-distro-basic-plana/140967/...
- 04:12 PM Revision 9b6f93a5 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:59 PM Revision 49a01900 (ceph): doc/release-notes: 0.78 notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:38 PM Revision 7b5d693d (ceph): Merge pull request #231 from ceph/wip-fix-rgw
- fix rgw task
- 03:36 PM Revision 4e2f36fc (ceph): rgw: handle empty conf case
- 2014-03-20T23:30:28.964 ERROR:teuthology.contextutil:Saw exception from nested tasks
Traceback (most recent call last... - 03:21 PM Revision 8012ba43 (ceph): Merge remote-tracking branch 'gh/wip-multimds-fixes'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 03:00 PM Feature #7757 (Resolved): erasure-code: enable jerasure-2 SSE optimizations
- 07:27 AM Feature #7757: erasure-code: enable jerasure-2 SSE optimizations
- "The problem with enabling that flag is that it apparently also gives the compiler license to use SSE2 instructions i...
- 07:01 AM Feature #7757 (Fix Under Review): erasure-code: enable jerasure-2 SSE optimizations
- "work in progress":https://github.com/ceph/ceph/pull/1512
- 04:58 AM Feature #7757: erasure-code: enable jerasure-2 SSE optimizations
- Waiting for review, K. Greenan may do it this week-end
- 02:51 PM Bug #7212 (Resolved): monitor fails to start
- 01:56 PM Revision dbcf4471 (ceph): erasure-code: gf-complete detects SSE at runtime
- And the gf-complete code has been updated to rely on the
gf_internal_t::sse flag instead of #if conditionals.
Signed... - 01:51 PM rgw Bug #7816 (Resolved): 403 Forbidden while accessing https://github.com/ceph/radosgw-agent.git/inf...
- teuthology.git 752a76fb4860afa8cd385e7103fc2832cdbb4098
- 01:30 PM rgw Bug #7816 (Resolved): 403 Forbidden while accessing https://github.com/ceph/radosgw-agent.git/inf...
- ...
- 01:41 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
- 01:40 PM rgw Bug #7818 (Resolved): syncdaemon: error geting op state: list index out of range
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-21_13:07:49-rgw-firefly-distro-basic-plana/140905<p...
- 01:34 PM rgw Feature #7817 (Resolved): rgw: some support for copy multipart part
- The minimum support should be returning a NotImplemented error code, rather than NoSuchKey.
- 01:29 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
- 12:07 PM rgw Bug #7815 (Can't reproduce): Test failed in upgrade:dumpling-x:parallel-firefly-testing-basic-pla...
- Logs are in http://qa-proxy.ceph.com/teuthology/ubuntu-2014-03-21_11:05:47-upgrade:dumpling-x:parallel-firefly-testin...
- 12:07 PM Revision 8c7f6c11 (ceph): autotools: AX_SSE detects the compiler SSE capabilities
- For each SSE feature supported by the compiler
* add the corresponding -msse* flag
* define HAVE_SSE*
Remove AX_EXT... - 09:19 AM Feature #7438 (Fix Under Review): EC: adapt watch/notify stress test for EC and add to nightly
- 06:46 AM CephFS Feature #7810 (Resolved): libcephfs: add a test that freezes + unfreezes a client, and then verif...
- 06:12 AM Revision 5a3f6c7c (ceph): test: Add erasure coding to stress watch test
- Fixes: #7438
Signed-off-by: David Zafman <david.zafman@inktank.com> - 06:10 AM Revision 6fb65882 (ceph): test: Reorg multi_stress_watch to prepare for ec option
- If old options are specified maintain backward compatibility
Signed-off-by: David Zafman <david.zafman@inktank.com> - 03:22 AM Revision b110275d (ceph): test: Fix ceph_filestore_dump.sh test for new EC pool creation
- Signed-off-by: David Zafman <david.zafman@inktank.com>
03/20/2014
- 11:51 PM Revision 798daf58 (ceph): upgrade/dumpling-x/stress-split: set fastcgi idle timeout to 2 min
- 30 seconds isn't enough when combined with osd thrashing.
Fixes: #7702
Signed-off-by: Sage Weil <sage@inktank.com> - 11:50 PM Revision 7dcfdd28 (ceph): Merge remote-tracking branch 'gh/firefly'
- 11:48 PM Revision 2943267a (ceph): Merge pull request #230 from ceph/wip-7702
- rgw: allow fastcgi idle timeout to be adjusted
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 11:09 PM Revision 3a2b77c1 (ceph): rgw: allow fastcgi idle timeout to be adjusted
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:07 PM Revision bcc254fe (ceph): Merge pull request #1500 from ceph/wip-tid_t
- Change tid_t to ceph_tid_t to avoid conflicts with a popular type
Reviewed-by: Sage Weil <sage@inktank.com> - 11:05 PM Revision c9b4e7d9 (ceph): Merge pull request #1465 from ceph/wip-s3pm-wusui
- Remove code duplication from s3 tests.
- 11:04 PM Revision f13c6421 (ceph): Merge pull request #1511 from dachary/wip-exclamation
- tests: use ^ instead of ! as invalid char
Reviewed-by: Sage Weil <sage@inktank.com> - 10:29 PM Revision dad0faf1 (ceph): tests: use ^ instead of ! as invalid char
- Because !!! is incorrectly interpreted as an error by gitbuilder.
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:43 PM Revision d4d77d71 (ceph): doc/release-notes: stop confusing sphinx
- ERROR: /srv/autobuild-ceph/gitbuilder.git/build/doc/release-notes.rst:594: Unknown target name: "debug".
Signed-off-... - 09:11 PM Revision f50d208c (ceph): Merge pull request #1503 from dachary/wip-jerasure-submodules
- erasure-code: add gf-complete / jerasure submodules
Reviewed-by: Sage Weil <sage@inktank.com> - 09:05 PM Revision 5158f154 (ceph): Merge pull request #1505 from ceph/wip-7728
- Wip 7728
Reviewed-by: Sage Weil <sage@inktank.com> - 05:56 PM Bug #7735 (Fix Under Review): osd: priorityqueue debug dump crashes
- 05:42 PM Revision 513e4ad8 (ceph): Merge remote-tracking branch 'gh/firefly'
- 05:35 PM Revision daa54292 (ceph): Merge branch 'firefly'
- 05:13 PM Revision 048ca96c (ceph): Merge pull request #1509 from guangyy/wip-folder-merge
- Make it possible for FileStore to be in a state which never do merge and keep it backward compatible
Reviewed-by: Sa... - 04:54 PM rgw Bug #7702 (Resolved): osd thrashing + rgw = timeouts
- 04:39 PM rgw Bug #7808 (Duplicate): "ERROR: testContainerSerializedInfo" in upgrade:dumpling-x:stress-split-fi...
- # 7799
- 04:37 PM rgw Bug #7808 (Duplicate): "ERROR: testContainerSerializedInfo" in upgrade:dumpling-x:stress-split-fi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_01:35:01-upgrade:dumpling-x:stress-split-firefl...
- 04:25 PM rbd Documentation #7807 (Closed): fix hostname on docu
- http://ceph.com/docs/master/install/upgrading-ceph
ceph-deploy install --stable {stable release} ceph-node1[ ceph-... - 04:24 PM Revision d1f8742d (ceph): Merge pull request #1506 from ceph/wip-7755
- PG::find_best_info: fix log_tail component
Reviewed-by: Sage Weil <sage@inktank.com> - 04:23 PM Bug #7805 (Resolved): emperor can go active with < min_size non-incomplete peers since we check a...
- 04:19 PM Revision b395cb19 (ceph): Merge pull request #1507 from ceph/wip-7733
- PG::start_peering_interval: always send_notify if !primary
Reviewed-by: Sage Weil <sage@inktank.com> - 04:19 PM Revision bf68daba (ceph): Merge pull request #1508 from ceph/wip-7777
- ReplicatedPG::do_op: delay if snapdir is unreadable
Reviewed-by: Sage Weil <sage@inktank.com> - 03:54 PM Bug #7804 (Duplicate): backfill racing with a hitset object remove
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_02:30:02-rados-firefly-distro-basic-plana/13947...
- 12:47 PM devops Bug #7585 (Resolved): ceph-deploy should handle requiretty failures
- Pull request opened https://github.com/ceph/ceph-deploy/pull/171
And merged into ceph-deploy's master branch with ... - 10:04 AM devops Bug #7585 (In Progress): ceph-deploy should handle requiretty failures
- 10:03 AM devops Bug #7585: ceph-deploy should handle requiretty failures
- To replicate the issue, in `/etc/sudoers` the following needs to be present:...
- 11:40 AM rgw Bug #7786: civetweb segfaults with file uploads larger than 2GB
- The patch has been merged.
- 11:17 AM rbd Bug #7790: Kernel panic when creating ZFS pools on CEPH RBD devices
- updated source to support.
- 10:35 AM Bug #7801 (Resolved): warn on ext4 remount journal replay INFO line
- fixed by teuthology commit 7088885ecd739a4006418eb9e7464d2f0128ea5d
- 10:23 AM Bug #7801 (Resolved): warn on ext4 remount journal replay INFO line
- Logs are in http://qa-proxy.ceph.com/teuthology/ubuntu-2014-03-19_17:33:45-powercycle-firefly-testing-basic-plana/138...
- 10:33 AM Bug #7208: CEPH_FEATURE_CRUSH_V2 feature mismatch
- oh, commit:08fa34d94e40f2f7230dec4dabad72107cdee27b removed the default erasure pool from the OSDMap which fixed this...
- 10:25 AM Bug #7208: CEPH_FEATURE_CRUSH_V2 feature mismatch
- workarounds:
ceph osd crush tunables bobtail
works with any kernel > 3.9. or,
ceph osd crush tunables fir... - 10:20 AM rbd Bug #5469: qemu-io: segfault when tried IO with invalid arguments
- we've got the same assertion failure today on 0.67.3. It's rare and random.
osdc/Striper.cc: In function 'static ... - 09:36 AM rgw Bug #7799 (Can't reproduce): Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_01:35:01-upgrade:dumpling-x:stress-split-firefl...
- 09:23 AM Bug #7755 (Resolved): auth_log selection depends on the primary identity and can cause a loop
- 09:19 AM Bug #7733 (Resolved): start_new_interval: always notify if !primary
- 09:18 AM Bug #7777 (Resolved): 2014-03-18T12:48:30.368 INFO:teuthology.task.rados.rados.0.err:[10.214.132....
- 08:17 AM rgw Bug #7796 (Resolved): RGW Keystone token auth fails with '411 Length Required' when Keystone usin...
- When using keystone behind apache/wsgi in the following config, radosgw is unable to authenticate tokens:
cat /etc... - 07:28 AM Feature #7792 (Closed): leveldb 1.12.0 for rhel
- It appears libleveldb1 version 1.12.0 is provided for debian/ubuntu here:
http://ceph.com/debian-dumpling/pool/mai... - 05:51 AM devops Bug #7677 (Resolved): Troubleshoot ceph-setup-nightly Jenkins failures
03/19/2014
- 06:00 PM Revision cffcf10f (ceph): Merge pull request #1312 from cernceph/master
- rados.py: add aio_remove
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 05:47 PM Revision c647a03f (ceph): Merge pull request #1504 from ceph/wip-7780
- objecter: waive OSDMAP_FULL check for MDS
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 05:46 PM Revision 72093f97 (ceph): Merge pull request #1476 from ceph/wip-scrub-lock
- osd: do not queue scrub for non-primary
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:40 PM Revision cb744ca3 (ceph): Merge pull request #1502 from ceph/wip-flush-journal-asok
- wip-flush-journal-asok
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 04:39 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
- Not wanting to commit to a full diagnosis just yet, this is looking a lot like a mild case of #7212 with a weird resu...
- 04:22 PM Revision 78ede90c (ceph): objecter: waive OSDMAP_FULL check for MDS
- The MDS expects to be able to perform writes to OSDs even
if the full ratio has been reached, in order to journal
fil... - 03:39 PM rgw Feature #7791 (New): radosgw-agent should show statistics
- radosgw-agent might be a good method of offering statistics and reporting, such as log version between gateways, spee...
- 03:37 PM rbd Bug #7790 (Resolved): Kernel panic when creating ZFS pools on CEPH RBD devices
- Creating a ZFS pool on top of krbd causes a kernel panic.
From the ZFSonLinux bug tracker (https://github.com/zfso... - 01:18 PM rbd Fix #7787 (Resolved): rbd diff takes longer as images grow larger
- rbd diff will currently take a VERY long time to complete for large images. This is not ideal. Perhaps a counter of s...
- 01:15 PM Revision 84cb345e (ceph): rgw: reset objv tracker on bucket recreation
- Fixes: #6951
If we cannot create a new bucket (as it already existed), we need to
read the old bucket's info. However... - 12:24 PM rgw Bug #7786 (Resolved): civetweb segfaults with file uploads larger than 2GB
- I submitted a pull request to fix this. I'm waiting to hear back from the maintainers of the project.
https://githu... - 11:46 AM Feature #7784: mon osd down out interval = 0 should prevent ceph health from reporting ok
- Perhaps this config option should be converted into the noout flag; that's already plumbed up for such things.
- 11:13 AM Feature #7784 (Resolved): mon osd down out interval = 0 should prevent ceph health from reporting ok
- 11:45 AM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- Sounds like this is a manual repair job to me, then...
I guess we could write tools that know all the xattr name pat... - 10:51 AM Bug #7393 (Duplicate): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whit...
- We don't seem to be seeing this any more, might have been related to the object_info_t leaking. Marking duplicate un...
- 10:36 AM Bug #7781 (Duplicate): "FAILED assert" in rados-firefly-distro-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/13740...
- 08:59 AM Revision a4849fb9 (ceph): qa: test_alloc_hint: flush journal before prodding the FS
- OSDs that for some reason get behind on processing their op queue break
expect_alloc_hint_eq(), as it pokes the FS an... - 08:59 AM Revision 9d31c1be (ceph): osd: add flush_journal admin socket command
- Add flush_journal admin socket command to be able to flush journal to
the permanent store for online osds. (For offl... - 08:28 AM CephFS Bug #7780 (Fix Under Review): When full flag is set, even MDS writes are blocked
- 05:12 AM CephFS Bug #7780: When full flag is set, even MDS writes are blocked
- Just tried commenting out the check in objecter and the MDS writes get through, so not too much work to do here.
- 04:05 AM CephFS Bug #7780 (Resolved): When full flag is set, even MDS writes are blocked
We're meant to allow the MDS to write even when the OSDs think they're full, so that we can journal file deletions ...- 08:25 AM Revision b444e886 (ceph): mds: fix typo in MDCache::handle_cache_rejoin_strong
- It should invent dirfrags according to the dirfragtree
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 07:02 AM Revision ddbb2f7b (ceph): erasure-code: add gf-complete / jerasure submodules
- Instead of copying the files in the ceph repository, which is less
convenient.
When building the headers are ignored... - 06:38 AM Revision 5c34a0f0 (ceph): erasure-code: remove copy of gf-complete / jerasure
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:30 AM Revision 0d167d2c (ceph): mds: fix NULL pointer dereference in Server::handle_client_rename
- Inode's parent dentry can be NULL, which causes segment fault in
Locker::acquire_locks
Signed-off-by: Yan, Zheng <zh... - 06:26 AM Revision 272b53b2 (ceph): mds: avoid infinite loop in MDLog::submit_entry()
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 04:34 AM Revision 6fd5ca9c (ceph): upgrade/dumpling-x/parallel: test cuttlefish->dumpling starting point
- Maybe this will trigger #7519. And anyway, it's good coverage.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:25 AM Revision 002c7e75 (ceph): Merge pull request #1496 from ceph/wip-7708
- mds/Locker: fix null deref on cap import
- 04:03 AM Revision 32894138 (ceph): Merge pull request #1499 from ceph/wip-no-version
- Add NO_VERSION to avoid rebuilding ceph_ver.h and relinking
Reviewed-by: Sage Weil <sage@inktank.com> - 04:01 AM Revision 5dd270e8 (ceph): Merge pull request #1498 from ceph/wip-limit-libkeyutils
- Makefiles: remove libkeyutils from every binary except two
Reviewed-by: Sage Weil <sage@inktank.com> - 03:35 AM Revision 3cadbfbb (ceph): mds: fix potential invalid pointer dereference
- pin importing inode until subtree importing finishes
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 03:35 AM Revision bc3325b3 (ceph): mds: fix stack overflow caused by nested dispatch
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:35 AM Revision e909eaf2 (ceph): mds: drop auth pins before waiting for dir unfreeze
- Otherwise deadlock can happen
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 03:35 AM Revision ed30b83a (ceph): mds: avoid issuing zero caps to client
- make sure CEPH_CAP_PIN exists in stale caps.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 03:35 AM Revision dc52581d (ceph): mds: properly initialize MDCache::fragment_info_t
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:35 AM Revision b225ca97 (ceph): mds: fix open remote dirfrag deadlock
- During subtree migration, the importer may need to open subtree
bound dirfrags. Opening subtree bound dirfrags happen... - 03:35 AM Revision dc54b7b3 (ceph): mds: re-issue caps after importing caps (rename)
- After importing inode, the issued caps can be less than the caps
client wants. So re-issue caps after importing inode... - 03:35 AM Revision 4973560e (ceph): mds: export file locks together with inode
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:35 AM Revision 3c39d6f5 (ceph): mds: cleanup CInode::decode_import()
- We have bumped protocol version several times, no need to maintain
compatibility for ancient message.
Signed-off-by:... - 03:35 AM Revision cbd1c447 (ceph): mds: improve success rate of subtree exporting
- When exporting a subtree, the migrator acquires the required locks,
then freezes the subtree and releases the locks. ... - 03:35 AM Revision de461a92 (ceph): fragtree_t: fix get_leaves_under()
- If fragtree is (*^1) and the caller wants leaves under frag 00*.
get_leaves_under() should return empty list.
Signed... - 03:35 AM Revision 150c6ce4 (ceph): mds: remove wrong assertion
- when handling resolve message, it's possible that bound dirfrags
are missing.
Signed-off-by: Yan, Zheng <zheng.z.yan... - 03:35 AM Revision 5150fe63 (ceph): mds: trim other MDS' mdsdir during recovery
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:35 AM Revision a8671666 (ceph): mds: don't mark scatter locks dirty when dirfrag is dirty
- The journal reply code has check that decides which scatter locks
should be marked as dirty. So don't unconditionally... - 03:35 AM Revision 91c88c1e (ceph): mds: rdlock dirfragtree lock when renaming directory
- This make sure inode importer and inode exporter have consistent
view of dirfrags.
Signed-off-by: Yan, Zheng <zheng.... - 03:35 AM Revision 63a597be (ceph): mds: rollback slave request after slave prepare is journalled
- Resolve ack message can abort slave requests that are being journalled.
The slave rollback does not handle this case ... - 03:29 AM Revision a1ff4896 (ceph): mds: treat flushing as dirty when rejoining scattered locks
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 02:06 AM Revision 1268dbb3 (ceph): Change tid_t to ceph_tid_t to avoid conflicts with a popular type
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:05 AM Revision b2274268 (ceph): Add NO_VERSION to avoid rebuilding ceph_ver.h and relinking
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:04 AM Revision cfb04b2a (ceph): Makefiles: remove libkeyutils from every binary except two
- Only rbd and mount_ceph need secret.c, and only secret.c needs libkeyutils;
remove it from LIBCOMMON_DEPS so it's not...
03/18/2014
- 11:56 PM Revision 381850b1 (ceph): Merge pull request #1497 from dachary/wip-jerasure
- remove gf-complete / jerasure sub modules
Reviewed-by: Sage Weil <sage@inktank.com> - 11:28 PM Revision e9eb641f (ceph): remove gf-complete / jerasure sub modules
- and add the source files in the tree.
Signed-off-by: Loic Dachary <loic@dachary.org> - 10:59 PM Revision 8b77995f (ceph): Merge pull request #1494 from dachary/wip-gitmodule-mirrors
- build: add gf-complete/jerasure to gitmodule_mirrors
- 10:47 PM Revision fdcf3eb4 (ceph): ReplicatedPG::do_op: delay if snapdir is unreadable
- Since all we really need on a snapdir is the context, we really only
need it to be !missing. However, it might becom... - 10:26 PM Revision 362d370d (ceph): Merge pull request #1125 from ceph/wip-mon-docs
- wip-mon-docs: Better explain required number of monitors & how to troubleshoot a monitor
Signed-off-by: Joao Eduardo... - 10:23 PM Revision 7088885e (ceph): internal: ignore ext4 recovery msg
- plana43 kernel: [ 21.179205] EXT4-fs (sda1): INFO: recovery required on readonly filesystem
is harmless.
Signed-o... - 10:19 PM Revision 6252d28d (ceph): distros: add wheezy
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:19 PM Revision 0bfc365d (ceph): distros: add rhel 6.4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:02 PM Revision cb194770 (ceph): Merge pull request #20 from ceph/wip-distros
- symlink all distros facets to a common set of 'supported' targets
- 10:01 PM Revision 5679ae2a (ceph): Merge branch 'firefly'
- 10:00 PM Revision 8e748c0c (ceph): ceph.conf: tolerate 500ms of clock drift (up from 250)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:54 PM Revision 7f7a9988 (ceph): mds/Locker: fix null deref on cap import
- The session Connection* may be NULL.
Fixes: #7708
Signed-off-by: Sage Weil <sage@inktank.com> - 09:28 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- 09:04 PM Revision 4221e0dd (ceph): build: add gf-complete/jerasure to gitmodule_mirrors
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:03 PM Revision a27ead67 (ceph): distros: add 14.04 to supported list
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:56 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- Yep. This particular object was written back in November, though, so it predates the fix by some time (and in fact m...
- 08:52 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- This exact bug is why we made the changes to xattr handling and no longer store unlimited numbers in the filesystem. ...
- 06:44 PM Bug #7779 (Resolved): osd: object file can have too many xattrs, get E2BIG
- if an object has too many xattrs on it, you get E2BIG from listxattr. one such object:...
- 08:55 PM Revision 8d4c4676 (ceph): distros: test rhel/centos 6.5 instead of 6.4
- 08:44 PM Revision 25d04fba (ceph): osd: dump priority queue state on dequeue at level 30
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:39 PM Revision 99f4e9dd (ceph): symlink all distros facets to a common set of 'supported' targets
- This makes it easier to maintain the supported/tested targets.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:22 PM Revision 4a3464ce (ceph): common/PrioritizedQueue: include first item's cost in dump
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:22 PM Revision ff11965c (ceph): osd: fix OpWQ dump locking
- The pqueue is protected by the wq lock, not by qlock; for example, see
OpWQ::_enqueue. qlock protects the pg_for_pro... - 08:16 PM Revision 8bd89442 (ceph): common/PrioritizedQueue: fix remove_by_class() corner case
- If i is the first entry, then setting cur = begin() sets us up to point at
something that we are about to delete. Mo... - 08:16 PM Revision de576d5b (ceph): common/PrioritizedQueue: constify a few things
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:09 PM Revision f1e3bc9a (ceph): doc/dev/cache-pool: describe the tiering agent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:07 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
- 07:35 PM Revision d7284268 (ceph): PG::start_peering_interval: always send_notify if !primary
- Otherwise, we might get into a situation where the primary
forgets about a stray pg. This is simpler and does not
in... - 07:29 PM Revision 77e46d0d (ceph): ReplicatedPG: don't skip missing if sentries is empty on pgls
- Formerly, if sentries is empty, we skip missing. In general,
we need to continue adding items from missing until we ... - 07:09 PM Revision b4420ffb (ceph): PG::find_best_info: fix log_tail component
- The previous logic should have kept the current best info if it found a
replica which best could log-recover, but p c... - 06:07 PM Revision 06bfdfc9 (ceph): Merge pull request #1491 from dachary/wip-submodules
- erasure-code: jerasure and gf-complete moved to ceph namespace
Reviewed-by: Alfredo Deza <alfredo.deza@inktank.com> - 06:00 PM Revision 1ddae7e2 (ceph): erasure-code: jerasure and gf-complete moved to ceph namespace
- for maintenance purposes
Signed-off-by: Loic Dachary <loic@dachary.org> - 05:49 PM Revision f8632699 (ceph): Merge pull request #1490 from ceph/wip-6806
- mon: Properly handle errors from 'cmd_getval()' when needed
Reviewed-by: Sage Weil <sage@inktank.com> - 04:35 PM Revision 652056ed (ceph): mon: Properly handle errors from 'cmd_getval()' when needed
- Not handling the error return from cmd_getval() may leave uninitialzied
values, which can cause issues, specially wit... - 04:35 PM Revision 074c8808 (ceph): mon: Monitor: handle invalid 'quorum' command argument
- Don't rely on client side validation of possible command arguments.
Signed-off-by: Joao Eduardo Luis <joao.luis@inkt... - 04:35 PM Revision 01a0f2d3 (ceph): mon: OSDMonitor: don't rely on client-side validation for command argum...
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:57 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137408
- 03:03 PM Bug #7776 (Resolved): client lockdep crash
- 2014-03-18T14:50:40.839 INFO:teuthology.task.workunit.client.0.err:[10.214.131.15]: -3> 2014-03-18 14:48:00.14746...
- 03:45 PM Bug #7777 (Resolved): 2014-03-18T12:48:30.368 INFO:teuthology.task.rados.rados.0.err:[10.214.132....
- is_missing_object(snapdir)->wait_for_unreadable
2014-03-18T12:48:27.770 INFO:teuthology.task.thrashosds.thrasher:T... - 02:47 PM Revision fcbacff7 (ceph): Merge pull request #1489 from dachary/wip-7757
- erasure-code: disable SSE extensions
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com> - 02:46 PM Revision 543c642b (ceph): erasure-code: disable SSE extensions
- Until jerasure-2 / gf-complete is able to detect them at runtime.
http://tracker.ceph.com/issues/7757 refs #7757
Si... - 02:45 PM Revision bd12d376 (ceph): Merge pull request #1488 from dachary/wip-jerasure-2
- erasure-code: update jerasure v2 submodule
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com> - 02:32 PM rgw Bug #7702: osd thrashing + rgw = timeouts
- this affects the dumpling-x/stress-split tests, and *would* affect rados thrashing if we had an rgw workload in there.
- 02:28 PM rgw Documentation #7434 (In Progress): rgw: doc user/group quota
- I have a local branch where this is in progress. I'll try and put it up at the end of the week after I finish the rel...
- 02:25 PM Bug #7398: osd: ERANGE from clone
- Seems that there is a stale ssc from a previous interval (?) mucking up the calc_clone_subsets process. Testing a br...
- 12:36 PM Bug #7398: osd: ERANGE from clone
- ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137259/remote
With logging. - 01:54 PM Revision d7f3eb34 (ceph): knfs: make it a list
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:41 PM Bug #6633: osd: pgls vs osd restart/peering race misses objects
- backported to dumpling.
- 12:40 PM rgw Feature #7774 (Resolved): rgw: cache decoded user and bucket info
- Instead of having to access raw objects and then decode them for each request. Needs an invalidation mechanism that i...
- 12:34 PM Bug #7733: start_new_interval: always notify if !primary
- 12:30 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- 12:30 PM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 11:40 AM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 12:05 PM Feature #7767 (Fix Under Review): messenger:buffer reads
- 08:43 AM Feature #7767 (Resolved): messenger:buffer reads
- The way we read message involves with multiple smallish reads, which can have a big performance impact. Need to buffe...
- 11:22 AM RADOS Feature #7770 (New): "ceph osd crush set" should handle ingestion of non-compiled crush maps
- "ceph osd crush dump" will output a decompiled version of the crush map in a format of choice. It would be nice to be...
- 10:49 AM Bug #6806 (Pending Backport): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 09:42 AM Bug #6806 (Fix Under Review): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 10:39 AM Revision 1c5411a7 (ceph): erasure-code: update gf-complete v1 submodule
- Point to https://bitbucket.org/dachary/gf-complete/branch/v1 which
aggregates the pending pull requests required by C... - 10:08 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
- Yep, you need the xfs-dev headers to build Ceph now.
- 01:45 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- invalidate this bug report
- 01:38 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- in order to avoid these errors, i think we should check xfs lib , not xfs header file
- 01:36 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
- when i used configure.ac to config ceph, i get an error "configure: error: xfs/xfs.h not found (--without-libxfs to d...
- 09:24 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi,
well, there is nothing else in dmesg, except several hours before this hang.
This servers are running about... - 09:07 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi Olivier,
Can you attach the entire dmesg or at least a few minutes worth of
messages prior to the assertion fa... - 09:00 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- and in a 3.13.5 kernel too :...
- 08:47 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi,
same thing with a 3.13.5 kernel :... - 08:50 AM Revision d5e38d4a (ceph): erasure-code: update jerasure v2 submodule
- to include the latest compilation warning fixes.
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:17 AM Bug #7765: Bogus bandwidth statistics during pg creation
- On the attachment, around 09:40 is some actual client I/O maxing out the cluster. Around 09:55 is where I start crea...
- 08:13 AM Bug #7765 (Can't reproduce): Bogus bandwidth statistics during pg creation
Noticed this while growing the number of PGs in an existing pool on a cluster running firefly branch....- 07:18 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- About the systemd not playing well with ceph-deploy, I am still doubtful because the way ceph-deploy is working with ...
- 07:00 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- I tried to replicate this with ceph-deploy and boy was it a nightmare to get there.
FC19 panics a few seconds afte... - 05:28 AM CephFS Feature #7764 (Resolved): InoTable/SessionMap/ manipulator (cephfs-table-tool)
Some bugs might create a situation where the metadata/journal may be okay but recovery fails because one of the glo...- 05:25 AM CephFS Feature #7763 (Resolved): journal-tool: import
- Given a binary journal dump, insert it back into the metadata pool.
- 05:23 AM CephFS Feature #7762 (Rejected): journal-tool: backwards-search after corrupt regions
- When a corrupt region is encountered, use the start pointers to walk from the end of the log back to the latest valid...
- 05:22 AM CephFS Feature #7352: mds: make classes encode/decode-able
- related, on journal-tool branch have got to a point where dencoder can handle getting the inodes out of .inode object...
- 05:20 AM CephFS Feature #7761 (Resolved): journal-tool: forwards-search through corrupt regions
When corruption is encountered, search forward byte by byte for the next sentinel word.- 05:18 AM CephFS Feature #7760 (Resolved): journal-tool: implement splice
Simple implementation based on new ENoOp event type that allows us to selectively blank out regions in existing log.- 05:17 AM CephFS Feature #7759 (Resolved): journal-tool: roll in resetter/dumper from MDS
To provide the capabilities in one convenient place and remove a few LOC from the MDS.- 05:15 AM CephFS Feature #7758 (Resolved): journal-tool: complete filtering
- Already done:
--path
--range
Remaining to do:
--by-inode <inodeno>
--by-dirfrag <frag id>:[dentry]
--by-... - 03:56 AM Revision fb7b1f87 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:52 AM Revision 7bc9ade2 (ceph): Merge pull request #1384 from dachary/wip-7599
- upgrade jerasure to version 2
Reviewed-by: Sage Weil <sage@inktank.com> - 03:51 AM Revision 390f57b4 (ceph): Merge pull request #1486 from ceph/wip-cli-err
- ceph.in: Better error on bad arg to 'tell'
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 02:52 AM Feature #7757 (Resolved): erasure-code: enable jerasure-2 SSE optimizations
- gf-complete, the library used by jerasure-2, decides to use SSE instructions based on CPU features found at compile t...
- 01:41 AM Revision e26ad135 (ceph): Merge pull request #1479 from ceph/wip-rados-outfile
- tools/rados: Allow binary file output of omap data
Reviewed-by: Sage Weil <sage@inktank.com> - 01:39 AM Revision d0975d17 (ceph): Merge pull request #1480 from ceph/wip-remotebit-dump
- mds: Fix remotebit::dump for less common types
Reviewed-by: Sage Weil <sage@inktank.com> - 01:26 AM Revision 29976607 (ceph): knfs: async export
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:08 AM Revision 1822a1cc (ceph): Merge pull request #229 from dachary/wip-ec-pool
- ceph_manager: update ec_pool creation parameters
03/17/2014
- 11:48 PM Revision 6acfa6d6 (ceph): ceph_manager: update ec_pool creation parameters
- As of https://github.com/ceph/ceph/pull/1477 the erasure code parameters
are controled via the osd erasure-code-profi... - 11:26 PM Revision 27ed6569 (ceph): Merge pull request #1477 from dachary/wip-erasure-code-profiles
- replace properties with erasure code profiles
Reviewed-by: Sage Weil <sage@inktank.com> - 11:23 PM Revision 4f1b372e (ceph): osd: use erasure code profile when building the PGBackend
- The PGBackend::build_pg_backend() prototype is modified to add an
OSDMapRef which is used to get the profile stored i... - 11:23 PM Revision 57743447 (ceph): mon: add crush ruleset name to osd pool create
- The ruleset to be used for the new erasure coded pool was expected in
the properties, under the name crush_ruleset. I... - 11:23 PM Revision f8aa1eda (ceph): mon: set the profile and ruleset defaults early
- The poolstr is removed from the prepare_pool_crush_ruleset prototype
because it no longer decides for the default rul... - 11:23 PM Revision 5c1db3b6 (ceph): osd: create erasure_code_profile in OSDMap::build_simple
- The "default" erasure_code_profile is set by OSDMap::build_simple using
the osd_pool_default_erasure_code_profile def... - 11:23 PM Revision b85330eb (ceph): osd: create the erasure-code ruleset in OSDMap::build_simple
- Using the "default" profile, add the matching erasure-code ruleset.
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:23 PM Revision 8cf85f04 (ceph): mon: add osd crush create-erasure functional tests
- Cleanup the TEST_crush_rule_all function from redundant leftovers.
Explicitly test crush rule rm instead of implicitl... - 11:23 PM Revision b2730118 (ceph): osd,mon: use profile instead of properties
- The qa and functional tests are adapted to the new command prototype
requiring a profile instead of a list of propert... - 11:23 PM Revision eac224a4 (ceph): doc: update the erasure-code dev documentation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:23 PM Revision 063de51e (ceph): osd: obsolete pg_pool_t properties with erasure_code_profile
- The generic map properties is only used for erasure code and should be
specialized. It is obsoleted by a string that ... - 11:23 PM Revision 173e9580 (ceph): mon: OSDMonitor use erasure_code_profile instead of properties
- The prepare_pool_properties is replaced with the
parse_erasure_code_profile method which looks up the same content fr... - 11:23 PM Revision 04d2fd10 (ceph): mon: add the erasure-code-profile {set,get,rm,ls} MonCommand
- "erasure-code-profile set" parses the key=value pairs given in argument
and stores them in OSDMap::erasure_code_profi... - 11:21 PM Revision fa1d957c (ceph): mon/Paxos: commit only after entire quorum acks
- If a subset of the quorum accepts the proposal and we commit, we will start
sharing the new state. However, the mon ... - 11:19 PM Revision 1048763e (ceph): Merge remote-tracking branch 'gh/firefly'
- 11:16 PM Revision a42e197f (ceph): rados/monthrash: add pool create/delete tests
- This is sufficient to trigger #7736 when combined with mon thrashing and
mon msg delay injection.
Signed-off-by: Sag... - 11:11 PM Revision 2b90be2b (ceph): ceph_manager: default to 16 initial pgs per pool
- 1 is really too few for anything to happen at a
reasonable rate.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:11 PM Revision 847462b4 (ceph): ceph_manager::wait_for_clean: reset timeout if we make progress
- Fixes: #7748
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:03 PM Revision 76beb5ce (ceph): Merge pull request #1487 from ceph/wip-7738
- os/FileJournal: return errors on make_writeable() if reopen fails
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:37 PM Revision aed07440 (ceph): os/FileJournal: return errors on make_writeable() if reopen fails
- This is why #7738 is resulting in a crash instead of an error.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:34 PM Revision c31f38c7 (ceph): ReplicatedPG: if !obc->obs->exists, lock snapdir obc if exists
- Otherwise, backfill might slip in during a copyfrom.
Fixes: #7728
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:33 PM Revision 9ee10842 (ceph): ReplicatedPG: disallow trans which atomically create and remove an object
- There are a few problems with such a transaction:
1) We don't really have a way to represent it in the log
2) How doe... - 09:48 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Hello Greg,
Can we backport this fix to dumpling? - 08:52 PM Feature #7599 (Resolved): erasure-code : upgrade to jerasure-2
- 08:38 PM Bug #7755 (Resolved): auth_log selection depends on the primary identity and can cause a loop
- calc_ec_acting assumes the first valid osd will be primary, this is not necessarily so with primary affinity. We can...
- 07:15 PM Revision f0944003 (ceph): Add file to store mirror location of module's.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 07:10 PM Revision a4261af7 (ceph): Merge pull request #227 from ceph/wip-7749
- Pass '--object-sync-timeout 30' to radosgw-agent
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:00 PM Revision ef2edcd3 (ceph): Pass '--object-sync-timeout 30' to radosgw-agent
- http://tracker.ceph.com/issues/7749
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:42 PM Revision 7f177b3a (ceph): Merge pull request #226 from ceph/wip-7714
- prevent undefined values in finally block
- 04:49 PM Revision ec362e89 (ceph): Merge pull request #1481 from ceph/wip-tmap2omap-warn
- mds: avoid spurious TMAP2OMAP warning
Reviewed-by: Sage Weil <sage@inktank.com> - 04:33 PM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
- 09:12 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
- "work in progress":https://github.com/ceph/ceph/pull/1477
- 04:22 PM Bug #7736 (Pending Backport): mon: can expose stale state
- 03:29 PM Bug #7736: mon: can expose stale state
- 04:45 AM Bug #7736: mon: can expose stale state
- 04:43 AM Bug #7736: mon: can expose stale state
- This works for me.
Also noticed that a custom crafted message could trigger a commit with the old code. Apparentl... - 04:21 PM Revision a9f8a9e4 (ceph): ceph.in: Better error on bad arg to 'tell'
- Previously would get a rather enigmatic error:
UnboundLocalError: local variable 'ret' referenced before assignment... - 04:19 PM Revision 98e27d7b (ceph): Fix max_job_time timeout
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:12 PM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 10:48 AM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 04:04 PM Bug #7738 (Pending Backport): osd: journal crash on startup on wheezy
- 04:04 PM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- 03:40 PM Bug #7738 (Fix Under Review): osd: journal crash on startup on wheezy
- As far as I can tell the problem is that the journal symlink isn't always present when we reopen the journal for writ...
- 03:48 PM Revision 514b5e3e (ceph): mon: add helper to selection functions implementing tests
- The call_TEST_functions will lookup SHARE_MON_TEST_* shell functions and
run them after creating a mon. Each is expec... - 03:48 PM Revision 1a451f2e (ceph): mon: functional tests teardown must be run on error
- otherwise daemons will keep running and interfere with tests happening
afterwards.
Signed-off-by: Loic Dachary <loic... - 03:48 PM Revision e4b4b1f1 (ceph): osd: OSDMap::erasure_code_profile accessors
- For both the incremental and the OSDMap fields.
Signed-off-by: Loic Dachary <loic@dachary.org> - 03:48 PM Revision c4f8f265 (ceph): osd: add OSDMap::erasure_code_profile
- A map of key=value properties to be interpreted by the erasure code
plugins. For instance profile["default"] = { "k":... - 03:43 PM Revision bdd96c62 (ceph): mon/Elector: bootstrap on timeout
- Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This... - 03:43 PM Revision a3e57b72 (ceph): mon: only learn peer addresses when monmap == 0
- It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ... - 03:43 PM Revision 68fcc63c (ceph): mon: tell MonmapMonitor first about winning an election
- It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i... - 03:43 PM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- 10:04 AM Bug #7713: "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:parallel-firef...
- actually, the problem is probably that dumpling still has the bug.
- 10:03 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- this was #7709, now fixed
- 03:42 PM Revision 2b9bd267 (ceph): mds: avoid spurious TMAP2OMAP warning
- The message "one or more OSDs do not support TMAP2OMAP" was printed
incorrectly when zero OSDs were up (and therefore... - 03:37 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
- commit:5e7a98911e6a6db525d65981034d28065a045e47
- 03:28 PM Revision e073a062 (ceph): mon: tell MonmapMonitor first about winning an election
- It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i... - 03:28 PM Revision 143ec028 (ceph): mon/Elector: bootstrap on timeout
- Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This... - 03:27 PM Revision 21ed5420 (ceph): ceph.in: do not allow using 'tell' with interactive mode
- This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult... - 03:19 PM Revision 4f1a56ed (ceph): Merge pull request #1483 from ceph/wip-7611.emperor
- mon: Monitor: make sure received command is valid before handling it
Reviewed-by: Sage Weil <sage@inktank.com> - 03:17 PM Revision 35aed15f (ceph): Merge pull request #1482 from ceph/wip-7611
- ceph.in: do not allow using 'tell' with interactive mode
Reviewed-by: Sage Weil <sage@inktank.com> - 03:10 PM Revision 1996fd89 (ceph): mon: only learn peer addresses when monmap == 0
- It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ... - 02:49 PM Revision d0fc52d9 (ceph): ceph.in: do not allow using 'tell' with interactive mode
- This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult... - 02:49 PM Revision 57c8fd96 (ceph): prevent undefined values in finally block
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:48 PM Revision 78d94cd1 (ceph): mon: Monitor: make sure received command is valid before handling it
- Fixes: 7611
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 02:48 PM Revision 7e9ece25 (ceph): Monitor: pull command mapping out of _allowed_command()
- We want to be able to validate commands against both the leader and
local command sets, so make that functionality ge... - 02:44 PM Revision e39c213c (ceph): ceph.in: do not allow using 'tell' with interactive mode
- This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult... - 02:42 PM Revision 8f542dba (ceph): schedule_suite.sh: turn up journal log too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:42 PM Revision d3c294d2 (ceph): Make distro kernels work on Trusty.
- Some grub changes and package names caused them to fail on trusty.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> - 02:28 PM Revision b2af217b (ceph): mds: Fix remotebit::dump for less common types
- This was hitting an assertion when used on anything
other than a regular/symlink/dir. Now covers
all types.
Signed-... - 01:56 PM Revision eb6cd3a6 (ceph): nkfs: 6h timeout of kernel build
- Yes, NFS reexport is slow. But at the moment appears to be reliable.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:56 PM Revision 9d77ce17 (ceph): tools/rados: Allow binary file output of omap data
- Extends getomapval and getompaheader to take an output
file argument the same way 'get' does. Removes misleading
'-o... - 01:53 PM rbd Feature #7746: Capacity Management: rbd df
- Confirmed that this doesn't just affect RBD pools but affects any pool, as the data is generated from reading the off...
- 10:14 AM rbd Feature #7746 (Resolved): Capacity Management: rbd df
- Currently, ceph df shows two sets of statistics: global and pool.
For global, the output is generated from aggrega... - 01:22 PM Bug #7751 (Closed): os: LevelDBStore: needs to check iter->status() during get()
- We are ignoring the status of the iterator during 'LevelDBStore::get()' -- we're also ignoring the state of the itera...
- 01:04 PM CephFS Bug #7750 (Can't reproduce): Attempting to mount a kNFS export of a sub-directory of a CephFS fil...
- Hi,
I have run into the following issue when trying to export a subset of a CephFS filesystem via NFS:
Machine ... - 01:03 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
- This looks like network issues - the run was killed, so there are no logs from radosgw to confirm.
- 01:00 PM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
- Fixed in teuthology commit:ef2edcd3a96a2118d793b7a102688f60fa100f52
- 11:58 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
- A different approach: https://github.com/ceph/teuthology/pull/227
- 11:23 AM rgw Bug #7749 (Fix Under Review): radosgw-agent: worker.DataWorker.wait_for_object() should bail on r...
- 11:22 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
- https://github.com/ceph/radosgw-agent/pull/9
- 11:16 AM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
- Currently, the method will do this forever if a connection goes down:...
- 10:40 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
- 10:09 AM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
- whitelisted this
- 10:03 AM Feature #7717: Per CRUSH bucket used/available space
- 09:22 AM Fix #6780 (Closed): monitor errors when checking for quorum status
- 09:13 AM Fix #6780: monitor errors when checking for quorum status
- can no longer reproduce this on firefly. any objections on closing?
- 08:48 AM Revision d4d6ff07 (ceph): mon,osd,erasure-code: update copyright notices
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:48 AM Revision bcc74879 (ceph): common,erasure-code,mon: s/erasure-code-//
- The parameters to erasure code do not need to be prefixed with the
erasure-code- string. There only are erasure-code ... - 08:48 AM Revision de62572c (ceph): erasure-code: remove dependency to the global context
- Instead of relying on derr to display error messages, add them to an
ostream parameter given in argument to load() an... - 08:48 AM Revision e6d9066f (ceph): erasure-code: add ostream to factory()
- Modify calls to ErasureCodePlugin::factory() to provide the new
ostream argument.
Signed-off-by: Loic Dachary <loic@... - 08:48 AM Revision be319983 (ceph): erasure-code: make libcommon include liberasure-code
- So that it can be used in OSDMap which is part of libcommon.
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:48 AM Revision 6a16eac7 (ceph): mon: create crush_ruleset_create_erasure helper
- Move the code bloc verbatim, from "osd crush rule create-erasure" to the
new crush_ruleset_create_erasure() method he... - 08:48 AM Revision 402e646a (ceph): mon: crush_ruleset_create_erasure reduce verbosity
- Only add error message to the stream, not informative messages because
they depend on the caller context.
Signed-off... - 08:48 AM Revision 8e07dbc0 (ceph): mon: crush_ruleset_create_erasure error codes
- Replace goto reply with error return and meaningfull error codes.
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:48 AM Revision 370e000e (ceph): mon: crush_ruleset_create_erasure set ruleset
- Use get_rule_id() instead of rule_exists() to test the existence of a
ruleset and preserve the ruleset.
Signed-off-b... - 08:48 AM Revision 96224883 (ceph): mon: crush_ruleset_create_erasure s/rule/err/
- Avoid using rule instead of ruleset to help clarify the
terminology. Using err instead is also clearer in the context... - 08:48 AM Revision 3bc607ae (ceph): mon: crush_ruleset_create_erasure indent
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:48 AM Revision 9850ab27 (ceph): mon: crush_ruleset_create_erasure s/_map//
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:48 AM Revision cf259461 (ceph): mon: create-erasure uses crush_ruleset_create_erasure
- Create the ruleset and branch depending on the result:
* If it succeeds, wait
* If it already exists and is pending ... - 08:48 AM Revision 32e122bd (ceph): mon: add pool name to prepare_pool_crush_ruleset
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:48 AM Revision b7db487a (ceph): mon: pool create erasure implicit ruleset creation
- If the crush_ruleset parameter is missing, set it to the pool name.
If the crush_ruleset parameter is set to a name ... - 08:48 AM Revision 29862f6f (ceph): mon: tests for pool create erasure implicit ruleset creation
- * Remove the tests checking that a missing or wrong crush_ruleset
parameters triggered an error.
* Add a test check... - 08:19 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
- 08:00 AM Bug #7611 (Fix Under Review): All mon nodes crash when running "ceph tell osd.X" and using the "v...
03/16/2014
- 07:57 PM Revision bf7f773b (ceph): Merge pull request #1462 from ceph/wip-cache-last-epoch-clean
- mon: fix caching for min_last_epoch_clean
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:12 PM Revision ce9bfb87 (ceph): Merge pull request #1474 from ceph/wip-7740
- OSD::handle_pg_query: on dne pg, send lb=hobject_t() if deleting
Reviewed-by: Sage Weil <sage@inktank.com> - 05:32 PM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 31a667918069ac72c70080dcacd6ff3b6d58f07b
- 04:37 PM Revision 2f9a7484 (ceph): Merge pull request #1473 from ceph/wip-7719
- PG: clear want_pg_temp in clear_primary_state only if primary
Reviewed-by: Sage Weil <sage@inktank.com> - 03:26 PM Feature #7662 (In Progress): add a "ec profiles" map to OSDMap
- 10:36 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
- *ABANDONNED* "work in progress":https://github.com/ceph/ceph/pull/1475
I've set it to urgent so someone can decide... - 12:54 PM Bug #7744 (Can't reproduce): osd: assert(last_e.version.version < e.version.version)
- I currently have 2 OSDs that won't start and it's preventing my
cluster from running my VMs.
My cluster is running ... - 12:11 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 12:10 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133582...
- 12:09 PM rgw Bug #7742 (Resolved): FAIL: s3tests.functional.test_s3.test_region_bucket_create_master_access_re...
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587
this may be a dup of the... - 12:08 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587...
- 09:36 AM Bug #7719 (Resolved): failed to become clean
- 04:47 AM Revision e9a3c8e2 (ceph): Merge pull request #1471 from ceph/wip-7684
- client: force getattr when inline data is missing
Reviewed-by: Sage Weil <sage@inktank.com> - 04:42 AM Revision 1ae33147 (ceph): client: force getattr when inline data is missing
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 02:39 AM Revision 4fdeafef (ceph): Merge pull request #1467 from ceph/wip-7684
- Wip 7684
http://pulpito.ceph.com/sage-2014-03-15_09:12:44-fs-wip-7684-testing-basic-plana
Reviewed-by: Sage Weil <s... - 12:58 AM Revision 04de7817 (ceph): OSD::handle_pg_query: on dne pg, send lb=hobject_t() if deleting
- We will set lb=hobject_t() if we resurrect the pg. In that case,
we need to have sent that to the primary before han...
03/15/2014
- 10:30 PM Revision 4dd94a00 (ceph): Merge pull request #1469 from ceph/wip-7718
- PG::issue_repop: only adjust peer_info last_updates if not temp
Reviewed-by: Sage Weil <sage@inktank.com> - 10:29 PM Revision 677b30c3 (ceph): Merge pull request #1468 from ceph/wip-7732
- PG::build_might_have_unfound: check pg_whomai, not osd whoami
Reviewed-by: Sage Weil <sage@inktank.com> - 08:58 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-15_17:09:08-rados:thrash-firefly-distro-basic-plana...
- 08:16 PM Revision affcc119 (ceph): Merge pull request #1470 from ceph/wip-7712
- osd/ReplicatedPG: fix enqueue_front race
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:39 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
- 06:12 PM Revision 2c875593 (ceph): multimds: fix misc -> fs/misc paths
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:39 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 05:07 PM Bug #7736 (Fix Under Review): mon: can expose stale state
- 02:15 PM Bug #7736: mon: can expose stale state
- This *is* committed state. Looks like we need to wait for everybody to ack or for leases to expire before responding ...
- 09:52 AM Bug #7736 (Resolved): mon: can expose stale state
- teuthology-2014-03-14_19:00:49-rados-dumpling-testing-basic-plana/130941
here is a deletion on the primary:... - 04:55 PM Revision 9e218402 (ceph): mds: include inline data in lock messages
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 04:54 PM Revision 5b3422a6 (ceph): mds: fix corner case of pushing inline data
- Following sequence of events can happen.
- Client releases an inode, queues cap release message.
- A 'lookup' reply... - 04:18 PM Revision 75971726 (ceph): upgrade/dumpling-x/stress-split: tolerate legacy crush tunables
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:17 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
- 03:30 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 03:30 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 11:15 AM CephFS Bug #7739 (Resolved): mds: uninitialized field in message
- ubuntu@teuthology:/a/teuthology-2014-03-14_23:01:36-multimds-master-testing-basic-plana/131675
hard to map this to... - 10:10 AM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- ubuntu@teuthology:/a/sage-wheezy/130813...
- 10:09 AM Bug #7737 (Resolved): osd: deletes vs backfill makes degraded go negative
- this is the tail end of a rados bench run that was outpacing backfill. once it started to delete objects, the degrad...
- 04:52 AM Revision b2fcc6e1 (ceph): Remove code duplication from s3 tests.
- A new module, s3_utilities.pm has been created. It contains
subroutines common to at least two of the workunits in t... - 01:00 AM Revision 979e8b44 (ceph): PG::build_might_have_unfound: check pg_whomai, not osd whoami
- Otherwise, we might skip (2,0) when we are (2,1).
Fixes: #7732
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- I'm 90% sure this is systemd killing everything in the cgroup when ceph-deploy's ssh session closes. The log file ju...
03/14/2014
- 11:32 PM Revision 0f75c541 (ceph): osd/ReplicatedPG: fix enqueue_front race
- When requeuing and item at the front, we need to shuffle the items in
pg_for_processing if there is an entry for this... - 10:53 PM Revision 5322ecb2 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 10:52 PM Revision ef1d7c91 (ceph): rados.py: Fixed docstring syntax warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:49 PM Revision f476c968 (ceph): Merge pull request #19 from ceph/wip-print
- added print task
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:46 PM Revision 02b746d4 (ceph): doc: Fixed release notes syntax warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:46 PM Revision 752380dc (ceph): added print task
- 10:45 PM Revision 9cd67bb2 (ceph): doc: Fixed hyperlink.
- Fixes: #7558
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:26 PM Revision c6214f86 (ceph): Merge pull request #1463 from ceph/wip-7698
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 10:19 PM Revision 31a66791 (ceph): tools: Fix ceph_filestore_dump to fully operate on EC pools
- Add spg_t and ghobject_t handling
Fixes: #7698
Signed-off-by: David Zafman <david.zafman@inktank.com> - 10:19 PM Revision 599a8d7f (ceph): test: Add ceph_filestore_dump.sh to test ceph_filestore_dump
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 10:18 PM Revision f633a03e (ceph): tools: Cleanups in ceph_filestore_dump
- Fix usage output of ceph_filestore_dump
Add missing error checking
Output full object name
Improve message consistenc... - 09:48 PM Revision bbc0d6dd (ceph): PG::issue_repop: only adjust peer_info last_updates if not temp
- Temp object repops have version eversion_t() since they don't
actually send log entries. Updating the last_updates h... - 08:30 PM Revision 35f1b042 (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
- CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload... - 08:29 PM Revision 0a0c1caf (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
- CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload... - 08:29 PM Revision be0205c3 (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
- CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload... - 08:26 PM Bug #7735: osd: priorityqueue debug dump crashes
- wip-pq
- 08:21 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
- discovered when doing backfill testing with wip-pq:...
- 08:23 PM Revision ab91b808 (ceph): mon/OSDMonitor: fix fall-thru case
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:21 PM Revision 0e0a9dbf (ceph): Merge remote-tracking branch 'gh/firefly'
- 08:20 PM Revision 208959a0 (ceph): mon/PGMap: cache min_last_epoch_clean
- We call this a lot. Only recalculate when we decode or when we apply
an incremental.
Adjust unit test accordingly.
... - 08:20 PM Revision fc850751 (ceph): mon/PGMap: only recalculate min_last_epoch_clean if incremental touches...
- If the Incremental updates a value that used to equal the old min, we may
have raised it and need to recalculate it a... - 08:19 PM Revision e941feff (ceph): unittest_ceph_argparse: fix warnings
- In file included from test/ceph_argparse.cc:17:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::Assertion... - 08:19 PM Revision 6f9db6c7 (ceph): unittest_mon_pgmap: fix warnings
- In file included from test/mon/PGMap.cc:15:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::AssertionResu... - 08:15 PM Revision f2c6ff33 (ceph): tools/: make filenames consistent
- _ for source files, - for (shippable) build targets.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:11 PM Revision f2ac06bf (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140312'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 08:09 PM Revision e3300978 (ceph): PG: clear want_pg_temp in clear_primary_state only if primary
- Clearing it in that way in on_shutdown() can cause a stray
shard to clobber the want_pg_temp value created by the pri... - 08:04 PM Revision 74ad3e30 (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140409'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:42 PM Revision 5873b0f0 (ceph): Merge remote-tracking branch 'gh/wip-da-SCA-firefly-20140304'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:36 PM Revision 984f1c3d (ceph): Merge pull request #1454 from ceph/wip-7709
- osd/ReplicatedPG: release op locks on on commit+applied
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by:... - 06:28 PM Revision bb755167 (ceph): Merge pull request #1459 from ceph/wip-7696
- Wip 7696
Reviewed-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision da159f8c (ceph): doc/release-notes: note that radosgw's should be upgraded together
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:05 PM Revision a2f3b309 (ceph): Merge pull request #1461 from ceph/wip-7692
- mon: on timecheck on monmap 0
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 06:03 PM Revision a3719e0a (ceph): Merge pull request #1460 from ceph/wip-warning
- PGLog: remove unused variable
Reviewed-by: Sage Weil <sage@inktank.com> - 06:03 PM Bug #7732: stuck recovering with unfound -- build_might_have_unfound bug
- 05:58 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 06:02 PM Revision f1bd59f8 (ceph): mon: only do timecheck with known monmap
- If we are still on monmap epoch 0, our mon ranks cannot yet be trusted
since there is not yet a shared source of trut... - 06:00 PM Revision fba88de1 (ceph): ceph-mon: be a bit more verbose on error
- Motivated by #7489
Signed-off-by: Sage Weil <sage@inktank.com> - 05:59 PM Bug #7733 (Resolved): start_new_interval: always notify if !primary
- 05:57 PM Revision 62af51cb (ceph): PG::activate: handle peer contigious with primary, but not auth_log
- The added case covers a situation where a replica is not contiguous with
the auth_log, but is contiguous with the pri... - 05:51 PM Revision 6aa5d4f1 (ceph): Merge pull request #1458 from ceph/wip-7489
- ceph_mon: split postfork() in two and finish postfork just before daemonize
Reviewed-by: Sage Weil <sage@inktank.com> - 05:45 PM Revision 70d87df7 (ceph): ceph_mon: output error message if unable to bind.
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:44 PM Revision 5ad9c166 (ceph): ceph_mon: all output after initial fork go to dout/derr
- We were doing it in some cases, and not doing in some other cases. Just
do it throughout.
Signed-off-by: Joao Eduar... - 05:39 PM Revision c95234ac (ceph): ceph_mon: split postfork() in two and finish postfork just before daemo...
- We split global_init_postfork() in two: start and finish, with the first
keeping much of postfork()'s tasks except cl... - 05:29 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
- I grabbed and compiled the patched version of FastCGI as a DSO from here:
https://github.com/ceph/mod_fastcgi.git
... - 05:03 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
- I'm not sure we actually require it. You're not using the modified fastcgi module and therefore chunked encoding is n...
- 03:52 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
- We are using the S3 SDK and I am getting a return from RGW claiming that Content-Length must be set. However, accordi...
- 05:05 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan Mick wrote:
> I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is t... - 04:52 PM Bug #7712: osd: ENOENT following copy-from
- it looks like the requeues get in all sorts of weird orders:
grep --color=auto 3\\.2\( remote/*/log/*osd.5* | egre... - 04:45 PM Bug #7712: osd: ENOENT following copy-from
- grep dequeue_op remote/*/log/*osd.5* | grep plana2926152-290
osd.5.3:79 and osd.1.3:681 get reordered
when they... - 10:33 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
- 2014-03-14T09:47:00.894 INFO:teuthology.task.rados.rados.0.out:[10.214.131.11]: 2625: delete oid 290 current snap is ...
- 04:36 PM Bug #7659 (In Progress): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing()....
- 04:20 PM rgw Documentation #7731 (Resolved): Warning about "rgw print continue" should be added to radosgw con...
- Here,
http://ceph.com/docs/dumpling/radosgw/config/
Just as there is a warning to turn off FastCgiWrapper on Ce... - 03:59 PM Documentation #6465: admin/build-doc should have some kind of build check for broken links
- Actually, it seems like the :ref: syntax at least catches a file name mismatch. We should probably begin converting t...
- 03:57 PM Documentation #7558 (Resolved): broken link in install/manual-deployment/
- Fixed. The file name was incorrect. Probably should be using :ref: syntax instead.
- 03:31 PM Revision 22c461b5 (ceph): upgrade/dumpling-x: more mon scrub whitelist
- There are two log messages; whitelist them both
Signed-off-by: Sage Weil <sage@inktank.com> - 03:30 PM Revision 5676d6e5 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:29 PM Revision ceac36b2 (ceph): doc/release-notes: 0.78 draft nodes; firefly draft notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:21 PM Revision 2e487d8a (ceph): knfs: test v3 and v4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:13 PM Documentation #7729 (Closed): CAPS with dot (.) notation can be unquoted
- Authentication documentation should indicate that CAPS with dot notation do not have to be quoted any longer.
htt... - 03:10 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- 01:28 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- ...
- 02:51 PM Bug #7728 (Resolved): osd/ReplicatedPG.cc: 4999: FAILED assert(got)
ceph version 0.77-859-g0bf5b52 (0bf5b52ae035d9893b5d079abee05bb3114ef51e)
1: (ReplicatedPG::finish_ctx(Replicate...- 02:47 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 02:46 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- issue_repop sets the last_update for stored peer_info to repop->v which is eversion_t() for temp objects. Testing fix.
- 12:58 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- ...
- 02:37 PM Feature #7698: Add EC handling to ceph_filestore_dump
- Ready to go into either master or firefly branches.
- 02:17 PM Documentation #7727 (Resolved): CRUSH "chassis" bucket type
- We should note that there is a new "chassis" default bucket type. It might go here:
http://ceph.com/docs/master/ra... - 02:09 PM Documentation #7726 (Resolved): Quick Start Requires Updating
- With size = 3 by default, the cluster as defined by the quick start guide will never get to an active + clean state u...
- 02:06 PM Documentation #7725 (Resolved): osd pool default size need updating
- The default value for size is now 3.
http://ceph.com/docs/master/rados/configuration/pool-pg-config-ref/ - 02:04 PM Documentation #7724: filestore xattr use omap removed
- It's a good idea to doc it, but in general we don't support reverting versions and should not give the appearance of ...
- 02:01 PM Documentation #7724 (Resolved): filestore xattr use omap removed
- Ceph Documentation needs to indicate that filestore xattr use omap was removed and specify the version. Users reverti...
- 01:59 PM Feature #7723 (New): Cancel RADOS Bench writes and still do reads
- Right now in RADOS bench if you write some data out with the --no-cleanup flag but ctrl+c or kill the process before ...
- 01:55 PM devops Cleanup #7722 (Resolved): Make /admin/build-doc distro independent
- The script for building Ceph documentation under admin/build-doc is currently Debian/Ubuntu only. This limits communi...
- 01:52 PM Documentation #7721 (Closed): Document the process to migrate from RBD format 1 to format 2 images
- There is a mention of that in the RBD man page, but I think we should also document it on ceph.com with some warning ...
- 01:08 PM Bug #7719 (Resolved): failed to become clean
- Stuck in remapped due to deleted pg shard clobbering want_pg_temp from primary.
2014-03-14T08:07:26.245 INFO:teuth... - 01:00 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Still getting these crashes multiple times a week across a dozen guests on separate hosts. These guests are video sur...
- 12:51 PM Feature #7717 (Closed): Per CRUSH bucket used/available space
- When using multiple pools spread across different failure domains it can be difficult to know how much space is avail...
- 12:30 PM devops Feature #7716 (Resolved): Build debug packages for EL6
- The debug packages for el6 are not available for releases >0.67.3.
http://ceph.com/rpm-dumpling/el6/x86_64/
http:... - 12:07 PM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---...
- 11:51 AM Bug #7216 (Can't reproduce): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 09:43 AM Bug #7216 (New): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 11:35 AM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
- 11:28 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 11:22 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---...
- 11:05 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
- 05:50 AM Bug #7692: mon: monitor fails to form quorum
- We are now seeing a more generalized failure were no monitor is able to form quorum (from ceph-deploy):...
- 10:51 AM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
- 06:02 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- Here's the thing: as is, ceph-mon is being run as a daemon. That entails dissociating it from its running terminal, ...
- 05:10 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- Tools like 'ceph-mon' are used by other tools to abstract ceph management and those tools will almost always check ex...
- 04:48 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- This only happens when the monitor is running as a daemon, which I would think is the expected result: all output is ...
- 10:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- 09:59 AM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
- 09:57 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- That doesn't seem like it's addressing the issue the right way. We've deliberately set it so that PGs which don't get...
- 09:40 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- How about this: in OSDService, add
Mutex pg_epoch_lock;
Cond pg_epoch_cond;
multiset<epoch_t> pg_epochs;
ma... - 09:50 AM Fix #7711 (New): OpTracker output doesn't include op size for subops
- Been discussing the OpTracker dumps on the mailing list and realized the subops don't contain transaction size inform...
- 09:49 AM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
- d0d21fae483cfaf5556b18b2f0e113c7d418e90c Landed to Firefly
- 09:44 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:44 AM Bug #7626 (New): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:42 AM Bug #7497 (Can't reproduce): timeout waiting to go clean
- 09:34 AM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
- I think we need a log for this.. hopefully we will hit it now that things are cranked up on the nightlies?
- 09:21 AM Bug #7710 (Fix Under Review): Multiple rados bench instance will overwrite the metadata object
- 06:53 AM Bug #7710: Multiple rados bench instance will overwrite the metadata object
- Please help to review the pull request - https://github.com/ceph/ceph/pull/1457
- 06:48 AM Bug #7710 (Resolved): Multiple rados bench instance will overwrite the metadata object
- rados bench is useful to benchmark the cluster, however, there is one user case it does not support: read after write...
- 07:45 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- So don't forget the patch I got accepted into libvirt a few weeks ago.
If you are running a RBD storage pool it wi... - 05:02 AM Revision 87c911ce (ceph): osd/ReplicatedPG: release op locks on on commit+applied
- We were releasing the op locks when we applied the update but (potentially)
before we committed it. This means that ... - 04:37 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- 02:12 AM Revision b125c95f (ceph): Merge pull request #18 from ceph/wip-knfs-fsstress
- knfs: add fsstress and kernel build
- 01:34 AM Revision 4773a277 (ceph): knfs: add fsstress and kernel build
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 01:14 AM Revision 4f43e53c (ceph): Merge pull request #1450 from ceph/wip-7641
- debian: make ceph depend on ceph-common >= 0.67
Reviewed-by: Loic Dachary <loic@dachary.org> - 12:42 AM Revision e1694b4c (ceph): knfs: restructure a bit
- Separate cluster buildup from tasks.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:39 AM Revision 7b0eda03 (ceph): nfs -> knfs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:38 AM Revision c5b557ee (ceph): qa/workunits: misc -> fs/misc
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:36 AM Revision adca6464 (ceph): workunits/misc -> fs/misc
- Signed-off-by: Sage Weil <sage@inktank.com>
03/13/2014
- 11:44 PM Revision 8c8b3e97 (ceph): PGLog: remove unused variable
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:43 PM Revision 89c3d97c (ceph): Merge pull request #1442 from ceph/wip-magic-bad
- osd: tunables instead of hard-coded target dirty/full ratios
Reviewed-by: Greg Farnum <greg@inktank.com> - 11:38 PM Revision fa6887b9 (ceph): osd: set default cache_target_{dirty,full}_ratios based on configurable
- These were hard-coded in the pg_pool_t constructor, but that was a dumb
idea.
Note that decoding legacy pg_pool_t's ... - 11:38 PM Revision 282497e8 (ceph): osd: add tunables for cache_min_{flush,evict}_age
- Why not.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:27 PM Revision 8b4c8cbf (ceph): upgrade/dumpling-x: whitelist mon scrub mismatch
- A mixed dumpling/firefly cluster will have each mon independently encode
the full map. Firefly now puts feature bits... - 11:24 PM Revision c452de17 (ceph): Merge pull request #1452 from ceph/wip-7706
- Wip 7706
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:53 PM Revision d0d21fae (ceph): Merge pull request #1447 from ceph/wip-7703
- rgw: manifest hold the actual bucket used for tail objects
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:41 PM Bug #7709 (Fix Under Review): osd: RWORDERED does not order reads ack vs write commit
- 10:02 PM Bug #7709: osd: RWORDERED does not order reads ack vs write commit
- 09:58 PM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
- We just fixed ceph_test_rados to wait for commit, not ack. It turns out that the RWORDERED flag is ordering a
wr... - 10:17 PM Revision a72b636b (ceph): mds: fix empty fs rstat
- In 81bcf43080a7be8a48aa13b88287cbfac0e01e3e we removed the .ceph directory
but did not adjust the rsubdirs back to 0.... - 10:15 PM Revision 5ec49360 (ceph): Merge remote-tracking branch 'gh/firefly'
- 09:57 PM Revision 2bbf5511 (ceph): ceph_test_rados: wait for commit, not ack
- First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha... - 09:55 PM Revision 6c3d4fbe (ceph): ceph_test_rados: wait for commit, not ack
- First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha... - 09:52 PM Revision eaf0cdc4 (ceph): Merge pull request #1449 from ceph/wip-7705
- ceph_test_rados: wait for commit not ack
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <g... - 09:49 PM Revision f2124c58 (ceph): ceph_test_rados: wait for commit, not ack
- First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha... - 09:49 PM Revision dd946e0a (ceph): MOSDOp: include reassert_version in print
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:10 PM Bug #7498 (Resolved): stuck in recovery
- 09:09 PM Bug #7210: mon: does not validate snapshot removal commands
- I would like to see this in the wild before doing the backport.
- 09:08 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Jasper Siero wrote:
> I submitted the new log with debug mon = 10 added to the ceph.conf.
> The two processes belo... - 05:09 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- I submitted the new log with debug mon = 10 added to the ceph.conf.
The two processes below also keeps running afte... - 09:07 PM Revision 73f6b4cb (ceph): config_opts: raise ms_pq_max_tokens_per_priority to 16MB
- Recovery messages can get pretty big.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:04 PM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- 09:04 PM Revision 2722a0a4 (ceph): PrioritizedQueue: cap costs at max_tokens_per_subqueue
- Otherwise, you can get a recovery op in the queue which has a cost
higher than the max token value. It won't get ser... - 09:01 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- ...
- 08:28 PM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- ...
- 11:01 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- And again:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_23:00:26-fs-firefly-testing-basic-plana/127977/... - 08:15 PM Revision d72335fe (ceph): Merge remote-tracking branch 'gh/firefly'
- 06:33 PM Revision 724f30e8 (ceph): client: Add lookup_parent & lookup_name
- Exposing the CEPH_MDS_OP_LOOKUPPARENT and
recently added CEPH_MDS_OP_LOOKUPNAME operations.
lookup_ino and lookup_pa... - 06:33 PM Revision d2ce0294 (ceph): libcephfs: add ceph_ll_lookup_inode
- This is a wrapper to lookup_ino, lookup_parent
and lookup_name, to provide the
caller with the requested inode and it... - 06:33 PM Revision 88cb1c49 (ceph): tools: Create ceph-client-debug
- For exposing test/dev functionality which uses
the cephfs client interface.
Initially just provides lookup-by-ino.
... - 06:30 PM Revision f1f28268 (ceph): mds: Return EINVAL for parent lookup on root ino
- This was the behaviour before 8d6b25a1, and distinguishes
the general failure to find a parent (ESTALE) from the spec... - 06:25 PM Revision a19ef011 (ceph): rgw: manifest hold the actual bucket used for tail objects
- Fixes: 7703
Object can be copied between different buckets, so we need to keep track
of which bucket is used for nami... - 06:24 PM Revision 33b889f3 (ceph): rbd-fuse: fix signed/unsigned warning
- rbd_fuse/rbd-fuse.c: In function 'enumerate_images':
rbd_fuse/rbd-fuse.c:113:2: warning: comparison between signed an... - 05:48 PM Revision c973e46c (ceph): mds/Mutation.h: init export_dir with NULL in ctor
- CID 1188167 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "export_d... - 05:39 PM Revision fd383a95 (ceph): mds/Migrator.h: init some members of import_state_t in ctor
- CID 1188166 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "state" is... - 05:30 PM Revision 5a53aa82 (ceph): mds/Migrator.h: init some export_state_t members in ctor
- CID 1188165 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "state" is... - 04:59 PM Revision b10692fb (ceph): CInode::encode_cap_message: add assert for cap
- CID 716913 (#1 of 1): Dereference after null check (FORWARD_NULL)
5. var_deref_op: Dereferencing null pointer "cap".
... - 04:50 PM Revision 2daed5ff (ceph): test-upgrade-firefly: skip watch-notify system test
- This also fails on mixed version clusters due to watch on a
non-existent object returning ENOENT in firefly and 0 in ... - 04:35 PM Bug #7648 (Won't Fix): ceph-mon corner case denial of service
- This only works on osd.0; for other osds, both dumpling and emperor behave (with bogus output)...
- 04:28 PM Bug #7706 (Pending Backport): osd: PrioritizedQueue can starve
- 01:58 PM Bug #7706 (Resolved): osd: PrioritizedQueue can starve
- starvation caused by pq max token limit
- 04:27 PM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
- 09:30 AM Bug #7704 (In Progress): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-...
- I think this is a manifestation of the full osdmap encoding features, which aren't specified for dumpling and can thu...
- 08:59 AM Bug #7704: "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-plana suite
- Also see in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---...
- 08:55 AM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---...
- 04:21 PM Revision 58e35a4b (ceph): test_filejournal.cc: use strncpy and terminate with '\0'
- CID 966632 (#1 of 1): Copy into fixed size buffer (STRING_OVERFLOW)
2. fixed_size_dest: You might overrun the 200 by... - 04:10 PM Bug #7635 (Duplicate): failed to recover before timeout expired
- 03:44 PM Revision 0073bc25 (ceph): Merge pull request #1433 from fractalcat/fix-crypto-init-race-condition
- Work around race condition in libnss
Reviewed-by: Sage Weil <sage@inktank.com> - 03:40 PM Revision bc7aa221 (ceph): Merge pull request #1443 from fghaas/doc-fix
- doc: fix formatting on PG recommendation
Reviewed-by: Sage Weil <sage@inktank.com> - 03:32 PM Bug #7208 (Resolved): CEPH_FEATURE_CRUSH_V2 feature mismatch
- this was fixed when i fixed up the default crush tunables to be firefly not optimal
- 03:27 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats
- 06:53 AM CephFS Bug #7565: Failed assert in check_rstats
- ubuntu@teuthology:/a/teuthology-2014-03-12_04:55:11-multimds-master-testing-basic-plana/127691
failed on trivial_s... - 02:59 PM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- 11:39 AM Bug #7705: ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong version")
- wip-7705
- 10:01 AM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- ...
- 02:22 PM Revision 44aaaaff (ceph): Work around race condition in libnss
- This change prevents a segfault in ceph::crypto::init when using NSS and
calling rados_connect from multiple threads ... - 02:22 PM Revision a2784baa (ceph): Add unit test for race condition in libnss
- This isn't in test/crypto.cc because common_init_finish is called prior
to running any tests. Will not build the test... - 01:14 PM devops Feature #7239: ceph-deploy: install cephfs java bindings
- I deployed Ceph to a cluster that I intended to run Hadoop on. In this case, a typical setup is to have the cephfs cl...
- 12:51 PM devops Feature #7239 (Need More Info): ceph-deploy: install cephfs java bindings
- Could you please elaborate why you think ceph-deploy should be in charge of installing a dependency like java binding...
- 01:10 PM Revision fe8a715c (ceph): Make the configuration "filestore merge threshold" can be negative whic...
- 1. We are trying to create the PG folder up to several levels with a standalone tool to prevent it from runtime split...
- 11:54 AM devops Bug #7598 (Need More Info): ceph-disk-activate error with ceph-deploy
- I can't replicate this behavior *at all*. I do know why that is the error that comes about though.
What happens is... - 11:20 AM rgw Bug #7703 (Fix Under Review): rgw: fail to copy object > 512k between buckets
- 10:35 AM Revision 27f06346 (ceph): doc: fix formatting on PG recommendation
- Previous commit (047287afbe0ddfaaafd05e9dbf25c1c7dea9a1be) broke
formatting on the formula, and also made mixed formu... - 10:21 AM Revision 7cf81ce2 (ceph): libcephfs/test.cc: shutdown cmount at end of MountNonExist
- CID 966624 (#5 of 5): Resource leak (RESOURCE_LEAK)
17. leaked_storage: Variable "cmount" going out of scope leaks t... - 10:00 AM rgw Bug #7702 (Need More Info): osd thrashing + rgw = timeouts
- 09:41 AM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
- 09:40 AM Bug #7260 (Can't reproduce): rados api test LibRadosList.ListObjectsNS failed
- reopen if we see this now that the enumerator/iterator changes are in place
- 09:38 AM Bug #7259 (Resolved): ceph mon crash in master branch
- 08:48 AM Revision 269cf138 (ceph): libcephfs/test.cc: shutdown cmount
- CID 743410 (#17 of 17): Resource leak (RESOURCE_LEAK)
65. leaked_storage: Variable "cmount" going out of scope leaks... - 08:03 AM Revision 94acb6b3 (ceph): test_librbd.cc: add missing va_end() to test_ls_pp
- CID 1054877 (#1 of 1): Missing varargs init or cleanup (VARARGS)
17. missing_va_end: va_end was not called for "ap".... - 06:49 AM Revision fb4ca940 (ceph): mailmap: Danny Al-Gaaf name normalization
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:29 AM Bug #7593: Disk saturation during PG folder splitting
- Thanks Sage very much for the comments.
To begin with, I propose a change here - https://github.com/ceph/ceph/pull... - 04:32 AM Revision fb8ff445 (ceph): doc/release-notes: note that WATCH can get ENOENT now
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:30 AM Revision 90a21d8c (ceph): qa/workunit/rados/test-upgrade-firefly: skip watch-notify test
- A watch on a non-existent object now returns ENOENT in firefly; skip this
test as it will fail on a hybrid or upgrade... - 01:33 AM Revision fce63aa8 (ceph): Merge pull request #1440 from ceph/wip-7649
- Wip 7649
Reviewed-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision b5d2df4a (ceph): Merge pull request #1441 from ceph/wip-7671
- Wip 7671
Reviewed-by: Sage Weil <sage@inktank.com>
03/12/2014
- 11:26 PM Revision 2cbad1b1 (ceph): test/librados/watch_notify: create foo before watching
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:26 PM Revision 9d549eb2 (ceph): test/system/st_rados_watch: expect ENOENT for watch on non-existent object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:45 PM Revision a5235956 (ceph): Merge pull request #1439 from ceph/wip-7682
- ReplicatedPG::already_(complete|ack) should skip temp object ops
Reviewed-by: Sage Weil <sage@inktank.com> - 10:37 PM Revision efdee0d3 (ceph): upgrade/dumpling-x: upgrade final client node for final test
- This means the final workloads are running firefly code.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:56 PM Revision b23a141d (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
- CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload... - 09:49 PM Revision 7fb5e146 (ceph): upgrade/dumpling-x: full librados tests after full upgrade
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:37 PM Revision 4057a306 (ceph): AbstractWrite: initialize m_snap_seq with 0
- CID 717223 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_snap_seq... - 09:07 PM Revision 90a2654f (ceph): ReplicatedPG::already_(complete|ack) should skip temp object ops
- We clearly won't get dup ops on these repops, and they don't
have meaningful versions since they don't carry log
entr... - 09:02 PM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
- This fails due to issue #7703.
- 08:59 PM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
- The new manifest does not hold bucket marker info which is needed, as when we're copying object between buckets we ne...
- 08:03 PM Revision 72bc1ef8 (ceph): AdminSocket: initialize m_getdescs_hook in the constructor
- CID 717212 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_getdesc... - 07:27 PM Revision f7529cf4 (ceph): RGWPutCORS_ObjStore_S3::get_params: check data before dereference
- CID 1063697 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
5. var_deref_model: Passing null pointer "data" to ... - 07:09 PM Revision 5334d5c8 (ceph): mds/Server.cc: check straydn before dereference
- ID 1019554 (#1 of 1): Dereference after null check (FORWARD_NULL)
13. var_deref_model: Passing null pointer "straydn... - 07:05 PM Revision f6b3a0b7 (ceph): Merge pull request #1423 from fractalcat/respect-python-env
- Update Python hashbang to respect environment
- 06:57 PM Revision 45f54539 (ceph): Merge pull request #1434 from ceph/wip-7695
- build-doc: fix checks for required commands for non-debian
Reviewed-by: Sage Weil <sage@inktank.com> - 06:55 PM Revision bbc228fc (ceph): Merge pull request #1438 from fghaas/doc-fix
- doc: Add "nearest power of two" to PG rule-of-thumb
Reviewed-by: Sage Weil <sage@inktank.com> - 06:51 PM Revision 047287af (ceph): doc: Add "nearest power of two" to PG rule-of-thumb
- Following an IRC discussion, it emerged that it would be helpful
to explain the merit of choosing a number of PGs per... - 06:37 PM Bug #7696: osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 10:07 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- Primary and replica disagree on last_backfill for some reason.
-3> 2014-03-12 03:31:58.711369 7feaff6c9700 10 ... - 06:32 PM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
- 06:09 PM Revision 7bb03598 (ceph): OSDMonitor::prepare_pool_op: add missing break in case
- CID 1191886 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This case (value 34) is not termin... - 05:46 PM Revision bcd41c0f (ceph): Merge pull request #1436 from ceph/wip-7681
- ECBackend: when removing the temp obj, use the right shard
Reviewed-by: Sage Weil <sage@inktank.com> - 05:44 PM Revision f52af306 (ceph): Merge pull request #1437 from ceph/wip-7650
- tools/rados/rados.cc: use write_full for sync_write for ec pools
Reviewed-by: Sage Weil <sage@inktank.com> - 05:38 PM Revision a4a91ccd (ceph): PG: do not wait for flushed before activation
- This should reduce the sting of the previous commit somewhat. We wait
for the activation transactions to clear prior... - 05:38 PM Revision a576eb32 (ceph): PG: do not serve requests until replicas have activated
- There are two problems:
1) We choose the min last_update amoung peers with the max local-les
value as an upper bound ... - 05:34 PM Revision 980d2b59 (ceph): ECBackend: when removing the temp obj, use the right shard
- Introduced in d0b1094ff7b98ef9262ecb45ee8324853003a77c
Fixes: #7681
Signed-off-by: Samuel Just <sam.just@inktank.com> - 05:32 PM Bug #7626 (Need More Info): After updating ceph from 0.75 to 0.77 one of the three monitors can't...
- 05:28 PM Revision dc00661d (ceph): osd_types: print lb if incomplete even if empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:09 PM Revision 8e76e4e4 (ceph): build-doc: fix checks for required commands for non-debian
- Fixes: 7695
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:09 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
- 04:50 PM Revision 85e7f4d8 (ceph): Merge pull request #1412 from ceph/wip-libxfs-flag
- FileStore: support compiling without libxfs
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 04:04 PM rgw Bug #7702 (Resolved): osd thrashing + rgw = timeouts
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl...
- 03:57 PM Revision 1ccabd80 (ceph): lock: allow -a with --brief
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:45 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
- 02:12 PM Bug #7682: osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first == repop->v)
- 02:46 PM Feature #7701 (Resolved): Filterable querying interface for PGMonitor
On larger clusters with 100,000s or millions of PGs, dumping everything for external tools becomes inefficient.
...- 02:38 PM Feature #7700 (New): Create a health severity between OK and WARN
I think the name we liked best so far was NOTICE.
For each WARN "health check" a la #7192, reconsider its severi...- 02:04 PM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl...
- 01:25 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is that, if the string ...
- 09:55 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> Danny Al-Gaaf wrote:
> > Dan van der Ster wrote:
> > > The other solution would be to co... - 09:32 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Danny Al-Gaaf wrote:
> Dan van der Ster wrote:
> > The other solution would be to copy block_name_prefix to a local... - 09:29 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> The other solution would be to copy block_name_prefix to a local null terminated in the fu... - 09:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- The other solution would be to copy block_name_prefix to a local null terminated in the function where it is printed ...
- 09:20 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Do you take a look at it (or do you have already a fix?) or should I?
The problem is that block_name_prefix in rbd... - 09:08 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Yeah, but I think it's data-dependent; must be max len and not have a zero byte directly after...
- 03:17 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan Mick wrote:
> Why I feel some guilt here: :)
>
> commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
> Author: D... - 03:05 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- I just rebuilt from current git dumpling head on my machine -- cannot reproduce. So I wonder this is something subtle...
- 01:24 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a... - 01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a... - 01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a 204 even if you atte...
- 11:57 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
- 09:50 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
- ./admin/build-doc runs even if e.g. ditaa or ant isn't installed on the system. The script part checking for the bina...
- 11:31 AM Feature #7192: An easier-to-process health report
- This sounds great to me. I assume we'd keep the 'detail' section as optional as it can get quite (!) big.
- 11:02 AM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 10:46 AM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 10:45 AM Bug #7256 (Duplicate): ceph osd crashed at ReplicatedPG::trim_object on next
- 10:44 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
- 10:06 AM Feature #7662: add a "ec profiles" map to OSDMap
- s/properties/ec profile/g
- 09:24 AM rbd Bug #7693 (Closed): virsh domblkinfo fails with 'Bad file descriptor'
- Found that the 'domblkinfo' command fails while 'domblklist' and 'domblkstat' commands function normally.
## Envir... - 06:35 AM Bug #7692: mon: monitor fails to form quorum
- at first glance, problem has nothing to do with the 0.0.0.0 ip.
This looks like it's early deployment, therefore t... - 06:09 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
- For some reason it is looking at 0.0.0.0 and of course that fails:...
- 04:54 AM Revision c55da14a (ceph): Merge pull request #1362 from dachary/wip-7548
- doc: erasure coded pool developer and operations documentation
Reviewed-by: Sage Weil <sage@inktank.com> - 04:41 AM Revision 01a93a2a (ceph): Merge pull request #1425 from ceph/wip-rbd-fuse-enumerate
- rbd-fuse: fix enumerate_images() image names buffer size issue
Reviewed-by: Sage Weil <sage@inktank.com> - 04:38 AM Revision 9987e486 (ceph): Merge pull request #1424 from fractalcat/thread-safety-doc-update
- rados_connect not thread-safe when using nss (documentation)
Reviewed-by: Sage Weil <sage@inktank.com> - 04:33 AM Revision 32fdca6d (ceph): Merge pull request #1411 from ceph/wip-7076-dumpling
- dumpling backport of watchers check for rbd_remove()
- 04:30 AM Revision e3f8dd03 (ceph): Merge pull request #1419 from ceph/wip-doc-prereq
- doc: update build prerequisites
- 04:29 AM Revision 004bf3b2 (ceph): Merge pull request #1415 from ceph/wip-build-doc
- doc: release-process documentation updates
Reviewed-by: Sage Weil <sage@inktank.com> - 04:25 AM Revision bd2defb9 (ceph): Merge pull request #1409 from enovance/wip-brag
- ceph-brag enhancements
Reviewed-by: Sage Weil <sage@inktank.com> - 04:22 AM Revision dc82cd78 (ceph): debian: make ceph depend on ceph-common >= 0.67
- The older versions of ceph-common (ceph CLI, in particular) can't talk to
newer clusters. The primary change happene... - 04:11 AM Revision d5442a57 (ceph): multimds: new (separate) suite for multi-mds tests
- Eventually we can merge this into the fs suite, but for now it is useful
to segregate the test cases.
Start with a d... - 04:07 AM Revision 88efa65e (ceph): Revert "fs/basic: multimds"
- This reverts commit aea501beb744dd6f6ec2b60678cefc7fae6761b0.
Let's put this in a separate subdir for now. It won't... - 02:23 AM Revision f1840bce (ceph): Merge pull request #1427 from ceph/wip-6889
- rgw: don't log system requests in usage log
Reviewed-by: Sage Weil <sage@inktank.com> - 02:20 AM Revision b70db7e7 (ceph): Merge remote-tracking branch 'gh/firefly'
- 02:16 AM Revision a18cd6dd (ceph): Merge remote-tracking branch 'gh/firefly'
- 02:16 AM Revision cfbbcf7c (ceph): upgrade/dumpling-x/stress-split: use dumpling workunits
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:04 AM Revision bfbfcf84 (ceph): Merge pull request #1422 from salehe/docfix-1
- rados.py: fix typo in Ioctx::read() docstring
- 01:54 AM Revision b455846d (ceph): Handle newer btrfstools.
- Newer btfs userland tools needs a -f like xfs instead of a prompt
for yes. Trusty needs this change.
Signed-off-by: ... - 01:48 AM Revision e5b65b45 (ceph): Merge pull request #222 from ceph/wip-trusty
- Handle newer btrfstools.
- 01:23 AM Revision a890ef09 (ceph): Merge pull request #1432 from ceph/wip-7687
- rgw: don't overwrite bucket entry data when syncing user stats
Reviewed-by: Sage Weil <sage@inktank.com> - 01:19 AM Revision d5737107 (ceph): rgw: don't overwrite bucket entry data when syncing user stats
- Fixes: #7687
When syncing user bucket stats we overwritten the entire entry with the
passed in entry. We should only ... - 01:15 AM Revision a5a94ae3 (ceph): Handle newer btrfstools.
- Newer btfs userland tools needs a -f like xfs instead of a prompt
for yes. Trusty needs this change.
Signed-off-by: ... - 01:13 AM CephFS Bug #1318: directories disappear across multiple rsyncs
- please check if there was file recovery involved (MDCache::do_file_recover )
- 01:11 AM Revision c0b1c107 (ceph): Merge pull request #16 from ceph/wip-hint-tests
- rados/singleton-nomsgr: add allocation hint test
Reviewed-by: Sage Weil <sage@inktank.com> - 01:09 AM Revision d72c2bbc (ceph): Merge pull request #1400 from ceph/wip-hint-tests
- wip-hint-tests
Reviewed-by: Sage Weil <sage@inktank.com> - 12:03 AM Revision 2fbd7720 (ceph): qa/workunits/cephtool/test.sh: fix thrash (more)
- If I have to touch this again I will remove it. Ugh. This time,
ubuntu@teuthology:/var/lib/teuthworker/archive/teu...
03/11/2014
- 11:38 PM Revision a459c4e2 (ceph): Merge pull request #1417 from ceph/wip-7663
- Wip 7663
Reviewed-by: Sage Weil <sage@inktank.com> - 11:05 PM Revision 0b31cf48 (ceph): Merge pull request #1416 from ceph/wip-div
- More log handling fixes
Reviewed-by: Sage Weil <sage@inktank.com> - 11:02 PM Revision f4196cc3 (ceph): doc/release-notes: firefly draft release notes
- Some updates; still incomplete.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:02 PM Revision 64a6b26b (ceph): doc/release-notes: fill in some firefly history
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:00 PM Revision 1a9f6c32 (ceph): Merge pull request #17 from ceph/wip-final_load_fix
- fixed final_load problem
- 10:40 PM Revision 72094a85 (ceph): fixed final_load problem
- 08:55 PM Revision 1c611330 (ceph): radosbench: cleanup will probably take longer than writing the objects
- With thrashing, cleanup will require recovering the degraded objects
first, while the initial write out doesn't since... - 07:30 PM devops Bug #7641 (Fix Under Review): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- It's sort of the other way around. ceph doesn't depend on version of the stuff in ceph-common at all, but ceph-commo...
- 07:24 PM Bug #7689: librados: ENOENT on ioctx create
- downgrading thsi weirdness until i see it again
- 06:05 PM Bug #7689: librados: ENOENT on ioctx create
- actually, no mon_command creating the pool appears in the logs. does not jive with the teuthology log.
- 04:54 PM Bug #7689 (Duplicate): librados: ENOENT on ioctx create
- I think this is a race with pool creation, mon quorum changes, and new client startup getting a not-quite-fresh osdma...
- 07:23 PM rgw Bug #6889 (Pending Backport): rgw: usage log: don't log system user operations
- 09:31 AM rgw Bug #6889 (Fix Under Review): rgw: usage log: don't log system user operations
- 07:15 PM Revision 24774a81 (ceph): osd/ReplicatedPG: fix typo
- This is the object count, not the dirty object count. Broken by
00bf3b56743830a4a9c5d6765946a4e68f530c57.
Reported-... - 07:11 PM Revision 728bd3c5 (ceph): upgrade/dumpling-x: upgrade mon before osd
- The MDS needs to see the TMAP2OMAP feature bit in the osdmap. THe mons
have to encode the feature bits passed by the... - 06:43 PM Revision 28a1d77a (ceph): Merge pull request #1430 from ceph/wip-7674
- osd/ReplicatedPG: do not include hit_set objects in full calculation
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:22 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:14 PM rgw Bug #7687 (Fix Under Review): rgw: bucket creation time is not set
- 06:09 PM rgw Bug #7687: rgw: bucket creation time is not set
- actually it's set, but then it's overwritten.
- 03:09 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:20 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
- 7635
- 06:19 PM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
- fixed by teuthology commit:57259b54beb746b31b70bb3a92de18d604002b0a
- 06:15 PM Bug #7631 (In Progress): command 'dump_ops_in_flight' not found
- 06:14 PM Revision 3d5a4b5a (ceph): ReplicatedPG: CEPH_OSD_OP_WATCH return -ENOENT if !obs.exists
- Fixes: #7671
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:10 PM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
- 05:53 PM Revision 00bf3b56 (ceph): osd/ReplicatedPG: do not include hit_set objects in full calculation
- If we have a low target and there are hit_set objects (which cannot be
evicted), we can get stuck in a full state and... - 05:23 PM Revision f57121ac (ceph): Merge pull request #1418 from ceph/wip-7672
- PG::choose_acting: filter CRUSH_ITEM_NONE out of have
Reviewed-by: Sage Weil <sage@inktank.com> - 05:18 PM Revision 18d80656 (ceph): Merge pull request #1429 from ceph/wip-7592-final
- Wip 7592 final
Reviewed-by: Sage Weil <sage@inktank.com> - 05:17 PM Bug #7682 (In Progress): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->fir...
- 12:59 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124761/teutholog...
- 05:04 PM Revision 9df52611 (ceph): Merge pull request #1428 from ceph/wip-is_down-boolean
- OSDMap: clarify is_{down,in}() definitions
Reviewed-by: Sage Weil <sage@inktank.com> - 05:00 PM Revision 59834d60 (ceph): Merge pull request #1410 from ceph/wip-flock
- mds: fix owner check of file lock
Reviewed-by: Sage Weil <sage@inktank.com> - 04:59 PM Revision 0752f284 (ceph): Merge pull request #1385 from ceph/wip-nfs-export
- mds: introduce LOOKUPNAME MDS request
Reviewed-by: Sage Weil <sage@inktank.com> - 04:51 PM Revision 1836b6c7 (ceph): osd: hit_set_persist(): Verify all objects aren't degraded
- Fixes: #7592
Signed-off-by: David Zafman <david.zafman@inktank.com> - 04:41 PM Revision a9a826ad (ceph): Merge pull request #220 from ceph/wip-print
- Add print task.
- 04:41 PM Bug #7688 (Won't Fix): warn at fs/btrfs/extent-tree.c:5748 __btrfs_free_extent+0x9ce/0xa20
- ...
- 04:38 PM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
- 01:01 PM Bug #7663 (Fix Under Review): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10....
- 04:37 PM Revision 42ef8ba5 (ceph): rgw: don't log system requests in usage log
- Fixes: 6889
System requets should not be logged in the usage log.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:17 PM devops Bug #7617: ceph-deploy uninstall should document why it doesn't remove all relevant packages
- The problem is that qemu-kvm depends on librbd1, and if you remove the latter, that means removing the former. That ...
- 04:13 PM Revision 6700dd06 (ceph): rgw: off-by-one in rgw_trim_whitespace()
- Fixes: #7543
Backport: dumpling
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Ray Lv <raylv@yahoo-in... - 04:11 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Why I feel some guilt here: :)
commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
Author: Dan Mick <dan.mick@inktank... - 04:10 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- True, I don't see any attempt to add a nul. Oddly, it looks like there was half a plan to do so in librbd/internal.c...
- 01:18 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- I'm not current on my c++, but I'm pretty sure Danny's correct. Looking at the code, rbd.cc just does a cout of the 2...
- 01:13 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Sent this in email, but: u007f sounds like maybe a 0x7f character?.. Which should be legal 7-bit ASCII, but perhaps i...
- 07:22 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Here's a bit more with json format:
{"name":"volume-f529978c-0981-4eba-a5b5-7ba8ecc05e1b","size":5368709120,"objec... - 06:40 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- So this is not a recent regression. I can reproduce on el6.5 with 0.67-0
[root@dvtest1 ceph]# ceph --version
ce... - 06:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu di... - 06:23 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu difference.
On my ubuntu 0... - 04:11 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Tried to reproduce, but couldn't. Looks to me like missing '\0' termination. Do you get this from all of your 0.67.7 ...
- 04:11 PM Revision 406ff0b7 (ceph): OSDMap: clarify is_{down,in}() definitions
- Make it clear that is_down() == !is_up() and is_in() == !is_out().
This is not a functional change.
Signed-off-by: I... - 04:05 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
- 01:03 PM Bug #7658 (Fix Under Review): PGLog: _merge_object_divergent_entries: fix the case where prior_ve...
- 04:05 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
- 01:04 PM Bug #7657 (Fix Under Review): PGLog: fix proc_replica_log divergent entry selection
- 03:15 PM rgw Bug #7676 (Fix Under Review): rgw: multi-part upload incompatible with EC backend
- 03:13 PM Bug #7635: failed to recover before timeout expired
- It did eventually recover, as it turns out.
2014-03-06 05:40:41.795123 mon.0 10.214.132.32:6789/0 521 : [INF] pgmap ... - 03:02 PM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
- 12:07 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
- commit:b4fbe4f81348be74c654f3dae1c20a961b99c895 and a later commit fixed feature forwarding, which is needed for the ...
- 12:04 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
- ...
- 10:09 AM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
- ubuntu@teuthology:/a/teuthology-2014-03-10_10:33:21-upgrade:dumpling-x:parallel-firefly---basic-plana/124951
mds r... - 03:00 PM Bug #7686 (Duplicate): osd spinning in agent_work
- 02:37 PM Bug #7686: osd spinning in agent_work
- agent_entry() is hitting a case where there appears to be work to do, but we never evict a hit set archive. In the l...
- 02:08 PM Bug #7686: osd spinning in agent_work
- FYI, this was/is on burnupiX after setting an OSD out and bringing it back in.
- 02:05 PM Bug #7686 (Duplicate): osd spinning in agent_work
- Probably related to the num_dirty/archived hitset issue?
2014-03-11 16:05:15.959964 7fc99340a700 20 osd.0 212 agen... - 02:44 PM devops Feature #7047 (Resolved): rhel7: build process for rbd.ko, ceph.ko kernel modules
- The kmods are built as a part of the Red Hat kmod packaging (#6986) at https://github.com/ceph/ceph-kmod-rpm
Speci... - 02:40 PM Bug #7681: osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 12:52 PM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124677/teuthol...- 02:21 PM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
- 02:21 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
- 09:07 AM rgw Bug #7375: s3_user_quota.pl fails
- 02:20 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
- 09:07 AM rgw Bug #7374: s3_multipart_upload.pl fails
- 02:01 PM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
- 02:00 PM Revision fe4ad291 (ceph): rbd-fuse: fix enumerate_images() image names buffer size issue
- Image names buffer is fixed at 1024. This turns out to be not enough:
there are at least two "rbd-fuse rbd_list: err... - 01:59 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
- 01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- I've turned up the timeout in the tests.
- 01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- The non-ec ones are probably just an inadequate timeout -- the cleanup is likely to take longer than the writeout. T...
- 01:57 PM CephFS Bug #7685 (Can't reproduce): hung/failed teuthology test: cfuse_workunit_misc
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_23:00:50-fs-firefly-testing-basic-plana/122094
http://qa-p... - 01:46 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_23:00:25-fs-firefly-testing-basic-plana/124157/
The teut... - 01:37 PM Bug #7093 (Resolved): osd: peering can send messages prior to auth
- Backported to Emperor and Dumpling
- 01:35 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- 01:31 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
- 01:24 PM Bug #5823 (Can't reproduce): cpu load on cluster node is very high, client can't get data on pg ...
- 01:20 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- can you please rerun the monitor with 'debug mon = 10' and attach the resulting log
- 01:20 PM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
- 01:11 PM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
- 01:10 PM Bug #7611 (In Progress): All mon nodes crash when running "ceph tell osd.X" and using the "versio...
- 11:43 AM Bug #7674 (Resolved): Cache pool configuration stalls
- 11:00 AM Bug #7674 (Fix Under Review): Cache pool configuration stalls
- 10:44 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- No, subusers are useful for S3 as well. Maybe this was by accident, but I'm relying on it already in production, for ...
- 09:09 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- Robin, is that still an issue (considering my previous comment), or should we close this one?
- 10:42 AM rbd Bug #7125: Assertion failure in rbd_img_obj_callback()
- Probably related are:
http://tracker.ceph.com/issues/5876
http://tracker.ceph.com/issues/5662
http://tracker.cep... - 10:29 AM Linux kernel client Bug #7069 (Resolved): CephFS hang when using fscache - several "blocked for more than 120 seconds...
- this is fixed in 8fb883f3e30065529e4f35d4b4f355193dcdb7a2, according to milosz. fixed in kernel 3.13
- 09:48 AM Linux kernel client Bug #7069 (Need More Info): CephFS hang when using fscache - several "blocked for more than 120 s...
- THere are several fscache fixes in the testing branch; perhaps they address this?
- 10:27 AM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 10:23 AM Revision 377c9190 (ceph): rados_connect not thread-safe when using nss (documentation)
- I'm not sure whether rados_connect is expected to be threadsafe or not,
so this is just a documentation patch rather ... - 10:18 AM Bug #7592 (Resolved): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7592 (Fix Under Review): hit_set_trim() removal races with backfill
- 10:15 AM rgw Feature #7680 (Resolved): Use new civetweb git repo for ceph
- It seems that the original repo used to fork the ceph civetweb repo from is outdated. The current README on https://g...
- 09:51 AM Linux kernel client Bug #2759: libceph: crush tree algorithm is not understood
- We should be testing CRUSH with multiple algorithms
- 09:46 AM Revision 861e62aa (ceph): Update Python hashbang to respect environment
- The /usr/bin/python hashbang causes doc builds to fail when Python3 is
the default Python and Python2 is being used f... - 09:44 AM Linux kernel client Bug #2224 (Rejected): Oops in __cfh_to_dentry
- 09:44 AM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
- 09:37 AM rbd Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
- e91fb910653a672560867d4a81aa30f9d5dc0af8
- 09:35 AM rbd Bug #7582 (Resolved): "FAIL: test_rbd.TestImage.test_remove_with_watcher" in upgrade:dumpling-x-f...
- 09:34 AM rbd Bug #7583 (Resolved): "librbd::ImageCtx: error finding header" in upgrade:dumpling-x-firefly---ba...
- 09:33 AM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
- 09:32 AM rbd Bug #6577 (Can't reproduce): arm testing: rbd test segfaults at FAILED assert((bool)_front == (bo...
- 09:21 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
- 09:18 AM rgw Bug #6913 (Duplicate): valgrind issues when running rgw tests
- 09:17 AM rgw Bug #6802 (Rejected): ARM: rgw_swift failure (internal server error, 500)
- 09:17 AM rgw Bug #6696 (Can't reproduce): Upgrade rgw failure in nightly tests. (/home/ubuntu/cephtest/s3-test...
- 09:15 AM rgw Bug #6765 (Rejected): ARM: RGW s3 tests fail.
- 09:13 AM rgw Feature #7589: rgw: configurable chunk size
- Josh - please review wip-7589
- 09:12 AM rgw Feature #7589 (Fix Under Review): rgw: configurable chunk size
- 09:10 AM devops Bug #6453: libapache2-mod-fastcgi Packages for Debian Squeeze have incorrect dependencies
- 09:08 AM rgw Bug #6911: rgw test failure on the arm set up
- this sounds like a 32 bit int (size_t?) overflow
- 09:07 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- 09:06 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
- the mon assert is a dup
- 08:32 AM Revision fa30eb5d (ceph): rados.py: fix typo in Ioctx::read() docstring
- Signed-off-by: Mohammad Salehe <salehe+dev@gmail.com>
- 07:18 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
- This looks like it's the writeback deadlock when trying to flush from the client to the OSD on a single memory-constr...
- 07:17 AM CephFS Bug #6599 (Resolved): client: invalid iterator dereference in Client::trim_caps
- 07:12 AM CephFS Feature #5486: kclient: make it work with selinux
- Hmm, Sage notes that maybe it'll work now we support ACLs. Or maybe we can use a special mount option?
- 07:00 AM CephFS Bug #2187 (Can't reproduce): pjd chown/00.t failed test 97
- 06:59 AM CephFS Bug #2740 (Resolved): mds: crash in Objecter when shutting down too early
- 03:40 AM Revision 1249b0bd (ceph): Use pgrep radosgw to determine if rados gateway is running.
- Fixes: 7528
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cher... - 03:40 AM Revision 745f72c5 (ceph): Fixed get_status() to find client.radosgw fields inside of ps output.
- Fixes: 7375
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cher... - 03:40 AM Revision 880bc3a5 (ceph): Fix get_status() to find client.rados text inside of ps command results.
- Added port (fixed value for right now in teuthology) to hostname.
Fixes: 7374
Reviewed-by: Yehuda Sadeh <yehuda@inkta... - 03:00 AM Revision 77c3cecb (ceph): Merge pull request #221 from ceph/wip-brief
- lock.py: allow --brief to stand on its own (without --list)
- 02:53 AM Revision fbd9c154 (ceph): osd: Remove unused checkpoint code
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 02:38 AM Revision 69ed31cc (ceph): lock.py: allow --brief to stand on its own (without --list)
- I use --brief all the time, and it's annoying to have to type
the useless --list at the same time.
Signed-off-by: Da... - 01:45 AM Revision d3e3df7a (ceph): mds: fix owner check of file lock
- flock and posix lock do not use process ID as owner identifier.
The process ID of who holds the lock is just for F_GE...
03/10/2014
- 11:45 PM Revision ed6a2001 (ceph): Add print task.
- Made a task that simply prints the output that is given to it as
an argument. Can be used like any other task (under ... - 11:13 PM Revision ccf9a745 (ceph): Merge pull request #1310 from ceph/wip-doc-documenting-ceph
- Wip doc documenting ceph
Reviewed-by: Sage Weil <sage@inktank.com> - 11:03 PM Revision 8a72de3e (ceph): ReplicatedPG: adjust pending_attrs correctly in copy_from
- Otherwise, subsequent reads might not get the correct cached attrs.
Fixes: #7663
Signed-off-by: Samuel Just <sam.jus... - 11:03 PM Revision 6669e4d6 (ceph): ReplicatedPG: _delete_head should adjust pending_attrs
- We need the old attr_cache in make_writeable for the clone,
so make the changes to pending_attrs.
Fixes: #7663
Signe... - 11:02 PM Revision 60c1b9a5 (ceph): ReplicatedPG: use pending_attrs in rollback
- Otherwise, we won't have the correct attr_cache in
make_writeable for the clone.
Fixes: #7663
Signed-off-by: Samuel ... - 10:58 PM Revision d7c4d6ab (ceph): doc: Added init caps to Signed-off-by: and Fixes:
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:54 PM Revision 2b284077 (ceph): doc: update build prerequisites
- Based on WIP branch by Gary Lowell <gary.lowell@inktank.com>.
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com> - 10:45 PM Revision 7ac98b2a (ceph): doc: Updated sign-off by to sign-off-by
- sign-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:06 PM Revision 2e420f9d (ceph): doc: rm duplicate info from release-process
- The "just push the new tag" bit is already done in the list of commands
above. Remove this piece, since it's duplicat... - 09:14 PM Revision 52a2d692 (ceph): doc: fix reST formatting in release-process
- Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
- 09:14 PM Revision bb737117 (ceph): doc: update release-process for packages
- New script to sign rpms in the repo and create the indexes, and
some description of additional packages that might ne... - 09:14 PM Revision dd5a378d (ceph): doc: misc updates for release-process
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Reviewed-by: Ken Dreyer <ken.dreyer@inktank.com> - 08:43 PM Revision e272f74f (ceph): rgw_rados.h: RGWRegion: initialize cct and store with NULL
- CID 1054869 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member "store" i... - 08:36 PM Revision 8de88193 (ceph): PG::choose_acting: filter CRUSH_ITEM_NONE out of have
- Fixes: #7672
Signed-off-by: Samuel Just <sam.just@inktank.com> - 07:27 PM Revision c7c9ae3b (ceph): RadosModel.h: initialize CopyFromOp::snap
- CID 1093219 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member "snap" is... - 07:20 PM Revision d7af7eb3 (ceph): RadosModel.h: TestOp: initialize comp with NULL
- CID 1135939 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "comp" is... - 07:12 PM Revision 9df9f4c7 (ceph): ReplicatedPG.h: CopyResults() initialize final_tx with NULL
- CID 1188177 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "final_tx... - 07:01 PM Revision 2daabc1e (ceph): scratchtoolpp.cc: check return value of getchar()
- CID 716865 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
1. check_return: Calling function "getcha... - 06:58 PM Revision 0f7d954b (ceph): doc: Updated pull request with suggested changes.
- signed-off by: John Wilkins <john.wilkins@inktank.com>
- 06:50 PM Revision a9df888c (ceph): AioTestData: initialize m_ioctx with NULL
- CID 717392 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_ioctx" ... - 06:37 PM Revision 6732c025 (ceph): rgw_rados.h: generator class: initialize manifest with NULL
- CID 1188180 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "manifest... - 06:27 PM Revision 61f640cf (ceph): IoCtxImpl: initialize last_objver with 0
- CID 717219 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "last_objve... - 05:34 PM Revision b6947c03 (ceph): ECSubWrite: pass some parameter by reference
- CID 1188143 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter stats of type ... - 05:22 PM Revision 200f7478 (ceph): test/bench/distribution.h: pass rngen_t by reference
- CID 1135927 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter rng of type rn... - 05:14 PM Revision d61fcfa2 (ceph): ceph-filestore-dump.cc: pass OSDSuperblock by reference
- CID 1100693 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter superblock of ... - 05:11 PM Bug #7593: Disk saturation during PG folder splitting
- At a high level, sure, if you know ahead of time how many objects per PG you expect you can pre-hash the PG directori...
- 01:26 AM Bug #7593: Disk saturation during PG folder splitting
- Hi Sage,
If we would like to make the following changes:
# Bring in a new configuration flag which can be used to... - 05:08 PM devops Bug #7677: Troubleshoot ceph-setup-nightly Jenkins failures
- Alfredo - please review.
- 04:57 PM devops Bug #7677 (Fix Under Review): Troubleshoot ceph-setup-nightly Jenkins failures
- Here is the code change to skip the Debian package diffs if they are not present: https://github.com/ceph/ceph-build/...
- 04:55 PM devops Bug #7677 (Resolved): Troubleshoot ceph-setup-nightly Jenkins failures
- h3. Background:
Ceph builds in Jenkins are broken up into three separate jobs: ceph-setup, ceph-build, and ceph-pa... - 05:07 PM Revision 7e43823f (ceph): doc: Fixed typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:05 PM devops Tasks #7678 (Resolved): f20 Jenkins slave
- In #7094, we got a new Fedora 20 gitbuilder. We need to add this host to Jenkins as well.
I don't think there are ... - 04:54 PM Revision 6cd797b3 (ceph): osd/Watch.cc: pass entity_addr_t by reference
- CID 1086832 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter addr of type e... - 04:38 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...
- 135c27ec74be352416d06a9d0ad78e63cf477433
- 04:29 PM Revision 40095ee2 (ceph): watch_item_t: pass entity_addr_t by reference
- CID 1030127 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter addr of type e... - 04:28 PM rgw Bug #7676 (Resolved): rgw: multi-part upload incompatible with EC backend
- multipart upload uses omap on data object. Need to provide a solution for this. Either we switch the data format for ...
- 04:16 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- *wip-doc-prereq* (was "5a811a":https://github.com/ceph/ceph/commit/5a811a0894db2619f5f916c0be85459d0f481265) has been...
- 03:44 PM devops Cleanup #7675 (In Progress): clean up Gary Lowell's WIP branches
- 03:26 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- *wip-build-doc* has been rebased and submitted for merging here: https://github.com/ceph/ceph/pull/1415
- 03:18 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- For the record, today I've reviewed and deleted the following wip branches from Gary.
*wip-lazy-cuttlefish-gl* (wa... - 03:13 PM devops Cleanup #7675 (Resolved): clean up Gary Lowell's WIP branches
- Gary Lowell had contributed a couple of work-in-progress branches that are still outstanding. Here are the seven that...
- 04:14 PM Revision 62763d56 (ceph): watch_info_t: pass parameter by reference
- CID 1030126 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter a of type enti... - 04:02 PM Revision 246564bf (ceph): pg_t::get_split_bits: add assert to silence coverity
- CID 751330 (#1 of 1): Overflowed return value (INTEGER_OVERFLOW)
overflow_sink: Overflowed or truncated value (or a ... - 03:54 PM Revision aba5b7cc (ceph): rbdmap: bugfix upstart script
- It seems like the upstart script is lacking a little behind [the initscript](https://github.com/ceph/ceph/blob/master...
- 02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- I believe the error is in the cache pool.
- 02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- [ERR] 4.3 scrub stat mismatch, got 48/48 objects, 0/0 clones, 21/23 dirty, 9/9
We are overestimating dirty now, ... - 02:17 PM Bug #7674: Cache pool configuration stalls
- This was on 0.77-735-gd171418-1saucy which is a couple of days old. I can retest on firefly from today if there have...
- 02:15 PM Bug #7674 (Resolved): Cache pool configuration stalls
- In testing the following cache pool configuration:...
- 02:09 PM Bug #7672: PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 01:32 PM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 02:09 PM Bug #7671: watch should return ENOENT if the object does not exist
- 12:56 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
- Currently, new_obs->exists doesn't get updated, so we create the log entry as a delete which messes everything up.
- 02:08 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- There are seem to be several of those, so 'major'
- 02:07 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic-plana/1238...
- 12:58 PM CephFS Bug #1318: directories disappear across multiple rsyncs
- By “this” I meant files with different timestamps from what they were last set to, as in the first paragraph of comme...
- 12:51 PM CephFS Bug #1318: directories disappear across multiple rsyncs
- I'm afraid this still occurs quite often with ceph 0.77 and ceph.ko 3.13.6-gnu. I have a slightly better understandi...
- 10:23 AM Bug #7592 (In Progress): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
- 09:44 AM Revision 2e342d6d (ceph): FileStore: support compiling without libxfs
- When configured with --without-libxfs, use GenericFileStoreBackend
instead of XfsFileStoreBackend for XFS. At this p... - 09:40 AM Cleanup #7668: remove custom googletest (gtest) copy from source tree
- I have no expertise here and am down with making this change if it works out better, but when we initially grabbed gt...
- 07:43 AM Cleanup #7668 (Resolved): remove custom googletest (gtest) copy from source tree
- Remove the the potentially outdated gtest code from the source tree to keep it up-to-date:
Needed steps:
- since ... - 09:32 AM devops Bug #7669 (New): obscure traceback when a partition of type TOBE_UUID can't be mounted
- Steps to reproduce:...
- 07:29 AM Revision 4d3c1a19 (ceph): Adds radosgw-agent small file sync test
- Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com>
- 07:29 AM Revision 93f5d607 (ceph): radosgw-admin: don't compare pools for different zones
- The actual data locations will be different if they are in the same
cluster.
Signed-off-by: Josh Durgin <josh.durgin... - 07:29 AM Revision 871fe020 (ceph): rgw: set placement targets for zones
- This lets zones use different pools for actual object data.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 07:29 AM Revision 8ba02bfc (ceph): radosgw-agent: add logging to radosgw-admin task tests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:29 AM Revision 1d8dcc4a (ceph): rgw utils: add function to get data log window configuration
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:29 AM Revision 55fad94a (ceph): rgw: create clients in all zones when regions are used
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:29 AM Revision a74cf330 (ceph): radosgw-admin: ignore 301 test against the same src and dest regions
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:29 AM Revision 1143539f (ceph): radosgw-admin: fix typo in data sync test
- re-indent and set k.key instead of k.Key
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 07:29 AM Revision dcad92eb (ceph): radosgw-admin: check that data deletions work as well
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:29 AM Revision 7cb750c4 (ceph): radosgw-admin: test data sync with more than max-entries objects
- For now hard code the max-entries for the radosgw-agent, since
this is the only test that is affected by it.
Signed-... - 07:24 AM Revision 26266045 (ceph): erasure-code: LARGEST_VECTOR_WORDSIZE is always 16
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:24 AM Revision 2beb2a5a (ceph): erasure-code: upgrade to jerasure version 2
- http://tracker.ceph.com/issues/7599 refs #7599
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:24 AM Revision b74115a5 (ceph): autotools: set SIMD_FLAGS with SSE flags
- As well as compiler options.
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:21 AM Revision eb6ffdbf (ceph): erasure-code: remove jerasure version 1
- http://tracker.ceph.com/issues/7599 refs #7599
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:21 AM Revision 4105ab8b (ceph): erasure-code: use jerasure as submodules
- Now that there is a git repository to refer to, it will be good for
maintenance. Pin the version to stable branches.
... - 06:35 AM Revision f92d3a56 (ceph): rgw: add data sync test
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:29 AM Revision e5a43b75 (ceph): rgw: use different keys for different system users
- Only one of these was being used before, due to a bug in
teuthology. This is fixed, and trying to create a second use... - 06:12 AM Revision c84f72ba (ceph): Merge branch 'master' of https://github.com/enovance/ceph-brag into fir...
- 06:11 AM Revision 18506ad6 (ceph): Removed all regular expression parsing and used '-f json' instead
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 05:53 AM Revision cd7986ca (ceph): rbd: check for watchers before trimming an image on 'rbd rm'
- Check for watchers before trimming image data to try to avoid getting
into the following situation:
- user does 'r... - 04:35 AM Revision 4cb6b2a1 (ceph): Modified num_bytes attribute in components_count to be a raw integer
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 03:20 AM devops Bug #7605: statup script /etc/init.d/ceph has incorrect slash
- I meant:
the correct line should be:
r = sprintf("%.2f", d) instead of
r = sprintf(\"%.2f\", d) - 02:33 AM Bug #7667 (Resolved): Fix ceph code to build with llvm (clang/clang++)
- Currently the code don't compile with clang++ due to non c++ standard usage of VLAs (http://clang.llvm.org/compatibil...
- 12:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
- Fixing the agent problem did not make the test pass. I don't think the remainder is an agent issue, but haven't looke...
- 12:20 AM Revision 18bdee6d (ceph): MDSMonitor::prepare_command: fix "mds set"
- CID 1160828 (#1 of 1): Operands don't affect result (CONSTANT_EXPRESSION_RESULT)
result_independent_of_operands: !cm...
03/09/2014
- 11:06 PM Revision 78847807 (ceph): osd_types.cc: add missing break in operator<< case handling
- CID 1086831 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This case (value 4635) is not term... - 09:27 PM Revision 2cf09089 (ceph): upgrade/dumpling-x: fix order
- Make it match the filename.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:58 PM Bug #7666 (Duplicate): librados: lock cycle on shutdown
- ...
- 07:22 PM Revision 83731a75 (ceph): ReplicatedPG::finish_ctx: clear object_info if !obs.exists
- Otherwise, we see a different object_info_t depending on whether the
transaction deleting the object clears before an... - 07:21 PM Revision 40dc3f8b (ceph): Merge pull request #1405 from ceph/wip-7575
- osd: Add hit_set_flushing to track current flushes and prevent races
Reviewed-by: Sage Weil <sage@inktank.com>
Revie... - 07:00 PM Bug #7592: hit_set_trim() removal races with backfill
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic-plana/123754
- 06:58 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- We hit this again with
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-09_03:00:01-rados-firefl... - 05:56 PM Revision f34c742a (ceph): Merge pull request #1406 from dachary/wip-7188-emperor
- common: ping existing admin socket before unlink (emperor)
Reviewed-by: Sage Weil <sage@inktank.com> - 05:56 PM Revision a931aaa6 (ceph): Merge pull request #1407 from dachary/wip-7188-dumpling
- common: ping existing admin socket before unlink (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com> - 05:32 PM Revision a7afa145 (ceph): config.cc: add debug_ prefix to subsys logging levels
- Add debug_ prefix also for 'ceph --admin-daemon *.asok config show'
as already done e.g. by 'ceph-osd --show-config'.... - 05:29 PM Revision a4dfbc88 (ceph): workunit: change timeout 1h -> 3h
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:28 PM Revision 55c23a1a (ceph): qa: add script for testing rados allocation hint
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 04:56 PM Revision 2474e532 (ceph): Merge pull request #1408 from ceph/wip-da-fix-doc
- Fixes and updates for doc
Reviewed-by: Sage Weil <sage@inktank.com> - 12:22 PM Bug #7655 (Resolved): osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
- 11:23 AM Bug #7602: 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys logging levels)
- @Sage: do we need a backport to dumpling?
- 10:32 AM Bug #7602 (Resolved): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys lo...
- 10:10 AM Bug #7602 (Fix Under Review): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (s...
- 11:19 AM Bug #7665 (Resolved): Documentation: cleanup and update doc/install/build-ceph.rst
- Update build instructions for firefly
* Differentiate package names between RPM and debian based distros.
* Differe... - 11:14 AM Feature #7664 (Resolved): systemd service files
- Since the most distributions will use systemd in the future, we need native service files to startup the ceph daemons...
- 10:59 AM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
- attr_cache is used improperly in _delete_head.
2014-03-08T20:39:21.992 INFO:teuthology.task.rados.rados.1.out:[10.... - 10:56 AM Bug #7188 (Resolved): Admin socket files are lost on log rotation calling initctl reload (ubuntu ...
- 10:54 AM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
- looks like #7575
- 10:51 AM Bug #7587 (Duplicate): Failure of LibRadosTwoPoolsPP.PromoteSnap
- I'm pretty sure this is due to teh object_t SnapContext map. #7634
- 05:06 AM Feature #7662: add a "ec profiles" map to OSDMap
- OSDMap has a new field properties, "a named list of properties map":https://github.com/dachary/ceph/blob/wip-erasure-...
- 01:12 AM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
- "work in progress":https://github.com/ceph/ceph/pull/1477
to be used instead of pg_pool_t which could be replaced ... - 01:18 AM Revision 54ffdcc4 (ceph): get-involved.rst: update information
- Added #ceph-devel IRC channel, more mailing lists, wiki and planet.ceph.com.
Signed-off-by: Danny Al-Gaaf <danny.al-... - 12:02 AM Revision d1a888e0 (ceph): swift/containerops.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
03/08/2014
- 11:58 PM Revision 93b95a28 (ceph): radosgw/troubleshooting.rst: s/ceph-osd/OSD/
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:30 PM Revision 2223a372 (ceph): radosgw/config-ref.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:26 PM Revision 0b9d8936 (ceph): Add missing space in error message
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:19 PM Revision 87618d45 (ceph): session_authentication.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:07 PM Revision 682c6958 (ceph): release-process.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:01 PM Revision 72ee3389 (ceph): doc: s/osd/OSD/ if not part of a command
- First attempt to unify usage of OSD over rst files.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 10:31 PM Revision e6660194 (ceph): doc/dev/logs.rst; fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:25 PM Revision bbd1c4ba (ceph): filestore-filesystem-compat.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:22 PM Revision ae123a6d (ceph): corpus.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:16 PM Revision cf9f017d (ceph): config.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:11 PM Revision 5aaecc72 (ceph): cephx_protocol.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:36 PM Revision e471f404 (ceph): Make try_push_job_info() retry using safe_while
- I've noticed sometimes try_push_job_info() fails because of server load
issues. It should try more than once (and now... - 09:19 PM Revision 73849c11 (ceph): Update safe_while's suggested usage pattern
- I didn't love the way safe_while was encouraged to be used and it didn't
fit right with the new no-raising behavior. ... - 08:58 PM Revision c9809849 (ceph): Add optional _raise parameter
- Defaults to True but if set to False, when giving up log a warning
instead of raising an exception.
Signed-off-by: Z... - 08:16 PM Revision eb667673 (ceph): Pass timeout to _spawn_on_all_clients()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:53 PM Revision f5668b36 (ceph): common: ping existing admin socket before unlink
- When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a... - 02:48 PM Revision 3f5fc965 (ceph): common: ping existing admin socket before unlink
- When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a... - 02:18 PM Revision 4e01884e (ceph): Log correct action in CephManager.remove_pool()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:01 PM Revision 72c63f13 (ceph): Log timeout value
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:58 PM Revision b4205cae (ceph): Iterate more sensibly over processes
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:27 AM Revision 2cbb0a40 (ceph): architecture.rst: fix typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:20 AM Revision f581bda5 (ceph): rados: add set-alloc-hint command
- Set allocation hint for an object.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com> - 10:13 AM Revision a4cbb192 (ceph): rados/operations/control.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:27 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Logs lines for *plana166726-98*...
- 09:16 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Crashing thread *7f991c37a700*...
- 08:56 AM Bug #7588 (In Progress): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyge...
- ...
- 08:05 AM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
- teuthology-2014-03-07_23:00:41-rgw-firefly-testing-basic-plana has the latest
- 07:00 AM Bug #7188 (Fix Under Review): Admin socket files are lost on log rotation calling initctl reload ...
- * "dumpling backport":https://github.com/ceph/ceph/pull/1407
* "emperor backport":https://github.com/ceph/ceph/pull/... - 05:17 AM Revision 9bf39e2c (ceph): Broke down sysinfo's format into a histogram with a value and count
- so that we just see how many of each version/distro/kernel/os/arch/cpu/etc are running
Signed-off-by: Babu Shanmugam... - 12:53 AM Revision 4d6a74d4 (ceph): TestPGLog::proc_replica_log: call doesn't adjust olog
- We don't adjust head with proc_replica_log, don't assert that
it's been adjusted.
Signed-off-by: Samuel Just <sam.ju... - 12:53 AM Revision e830f9ff (ceph): TestPGLog: check on last_update in run_test_case
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:53 AM Revision 7c77ff62 (ceph): TestPGLog: add a test case verifying case where we have the prior_version
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:53 AM Revision 3befb936 (ceph): PGLog::_merge_object_divergent_entries: handle missing.have == prior_ve...
- Fixes: #7658
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:53 AM Revision 25916681 (ceph): PGLog::proc_replica_log: select divergent log entries correctly
- Looking for an entry in olog which matches one of ours might add
extra divergent entries. Instead, do what merge_log...
03/07/2014
- 11:46 PM Revision 9db66564 (ceph): upgrade/dumpling-x: do not thrash primary-affinity
- We can't do it on a mixed cluster
Signed-off-by: Sage Weil <sage@inktank.com> - 11:27 PM Revision 71b4474b (ceph): client: fix Client::getcwd()
- An recent commit made MDS not include dentry trace in LOOKUPPARENT
reply. It broke Client::getcwd. The fix is change ... - 11:23 PM Revision db0c3782 (ceph): Merge remote-tracking branch 'gh/wip-7210' into firefly
- Reviewed-by: Sage Weil <sage@inktank.com>
- 11:22 PM Revision 617ce676 (ceph): mds: introduce LOOKUPNAME MDS request
- The new MDS request is used for connecting a given inode to its
parent inode. It allows client to have efficient impl... - 11:21 PM Revision 1c8c6189 (ceph): qa/workunits/cephtool/test.sh: fix 'osd thrash' test
- - fix the wait check for osds to come back up
- make sure they get marked back in, too
Signed-off-by: Sage Weil <sag... - 11:05 PM Revision 20754779 (ceph): Merge pull request #1403 from ceph/wip-7642
- mon: fix check for primary-affinity feature bit, and fix a race in similar checks
Reviewed-by: Samuel Just <sam.just... - 10:44 PM Revision b62f9f07 (ceph): mon/OSDMonitor: feature feature check bit arithmetic
- Make sure all features are present (instead of just any of them).
Signed-off-by: Sage Weil <sage@inktank.com> - 10:19 PM Revision 21c22595 (ceph): Merge pull request #1404 from ceph/wip-7652
- mon: fix infininte pg create msgs for erasure pools
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:02 PM Revision 8d52fb70 (ceph): mon/PGMap: send pg create messages to primary, not acting[0]
- For erasure pools, these may not match.
In the case of #7652, this caused pg_create messages to be send
indefinitely... - 09:56 PM Revision c8b34f19 (ceph): mon/PGMonitor: improve debugging on PGMap updates slightly
- Chasing #7652
Signed-off-by: Sage Weil <sage@inktank.com> - 09:29 PM Revision b9bcc159 (ceph): mon/OSDMonitor: prevent set primary-affinity unless all OSDs support it
- Make sure all running OSDs support the feature before we start using it
(even if the config option is on!).
Fixes: #... - 09:29 PM Revision 819cce2d (ceph): mon/OSDMonitor: make osdmap feature checks non-racy
- The check for OSD features may race with the boot of an OSD that does not
have the necessary features. Check the pen... - 09:14 PM Revision 204b3ac7 (ceph): Change default workunit timeout to 1h
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 09:03 PM Revision 9109008a (ceph): stress-split: use dumpling version of rbd.py tests
- The firefly version has a test that depends on new behavior.
Fixes: #7643
Signed-off-by: Josh Durgin <josh.durgin@in... - 08:43 PM Revision 5f7efec1 (ceph): tools/rados/rados.cc: use write_full for sync_write for ec pools
- Fixes: #7650
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:06 PM Bug #7587 (In Progress): Failure of LibRadosTwoPoolsPP.PromoteSnap
- 08:04 PM Revision ec38bd3c (ceph): Use safe_while's action arg
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:02 PM Revision 73f5af2f (ceph): Add optional 'action' parameter to safe_while
- This is to make it easier to see what actually timed out when scanning
error logs
Signed-off-by: Zack Cerza <zack.ce... - 07:49 PM Revision 38fd666a (ceph): qa: workunits/mon/rbd_snaps_ops.sh: ENOTSUP on snap rm from copied pool
- 'rados cppool' copies the contents but that doesn't make the destination
pool an unmanaged snaps pool. Therefore, we... - 07:49 PM Revision c13e1b79 (ceph): mon: OSDMonitor: don't remove unamanaged snaps from not-unmanaged pools
- Although we should allow creating unmanaged snaps on not-unamanaged pools,
as long as those pools don't have any mana... - 07:48 PM Revision 135c27ec (ceph): osd: Add hit_set_flushing to track current flushes and prevent races
- When flushing a HitSet track in hit_set_flushing map so that
agent_load_hit_sets() doesn't try to read it too soon.
... - 07:36 PM Revision 7604a1b6 (ceph): Update safe_while users to reflect new defaults
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:33 PM Revision 8258c847 (ceph): Change safe_while defaults to 6s 10x no increment
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:03 PM Revision 081a5c4b (ceph): Look for ready() in the right place
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:33 PM Bug #7636 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.EvictSnap
- this is due to the SnapContext object_t map key bug, see #7634
- 05:39 PM Revision ad04075b (ceph): Merge pull request #218 from ceph/wip-radosbench-timeout
- Introduce a timeout to radosbench's join phase
- 05:36 PM Revision 1778d358 (ceph): Use a timeout of config.get('time') * 2
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:21 PM Revision 0be5f1f0 (ceph): Introduce a timeout to radosbench's join phase
- Set to 15min right now.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 05:16 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
- ReplicatedPG::start_flush needs to handle the case where a clone is missing
- 05:08 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
- 05:08 PM Bug #7659 (Resolved): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
ceph version 0.77-746-g65c0738 (65c07386f5e18d543e266c4ae81dcd1a9724df8b)
1: (ReplicatedPG::get_object_context(h...- 05:08 PM Bug #7660 (Rejected): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
- 05:08 PM Bug #7660 (Rejected): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
ceph version 0.77-746-g65c0738 (65c07386f5e18d543e266c4ae81dcd1a9724df8b)
1: (ReplicatedPG::get_object_context(h...- 04:53 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
- 04:52 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
- 04:38 PM Revision aea501be (ceph): fs/basic: multimds
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:32 PM Revision 0815e4fa (ceph): rados/singleton-nomsgr: add allocation hint test
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 04:20 PM Revision fbb05b73 (ceph): Remove the mds-mon-osd upgrade sequence
- It wasn't actually supported.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 04:19 PM Revision 0fd636c4 (ceph): Merge remote-tracking branch 'gh/firefly'
- Conflicts:
README - 03:44 PM Bug #7644 (Duplicate): cephx: verify_reply couldn't decrypt with error: error decoding block for ...
- same cause as #7642.. missing features due to primary-affinity
- 03:33 PM Bug #7644 (In Progress): cephx: verify_reply couldn't decrypt with error: error decoding block fo...
- 08:53 AM Bug #7644 (Duplicate): cephx: verify_reply couldn't decrypt with error: error decoding block for ...
- 2014-03-07T01:15:35.712 INFO:teuthology.task.radosbench.radosbench.0.err:[10.214.131.3]: 2014-03-07 01:15:35.712493 7...
- 03:44 PM Bug #7655: osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
- Also caused:
-95> 2014-03-07 15:04:11.803637 7f504ecb4700 10 _merge_object_divergent_entries: merging hoid c520... - 03:19 PM Bug #7655 (Resolved): osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
ceph version 0.77-757-g8221a8e (8221a8ecba14f80eb7e35e3b1e6fe8487502b2d9)
1: (ReplicatedPG::recover_primary(int,...- 03:34 PM devops Feature #7656: kmod: remove hardcoded "rhel7" branch name
- As a bit of context, this feature comes from a suggestion by Sage that it would be nice to be able to build rhel7* br...
- 03:28 PM devops Feature #7656 (Rejected): kmod: remove hardcoded "rhel7" branch name
- We have preliminary kmod packages available at http://ceph.com/rpm-testing/rhel7/x86_64/ (source at https://github.co...
- 03:24 PM Bug #7210 (Pending Backport): mon: does not validate snapshot removal commands
- 03:23 PM Bug #7210 (Resolved): mon: does not validate snapshot removal commands
- 03:05 PM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
- 01:30 PM Bug #7642 (Fix Under Review): osd: upgrade stress-split: bad state machine event
- 01:15 PM Bug #7642: osd: upgrade stress-split: bad state machine event
- the thrasher set primary-affinity, which dumpling doesn't understand, so they disagreed on pg mappings.
- 10:22 AM Bug #7642 (Need More Info): osd: upgrade stress-split: bad state machine event
- 08:30 AM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
- ...
- 02:31 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_02:30:02-rados-firefly-testing-basic-plana/1209...
- 02:27 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_02:30:02-rados-firefly-testing-basic-plana/1211...
- 02:22 PM Bug #7643 (Resolved): librbd: upgrade stress-split: FAIL test_rbd.TestImage.test_remove_with_watcher
- Changed the suite to use the dumpling version of python rbd tests in commit:9109008ad7473836c8c408fd68a7eb6353121298
- 08:31 AM Bug #7643 (Resolved): librbd: upgrade stress-split: FAIL test_rbd.TestImage.test_remove_with_watcher
- ...
- 02:19 PM Bug #7652 (Resolved): mon not removing from creating_pgs
- 01:21 PM Bug #7652 (Resolved): mon not removing from creating_pgs
- 2014-03-06 22:25:54.839669 7fe7e42b6700 1 -- 10.214.134.34:6789/0 --> 10.214.134.34:6800/41782 -- osd_pg_create(pg3....
- 12:49 PM Revision 3dd09e36 (ceph): Removed nw_info from sysinfo
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 12:42 PM Bug #7650: rados bench seq tests not performed at correct IO sizes
- 11:22 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
- With the fix that was put in place for bug #7610, rados bench appears to not be correctly respecting the -b flag when...
- 12:42 PM Bug #7649: ec ceph_test_rados stuck recovering
- 10:58 AM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
- 2014-03-06 21:08:49.685246 7ff6f50d9700 10 osd.1 pg_epoch: 534 pg[4.3s0( v 534'466 lc 13'23 (0'0,534'466] local-les=5...
- 11:23 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_20:46:32-upgrade:dumpling-x:parallel-firefly---...
- 10:03 AM Bug #7648 (Resolved): ceph-mon corner case denial of service
- ceph-mon corner case denial of service
Improperly positioned (in CRUSH map) OSD may cause mon process to stop resp... - 09:35 AM rgw Bug #7647 (Resolved): Ensure that swift keys don't include backslashes
- Currently, when we generate a Swift key it can include a backslash as part of the JSON encoding output, so when peopl...
- 09:10 AM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
- ...
- 09:09 AM devops Bug #7645 (Resolved): mira020 is having problems
- Been seeing a lot of jobs get borked because of this:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-07_01... - 08:51 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- the blocking only happens if the limits are set... which we should probably just disable for the osd since we are alr...
- 08:06 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- "start_copy":https://github.com/ceph/ceph/blob/88047d0b7741d1e131dc423b83bd9bf4cf7f6b46/src/osd/ReplicatedPG.cc#L5316...
- 06:47 AM Revision 09a317fb (ceph): Made crush_types to be a map of type to count, so we can tell how many ...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 05:14 AM Revision 88047d0b (ceph): Merge pull request #1399 from jrcresawn/docfix
- Changed Availability section of ceph-mds.rst to reference ceph-mds, not ...
Reviewed-by: Sage Weil <sage@inktank.com> - 05:11 AM Subtask #6586 (Resolved): ErasureCodeJerasure::decode does not use want_to_read
- "fixed":https://github.com/ceph/ceph/commit/3650da69
- 05:11 AM Revision 8221a8ec (ceph): Merge pull request #1394 from ceph/wip-7610
- obj_bencher: allocate contentsChars to object_size, not op_size
Reviewed-by: Sage Weil <sage@inktank.com> - 05:11 AM Revision e53aed28 (ceph): SubmittingPatches: clarify "github fork" in preference to "clone"
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 05:09 AM Revision 4b11d072 (ceph): Mark this 'while True' loop with 'finite' comment
- If we're going to embark on a mission to rid ourselves of
infinitely-looping while loops, it seems smart to start mar... - 05:09 AM Revision 1322e05d (ceph): Merge pull request #1371 from ceph/wip-debian-files
- packaging: use wildcard for test files in Debian
Reviewed-by: Sage Weil <sage@inktank.com> - 05:05 AM Cleanup #7388 (Closed): ceph osd find has no format argument
- The --format argument is implicit for all commands.
- 05:05 AM Revision c09caf03 (ceph): Merge pull request #1374 from ceph/wip-vstart-paths
- test: Use non-default out/ dev/ paths in vstart
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Sage Weil ... - 05:05 AM Revision c9eaa651 (ceph): Changed Availability section of ceph-mds.rst to reference ceph-mds, not...
- Signed-off-by: James Ryan Cresawn <jrcresawn@gmail.com>
- 05:03 AM Feature #6645 (Closed): EC: [link] BPC (basic pyramid code)
- 05:01 AM Feature #4929 (Resolved): Erasure encoded placement group
- 04:49 AM Subtask #5877 (Resolved): Plugable erasure code library
- 04:48 AM Subtask #5860 (Rejected): PG::calc_acting and friends should use PGBackend to select the acting s...
- Done elsewhere
- 04:42 AM Subtask #6888 (Resolved): EC/Tiering: Disallow omap writes on pools which are backed by EC pools
- In firefly
- 04:41 AM Subtask #5863 (Rejected): OSD internals must work in terms of cpg_t
- Done elsewhere
- 04:40 AM Subtask #5859 (Rejected): GetInfo should use PGBackend methods to determine when peering can cont...
- Done elsewhere
- 04:39 AM Subtask #5433 (Rejected): Factor out the ReplicatedPG object replication and client IO logic as a...
- Done elsewhere
- 04:32 AM Revision 20bfc978 (ceph): Give up on wait_until_healthy() after 15min
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:06 AM Revision 23db6782 (ceph): Merge pull request #1397 from ceph/wip-7638
- ReplicatedPG::trim_object: use old_snaps for rollback
Reviewed-by: Sage Weil <sage@inktank.com> - 04:05 AM Revision 4a0c3a66 (ceph): Merge pull request #1398 from ceph/wip-7634
- ReplicatedPG: use hobject_t for snapset_contexts map
Reviewed-by: Sage Weil <sage@inktank.com> - 03:19 AM Revision 0037ee45 (ceph): Merge pull request #1395 from ceph/wip-7637
- osd: fix agent thread shutdown
Reviewed-by: Samuel Just <sam.just@inktank.com> - 02:52 AM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- On Ubuntu 12.04.2 When cuttlefish is installed, apt-get install ceph to emperor will not upgrade ceph-common...
- 02:00 AM Revision ac6ebf87 (ceph): Merge pull request #217 from ceph/wip-fix-plus
- suite: fix + handling
- 01:56 AM Revision 94d73bd4 (ceph): suite: fix build_matrix for + case
- The + means we should concatenate everything in the directory. Do that.
This was totally broken before (and unused ... - 01:51 AM Revision 136775b4 (ceph): Don't warn on legacy crush tunables
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:32 AM Revision 57259b54 (ceph): rados: use backwards compatible args
- For ops that default to 0, only add arguments for them if they are
specified in the task config. This lets us use the... - 01:04 AM Revision 022a6a3e (ceph): Revert "The parallel task expects dicts here..."
- This reverts commit 79e348320f3695d085693b7ce0c538a9dfdd182b.
- 12:57 AM Revision 95d445da (ceph): Merge remote-tracking branch 'gh/firefly'
- 12:56 AM Revision 70de7d52 (ceph): Revert "Do not spawn a parallel task if dictionary entry does not exist."
- This reverts commit dadc9f7d0b6d9c13ccbc4edeb9f7875fc0ae0cac.
- 12:32 AM Revision 79e34832 (ceph): The parallel task expects dicts here...
- We should fix that at some point.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 12:12 AM Revision 09668a49 (ceph): osd: fix agent thread shutdown
- We had an old invariant that agent_queue would have at least 1 entry in
it to simplify some other code paths, but it ... - 12:04 AM Revision bda2fd3d (ceph): upgrade: fix typo in subsection name
- It's referred to as workload, not workunit, by the parallel task earlier.
Signed-off-by: Josh Durgin <josh.durgin@in... - 12:04 AM Revision 487be437 (ceph): upgrade: fix indentation for final-workload
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
03/06/2014
- 11:51 PM Revision 06b96ffd (ceph): Merge pull request #1389 from ceph/wip-firefly-misc
- fix rest tests; fix COLL_MOVE_RENAME dump
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:51 PM Revision d4b4468c (ceph): Merge pull request #1393 from dachary/wip-7072
- logrotate: copy/paste daemon list from ceph-*-all-starter.conf
Reviewed-by: Sage Weil <sage@inktank.com> - 11:47 PM Revision 7411c3c6 (ceph): logrotate: copy/paste daemon list from *-all-starter.conf
- Each upstart/*-all-starter.conf use the same script to find the list of
daemons and their ids. Copy it over to the co... - 11:34 PM Revision 6f7c8c79 (ceph): Merge pull request #1392 from ceph/wip-7632
- ReplicatedPG: consistently use ctx->at_version.version for stashed objec...
Reviewed-by: Sage Weil <sage@inktank.com> - 11:30 PM Revision 57c7e198 (ceph): Merge pull request #1391 from ceph/wip-7393
- ReplicatedPG: clean up num_dirty adjustments
Reviewed-by: Sage Weil <sage@inktank.com> - 11:29 PM Revision 51461432 (ceph): upgrade/dumpling-x: more indentation
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:27 PM Revision 0bf78e6b (ceph): upgrade/dumpling-x: fix indentation
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:16 PM Revision d7892f12 (ceph): Merge remote-tracking branch 'gh/firefly'
- 11:01 PM Revision b6872b25 (ceph): ReplicatedPG::trim_object: use old_snaps for rollback
- We need to rollback the old value of snaps, not the
new one.
Fixes: #7638
Signed-off-by: Samuel Just <sam.just@inkta... - 10:53 PM Revision 7f5fcd7b (ceph): Merge pull request #14 from ceph/wip-final-workload-wusui
- Fix parallel workunit issues.
- 10:40 PM Revision b5b67d19 (ceph): ReplicatedPG: use hobject_t for snapset_contexts map
- Otherwise, two objects with different namespaces but
the same object_t will end up clobbering each other's
contexts.
... - 10:34 PM Revision 182667ae (ceph): Fix parallel workunit issues.
- Fixed the spacing of workunits inside 2-workload and 4-final-workland
files. Removed parallel final-workload referen... - 10:27 PM Revision 7d1e97f7 (ceph): Revert "Update rados_api_tests.yaml"
- This needs to reference dumpling now.
This reverts commit 8e88922581f80000784072e381867f0b5448cd7f. - 10:27 PM Revision 7b497e1f (ceph): get test-upgrade-firefly.sh from the dumpling branch
- it doesn't exist elsewhere
- 09:46 PM Revision b4369307 (ceph): qa/workunits/rest/test.py: do not test 'osd thrash'
- This wreaks havoc on our QA because it marks osds up and down and then
immediately after that we try to scrub and som... - 09:44 PM Revision 237f0fb4 (ceph): os/ObjectStore: dump COLL_MOVE_RENAME
- This got missed way back in ef7cffc34f3bad4ffc090361ad9030a47584a3bf
(pre-0.71).
Signed-off-by: Sage Weil <sage@inkt... - 09:11 PM Bug #7610 (Resolved): Memory corruption during rados bench
- 11:28 AM Bug #7610: Memory corruption during rados bench
- 08:11 PM Revision f888ab41 (ceph): ReplicatedPG: consistently use ctx->at_version.version for stashed object
- Otherwise, two ops might end up using the same version number.
Fixes: #7632
Signed-off-by: Samuel Just <sam.just@ink... - 08:09 PM Bug #7637 (Resolved): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 03:39 PM Bug #7637 (In Progress): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 03:10 PM Bug #7637 (Fix Under Review): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 01:42 PM Bug #7637 (Resolved): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- -7> 2014-03-04 14:58:03.649200 1a55b700 1 OSD::op_tp worker finish
-6> 2014-03-04 14:58:03.653399 1ff68700 ... - 08:07 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
- 04:51 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
- ...
- 08:06 PM Bug #7638 (Resolved): snap update rollback not working right
- 03:28 PM Bug #7638: snap update rollback not working right
- 02:41 PM Bug #7638 (Resolved): snap update rollback not working right
- failure_reason: '"2014-03-06 13:29:45.498787 osd.1 10.214.134.34:6809/33548 28 : [ERR]
osd.1 found snap mapper err... - 08:05 PM Bug #7634 (Resolved): osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.len...
- 03:28 PM Bug #7634: osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.length() == 0)...
- 11:51 AM Bug #7634: osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.length() == 0)...
Also happened:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-pla...- 11:04 AM Bug #7634 (Resolved): osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.len...
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118367/teutholo...- 08:05 PM Revision eca7e633 (ceph): ReplicatedPG: clean up num_dirty adjustments
- Previously, a _delete_head() followed by a recreation on an object in
the same transaction would result in num_dirty ... - 07:35 PM Revision d379b1f1 (ceph): osd: bracket role changes with scrub reg/unreg
- Make sure the reg/unreg calls for putting ourselves in the scrub schedule
bracket any PG role changes, or that initia... - 07:35 PM Revision 173116fa (ceph): osd: only register for scrub if we are the PG primary
- There is no reason to put non-primary PGs on the scrub schedule as they
will be ignored when the worker comes around.... - 07:32 PM Revision c8c2f547 (ceph): Client: fix build issue (lost semicolon)
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 07:12 PM Revision d1714180 (ceph): obj_bencher: allocate contentsChars to object_size, not op_size
- Otherwise, our attempt to sanitize object_size bytes of
data.object_contents will be doomed to memory corruption.
Fi... - 07:01 PM Revision 7403b235 (ceph): Merge pull request #1386 from ceph/wip-7624
- ReplicatedPG: ensure clones are readable after find_object_context
Reviewed-by: Sage Weil <sage@inktank.com> - 06:59 PM Revision cf2f3adf (ceph): Merge pull request #1387 from ceph/wip-7618
- ReplicatedPG::wait_for_degraded_object: only recover if found
Reviewed-by: Sage Weil <sage@inktank.com> - 06:54 PM Revision b1ac3aff (ceph): Merge pull request #1320 from ceph/wip-libcephfs-fixes
- Wip libcephfs fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:44 PM Revision aa7945ab (ceph): Merge pull request #1379 from ceph/wip-7562
- mon: make quorum list (by name) be in quorum order
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:29 PM Fix #6278: osd: throttle snap trimming
- We are seeing the very same issue. Is there an ETA or can we sponsor someone to fix it :D ?
- 06:14 PM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- ...
- 06:47 AM devops Bug #7627 (Resolved): ceph-disk: does not start daemons properly under systemd
- After creating a cluster with ceph-deploy, the test waits up to 15 minutes to get a HEALTH_OK back, but as the output...
- 05:57 PM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...
- 04:48 PM Revision bafd76ad (ceph): ReplicatedPG: ensure clones are readable after find_object_context
- We only get EAGAIN if the object is missing. We also need the
clone to be readable if we are reading it.
The other ... - 04:15 PM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- there is just one string : C_ObjectOperation_copyget::out_category
- 03:57 PM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- (10:44:51 AM) sjusthm: loicd: that one may be tricky to track down, you'll probably want to find a way for the struct...
- 10:12 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Can I help ?
- 03:50 PM Bug #7072 (Resolved): logrotate not sending HUP signal
- 03:21 PM Bug #7072 (Fix Under Review): logrotate not sending HUP signal
- "work in progress":https://github.com/ceph/ceph/pull/1393
- 03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- 57c7e1981991091fa78ed65940eede3420a47d80 to Firefly
- 03:30 PM Bug #7393 (Resolved): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 white...
- 12:12 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- 03:34 PM Bug #7632 (Resolved): os/FileStore.cc: 2538: FAILED assert(0 == "unexpected error")
- 08:55 AM Bug #7632 (Resolved): os/FileStore.cc: 2538: FAILED assert(0 == "unexpected error")
- 2014-03-06 02:55:55.283863 7eff27ce1700 -1 os/FileStore.cc: In function 'unsigned int FileStore::_do_transaction(Obje...
- 03:00 PM Bug #7633 (Resolved): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefl...
- 01:36 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
- wip-final-workload-wusui contains the changes.
https://github.com/ceph/ceph-qa-suite/pull/14 is a pull request for t... - 12:49 PM Bug #7633 (In Progress): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-fir...
- 12:44 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
- this looks like malformed yaml
- 12:34 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
- What is the relation here?
- 10:16 AM Bug #7633 (Resolved): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefl...
- Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-03-05_10:33:26-upgrade:dumpling-x:parallel-firefly---basic-p...
- 02:22 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
- 12:12 PM Bug #7636 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.EvictSnap
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118451/teutholo...- 11:47 AM Bug #7635 (Duplicate): failed to recover before timeout expired
- http://pulpito.ceph.com/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118391/
Strange it looks l... - 11:32 AM Bug #7601 (Duplicate): "command crashed with signal 6" in rados-firefly-testing-basic-plana suite...
- Closing, we'll create a new one if it wasn't 7604 and we have logs.
- 11:30 AM Bug #7601: "command crashed with signal 6" in rados-firefly-testing-basic-plana suite - hung tests
- No logs, probably 7604.
- 11:01 AM Bug #7624 (Resolved): osd/ECBackend.cc: 1644: FAILED assert(r == 0)
- 10:59 AM Bug #7618 (Resolved): osd/ECBackend.cc: 475: FAILED assert(r == 0)
- 10:44 AM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
- Merged into master as of commit: aa7945a
- 10:30 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
- 10:29 AM Bug #7590 (Resolved): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap create <base>...
- 10:28 AM Bug #7630 (Duplicate): Simple tiering test produces OSD assert
- #7604
- 10:28 AM Bug #7630 (Resolved): Simple tiering test produces OSD assert
- 07:32 AM Bug #7630: Simple tiering test produces OSD assert
- rados bench command run:
/usr/bin/rados -c /tmp/cbt/ceph/ceph.conf -p base -b 4194304 bench 300 write --concurrent... - 07:31 AM Bug #7630 (Duplicate): Simple tiering test produces OSD assert
- An initial teiring test produced the included assert just as rados bench started. pools were on the same physical di...
- 09:46 AM Feature #7058: osd primary affinity
- https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity
- 09:24 AM rbd Feature #7455: krbd,kcephfs: support primary-affinity
- https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity
- 09:17 AM rbd Feature #7455 (In Progress): krbd,kcephfs: support primary-affinity
- 09:10 AM Feature #7619 (In Progress): objecter: replace client_lock with fine grained read-write locks
- 08:43 AM Bug #7210: mon: does not validate snapshot removal commands
- Finally got to reproduce this. I was missing the part where we actually needed to remove the image's snapshot using ...
- 03:23 AM Bug #7210: mon: does not validate snapshot removal commands
- I've got bitten by this. I have an openstack glance volume, and it contains images and snapshots. I did the following...
- 08:39 AM Revision 90f5a687 (ceph): 1. Removed name of the pool from pool_metadata
- 2. Included pool type in pool_metadata
3. Renamed rep_size attribute to size in pool_metadata
Signed-off-by: Babu Sh... - 07:58 AM Revision da97feea (ceph): 1. simplified the 'bytes' info to just be bytes
- 2. prefix all the members of the components_info with 'num_'
Signed-off-by: Babu Shanmugam <anbu@enovance.com> - 07:38 AM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
- Apologies in advance if this is a test misconfiguration.
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-06... - 07:30 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- can upload the core dump and ceph-mds binary to somewhere?
- 06:24 AM Bug #6301: ceph-osd hung by XFS using linux 3.10
- One fix has been integrated in kernel commit b3f03bac8132207a20286d5602eda64500c19724
(3.14rc1).
No backport AFA... - 04:58 AM Revision 9d387d38 (ceph): Merge pull request #1378 from ceph/wip-7487
- mon: no crush buckets with type 0 (#7487)
Reviewed-by: Greg Farnum <greg@inktank.com> - 03:27 AM Bug #7626 (Closed): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- We are using CentOS 6.5 and Ceph 0.77
After updating to 0.77 one monitor can't start:
cluster 554b69c8-bdca... - 01:38 AM Revision 697bf8fd (ceph): Merge pull request #1380 from ceph/wip-pool-delete
- mon/OSDMonitor: fix pool deletion races
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
03/05/2014
- 11:58 PM Revision 2adc534a (ceph): mon/OSDMonitor: fix pool deletion checks, races
- Unify the pool deletion safety checks into a single set of functions.
Make sure we check the committed state and erro... - 11:51 PM Revision d9e88063 (ceph): ReplicatedPG::wait_for_degraded_object: only recover if found
- Fixes: #7618
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:31 PM Revision b563a7c7 (ceph): Merge pull request #1381 from ceph/wip-7618
- ReplicatedPG::recover_replicas: do not assume that missing objects are u...
Reviewed-by: Sage Weil <sage@inktank.com> - 11:18 PM Revision 16e3d4d3 (ceph): Merge pull request #1382 from ceph/wip-7616
- Wip 7616
Reviewed-by: Sage Weil <sage@inktank.com> - 11:14 PM Revision a222e7a1 (ceph): ReplicatedPG::recover_replicas: do not assume that missing objects are ...
- Fixes: #7618
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:13 PM Revision 3f59f029 (ceph): Revert "c_read_operations.cc: fix resource leak"
- This reverts commit 3cd751b0a280909510c3e633cc8cd4b9f5e3b2d9.
A rados_release_read_op() has already been performed, ... - 10:29 PM Revision a71ddb0b (ceph): mon: make quorum list (by name) be in quorum order
- Fixes: #7562
Signed-off-by: Sage Weil <sage@inktank.com> - 10:22 PM Revision b642e388 (ceph): Merge pull request #1343 from ceph/wip-cache-warn-full
- mon: warn when cache tier is full
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Greg Farnum <greg@inktan... - 10:21 PM Revision 10f66072 (ceph): Merge pull request #1372 from ceph/wip-7607
- wip 7607
Reviewed-by: Sage Weil <sage@inktank.com> - 10:19 PM Revision b476d324 (ceph): Merge pull request #1366 from ceph/wip-6820.dumpling
- mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump
- 10:19 PM Revision dd703345 (ceph): Merge pull request #1365 from ceph/wip-6820.emperor
- mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump
- 10:18 PM Revision b093958a (ceph): Merge pull request #1351 from ceph/wip-7248
- osd: OSD: limit the value of 'size' and 'count' on 'osd bench'
Reviewed-by: Sage Weil <sage@inktank.com> - 09:39 PM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
- Several examples of this in the following run, but here is one job:
http://pulpito.front.sepia.ceph.com/teuthology... - 09:17 PM Revision 240446e7 (ceph): test: merge unittest_crushwrapper and unittest_crush_wrapper
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:15 PM Revision 772968e6 (ceph): mon/OSDMonitor: disallow crush buckets of type 0
- Prevent creation of buckets of type 0 ('osd', 'device', etc.), as they
will confusing the mapping algorithm.
Signed-... - 08:53 PM Revision 8b3934fc (ceph): PGBackend::rollback_stash: remove the correct shard
- Fixes: #7616
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:52 PM Revision 1ddec86e (ceph): FileStore::_collection_move_rename: propogate EEXIST
- Previously, an EEXIST would get masked by the subsequent clone
operation.
Signed-off-by: Samuel Just <sam.just@inkta... - 08:52 PM Revision ca12e0d9 (ceph): qa/workunits/mon/crush_ops: use expect_false
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:45 PM Revision d3e13a7c (ceph): Merge pull request #1377 from ceph/wip-7584
- qa/workunit/rados/test-upgrade-firely.sh
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:39 PM Revision 9a8bf66d (ceph): ceph.conf.template: add in sensible erasure coding defaults
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:38 PM Revision c3766c58 (ceph): upgrade/dumpling-x: skip rados api tests that fail against firefly OSDs
- Fixes: #7584
Signed-off-by: Sage Weil <sage@inktank.com> - 08:38 PM Revision e6698af8 (ceph): ceph_manager: fix erasure coding m, k values
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:37 PM Revision 9c626e0b (ceph): qa/workunit/rados/test-upgrade-firely.sh
- Skip the tests that don't pass when run against firefly OSDs.
Fixes: #7584
Signed-off-by: Sage Weil <sage@inktank.com> - 08:35 PM Revision 561869d9 (ceph): Merge pull request #1376 from ceph/wip-7608
- test: Fix tiering test cases to use ---force-nonempty
Reviewed-by: Sage Weil <sage@inktank.com> - 08:31 PM Revision e016e83b (ceph): test: Fix tiering test cases to use ---force-nonempty
- Fixes: #7608
Signed-off-by: David Zafman <david.zafman@inktank.com> - 08:13 PM Revision e69da0a5 (ceph): Log job PID
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:59 PM Revision 05923680 (ceph): mon: warn when pool nears target max objects/bytes
- The cache pools will throttle when they reach the target max size, so it
is important to make the administrator aware... - 07:07 PM Revision 8106adee (ceph): Merge pull request #1375 from ceph/wip-pgmap-stat
- mon/PGMap: return empty stats if pool is not in sum
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:44 PM Revision f6edceef (ceph): mon/PGMap: return empty stats if pool is not in sum
- Greg was right!
When a pool is created, the PGs are not added to the PGMap until the *next*
proposal. Weaken the as... - 06:14 PM Revision c5f0e718 (ceph): Merge pull request #216 from ceph/wip-workunit-timeout
- Add a 6h timeout to workunits
- 05:50 PM Revision dab02408 (ceph): Merge pull request #9 from ceph/wip-upgrade-dumpling
- upgrade/dumpling: two fixes
- 05:47 PM Bug #7593: Disk saturation during PG folder splitting
- Sage Weil wrote:
> It is difficult to delay splitting without breaking the semantics.
Can you elaborate a little bi... - 09:44 AM Bug #7593: Disk saturation during PG folder splitting
- It is difficult to delay splitting without breaking the semantics. The simplest way to throttle right now is to incr...
- 05:46 PM Revision 66ea0710 (ceph): Merge pull request #13 from ceph/wip-upgrade
- a few upgrade fixes
- 05:43 PM Bug #7623: local 'best' uninitialized in Objecter
- osdc/Objecter.cc: In member function 'int Objecter::recalc_op_target(Objecter::Op*)':
warning: osdc/Objecter.... - 05:40 PM Bug #7623 (Resolved): local 'best' uninitialized in Objecter
- 05:42 PM Bug #7624 (Resolved): osd/ECBackend.cc: 1644: FAILED assert(r == 0)
- Reading from clone needs to require readable on the clone.
ceph version 0.77-729-gd9e8806 (d9e8806308dcd6e52c6907... - 05:30 PM Revision f0ac0f67 (ceph): upgrade/dumpling-x/parallel: do all final workloads
- Run all of the final workloads in succession instead of in separate tests.
Since we are not concerned about timing in... - 05:27 PM Revision bce605d3 (ceph): upgrade/dumpling-x: do not upgrade client host
- If we are running against a mixed cluster for the duration of the upgrade,
we need to make sure we are running the *o... - 05:20 PM Revision 640ff98d (ceph): test: Use non-default out/ dev/ paths in vstart
- Currently, running "make check" nukes any existing vstart
setup in the tree. This change makes it use test_dev/ and ... - 05:17 PM Revision c3c0b080 (ceph): Add a 6h timeout to workunits
- The timeout is configurable, but defaults to six hours. It's implemented
by using the 'timeout' command on the remote... - 04:52 PM Revision 4901347e (ceph): Merge pull request #1373 from ceph/wip-crush-json
- crush: revise JSON format for 'item' type
Reviewed-by: Sage Weil <sage@inktank.com> - 04:30 PM devops Feature #7293 (Resolved): packaging: enable qemu to find librbd on rhev or rhel-osp
- This is done and was commited/merged yesterday (wip-2793) sha1 65f3354903fdbdb81468a84b8049ff19c00f91ba
- 04:28 PM Bug #7580 (Resolved): The package librados2-0.77-0.el6.x86_64.rpm is corrupt and won't install
- Looks like the file was truncated during the copy process into the staging area. I re-did the repo's and re-sync'd wi...
- 04:28 PM Revision 1685c6f7 (ceph): crush: revise JSON format for 'item' type
- Commit a7e9a7b648 changed the JSON format of CRUSH rules
such that the 'item' attribute on a step was sometimes
an in... - 03:59 PM Bug #7621: ceph_test_rados_api_c_read_operations core dumped
- Sorry my fault added the rados_release_read_op() call accidentally to the wrong line. It should have been like this:
... - 03:18 PM Bug #7621 (Resolved): ceph_test_rados_api_c_read_operations core dumped
- 3f59f02913f4277f419052d546bb7448f74aec4d
- 03:00 PM Bug #7621 (In Progress): ceph_test_rados_api_c_read_operations core dumped
- The rados_release_read_op() that crashed it was added Mar 1 in 3cd751b0.
- 02:45 PM Bug #7621 (Resolved): ceph_test_rados_api_c_read_operations core dumped
- 2014-03-05 14:24:27,294.294 INFO:teuthology.task.workunit.client.0.err:[10.214.132.34]: 7fff7f956000-7fff7f957000 r-x...
- 03:32 PM Bug #7618: osd/ECBackend.cc: 475: FAILED assert(r == 0)
- Merged 1 fix, found another problem.
- 01:15 PM Bug #7618 (Resolved): osd/ECBackend.cc: 475: FAILED assert(r == 0)
- recover_replicas must not assume that unfound objects are missing
red_to:921600, data_complete:false, omap_recover... - 03:31 PM Bug #7616 (Resolved): broken rollback_stash
- 12:48 PM Bug #7616 (Resolved): broken rollback_stash
- 2014-03-04 22:35:48.598322 7f8e69953700 10 osd.4 459 do_waiters -- start
2014-03-04 22:35:48.598324 7f8e69953700 10 ... - 03:27 PM Bug #7590 (Fix Under Review): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap creat...
- 02:47 PM Fix #7562 (Fix Under Review): mon: pretty-print of mon status should keep monitor ranks and names...
- 02:24 PM Feature #7442 (Resolved): mon: health warn on pg "full"
- 02:21 PM Bug #7607 (Resolved): ReplicatedPG::fill_in_copy_get: omap doesn't get filled in correctly for sm...
- 02:19 PM Bug #6820 (Resolved): Bad commandline usage crashed my monitor
- 02:18 PM Bug #7248 (Resolved): osd: bench set max size
- 02:18 PM rbd Bug #7620 (Can't reproduce): BUG: soft lockup - CPU#0 stuck for 23s!
- Noticed this hung job:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-04_19:01:51-rbd-dumpling-testing-bas... - 02:12 PM Feature #7619 (Resolved): objecter: replace client_lock with fine grained read-write locks
- 01:26 PM Bug #7610: Memory corruption during rados bench
- Performed further tests with tcmalloc's HEAPCHECK but without much luck.
I also ran through the same tests with 3x... - 11:08 AM Bug #7610: Memory corruption during rados bench
- Ran rados under valgrind and valgrind is not happy, but I'm not sure it's really telling us much. Sam suspects gener...
- 06:24 AM Bug #7610 (Resolved): Memory corruption during rados bench
- This is ceph 0.77-655-g195d53a-1saucy
After doing parallel 4194306 byte object writes/reads to EC encoded pools vi... - 12:56 PM Bug #7487 (Fix Under Review): mon: crashes when moving CRUSH items in zero-weighted tree?
- The problem is adding a bucket of type 'osd'; fixing the mon to error out at that stage. Tested this with a normal t...
- 12:55 PM devops Bug #7617 (Resolved): ceph-deploy uninstall should document why it doesn't remove all relevant pa...
- ceph-deploy uninstall on Precise left behind librbd1 and librados2 (dependencies, not explicitly installed); an audit...
- 12:41 PM Bug #7608 (Resolved): test/librados/tier.cc multiple -ENOTEMPTY failures
- 12:30 PM Bug #7608 (Fix Under Review): test/librados/tier.cc multiple -ENOTEMPTY failures
- 09:37 AM Bug #7608 (In Progress): test/librados/tier.cc multiple -ENOTEMPTY failures
- 11:55 AM rgw Bug #7597: hang in rados/test.sh
- Unsure if this is identical:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-05_02:30:28-rados-firefly-testin... - 07:47 AM rgw Bug #7597: hang in rados/test.sh
- This job was running for over 60 hours:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-01_23:02:09-rbd-fir... - 11:48 AM Feature #7599: erasure-code : upgrade to jerasure-2
- suggest "sse detection at runtime":https://bitbucket.org/jimplank/gf-complete/issue/4/sse-capabilities-should-be-chec...
- 12:22 AM Feature #7599 (In Progress): erasure-code : upgrade to jerasure-2
- requested release branches https://bitbucket.org/jimplank/jerasure/issue/3/v2-branch and https://bitbucket.org/jimpla...
- 09:59 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- I shouldn't have said anything -- minutes later the problem is now happening again.
- 09:47 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- Stopping the clients that were attempting to mount cephfs (by restarting them) appeared to let the mds start with no ...
- 08:48 AM CephFS Bug #7613 (Can't reproduce): mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- ...
- 09:45 AM Bug #7611: All mon nodes crash when running "ceph tell osd.X" and using the "version" command
- Easily reproduceable on 0.72.2; unable to reproduce on current master. Will further look into it.
- 09:41 AM Bug #7611: All mon nodes crash when running "ceph tell osd.X" and using the "version" command
- i think the reason why we never saw this is that nobody uses the interactive command.
joao, this sounds trivial to... - 07:48 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
- I'm on 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
I did on one of the mon nodes:
$ ceph tell osd.151
... - 09:26 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- Still problem on 3/5/14 run http://pulpito.front.sepia.ceph.com/teuthology-2014-03-04_23:00:33-rgw-firefly-distro-bas...
- 07:55 AM Revision 60a329f8 (ceph): Merge pull request #1338 from dachary/wip-mailmap
- mailmap updates
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com> - 07:47 AM Revision d4950a1d (ceph): mailmap: Danny Al-Gaaf affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision a85d0ef6 (ceph): mailmap: Steve Stock affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision fdb644a2 (ceph): mailmap: Ron Allred affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision 0eac1ba0 (ceph): mailmap: Bjørnar Ness affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision 076bec85 (ceph): mailmap: Christopher O'Connell affiliation
- Reviewed-by: Christopher O'Connell <jwriteclub@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:13 AM rbd Bug #7327 (Resolved): Assertion failure in rbd_object_request_destroy()
- I see. In any case, it shouldn't crash anymore. If it pops up again,
you'll see something like... - 05:06 AM Support #7609 (Resolved): http://tracker.ceph.com/account/register returns 500 Internal error
- I tried to create an account on http://tracker.ceph.com/account/register, but it returned "Internal error" several ti...
- 03:36 AM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
- __queue_cap_release has code which limits the size of cap release message
- 03:29 AM Revision 4cb1cbfb (ceph): ReplicatedPG::fill_in_copy_get: fix omap loop conditions
- cursor.omap_offet indicates the most recently recovered key, we continue
filling in at the smallest key k | k > curso... - 03:29 AM Revision 11393ab7 (ceph): ReplicatedPG::fill_in_copy_get: remove extraneous if statement
- This should leave the behavior unchanged.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 03:23 AM Revision 8fdfece9 (ceph): ReplicatedPG::fill_in_copy_get: fix early return bug
- This is not a leak: we are in an else block where cb must
be NULL. The fix as introduced did not include braces on
t... - 03:22 AM Revision 4bf28df2 (ceph): Merge remote-tracking branch 'upstream/wip-7447' into firefly
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 02:55 AM Revision 364fed81 (ceph): packaging: use wildcard for test files in Debian
- we can also use test_* instead of listing all test_xx files while
building debian package
Reviewed-by: Ken Dreyer <... - 02:02 AM Revision 225eb4a7 (ceph): Merge pull request #1370 from ceph/wip-7293
- Make symlink of librbd to qemu's folder so it can detect it.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 12:15 AM Revision 65f33549 (ceph): Make symlink of librbd to qemu's folder so it can detect it.
- Per issue #7293.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> - 12:09 AM Revision fb510c29 (ceph): Merge pull request #12 from ceph/wip-final-workload-wusui
- Fix dumpling-x upgrade suite.
Also available in: Atom