Activity
From 08/04/2014 to 09/02/2014
09/02/2014
- 10:30 PM Revision ca6eb612 (ceph): client: vxattr support for rstat
- copy the kernel client code (which uses table to present vxattrs)
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 09:09 PM Revision 299f28b0 (ceph): Merge pull request #2363 from ceph/wip-9285
- osd/ReplicatedPG: do not evict blocked objects
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:02 PM Revision 8657022c (ceph): Merge pull request #2343 from ceph/wip-9151
- Wip 9151 + 9152
Reviewed-by: Sage Weil <sage@redhat.com> - 08:43 PM Revision 79989de8 (ceph): Merge pull request #112 from ceph/wip-8231-forreview
- Wip 8231 forreview
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:47 PM Revision d0e0eb47 (ceph): Merge pull request #2362 from ceph/wip-9294
- osd/ReplicatedPG: avoid dereferencing iterator at end()
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:24 PM rbd Bug #6494: High memory consumption of qemu/librbd with enabled cache
- We are experiencing the same issue, even if we are using quite different software versions.
We have our setup runn... - 06:40 PM Revision ed62ae58 (ceph): Merge pull request #2322 from ceph/wip-doc-authentication
- doc: Refactored authentication docs.
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 06:38 PM Revision c2443b95 (ceph): doc: Provided additional detail on daemon-specific caps syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:37 PM Revision 8569b93c (ceph): doc: Updated Keyring settings from comments and ceph-deploy defaults.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:26 PM Revision 275df440 (ceph): Fix FTBFS on alpha due to incorrect check on BLKGETSIZE
- Ceph FTBFS on Alpha with:
~~~~
libtool: compile: g++ -DHAVE_CONFIG_H -I. -D__CEPH__ -D_FILE_OFFSET_BITS=64 -D_REENT... - 05:18 PM Revision 9c98d555 (ceph): Merge pull request #2372 from dachary/wip-disk-thread-ioprio
- documentation: document disk thread ioprio options
Reviewed-by: Volker Voigt <volker.voigt@1und1.de> - 05:08 PM Revision b6a97d83 (ceph): documentation: disk thread ioprio options
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 04:47 PM devops Bug #9267: "Gem::DependencyError" in upgrade:dumpling-dumpling-distro-basic-vps
- Several same errors in http://pulpito.front.sepia.ceph.com/teuthology-2014-09-02_16:17:54-rgw:multifs-dumpling-testin...
- 04:07 PM Bug #9326 (Resolved): osd crash in upgrade:dumpling-firefly-x-master-distro-basic-vps suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-09-02_10:22:50-upgrade:dumpling-firefly-x-master-dist...
- 04:03 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- 2014-08-31 01:24:18.568610 7f45febb1700 10 osd.2 pg_epoch: 192 pg[2.1( v 192'1575 (0'0,192'1575] local-les=105 n=49 e...
- 03:46 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- nvm, reopening
- 02:06 PM Bug #9054 (Resolved): ceph_test_rados: FAILED assert(!old_value.deleted())
- Opening new bug for that one.
- 02:05 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- 2014-08-31T01:36:27.057 INFO:tasks.rados.rados.0.plana80.stdout:update_object_version oid 348 v 3674 (ObjNum 1096 sna...
- 03:46 PM Bug #9324 (Rejected): FAILED assert(!old_value.deleted()), expect (ObjNum 34580816 snap 0 seq_num...
- 02:07 PM Bug #9324 (Rejected): FAILED assert(!old_value.deleted()), expect (ObjNum 34580816 snap 0 seq_num...
- ubuntu@teuthology:/a/sage-2014-08-30_20:39:25-rados-wip-sage-testing-testing-basic-multi/462661
probably a bug or ... - 03:24 PM CephFS Documentation #8258 (Resolved): 0.80~rc1: outdated MDS man page
Oops, forgot to close this at the time....- 03:23 PM CephFS Bug #9252 (Resolved): Worker thread to advance MDS in absence of messages
- ...
- 03:23 PM CephFS Bug #9152 (Resolved): mds: beacon needs to not take mds_lock
- ...
- 03:23 PM CephFS Bug #9151 (Resolved): mds should log/error/warn when segments are NOT getting trimmed
- ...
- 03:19 PM Revision 1b9e670e (ceph): systemd support in ceph-disk activate
- previous code just fails for systemd with an error
Signed-off-by: Owen Synge <osynge@suse.com> - 02:38 PM Bug #9285: osd: promoted object can get evicted before promotion completes
- This appears to be independent of promotion. Is the problem not simply that we don't guarantee that the object will ...
- 12:01 AM Bug #9285: osd: promoted object can get evicted before promotion completes
- Tested Sage's the pull request, checking the object is blocked or not doesn't work. Actually this check is already do...
- 02:05 PM devops Tasks #8366 (In Progress): Update ceph.com/docs to default to the latest major release (0.80)
- 01:58 PM devops Feature #7925: Feature: create new download.ceph.com site
- 01:55 PM Feature #9323 (Resolved): osdmonitor: allow users to set/clear cluster state flags (CEPH_OSDMAP_F...
- While investigating a cluster that was failing to remove the OSDMap's full flag, we wished we had a command that woul...
- 01:54 PM Bug #9321: pgmap updates from OSDMap can be delayed indefinitely
- I should also note that I *suspect* this condition might have been exacerbated by our full map handling. We probably ...
- 01:44 PM Bug #9321 (Resolved): pgmap updates from OSDMap can be delayed indefinitely
- We saw a customer cluster in which a full OSD had been removed from the OSDMap, but after almost two hours that chang...
- 01:48 PM Bug #9322 (Resolved): OSDMap updates from pgmap can be delayed indefinitely
- Like #9321, but in the other direction: we try to update the osdmap from the pgmap in OSDMonitor::tick(), but if pgmo...
- 01:47 PM rgw Feature #9013 (Fix Under Review): rgw: set civetweb as a default frontend
- 01:40 PM Feature #9320 (Rejected): "ceph osd dump" does not flag full OSDs
- Right now, when there are full OSDs in the cluster, the only way to find them is by running "ceph health detail". The...
- 01:15 PM Revision 6ec08e06 (ceph): client/Client.cc: fix null pointer checks for 'in'
- Cleanup checks for null pointer dereference of 'in' use a
wider code block the cover 'in'.
Signed-off-by: Danny Al-G... - 01:06 PM Revision f5e7a4be (ceph): mds: use HeartbeatMap to control beacons
- ...so that if something hogs mds_lock without
pinging the heartbeat map, we will stop sending
beacons to the mon and ... - 01:06 PM Revision 12ab937a (ceph): messages: add health fields to MMDSBeacon
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:06 PM Revision 0fc8a0da (ceph): mds: populate health metrics in beacon
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:06 PM Revision 1058a9e1 (ceph): mon: handle beacon health metrics in MDSMonitor
- Fixes: #9151
Signed-off-by: John Spray <john.spray@redhat.com> - 01:06 PM Revision 9ee80152 (ceph): mds: add thread to progress queues outside dispatch
- This speeds up processing of queued waiters.
Fixes: #9252
Signed-off-by: John Spray <john.spray@redhat.com> - 01:06 PM Revision c8d23880 (ceph): mon: add MDS metric metadata to health detail
- This is a bit wonky because the mon health structure expects
a string, and we have a key-val structure, but it's bett... - 01:06 PM Revision e69f3214 (ceph): include/CompatSet: make merge const()
- With usual shenanigans to deal with [] on map
not being const-safe.
Signed-off-by: John Spray <john.spray@redhat.com> - 01:06 PM Revision 17d547ed (ceph): mds: extract beacon state from MDS lock
- For clarity, give it its own class for the
state protected by the separate lock too.
Fixes: #9152
Signed-off-by: Jo... - 01:06 PM Revision 232757f4 (ceph): mds: promote Beacon to be a Dispatcher
- This allows it to handle its own MSG_MDS_BEACON
messages from the mon, outside of mds_lock.
This is less important t... - 01:06 PM Revision 124856ab (ceph): include/CompatSet: more const-ness
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:06 PM Revision 681f4f8b (ceph): mds: const getters in MDLog
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:56 PM Revision 46c94e95 (ceph): mds/CInode.h: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:56 PM Revision a5468abe (ceph): ceph_objectstore_tool.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:18 PM Revision 4d9927e0 (ceph): mds: cap and lease count in `session ls` asok
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:18 PM Revision ea2a8d04 (ceph): mds: Fix Session::get_request_count
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:15 PM Revision 15df8ac4 (ceph): rbd_replay/Replayer.cc: pass const string parameter by reference
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:03 PM Revision 9d926f1e (ceph): ReplicatedPG.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:03 PM Revision dae05938 (ceph): IndexManager.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:57 AM Revision 40189a28 (ceph): PGMonitor.cc: prefer empty() over size() for emptiness check
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:53 AM Revision 99fc33f9 (ceph): ErasureCodeLrc.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:49 AM Revision 2dcfe0fe (ceph): ErasureCodePlugin.cc: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:42 AM Revision a754ce51 (ceph): ErasureCodeLrc.cc: fix -Wmaybe-uninitialized compiler warning
- Init 'n' with 0 to prevent uninitialized integer.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 11:35 AM Feature #9313: Add flag to ceph-deploy to start services manually (skip Upstart)
- Forgot to include - this is the error that ceph-deploy generates while it's waiting for the monitors to come up:
a... - 11:25 AM Feature #9313 (Closed): Add flag to ceph-deploy to start services manually (skip Upstart)
- I am trying to deploy Ceph entirely within Docker containers. I have no Upstart daemon running in my container - as i...
- 11:22 AM Revision 38e6c64a (ceph): test_rgw_admin_log.cc: remove unused variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:22 AM Revision 0d27bcc5 (ceph): osd/ReplicatedPG.cc: fix resource leak
- CID 1204294 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable filter going out of scope leaks the
s... - 11:22 AM Revision 16cbabab (ceph): osd/PGLog.h: prefer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:22 AM Revision 473b33b0 (ceph): osdc/ObjectCacher.cc: refer ++operator for non-primitive iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:06 AM CephFS Feature #9312 (Resolved): kclient: support signatures in kernel code
- While refactoring authentication docs, Sage pointed out in review comments that "somewhere here we should note that t...
- 10:29 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- "remove_snap_mapped_object":https://github.com/ceph/ceph/blob/master/src/osd/ReplicatedPG.cc#L199 removes the object ...
- 08:03 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- tentative solution to a problem related to what happens although it does not address the main issue https://github.co...
- 07:43 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- An idea, which is not a fix but may help. When the following sequence is done:...
- 09:56 AM Cleanup #2458 (Resolved): filestore: backend abstraction
- I believe this has been addressed by last year works on implementing alternatives to the FileStore
- 09:48 AM Cleanup #1960 (Resolved): You should be able to print daemon options without specifying a config ...
- Not sure when or how but I tested ceph-osd --help when no ceph.conf is available and the help shows as expected.
- 09:43 AM rbd Feature #9311 (Resolved): rbd: parallelize import/export
- Add AIO support when importing/exporting images to/from RBD.
- 09:41 AM Documentation #1819 (Resolved): document librados python api
- https://github.com/ceph/ceph/commit/8cb3dad5488874b2af3234ac3bf2c627ba19a5ae
- 09:32 AM RADOS Feature #628: crushtool: better error messages when parsing a crushmap.txt
- The crush compiler indeed has minimal error handling...
- 09:27 AM Feature #610 (Resolved): gui: make PG view prettier
- With http://tracker.ceph.com/projects/calamari :-)
- 09:24 AM RADOS Feature #1474: scrub: repair intra-node inconsistencies
- I believe this is no longer a problem. Is it ?
- 09:04 AM rgw Documentation #9237 (Closed): rgw: Feature comparison document
- 08:53 AM Cleanup #871 (Resolved): replace gnu_cxx::hash_map with tr1::unordered_set
- gnu_cxx::hash_map is not found in today's master
- 08:40 AM RADOS Fix #6109: pg <pgid> mark_unfound_lost fails if a completely-gone OSD still in map
- Is there a known workaround ?
- 06:29 AM CephFS Feature #9284 (In Progress): mds: warn when clients are not responding to cache pressure
- 02:54 AM CephFS Bug #8648 (Fix Under Review): Standby MDS leaks memory over time
- https://github.com/ceph/ceph/pull/2375
- 12:52 AM Revision 8f368c51 (ceph): mailmap: Ashish Chandra affiliation
- Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
- 12:34 AM Revision 5fd50c99 (ceph): mailmap: Boris Ranto affiliation
- Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
09/01/2014
- 11:54 PM rbd Bug #9078: Removing an RBD is very slow whenever there is write's in other RBD which also belongs...
- Either rbd remove will get any impact on different orders(12-24) or it will be same behaviour ?, because for lesser o...
- 11:20 PM CephFS Feature #9026 (Fix Under Review): client: vxattr support for rctime, rsize, etc.
- https://github.com/ceph/ceph/pull/2373
- 05:18 PM CephFS Bug #9216: mds may regard active clients as stale due to slow pg recovery
- maybe it's the same as #9212
- 04:17 PM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- When scrub "scans objects":https://github.com/ceph/ceph/blob/3215c520e1306f50d0094b5646636c02456c9df4/src/osd/PGBacke...
- 03:38 PM Revision bbf569de (ceph): tasks: fix mount race in mds_client_recovery
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:25 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Ilya Dryomov wrote:
> Well, the issue didn't get resolved, you simply found a kernel it doesn't show up on. I'm sti... - 09:24 AM Revision 3215c520 (ceph): Merge pull request #2366 from dachary/wip-mailmap
- mailmap: add .peoplemap
Reviewed-by: M Ranga Swami Reddy <swamireddy@gmail.com> - 08:14 AM Revision 5554c7e7 (ceph): Merge pull request #2370 from ceph/wip-9309
- lockdep: increase max locks (1000 -> 2000)
Reviewed-by: Loic Dachary <loic-201408@dachary.org> - 05:43 AM Bug #9224 (Need More Info): osd: segv in dlopen
- grep in the ceph-osd logs from runs august, 23,24,25 found no match for _dl_map_object_deps . I'm unable to find a le...
- 04:05 AM CephFS Bug #9297 (Duplicate): mds: null deref in _session_logged
- Dupe of #9173: the fix hadn't landed at the point these tests were run.
- 12:53 AM rgw Bug #9310 (Duplicate): Rados gateway swift subuser creation problem on FIREFLY
I have two problems both related to Rados gateway swift user creation on FIREFLY
Ceph version 0.80.5
Centos ...- 12:46 AM Revision a5b4c583 (ceph): lockdep: increase max locks (1000 -> 2000)
- We hit the 1000 lock limit on
ubuntu@teuthology:/a/teuthology-2014-08-31_02:30:01-rados-next-testing-basic-multi/46... - 12:32 AM Revision 41914ec3 (ceph): Merge pull request #2369 from dachary/wip-mark-unfound-lost
- documentation: add the mark_unfound_lost delete option
Reviewed-by: Sage Weil <sage@redhat.com> - 12:31 AM Revision 89ca4f6f (ceph): Merge pull request #2368 from dachary/wip-pg-const
- osd: MissingLoc::get_all_missing is const
Reviewed-by: Sage Weil <sage@redhat.com> - 12:30 AM Revision bf0a76ff (ceph): Merge pull request #2367 from dachary/wip-early-fail
- tests: qa/workunits/cephtool/test.sh early fail
Reviewed-by: Sage Weil <sage@redhat.com>
08/31/2014
- 10:42 PM Revision 9fac0723 (ceph): documentation: add the mark_unfound_lost delete option
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 09:01 PM Revision bec30324 (ceph): osd: MissingLoc::get_all_missing is const
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 08:59 PM Revision e13ddc7d (ceph): tests: qa/workunits/cephtool/test.sh early fail
- Add tests to fail as soon as an unexpected condition is met in
test_mon_osd. Otherwise the actual error will be more ... - 08:08 PM Revision fc499aa5 (ceph): mailmap: add .peoplemap
- In .mailmap, an individual may be represented by multiple mails which
may reflect an organization affiliation change ... - 07:54 PM CephFS Bug #7750 (Can't reproduce): Attempting to mount a kNFS export of a sub-directory of a CephFS fil...
- can't reproduce on 3.16 kernel
- 05:54 PM Bug #9294: invalid read of size 8 in ReplicatedPG::start_flush()
- ...
- 05:49 PM Bug #8997: ceph_test_rados_watch_notify hangs
- probably same root issue: LibRadosWatchNotifyPPTests/LibRadosWatchNotifyPP.WatchNotifyTestPP/0 hangs in
ubuntu@teu... - 05:47 PM Bug #9309 (Fix Under Review): common/lockdep.cc: 127: FAILED assert(last_id < 1000)
- https://github.com/ceph/ceph/pull/2370
- 05:45 PM Bug #9309 (Resolved): common/lockdep.cc: 127: FAILED assert(last_id < 1000)
- ubuntu@teuthology:/a/teuthology-2014-08-31_02:30:01-rados-next-testing-basic-multi/463411...
- 05:41 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- ubuntu@teuthology:/a/teuthology-2014-08-31_02:30:01-rados-next-testing-basic-multi/463412 (but didn't have debug enab...
- 05:39 PM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- ubuntu@teuthology:/a/teuthology-2014-08-31_02:30:01-rados-next-testing-basic-multi/463346
- 05:25 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- Sage Weil wrote:
> ubuntu@teuthology:/a/sage-2014-08-30_20:39:25-rados-wip-sage-testing-testing-basic-multi/462661
... - 05:16 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- ubuntu@teuthology:/a/sage-2014-08-30_20:39:25-rados-wip-sage-testing-testing-basic-multi/462661
same symptom, at l... - 05:20 PM Bug #8885: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- on master this time: description: rados/thrash/{clusters/fixed-2.yaml fs/btrfs.yaml msgr-failures/few.yaml
thrashe... - 05:03 PM Bug #9308 (Can't reproduce): EBUSY on umount of osd volume after ceph-osd shutdown
- ...
- 01:00 PM rgw Bug #9307 (Resolved): "s3.test_multipart_upload_multiple_sizes ... ERROR" in upgrade:dumpling-fir...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-31_08:49:23-upgrade:dumpling-firefly-x-master-dist...
- 12:48 PM Revision 8a2a19e9 (ceph): Merge pull request #117 from dachary/wip-erasure-code-workloads
- erasure-code: do not schedule isa workloads just yet
- 11:30 AM Revision 1052f5cc (ceph): add osds to firefly-x upgrade suite
- so that the lrc plugin has enough to work with
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 10:52 AM Revision fb79062f (ceph): Merge pull request #2358 from dachary/wip-lrc
- rename LRC to lrc + preload
Reviewed-by: Sage Weil <sage@redhat.com> - 10:51 AM Revision 177202e4 (ceph): erasure-code: lowercase LRC plugin name
- So that all erasure code plugins are lowercase.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 09:13 AM Feature #9306 (New): erasure-code: optimize IsReadablePredicate to check data chunks instead of j...
- there is no need to check rec_pred if all data chunks are available, because all codes are systematic. Not sure how m...
- 09:09 AM Feature #9305 (New): erasure-code: cache minimum-to-decode results
- with a LRU, in ErasureCode, so that it does not matter if the logic is complex. It is worth it in general and even mo...
- 08:47 AM Revision a624d445 (ceph): erasure-code: do not schedule isa workloads just yet
- they should be selectively activated, depending the isa plugin availability
Signed-off-by: Loic Dachary <loic-201408... - 08:41 AM Bug #9304 (Resolved): pool create with invalid crush rule name succeeds
- ...
- 05:43 AM Feature #7291 (In Progress): EC: add mechanism for mon to detect and whitelist EC plugins which a...
- Does "this draft patch":https://github.com/ceph/ceph/pull/2364 goes in the right direction ? Or should the fix use a ...
- 04:21 AM Feature #7291: EC: add mechanism for mon to detect and whitelist EC plugins which are globally av...
- It happens on partial upgrades, when trying to create a pool that uses the lrc plugin. The OSD that have not been upd...
- 05:39 AM Revision 4c9fdbf6 (ceph): common/LogEntry: fix warning on x86_64
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:29 AM Bug #9303 (Rejected): file deps.deb.txt doesn't exist in github repository
- The readme.md in the github repository https://github.com/ceph/ceph mentions `deps.deb.txt` which doesn't exist in v0...
- 04:56 AM Revision a24c8bac (ceph): common/LogEntry: fix warning on i386
- common/LogEntry.cc: In member function 'void LogEntry::log_to_syslog(std::string, std::string)':
warning: common/LogE... - 04:38 AM Feature #7266 (Resolved): erasure code : implement locality (was pyramid)
- 04:36 AM Bug #9273 (Resolved): mon doesn't preload ec plugins; triggers crash in upgrade tests
- 04:23 AM Feature #9167 (Resolved): erasure-code: check plugin version when loading it
- 01:52 AM Bug #9224: osd: segv in dlopen
- grep running
- 01:03 AM Revision a63cf0bd (ceph): lib: updating comments
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
08/30/2014
- 11:20 PM Revision 9ade22dd (ceph): ceph_objectstore_tool: Add task for testing of tool of the same name
- Based on ceph/src/test/ceph_objectstore_tool.py but only does
replicated pool testing and doesn't test argument valid... - 11:20 PM Revision 0cdf6e81 (ceph): ceph_manager: Implement export/import when thrasher kills an osd
- Use list-pgs to avoid races by seeing actual pgs present
Signed-off-by: David Zafman <david.zafman@inktank.com> - 11:20 PM Revision 05eee9fa (ceph): ceph_manager: Add test code to use export/import to move a pg
- Check for more than 1 osd down and randomize on chance_move_pg (100%)
For now only export from older down osd to newl... - 10:36 PM Feature #9302 (Resolved): mon: 'ceph osd pool ls' command
- i do a lot of
ceph osd dump | grep ^pool
which is stupid. plaintext can list just names; formatted can list p... - 10:19 PM Bug #9301 (Resolved): paxos: off by one w/ versions in forming quorum
- we are stuck in an election loop and seeing...
- 10:04 PM Bug #9300 (Can't reproduce): os/DBObjectMap.cc: 399: FAILED assert(!valid || cur_iter->valid())
- ...
- 09:18 PM Revision 66d29a9c (ceph): thrashers/mapgap.yaml: ignore osd_map_cache_size warning
- Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 77670aeadf9f2f43db5858ad096016353ce578bb) - 05:36 PM Revision f912b97b (ceph): test: make ping monitor robust; clean-ups
- Tries to guess a monitor id to ping. Currently tests "a" which is used
with vstart.sh, or tests all hostnames that ar... - 05:34 PM Revision 79f2f120 (ceph): test: add some test cleanup
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:33 PM Revision 222a935b (ceph): test: add data to cluster before stat
- For an empty cluster we need to write data into the cluster so cluster
stats come back as non-zero. This also adds a ... - 05:30 PM Revision b8609f82 (ceph): lib: fix parse commnad line arguments
- Adds a placeholder string at argv[0] position because Ceph will start
parsing the provided arguments at position argv... - 05:29 PM Revision 728afd56 (ceph): lib: update comments
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:28 PM Revision fae47341 (ceph): lib: add make/delete pool interfaces
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:45 PM Revision fb7befb3 (ceph): rgw: increase the number of OSDs for erasure coded pools
- So that there never is less than 4 osd which is the minimum when trying
erasure coded workloads that only work with 4... - 04:45 PM Revision 9825d859 (ceph): Merge pull request #115 from dachary/wip-erasure-code-workloads
- erasure-code: do not schedule lrc workloads just yet
- 04:31 PM Revision 378113cc (ceph): erasure-code: do not schedule lrc workloads just yet
- testing after renaming is in progress
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 04:26 PM Feature #8276 (Resolved): ceph-filestore-dump import-rados -p <pool> <archive>
- 23ec93a86140c4b271b45d87c62682288079cbba
- 04:06 PM Revision 4167ed2a (ceph): Merge pull request #114 from dachary/wip-erasure-code-workloads
- DNM: erasure-code: add various erasure-code workloads
- 09:42 AM CephFS Feature #9299 (New): mds: improve cache lru
- it appears to be very easy for a single task/client to push everything out of the cache. we have a stratified lru, b...
- 09:31 AM CephFS Bug #9297 (Duplicate): mds: null deref in _session_logged
- ubuntu@teuthology:/var/lib/teuthworker/archive/john-2014-08-29_03:49:04-fs-wip-jcsp-test-testing-basic-multi/459392<p...
- 09:18 AM Revision a019c84f (ceph): erasure-code: add to suites/upgrade/*-x final workloads
- And replace the ec-readwrite.yaml custom workloads with links to the
workloads found in the erasure-code directory.
... - 09:17 AM Revision 5d2a33d6 (ceph): erasure-code: add various erasure-code workloads
- The erasure-code directory is populated with files describing rados
workloads suitable to test the default erasure co... - 02:41 AM Revision acfe62e0 (ceph): Revert "os/FileJournal: For journal-aio-mode, don't use aio when closin...
- This reverts commit e870fd09ce846e5642db268c33bbe8e2e17ffef2.
The aio completion thread will now wait for the final ... - 02:40 AM Revision c776a898 (ceph): os/FileJournal: stop aio completion thread *after* writer thread
- The writer thread may submit a new aio to update the header in its
final moments before shutting down. Do not stop t... - 02:27 AM Revision fa45ed81 (ceph): osd/ReplicatedPG: do not evict blocked objects
- If the object is blocked, that means we are either still promoting it, or
we are in the process of doing a blocking f... - 02:16 AM Revision ded1cf4a (ceph): osd/ReplicatedPG: avoid dereferencing iterator at end()
- The preceding loop could terminate with p == snapset.clones.end(), which
we assign to dnewest. We can't dereference ... - 12:46 AM Revision bb26c66b (ceph): Merge pull request #2360 from ceph/wip-9281
- tools: use cout instead of cerr in journal tool
Reviewed-by: Sage Weil <sage@redhat.com> - 12:31 AM Revision fbbdc31a (ceph): Merge pull request #2356 from dachary/wip-9273-mon-preload-erasure-code...
- erasure-code: preload the default plugins in the mon (firefly)
Reviewed-by: Sage Weil <sage@redhat.com> - 12:12 AM Revision d20432ec (ceph): erasure-code: preload LRC plugin
- Add LRC to the list of erasure code plugins preloaded by default.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 12:10 AM Revision 67c552be (ceph): Merge pull request #2359 from dachary/wip-fix-lrc
- fix lrc tests and prototype
Reviewed-by: Sage Weil <sage@redhat.com>
08/29/2014
- 11:56 PM Revision b97f807a (ceph): Merge pull request #2338 from ceph/wip-reweight
- mon/OSDMonitor: make reweight_by_* output less misleading
- 11:52 PM Revision 9edd6551 (ceph): osd/osd_types: add num_bytes_hit_set_archive to stats
- The tiering agent's life is easier/better if it knows how many bytes these
objects consume (instead of making a conse... - 11:52 PM Revision 3409c386 (ceph): osd/ReplicatedPG: account for hit_set_archive bytes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:52 PM Revision 6ce36b0d (ceph): osd/ReplicatedPG: scrub and repair hit_set_archive bytes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:52 PM Revision 3fc6a73b (ceph): osd/ReplicatedPG: calculate num_user_bytes
- This is the bytes stored by the user, excluding hit_sets.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:52 PM Revision 982c9dda (ceph): osd/ReplicatedPG: adjust avg_size calculation in agent_choose_mode
- Signed-off-by: Zhiqiang Wang <wonzhq@hotmail.com>
- 11:44 PM Revision 93beff19 (ceph): erasure-code: use s/get_str_map/get_json_str_map/
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 11:43 PM Revision 6388934b (ceph): erasure-code: mkfs.sh needs to know the plugin directory
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 11:11 PM Revision 21e25e77 (ceph): Merge remote-tracking branch 'gh/wip-7988'
- Conflicts:
src/mds/RecoveryQueue.cc
Reviewed-by: Sage Weil <sage@redhat.com> - 11:08 PM Revision 46d9611a (ceph): osd: OSDMap: ordered blacklist on non-classic encode function
- Fixes: #9211
Backport: firefly
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage... - 11:08 PM Revision 994a9e35 (ceph): osd/OSDMap: encode blacklist in deterministic order
- When we use an unordered_map the encoding order is non-deterministic,
which is problematic for OSDMap. Construct an ... - 11:06 PM Revision 81102044 (ceph): osd: OSDMap: ordered blacklist on non-classic encode function
- Fixes: #9211
Backport: firefly
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage... - 10:56 PM Revision 31036987 (ceph): lib: add accessor for cluster fsid/instance_id
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 09:08 PM Revision 94fe3bca (ceph): Merge pull request #1921 from dachary/wip-7238-lrc-plugin
- erasure-code: locally repairable code plugin
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:04 PM Revision 1e69ff2f (ceph): PG::init: clear rollback info for backfill as well
- Otherwise, we won't remove the old rollback objects from a resurrected pg. In
rare cases, this can cause us to get a... - 07:29 PM Bug #9285 (Fix Under Review): osd: promoted object can get evicted before promotion completes
- https://github.com/ceph/ceph/pull/2363
- 07:14 AM Bug #9285 (Resolved): osd: promoted object can get evicted before promotion completes
- ...
- 07:17 PM Bug #9294 (Fix Under Review): invalid read of size 8 in ReplicatedPG::start_flush()
- https://github.com/ceph/ceph/pull/2362
- 07:08 PM Bug #9294: invalid read of size 8 in ReplicatedPG::start_flush()
- This is somewhere in start_flush(). A quick re-read of the code for places where we dereference a snapid_t iterator ...
- 05:36 PM Bug #9294 (Rejected): invalid read of size 8 in ReplicatedPG::start_flush()
- ...
- 06:18 PM Bug #9295 (Fix Under Review): osd/OSD.cc: 5501: FAILED assert(session) in ms_fast_dispatch
- 06:06 PM Bug #9295: osd/OSD.cc: 5501: FAILED assert(session) in ms_fast_dispatch
- we receive a message......
- 05:39 PM Bug #9295 (Resolved): osd/OSD.cc: 5501: FAILED assert(session) in ms_fast_dispatch
- ...
- 05:58 PM Bug #9224: osd: segv in dlopen
- ...
- 05:43 PM Bug #9281 (Resolved): cephfs-journal-tool stderr output gets mixed up with log output
- 05:31 PM Bug #9281 (Fix Under Review): cephfs-journal-tool stderr output gets mixed up with log output
- https://github.com/ceph/ceph/pull/2360
- 11:13 AM Bug #9281: cephfs-journal-tool stderr output gets mixed up with log output
- 06:42 AM Bug #9281 (Resolved): cephfs-journal-tool stderr output gets mixed up with log output
Causes an "Import failed to preserve event state" in automated tests with logging enabled
http://pulpito.front.sep...- 05:42 PM Bug #9296 (Duplicate): timeout during recovery, slow requests
- > reached maximum tries (1500) after waiting for 9000 seconds
remote/plana62/log/ceph.log.gz:2014-08-28 23:34:... - 05:39 PM Revision 01b943b2 (ceph): erasure-code: test LRC pool, profile and crush ruleset
- Using the command line to create an LRC pool validates that the plugin
can be loaded and the ruleset created immediat... - 05:39 PM Revision 734ae88e (ceph): erasure-code: LRC plugin documentation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 05:39 PM Revision 45a61ad6 (ceph): erasure-code: ECRecPred must be true if all chunks can be recovered
- ECRecPred assumes recovering any number of chunk is possible as long as
at least K chunks are available. It builds th... - 05:38 PM Revision 4670d9e6 (ceph): erasure-code: relax profile parameter syntax
- Do not restrict the character set of the key=value pairs of osd
erasure-code-profile set to allow for things like:
... - 05:38 PM Revision b517ca48 (ceph): erasure-code: override the default only if the plugin match
- When setting a new erasure coded profile, the key/value of the default
profile are re-used so that ruleset-failure-do... - 05:38 PM Revision c2ca0117 (ceph): erasure-code: delegate chunk remapping to the plugin
- Remapping the chunks after they have been encoded by the plugin is fine
if remapping is transparent to the plugin. Ho... - 05:38 PM Revision b0fd4815 (ceph): erasure-code: locally repairable code plugin
- Recursively apply erasure code techniques so that recovering from the
loss of some chunks only require a subset of th... - 05:38 PM Revision c2226017 (ceph): erasure-code: high level LRC configuration
- Add a configuration mode to the LRC plugin, suitable for most use cases
and simpler to explain and understand. It use... - 05:38 PM Revision e2e07d95 (ceph): erasure-code: add ErasureCodeInterface::get_coding_chunk_count
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 05:37 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- ...
- 05:34 PM Revision 9fc26840 (ceph): tools: use cout instead of cerr in journal tool
- Aside from being a bit odd to begin with, using stderr
was causing tests to fail because the output was polluted
by l... - 05:34 PM Bug #9241: osdc/Objecter.cc: 1320: FAILED assert(s->get_nref() == 1)
- ubuntu@teuthology:/a/sage-2014-08-28_16:08:59-rados-master-testing-basic-multi/458975...
- 05:32 PM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- sage-2014-08-28_16:08:59-rados-master-testing-basic-multi/458658
rados/thrash/{clusters/fixed-2.yaml fs/btrfs.yaml m... - 05:26 PM Revision 895bddc5 (ceph): erasure-code: preload the default plugins in the mon
- The commit 164f1a1959a863848319585fa752250c7b261381 preloads the
jerasure plugin in the OSD. They must also be preloa... - 04:54 PM Feature #8231 (Resolved): ceph filestore dump improvements
- 04:52 PM Bug #9253 (Duplicate): ECBackend::continue_recovery_op assert when not enough shards
- Duplicate of #9263
- 04:41 PM rbd Bug #9210 (Resolved): osdc/ObjectCacher.cc: 529: FAILED assert(i->empty()) on fencing test shutdown
- 6f3bb55a3d52403c1910f576ed835aa73013ca50
- 04:40 PM Revision 4ff181b2 (ceph): lib: add and update comments
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:21 PM Revision 130cb56e (ceph): lib: more conf_* wrappers and test clean-ups
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:19 PM Revision 8cf21ec4 (ceph): Merge pull request #2258 from ceph/wip-mds-recover
- mds: make max file recovers tunable
Reviewed-by: Yan, Zheng <ukernel@gmail.com>
Reviewed-by: John Spray <john.spray@... - 04:09 PM Feature #7988 (Resolved): Logs: Log every administrative action taken by a user
- 04:07 PM Bug #9211 (Resolved): osdmap blacklist encoding order is nondeterministic
- commit:4672e50922b75d642056020b9745a3a5844424d3 and commit:81102044f417bd99ca570d9234b1df5195e9a8c9
backported to ... - 12:20 PM Bug #9211: osdmap blacklist encoding order is nondeterministic
- https://github.com/ceph/ceph/tree/wip-9211
- 03:32 PM Revision 9a86858d (ceph): Merge pull request #2353 from wonzhq/compile-warn
- Test: fixing a compile warning in ceph_objectstore_tool.cc
Reviewed-by: Sage Weil <sage@redhat.com> - 03:29 PM Revision a9941458 (ceph): mds/RecoveryQueue: do not start prioritized items synchronously
- When we prioritize an item move it into a second priority list/set, but
do not start immediately, so that we still ob... - 03:18 PM Revision 08fc1f33 (ceph): Merge pull request #2352 from wonzhq/local-mtime
- Cache tiering: use local_mtime to calculate the age of objects during evicting
Reviewed-by: Sage Weil <sage@redhat.com> - 03:17 PM Revision 150542dd (ceph): Merge pull request #2354 from dachary/wip-9273-mon-preload-erasure-code
- erasure-code: preload the default plugins in the mon
Reviewed-by: Sage Weil <sage@redhat.com> - 02:11 PM Revision 6d79ed52 (ceph): Merge pull request #2355 from ceph/wip-hadoop
- Wip hadoop
Reviewed-by: Sage Weil <sage@redhat.com> - 02:09 PM Feature #7238 (Resolved): erasure code : implement LRC plugin
- 07:15 AM Feature #7238: erasure code : implement LRC plugin
- the above teuthology test ran successfully, with trashosd...
- 04:10 AM Feature #7238: erasure code : implement LRC plugin
- thrashosd passed because it had enough OSD to never be in a situation where mapping fails. When this happens, it trig...
- 01:55 PM Revision fce95c3b (ceph): Merge pull request #2340 from ceph/wip-blacklist-mds
- mds: restart on -EBLACKLISTED
Reviewed-by: Sage Weil <sage@redhat.com> - 12:29 PM Revision e0b19e30 (ceph): qa: fix+cleanup hadoop wordcount test
- The glob for the examples jar was wrong.
Fixes: #9260
Signed-off-by: John Spray <john.spray@redhat.com> - 10:57 AM Bug #9293: _collection_move_rename EEXIST
- Ah. When we reset the log after pg removal, we need to clear the old rollback entries.
- 10:50 AM Bug #9293: _collection_move_rename EEXIST
- 2014-08-28 19:33:33.440111 7f2bb8bf2700 10 filestore(/var/lib/ceph/osd/ceph-3) _collection_move_rename 1.cs0_head/979...
- 10:49 AM Bug #9293 (Resolved): _collection_move_rename EEXIST
- 2014-08-28 19:33:56.288775 7f2bb83f1700 15 filestore(/var/lib/ceph/osd/ceph-3) _collection_move_rename 1.cs0_head/979...
- 10:40 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Ilya sorry, I did a mistyping, I was trying to give some background to German about why it's important to have stable...
- 10:16 AM devops Feature #5773 (Resolved): ceph-deploy: should add more tests to ceph-deploy task
- commit 7dcacc9bd5189b7c81fc2bc39e433d1f1c630c95 has been merged.
- 10:12 AM Revision 76b8e57b (ceph): erasure-code: preload the default plugins in the mon
- The commit 9b802701f78288ba4f706c65b853415c69002d27 preloads the
supported plugins in the OSD. They must also be prel... - 10:08 AM CephFS Bug #9260 (Resolved): hadoop fs gets EINVAL
- ...
- 09:59 AM CephFS Bug #9252 (Fix Under Review): Worker thread to advance MDS in absence of messages
- 09:59 AM CephFS Bug #9151 (Fix Under Review): mds should log/error/warn when segments are NOT getting trimmed
- 09:14 AM Bug #9273 (Pending Backport): mon doesn't preload ec plugins; triggers crash in upgrade tests
- "firefly backport":https://github.com/ceph/ceph/pull/2356 being tested
- 03:10 AM Bug #9273 (Fix Under Review): mon doesn't preload ec plugins; triggers crash in upgrade tests
- "proposed fix":https://github.com/ceph/ceph/pull/2354
- 08:39 AM Revision c3e1466b (ceph): Test: fixing a compile warning in ceph_objectstore_tool.cc
- For the compiler's sake:
tools/ceph_objectstore_tool.cc:2547:15: warning: ‘r’ may be used
uninitialized in this funct... - 08:20 AM rgw Bug #9279: test_s3.test_atomic_* tests failed in rgw:multifs-dumpling-testing-basic-vps suite
- Same problems on http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-28_19:00:01-upgrade:firefly-firefly-testing-b...
- 08:15 AM Bug #9288 (Resolved): "Assertion `nlock == 0' failed" in upgrade:firefly-firefly-testing-basic-vp...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-28_19:00:01-upgrade:firefly-firefly-testing-basic-...
- 08:15 AM Documentation #6142: Ceph needs mor than 32k pids
- Greater than 20 is a safe number. Have not yet seen this issue on a host with 24 OSDs.
- 08:07 AM Documentation #6142: Ceph needs mor than 32k pids
- Adding a warning if deploying more than N OSDs into a single host sounds entirely reasonable to me and easy to add to...
- 08:06 AM Revision 1b427260 (ceph): Cache tiering: use local_mtime to calculate the age of objects during
- evicting
Commit 13b9dc70 introduces local_mtime to fix an issue when doing
flushing. Should also use this to calcula... - 07:18 AM CephFS Feature #9287 (Rejected): qa: hadoop: add big top tests to suite
- 07:18 AM CephFS Feature #9286 (Rejected): qa: hadoop: test 2.x with teuthology
- 07:02 AM CephFS Feature #9284 (Resolved): mds: warn when clients are not responding to cache pressure
- 07:00 AM CephFS Feature #9283 (New): mds: limit inodes with caps to <100% of cache
- 07:00 AM CephFS Feature #9282 (Resolved): mds: warn (and kill?) sessions to clients which aren't revoking caps
- We need better ways of dealing with clients who aren't following our instructions. The most obvious of them is to sim...
- 06:37 AM CephFS Bug #9280 (Resolved): valgrind failures in ceph-fuse
/a/john-2014-08-29_03:49:04-fs-wip-jcsp-test-testing-basic-multi
Valgrind: client (Leak_DefinitelyLost, Leak_Ind...- 03:21 AM Bug #9263 (Rejected): erasure-code: ECBackend crashes when mapping fails
- I misread the logs, the failure is on ...
- 03:13 AM Bug #9153 (Resolved): erasure-code: jerasure_matrix_dotprod segmentation fault due to package upg...
- This is addressed in http://tracker.ceph.com/issues/9273
- 03:09 AM Revision 7dcacc9b (ceph): Merge pull request #113 from ceph/ceph-deploy-dmcrypt
- Added dmcrypt option and ability to choose same or different disk for ce...
- 01:48 AM Revision f1585946 (ceph): added config_options to enable adding ceph config file entries to ceph-...
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:21 AM Revision b3dfe475 (ceph): Added dmcrypt option and ability to choose same or different disk for c...
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:07 AM Revision 335c1f74 (ceph): doc: Added rbd-replay-prep and rbd-replay manpages to block device TOC.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:45 AM Revision b9653989 (ceph): doc: Fixed broken hyperlink.
- Fixes: #9116
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 12:43 AM CephFS Bug #9123: kceph: had 130k+ inodes with write caps
- 12:43 AM CephFS Bug #9123: kceph: had 130k+ inodes with write caps
- I saw 10.214.137.25 in the mds log, 10.214.137.25 is gitbuilder-archive if IP hasn't changed. Maybe the issue and #89...
- 12:25 AM Revision 7948e13b (ceph): doc: Added sysctl max thread count discussion.
- Fixes: #6142
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 12:15 AM CephFS Bug #8962: kcephfs: client does not release revoked cap
- ...
- 12:08 AM Revision 9011e378 (ceph): Merge pull request #2351 from ceph/wip-9266
- client: fix dispatcher ordering (broken fuse)
Reviewed-by: Sage Weil <sage@redhat.com>
08/28/2014
- 11:59 PM Revision a257291a (ceph): client: fix dispatcher ordering (broken fuse)
- Objecter never saw any OSD maps because of 1e1ee480 and
the dispatchers being in the wrong order -- ignoring map
in C... - 11:37 PM Revision 038992b1 (ceph): Merge pull request #2332 from ceph/wip-8231-forreview
- Wip 8231 forreview
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:22 PM Revision f464f577 (ceph): ceph_filestore_dump.py: Replace ceph_filestore_dump.sh with better pyth...
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:22 PM Revision 77864193 (ceph): Renames and removal towards a unified ceph_objectstore_tool
- Rename ceph_filestore_dump.cc and ceph_filestore_dump.py
Remove ceph_filestore_tool.cc
Signed-off-by: David Zafman <... - 11:22 PM Revision 83fbc91e (ceph): Complete replacement of ceph_filestore_tool and ceph_filestore_dump
- with unified ceph_objectstore_tool
Move list-lost-objects and fix-lost-objects features from
ceph_filestore_tool t... - 11:22 PM Revision f01e334c (ceph): ceph_objectstore_tool, test: Add list-pgs operations and unit test case
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:22 PM Revision a2bd2aa7 (ceph): ceph_objectstore_tool: Minor improvements
- Make all non-error non-debug output to stdout
Fix a message
Signed-off-by: David Zafman <david.zafman@inktank.com> - 11:22 PM Revision 9325ec15 (ceph): ceph_objectstore_tool: Add past_intervals to export/import code
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:22 PM Revision 3694068b (ceph): ceph_objectstore_tool: Add operation "rm-past-intervals" for testing pu...
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:22 PM Revision 54dcbf24 (ceph): test: ceph_objectstore_tool unit test improvements
- Add namespaces to testing
Increase filesize so export will have multiple chunks
Put json for each object into the db ... - 11:22 PM Revision b193812b (ceph): tools/rados: Improve trigger for op_size rounding info message
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:22 PM Revision 23ec93a8 (ceph): ceph_objectstore_tool, test: Implement import-rados feature and unit te...
- Fixes: #8276
Signed-off-by: David Zafman <david.zafman@inktank.com> - 11:22 PM Revision a03f719e (ceph): ceph_objectstore_tool: Bug fixes and test improvements
- ceph_objectgstore_tool:
Fix bugs in the way collection_list_partial() was being called
which caused objects to be see... - 11:22 PM Revision ce29b768 (ceph): Fix ceph_scratchtoolpp to create and delete its own pool
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 11:21 PM Revision 970d9830 (ceph): PG: wait until we've build the missing set to discover_all_missing
- Fixes: #9179
Backport: firefly
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:21 PM Revision 7520e504 (ceph): ceph_filestore_dump: Fail import/export with a tty for stdin/stdout
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision d4a9dafe (ceph): ceph_filestore_dump: Add utility function get_fd_data()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 605caec6 (ceph): ceph_filestore_dump: Add remove object command and usage for new commands
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 844dabb7 (ceph): ceph_filestore_dump: Add --type list to output objects in a pg in json
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 00c6b067 (ceph): ceph_filestore_dump: Add list-attrs object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 48890c77 (ceph): ceph_filestore_dump: Add list-omap object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 869dd92c (ceph): ceph_filestore_dump: Add get-bytes object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 3c24d1f4 (ceph): ceph_filestore_dump: Add set-bytes object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 55d43c0e (ceph): ceph_filestore_dump: Add get-attr object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 95554e03 (ceph): ceph_filestore_dump: Add set-attr object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 465d7773 (ceph): ceph_filestore_dump: Add rm-attr object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision b50c43ce (ceph): ceph_filestore_dump: Add get-omap object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 50cd57e9 (ceph): ceph_filestore_dump: Add set-omap object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 0fc6bd27 (ceph): ceph_filestore_dump: Add rm-omap object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 30c0f311 (ceph): ceph_filestore_dump: Add get-omaphdr object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision b4d95cc8 (ceph): ceph_filestore_dump: Add set-omaphdr object command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 3e9e108b (ceph): test: ceph_filestore_dump.sh test improvements
- Add some usage error tests
Don't use the same var in second for loop
Add xattr/omap to rep pool and xattr to ec pool
... - 11:21 PM Revision 087c0f9d (ceph): ceph_filestore_dump: Use cerr now that we aren't closing stderr
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 44b261d5 (ceph): ceph_filestore_dump: Improve debug output by showing actual offset
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 3d9fde9d (ceph): os: Add optional flags to generic ObjectStore creation (SKIP_JOURNAL_RE...
- and SKIP_MOUNT_OMAP)
Only FileStore cares about these flags, so passed on during create()
Signed-off-by: David Zafm... - 11:21 PM Revision 2e9dcb25 (ceph): ceph_filestore_dump: Add --skip-journal-replay and --skip-mount-omap
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision c05f895d (ceph): common: Add missing ghobject_t::decode() for json
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:21 PM Revision 3a574cc7 (ceph): ceph_filstore_dump: Save if stdout is a tty and add routine to clean bi...
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 11:20 PM Revision f7f9b251 (ceph): common,ceph_filestore_dump: Add ability for utilities to suppress libra...
- Suppress dout output with CODE_ENVIRONMENT_UTILITY_NODOUT
ceph_filestore_dump turns on dout output if --debug specifi... - 10:30 PM Revision f807a7ee (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/osd/ReplicatedPG.cc - 09:34 PM Revision 3bc42915 (ceph): doc/install/manual-deployment: move 'done' comment up
- It's the same for upstart and sysvinit.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:27 PM Revision 9869f665 (ceph): Merge branch 'master' of git://github.com/flaf/ceph
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:24 PM Revision 1a2c8ed5 (ceph): Merge pull request #2248 from theanalyst/wip-8112
- rgw: move generic server usage after all options
- 09:08 PM Revision faf8128f (ceph): rados/singleton/all/thrash_cache_writeback_forward_none: thrash cache p...
- Enable/disable cache pool against a running workload.
Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
... - 09:08 PM rgw Bug #9279: test_s3.test_atomic_* tests failed in rgw:multifs-dumpling-testing-basic-vps suite
- Could be related to 9169 or idle_timeout (?)
- 09:06 PM rgw Bug #9279 (Duplicate): test_s3.test_atomic_* tests failed in rgw:multifs-dumpling-testing-basic-v...
- In the run teuthology-2014-08-28_18:37:07-rgw:multifs-dumpling-testing-basic-vps
the following jobs failed: ['459233... - 08:37 PM Revision 5b353882 (ceph): Merge pull request #2336 from wonzhq/release-op-ctx-lock
- osd: Remove extra call to release_op_ctx_locks in eval_repop
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:35 PM Bug #9269: ceph osd perf outputs the commit cycle latency for fs_commit_latency
- what do you mean "avg per-op latency"
- 01:25 PM Bug #9269 (Resolved): ceph osd perf outputs the commit cycle latency for fs_commit_latency
- It seems to ouptut l_os_commit_lat which is the commit cycle latency. We really want that to be the avg per-op latency.
- 08:28 PM devops Bug #9278: gitbuilder bad rpm URL in rgw:verify-dumpling-testing-basic-vps
- Correction - 15 jobs failed.
- 08:24 PM devops Bug #9278 (Resolved): gitbuilder bad rpm URL in rgw:verify-dumpling-testing-basic-vps
- 8 job failed with this problem in teuthology-2014-08-28_18:37:44-rgw:verify-dumpling-testing-basic-vps run
All job... - 08:20 PM Bug #9277 (Rejected): gitbuilder URL not found in rgw:verify-dumpling-testing-basic-vps
- 08:09 PM Revision 0747ca7f (ceph): mds: make max file recovers configurable
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:09 PM Revision 8f4ea81c (ceph): mds: change mds_max_file_recover from 5 -> 32
- These are reasonably cheap operations (stat) and we should be too worried
about queueing up a bunch of them.
Ideally... - 08:09 PM Revision bd3c8bc1 (ceph): mds/RecoveryQueue: add method to prioritize a file recovery; fix logging
- Add a prioritize() method to make file recovery start immediately for the
given inode. Note that this doesn't respec... - 08:09 PM Revision 0fcdc6bd (ceph): mds/Locker: prioritize file recovery on rd/wr/x lock
- If someone specifically touches the file lock, prioritize recovery for this
file.
Signed-off-by: Sage Weil <sage@red... - 08:09 PM Revision dc6bd3b3 (ceph): mds/Locker: if a client asks for file caps, prioritize file recovery
- This normally happens when a process opens the file. Prioritize in that
case.
Signed-off-by: Sage Weil <sage@redhat... - 07:42 PM Revision 22880117 (ceph): Merge pull request #2350 from ceph/wip-8718
- rgw: don't try to authenticate a CORS preflight request
Reviewed-by: Sage Weil <sage@redhat.com> - 07:40 PM Revision 2d9b1560 (ceph): Merge pull request #2348 from athanatos/wip-9054
- Wip 9054
Reviewed-by: Sage Weil <sage@redhat.com> - 06:55 PM Revision 53f93800 (ceph): Merge pull request #2294 from rootfs/wip-java-pom
- add pom.xml so to deploy the libcephfs to maven repository.
Reviewed-by: Noah Watkins <noahwatkins@gmail.com>
Review... - 06:52 PM Revision 92fc17b8 (ceph): Merge pull request #2341 from dachary/wip-osd-crush
- tests: reduce osd-crush.sh execution time
Reviewed-by: Sage Weil <sage@redhat.com> - 06:51 PM Revision c3a8087b (ceph): Merge pull request #2342 from ceph/wip-mds-namespace
- Wip mds namespace
Reviewed-by: Sage Weil <sage@redhat.com> - 06:49 PM Revision 8f59c4d3 (ceph): Merge pull request #2349 from athanatos/wip-9240
- Wip 9240
Reviewed-by: Sage Weil <sage@redhat.com> - 06:42 PM Revision 848fcf78 (ceph): rgw: don't try to authenticate a CORS preflight request
- Fixes: #8718
Backport: firefly
CORS preflight requests don't need to be authenticated. Treat them as
coming from ano... - 06:30 PM Revision 6495f898 (ceph): Merge pull request #2335 from ceph/wip-9218
- osd: fix osd_tp shutdown
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:25 PM devops Feature #5773 (Fix Under Review): ceph-deploy: should add more tests to ceph-deploy task
- https://github.com/ceph/ceph-qa-suite/pull/113
- 06:19 PM Revision e2815455 (ceph): Merge pull request #2347 from athanatos/wip-9205
- OSD::session_notify_pg_create: requeue at the start of the queue
Reviewed-by: Sage Weil <sage@redhat.com> - 06:19 PM Revision aa99dba9 (ceph): Merge pull request #2346 from athanatos/wip-8777
- PG: mark_log_for_rewrite on resurrection
Reviewed-by: Sage Weil <sage@redhat.com> - 06:18 PM Revision d9ffa080 (ceph): Merge pull request #2345 from athanatos/wip-9259
- PG::can_discard_op: do discard old subopreplies
Reviewed-by: Sage Weil <sage@redhat.com> - 05:59 PM Revision fc1186a2 (ceph): Merge branch 'wip-8639'
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:59 PM Revision e440fb49 (ceph): test/mon/*: prime mon with initial command before injection
- The osdmonitor_prepare_command is very fragile. Send an initial command
to the mon beforehand. This seems to preven... - 05:46 PM CephFS Bug #9266 (Resolved): ceph_test_libcephfs pool name failures
- ...
- 11:59 AM CephFS Bug #9266 (In Progress): ceph_test_libcephfs pool name failures
- 09:20 AM CephFS Bug #9266 (Resolved): ceph_test_libcephfs pool name failures
http://pulpito.front.sepia.ceph.com/teuthology-2014-08-25_23:04:01-fs-master-testing-basic-multi/451157/
Also fa...- 05:43 PM rgw Documentation #9116 (Resolved): rgw: broken link
- 05:39 PM rgw Documentation #9116 (In Progress): rgw: broken link
- 05:36 PM CephFS Bug #9276 (New): Client::get_file_extent_osds asserts in object_locator_to_pg if osd map is out o...
This would happen if files in the filesystem had layouts referring to pools that were no in the OSD map, which can ...- 05:34 PM Documentation #6142: Ceph needs mor than 32k pids
- Added commentary in Hardware section and in troubleshooting.
http://ceph.com/docs/master/start/hardware-recommend... - 04:39 PM Documentation #6142 (In Progress): Ceph needs mor than 32k pids
- 02:25 PM Documentation #6142: Ceph needs mor than 32k pids
- FWIW there might be a bug to extract out of this. Adding this just for cross-reference: http://lists.openstack.org/pi...
- 09:39 AM Documentation #6142: Ceph needs mor than 32k pids
- This is a critical change for denser hardware and more threads allocated per OSD. Can we get a message into ceph-depl...
- 05:34 PM Revision 5b0af4c8 (ceph): Merge pull request #2344 from ceph/wip-8863
- osd/PG: fix crash from second backfill reservation rejection
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:16 PM Bug #9220: objecter doesn't reconnect watch on interval change w/ same primary
- the problem is that the linger op isn't resent on an interval change where the primary is the same.
- 02:16 PM Bug #9220: objecter doesn't reconnect watch on interval change w/ same primary
- I think this is what's happening:
- op arrives, we register the watcher, fire off repops
- pg repeers, but keeps ... - 04:21 PM CephFS Bug #9264 (Duplicate): mds: occasionally log segments can't trim
- 04:20 PM CephFS Bug #9264: mds: occasionally log segments can't trim
- ...
- 04:16 PM CephFS Bug #9264: mds: occasionally log segments can't trim
- ...
- 07:00 AM CephFS Bug #9264 (Duplicate): mds: occasionally log segments can't trim
- it happened with latest lab mds restart yesterday; we have the logs (for another 6 days or so)...
- 04:20 PM Revision f4c34078 (ceph): Merge pull request #2297 from ceph/wip-9173
- Wip 9173
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:11 PM Bug #9274 (Can't reproduce): "AssertionError: failed to recover before timeout expired" in upgrad...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_15:40:02-upgrade:dumpling-x:stress-split-master...
- 04:10 PM Revision c7da3957 (ceph): Merge pull request #2299 from dachary/wip-jerasure-upgrade
- erasure-code: jerasure upgrade
Reviewed-by: Sage Weil <sage@redhat.com> - 04:05 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- Fix can be verified in this suite as well:
upgrade:dumpling-x:stress-split-master-distro-basic-vps
Latest manif... - 11:21 AM Bug #8777 (Pending Backport): osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == lo...
- 03:27 PM Bug #9179: unfound objects, recovery timeout
- Ok, discover_all_missing is called in the wrong place, we don't have unfound yet there in activate.
- 02:48 PM Bug #9179: unfound objects, recovery timeout
- For some reason, we waited a really long time to call discover_all_missing.
- 02:30 PM Bug #9179: unfound objects, recovery timeout
- 2014-08-19 13:28:43.734887 7fc31beac700 10 osd.4 pg_epoch: 69 pg[4.0( v 69'11622 lc 33'847 (33'847,69'11622] local-le...
- 03:18 PM Bug #9153 (In Progress): erasure-code: jerasure_matrix_dotprod segmentation fault due to package ...
- Preloading must also be done in the mon, for the exact same reasons as in the osd.
- 03:11 PM Bug #9273 (Resolved): mon doesn't preload ec plugins; triggers crash in upgrade tests
- In run : http://pulpito.front.sepia.ceph.com/teuthology-2014-08-28_11:18:18-upgrade:dumpling-firefly-x-master-distro-...
- 02:30 PM Bug #9240 (Pending Backport): osd_max_backfills = 1 can cause reserver deadlock for EC
- 02:27 PM Bug #9272 (Duplicate): Test failed on wait_until_healthy in upgrade:dumpling-firefly-x-master-dis...
- Logs are in:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-28_11:18:18-upgrade:dumpling-firefly-x-master-... - 02:19 PM Bug #9054 (Pending Backport): ceph_test_rados: FAILED assert(!old_value.deleted())
- 01:07 PM Revision 7a93258f (ceph): mds: remove `using namespace std` in headers
- Avoid polluting global namespace: .cc files should
do the `using` if they want it.
Signed-off-by: John Spray <john.s... - 01:04 PM Revision fc89c276 (ceph): messages: remove `using namespace std` in headers
- Avoid polluting global namespace: .cc files should
do the `using` if they want it.
Signed-off-by: John Spray <john.s... - 12:39 PM rgw Bug #8718 (Pending Backport): CORS OPTIONS request fails for presigned urls
- 11:47 AM rgw Bug #8718 (Fix Under Review): CORS OPTIONS request fails for presigned urls
- 11:59 AM CephFS Bug #9260: hadoop fs gets EINVAL
- Could be related to #9266, a recurrence of something trying to look up pool names before osdmap is loaded in client. ...
- 10:08 AM CephFS Bug #9260: hadoop fs gets EINVAL
- Duh, that last exception was just libcephfs-java not being installed.
- 09:46 AM CephFS Bug #9260: hadoop fs gets EINVAL
Hmm, apparently there's more than one way this can fail:...- 11:31 AM CephFS Bug #9178: samba: ENOTEMPTY on "rm -rf"
- It might not need to if there's a client bug somewhere. (Or some other issue?)
- 06:40 AM CephFS Bug #9178: samba: ENOTEMPTY on "rm -rf"
- The strange thing is that the MDS never reply ENOTEMPTY.
- 11:27 AM Bug #9218 (Pending Backport): FAILED assert(peering_queue.empty()) during OSD shutdown
- 11:26 AM Bug #9263: erasure-code: ECBackend crashes when mapping fails
- I suspect the problem is that we are feeding back to the plugin the set of shards it already told us it could use for...
- 06:39 AM Bug #9263 (Rejected): erasure-code: ECBackend crashes when mapping fails
- The mapping of erasure coded PG fails (it has *[4,1,2147483647,3,2147483647,9,8,11]*) and although the plugin claims ...
- 11:23 AM Bug #8863 (Pending Backport): osd: second reservation rejection -> crash
- 11:20 AM Bug #9205 (Pending Backport): osd: notify ops reordered
- 11:20 AM Bug #9259 (Pending Backport): persistent slow request warnings on an osd/pg combo which has not b...
- 10:57 AM Feature #8639 (Resolved): mon: dispatch messages while blocked waiting for IO
- 10:47 AM Revision e5930a31 (ceph): tests: reduce osd-crush.sh execution time
- A loop creating 255 crush rulesets via the command line takes
minutes. It is replaced by the generation of a crushmap... - 10:17 AM Revision c02c41c1 (ceph): erasure-code: wrap lines for emacs compile command
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 10:17 AM Revision d4ea682f (ceph): erasure-code: implement ErasureCodePluginRegistry::remove
- Which is symmetric to the add method and used for test.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 10:17 AM Revision 3c4220e1 (ceph): erasure-code: add Ceph version check to plugins
- Add the __erasure_code_version function to all plugins, to return the
Ceph version against which they have been compi... - 10:17 AM Revision b059bcdc (ceph): erasure-code: assert the PluginRegistry lock is held when it must
- Add lock to the preload method and assert that it is held by methods
requiring it. Although preload is called at boot... - 10:13 AM Revision efc8bfd1 (ceph): erasure-code: jerasure preloads the plugin variant
- The variant selection depending on the available CPU features is
encapsulated in a helper. The helper is used in the ... - 09:58 AM Feature #9262: Additional namespace issues
Support for rados export/import:
Given a directory export will do the following:
All default namespace object...- 09:49 AM rgw Bug #9169 (New): 100-continue broken for centos/rhel
- Seems to be still here.
In run http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_17:50:01-upgrade:dumpling-f... - 09:44 AM Bug #9258 (Resolved): "Floating point exception" in upgrade:dumpling-firefly-x-master-distro-basi...
- that crash is on the same old commit before the fix was applied. the latest firefly has the backported patch.
- 09:41 AM Bug #9258 (New): "Floating point exception" in upgrade:dumpling-firefly-x-master-distro-basic-vps...
- Still see the crash, but only in one tests now:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_17:50:01... - 09:33 AM Bug #9224: osd: segv in dlopen
- Will re-run a grep on flab.front.sepia.ceph.com on the osd logs of 2014-08-23 and 2014-08-25 because it does not show...
- 09:32 AM devops Bug #9268 (Resolved): Recipe errors in rgw:multifs-dumpling-testing-basic-vps
- Logs are n http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_17:32:41-rgw:multifs-dumpling-testing-basic-vps/...
- 09:23 AM devops Bug #9267 (Resolved): "Gem::DependencyError" in upgrade:dumpling-dumpling-distro-basic-vps
- Majority of failures like these in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_15:31:01-upgrade:dumplin...
- 09:17 AM CephFS Bug #9173 (Resolved): Crash in Server::_session_logged
- 09:09 AM Revision 39bcb43a (ceph): erasure-code: preload the isa plugin by default
- But only do so when it has been compiled because a recent enough yasm
has been found.
Signed-off-by: Loic Dachary <l... - 09:09 AM Revision 487105df (ceph): erasure-code: add directory to plugin init functions
- The prototype of the init functions of erasure coded plugins is changed
from
int __erasure_code_init(char *plugin... - 09:09 AM Revision 203d62f8 (ceph): erasure-code: remove unused errno.h include
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 09:09 AM Revision 56db6def (ceph): erasure-code: add Red Hat to copyright notices
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 08:09 AM CephFS Bug #8962: kcephfs: client does not release revoked cap
- ...
- 07:37 AM Feature #7238: erasure code : implement LRC plugin
- the above teuthology test ran successfully, with trashosd...
- 07:09 AM devops Bug #9265 (Resolved): ceph-deploy: don't force users to install `wget` if `wget` is available
- ceph-deploy should check first (super easy to do this) before attempting to install that always.
- 06:19 AM CephFS Bug #9252: Worker thread to advance MDS in absence of messages
- Testing on wip-jcsp-test
- 06:19 AM CephFS Bug #9151: mds should log/error/warn when segments are NOT getting trimmed
- Testing on wip-jcsp-test
- 06:18 AM Revision e9a05b8a (ceph): doc: Update docs about OSD benchmark syntax
- 06:16 AM Revision a087f031 (ceph): Revert "doc: Update docs about OSD benchmark syntax"
- This reverts commit 36f15c3026debd808920a04bc3a60c96b119405b.
Commit included submodule change which was not suppose... - 06:12 AM Revision 36f15c30 (ceph): doc: Update docs about OSD benchmark syntax
- 12:32 AM Revision db8d6e6e (ceph): mds: fix FP error in ROUND_UP_TO
- Explicitly handle case where denominator is 0, instead of
passing into ROUND_UP_TO.
Regression from 9449520b121fc6ce... - 12:26 AM Revision a58518b1 (ceph): Merge pull request #2310 from ceph/wip-9148
- Wip 9148
Reviewed-by: Sage Weil <sage@redhat.com>
08/27/2014
- 11:54 PM Feature #9262 (Resolved): Additional namespace issues
I’ve identified the following namespace issues:
1. "rados cppool" only copies objects in default namespace
2. "...- 11:24 PM Revision ae3d8734 (ceph): PG::can_discard_op: do discard old subopreplies
- Otherwise, a sub_op_reply from a previous interval can stick around
until we either one day go active again and get r... - 10:35 PM Revision 97e4e115 (ceph): civetweb: update submodule
- Add access log api
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 09:43 PM Revision b013625c (ceph): Merge pull request #2339 from leseb/sample-ceph-conf-addition
- sample.ceph.conf: some updates
- 09:37 PM Revision 1434e5c8 (ceph): mds: restart on -EBLACKLISTED
- Previously these cases would (hopefully) hit an
assert(r==0) in the various completion contexts,
and the MDS would "c... - 09:36 PM Revision 6a71159e (ceph): mon/Paxos: add writing and refresh states
- The new transition will be
(updating or updating-previous) -> writing -> refresh -> active
Signed-off-by: Sage Wei... - 09:36 PM Revision 3dcea3b7 (ceph): mon/Paxos[Service]: allow reads during WRITING state
- The REFRESH state is not readable; that's when we are re-reading our state
out of leveldb, and we hold the mon_lock d... - 09:36 PM Revision a0e0b9bb (ceph): mon/Paxos: make backend write async
- Move into the WRITING state and do the write to leveldb (or whatever the
backend is) asynchronously.
A few tricks he... - 09:36 PM Revision 805e5d7b (ceph): mon/Paxos: flush io on reset()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision d3bb477c (ceph): mon: flush before scrub
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision 96030d63 (ceph): mon: _reset() before updating state
- In _reset() we call Paxos::restart(), which waits for commit completion,
and assumes the state hasn't been twiddled y... - 09:36 PM Revision b1cf2104 (ceph): mon/Paxos: WRITING != WRITING_PREVIOUS
- This distinction is important: the update-previous state should not be
writeable, as reflected by PaxosService::is_wr... - 09:36 PM Revision bb119360 (ceph): mon: flush paxos write on shutdown
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision a6a1e994 (ceph): mon: interact with MonitorDBStore::Transactions by shared_ptr Ref
- TransactionRef everywhere!
Signed-off-by: Sage Weil <sage@redhat.com> - 09:36 PM Revision 01072b02 (ceph): mon/MonitorDBStore: add close() method
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision 02a7209d (ceph): mon/MonitorDBStore: add async queue_transaction()
- Do the transaction async, and then trigger a callback.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:36 PM Revision bb50371c (ceph): mon/MonitorDBStore: drop useless ctor
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision e74c044c (ceph): mon/MonitorDBStore: assert closed in destructor
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:36 PM Revision 08f331be (ceph): mon/Paxos: break commit() into two pieces
- One part happens before the txn starts, the other after. Move all of the
internal state update to the bottom half. ... - 09:36 PM Revision 663146ac (ceph): mon/Paxos: move post-commit finish work into commit_finish()
- The main change here is that we are merging the singleton and clustered
finish code together. This is mostly a code ... - 09:36 PM Revision cfc68307 (ceph): common/Finisher: fix perfcounter
- Make sure we add in the nubmer of elements when we queue them
from a list or deque or vector.
Fix the type to be a c... - 09:34 PM Revision 97f9b6df (ceph): mon/OSDMonitor: fix double-free on old MOSDBoot
- send_latest() does an m->put().
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 09:24 PM Revision 9ebc8ee7 (ceph): Merge remote-tracking branch 'gh/wip-rewrite-PR2189'
- 09:22 PM Revision 322e2498 (ceph): Merge pull request #101 from ceph/wip-7810
- Wip 7810
- 07:56 PM Revision 06b92cee (ceph): Move fedora patch file (used by ceph.spec.in) to rpm/ subdir
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:56 PM Revision 875a99e2 (ceph): ceph.spec.in: Obsolete all older versions.
- Now this changeset can be used on all current ceph releases that already
have the package split.
Signed-off-by: Erik... - 07:56 PM Revision e37b262c (ceph): ceph.spec.in: Add a small comment on the empty %files section
- as suggested by Dan Mick.
Signed-off-by: Erik Logtenberg <erik@logtenberg.eu> - 07:56 PM Revision 7474f720 (ceph): ceph.spec.in: tests for rhel or centos need to not include _version
- rhel_version and centos_version are apparently the OpenSUSE Build
names; the native macros are just "rhel" and "cento... - 07:56 PM Revision 6c264f22 (ceph): ceph.spec.in: add ceph-libs-compat
- Added a ceph-libs-compat package in accordance with Fedora packaging
guidelines [1], to handle the recent package spl... - 07:56 PM Revision e9da2d8f (ceph): ceph.spec.in: Add obsoletes for libcephfs
- This fixes a bug for Fedora:
https://bugzilla.redhat.com/show_bug.cgi?id=1116614
Signed-off-by: Erik Logtenberg <eri... - 07:56 PM Revision 461523b0 (ceph): ceph.spec.in, init-ceph.in: Don't autostart ceph service on Fedora.
- This patch is taken from the current Fedora package and makes the upstream
ceph.spec compliant with Fedora policy. Th... - 07:56 PM Revision 00877ae5 (ceph): ceph.spec.in: We need those nice recent changes for rhel7 in Fedora too.
- Signed-off-by: Erik Logtenberg <erik@logtenberg.eu>
- 07:56 PM Revision 75985024 (ceph): ceph.spec.in: Obselete ceph-libcephfs (not libcephfs)
- I am guessing that because it was a sub-package libcephfs was mistakenly
used instead of ceph-libcephfs.
Signed-off-... - 07:56 PM Revision 8f95daf6 (ceph): ceph.spec.in: No version on ceph-libs Obsoletes.
- If we are installing with the new package structure we don't ever want the
new package to co-exist with the old one; ... - 07:27 PM Revision 62d74b30 (ceph): civetweb: update submodule
- Fixes: #9208
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 07:27 PM Revision 11acb709 (ceph): rgw: convert header field underscores into dashes
- Fixes: 9206
Backport: firefly
Certain web servers filter out underscores in the header field name.
Convert them into... - 06:12 PM Revision 06ec5ef5 (ceph): test: common: test_config: whitelist '$channel' meta-variable
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:12 PM Revision 8a9831f9 (ceph): osd/mds/monc: Adjust for LogClient/LogChannel usage
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision b7ce6334 (ceph): common: LogEntry: if 'channel' is empty on decode assign default
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 43075bf1 (ceph): mon: Monitor: log every administrative action in an 'audit log'
- Fixes: #7988
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 06:02 PM Revision 301fc0ce (ceph): mon: Monitor: log administrative actions via admin socket
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 3ee90617 (ceph): mon: Monitor: propagate return for functions called for admin socket
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 68ef6814 (ceph): mon: Monitor: observe log client config changes
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 8b5e0cfe (ceph): mon: Monitor's clog/audit_clog need to accessed as pointers
- :1,$s/clog\./clog->/
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 06:02 PM Revision b97b06e1 (ceph): mon: LogMonitor: write log messages on a per-channel basis
- Instead of dumping everything to the same log file, let us this way
allow a user to specify per-channel log files, le... - 06:02 PM Revision 86b21539 (ceph): mon: LogMonitor: observe config changes
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 8f9e105d (ceph): mon: LogMonitor: expand meta variables at time-of-call
- Instead of expanding it when we updated config options, as that would be
nothing but trouble.
Signed-off-by: Joao Ed... - 06:02 PM Revision bb9d4ca3 (ceph): mon: LogMonitor: debug update_from_paxos
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:01 PM Revision 7ef1273a (ceph): common: LogClient: allow specifying facility for LogClient
- Instead of allowing only one LogClient, we will now allow any daemon to
have any number of LogClients. They may eith... - 05:57 PM Bug #9235: unittest_histogram test case Histogram.Position fail
- The master branch is correct.
- 05:57 AM Bug #9235: unittest_histogram test case Histogram.Position fail
- Could you try again with the master branch ?
- 05:55 PM Revision 68858249 (ceph): common: str_map: have 'get_str_map' only handling plain-text
- 'get_str_map()' used to handle both JSON and plain-text. In fact it
would try parsing the map as JSON on a first try... - 05:31 PM Bug #9258 (Resolved): "Floating point exception" in upgrade:dumpling-firefly-x-master-distro-basi...
- backported fix, commit:db8d6e6e190de964ec3d5d1bbc87da2dcb3213f5
- 03:32 PM Bug #9258 (Resolved): "Floating point exception" in upgrade:dumpling-firefly-x-master-distro-basi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-27_14:00:01-upgrade:dumpling-firefly-x-master-dist...
- 05:29 PM Revision 9181114d (ceph): rgw: clear bufferlist if write_data() successful
- Fixes: #9201
Backport: firefly
We sometimes need to call RGWPutObjProcessor::handle_data() again,
so that we send th... - 05:26 PM rgw Feature #9200 (Pending Backport): rgw: log civetweb access
- 05:25 PM rgw Bug #9208 (Pending Backport): rgw: civetweb does not drain request buffer correctly
- 05:25 PM rgw Bug #9206 (Pending Backport): rgw: cross rgw message headers filtered by apache 2.4
- 05:24 PM rgw Bug #9201 (Pending Backport): rgw: bad object with different pool alignment
- 05:23 PM rgw Bug #9148 (Pending Backport): rgw: multiregion tests failing, s3tests.functional.test_s3.test_reg...
- 05:21 PM Revision 0d2a6c70 (ceph): common: LogEntry: change field name from 'type' to 'prio' (aka priority)
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:21 PM Revision 3178ca9e (ceph): common: LogEntry: add clog_type_to_string()
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:21 PM Revision 8a2bfcd8 (ceph): common: LogEntry: add 'channel' field
- We now introduce the concept of 'channel', analogous to syslog
facilities, for log entries. This will, shortly, allo... - 05:21 PM Revision 59dac427 (ceph): common: LogEntry: refactor how we output to syslog
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:21 PM Revision 15e9fc45 (ceph): common: LogClient: delegate message reference release to caller
- Caller decides whether to release the message's reference. It may want
to use the same message on another LogClient,... - 05:21 PM Revision b1af4bd0 (ceph): common: str_map: add helper methods to get values from maps
- Both methods obtain values for keys from a given map. Main distinction
is that one method will return a default valu... - 05:12 PM rgw Bug #8718: CORS OPTIONS request fails for presigned urls
- I pushed some fix to wip-8718. However, further investigation shows that we shouldn't even try to authenticate in a C...
- 05:02 PM CephFS Bug #9260 (Resolved): hadoop fs gets EINVAL
- This will fail on hadoop fs -put with EINVAL. No apparent problems in the libcephfs log....
- 04:22 PM Revision f25bca31 (ceph): systemd: ceph-mds and ceph-mon need networking too
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:22 PM Revision 9c9b1602 (ceph): Merge pull request #2306 from mgarces/patch-1
- needs network or it will not start if enabled
Reviewed-by: Sage Weil <sage@redhat.com> - 04:17 PM Revision d36eaa9b (ceph): Merge pull request #2313 from dachary/wip-buffer
- common: remove spurious uint32_t in buffer.c
Reviewed-by: Sage Weil <sage@redhat.com> - 04:11 PM Bug #9259 (Resolved): persistent slow request warnings on an osd/pg combo which has not been for ...
- PG::can_discard_request just returns false for sub op replies. No idea why. Oops.
(03:35:38 PM) Brian A: 2014-08... - 04:06 PM Revision c6f4b42f (ceph): sample.ceph.conf: some updates
- This commit adds:
- a section for radosgw
- fix the replica count value (default is 3 since firefly)
- more OSDs opti... - 03:56 PM Revision fdfe77f9 (ceph): Merge pull request #1950 from xylv/wip-8583
- rgw: admin ops create user API can not determine existing user
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:41 PM rgw Bug #9089 (Pending Backport): rgw: copy_obj_data() does not stripe target object
- This was fixed at commit:800eff24824c0083b8e2441fc34e0bdca5da36dc
- 03:32 PM rgw Bug #8583 (Resolved): rgw: admin ops create user API can not determine existing user
- Merged, commit:fdfe77f9e44be6153ead8bb082717762c747f7eb
- 02:37 PM CephFS Feature #4583 (Resolved): libcephfs: add test that kills a client and verifies mds cleans it up
- ...
- 02:22 PM CephFS Feature #7810 (Resolved): libcephfs: add a test that freezes + unfreezes a client, and then verif...
- ...
- 02:21 PM CephFS Feature #4886 (Resolved): teuthology: add tests that use the MDS dumper
- 02:21 PM CephFS Feature #4886: teuthology: add tests that use the MDS dumper
- ...
- 01:19 PM Revision 2b13de16 (ceph): osd/PG: fix crash from second backfill reservation rejection
- If we get more than one reservation rejection we should ignore them; when
we got the first we already sent out cancel... - 12:39 PM Revision 5a632158 (ceph): mon/OSDMonitor: make reweight_by_* output less misleading
- Sometimes we increase weights. State simply which OSDs are reweighted
(not overloaded).
Signed-off-by: Sage Weil <s... - 10:31 AM devops Bug #9243 (Resolved): teuthology's jenkins is broken
- The rest of the fix:
https://github.com/ceph/teuthology/commit/95a08b566c8ee5c5e4979b6bc1524f1c7615d9b9#diff-d41d8cd... - 10:03 AM CephFS Bug #8962: kcephfs: client does not release revoked cap
- ...
- 09:29 AM Bug #9156: SWIFT tests failed in upgrade:dumpling:rgw-dumpling-distro-basic-vps suite
- Thrashing was removed - https://github.com/ceph/ceph-qa-suite/pull/108/
Now testing. - 08:56 AM rgw Bug #9254 (Resolved): rgw: civetweb requires explicit \r\n for http headers
- Otherwise certain windows client fail.
- 08:20 AM Revision 146e60d7 (ceph): osd: Remove extra call to release_op_ctx_locks in eval_repop. It is
- called in remove_repop.
Signed-off-by: Zhiqiang Wang <wonzhq@hotmail.com> - 07:28 AM Feature #7238: erasure code : implement LRC plugin
- "IsRecoverablePredicate":https://github.com/ceph/ceph/blob/95be35abd30bb2374accea5a72ffd26a6c25635a/src/osd/ECBackend...
- 03:06 AM Feature #7238: erasure code : implement LRC plugin
- It crashes the OSD in decode() but the plugin is silent on the reason why it refuses to decode. Adding debug informat...
- 07:04 AM Bug #9253: ECBackend::continue_recovery_op assert when not enough shards
- Using 95be35abd30bb2374accea5a72ffd26a6c25635a...
- 07:03 AM Bug #9253 (Duplicate): ECBackend::continue_recovery_op assert when not enough shards
- The object is missing on too many shards to recover ( *missing_on_shards=1,2,3,4,5,6,7* ) and when "minimum_to_decode...
- 06:51 AM CephFS Bug #9252 (Resolved): Worker thread to advance MDS in absence of messages
As we move dispatchers outside of the MDS (first Objecter, now Beacon), there are some cases that don't progress pr...- 06:46 AM Feature #9251 (Duplicate): check consistency of rbd export and import function
- It would be very helpful to have a function that checks the consistency of rbd export / import and likewise export-di...
- 06:16 AM Bug #8863 (Fix Under Review): osd: second reservation rejection -> crash
- see wip-8863
- 05:23 AM Bug #8835 (Resolved): rados mkpool doesn't error out for pools which are existing
- 04:18 AM Revision 3bfbc141 (ceph): test/mon/mkfs.sh: fix test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:05 AM Revision 68b942e3 (ceph): Merge pull request #2197 from ceph/wip-mon-empty-store
- ceph_mon: check for existing mon store before opening db
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Pavan... - 01:03 AM Revision e9f7311b (ceph): Merge pull request #2312 from ceph/wip-config-diff
- config diff: obtain diff between current config and default config
Reviewed-by: Sage Weil <sage@redhat.com> - 12:43 AM Revision c2f21c04 (ceph): osd: fix osd_tp shutdown
- We need to clear the queue, not just drain the currently executing jobs.
Fixes: #9218
Backport: firefly
Signed-off-b... - 12:33 AM Revision 0a0c10f0 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/os/CollectionIndex.h - 12:00 AM Revision 8e3120fc (ceph): mon: generate cluster_fingerprint if null
- This triggers after an upgrade of a legacy cluster that has no fingerprint.
Signed-off-by: Sage Weil <sage@redhat.co... - 12:00 AM Revision ebcdeb4c (ceph): mon: add a cluster fingerprint
- Generate it on cluster creations with the initial monmap. Include it in
the report. Provide no way for this uuid to...
08/26/2014
- 11:53 PM Revision 8346e107 (ceph): PG: mark_log_for_rewrite on resurrection
- Fixes: #8777
Backport: firefly
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:39 PM Revision cb4c5e83 (ceph): OSD::session_notify_pg_create: requeue at the start of the queue
- Introduced: 2120f4bb6c5ba0f066d4541a51ce1d43c8ab6881
Fixes: #9205
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:29 PM Revision 13f603cc (ceph): Merge pull request #111 from ceph/wip-fix-stress_split
- Moved mon.c to the first host with mon.a and mon.b to address the issue
- 11:19 PM Revision 1ba6e02c (ceph): Moved mon.c to the first host with mon.a and mon.b to address the issue
- Sage found:
"... supposed to have half dumpling, half x osds. but the steps that upgrade and restart the mons upgrade... - 11:11 PM Revision 91cc5b62 (ceph): Merge pull request #110 from ceph/wip-fix-stress_split
- Moved mon.c to teh first host with mon.a and mon.b to address the issue ...
- 11:06 PM Revision 752356fc (ceph): Moved mon.c to teh first host with mon.a and mon.b to address teh issue...
- "... supposed to have half dumpling, half x osds. but the steps that upgrade and restart the mons upgrade the packag...
- 10:31 PM Revision ef51160b (ceph): common: config: let us obtain a diff between current and default config
- It's mildly annoying when trying to figure out what has been changed on
a running system's config options and having ... - 10:31 PM Revision 3c847c5a (ceph): common: ceph_context: add admin socket command 'config diff'
- Outputs a diff between the current config and what the daemon believes
to be its default config.
Signed-off-by: Joao... - 10:16 PM Bug #8835: rados mkpool doesn't error out for pools which are existing
- I should have rather mentioned the commit https://github.com/ceph/ceph/commit/448edb191ca38c22c00923d63a5a83c884c2f223
- 10:10 PM Bug #8835: rados mkpool doesn't error out for pools which are existing
- This tracker has been fixed via the pull request https://github.com/ceph/ceph/pull/2209.
- 02:00 PM Bug #8835 (Won't Fix): rados mkpool doesn't error out for pools which are existing
- 09:43 PM Revision ac4b4562 (ceph): Merge pull request #2334 from dachary/wip-9235-uninitialized-variables
- tests: histogram prevent re-use of local variables
- 09:23 PM Revision 4b8b25ec (ceph): tests: histogram prevent re-use of local variables
- By moving the tests to separate functions.
http://tracker.ceph.com/issues/9235 Fixes: #9235
Signed-off-by: Loic Dac... - 09:15 PM Revision 722a3b9f (ceph): Merge pull request #2333 from dachary/wip-9235-uninitialized-variables
- tests: histogram prevent re-use of local variables
Reviewed-by: Sage Weil <sage@redhat.com> - 09:13 PM Revision a525bf31 (ceph): ReplicatedPG:start_flush send a second delete
- Suppose we start with the following in the cache pool:
30:[29,21,20,15,10,4]:[22(21), 15(15,10), 4(4)]+head
The obj... - 08:46 PM Bug #9046 (Resolved): Limiting the pool object quota stops the IO, however IO does not restart if...
- This bug was fixed in the 3.14 kernel. There have been several other fixes since then as well... your best bet is to...
- 05:41 AM Bug #9046: Limiting the pool object quota stops the IO, however IO does not restart if we reset t...
- Please let me know if there is any update on this issue?
- 05:40 AM Bug #9046: Limiting the pool object quota stops the IO, however IO does not restart if we reset t...
- Hirak Mazumder wrote:
> Issue Title: Limiting the pool object quota stops the IO, however IO does not restart if we... - 08:13 PM Revision b3b02916 (ceph): Merge pull request #2244 from dachary/wip-9044-use-ruleset-firefly
- erasure-code: OSDMonitor::crush_ruleset_create_erasure needs ruleset (firefly)
- 08:10 PM Revision 21e1faa7 (ceph): ReplicatedPG::cancel_copy: clear cop->obc
- Otherwise, an objecter callback might still be hanging
onto this reference until after the flush.
Fixes: #8894
Intro... - 08:05 PM Revision ee02293a (ceph): tests: histogram prevent re-use of local variables
- By moving the test to a separate function.
http://tracker.ceph.com/issues/9235 Fixes: #9235
Signed-off-by: Loic Dac... - 07:54 PM Revision 66c7439e (ceph): ReplicatedPG::start_flush: remove superfluous loop
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:52 PM Revision 0416b884 (ceph): update license for libcephfs
- Signed-off-by: rootfs <hchen@redhat.com>
- 07:31 PM Bug #9235: unittest_histogram test case Histogram.Position fail
- I merger this change, rebuild the unittest, rerun this test case. lb, ub is still 0 in my machine....
- 02:12 PM Bug #9235 (Resolved): unittest_histogram test case Histogram.Position fail
- 01:03 PM Bug #9235 (Fix Under Review): unittest_histogram test case Histogram.Position fail
- "need review":https://github.com/ceph/ceph/pull/2333
- 12:50 PM Bug #9235 (In Progress): unittest_histogram test case Histogram.Position fail
- 02:46 AM Bug #9235 (Resolved): unittest_histogram test case Histogram.Position fail
- unittest_histogram test case Histogram.Position fail.
https://github.com/ceph/ceph/blob/master/src/test/common/his... - 07:24 PM Revision e81723a3 (ceph): Merge pull request #2330 from ceph/wip-9211
- osd/OSDMap: encode blacklist in deterministic order
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:05 PM Revision e6da7323 (ceph): PG: recover from each osd at most once
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:51 PM Support #9249 (Closed): unable map stripe rbd
- Hi
I have create stripe rbd,but i can't map this rbd.when i create normal rbd,it can be mapped.
this is info whe... - 06:38 PM Revision 8a1723f6 (ceph): PG: make the reservation sets more descriptively named
- These sets won't precisely be the backfill_targets or actingbackfill
shortly.
%s/sorted_backfill_set/remote_shards_t... - 06:08 PM Revision 78cbe115 (ceph): Merge pull request #2331 from ceph/wip-9238
- mds: fix FP error in ROUND_UP_TO
Reviewed-by: Sage Weil <sage@redhat.com> - 05:41 PM Bug #9218 (Fix Under Review): FAILED assert(peering_queue.empty()) during OSD shutdown
- https://github.com/ceph/ceph/pull/2335
- 05:30 PM Revision 938d7356 (ceph): Merge pull request #2203 from ceph/wip-scrub-firefly
- backport scrub throttling to firefly
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:00 PM Revision 0fcae823 (ceph): Merge pull request #109 from ceph/wip_fix_firefly-x
- Added sequential: clause, so test stop thrashing the mon after it runs t...
- 04:53 PM Revision 3afa81b0 (ceph): Fixed typo
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:49 PM Bug #9205: osd: notify ops reordered
- 04:32 PM Bug #9205: osd: notify ops reordered
- OSD::session_notify_pg_create queues the pg waiters at the end of the waiting_for_map queue rather than at the beginn...
- 03:46 PM Bug #9205: osd: notify ops reordered
- first 2 ops arrive...
- 03:16 PM Bug #9205: osd: notify ops reordered
- ...
- 04:49 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- 04:39 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- i think th eerror is when the osd next restarts and loads the log:...
- 02:49 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- This is a bug with pg resurrection. I can't seem to find where pg->log is supposed to get cleared.. which is why the...
- 02:47 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- ...
- 04:44 PM Revision bf3e4835 (ceph): mds: fix FP error in ROUND_UP_TO
- Explicitly handle case where denominator is 0, instead of
passing into ROUND_UP_TO.
Regression from 9449520b121fc6ce... - 04:39 PM devops Bug #9243: teuthology's jenkins is broken
- I fixed most of the problem on gitbuilder-cdep-deb-cloud-precise-amd64-basic by doing:
@sudo apt-get install python-... - 02:30 PM devops Bug #9243 (Resolved): teuthology's jenkins is broken
- http://jenkins.ceph.com/job/teuthology-pull-requests/564/console
- 04:21 PM Revision 93167563 (ceph): Added sequential: clause, so test stop thrashing the mon after it runs ...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:18 PM Revision a7531808 (ceph): Merge pull request #2321 from ceph/wip-9226
- rgw: fix test to identify whether object has tail
Reviewed-by: Sage Weil <sage@redhat.com> - 04:15 PM Feature #7238: erasure code : implement LRC plugin
- The rados test is running, with thrashing after a rebase on master.
- 04:11 PM Revision 46d9f56c (ceph): set boto timeout, too, for s3tests
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 9e5397237857d9015ac8c9e908f0cbeb1777576d)
Conf... - 04:10 PM Revision de54f230 (ceph): tasks/s3tests: push boto config with idle_timeout setting
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 9d466aa110e293cb88c1f61cc7391d59b64b553b) - 04:07 PM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- 04:04 PM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- NB the handing for this case in rbd landed with wip-objecter, keep this ticket open for general purpose ObjectCacher ...
- 04:05 PM CephFS Bug #9238: Floating point exception in Locker::calc_new_client_ranges
- Loic: if the original change was on firefly too then yes
- 11:34 AM CephFS Bug #9238: Floating point exception in Locker::calc_new_client_ranges
- Should this be backport to firefly ?
- 11:05 AM CephFS Bug #9238 (Resolved): Floating point exception in Locker::calc_new_client_ranges
- 09:50 AM CephFS Bug #9238 (Fix Under Review): Floating point exception in Locker::calc_new_client_ranges
- https://github.com/ceph/ceph/pull/2331
- 09:29 AM CephFS Bug #9238 (Resolved): Floating point exception in Locker::calc_new_client_ranges
On master, MDS starts fine first time and then crashes on second start.
Floating point error on Locker::calc_new...- 03:59 PM Fix #9245 (Resolved): remove Monitor::osdmonitor_prepare_command
- osdmonitor_prepare_command is too fragile and leads to obscure problems when it fails. A possible replacement would b...
- 03:58 PM Revision 7baeb804 (ceph): Merge pull request #105 from ceph/wip-boto
- tasks/s3tests: push boto config with idle_timeout setting
- 03:37 PM Revision 53c47f90 (ceph): Merge pull request #2314 from ceph/wip-mds-pc
- mds: clean up perfcounter names
Reviewed-by: John Spray <john.spray@redhat.com> - 03:20 PM Revision 2f11631f (ceph): os/FileStore: fix mount/remount force_sync race
- Consider:
- mount
- sync_entry is doing some work
- umount
- set force_sync = true
- set done = true
- syn... - 03:16 PM Revision 4672e509 (ceph): osd/OSDMap: encode blacklist in deterministic order
- When we use an unordered_map the encoding order is non-deterministic,
which is problematic for OSDMap. Construct an ... - 02:53 PM Revision aaa5e382 (ceph): Merge pull request #2325 from xinxinsh/wip-9217
- fix wrong value of op_w_latency perf counter
Reviewed-by: Sage Weil <sage@redhat.com> - 02:48 PM Bug #7934: ceph_test_rados_watch_notify doesn't clean-up all pools it creates
Yes it still does this.
- 02:19 PM Bug #8736 (Duplicate): thrash and scrub combination lead to error
- ha, it's the riter bug. #8777
- 02:11 PM devops Bug #9239: Process from starting locking machines till tests start running take long time (~1 hour)
- Something is badly broken, this suite actually never got off the ground - http://pulpito.front.sepia.ceph.com/teuthol...
- 10:09 AM devops Bug #9239 (Resolved): Process from starting locking machines till tests start running take long t...
- We are seeing this on late runs.
For example - http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-26_08:50:02-... - 02:10 PM Bug #8555 (Can't reproduce): PUT osd/pool/rename?srcpool=data2&destpool=data3: 400 (dumpling)
- 02:10 PM Bug #7120 (Can't reproduce): osd: EEXIST on mkcoll on dumpling
- 02:09 PM Bug #7744 (Can't reproduce): osd: assert(last_e.version.version < e.version.version)
- 02:09 PM Bug #8163 (Resolved): stuck recovering due to a 50 min delay in processing Push op
- 02:08 PM Bug #8753 (Can't reproduce): PG::activate assert failed when recover finished
- 02:07 PM Bug #8519 (Resolved): msgr: deadlock, blocked on SimpleMessenger::lock
- 02:06 PM Bug #8582 (Can't reproduce): Cluster very slow after upgrade to 80.1
- 02:06 PM rgw Bug #8676: md5sum check failed during readwrite.py
- After some more research: The 103 is part of the normal shutdown sequence. Still might be a client teardown handling ...
- 12:40 PM rgw Bug #8676: md5sum check failed during readwrite.py
- Well, it seems that the md5 digest is embedded in the object's data, so even if writes are racing (as they are), it s...
- 11:14 AM rgw Bug #8676: md5sum check failed during readwrite.py
- Something I noticed now:...
- 02:05 PM Bug #5395 (Can't reproduce): arm: osd: big performance differential between read/write
- 02:05 PM Bug #8212 (Resolved): Update Web docs for building ceph
- README is now up to date with dependencies
- 02:04 PM Bug #8256 (Won't Fix): unhelpful ceph cli command --help
- 02:03 PM Bug #8578 (Can't reproduce): teuthology: OSD thrasher killing OSDs which hold the sole copies of PGs
- 02:03 PM Bug #8630 (Resolved): test osd-config.sh ENXIO
- 01:58 PM Bug #8959 (Can't reproduce): osd crashed in upgrade:dumpling-x-firefly---basic-vps suite
- 01:57 PM Bug #7576 (Resolved): osd: large skew in pg epochs (dumpling)
- 01:56 PM Bug #7902 (Resolved): osd/PG.cc: 6803: FAILED assert(!pg->actingbackfill.empty())
- 01:56 PM Bug #9018 (Resolved): "LibRadosTwoPoolsPP*" failed in upgrade:dumpling-x-firefly---basic-vps
- 01:56 PM Bug #9065 (Resolved): LibRados* tests failed in upgrade:dumpling-x-firefly---basic-vps
- 01:55 PM Bug #8922 (Can't reproduce): ceph-deploy mon create fails to create additional monitoring nodes.
- 01:55 PM Bug #8895 (Duplicate): ceph osd pool stats (displayed incorrect values)
- 01:52 PM Bug #9158 (Duplicate): osd crashed in upgrade:dumpling-x:stress-split-master-distro-basic-vps suite
- 01:51 PM Bug #9156: SWIFT tests failed in upgrade:dumpling:rgw-dumpling-distro-basic-vps suite
- confirm the thrashing has been removed from the test
- 01:51 PM rgw Bug #9169 (Closed): 100-continue broken for centos/rhel
- 01:50 PM Bug #8985 (Resolved): "[WRN] map e9 wrongly marked me down" in upgrade:dumpling-x-firefly---basic...
- 01:45 PM Bug #9111: PG stuck with 'active+remapped' forever with cluster wide change (add/remove OSDs)
- We probably want to add a heuristic that notices if a pool might have this problem and point the user at a doc page.
- 01:45 PM Bug #9111: PG stuck with 'active+remapped' forever with cluster wide change (add/remove OSDs)
- Ah, I think it's your very wide EC stripe. Try increasing total retries on the crush rule for that pool.
- 01:43 PM Revision a38cf1bd (ceph): Add random_cache.hpp to Makefile.am
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
(cherry picked from commit a3e5c6d632119febd2150944a6f2cbce33cfda3a) - 01:42 PM Bug #8785 (Resolved): valgrind tcmalloc false positive (firefly)
- 01:42 PM Revision a2c1532b (ceph): os/KeyValueStore, MemStore: fix warning
- os/MemStore.cc: In member function 'void MemStore::_do_transaction(ObjectStore::Transaction&)':
os/MemStore.cc:956:18... - 01:39 PM Revision 2b86bf4f (ceph): osd: automatically scrub PGs with invalid stats
- If a PG has recnetly split and has invalid stats, scrub it now, even if
it has scrubbed recently. This helps the sta... - 01:38 PM Revision 271ca7d9 (ceph): Merge pull request #2328 from dachary/wip-9209-round-up-to-firefly
- common: ROUND_UP_TO accepts any rounding factor (firefly)
- 01:34 PM Revision 4f8436bf (ceph): Merge pull request #106 from ceph/wip-9091-wusui
- mplement ceph.created_pool
Reviewed-by: Sage Weil <sage@redhat.com> - 01:29 PM Bug #9040: clients can SEGV during package upgrade
- 01:29 PM Bug #9023 (Can't reproduce): valgrind failures in OSD
- This may be fixed, let's mark can't reproduce until it recurrs.
- 01:28 PM Bug #9077: Cluster is up in MON node even if Ceph is uninstalled in OSD node
- Can you reproduce and verify that the two osds are actually not still running?
- 01:23 PM Bug #9073 (Resolved): OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- 01:23 PM Revision 6f000da3 (ceph): Merge pull request #2327 from theanalyst/fix/vstart_rgw_port
- vstart: start rgw on port specified by env var
Reviewed-by: Sage Weil <sage@redhat.com> - 01:21 PM Bug #9135 (Can't reproduce): ENOENT on collection_add
- 01:13 PM Bug #8824 (Can't reproduce): osd: hung MOSDECSubOpWrite
- 01:13 PM Bug #8822 (Can't reproduce): osd: hang on shutdown, spinlocks
- 01:11 PM Bug #8977 (Can't reproduce): osd: didn't discard sub_op_reply from previous interval?
- 01:10 PM Bug #9044 (Resolved): erasure-code: use ruleset instead of ruleid
- 01:09 PM Revision 54333a49 (ceph): Merge pull request #2326 from yuyuyu101/wip-kvstore-firefly
- Backport from master to Firefly(KeyValueStore)
- 01:08 PM Bug #8894 (Resolved): osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- 01:08 PM Bug #8894 (Pending Backport): osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- 01:08 PM Feature #8276 (Fix Under Review): ceph-filestore-dump import-rados -p <pool> <archive>
- 01:07 PM Bug #9114 (Duplicate): osd: segv in build_push_op
- 01:07 PM Feature #8231 (Fix Under Review): ceph filestore dump improvements
- 01:06 PM Bug #9139 (Rejected): ceph_test_rados reports incorrectly missing object
- 01:04 PM Bug #9119 (Resolved): READFORWARD ordering bug
- 01:03 PM Bug #9175 (Duplicate): osd: stuck recovery
- 01:02 PM Bug #9144 (Resolved): filestore: commit triggered during journal replay
- 01:02 PM Bug #7995 (Need More Info): osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs....
- 01:01 PM Bug #9220: objecter doesn't reconnect watch on interval change w/ same primary
- 12:46 PM Bug #9241: osdc/Objecter.cc: 1320: FAILED assert(s->get_nref() == 1)
- /a/samuelj-2014-08-25_22:38:54-rados-wip-sam-testing-testing-basic-multi/450704
- 12:46 PM Bug #9241 (Resolved): osdc/Objecter.cc: 1320: FAILED assert(s->get_nref() == 1)
- 2014-08-26T03:00:57.472 INFO:tasks.radosbench.radosbench.0.burnupi24.stderr: -1> 2014-08-26 03:00:57.380019 7fae60...
- 12:40 PM Bug #9240: osd_max_backfills = 1 can cause reserver deadlock for EC
- 11:07 AM Bug #9240 (Resolved): osd_max_backfills = 1 can cause reserver deadlock for EC
- You can have two non-primary shards in the acting set on the same OSD.
- 12:24 PM Feature #7291: EC: add mechanism for mon to detect and whitelist EC plugins which are globally av...
- 12:24 PM Feature #7291: EC: add mechanism for mon to detect and whitelist EC plugins which are globally av...
- It probably is higher priority for giant because there is more than one plugin.
- 12:22 PM Bug #9211 (Pending Backport): osdmap blacklist encoding order is nondeterministic
- 08:14 AM Bug #9211 (Fix Under Review): osdmap blacklist encoding order is nondeterministic
- https://github.com/ceph/ceph/pull/2330
- 12:17 PM Subtask #6064 (Rejected): erasure code : convenience functions to code / decode
- The code has evolved in a way that makes this irrelevant. The ECUtil class in osd plays this role.
- 12:15 PM Cleanup #4101: buffer::list::iterator constructor should be private
- still relevant
- 12:12 PM Cleanup #7314: remove dead code from OSDMonitor::should_propose
- still relevant
- 12:08 PM Subtask #7358 (Rejected): erasure code : plugin upgrade documentation
- There is no upgrade mechanism for now : the plugins must run against the version of ceph their were built with.
- 11:57 AM Feature #9167 (Fix Under Review): erasure-code: check plugin version when loading it
- "need review":https://github.com/ceph/ceph/pull/2299
- 11:48 AM Bug #9186 (Duplicate): erasure-code: conditionally preload isa plugin
- Resolved as part of http://tracker.ceph.com/issues/9170
- 11:46 AM Bug #9170 (Fix Under Review): erasure-code: preload erasure code plugins
- "pending pull request":https://github.com/ceph/ceph/pull/2299
- 11:42 AM Bug #8433 (Can't reproduce): SSHException: Key-exchange timed out waiting for key negotiation
- 11:18 AM devops Bug #9166: activate dmcrypt volumes via init script
- i think ceph-disk activate-all should do this. but you're right, it doesn't do the dmcrypt mappings.
- 11:17 AM devops Bug #9190 (Resolved): idle times out do not work on ubuntu precise
- 11:16 AM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- 11:15 AM devops Bug #8976: httpd on RHEL7 (RHEL repo) incompatible with mod_fastcgi (ceph repo)
- 11:15 AM devops Bug #8850 (Can't reproduce): ceph-deploy tests fail during tar due to file changed; incomplete sh...
- 10:24 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Xavier Trilla wrote:
> German,
>
> 3.14.x will work well, but it will not work with TUNABLES V3, specifically cho... - 09:29 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- German,
3.14.x will work well, but it will not work with TUNABLES V3, specifically chooseleaf_vary_r turned on. Fo... - 07:08 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Well, the issue didn't get resolved, you simply found a kernel it doesn't show up on. I'm still interested to hear a...
- 07:02 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- It seems that using kernel 3.14.9 resolved the issue. Have tested for more than two days with lot of perf tests and r...
- 10:18 AM Revision a15ad385 (ceph): vstart: start rgw on port specified by env var
- This ensures that user specified option according to $CEPH_RGW_PORT is
considered before starting radosgw
Signed-off... - 10:07 AM Revision 87cd3a8f (ceph): common: ROUND_UP_TO accepts any rounding factor
- The ROUND_UP_TO function was limited to rounding factors that are powers
of two. This saves a modulo but it is not us... - 10:07 AM Linux kernel client Bug #9192: krbd: poor read (about 10%) vs write performance
- We started with the Ubuntu 14.04 supplied 3.13 kernel, but found out that it would not work if 'ceph osd crush tunabl...
- 09:30 AM Linux kernel client Bug #9192 (Need More Info): krbd: poor read (about 10%) vs write performance
- 09:29 AM Linux kernel client Bug #9192: krbd: poor read (about 10%) vs write performance
- Have you compared with 3.16 with the same workload? Or any other past kernel?
- 09:34 AM rbd Feature #2644 (Rejected): qa: gitbuilder for qemu
- 09:33 AM rbd Feature #2625 (Rejected): qa: gitbuilder for libvirt
- 09:33 AM rbd Bug #6631 (Closed): disabling writethrough until flush appears to disable RBD cache
- pretty sure this is resolved now. if not, let us know so we can reopen!
- 09:31 AM rbd Bug #9078: Removing an RBD is very slow whenever there is write's in other RBD which also belongs...
- This seems like more or less what I would expect. What do you suggest should happen? Either rbd remove is slow and ...
- 09:30 AM rbd Bug #9076 (Resolved): Can't completely remove a version 1 image on RHEL 7
- 09:28 AM rbd Bug #9075 (Resolved): Can't create a version 2 images on RHEL 7
- 09:25 AM rgw Bug #8583 (Fix Under Review): rgw: admin ops create user API can not determine existing user
- 09:21 AM rgw Bug #8383 (Rejected): Upload part of one object passed with incorrect upload id or incorrect obje...
- 09:17 AM rgw Bug #8784 (Pending Backport): rgw: completion leak
- 09:15 AM rgw Bug #9226 (Pending Backport): rgw: crash when copying specific objects
- 09:08 AM rgw Bug #9226 (Fix Under Review): rgw: crash when copying specific objects
- Pull request: https://github.com/ceph/ceph/pull/2321
- 09:12 AM rgw Bug #9155: Swift Subuser - 403 Forbidden - during upload/post
- 09:11 AM rgw Bug #9227 (Resolved): test.functional.tests.TestFile fail on dumpling on VPS
- 09:11 AM rgw Feature #9200 (Fix Under Review): rgw: log civetweb access
- 09:10 AM rgw Bug #9148 (Fix Under Review): rgw: multiregion tests failing, s3tests.functional.test_s3.test_reg...
- Pull request: https://github.com/ceph/ceph/pull/2310
- 09:09 AM rgw Bug #9208 (Fix Under Review): rgw: civetweb does not drain request buffer correctly
- 09:09 AM rgw Bug #9201 (Fix Under Review): rgw: bad object with different pool alignment
- 09:09 AM rgw Bug #9206 (Fix Under Review): rgw: cross rgw message headers filtered by apache 2.4
- 09:01 AM rgw Documentation #9237 (Closed): rgw: Feature comparison document
- 08:59 AM rgw Documentation #9003 (Closed): rgw: document development setup for rgw
- Enhancement has been merged to master
- 08:58 AM rgw Subtask #9068 (Closed): rgw: add rgw setup to vstart
- 08:58 AM rgw Subtask #9068: rgw: add rgw setup to vstart
- Completed and merged.
- 07:50 AM Bug #9217 (Resolved): wrong value of osd::op_w_latency
- 06:36 AM Bug #9209 (Resolved): osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- 06:27 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- "backport to firefly":https://github.com/ceph/ceph/pull/2328
- 06:27 AM devops Bug #9185 (Rejected): incorrect Centos 6.5 fastcgi package
- this isn't the package, it's boto timeouts.
we can now adjust them up some, but there seems to be a limit of ~3-4 ... - 06:26 AM CephFS Bug #9212: mon election delays mds beacon
- mds sent beacon...
- 06:22 AM Bug #9215 (Resolved): Ceph Firefly 0.80.5 : OSD flapping too frequently
- 04:34 AM Bug #9215: Ceph Firefly 0.80.5 : OSD flapping too frequently
- You can close this case , problem has been solved after applying fix (0.80.5-1-gc4b77d2)
- 06:19 AM Revision dbe6c798 (ceph): don't update op_rw_rlatency/op_w_rlatency when rlatency is zero
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 06:19 AM Revision f3bf2468 (ceph): fix wrong value of op_w_latency perf counter
- Fixes: #9217
Signed-off-by: xinxin shu <xinxin.shu@intel.com> - 06:09 AM CephFS Bug #9152 (Fix Under Review): mds: beacon needs to not take mds_lock
- 06:06 AM Bug #9223 (Resolved): ObjectStore/StoreTest.BigRGWObjectName/1 failure on KeyValueStore, firefly
- 04:50 AM Revision 58d08714 (ceph): Remove exclusive lock on GenericObjectMap
- Now most of GenericObjectMap interfaces use header as argument not the union of
coll_t and ghobject_t. So caller shou... - 04:48 AM Revision 98df982a (ceph): common/RandomCache: Fix inconsistence between contents and count
- The add/clear method may cause count inconsistent with the real size of
contents.
Signed-off-by: Haomai Wang <haomai... - 04:47 AM Revision c8ec7721 (ceph): Add random cache and replace SharedLRU in KeyValueStore
- SharedLRU plays pool performance in KeyValueStore with large header cache size,
so a performance optimized RandomCach... - 04:40 AM Revision 33ca26a1 (ceph): Add Header cache to KeyValueStore
- In the performance statistic recently, the header lookup becomes the main time
consuming for the read/write operation... - 04:39 AM Revision e8dcb8cc (ceph): Fix write operation on a deleted object in the same transaction
- If the following op happened:
touch obj
delete obj
write obj
KeyValueStore will fail at "write" operation.
Signed-o... - 04:39 AM Revision e0ae6f9d (ceph): Remove SequencerPosition from KeyValueStore
- Now KeyValueStore expects kv backend to ensure consistency and there is unusable
for KeyValueStore to store a Sequenc... - 04:28 AM Revision 44721f71 (ceph): Fix keyvaluestore fiemap bug
- The result of fiemap is wrong and the offset get from
"StripObjectMap::file_to_extents" need to multiply by sequence ... - 01:52 AM Linux kernel client Feature #8842: CephFS kernel module for RHEL7.0 GA
- Is there already an update on this? (I had also logged an issue for this: #8786)
- 01:27 AM Revision 398b418e (ceph): ceph_filestore_dump: Remove unused bufferlist databl
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 01:27 AM Revision 501dd3c0 (ceph): ceph_filestore_dump: Export omap in batches for large omap case
- New function get_omap_batch()
Create a TYPE_OMAP section for each batch
Signed-off-by: David Zafman <david.zafman@in... - 12:29 AM Revision 1698c7a5 (ceph): Merge pull request #2320 from ceph/wip-9221
- ceph_test_rados_api_tier: make PromoteOn2ndRead test tolerate retries
Reviewed-by: Samuel Just <sam.just@inktank.com> - 12:04 AM Revision 4dbc4c41 (ceph): Merge branch 'wip-objecter'
- Reviewed-by: Sage Weil <sage@redhat.com>
08/25/2014
- 09:47 PM Revision fe204e81 (ceph): Merge pull request #107 from dachary/wip-9209-ec-workload
- erasure-code: add jerasure k=3 m=1 workload
- 09:47 PM Revision f7a31191 (ceph): Merge pull request #2319 from dachary/wip-9209-round-up-to
- common: ROUND_UP_TO accepts any rounding factor
Reviewed-by: Sage Weil <sage@redhat.com> - 09:16 PM Bug #9223: ObjectStore/StoreTest.BigRGWObjectName/1 failure on KeyValueStore, firefly
- https://github.com/ceph/ceph/pull/2326
- 09:00 AM Bug #9223 (Resolved): ObjectStore/StoreTest.BigRGWObjectName/1 failure on KeyValueStore, firefly
- ubuntu@teuthology:/a/sage-2014-08-23_16:02:03-rados-firefly-testing-basic-multi/444749...
- 08:50 PM Bug #9217: wrong value of osd::op_w_latency
- https://github.com/ceph/ceph/pull/2325
- 08:49 PM Bug #9217 (Fix Under Review): wrong value of osd::op_w_latency
- 09:36 AM Bug #9217: wrong value of osd::op_w_latency
- I think it's a bug:...
- 02:40 AM Bug #9217 (Resolved): wrong value of osd::op_w_latency
- when i use fio to test rbd performance (4kb random write) , i found that osd::op_w_latency which i got from perf coun...
- 07:56 PM Revision 9449520b (ceph): common: ROUND_UP_TO accepts any rounding factor
- The ROUND_UP_TO function was limited to rounding factors that are powers
of two. This saves a modulo but it is not us... - 06:59 PM devops Bug #9233 (Rejected): packaging changes without control directives to allow upgrade
- Changes to Debian packaging that move files from one package to another need to be accompanied with changes to debian...
- 06:53 PM Revision 9720019d (ceph): Merge pull request #2323 from lpabon/fix-quick-guide
- Fix syntax error in rst documentation
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:44 PM Revision df3b6fc4 (ceph): Fix syntax error in rst documentation
- Signed-off-by: Luis Pabón <lpabon@redhat.com>
- 06:08 PM devops Bug #9232 (Closed): disk zap doesnt remove the dmcrypt settings on disk
- Well, am really not sure how this is supposed to behave.
deployed a cluster using ceph-deploy and enabled dmcrypt ... - 06:04 PM Revision cef12993 (ceph): doc: Added links. Clarified namespace comments. Added limitations.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:03 PM Revision d817a6a3 (ceph): doc: Minor changes.
- Removed arch-related comments.
Added links to relevant docs.
Moved limitations to user management.
Signed-off-by: Jo... - 06:03 PM Revision 16d946bf (ceph): qa/workunits/hadoop/wordcount: remove bogus rm -r
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:02 PM Revision 5db51d6f (ceph): doc: Added a few comments and links to other relevant docs.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:56 PM Feature #7619 (Resolved): objecter: replace client_lock with fine grained read-write locks
- Merged, commit:4dbc4c412b5b86b1694b47fff02661e332ef4b3c
- 05:49 PM Bug #9211 (In Progress): osdmap blacklist encoding order is nondeterministic
- ...
- 05:38 PM Revision 751b3e26 (ceph): rgw: fix test to identify whether object has tail
- Fixes: #9226
Reported-by: Sylvain Munaut <s.munaut@whatever-company.com>
Backport: firefly
We need to identify wheth... - 05:37 PM Bug #9221 (Resolved): LibRadosTwoPoolsPP.PromoteOn2ndRead
- 10:16 AM Bug #9221 (Fix Under Review): LibRadosTwoPoolsPP.PromoteOn2ndRead
- 09:41 AM Bug #9221: LibRadosTwoPoolsPP.PromoteOn2ndRead
- ...
- 07:05 AM Bug #9221 (Resolved): LibRadosTwoPoolsPP.PromoteOn2ndRead
- ...
- 05:19 PM Revision c7e1b9e1 (ceph): ceph_test_rados_api_tier: make PromoteOn2ndRead test tolerate retries
- If there is an ill-timed connection reset our read could get sent twice.
Weaken our assertion if the read was slow to... - 05:17 PM Revision 8d50abce (ceph): Merge pull request #2311 from onlyjob/master
- Fix FTBFS on alpha due to incorrect check on BLKGETSIZE
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:15 PM Bug #9203: ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limit' failed.
#9054 already existed for the !old_value.deleted issue specifically, renaming this ticket for the issues found by t...- 04:24 PM Bug #9203: ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limit' failed.
- Seen on next:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-24_02:30:02-rados-next-testing-basic-multi/4467... - 05:07 PM Revision 31df59f2 (ceph): erasure-code: add jerasure k=3 m=1 workload
- It validates that http://tracker.ceph.com/issues/9209 is fixed.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 05:07 PM CephFS Bug #8878 (Resolved): mds lock cycle (wip-objecter)
- 04:28 PM Bug #9218: FAILED assert(peering_queue.empty()) during OSD shutdown
Seen on next:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-24_02:30:02-rados-next-testing-basic-multi/44...- 03:26 AM Bug #9218 (Resolved): FAILED assert(peering_queue.empty()) during OSD shutdown
http://pulpito.front.sepia.ceph.com/john-2014-08-25_02:37:45-rados-wip-objecter-testing-basic-multi/448053/
<p...- 04:25 PM Revision 4bff6f34 (ceph): mon: fix occasional message leak after session reset
- Consider:
- we get a message, put it on a wait list
- the client session resets
- we go back to process the messa... - 03:58 PM rgw Bug #9227: test.functional.tests.TestFile fail on dumpling on VPS
- this appears to be a vps thing; suite passes on bare metal.
- 03:55 PM rgw Bug #9227: test.functional.tests.TestFile fail on dumpling on VPS
- The run Sage was referring to is - http://pulpito.ceph.com/teuthology-2014-08-25_08:45:03-upgrade:dumpling-dumpling-d...
- 10:45 AM rgw Bug #9227 (Resolved): test.functional.tests.TestFile fail on dumpling on VPS
- ...
- 03:56 PM CephFS Bug #9216: mds may regard active clients as stale due to slow pg recovery
- I haven't got that far yet, but if I had to guess I'd say it is not about caps, since when this happens, all existing...
- 10:26 AM CephFS Bug #9216: mds may regard active clients as stale due to slow pg recovery
- Interesting. Did you establish the mechanism by which the clients are being stale? Do they have a renew caps request ...
- 01:59 AM CephFS Bug #9216 (New): mds may regard active clients as stale due to slow pg recovery
- I occasionally get fuse and ceph.ko mounts into weird states, and I can generally track them down to the mds's decidi...
- 03:52 PM Revision fc5caa07 (ceph): thrashosds: increase osd revive timeout (75s -> 150s)
- This is needed when running valgrind.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 12a391ea... - 03:52 PM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- ...
- 03:52 PM Revision 12a391ea (ceph): thrashosds: increase osd revive timeout (75s -> 150s)
- This is needed when running valgrind.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:51 PM Bug #9207 (Resolved): osdc/Objecter.cc: 1074: FAILED assert(op->get_nref() > 1)
- Didn't recur with this fix:...
- 03:32 PM Revision 3df93026 (ceph): Merge pull request #2318 from dachary/wip-osd-config
- documentation: update recovery config options defaults
- 02:44 PM Bug #9209 (Pending Backport): osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- 10:06 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- "associated ceph-qa-suite workload":https://github.com/ceph/ceph-qa-suite/pull/107
- 09:22 AM Bug #9209 (Fix Under Review): osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- With "the proposed patch":https://github.com/ceph/ceph/pull/2319 the above workload passes. An inspection of the OSD ...
- 08:07 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- Teuthology must have changed the default recovery chunk for the OSDs at runtime because...
- 07:38 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- "ROUND_UP_TO":https://github.com/ceph/ceph/blob/master/src/include/intarith.h#L31 only works with powers of 2....
- 07:14 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- In the logs "RecoveryOp::IDLE":https://github.com/ceph/ceph/blob/master/src/osd/ECBackend.cc#L494 shows...
- 06:24 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- ...
- 06:07 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- The stripe width for k=6,m=2 is 4224 instead of the 4096 default. It probably breaks a requirement somewhere. ...
- 01:21 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- The teuthology job re-creating the problem is running on teuthology.front.sepia.com in *screen -x -r 17865.loic*
- 01:14 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- The job above with k=2,m=1 passes...
- 01:52 PM Revision 73733ddb (ceph): documentation: update recovery config options defaults
- So they match the values from config_opts.h
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 01:29 PM Revision 97b1916e (ceph): CollectionIndex: Collection name is added to the access_lock name
- The CollectionIndex constructor is changed to accept the coll_t
so that the collection name can be used to form acces... - 01:25 PM Revision 7513b9f7 (ceph): Merge pull request #2275 from ceph/wip-9079
- msg/Accepter: do not unlearn_addr on bind()
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:13 PM Revision 3e85041a (ceph): rgw: admin ops create user API can not determine existing user
- Fixes: #8583
Signed-off-by: Ray Lv <raylv@yahoo-inc.com> - 12:10 PM Revision 469f5ba7 (ceph): Merge pull request #2317 from ashishchandra1/patch-1
- Update python.rst
Reviewed-by: Loic Dachary <loic-201408@dachary.org> - 12:06 PM Revision f7ca1bf1 (ceph): Update python.rst
- Signed-off-by:ashish.a.chandra@ril.com
- 10:29 AM CephFS Bug #9212: mon election delays mds beacon
- 10:21 AM CephFS Bug #9212: mon election delays mds beacon
- Did we identify why it was blacklisted? I don't think we have any tests that should make it that slow or whatever.
- 09:30 AM CephFS Bug #9212 (Rejected): mon election delays mds beacon
- EBLACKLISTED
- 10:24 AM Bug #9188 (Rejected): make check fails for setmaxosd
- 12:52 AM Bug #9188: make check fails for setmaxosd
- make check works after rebase. False alarm.
- 10:13 AM Bug #9140 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.PromoteOn2ndRead (9913 ms)
- 10:06 AM Revision d7fc9a73 (ceph): Merge pull request #2316 from dachary/wip-warning
- rbd: fix signess warning
Reviewed-by: John Spray <john.spray@redhat.com> - 09:43 AM Cleanup #9225 (Closed): check that ROUND_UP_TO is not used with improper rounding values
- Will make ROUND_UP_TO generic instead.
- 09:25 AM Cleanup #9225 (Closed): check that ROUND_UP_TO is not used with improper rounding values
- The "ROUND_UP_TO":https://github.com/ceph/ceph/blob/master/src/include/intarith.h#L31 function requires the rounding ...
- 09:40 AM rgw Bug #9226 (Resolved): rgw: crash when copying specific objects
- as reported on the mailing list...
- 09:24 AM Bug #9176 (Resolved): mon: leaked MMonGetVersion
- 09:04 AM Bug #9224 (Can't reproduce): osd: segv in dlopen
- ...
- 08:54 AM Feature #9222 (New): annotate config options
- Implement http://wiki.ceph.com/Planning/Blueprints/Giant/annotate_config_options
- 08:41 AM Bug #8333: ceph_test_rados_delete_pools_parallel: Received fewer notifies than expected: 0 < 1
- ubuntu@teuthology:/a/sage-2014-08-23_16:02:03-rados-firefly-testing-basic-multi/445025
- 08:32 AM devops Feature #9118 (Resolved): ceph-deploy: Add pre-generated keys to a Monitor
- merged commit b00d1fb into ceph:master
- 07:01 AM Bug #9220: objecter doesn't reconnect watch on interval change w/ same primary
- ubuntu@teuthology:/a/teuthology-2014-08-24_02:30:02-rados-next-testing-basic-multi/446755 too ?
- 06:59 AM Bug #9220 (Resolved): objecter doesn't reconnect watch on interval change w/ same primary
- ubuntu@teuthology:/a/teuthology-2014-08-24_02:30:02-rados-next-testing-basic-multi/446803...
- 06:51 AM Bug #9219 (Resolved): lost_unfound test got ENOENT: i don't have pgid 1.e
- ...
- 06:24 AM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- ubuntu@teuthology:/a/teuthology-2014-08-24_02:30:02-rados-next-testing-basic-multi/446938
- 06:22 AM Bug #9079 (Pending Backport): osd: bad learned_addr during send_boot
- 05:13 AM rgw Bug #8583: rgw: admin ops create user API can not determine existing user
- Added new commit per Yehuda's comments, please check it at: https://github.com/ceph/ceph/pull/1950
- 04:18 AM Revision f651f93b (ceph): msg/Accepter: do not unlearn_addr on bind()
- It is dangerous to set need_addr = true as it means someone may set the
addr to something else (specifically the port... - 01:43 AM Bug #9215 (Resolved): Ceph Firefly 0.80.5 : OSD flapping too frequently
- I have not performed any changes to my cluster yet OSD's has started flapping too frequently ( within seconds ) , the...
- 12:45 AM Revision a67421a5 (ceph): osd: update handle_osd_map call
- I had changed the implementation in Objecter
to avoid a spurious get/put cycle in "osdc/Objecter: fix resource
manage... - 12:34 AM Revision 5d1b295b (ceph): test: fix prematurely released lock in RadosModel
- Should hold this lock while touching context->snaps. Don't
think this has anything to do with #9203 though.
Signed-... - 12:34 AM Revision 28110ff3 (ceph): osdc/Objecter: hold session ref longer in resend
- This is mostly cosmetic: in fact we are getting an extra
ref in _map_session and holding the session lock, so
it's sa... - 12:34 AM Revision 10efe178 (ceph): osdc/Objecter: fix op_cancel on homeless session
- Wrote this block without realizing that op_cancel
takes write lock on session lock, and that operation
is undefined w... - 12:34 AM Revision ef442928 (ceph): common/Timer: fix deadlock in RWTimer::shutdown
- Fixes: #9213
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision e4e7a180 (ceph): librados: prefix msg handler with handle_
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 69612e75 (ceph): librados: refactor watch/notify; return notify error code
- Get rid of a level of intermediate classes with confusing names and put
the notify and notify finish logic in a singl... - 12:34 AM Revision 6f3bb55a (ceph): librbd: handle blacklisting during shutdown
- This was failing the test_lock_fence.sh test due to
a crash during shutdown when the rbd client was blacklisted.
We ... - 12:34 AM Revision e7845862 (ceph): librados: separate ::notify return values
- There is a return code from objecter for committing
the notify linger op, and then later a code in the
CEPH_MSG_WATCH... - 12:34 AM Revision f356d0bb (ceph): librados: fix uninitialized values in notify
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:34 AM Revision 73e5bb0a (ceph): librados: verbose logging in ::notify
- One is interested in knowning specifically which stage
of the operation we are at.
Signed-off-by: John Spray <john.s... - 12:34 AM Revision 2b944085 (ceph): mon/MonClient: ensure !cur_con == cur_mon.empty()
- Keep these in sync.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 6baf36f9 (ceph): librados: shut down monclient after objecter
- The objecter ms_handle_reset may call into monc; shut objecter down first.
Fixes: #9130
Signed-off-by: Sage Weil <sa... - 12:34 AM Revision 1e1ee480 (ceph): client: handle (and ignore) MOSDMap
- To avoid spamming the log.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 213f6524 (ceph): librados: handle (and ignore) MOSDMap; do not leak
- We return true, so we should drop the MOSDMap ref.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 9a5651b3 (ceph): osdc/Objecter: fix resource management
- The refactor introduced various reference leaks, and
lacked cleanup in shutdown.
Things done here:
* Reinstate _rec... - 12:34 AM Revision 8a0382be (ceph): common/RWLock: allow disable lockdep on calls
- To support callers with special cases where they
know they can safely take two locks with the
same name at the same t... - 12:34 AM Revision 2463be5b (ceph): osdc/Objecter: disable lockdep for double lock
- There is a special case in _recalc_linger_op_target
where we lock two sessions at once to transfer an op
between them... - 12:34 AM Revision ad193e1e (ceph): osdc/Objecter: avoid locking two sessions at once
- ... in close_session
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision e7e7fdb9 (ceph): osdc/Objecter: fix ref counts in *Map_Latest
- These contexts were putting before continuing to
use the CommandOp/LingerOp. I added an assert to
reflect that, whic... - 12:34 AM Revision 10a08b82 (ceph): osdc/Journaler: remove unused waitfor_trim
- There was no code path for ever adding contexts to this list.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision e1e28667 (ceph): osdc/Journaler: use finisher for public callbacks
- This is needed because of occasional lock cycles with
external callers doing e.g. write_head.
We do get some weird-l... - 12:34 AM Revision c2728559 (ceph): mds: convert IO contexts
- As of this change, the only thing in the MDS inheriting
directly from Context is MDSContext.
The only files touching... - 12:34 AM Revision 3487f21c (ceph): osdc/Journaler: fix C_RetryRead locking
- Not sure this was ever actually getting used, but
it would have had a problem if it was.
Signed-off-by: John Spray <... - 12:34 AM Revision a0fd5e0c (ceph): mds/Server: fix wait_for_osd_map calls
- These needed a C_OnFinisher and C_IO_Wrapper because they
are called back from the Objecter like an I/O completion.
... - 12:34 AM Revision 13e6c5f2 (ceph): osdc: Add lock to Filer::Probe
- This is necessary now that Objecter can call back
from multiple OSD op completions in parallel: otherwise
we get mult... - 12:34 AM Revision ed1f8078 (ceph): test: add some missing modelines
- Just happened to be editing these and they had
emacs modelines but no vim modelines.
Signed-off-by: John Spray <john... - 12:34 AM Revision 13fbefad (ceph): osdc: remove unused Blinker.h
- Not used anyway, not touched since 2007.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision 63731120 (ceph): common: fix Finisher perf counter
- This was declared as a long running average
but then .dec() was called on it, which
triggers an assertion.
You only ... - 12:34 AM Revision 28e5c03d (ceph): tools: update for Journaler/Objecter interfaces
- Journaler now requires a Finisher: construct one in
MDSUtility.
Objecter now requires separate calls to init() and s... - 12:34 AM Revision 545baf85 (ceph): librados: update Objecter shutdown
- Previously checking for CONNECTED was equivalent to
checking the objecter had been initialized, but since
the separat... - 12:34 AM Revision 52b0ddcf (ceph): librados: fix race on osdmap initialization
- This would cause occasional failures where calls
to lookup_pool immediately after connect() would
fail to find any po... - 12:34 AM Revision 611d0f77 (ceph): librados: avoid unnecessary locks
- Revise wait_for_osdmap to be called outside of RadosClient::lock
and only take the lock if it has to wait for a map.
... - 12:34 AM Revision a786d2d0 (ceph): messages/MWatchNotify: include an error code in the message
- Document the fields, while we are here.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 7a2ec05c (ceph): osd: include ETIMEDOUT in notify reply on timeout
- If a notify operation times out (all watchers to not ACK in time), include
an ETIMEDOUT in the final error message ba... - 12:34 AM Revision 59a97850 (ceph): librados: rename watch/notify callback register functions
- Make it clear these are for watch OR notify, not just watch. I was
confused.
Signed-off-by: Sage Weil <sage@redhat.... - 12:34 AM Revision 1e0387a3 (ceph): client: remove unused C_SnapFlush
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:34 AM Revision 6b55c42a (ceph): client: add missing lock in sync_write_commit
- This would otherwise assert when entering
the objectcacher.
Also add assertions for all the other Contexts
in Client... - 12:34 AM Revision 04d01eb3 (ceph): common: assert non-null ptrs in OnFinisher
- Callers should not be constructing C_OnFinisher
if they have no context to call back.
Signed-off-by: John Spray <joh... - 12:34 AM Revision dcdcfd30 (ceph): include: generalize C_Contexts and C_Gather*
- ... by making them templates so that they can be
used in places that expect a subclass of Context.
The existing name... - 12:34 AM Revision 0860f1a6 (ceph): mds: add MDSContext subclasses
- These allow contexts within the MDS to identify themselves
as either 'internal' contexts (expecting to be called with... - 12:34 AM Revision 4f3b8032 (ceph): mds: Switch to new context types
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:34 AM Revision 85fbddc9 (ceph): mds: rename IO completions with _IO_
- If they are IO operations and need to take mds_lock on finish, label them.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 27aed2d2 (ceph): osdc/Objecter: make homeless_session a pointer
- Have a non-pointer member that's a RefCountedObject
was awkward, e.g. tripping nref==0 assertion during
destruction. ... - 12:34 AM Revision 45b355ea (ceph): mds/MDLog: del stale ref to C_MDS_WroteImportMap
- (class no longer exists)
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision 29533f3d (ceph): mds: fix C_MDC_TruncateFinish locking
- This one needed to take mds_lock, and be invoked
from a finisher.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision 68d14976 (ceph): mds: fix Server::C_MarkEvent locking
- ... it should acquire mds_lock.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:34 AM Revision d8939380 (ceph): mds: update mds_lock handling in Locker contexts
- For some contexts, we expect to be called back from the objecter/filer
on an I/O completion, so we must take mds_lock... - 12:34 AM Revision 0cfaeb91 (ceph): mds/MDLog: enable Journaler finisher
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:34 AM Revision 0a54f005 (ceph): librados: wait for map on create_ioctx failure
- Ensure we have a map so we don't simply complain that a pool doesn't
exists. Only take the lock and wait if we fail ... - 12:34 AM Revision f6cd5fa8 (ceph): mds: use finisher for BootStart contexts
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:34 AM Revision 619ea1fd (ceph): mds: update MDLog._replay_thread for locking
- ... no longer use mds_lock as a guard for condition variable
while waiting for journaler contexts.
Signed-off-by: Jo... - 12:34 AM Revision 2be623b3 (ceph): mds: fix calls to Objecter::wait_for_map
- These were wrong in the earlier commit:
"mds: use lock-safe OSDMap accessors; adjust Objecter wait_for_map call"
Rat... - 12:34 AM Revision db7369bb (ceph): osdc: locking for Journaler
- also remove the lock pointers that JournalPointer load/save
used to require in order to use the objecter.
Signed-off... - 12:34 AM Revision 61a69c80 (ceph): osdc: Use a finisher from Journaler
- Completions from I/O operations (i.e. the objecter) hop
through the finisher twice, because of the three layers of
lo... - 12:34 AM Revision 8c860f94 (ceph): osdc/Objecter: make OSDMap private
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision c7b7bdd9 (ceph): osdc/Objecter: take over ownership of OSDMap
- Instead of taking a pointer to an existing OSDMap in our constructor,
allocate our own, so that we completely own it.... - 12:34 AM Revision 641364e7 (ceph): mds: mark objecter completions with _IO_, take mds_lock
- For any completion we pass directly to Objecter, make sure we take the
mds_lock in finish(), and mark the class with ... - 12:34 AM Revision 2e308123 (ceph): mds: push objecter completions to a Finisher
- Most/all of the MDS completions need to be reentrant (and potentially
call back into the Objecter). Shove them all o... - 12:34 AM Revision 9cb2c815 (ceph): include/Context: add generic C_Lock
- Wrap a callback in a Mutex.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision d3b87fb6 (ceph): client: add a Finisher for the Objecter
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 7262da3a (ceph): client: let Objecter dispatch directly
- Add Objecter as a direct dispatcher. Drop all of the callbacks and
messages we were passing along. Wrap the IO comp... - 12:34 AM Revision 65f90804 (ceph): librados dispatch fix
- 12:34 AM Revision a30f7c63 (ceph): mon/MonClient: fix shutdown typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 56689419 (ceph): osdc/Objecter: ignore messenger events before or after initalized
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 83d983f4 (ceph): mds: allow Objecter to dispatch its own messages
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 62365217 (ceph): librados/RadosClient: remove unused get_pool_name()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision a37fcd85 (ceph): osdc/Objecter: add name-base pool_delete
- Avoid a lookup then delete race.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 1848e990 (ceph): osd/OSDMap: make lookup_pg_pool_name const
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 1145b2cb (ceph): librados: drop osdmap pool name cache
- We now have a rwlock for Objecter; no more need for a separate cache here.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision af15f9e5 (ceph): osd/OSDMap: return const string from get_pool_name
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision f6981129 (ceph): librados: use {get,put}_osdmap_read() accessors
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 5ec56c32 (ceph): client: use Objecter::{get,put}_osdmap_read() interface
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 9f37f3da (ceph): osdc/Objecter: make wait_for_osd_map() locking safe
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision fd179ead (ceph): test_mon_workloadgen: use Objecter::wait_for_osd_map
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 5328f0ae (ceph): client/SyntheticClient: use lock safe OSDMap accessors
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 85bffa30 (ceph): mds: use lock safe OSDMap accessors for TMAP2OMAP check
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision fad36411 (ceph): mds: use lock-safe OSDMap accessors; adjust Objecter wait_for_map call
- We need to handle a race between when we inspect the OSDMap and when we
try to wait for the next map.
Signed-off-by:... - 12:34 AM Revision 0dfe6d6f (ceph): mds/SnapServer: use lock safe OSDMap accessors
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 659909e3 (ceph): osdc/Filer: use lock-safe OSDMap accessors
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision e76cfcc6 (ceph): objecter: don't serialize responses if there's no object name
- This implicitly fixes an issue with the list_objects() being reentrant,
and triggers a lock dependency issue. The bet... - 12:34 AM Revision b4405970 (ceph): objecter: Objecter::Op is refcounted
- Cancellation of lingerin ops collided with ops that we sent osdmap on,
needed to add a refcount for correct object de... - 12:34 AM Revision 9b811a33 (ceph): objecter: split objecter initialization
- Separate objecter initialization to non cluster related work (e.g.,
internal data structures, other registrations), a... - 12:34 AM Revision 795cba94 (ceph): objecter: fix locking
- ms_handle_reset() takes the session lock, needed to be able to call
_kick_requetss() with it held.
Signed-off-by: Ye... - 12:34 AM Revision 8147f9fa (ceph): rwlock: assert on unlock if not locked
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:34 AM Revision a6a88407 (ceph): objecter: take write lock in ms_handle_reset()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:34 AM Revision 2c2e38e7 (ceph): mds: add finisher
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 09a85438 (ceph): osdc/Objecter: make Objecter a Dispatcher
- Note that it's not actually doing it yet, though!
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision 31b0ead9 (ceph): osdc/Objecter: wire up native Dispatcher fast dispatch
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision 0c7dd662 (ceph): osd: let Objecter dispatch directly
- No need for our ObjecterDispatcher wrapper, now!
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision c86d2b92 (ceph): librados: let Objecter dispatch its own messages
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:34 AM Revision d83d0f48 (ceph): osdc/Objecter: add OSDMap accessors that are lock-safe
- Everybody needs to use these to inspect the OSDMap.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:34 AM Revision d0d16056 (ceph): osdc/Objecter: protect pool ops with rwlock
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:33 AM Revision 8f5cb22f (ceph): librados: cancel operation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 452dc9e6 (ceph): timer: fix RWTimer shutdown
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 9e6aedf9 (ceph): objecter: a major refactoring
- Fixes: #7619
Removed the client_lock (that used to pass in as a param) and replaced
it with a read-write lock (compl... - 12:33 AM Revision cdb8899a (ceph): objecter: shard completion_lock
- Object ops responses are sharded, lock hashed by object name. This
guarantees ordering on the same object. Cross obje... - 12:33 AM Revision 94119c46 (ceph): test_mon_workloadgen: fix for new objecter interface
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 1d07ef2f (ceph): rgw: abort early from logging function
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 09af405d (ceph): osd: adapt to new Objecter interface
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision a2f94d2a (ceph): librados: remove warning
- Seems that the current locking scheme is ok. Objecter handles its
locking internally, librados needs to hold its lock... - 12:33 AM Revision c9d4cdeb (ceph): librados: push snap related functions down to objecter
- Need to take appropriate lock.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 12:33 AM Revision dc8494d9 (ceph): librados: call objecter->handle_osd_map() under lock
- The lock is not shared with the objecter anymore so we need to call
it under this lock, otherwise we're going to race... - 12:33 AM Revision 517f10d0 (ceph): librados: adapt to new objecter interface
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision e2fa0cf2 (ceph): librados: don't hold client lock in certain operations
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision aac22428 (ceph): librados: don't hold lock in dispatch()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision bcc69edb (ceph): mds: adapt to new objecter interface
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 94e18093 (ceph): time: create RWTimer
- a timer implementation that uses RWLock
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 12:33 AM Revision 4c6eb6e7 (ceph): client: adapt to new objecter interface
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 92615ea9 (ceph): common/RWLock: track read/write locks via atomics for assertion checks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 8f9a9dbb (ceph): common/RWLock: check return values
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 3a399ea8 (ceph): common/RWLock: add get()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 91c938f5 (ceph): common/RWLock: add explicit unlock() to *Lockers
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:33 AM Revision 33ecf3d1 (ceph): common/RWLock: add lock context
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
08/24/2014
- 11:40 PM Revision 74ce4f26 (ceph): rbd: fix signess warning
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 10:50 PM Revision d848a400 (ceph): Merge pull request #2138 from xiaoxichen/fix_crush_ruleset
- mon/OSDMonitor : Use user provided ruleset for replicated pool
Reviewed-by: Loic Dachary <loic-201408@dachary.org> - 07:49 PM Revision f7c0001a (ceph): common: remove spurious uint32_t in buffer.c
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 04:10 PM Feature #8343 (Closed): please enable data integrity checking (by default) / silent data corruption
- 04:06 PM Bug #8349 (Resolved): env-vs-args unittest is racy
- Fixed by https://github.com/ceph/ceph/commit/3230060f07c738383cc1034a99d60d2ad369560f
- 03:32 PM Support #8462: related to integrity of objects
- 03:12 PM Feature #7238 (Fix Under Review): erasure code : implement LRC plugin
- The rados test work (no thrashing).
- 02:57 PM Support #8310 (Closed): Most pgs stuck stale, no osds reporting them, repair ineffective
- 09:25 AM CephFS Bug #9212 (Won't Fix): mon election delays mds beacon
- ubuntu@teuthology:/a/teuthology-2014-08-22_23:04:01-fs-master-testing-basic-multi/444359...
- 08:36 AM Bug #9211 (Resolved): osdmap blacklist encoding order is nondeterministic
- ...
08/23/2014
- 05:00 PM Bug #9203: ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limit' failed.
- fwiw the reproducer hits a crash on firefly, but not emperor or dumpling. A fair bit changed in ceph_test_rados for ...
- 03:13 PM Bug #9203: ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limit' failed.
So it turns out that ceph_test_rados is also crashy on master, as I found when I took my reproducer for this issue ...- 03:53 PM rbd Bug #9210 (Resolved): osdc/ObjectCacher.cc: 529: FAILED assert(i->empty()) on fencing test shutdown
- ...
- 12:41 PM Revision 6ad8e61a (ceph): Fix FTBFS on alpha due to incorrect check on BLKGETSIZE
- Ceph FTBFS on Alpha with:
~~~~
libtool: compile: g++ -DHAVE_CONFIG_H -I. -D__CEPH__ -D_FILE_OFFSET_BITS=64 -D_REENT... - 11:50 AM Feature #7238: erasure code : implement LRC plugin
- 11:25 AM Feature #7238 (Fix Under Review): erasure code : implement LRC plugin
- Although thrashing tests using an LRC pool fail, I believe this is due to the size of the pool rather than the plugin...
- 11:29 AM Bug #9209: osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- The same YAML file run against firefly 0.80.5-171-gca3ac90-1trusty instead of master succeeds.
- 11:23 AM Bug #9209 (Resolved): osd/ECUtil.h: 66: FAILED assert(offset % stripe_width == 0)
- Using ...
- 12:39 AM Revision 0ec5bd1a (ceph): mplement ceph.created_pool
- ceph.created_pool allows the user (via yaml lines) to add pools
that the ceph_manager knows about.
Fixes: 9091
Signe...
08/22/2014
- 11:52 PM Revision 25542430 (ceph): mds/Server: rename perfcounters
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:31 PM Revision b0cc869a (ceph): mds: rename a bunch of metrics
- Also clean out a few that were unused and some dead code.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:14 PM Revision 31ef1a97 (ceph): mds: set l_mds_req on client request
- This is one input for the load balancer.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:28 PM Revision 9e539723 (ceph): set boto timeout, too, for s3tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:28 PM Revision 9d466aa1 (ceph): tasks/s3tests: push boto config with idle_timeout setting
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:26 PM rgw Bug #9208 (Resolved): rgw: civetweb does not drain request buffer correctly
- When radosgw returns an early error without reading the request content, we need civetweb to drain the buffer so that...
- 06:10 PM Revision 8d406001 (ceph): Merge branch 'wip-weak-refs'
- 06:08 PM Revision 06682c4b (ceph): vstart.sh: debug rgw = 20 on -d
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:08 PM Revision 8a212170 (ceph): Merge pull request #2292 from lpabon/rgw-doc
- vstart.sh to enable support for simple Rados
Tested-by: GWabhishek.lekshmanan@gmail.com - 05:24 PM Subtask #6478 (Rejected): ErasureCode : XOR plugin
- This has been obsoleted by the work on the ISA plugin.
- 05:22 PM Feature #7238: erasure code : implement LRC plugin
- Fixed a bug that made the plugin incorrectly claiming it could not recover when the last OSD was out, running tests a...
- 05:05 PM Revision 850242ca (ceph): rgw: separate civetweb log from rgw log
- The civetweb log now is independent from the rgw log.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:05 PM Revision 00c677b4 (ceph): rgw: use a separate callback for civetweb access log
- Access log is separate from the regular civetweb logging. Also, changed
the log level for the regular logging as it's... - 04:17 PM Revision f246b569 (ceph): common/shared_cache: dump weak refs on shutdown
- Before asserting, dump what the refs are along with the counts.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:13 PM Revision 6f15a4ca (ceph): Merge pull request #2304 from majianpeng/fix1
- small bug fix for journal
Reviewed-by: Sage Weil <sage@redhat.com> - 04:04 PM Revision 6cf583c4 (ceph): common/shared_cache: take a cct
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:46 PM Revision 997f766a (ceph): Merge pull request #2291 from ceph/wip-fingerprint
- mon: add a unique clsuter fingerprint
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 03:17 PM Revision d6aa7833 (ceph): Merge pull request #2307 from dmsimard/crushdoc
- Doc: Add config option to turn off crush update
Reviewed-by: Loic Dachary <loic-201408@dachary.org> - 03:09 PM Bug #9207 (Resolved): osdc/Objecter.cc: 1074: FAILED assert(op->get_nref() > 1)
- ubuntu@teuthology:/var/lib/teuthworker/archive/john-2014-08-22_10:24:47-rados-wip-objecter-testing-basic-multi/441988...
- 03:04 PM rgw Bug #9206 (Resolved): rgw: cross rgw message headers filtered by apache 2.4
- apache 2.4 filters out header fields that have underscores in them. Need to convert underscores into dashes.
- 03:00 PM Revision 2ba081d4 (ceph): Merge pull request #2288 from xiaoxichen/fix_add_simple_ruleset
- CrushWrapper: pick a ruleset same as rule_id
Reviewed-by: Loic Dachary <loic-201408@dachary.org> - 02:55 PM Revision 2c274851 (ceph): Doc: Add config option to turn off crush update
- Signed-off-by: David Moreau Simard <dmsimard@iweb.com>
- 02:52 PM Bug #9205 (Resolved): osd: notify ops reordered
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-21_11:40:02-upgrade:dumpling-x:stress-split-master...
- 01:23 PM devops Feature #9136 (Resolved): ceph-deploy: use pre-existing ceph.conf
- merged commit 2781538 into ceph:master
- 01:22 PM Revision 78e84f34 (ceph): CrushWrapper: pick a ruleset same as rule_id
- Originally in the add_simple_ruleset funtion, the ruleset_id
is not reused but rule_id is reused. So after some add/r... - 12:44 PM devops Feature #9118 (Fix Under Review): ceph-deploy: Add pre-generated keys to a Monitor
- Pull request opened https://github.com/ceph/ceph-deploy/pull/235
- 12:02 PM Bug #9203: ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limit' failed.
- Does not reproduce very often, but eventually caught in the act with debug turned up.
The oid in the asserting ope... - 06:39 AM Bug #9203 (Resolved): ceph_test_rados: ObjectDesc::iterator::advance(bool): Assertion `pos < limi...
http://pulpito.front.sepia.ceph.com/john-2014-08-22_02:21:21-rados-wip-objecter-testing-basic-multi/440722/
http:/...- 11:28 AM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- added patches to master that will dump the weak_refs on shutdown
- 06:32 AM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- http://pulpito.front.sepia.ceph.com/john-2014-08-22_02:21:21-rados-wip-objecter-testing-basic-multi/440850/
http://p... - 06:24 AM Bug #7995 (New): osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- This is happening again:
http://pulpito.front.sepia.ceph.com/john-2014-08-22_02:21:21-rados-wip-objecter-testing-b... - 11:15 AM Bug #8736: thrash and scrub combination lead to error
- This needs to be prioritized.
Confirmed, logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-21_11:... - 10:30 AM Revision 18357782 (ceph): needs network or it will not start if enabled
- example error message: "unable to find any IP address in networks: 10.2.27.0/25", so the service wont start
- 10:19 AM Bug #8985: "[WRN] map e9 wrongly marked me down" in upgrade:dumpling-x-firefly---basic-vps suite
- 06:36 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- The stack trace created by the minimal script is different from the one reported above, but it fails at the same poin...
- 05:51 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- The problem does not show if waiting after the object is inserted. It is a race condition....
- 05:25 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- For the problem to show the file being removed has to be the primary.
- 05:06 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- Even simpler and does not require root privileges...
- 04:56 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- The following reproduces it reliably on my laptop:...
- 03:47 AM Fix #8914 (In Progress): osd crashed at assert ReplicatedBackend::build_push_op
- Thanks for the update, will try again :-)
- 05:33 AM Revision 8c69054b (ceph): osd: make coll_t::META static to each file
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 02:57 AM CephFS Bug #4545: error creating empty object store. Invalid argument.
- i maybe found the problem.
before you mkcephfs,you should ensure the dir(/var/lib/ceph/osd/ceph-0) empty.
once i wr... - 02:32 AM Bug #9202 (Can't reproduce): Performance degradation during recovering and backfilling
- From recent test and analysis, we find slow requests mainly happen at 2 patterns during recovering and backfilling.
... - 01:05 AM Revision 5234abfa (ceph): Merge pull request #2273 from dachary/wip-mailmap
- mailmap updates
- 12:48 AM Revision 5f1e1e0e (ceph): Merge remote-tracking branch 'gh/wip-filejournal'
- Reviewed-by: Sage Weil <sage@redhat.com>
Tested-by: Mark Kirkwood <mark.kirkwood@catalyst.net.nz>
08/21/2014
- 11:39 PM Revision 825212a5 (ceph): Merge pull request #104 from dachary/wip-8933-rgw-erasure-code-profile
- rgw: add erasure_code_profile configuration
- 11:27 PM Revision e5c5bcf9 (ceph): rgw: add erasure_code_profile configuration
- If erasure_code_profile is present at the same leve as ec-data-pool, it
is used to override the default hard coded pr... - 11:12 PM rgw Feature #8911: RGW doesn't return 'x-timestamp' in header which is used by 'View Details' of Open...
- Thanks Luis... actually its a new feature request not a bug. Since we want one to one headers mapping between Swift a...
- 10:24 PM Revision 493577bf (ceph): mds: fix crash killing sessions without conn
- Bug was introduced in 54eca56695 (mds: use Connection::mark_down()).
Used to call SimpleMessenger::mark_down, which ... - 10:22 PM Revision dcf8c037 (ceph): mds: logging in SessionMap
- (move definitions to .cc to get it)
Signed-off-by: John Spray <john.spray@redhat.com> - 10:09 PM Revision 5c29ae6b (ceph): tasks/ceph: add ceph.stop task
- So that we can explicitly stop daemons on demand. Useful
for MDS tool tests that want the MDS daemons not to be runn... - 10:09 PM Revision 1e7bfb84 (ceph): tasks/workunit: fix log message
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:09 PM Revision 8211d83d (ceph): tasks/ceph_fuse: enable umounting from config
- This is for any test config that needs to run
some workunit with clients unmounted. It allows
you to go toggle the m... - 10:09 PM Revision bb52a973 (ceph): tasks/mds_client_recovery: network freeze test
- This is about testing the CephFS client's handling
of losing connectivity to the MDS.
Fixes: #7810
Signed-off-by: J... - 10:09 PM Revision d001cc27 (ceph): tasks/mds_client_recovery: use existing clients
- This will enable using .yaml changes to switch this
guy over to use kcephfs client once the teuthology
code around it... - 10:09 PM Revision 1855e094 (ceph): suites/fs: add client recovery
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:09 PM Revision 83a745d2 (ceph): gitignore: ignore vim temp files
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:09 PM Revision 0d37b8e4 (ceph): suites/fs: add cephfs_journal_tool test
- Fixes: #4886
Signed-off-by: John Spray <john.spray@redhat.com> - 10:06 PM Revision 82ac61fc (ceph): Merge remote-tracking branch 'gh/wip-lttng'
- 10:05 PM Revision 01ce2497 (ceph): Revert "Merge pull request #2253 from adamcrume/wip-lttng"
- This reverts commit 5b9ade5058f72116eb3dc920f442361c2a33b46b, reversing
changes made to b0aa846b3f81225a779de00100e15... - 09:58 PM Revision 0b1a4328 (ceph): Merge pull request #2301 from ceph/wip-9176
- mon: fix occasional memory leak; clean up dispatch return codes
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 09:11 PM rgw Bug #9201 (Resolved): rgw: bad object with different pool alignment
- http://qa-proxy.ceph.com/teuthology/sage-2014-08-21_17:03:27-rgw-master-testing-basic-multi/440046/teuthology.log
... - 08:43 PM Revision 7e4b525e (ceph): Merge pull request #2274 from ceph/wip-9144
- filestore: fix force_sync race with mount + umount + mount
Reviewed-by: David Zafman <dzafman@redhat.com> - 08:14 PM Revision 5b9ade50 (ceph): Merge pull request #2253 from adamcrume/wip-lttng
- RBD-replay
Reviewed-by: Sage Weil <sage@redhat.com> - 08:10 PM Revision 3ced97b2 (ceph): mon: make dispatch(), _ms_dispatch() void
- They always return true.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:07 PM Revision 610f4be5 (ceph): mon: always process the message in dispatch
- Nobody should be chained after teh mon, so we can safely drop any message
we don't understand.
Signed-off-by: Sage W... - 08:05 PM Revision 19df386b (ceph): mon: fix occasional message leak after session reset
- Consider:
- we get a message, put it on a wait list
- the client session resets
- we go back to process the messa... - 06:14 PM Revision 675b0042 (ceph): mon: add a cluster fingerprint
- Generate it on cluster creations with the initial monmap. Include it in
the report. Provide no way for this uuid to... - 06:14 PM Revision b245d600 (ceph): mon: generate cluster_fingerprint if null
- This triggers after an upgrade of a legacy cluster that has no fingerprint.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:57 PM Revision 07ab36f9 (ceph): lttng: Remove tracing-specfic local variables when lttng disabled
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 9673e2f3 (ceph): lttng: Split --with-lttng and --with-babeltrace options
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 76160925 (ceph): rbd-replay: Add unit test for Ser
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 552c4b44 (ceph): rbd_replay: Add unit test for batch_unreachable_from
- This requires a fair amount of code reorganization, since the types in
the function signature were previously not in ... - 05:57 PM Revision 7ff6ed11 (ceph): lttng: Only require lttng for Fedora >= 20 and RHEL == 6 for RPM distros
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 861e6a39 (ceph): lttng: Update packaging
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision a35b5d2c (ceph): lttng: Don't build trace headers when lttng is disabled
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 42d633f3 (ceph): lttng: Remove -lboost_regex from unit test
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision d1064bff (ceph): lttng: Fix build error on 32-bit systems
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e419ba60 (ceph): lttng: Don't build trace libraries when lttng is disabled
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 84bfe910 (ceph): lttng: Test for sane lttng-gen-tp
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 9c388f08 (ceph): lttng: Check that the main babeltrace header is present
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 141f37a6 (ceph): lttng: Check for babeltrace when autoconfiguring lttng
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 230c5b8e (ceph): lttng: Only install rbd-replay-prep when enabled
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 3f1917c0 (ceph): lttng: Add informational messages to configure.ac
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e18748ed (ceph): rbd-replay: Add man page, and add binaries to Debian packaging
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 0f052f8c (ceph): rbd-replay: Convert prep-for-replay.py to rbd-replay-prep.cc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 0cd2651c (ceph): rbd-replay: Add man page and package binaries for rbd-replay-prep
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e555867e (ceph): rbd-replay: Move tracepoints from internal.cc to librbd.cc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 18c081e5 (ceph): rbd-replay: Remove extent tracepoints and inline extents
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 660f1d68 (ceph): rbd-replay: Fix bug in rbd-replay-prep, Thread::issued_io with wrong IO
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 8d71b6c1 (ceph): lttng: Remove tracing from libcommon
- This is a short-term fix for issues caused by tracepoints in libcommon.
Code crashes at runtime if the same tracepoin... - 05:57 PM Revision d4186fee (ceph): lttng: Support --with-lttng=check
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision edddb3fa (ceph): lttng: Fix "make distcheck"
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision fed22f49 (ceph): lttng: Add distro packaging
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e22f59f7 (ceph): rbd-replay: Support replaying partial traces
- Tracing may start after the application is started, and image open calls
may missed. To support replaying these trace... - 05:57 PM Revision 684643a3 (ceph): lttng: Fix ceph_ctf_stringp
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision c40ac911 (ceph): rbd-replay: Use standard image@snap instead of image/snap
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 612e85b0 (ceph): rbd-replay: Add rbd_replay::rbd_loc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 6f79f132 (ceph): rbd-replay: Switch ImageNameMap to using rbd_loc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision c78f994e (ceph): rbd-replay: Switch ImageNameMap from regex to plain string matching
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision f64776ac (ceph): rbd-replay: Fix compiler warning in unit tests
- Was getting:
test/test_rbd_replay.cc:44:3: warning: converting ‘false’ to pointer type for argument 1 of ‘char testin... - 05:57 PM Revision 8b9f8878 (ceph): rbd-replay: Remove boost_regex from LIBADD and LDADD
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 63273a28 (ceph): lttng: Replace Boost dependencies with custom string code
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision f5272d57 (ceph): rbd-replay: Remove outdated message that says regexes are used
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 4109879f (ceph): lttng: Default to not storing buffer content
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 5365a3e6 (ceph): rbd-replay: Add assertions
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 2a66e09a (ceph): rbd-replay: Add --pool option
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 2eb6ea33 (ceph): rbd-replay: Add --map-image option for image name mapping
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision c888a898 (ceph): lttng: Fix 'make check' by setting up fake HOME
- If the HOME variable is not set, LTTng complains, and the extra output
fails to match what the tests expect, so they ... - 05:57 PM Revision 2a11a5cc (ceph): lttng: Disable LTTng by default, add --with-lttng configure option
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision c4939f9a (ceph): lttng: Preload liblttng-ust-fork.so in TESTS_ENVIRONMENT
- This adds LD_PRELOAD=liblttng-ust-fork.so to TESTS_ENVIRONMENT.
This prevents lttng from complaining when processes a... - 05:57 PM Revision 8a67647a (ceph): rbd-replay: Add unit tests
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 0d822225 (ceph): rbd-replay: Use non-zero fake data
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision c651bf20 (ceph): rbd-replay: Support writing Actions to ostreams
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision dd8ad8e8 (ceph): rbd-replay: Check that return values are non-negative
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 2db768f0 (ceph): rbd-replay: Fix memory leak in PendingIO
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision d4697bca (ceph): doc: Add usage comment to librbd::RBD::AioCompletion
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision ffc9d05b (ceph): rbd-replay: Add --latency-multiplier option to usage statement
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 25d3d422 (ceph): rbd-replay: Hash completions across multiple mutexes to reduce contention
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e7bf657e (ceph): rbd-replay: Clean up prep-for-replay.py
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 4c360ce9 (ceph): rbd-replay: Fix examples/rbd-replay/replay
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 3dc8443c (ceph): rbd-replay: Add --read-only flag
- Removes ignoreWrites flag in prep-for-replay.py
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 05:57 PM Revision 1540f2fd (ceph): rbd-replay: Fix async writes in prep-for-replay.py
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 0421b692 (ceph): rbd-replay: Add command-line arguments to prep-for-replay.py
- Includes:
--print-on-read
--print-on-write
--window
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 05:57 PM Revision e9b39d91 (ceph): tracing: instrument filestore
- This adds objectstore tracepoints for the filestore. It'd be nice to add
these to the objectstore interface some how ... - 05:57 PM Revision f6257758 (ceph): lttng: Add more tracing to librbd
- Includes:
- aio_complete
- aio_discard
- aio_flush
- aio_get_return_value
- aio_is_complete
- aio_read
- aio_wait_for... - 05:57 PM Revision 4c4289c2 (ceph): lttng: Add rbd-replay
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 16b75623 (ceph): rbd-replay: Switch logging from cout to dout
- To enable logs, we also have to use global_init to parse our
command-line args, so we now have other standard Ceph go... - 05:57 PM Revision 4eac5187 (ceph): Add assertf macro
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 9452423f (ceph): rbd-replay: Add rbd_replay subsystem
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision b99f8199 (ceph): rbd-replay: Bugfix: ensure PendingIOs are added before they're removed
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 80110160 (ceph): rbd-replay: Printing pending IOs when worker threads waiting to die
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision f2228c0c (ceph): rbd-replay: Change Worker::m_pending_ios from vector to map
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision eec93823 (ceph): rbd-replay: Print "Still waiting for" more judiciously
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e312be61 (ceph): lttng: Trace ReplicatedPG::do_osd_ops
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision fcf49257 (ceph): lttng: Add tracing-common.h
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 10a476ad (ceph): examples: Add example for the librados C API
- Simply copied and modified the C++ API example.
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 05:57 PM Revision 16cd0744 (ceph): lttng: Trace librados C API
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 012ff295 (ceph): lttng: Prevent creation of incorrect .o files when generating from .tp
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 00b2ec6f (ceph): lttng: Prevent deletion of tracing-common.h when cleaning
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision e1e157fb (ceph): lttng: Split up libtracepoints
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 772148e2 (ceph): lttng: Remove 'ver' from trace in code for CEPH_OSD_OP_NOTIFY
- 'ver' is obsolete and variable exists only for proper deserialization
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 05:57 PM Revision d0834bb8 (ceph): lttng: Basic tracing of librbd
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 115cfb3a (ceph): tracing: bootstrap lttng-ust with mutex events
- See src/tracing/README.md
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 05:57 PM Revision 7fa513ea (ceph): lttng: trace mutex::unlock
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:57 PM Revision 3ac99e3f (ceph): lttng: add pg and osd tracepoints
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:57 PM Revision 915a6a64 (ceph): lttng: Check for lttng/tracepoint.h when configuring
- 05:57 PM Revision 33b87f92 (ceph): tracing: automake-ify tracepoint generation
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:57 PM Revision ae599464 (ceph): lttng: Trace OpRequest
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:57 PM Revision 1802bc25 (ceph): lttng: Add rmw_flags to tracepoint in PG::queue_op
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 05:28 PM Bug #9153 (Resolved): erasure-code: jerasure_matrix_dotprod segmentation fault due to package upg...
- 05:14 PM Revision ca3ac907 (ceph): Merge pull request #2298 from dachary/wip-9153-jerasure-upgrade-firefly
- erasure-code: preload the jerasure plugin variant (sse4,sse3,generic)
Reviewed-by: Sage Weil <sage@redhat.com> - 04:55 PM Feature #8147 (Resolved): osd: make split automatically trigger scrub
- 04:49 PM Bug #8998 (Resolved): osd: SEGV in OSD::heartbeat()
- no backport needed; this happened bc update_osd_stats() was in OSDService but still using hte other dout macro, but f...
- 04:49 PM rgw Feature #9200 (Resolved): rgw: log civetweb access
- Apache has an access log, civetweb has one too, however we need to incorporate it into our logging system.
- 04:44 PM CephFS Bug #5762 (Resolved): teuthology: Failed MPI runs lead to a hung test instead of a failure
- 03:38 PM Revision 50fd1fcf (ceph): use 'mon create-initial' always
- But don't error if it fails, as this would mean that the monitors
are just taking longer to form quorum. Go and try t... - 03:38 PM Revision 182f22fe (ceph): ignore errors on informational service status
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 5b946e1a6df8b7f80001f5176435eb36b12... - 03:29 PM Feature #8639: mon: dispatch messages while blocked waiting for IO
- 03:29 PM Feature #7516 (Resolved): mon: reweight-by-pg
- 03:27 PM Fix #9199 (Resolved): librados: watch linger pings need to verify pg mapping hasn't changed
- at the same time, osds might want to push osdmap incrementals to client sessions with watchers to expedite things ...
- 03:22 PM Feature #9198 (Resolved): librados: notify callback includes gid of notifier
- 03:21 PM Feature #9197 (Resolved): librados/osd: notify reply payload
- 03:21 PM Revision e870fd09 (ceph): os/FileJournal: For journal-aio-mode, don't use aio when closing journal.
- For jouranl-aio-mode when closing journal, the write_finish_thread_entry may exit before
write_thread_entry. This cau... - 03:21 PM Fix #9196 (Resolved): librados: watch_check() to synchronous verify we haven't missed notifies
- 03:21 PM Fix #9195 (Resolved): librados: issue watch callback on (possibly) missed notifies
- 03:20 PM Fix #9194 (Resolved): librados/osd: watch reconnect needs to be exclusive to detect possibly miss...
- 03:18 PM Linux kernel client Bug #8806: libceph: must use new tid when watch is resent
- the watch resend needs to use a new tid to avoid the dup op detection in the osd. this is how librbd avoids this pro...
- 03:16 PM Revision 5765fde1 (ceph): Merge pull request #102 from ceph/9171
- ignore errors on informational service status
- 03:15 PM Revision 54870dcc (ceph): Merge pull request #103 from ceph/9172
- use 'mon create-initial' always
- 02:55 PM Bug #9176 (Pending Backport): mon: leaked MMonGetVersion
- 01:08 PM Bug #9176 (Fix Under Review): mon: leaked MMonGetVersion
- https://github.com/ceph/ceph/pull/2301
- 02:49 PM rgw Bug #9160: rgw failures with 'NoneType' object has no attribute 'get_contents_as_string'
- http://pulpito.front.sepia.ceph.com/sage-2014-08-19_15:19:41-rgw-master-testing-basic-multi/435812/
http://pulpito.f... - 02:43 PM rgw Bug #9160: rgw failures with 'NoneType' object has no attribute 'get_contents_as_string'
- http://pulpito.front.sepia.ceph.com/john-2014-08-20_19:21:46-rgw-wip-objecter-testing-basic-plana/438545/
- 02:03 PM Revision 70a1f18a (ceph): use 'mon create-initial' always
- But don't error if it fails, as this would mean that the monitors
are just taking longer to form quorum. Go and try t... - 01:56 PM Bug #9144 (Pending Backport): filestore: commit triggered during journal replay
- 01:44 PM Revision 5b946e1a (ceph): ignore errors on informational service status
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 01:21 PM Bug #9193: notify does not return an error code on timeout
- https://github.com/ceph/ceph/pull/2302
- 01:20 PM Bug #9193 (Resolved): notify does not return an error code on timeout
- commit:7c7bf5fee7be397ef141b947f532a2a0b3567b42
There is simply no error code passed back to the caller; the API c... - 01:10 PM Bug #9150: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.aligned_logical_offset...
- suspect this and #9135 to be a ghost due to misbehaving underlying fs
- 01:09 PM Bug #9145 (Resolved): recursive lock of CollectionIndex::access_lock (52)
- 01:07 PM Revision a66a4931 (ceph): os/FileJournal: Only using aio then alloc the related resources.
- If define HAVE_LIBAIO, it alloc related resouces. But itt don't check whether
using aio mode. Only using aio it alloc... - 12:51 PM Bug #9182 (Need More Info): osd deadlock after ms_handle_reset
- 12:50 PM Bug #9181 (Need More Info): Osd: segv in OpTracker::unregister_inflight_op
- no log, core isn't giving me good info :(
- 12:41 PM Revision 8d7e77b9 (ceph): erasure-code: preload the jerasure plugin variant (sse4,sse3,generic)
- The preloading of the jerasure plugin ldopen the plugin that is in
charge of selecting the variant optimized for the
... - 12:34 PM Bug #8885 (Can't reproduce): SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- 12:09 PM devops Feature #9136 (Fix Under Review): ceph-deploy: use pre-existing ceph.conf
- Pull request opened https://github.com/ceph/ceph-deploy/pull/234
- 12:07 PM devops Bug #9185: incorrect Centos 6.5 fastcgi package
- ok, the idle timeout is working fine.. i can pause the radosgw process (kill -STOP) and curl will block for well over...
- 10:27 AM devops Bug #9185 (In Progress): incorrect Centos 6.5 fastcgi package
- 09:52 AM devops Bug #9185: incorrect Centos 6.5 fastcgi package
- (09:51:57 AM) sagehm@newdream.net/montreal: mod_fastcgi-2.4.7-1.ceph.el6.x86_64
(09:52:15 AM) sagehm@newdream.net/mo... - 11:43 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Does fio complete eventually? Are there any other hung tasks in dmesg? A task blocking for more than 120 seconds is...
- 11:38 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- I apply http://gitbuilder.ceph.com/kernel-deb-precise-x86_64-basic/ref/wip-request-fn/linux-image-3.16.0-ceph-00037-g...
- 11:37 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Ok, I've applied the "..." with Kernel 3.16.0 and the error continues:
...
Aug 21 14:38:45 mail02-old kernel: [ 7... - 10:19 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Eric is correct, the fix isn't in 3.16 stable yet, and unfortunately won't be in 3.15 at all - Linus pulled it into h...
- 10:10 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- The fix looks like it made it into 3.17rc1. I have been testing this kernel since Sunday, and have not triggered the ...
- 09:31 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Upgrade to kernel: 3.16.0 and got the same problem:
...
[ 70.858716] Key type ceph registered
[ 70.858800] l... - 11:18 AM Linux kernel client Bug #9192 (New): krbd: poor read (about 10%) vs write performance
- We started testing the 3.17rc1 kernel over the weekend, as it is the only Linus
released kernel that has the fix fo... - 10:05 AM devops Feature #5773 (In Progress): ceph-deploy: should add more tests to ceph-deploy task
- 09:55 AM CephFS Bug #9152 (In Progress): mds: beacon needs to not take mds_lock
- wip-9152
- 09:50 AM CephFS Bug #9177: ceph-fuse: failing MPI mdtest runs
- The compiler is spitting out a warning about getcwd -- no evidence that that's what it's actually hitting in this ins...
- 08:53 AM CephFS Bug #9177: ceph-fuse: failing MPI mdtest runs
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-20_23:04:01-fs-next-testing-basic-multi/439228/
- 08:29 AM CephFS Bug #9177: ceph-fuse: failing MPI mdtest runs
- How did you track it down to getcwd? If that is the issue there are a bunch of avenues of attack here, and we should ...
- 06:31 AM CephFS Bug #9177: ceph-fuse: failing MPI mdtest runs
- mdtest has a getcwd call into an unzeroed buffer that it doesn't check the error of. If fuse is failing the getcwd f...
- 09:46 AM devops Bug #9190 (Resolved): idle times out do not work on ubuntu precise
- This maybe similar to #9185
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-21_08:29:18-upgrade... - 08:26 AM Bug #9188: make check fails for setmaxosd
- "make check" is passing on our gitbuilders (http://ceph.com/gitbuilder.cgi). Try updating and running it again? If th...
- 02:28 AM Bug #9188 (Rejected): make check fails for setmaxosd
- make check fails for setmaxosd. This is after a recent change in setmaxosd behavior to disallow shrinking of OSDs. He...
- 07:49 AM Revision c8e2b89c (ceph): os/FileJournal: Tune the judge logic for read_header.
- When reading journal-header, it should firstly check the result of
pread and then do decoce operation.
Signed-off-by... - 06:56 AM CephFS Bug #9151 (In Progress): mds should log/error/warn when segments are NOT getting trimmed
- 05:56 AM CephFS Feature #9189 (Resolved): Expose client identifying metadata to MDS, e.g. hostname
Currently, when doing e.g. a "session ls" on an MDS's admin socket, we get client IDs and IP addresses. It would b...- 05:35 AM CephFS Bug #9173 (Fix Under Review): Crash in Server::_session_logged
https://github.com/ceph/ceph/pull/2297- 05:27 AM Revision 389ad614 (ceph): added a test with erasure_code_profile parameters
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 03:50 AM Revision fdbab468 (ceph): Fix set_alloc_hint op cause KeyValueStore crash problem
- Now KeyValueStore doesn't support set_alloc_hit op, the implementation of
_do_transaction need to consider decoding t... - 03:28 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- Missed a step to mention.
before i did a repair on the primary osd; i aslo did a scrub
#:/build/ceph-firefly84/sr... - 03:17 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- Hi Loic,
please find below the steps to reproduce the issue.
@*#:/build/ceph-firefly84/src# ./ceph -v
*** DEVE... - 01:09 AM rgw Bug #9155: Swift Subuser - 403 Forbidden - during upload/post
- made a comment on your proposed fix.
08/20/2014
- 10:09 PM Revision b0aa846b (ceph): Merge pull request #2295 from dachary/wip-9153-jerasure-upgrade
- erasure-code: do not preload the isa plugin
Reviewed-by: Sage Weil <sage@redhat.com> - 09:10 PM Revision 3ed8c682 (ceph): erasure-code: do not preload the isa plugin
- Because it's not built for all architectures and distributions.
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 09:02 PM devops Bug #9187 (Resolved): osds down after fresh deploy in master branch of ceph
- 09:02 PM devops Bug #9187: osds down after fresh deploy in master branch of ceph
- thsi si fixed later today. it was the isa preload thing:
2014-08-20 21:04:58.845739 7f7369af2780 -1 load: jerasur... - 04:37 PM devops Bug #9187 (Resolved): osds down after fresh deploy in master branch of ceph
- ceph version 0.84-367-gf71c889
test setup: mira023
ceph-deploy version: 1.5.11
created 4 osds, with a combi... - 08:48 PM Bug #9180 (Resolved): keyvaluestore: bad op 2563
- done, commit:fdbab46852e74d405b5c747da98564a5866ec8a7 . thanks!!
- 08:07 PM Bug #9180: keyvaluestore: bad op 2563
- We need to backport commit c08adbc98ff5f380ecd215f8bd9cf3cab214913c(https://github.com/ceph/ceph/commit/c08adbc98ff5f...
- 10:39 AM Bug #9180 (Resolved): keyvaluestore: bad op 2563
- ...
- 08:11 PM Revision 4c2ae691 (ceph): add pom.xml so to deploy the libcephfs to maven repository.
- to build a jar, version=0.80-rc1-2008-gf71c889 mvn package -Dversioin=;
and mvn deploy command will deploy the jar to... - 08:08 PM Revision 54aa5d92 (ceph): Merge pull request #2219 from somnathr/wip-optracker-lock
- TrackedOp: Removed redundant lock in OpTracker::_mark_event()
Reviewed-by: Sage Weil <sage@redhat.com> - 06:41 PM Revision f680a24b (ceph): TrackedOp: Removed redundant lock in OpTracker::_mark_event()
- ops_in_flight_lock seems redundant in OpTracker::_mark_event()
and this lock is highly contended for. Removing the sa... - 06:41 PM Revision e45f5c2c (ceph): TrackedOp:_dump_op_descriptor is renamed to _dump_op_descriptor_unlocked
- Caller don't need to hold lock before calling _dump_op_descriptor(),so,
to reflect this it is renamed to _dump_op_des... - 06:23 PM Revision 5026a898 (ceph): Rebased civetweb version to master's
- 06:17 PM Revision e665e627 (ceph): Rebased and changed debug option
- Signed-off-by: Luis Pabón <lpabon@redhat.com>
- 06:15 PM Revision 4fa4553d (ceph): Merge branch 'master' into rgw-doc
- Conflicts:
src/vstart.sh - 05:33 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Plugging one of the 520s into a 3Gbit sata port makes no difference either.
- 04:58 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Updated the bios on the work machine. No difference.
- 05:27 PM Revision bfe31bec (ceph): Add centos/rhel7 to distros 'all' folder.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 05:10 PM Revision 922e24e6 (ceph): Merge pull request #2286 from dachary/wip-9153-jerasure-upgrade-firefly
- erasure-code: preload the jerasure plugin (firefly)
Reviewed-by: Sage Weil <sage@redhat.com> - 05:08 PM Revision f71c8898 (ceph): Merge pull request #2282 from dachary/wip-9153-jerasure-upgrade
- erasure-code: preload the jerasure plugin
Reviewed-by: Sage Weil <sage@redhat.com> - 04:21 PM Revision 98b24f39 (ceph): vstart.sh to enable support for simple RadosGW
- Signed-off-by: Luis Pabón <lpabon@redhat.com>
- 04:08 PM Bug #9153 (In Progress): erasure-code: jerasure_matrix_dotprod segmentation fault due to package ...
- preloading jerasure is not enough : the plugin selects another plugin to be loaded depending on the CPU features (jer...
- 03:29 PM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- I still see this error in today's run http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-20_13:52:13-upgrade:dump...
- 10:07 AM Bug #9153 (Resolved): erasure-code: jerasure_matrix_dotprod segmentation fault due to package upg...
- 03:31 PM Revision 5bf472ae (ceph): os/FileJournal: Update the journal header when closing journal
- When closing journal, it should check must_write_header and update
journal header if must_write_header alreay set.
It... - 03:31 PM Revision 57778e2c (ceph): os/FileJournal: signal aio_cond even if seq is 0
- This can happen if we write a journal but no events.
Reported-by: Somnath Roy <somnath.roy@sandisk.com>
Reported-by:... - 03:27 PM devops Bug #9185: incorrect Centos 6.5 fastcgi package
- fcgi? how does that even enter into it? I thought our work was only with fastcgi?
Is this on teuthology, or cust... - 03:26 PM devops Bug #9185: incorrect Centos 6.5 fastcgi package
- So this problem is with the fcgi package not mod_fastcgi?
- 02:07 PM devops Bug #9185: incorrect Centos 6.5 fastcgi package
- This should fix #9169
- 01:54 PM devops Bug #9185 (Rejected): incorrect Centos 6.5 fastcgi package
- The fastcgi package that is being installed is, or either based off: fcgi-2.4.0-10.el6.x86_64. Not 100% sure that it ...
- 02:33 PM Feature #9031: List RADOS namespaces and list all objects in all namespaces
- 02:31 PM Bug #9186 (Duplicate): erasure-code: conditionally preload isa plugin
- The isa plugin is only built on some platforms. When the OSD preloads plugins, it should not try to load plugins that...
- 02:05 PM rgw Bug #9169: 100-continue broken for centos/rhel
- This seems to be due to idle timeout is not working, should be fixed by #9185
- 01:27 PM devops Feature #9136 (In Progress): ceph-deploy: use pre-existing ceph.conf
- 10:54 AM Bug #9182: osd deadlock after ms_handle_reset
- ..and when i detached gdb the osd saw it was marked down, and came back to life after that. :/
- 10:52 AM Bug #9182: osd deadlock after ms_handle_reset
- ...
- 10:51 AM Bug #9182 (Can't reproduce): osd deadlock after ms_handle_reset
- ubuntu@teuthology:/a/teuthology-2014-08-19_02:30:02-rados-firefly-distro-basic-multi/435572...
- 10:47 AM CephFS Bug #9173: Crash in Server::_session_logged
- Better log.
- 06:30 AM CephFS Bug #9173 (Resolved): Crash in Server::_session_logged
Hit by mds_client_recovery task...- 10:43 AM Bug #9181 (Resolved): Osd: segv in OpTracker::unregister_inflight_op
- ...
- 10:38 AM Bug #9179 (Resolved): unfound objects, recovery timeout
- 402/7722 unfound (
all osds up
ubuntu@teuthology:/a/teuthology-2014-08-19_02:30:02-rados-firefly-distro-basic-m... - 10:33 AM CephFS Bug #9178: samba: ENOTEMPTY on "rm -rf"
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-10_23:14:02-samba-next-testing-basic-plana/415869/
- 10:30 AM CephFS Bug #9178 (Resolved): samba: ENOTEMPTY on "rm -rf"
- ...
- 10:14 AM CephFS Bug #9177 (Resolved): ceph-fuse: failing MPI mdtest runs
- ...
- 09:40 AM Bug #9176 (Resolved): mon: leaked MMonGetVersion
- ubuntu@teuthology:/a/teuthology-2014-08-19_02:30:02-rados-firefly-distro-basic-multi/435589
- 09:38 AM Bug #9175 (Duplicate): osd: stuck recovery
- ubuntu@teuthology:/a/teuthology-2014-08-19_02:30:02-rados-firefly-distro-basic-multi/435529
pgs stuck recovery, ne... - 09:33 AM Feature #7238: erasure code : implement LRC plugin
- Reserved three machines and run the following job on them:...
- 09:32 AM rgw Subtask #9068 (In Progress): rgw: add rgw setup to vstart
- Pull request: https://github.com/ceph/ceph/pull/2292
- 09:31 AM rgw Documentation #9003: rgw: document development setup for rgw
- Abhishek L wrote:
> Luis Pabon wrote:
> > I have edited vstart.sh so that it can setup rgw automatically. I have a... - 09:30 AM rgw Documentation #9003: rgw: document development setup for rgw
- patch has been submitted: https://github.com/ceph/ceph/pull/2292
- 05:21 AM rgw Documentation #9003: rgw: document development setup for rgw
- Luis Pabon wrote:
> I have edited vstart.sh so that it can setup rgw automatically. I have also documented most of ... - 09:19 AM Bug #9128: Newly-restarted OSD may suicide itself after hitting suicide time out value because it...
- sounds like we need to use the TPHandle and tp.reset_tp_handle() inside the search_For_missing loop
- 07:53 AM Documentation #9174: wrong picture on http://ceph.com/docs/master/cephfs/
- ...
- 07:46 AM Documentation #9174 (Closed): wrong picture on http://ceph.com/docs/master/cephfs/
- The picture on page http://ceph.com/docs/master/cephfs/
is not correct.
ceph.ko is not on top of libcephfs / librad... - 04:24 AM Revision 790de974 (ceph): doc/start/quick-ceph-deploy: missing {ceph-node} from mon create-initial
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:56 AM Revision b3624500 (ceph): Merge pull request #2283 from somnathr/wip-sd-9145
- CollectionIndex: Collection name is added to the access_lock name
Reviewed-by: Samuel Just <sam.just@inktank.com> - 03:11 AM devops Feature #8868 (Resolved): Update Fedora to 0.80.5 packages with ceph-common
- The updated packages with spec file synced up with the upstream spec file were pushed to epel 7, fedora 22, fedora 21...
- 01:50 AM Revision 615d2d90 (ceph): CollectionIndex: Collection name is added to the access_lock name
- The CollectionIndex constructor is changed to accept the coll_t
so that the collection name can be used to form acces... - 12:37 AM Revision 164f1a19 (ceph): erasure-code: preload the jerasure plugin
- Load the jerasure plugin when ceph-osd starts to avoid the following
scenario:
* ceph-osd-v1 is running but did not ... - 12:31 AM Revision 9b802701 (ceph): erasure-code: preload the jerasure plugin
- Load the jerasure plugin when ceph-osd starts to avoid the following
scenario:
* ceph-osd-v1 is running but did not ...
08/19/2014
- 10:45 PM Revision bb77e3af (ceph): Merge pull request #2043 from guangyy/wip-pg-splitting
- Support 'expected_num_objects' parameter when creating pool for pg folder splitting
Reviewed-by: Samuel Just <sam.ju... - 09:33 PM Revision fc412734 (ceph): mon: fix signed/unsigned warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:31 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- A related thought is that the Intel 520s are plugged into the sata 6Gbit ports on the motherboard, so if there are an...
- 06:52 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- It might be worth trying an Intel 530 if that is dramatically easier to source - as it is similar to the 520 in the m...
- 06:26 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- That should have said unpatched wip-9073.
- 06:25 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Doing a little more digging for the cause of 2/ (invalid argument erro). Using unpatched ipw-0973 and changing the jo...
- 09:07 PM rgw Bug #9125 (Resolved): rgw: swift tests fail with civetweb
- 08:15 PM Revision 1441ffe8 (ceph): rgw: subuser creation fixes
- Fixes: #8587
There were a couple of issues, one when trying to identify whether swift
user exists, we weren't using t... - 08:06 PM Revision 23a9b763 (ceph): Merge pull request #2287 from ceph/wip-reweight-tunables
- mon: make reweight-by-* sanity limits configurable
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:47 PM Revision 6271ca91 (ceph): Merge pull request #99 from ceph/wip-hadoop
- reorg hadoop tests
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:47 PM Revision d9cf2991 (ceph): Merge pull request #2279 from ceph/wip-hadoop
- fix and reorg hadoop workunits
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:32 PM Revision 82409ee6 (ceph): mon: make reweight-by-* sanity limits configurable
- Also drop the somewhat redundant osd_sum.kb check; the main thing we care
about here is
Signed-off-by: Sage Weil <sa... - 05:44 PM Feature #7238: erasure code : implement LRC plugin
- There is no need to test upgrade on a plugin that does not exist in LRC.
- 02:34 PM Feature #7238: erasure code : implement LRC plugin
- canceled the previous job because it did not have enough OSD to complete (the LRC rule requires a minimum of 8 for ea...
- 12:22 PM Feature #7238: erasure code : implement LRC plugin
- Cancel the "teuthology run that did not contain any LRC workload":http://pulpito.ceph.com/loic-2014-08-19_20:27:09-up...
- 11:27 AM Feature #7238: erasure code : implement LRC plugin
- Fixed a few problems and running "a firefly upgrade suite":http://pulpito.ceph.com/loic-2014-08-19_20:27:09-upgrade:f...
- 05:40 PM Revision c36b72c1 (ceph): Merge pull request #2199 from ceph/wip-reweight
- mon: allow reweighting of osds by pg (isntead of bytes used)
Reviewed-by: Guang Yang <yguang@yahoo-inc.com> - 03:16 PM Revision 33048410 (ceph): mon/OSDMonitor: respect CRUSH weights for reweight-by-pg
- Do not assume that all OSDs are weighted equally for reweight-by-pg.
Note that reweight-by-utilization already rewei... - 03:16 PM Revision 1ecf44eb (ceph): mon/OSDMonitor: reweight-by-pg for pool(s)
- Allow the reweight-by-pg to look at a specific set of pools. If the list
is ommitted, use PGs from all pools. This ... - 03:16 PM Revision 977f8527 (ceph): qa/workunits/cephtool/test.sh: test reweight-by-pg
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:16 PM Revision 8b971e94 (ceph): mon/OSDMonitor: adjust weights up, when possible
- Note when OSDs are underloaded, as well. If that is the case, adjust the
OSD reweight value if, if possible. (It wo... - 03:16 PM Revision 01cb4054 (ceph): mon/OSDMonitor: reweight-by-pg
- This is just like reweight-by-utilization, but looks purely at the PG to
OSD mapping, not at the number of bytes used... - 03:08 PM Bug #9156: SWIFT tests failed in upgrade:dumpling:rgw-dumpling-distro-basic-vps suite
- Further analyzes and chants with Loic and Yehuda revealed that in apache access log we indeed have 30 sec not 1200 se...
- 03:02 PM Bug #9156: SWIFT tests failed in upgrade:dumpling:rgw-dumpling-distro-basic-vps suite
- Suspected backport apache 2.4 issue, test branch wip-rgw-dumpling for ceph-qa-suite
Running now ... - 02:15 PM Fix #8914 (Need More Info): osd crashed at assert ReplicatedBackend::build_push_op
- I'm not able to reproduce the problem on *ceph version 0.84-343-g92b227e (92b227e1c0b1533c359e74c81de58140b483ee8e)* ...
- 01:15 PM rgw Bug #9155: Swift Subuser - 403 Forbidden - during upload/post
- I pushed a different fix to wip-8587, please take a look and see if you think it makes sense.
- 01:10 PM Feature #8155: Disallow changing cache_mode in nonsensical ways
- c3f403293c7f8d946f66a871aa015a558120ce78
- 01:10 PM Feature #8155 (Resolved): Disallow changing cache_mode in nonsensical ways
- 01:09 PM devops Feature #9050: Calamari builds for ceph.com
- Asking Ian and Neil, they confirm that what this means is "repos". The hard choice is going to be figuring out what ...
- 12:15 PM Bug #9170 (Resolved): erasure-code: preload erasure code plugins
- Whitelist the plugins to be preloaded.
- 11:19 AM devops Feature #3019 (Closed): juju: modernize ceph charm, mon & osd bootstrap
- 11:11 AM rgw Bug #9169 (Resolved): 100-continue broken for centos/rhel
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-18_16:07:27-upgrade:dumpling-firefly-x-firefly-dis...
- 11:10 AM devops Feature #8868 (In Progress): Update Fedora to 0.80.5 packages with ceph-common
- 11:04 AM Revision e6658e2a (ceph): mailmap: Anand Bhat affiliation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 11:03 AM Revision 4535cc98 (ceph): mailmap: Federico Simoncelli affiliation
- Reviewed-by: Federico Simoncelli <fsimonce@redhat.com>
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 09:20 AM rgw Feature #8911: RGW doesn't return 'x-timestamp' in header which is used by 'View Details' of Open...
- I'll take a look. Seems like this is new functionality in RGW, not a bug, right?
- 09:13 AM CephFS Bug #9152: mds: beacon needs to not take mds_lock
- Hmm, the beacon send code doesn't need to hold the lock on its own, but it's triggered by the SafeTimer, which is jus...
- 09:07 AM rgw Documentation #9003: rgw: document development setup for rgw
- I have edited vstart.sh so that it can setup rgw automatically. I have also documented most of the steps needed by n...
- 09:02 AM rgw Documentation #9003 (In Progress): rgw: document development setup for rgw
- 09:05 AM CephFS Bug #9151: mds should log/error/warn when segments are NOT getting trimmed
- What kind of logging do we want? I assume you mean journal segments, and this is a bog standard operation...
If it's... - 09:04 AM rgw Feature #8945: rgw: support swift /info api
- After spending some time on this call, I am going to have to break it down to smaller tasks. I am currently investig...
- 09:02 AM Bug #9143: Incorrect key sequence in encoding object name to key for GenericObjectMap
- How did you run across this? Is it feasible to fix it by typing the escaped strings and writing a custom comparator?
- 07:47 AM Bug #9079: osd: bad learned_addr during send_boot
- "pending pull request":https://github.com/ceph/ceph/pull/2275
- 07:41 AM Feature #9167 (Resolved): erasure-code: check plugin version when loading it
- When loading the erasure code plugin, check the Ceph version against which it was built and fail if it does not match...
- 07:22 AM devops Bug #9166 (Closed): activate dmcrypt volumes via init script
- Hi,
I don't know if this is more a bug or a feature request.
I think it would helpful if the activation of ceph ... - 07:16 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- "firefly backport":https://github.com/ceph/ceph/pull/2286
- 07:10 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- The teuthology upgrade tests fails consistently with the same problem. Backporting to firefly seem to be the only way...
- 05:21 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- "Running upgrade:dumpling-firefly-x with the proposed fix":http://pulpito.ceph.com/loic-2014-08-19_14:23:09-upgrade:d...
- 07:10 AM Revision ad6a2be4 (ceph): Implement the collection hint transaction, add a new transation type as...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 07:10 AM Revision dbf624e1 (ceph): Add tests for the collection hint OP: 1) Store Test 2) Idempotent Test.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 07:08 AM Revision da37273d (ceph): Add a new field 'expected_num_objects' to pg_pool_t which denotes the e...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 07:08 AM Revision 35f323d9 (ceph): Add a new monitor command to let user specify the expected number of ob...
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 07:08 AM Revision 7d266d13 (ceph): Add a new transaction OP (collection hint) to ObjectStore.
- Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
- 06:49 AM CephFS Fix #4286: SLES 11 - cfuse: disable 'big_writes'and 'atomic_o_trunc
- 04:17 AM rbd Bug #9076: Can't completely remove a version 1 image on RHEL 7
- Ok it's better with ceph.com packages. You can close this :)
Thanks! - 04:16 AM rbd Bug #9075: Can't create a version 2 images on RHEL 7
- Ok it's better with ceph.com packages. You can close this :)
Thanks! - 04:10 AM Revision 92b227e1 (ceph): Merge remote-tracking branch 'gh/next'
08/18/2014
- 11:21 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- FWIW - checked this myself on my home machine (which was *not* seeing this last issue recall, only the hang) by reboo...
- 07:48 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- My linux version is 3.2 && 3.5. I'll test on 3.13.0-32-generic to find whether kernel cause this bug.
- 07:00 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Excellent. Purely out of interest, any idea (now) why we only saw this bug on one particular system?
- 04:04 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Hmm, thanks very much! I'll send the patch.
Thanks again, Mark! - 03:44 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Retested with only debug-journal-header-3.diff on wip-9073. I did 200 test runs, good journal every time.
- 02:39 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I think you should retest only using debug-journal-header-3.diff on wip-9073. And test more times to avoid the bug r...
- 02:36 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I had your last debugging diff on there as well (I can retest without that if needed).
- 02:34 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Are you only apply debug-journal-header-3.diff on wip-9073 to test ?
- 02:32 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Heh - sorry, means 'really fixed it well'!
- 02:30 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- What's mean of nail it? sorry, i don't know.
- 02:21 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Lol, you certainly have - been a pleasure debugging this with you!
I actually applied the patch attached in this n... - 02:01 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- growl, make that 3.13.0-32-generic, typed 'uname -a' in wrong (x)window before!
- 02:01 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I have a thought. It's strange.
Using aio, the kernel use user-space to write. But if before write to journal, the u... - 01:58 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- ...oh and kernel is 3.13.0-34-generic (sorry)!
- 01:52 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Yeah, disabling dio seems to get a consistently good header (10 consecutive runs)
- 01:22 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- From the latest ceph-osd.o.log. Before io_submit, the content is ok.
I found another issue.
2014-08-18 20:10:09.7... - 01:10 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Seems I spoke too soon - a few more runs showed up:
$ hexdump -n8 journalblk-prestart--20864.txt
0000000 7000 033... - 12:38 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- With *only* your latest pacth applied to wip-9073 I'm seeing a good journal header:
$ hexdump -n8 journalblk-prest... - 12:12 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Using my latest patch, is journal-header corrupt?
From my debug info, before io_submit and after aio completed, the ... - 09:44 PM rgw Bug #9155: Swift Subuser - 403 Forbidden - during upload/post
- Here's the pull request:
[[https://github.com/ceph/ceph/pull/2281]] - 08:20 AM rgw Bug #9155: Swift Subuser - 403 Forbidden - during upload/post
- That's duplicate of #8587, a pull request for your fix would be great.
- 07:49 AM rgw Bug #9155 (Resolved): Swift Subuser - 403 Forbidden - during upload/post
- Swift Upload fails with HTTP error 403 for an subuser that was created with the required permissions. This happens ge...
- 09:29 PM Revision ab886c4a (ceph): doc: Removed quick guide and wireshark from top-level IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:28 PM Revision acee2e58 (ceph): doc: Move wireshark documentation to dev.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:57 PM Revision ce6e9a91 (ceph): doc/release-notes: v0.84
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:26 PM Bug #9062: Mon segfault in waitlist_or_zap_client
- the fix was merged in commit:321d4defd4a0f5a53a41276e6dc048479cb3084a
- 05:51 PM Revision ae787cfa (ceph): Work around an apparent binding bug (GCC 4.8).
- A reference to h->seq passed to std::pair ostensibly could not bind
because the header structure is packed. At first... - 05:14 PM Bug #9145: recursive lock of CollectionIndex::access_lock (52)
- The fix Sam suggested is to name the CollectionIndex lock based on the collection names. This will make lockdep happy...
- 01:58 PM Bug #9145: recursive lock of CollectionIndex::access_lock (52)
- Sage,
Yes, I am able to reproduce this following the steps you suggested. But, this time I am hitting the issue in _... - 05:10 PM Revision 73e75fdb (ceph): use the right syntax for RHEL/CentOS distros to check for ceph status
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 4b15d0118ec000fe1e947131a62ef9990b2... - 05:10 PM Revision c1a2463c (ceph): Merge pull request #100 from ceph/wip-9154
- use the right syntax for RHEL/CentOS distros to check for ceph status
Reviewed-by: Sage Weil <sage@redhat.com> - 05:05 PM Revision 209226f1 (ceph): Merge pull request #98 from ceph/rgw_civetweb
- bug 8927: include frontend:civetweb for rgw tests
- 05:04 PM Revision a59bc865 (ceph): Merge pull request #2280 from ceph/wip-fs-docs
- doc: add notes on using "ceph fs new"
Reviewed-by: Sage Weil <sage@redhat.com> - 04:51 PM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- "minimal fix":https://github.com/ceph/ceph/pull/2282
- 09:05 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Stopping the daemons may not be the brightest idea because of http://tracker.ceph.com/issues/8849 . Pre-loading the p...
- 08:09 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- "proposed fix":https://github.com/ceph/ceph/pull/2278
- 07:27 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Here is a possible scenario:
* ceph-osd-0.80.5 is running but did not load jerasure
* ceph-osd-0.83 is installed ... - 07:09 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Here is the part of the teuthology log dealing with the upgrade, which is immediately followed by a core dump from os...
- 06:43 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Trying a manual upgrade...
- 06:25 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- The ceph-libs package is obsolete and the jerasure plugin now lives in the ceph package. The problem does not come fr...
- 06:18 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- It looks like the ceph-libs package is not upgraded, which explains the core dump : master cannot successfully load a...
- 05:31 AM Bug #9153 (Fix Under Review): erasure-code: jerasure_matrix_dotprod segmentation fault due to pac...
- "proposed fix":https://github.com/ceph/ceph/pull/2276
- 05:22 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- If the ceph-libs package is upgraded before the ceph package, it is entirely possible that the shared library is repl...
- 04:47 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- The upgrade sequence
* dumpling
* firefly -> installs and load the jerasure plugin
* master -> installs an updat... - 04:41 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- The stack trace is bizarre. ECUtil::decode calls ErasureCodeJerasure::encode_chunks which makes no sense becase a) de...
- 04:29 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Got three VPS with rhel 6.5 installed, running the job on them with no "nuke-on-error"
- 03:43 AM Bug #9153 (In Progress): erasure-code: jerasure_matrix_dotprod segmentation fault due to package ...
- As soon as VPS are available, lock three and run the job again hoping to repeat it...
- 01:22 AM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Ack
- 04:47 PM Revision b016f846 (ceph): doc: add notes on using "ceph fs new"
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:40 PM Revision 4b15d011 (ceph): use the right syntax for RHEL/CentOS distros to check for ceph status
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 04:22 PM Revision 948178aa (ceph): ceph_mon: check for existing mon store before opening db
- This will make sure that the monitor data directory is populated before
proceeding to opening it up. We have to do t... - 04:02 PM Revision 8336f81c (ceph): 0.84
- 03:47 PM Revision bda23018 (ceph): qa/workunits/rbd/qemu-iotests: touch common.env
- This seems to be necessary on trusty.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry... - 03:41 PM Revision a02c90b8 (ceph): suites/hadoop: update workunit names
- These were renamed/reorged.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:39 PM Revision 1dc1fb8a (ceph): qa/workunits/hadoop: move all hadoop tests into a hadoop/ dir
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:38 PM Revision 3d3fcc98 (ceph): qa/workunits/hadoop-wordcount: fix/use -rmr command
- -rm -r -f ... doesn't seem to work; use -rmr instead.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:37 PM Revision adaf5a6a (ceph): qa/workunits/hadoop-wordcount: use -x
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:42 PM Feature #9161 (New): Cache warmup and ejection
- Initial access of an object in a high performance cache tier can have high latency as the object is fetched from the ...
- 02:20 PM rgw Bug #9160 (Closed): rgw failures with 'NoneType' object has no attribute 'get_contents_as_string'
Several jobs in this suite failed with this error:
http://pulpito.ceph.com/john-2014-08-18_16:28:28-rgw-wip-object...- 01:56 PM rgw Bug #9125: rgw: swift tests fail with civetweb
- looks like the fix is merged to master, tested it on master branch and it worked fine.
will mark it as "Resolved"... - 10:45 AM Bug #9158 (Duplicate): osd crashed in upgrade:dumpling-x:stress-split-master-distro-basic-vps suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-17_11:40:01-upgrade:dumpling-x:stress-split-master...
- 10:24 AM Bug #9072 (Resolved): error setting 'mon_pg_warn_min_objects' to '10K': (22) Invalid argument
- 09:23 AM Bug #9072: error setting 'mon_pg_warn_min_objects' to '10K': (22) Invalid argument
- I checked the firefly branch and Sage cherry-picked the required patches to it.
That ought to fix all issues with ... - 09:08 AM devops Feature #9118: ceph-deploy: Add pre-generated keys to a Monitor
- Keith Schincke wrote:
> Can the precreated/populated keyring be propagated with the ceph-deploy command when the clu... - 09:04 AM devops Feature #9118: ceph-deploy: Add pre-generated keys to a Monitor
- Can the precreated/populated keyring be propagated with the ceph-deploy command when the cluster is created?
- 08:23 AM Bug #9156 (Resolved): SWIFT tests failed in upgrade:dumpling:rgw-dumpling-distro-basic-vps suite
- 12 tests total failed in http://pulpito.front.sepia.ceph.com/teuthology-2014-08-17_12:05:01-upgrade:dumpling:rgw-dump...
- 05:17 AM Bug #9112 (Resolved): (wip-objecter) librados notify calls freezing
- No longer occurring after reinstating _recalc_linger_op_target and updating related bits of code
- 03:54 AM Revision c7948afa (ceph): qa/workunits/rbd/qemu-iotests: touch common.env
- This seems to be necessary on trusty.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry... - 03:54 AM Revision 486deefd (ceph): qa/workunits/rbd/qemu-iotests: touch common.env
- This seems to be necessary on trusty.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry... - 03:54 AM Revision 055be68c (ceph): qa/workunits/rbd/qemu-iotests: touch common.env
- This seems to be necessary on trusty.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 03:49 AM Revision 313e60b3 (ceph): Merge pull request #2010 from ceph/wip-misplaced
- osd: track misplaced objects separately from degraded objects
Reviewed-by: Samuel Just <sam.just@inktank.com> - 12:15 AM Revision a60267d8 (ceph): rgw: httpd instead of httpd.worker
- httpd exists on rhel 6.5 too ...
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit f7b32bcc318c4... - 12:15 AM Revision 211fd6d1 (ceph): rgw: need alll of mod unixd, version, authz
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 6392758f1bf503c3bbb2b3ad2f2ee9e6f79d6841) - 12:15 AM Revision ea023597 (ceph): tasks/rgw: include mod_authz
- As per http://www.webhostingtalk.com/showthread.php?t=1173594
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry pic... - 12:15 AM Revision d14fb136 (ceph): tasks/rgw: get mpm_event frmo mods-available, not mods-enabled
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 2aae91929f720c54f406b7612631d82b27c98fe6) - 12:15 AM Revision 8b5f114b (ceph): Add extra conf for Apache 2.4
- Inside a conditional to affect only 2.4, set User, Group, and the
module config to load mpm_event. This is normally ...
08/17/2014
- 11:52 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Meanwhile, I have been doing a little digging of my own: if I disable dio or aio via
[osd]
journal [d,a]io = fals... - 11:40 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Here's the log with that patch applied.
- 07:27 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Hi Mark,
Could you test again? I add more debug message this time.
Thanks!
- 08:53 PM rbd Bug #8919 (Resolved): qemu-iotests fails to find common.env
- 05:15 PM Bug #9153: erasure-code: jerasure_matrix_dotprod segmentation fault due to package upgrade race
- Loic, can you take a look?
- 04:38 PM Bug #9153 (Resolved): erasure-code: jerasure_matrix_dotprod segmentation fault due to package upg...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-17_11:30:03-upgrade:dumpling-firefly-x-master-dist...
- 03:35 PM Revision ff893d55 (ceph): mailmap: Andreas Peters name normalization
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 03:35 PM Revision 4cdec2f1 (ceph): mailmap: Owen Synge affiliation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 03:35 PM Revision 4d5d0d96 (ceph): mailmap: Pavan Rallabhandi affiliation
- Reviewed-by: Pavan Rallabhandi <pavan.rallabhandi@sandisk.com>
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 01:00 PM CephFS Bug #9152 (Resolved): mds: beacon needs to not take mds_lock
- any random task that holds the mds lock for a long time prevents beacons, which will trigger a failover
- 12:48 PM CephFS Bug #9151 (Resolved): mds should log/error/warn when segments are NOT getting trimmed
- 11:20 AM Revision 725aa4e7 (ceph): mailmap: Huamin Chen affiliation
- and name normalization
Reviewed-by: Huamin Chen <hchen@redhat.com>
Signed-off-by: Loic Dachary <loic-201408@dachary.... - 11:20 AM Revision 78de7e13 (ceph): mailmap: Zhiqiang Wang affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 11:20 AM Revision 309c98bd (ceph): mailmap: Xiaoxi Chen affiliation
- Reviewed-by: Xiaoxi Chen <xiaoxi.chen@intel.com>
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 08:43 AM Revision 55227aae (ceph): mailmap: Shu, Xinxin affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 08:43 AM Revision a06affbb (ceph): mailmap: Thorsten Behrens affiliation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 08:43 AM Revision bac88db0 (ceph): mailmap: Luis Pabón affiliation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 08:43 AM Revision cc3b5ada (ceph): mailmap: Abhishek Lekshmanan affiliation
- Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
Signed-off-by: Loic Dachary <loic-201408@dachary.org> - 05:07 AM Revision 6d7a229c (ceph): qa/workunits/rest/test.py: fix rd_kb -> rd_bytes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:07 AM Revision 3279f3e7 (ceph): qa/workunits/rest/test.py: do snap test on our data2/3 pool
- This way it works when a 'data' pool doesn't already exist.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:07 AM Revision 5045c5cb (ceph): qa/workunits/rest/test.py: use rbd instead of data pool for size tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:04 AM Revision 284647f3 (ceph): Merge pull request #2272 from ceph/wip-8621
- Wip 8621
Reviewed-by: Sage Weil <sage@redhat.com>
08/16/2014
- 11:44 PM Revision 6392758f (ceph): rgw: need alll of mod unixd, version, authz
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:44 PM Revision f7b32bcc (ceph): rgw: httpd instead of httpd.worker
- httpd exists on rhel 6.5 too ...
Signed-off-by: Sage Weil <sage@redhat.com> - 10:24 PM Revision cc4e6258 (ceph): unittest_strtol: fix compilation warning
- Was fixed in master by a4923f5bc373d530d1ffdf6c58a4d88139daedd2
Signed-off-by: Sage Weil <sage@redhat.com> - 10:01 PM rgw Bug #8621 (Pending Backport): civetweb frontend fails authentication if URL has special chars
- 09:55 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Sage's comment suggested I check something - reverting 4eb18dd487da4cb621dcbecfc475fc0871b356ac from wip-9073 and run...
- 08:59 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I've reverted commit:4eb18dd487da4cb621dcbecfc475fc0871b356ac on next so we can release v0.84. once we sort this out...
- 12:47 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- jianpeng ma wrote:
> I read the #6003. I think they are not the same.
> You can see those two files (patch.diff ... - 09:53 PM Feature #9030 (Resolved): mon: quickly identify 'problem' osds
- 09:51 PM Revision 0e07f7f0 (ceph): osd: fix theoretical use-after-free of OSDMap
- In practice, the map will remain pinned for a while, but this
will make coverity happy.
*** CID 1231685: Use after ... - 09:26 PM Bug #9150 (Can't reproduce): osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.alig...
- ...
- 08:57 PM rgw Bug #9137 (Resolved): AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- 04:56 PM rgw Bug #9137: AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- works on el6 and el7. fc20 fails the ceph-qa-chef because of tiobench.
- 02:16 PM rgw Bug #9137: AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- verfied to work on precise and trusty.
still need to test on el6, el7, and fedora. - 08:56 PM Revision 27b7ecee (ceph): tasks/rgw: include mod_authz
- As per http://www.webhostingtalk.com/showthread.php?t=1173594
Signed-off-by: Sage Weil <sage@redhat.com> - 08:52 PM rgw Bug #9148 (Resolved): rgw: multiregion tests failing, s3tests.functional.test_s3.test_region_copy...
- ...
- 08:41 PM Revision 44a0e376 (ceph): Merge pull request #2259 from ceph/wip-9039
- Wip 9039
Reviewed-by: Sage Weil <sage@redhat.com> - 08:37 PM Revision 2aae9192 (ceph): tasks/rgw: get mpm_event frmo mods-available, not mods-enabled
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:19 PM Revision dbc3f650 (ceph): osd: track last_undegraded pg stat
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:19 PM Revision 5168907f (ceph): osd: track last_fullsized in pg_stat_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:19 PM Revision 190dc2f3 (ceph): mon: track pgs that get stuck degraded
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:19 PM Revision 932e4787 (ceph): mon: track stuck undersized
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:19 PM Revision 904a5f1c (ceph): vstart.sh: make filestore fd cache size smaller
- I hit the fd limit on a vstart cluster with the default 128; reduce this
to 16.
Signed-off-by: Sage Weil <sage@redha... - 08:19 PM Revision 1907066f (ceph): osd/osd_types: add last_undegraded, last_undersized to pg_stat_t
- Keep track of the last time the PG was known to not be degraded or
undersized.
Signed-off-by: Sage Weil <sage@redhat... - 08:18 PM Revision 6c0a2134 (ceph): osd/PG: account for misplaces separately than degraded
- A degraded object does not have enough replicas or shards, while a
misplaced object is not stored in the correct plac... - 08:18 PM Revision b037e47a (ceph): osd: add PG_STATE_UNDERSIZED
- This is a distinct concept from degraded.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:18 PM Revision 6d6767d3 (ceph): osd/PG: track PG_STATE_UNDERSIZED separately from DEGRADED
- DEGRADED means there are objects without complete reduncancy; also check
for needs_recovery().
UNDERSIZED means acti... - 08:18 PM Revision a3149994 (ceph): osd: num_objects_misplaced
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:18 PM Revision d734d7fc (ceph): mon: warn about misplaced objects, just like degraded
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:18 PM Revision 988d7419 (ceph): librados: approximate legacy 'degraded' value
- The librados API returns a degraded count and no misplaced count. Sum them
to approximate the old behavior.
Signed-... - 08:15 PM Revision 34fe7a82 (ceph): Merge pull request #2217 from ceph/wip-problem-osds
- mon: 'ceph osd blocked-by' for histogram of peers OSDs are waiting for
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:06 PM Revision 14614e01 (ceph): qa/workunits/rest/test.py: fix 'df' test to use total_used_bytes
- This changed back in ee2dbdb0f5e54fe6f9c5999c032063b084424c4c
Signed-off-by: Sage Weil <sage@redhat.com> - 07:56 PM Revision 93c5b25b (ceph): Revert "os/FileJournal: Update the journal header when closing journal"
- This reverts commit 4eb18dd487da4cb621dcbecfc475fc0871b356ac.
This may be responsible for #9073. Until that is reso... - 07:43 PM Revision 29e93f7c (ceph): os/FileStore: rename start_sync() -> do_force_sync()
- Just to avoid confusion with start_sync(Context*c), which is totally
different.
Signed-off-by: Sage Weil <sage@redha... - 07:42 PM Revision dd11042f (ceph): os/FileStore: fix mount/remount force_sync race
- Consider:
- mount
- sync_entry is doing some work
- umount
- set force_sync = true
- set done = true
- syn... - 04:18 PM Revision ee9e1ead (ceph): Merge pull request #2271 from ceph/wip-9053
- paxos: fix problem with disjoint quorum members
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 03:42 PM CephFS Bug #8574 (Resolved): teuthology: NFS mounts on trusty are failing
- chef adds a dummy export and restarts nfs-kernel-server now
- 02:41 PM CephFS Bug #8574: teuthology: NFS mounts on trusty are failing
- root@mira055:~# service nfs-kernel-server restart
* Stopping NFS kernel daemon ... - 02:08 PM Linux kernel client Bug #9147 (Closed): krbd: run_xfstests.sh fails
- ...
- 02:07 PM rbd Bug #9146 (Can't reproduce): EPERM from image_read.sh
- ...
- 01:54 PM rgw Bug #9039: Using COPY on radosgw to copy object from one bucket to another that's in another pool...
- The restriping tool never made it to dumpling. It actually isn't even in firefly.
- 01:39 PM rgw Bug #9039 (Pending Backport): Using COPY on radosgw to copy object from one bucket to another tha...
- the restriping fix patches also need to go to dumpling...
- 01:46 PM Bug #8997: ceph_test_rados_watch_notify hangs
- ubuntu@teuthology:/a/sage-2014-08-15_21:44:35-rados-master-testing-basic-multi/427533 (probably)
- 01:43 PM Bug #9145 (Resolved): recursive lock of CollectionIndex::access_lock (52)
- ...
- 01:17 PM Feature #7238: erasure code : implement LRC plugin
- "running teuthology test run":http://pulpito.ceph.com/loic-2014-08-16_22:17:50-upgrade:firefly-x:stress-split-wip-723...
- 12:41 PM Bug #9144 (Fix Under Review): filestore: commit triggered during journal replay
- https://github.com/ceph/ceph/pull/2274
- 09:26 AM Bug #9144 (Resolved): filestore: commit triggered during journal replay
- ...
- 09:38 AM Feature #9033 (Resolved): erasure-code: simplified LRC
- "part of a larger pull request":https://github.com/dachary/ceph/commit/43b8f66797184b1138560184708573aa6930e8c4
- 09:15 AM Bug #9053 (Pending Backport): mon/Paxos.cc: 628: FAILED assert(begin->last_committed == last_comm...
- 09:06 AM Revision 03959147 (ceph): mailmap: Loic Dachary affiliation
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 07:47 AM Bug #9143 (Rejected): Incorrect key sequence in encoding object name to key for GenericObjectMap
- For example, two oid has same hash and their name is:
A: "rb.data.123"
B: "rb-123"
In ghobject_t compare level, ... - 06:02 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- "all green !":http://pulpito.ceph.com/loic-2014-08-16_10:42:43-upgrade:firefly-x:stress-split-wip-9025-chunk-remappin...
- 05:37 AM Revision 9de5bd1d (ceph): Add extra conf for Apache 2.4
- Inside a conditional to affect only 2.4, set User, Group, and the
module config to load mpm_event. This is normally ... - 04:47 AM Revision 7f9fe22a (ceph): Fix EINVAL err when use "ceph tell osd.* bench"
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
(cherry picked from commit 7dc93a9651f602d9c46311524fc6b54c2f1ac595) - 04:42 AM Revision 14607fc0 (ceph): qa/workunits/cephtool/test.sh: fix get erasure_code_profile test
- Manual backport of 4d6899c7560e990650959b442980a7249f0ba4c1
Signed-off-by: Sage Weil <sage@redhat.com> - 04:37 AM Revision c83c90ca (ceph): rgw: update civetweb submodule
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 04:36 AM Revision 068b906e (ceph): mon: OSDMonitor: add 'osd pool get-quota' command
- Enables us to obtain current quotas for a given pool.
Fixes: #8523
Signed-off-by: Joao Eduardo Luis <joao.luis@inkt... - 04:30 AM Revision 2ed0fa03 (ceph): mon: name instead of id in "has tiers" message
- Instead of "Pool foo has tiers 1 2" print
"Pool foo has tiers bar baz".
Signed-off-by: John Spray <jspray@redhat.com... - 04:01 AM Revision 7e509b1b (ceph): common/config.cc: allow integer values to be parsed as SI units
- We are allowing this for all and any integer values; that is, OPT_INT,
OPT_LONGLONG, OPT_U32 and OPT_U64.
It's on th... - 04:00 AM Revision 4e34d83e (ceph): test/strtol.cc: Test 'strict_strtosi()'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 40587d4792fd55db72d33870aae8b6a80... - 04:00 AM Revision 3b06b8f4 (ceph): common/strtol.cc: strict_strtosi() converts str with SI units to uint64_t
- Accepts values with a suffix (B, K, M, G, T, P, E) and returns the
appropriate byte value.
E.g., 10B = 10, while 10K... - 12:15 AM Revision 08772fd8 (ceph): ceph-disk: warn about falling back to sgdisk (once)
- This way the user knows something funny might be up if dmcrypt is in use.
Signed-off-by: Sage Weil <sage@redhat.com>... - 12:15 AM Revision 92ab6ecf (ceph): ceph-disk: linter cleanup
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit d74ed9d53fab95f27a9ad8e9f5dab719299... - 12:15 AM Revision 8a8a9c35 (ceph): Revert "Fix for bug #6700"
- This reverts commit 673394702b725ff3f26d13b54d909208daa56d89.
This appears to break things when the journal and data... - 12:15 AM Revision 1804a834 (ceph): ceph-disk: fix log syntax error
- File "/usr/sbin/ceph-disk", line 303, in command_check_call
LOG.info('Running command: %s' % ' '.join(arguments))... - 12:15 AM Revision 6775f46e (ceph): ceph-disk: use partition type UUIDs, and blkid
- Use blkid to give us the GPT partition type. This lets us distinguish
between dmcrypt and non-dmcrypt partitions. F... - 12:15 AM Revision b09e6592 (ceph): ceph-disk: move fs mount probe into a helper
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit f80ed26d2403ba12e80da6459fc45c22584f72de) - 12:15 AM Revision 8c04e475 (ceph): ceph-disk: display information about dmcrypted data and journal volumes
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit c7a1ceba441fa99a82e19ed2cd3c6782a5d77636) - 12:15 AM Revision a45e815c (ceph): ceph-disk: add get_partition_base() helper
- Return the base devices/disk for a partition device.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from ... - 12:15 AM Revision 50166efd (ceph): ceph-disk: only fall back to sgdisk for 'list' if blkid seems old
- If the blkid doesn't show us any ID_PART_ENTRY_* fields but we know it is
a GPT partition, *then* fallback. Otherwis... - 12:15 AM Revision 80896dcf (ceph): support dmcrypt partitions when activating
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit ef8a1281512c4ee70a3764b28891da691a1... - 12:15 AM Revision 40649902 (ceph): ceph-disk: fix list for encrypted or corrupt volume
- Continue gracefully if an fs type is not detected, either because it is
encrypted or because it is corrupted.
Signed... - 12:15 AM Revision c9847ef0 (ceph): better error reporting on incompatible device requirements
- Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 1ac3a503a15ddf7f7c1a33310a468fac10a1b7b6) - 12:15 AM Revision 50b700fa (ceph): ceph-disk: fix verify_no_in_use check
- We only need to verify that partitions aren't in use when we want to
consume the whole device (osd data), not when we... - 12:05 AM Revision 1b0da81d (ceph): init-ceph: don't use bashism
- -z STRING
the length of STRING is zero
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from ...
08/15/2014
- 11:42 PM Revision a14a700a (ceph): Merge pull request #2270 from ceph/wip-init-ceph
- init-ceph: don't use bashism
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 11:41 PM Revision 0d6d1aa7 (ceph): init-ceph: don't use bashism
- -z STRING
the length of STRING is zero
Signed-off-by: Sage Weil <sage@redhat.com> - 11:40 PM Revision dc611e86 (ceph): Merge pull request #2247 from ceph/wip-ceph-disk
- ceph-disk: fix various dmcrypt bugs
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 10:33 PM Revision 9005f33d (ceph): osd: fix feature requirement for mons
- These features should be set on the client_messenger, not
cluster_messenger.
Backport: firefly
Signed-off-by: Sage W... - 10:19 PM Revision 082db05c (ceph): Merge pull request #2269 from ceph/wip-osd-mon-feature
- osd: fix mon feature requirement
Reviewed-by: Loic Dachary <loic@dachary.org> - 10:14 PM Revision 48a8434f (ceph): Merge pull request #97 from dachary/firefly
- rgw.yaml: keep the client.0 key even if empty (firefly)
- 10:09 PM Revision 12ded3c9 (ceph): Merge pull request #96 from dachary/wip-8988-default-idle-timeout
- rgw.yaml: keep the client.0 key even if empty
- 10:01 PM Revision 1d0c66ae (ceph): Merge remote-tracking branch 'gh/next'
- 10:00 PM Revision 7df67a54 (ceph): Fix -Wno-format and -Werror=format-security options clash
- This causes build failure in latest fedora builds, ceph_test_librbd_fsx adds -Wno-format cflag but the default AM_CFL...
- 09:50 PM Revision 703c5f4f (ceph): Merge pull request #89 from dachary/wip-9027-create-unique-pool
- initialize ctx.manager in ceph.py
Reviewed-by: Sage Weil <sage@redhat.com> - 09:29 PM Revision ae0b9f17 (ceph): osd: fix feature requirement for mons
- These features should be set on the client_messenger, not
cluster_messenger.
Backport: firefly
Signed-off-by: Sage W... - 09:11 PM Revision d9e96b17 (ceph): Merge pull request #2268 from ceph/wip-9119
- Wip 9119
Reviewed-by: Sage Weil <sage@redhat.com> - 09:04 PM Revision 50404130 (ceph): ReplicatedPG::cancel_copy: clear cop->obc
- Otherwise, an objecter callback might still be hanging
onto this reference until after the flush.
Fixes: #8894
Intro... - 09:04 PM Revision 0db3e511 (ceph): ReplicatedPG::maybe_handle_cache: do not forward RWORDERED reads
- Even with READFORWARD, we can't forward RWORDERED reads.
Fixes: #9119
Backport: firefly
Signed-off-by: Samuel Just <... - 09:04 PM Revision 9e46c5ad (ceph): unittest_osdmap: test EC rule and pool features
- TODO: tiering feature bits.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 2f0e2951d773b6acce... - 09:04 PM Revision dbbe0c62 (ceph): unittest_osdmap: create an ec pool in test osdmap
- This is part of 7294e8c4df6df9d0898f82bb6e0839ed98149310.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:56 PM Revision c2aa74a2 (ceph): osd: only require crush features for rules that are actually used
- Often there will be a CRUSH rule present for erasure coding that uses the
new CRUSH steps or indep mode. If these ru... - 08:56 PM Revision 12430fed (ceph): crush: add is_v[23]_rule(ruleid) methods
- Add methods to check if a *specific* rule uses v2 or v3 features. Refactor
the existing checks to use these.
Signed... - 08:55 PM Revision eb589428 (ceph): Merge pull request #2264 from ceph/wip-crush-features
- do not require crush features for rules that aren't being used
Reviewed-by: Loic Dachary <loic@dachary.org> - 08:54 PM Revision 2f0e2951 (ceph): unittest_osdmap: test EC rule and pool features
- TODO: tiering feature bits.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:41 PM Revision e4d238bb (ceph): Merge pull request #2266 from kevincox/removewirehsark
- Remove Old Wireshark Dissectors
Reviewed-by: Sage Weil <sage@redhat.com> - 08:37 PM Revision cab47936 (ceph): Merge pull request #2070 from somnathr/wip-sd-filestore-optimization
- Wip sd filestore optimization
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:06 PM Revision 984f3ce4 (ceph): rgw.yaml: keep the client.0 key even if empty
- Because rgw.py iterates over it to run the rgw server. If it is removed
the rgw servers are not run and all fails.
S... - 08:03 PM Revision bcb9c1f8 (ceph): rgw.yaml: keep the client.0 key even if empty
- Because rgw.py iterates over it to run the rgw server. If it is removed
the rgw servers are not run and all fails.
S... - 07:50 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I read the #6003. I think they are not the same.
You can see those two files (patch.diff Magnifier (571 Bytes) ji... - 06:19 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- This is starting to sound a lot like #6003!
- 01:56 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- hexdump -n8 journalblk-prestart.txt
0000000 3000 021d 0000 0000 - 12:09 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you paste the journal head after this command. Only first 8byte.
- 07:27 PM Revision 0b276103 (ceph): Remove Old Wireshark Dissectors
- Remove the two old Wireshark plugins. They do not build and are
superseded by the dissector which is inside Wireshar... - 05:43 PM Revision 2427ea8f (ceph): PGLog: fix clear() to avoid the IndexLog::zero() asserts
- Introduced in:
c5b8d8105d965da852c79add607b69d5ae79a4d4
ac11ca40b4f4525cbe9b1778b1c5d9472ecb9efa
Signed-off-by: S... - 04:41 PM rgw Bug #9137: AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- The MPM selection is supposed to be made in the default config.
- 01:23 PM rgw Bug #9137: AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- Looking into this; my theory is two problems: 1) package structure changed in 2.4 and we might need to explicitly in...
- 11:46 AM rgw Bug #9137 (Resolved): AH00534: apache2: Configuration error: No MPM loaded. (rpm distros)
- ...
- 03:55 PM Revision 1d954867 (ceph): crush: add is_v[23]_rule(ruleid) methods
- Add methods to check if a *specific* rule uses v2 or v3 features. Refactor
the existing checks to use these.
Signed... - 03:55 PM Revision 16dadb86 (ceph): osd: only require crush features for rules that are actually used
- Often there will be a CRUSH rule present for erasure coding that uses the
new CRUSH steps or indep mode. If these ru... - 03:49 PM Bug #9130 (Resolved): (wip-objecter) FAILED assert(cur_con) in MonClient
- fix in wip-objecter
- 06:42 AM Bug #9130 (Resolved): (wip-objecter) FAILED assert(cur_con) in MonClient
http://pulpito.front.sepia.ceph.com/john-2014-08-15_03:34:51-rbd-wip-mds-contexts-testing-basic-multi/425519/
<p...- 02:08 PM Bug #9119 (Pending Backport): READFORWARD ordering bug
- 02:03 PM RADOS Bug #8963 (Resolved): erasure coding crush rulset breaks rbd kernel clients on non-ec pools on Ub...
- backported to firefly
- 01:56 PM Revision 821b2a43 (ceph): replace locally instantiated CephManager
- Use the ctx.manager instance created by ceph.py instead
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:56 PM Revision f53ea258 (ceph): move functions from ceph to ceph_manager
- mount_osd_data and make_admin_daemon_dir are only used by
ceph_manager.py although they are defined in ceph.py
Signe... - 01:56 PM Revision 9782465c (ceph): initialize ctx.manager in ceph.py
- instead of rados.py because ceph.py is only run once where rados.py
could be run multiple time, leading to race condi... - 01:42 PM Revision e908e42e (ceph): Merge pull request #93 from ceph/wip-9126-firefly
- rgw: s/idle_timeout/default_idle_timeout/
- 01:34 PM Bug #9142 (Can't reproduce): [ RUN ] LibRadosTwoPoolsPP.PromoteSnapScrub hang
- ubuntu@teuthology:/a/samuelj-2014-08-14_18:41:07-rados-wip-sam-testing-testing-basic-multi/425498
- 01:33 PM Bug #9140: [ FAILED ] LibRadosTwoPoolsPP.PromoteOn2ndRead (9913 ms)
- ubuntu@teuthology:/a/samuelj-2014-08-14_18:41:07-rados-wip-sam-testing-testing-basic-multi/425458
- 01:30 PM Bug #9140 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.PromoteOn2ndRead (9913 ms)
- 2014-08-15T05:48:20.619 INFO:tasks.workunit.client.0.plana16.stdout:[ OK ] LibRadosTwoPoolsPP.HitSetWrite (2908...
- 01:32 PM Bug #9141 (Can't reproduce): [ RUN ] LibRadosAio.IsCompletePP hang
- ubuntu@teuthology:/a/samuelj-2014-08-14_18:41:07-rados-wip-sam-testing-testing-basic-multi/425497
- 01:30 PM Revision 592a524d (ceph): rgw: s/idle_timeout/default_idle_timeout/
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from da00662191e9ec173be50b551253f4460f369f9da) - 01:01 PM Bug #9139 (Rejected): ceph_test_rados reports incorrectly missing object
- ORDERSNAPS was fixing something important:
1) cache-primary send DELETE on object we are flushing
2) base-primary q... - 11:32 AM Revision 3326a9fe (ceph): Merge pull request #90 from dachary/wip-8988-default-idle-timeout
- rgw: s/idle_timeout/default_idle_timeout/
Reviewed-by: John Spray <john.spray@redhat.com> - 11:28 AM devops Feature #9134 (Duplicate): ceph-deploy: add pre-generated client keys to MON
- 9118
- 11:22 AM devops Feature #9134 (Duplicate): ceph-deploy: add pre-generated client keys to MON
- User story: As an admin, I have already generated Ceph client keys and would like to add them to the cluster during t...
- 11:27 AM devops Feature #9136 (Resolved): ceph-deploy: use pre-existing ceph.conf
- User story: As an admin, I have already generated a ceph,conf file and would like to use it for a new cluster install...
- 11:26 AM Bug #9135 (Can't reproduce): ENOENT on collection_add
- ...
- 11:08 AM CephFS Feature #8869 (Resolved): MDS: support standby-replay on old-format journals
- This merged a couple of weeks ago in https://github.com/ceph/ceph/commit/440c820cce2c262570ab78e352bed8a630d41be5
- 10:49 AM devops Feature #9133 (Rejected): create ceph user/group; run daemons as ceph (non-root)
- this will involve lots of updates to packaging.
- 10:43 AM Revision cb4c5649 (ceph): Merge pull request #2213 from dachary/wip-9025-chunk-remapping
- erasure-code: chunk remapping
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:34 AM Revision da006621 (ceph): rgw: s/idle_timeout/default_idle_timeout/
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 05:33 AM Feature #7238: erasure code : implement LRC plugin
- Teuthology job description:...
- 04:45 AM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- Punting on a general purpose fix for ObjectCacher for the time being, and just fixing this in librbd teardown.
- 04:44 AM CephFS Bug #9105 (Fix Under Review): ~ObjectCacher behaves poorly on EBLACKLISTED
- https://github.com/ceph/ceph/pull/2263
- 04:33 AM Revision b22d693f (ceph): lttng: Add distro packaging
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 03:53 AM Bug #9128 (Resolved): Newly-restarted OSD may suicide itself after hitting suicide time out value...
- Stop one OSD daemon for a long time, like many hours even to 1 day, without marking it as out. During this time, ther...
- 03:40 AM Feature #9025 (Resolved): erasure-code: chunk remapping
- 03:38 AM Feature #9025: erasure-code: chunk remapping
- Teuthology job passes.
- 01:25 AM Revision 6891f4ed (ceph): lttng: Fix "make distcheck"
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 12:55 AM Revision edbf82ad (ceph): rgw: add default_idle_timeout to allow override
- Globally overriding the rgw idle_timeout is not possible because it it
needs to be done on a per client.0, client.1, ... - 12:41 AM Revision 4f9f023c (ceph): rest-api tests: enable debugging
- Hoping to catch #9058
Signed-off-by: Sage Weil <sage@redhat.com>
08/14/2014
- 11:56 PM Revision c54f1e4d (ceph): mon/Paxos: share state and verify contiguity early in collect phase
- We verify peons are contiguous and share new paxos states to catch peons
up at the end of the round. Do this each ti... - 11:55 PM Revision 3e5ce5f0 (ceph): mon/Paxos: verify all new peons are still contiguous at end of round
- During the collect phase we verify that each peon has overlapping or
contiguous versions as us (and can therefore be ... - 11:25 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- The strace attached. So this is the mkfs...and wip-9073 with *just* the last patch applied.
- 11:20 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you using strace to catch the ceh-osd command? Please using strace -f to cache all child process.
Thanks! - 11:14 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Back to seeing the same error (invalid argument) with this latest patch :-(
- 10:58 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Makr, i don't find the reason. But i think this bug may caused by patch. So i modify my patch and hope the bug don't ...
- 10:58 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- ...suggests a memory overwrite problem - we really need to get the binaries running under valgrind!
- 08:11 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- With that last patch applied, journal header looks good every mkfs and osd is starting every time.
- 07:47 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Yes. It's a great step. A strange bug.
The attachment is a patch which add read_header on some place.Can you try t... - 07:41 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Very interesting: *somethimes* after the mkfs the header looks like:
0000000 b000 02b5 0000 0000 0001 0000 0000 00... - 07:12 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Will do.
- 06:57 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- But from the code, when start osd, read journal-header is the first thing for journal.
I don't know the command 's... - 06:54 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Hmmm - just checked again and got:
$ hexdump journalblk-prestart.txt|head -1
0000000 3000 02a0 0000 0000 0001 000... - 06:45 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Funny you should mention that, I had just check that myself:
So, just after the mkfs, journal header is:
$ hexd... - 06:30 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Hi Mark,
I use different on my hand but i can't reproduce this.
From the deply.sh, for osd operation
1:ceph-osd ... - 03:33 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you use "strace -f ceph-osd .." to trace all syscall?
We may from the info find some clue. - 03:20 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- No, sorry,
$ sudo dd if=/dev/zero of=/dev/sdc1 bs=512
$ sudo ./deploy.sh
is the prescription. The result is os... - 03:08 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Are you mean if you zero the journal-disk then the osd can start? Otherwise, it will met this bug.
- 03:04 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Sure - I'm running the script attached initially - now using a minor variation thereof (attached again).
The only ot... - 02:40 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- The first 8 byte of journal-header destroyed. But the debug info show the content of journal-header is right.
Now ... - 02:06 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Also, I note that running
$ sudo ceph-osd -i 0 --mkjournal
results in a journal state that lets the osd start, ... - 01:38 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Shame about no 520, but here are the files.
- 11:07 PM Revision 164cfe85 (ceph): erasure-code: parse function for the mapping parameter
- Each D letter is a data chunk. For instance:
_DDD_DDD
is going to parse into:
[ 1, 2, 3, 5, 6, 7 ]
the 0 a... - 11:07 PM Revision 5c2d2320 (ceph): erasure-code: remap chunks if not sequential
- If the remap vector is not empty, use it to figure out the sequence of
data chunks.
http://tracker.ceph.com/issues/9... - 11:07 PM Revision 298da45c (ceph): erasure-code: ErasureCodeInterface::get_chunk_mapping()
- Add support for erasure code plugins that do not sequentially map the
chunks encoded to the corresponding index. This... - 11:06 PM Revision ffac52b3 (ceph): rgw: disable civetweb url decoding
- Fixes: #8621
We want to have the raw request uri, as we do the decoding ourselves.
Signed-off-by: Yehuda Sadeh <yeh... - 11:06 PM Revision 1293e6ba (ceph): rgw: log civetweb messages
- Handle the civetweb log_message callback, divert messages into our debug
log.
Signed-off-by: Yehuda Sadeh <yehuda@re... - 11:06 PM Revision 0e74b7a1 (ceph): rgw: don't allow negative / invalid content length
- Certain frontends (e.g., civetweb) don't filter such requests.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 11:06 PM Revision 240764fc (ceph): rgw: update civetweb submodule
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 11:02 PM Revision 8fb47299 (ceph): Merge remote-tracking branch 'gh/next'
- 10:28 PM Revision 95ac43f3 (ceph): FileStore: remove the fdcache_lock
- With the changes to the shared_cache, we no longer need the fdcache_lock
to prevent us from inserting a second fd for... - 10:28 PM Revision b04d84db (ceph): shared_cache: pass key (K) by const ref in interface methods
- Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
- 10:28 PM Revision 78d70daf (ceph): FileStore: Index caching is introduced for performance improvement
- IndexManager now has a Index caching. Index will only be created if not
found in the cache. Earlier, each op is creat... - 10:28 PM Revision cfff9f6a (ceph): FileStore: FDCache lookup is rearranged
- In lfn_open() there is no point of building the Index if the
cache lookup is successful and caller is not asking for ... - 10:28 PM Revision 3e7848d5 (ceph): FileStore: No need to hold Index lock during omap calls
- The Index lock is held during all the omap calls which is
not necessary.
Signed-off-by: Somnath Roy <somnath.roy@san... - 10:28 PM Revision b24db81e (ceph): FileStore: Introduced a RLock instead of WLock
- While calling index->collection_version, there is no need to
hold WLock at the index level. RLock should be sufficien... - 10:26 PM Revision a9f76d43 (ceph): FDCache: implement a basic sharding of the FDCache
- This is just a basic sharding. A more sophisticated implementation would
rely on something other than luck for keepin... - 09:11 PM Revision 4c2828ed (ceph): shared_cache: expose prior existence when inserting an element
- The LRU now handles you attempting to insert multiple values for the
same key, by telling you that you've done so and... - 08:50 PM Revision 435c6d6c (ceph): Merge pull request #2235 from kevincox/wireshark
- doc: Add documentation about Wireshark dissector.
Reviewed-by: Sage Weil <sage@redhat.com> - 08:45 PM Revision a1e79dbb (ceph): rgw_admin: add --min-rewrite-stripe-size for object rewrite
- A new param to check whether the object has requires restriping,
checking whether a specific object stripe is bigger ... - 08:42 PM Revision 46d8c97e (ceph): doc: Add documentation about Wireshark dissector.
- Signed-Off-By: Kevin Cox <kevincox@kevincox.ca>
- 08:35 PM Revision 6a555434 (ceph): rgw: fix compilation
- RGWRadosPutObj couldn't refer to the ceph context.
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Yehuda Sa... - 08:28 PM Revision f6771f20 (ceph): shared_cache: use a single lookup for lookup() too
- We didn't convert this one to use iterators before.
Signed-off-by: Greg Farnum <greg@inktank.com> - 08:18 PM Revision cec40dae (ceph): qa/workunits/cephtool: verify setmaxosd doesn't let you clobber osds
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:58 PM Revision a1c3afb6 (ceph): OSDMonitor: Do not allow OSD removal using setmaxosd
- Description: Currently setmaxosd command allows removal of OSDs by providing
a number less than current max OSD numbe... - 06:38 PM Revision 16a43609 (ceph): rgw: pass set_mtime to copy_obj_data()
- Sometimes we need to set the mtime when copying object data (e.g., when
we rewrite the obj).
Signed-off-by: Yehuda S... - 06:28 PM Revision 800eff24 (ceph): rgw: copy_obj_data() uses atomic processor
- Fixes: #9089
copy_obj_data was not using the current object write infrastructure,
which means that the end objects w... - 06:27 PM Revision a8cabfa6 (ceph): Merge pull request #2257 from ceph/wip-8784
- rgw: call throttle_data() even if renew_state() failed
Reviewed-by: Sage Weil <sage@redhat.com> - 06:25 PM Revision 5d3a7e59 (ceph): rgw: copy object data if target bucket is in a different pool
- Fixes: #9039
Backport: firefly
The new manifest does not provide a way to put the head and the tail in
separate pool... - 06:06 PM rgw Bug #9125 (Resolved): rgw: swift tests fail with civetweb
- logs are copied to ubuntu@mira042.front.sepia.ceph.com:/home/ubuntu/civetweb_swift...
- 05:57 PM rgw Bug #8971 (Duplicate): rgw: s3 test failures with civetweb
- 05:56 PM rgw Bug #8971: rgw: s3 test failures with civetweb
- s3tests now pass on wip-8621 branch.
- 05:55 PM rgw Bug #8621: civetweb frontend fails authentication if URL has special chars
- s3tests passed with recent changes to wip-8621.
- 05:39 PM Bug #9058 (Need More Info): rest-api: long-running process may fail 'tell osd...' due to stale os...
- ok, my theory doesn't seem right.. Objecter is checking for a new map if it gets ENXIO or similar. enabled logging i...
- 05:36 PM devops Bug #8330 (Resolved): repodata on rpm repos do not list latest ceph-deploy (1.5.2)
- Thanks for verifying.
- 05:33 PM devops Bug #8976 (Fix Under Review): httpd on RHEL7 (RHEL repo) incompatible with mod_fastcgi (ceph repo)
- We have a new version available out at:
http://gitbuilder.ceph.com/apache2-rpm-rhel7-x86_64-basic/ref/master/
A... - 05:13 PM Bug #8895: ceph osd pool stats (displayed incorrect values)
- Can probably close this as dupe of #5884?
- 04:14 PM CephFS Bug #9101: multimds: unlinked file is not pruned from replica mds caches
- 03:36 PM Revision 8393fdea (ceph): Merge pull request #2251 from ceph/wip-9102
- ceph-disk: linter cleanup
Reviewed-by: Sage Weil <sage@redhat.com> - 03:28 PM Revision 2fc76d6e (ceph): Merge pull request #86 from dachary/wip-9027-create-unique-pool
- rados.py: avoid CephManager creation race
- 03:24 PM Revision 4783b378 (ceph): Merge pull request #87 from dachary/wip-8988-default-idle-timeout
- rgw: add default_idle_timeout to allow override
- 03:20 PM CephFS Bug #9123 (Can't reproduce): kceph: had 130k+ inodes with write caps
- in #9121 the client had more than 130k inodes open for write, resulting in a huge file recovery queue. there definit...
- 02:37 PM CephFS Bug #9121 (In Progress): mds: inode stuck recovering after client restart
- recovery is working.. there are just a lot of inodes queued:
2014-08-14 14:40:06.695087 7fd45f757700 10 mds.0.cach... - 02:10 PM CephFS Bug #9121 (Resolved): mds: inode stuck recovering after client restart
- ...
- 02:02 PM Revision aec684bf (ceph): add calamari to the api/index section
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 01:51 PM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- John Spray wrote:
> This is happening when the librbd-using client is blacklisted, ObjectCacher fails to flush when ... - 10:16 AM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- This is happening when the librbd-using client is blacklisted, ObjectCacher fails to flush when requested, and ImageC...
- 09:44 AM CephFS Bug #9105: ~ObjectCacher behaves poorly on EBLACKLISTED
- Started failing in 061c8e93f76dc4fd6290d6d15723d76e73267444 where rbd_cache and rbd_cache_writethrough_until_flush we...
- 01:50 PM Revision 321d4def (ceph): Merge pull request #2255 from ceph/wip-9062
- msg/PipeConnection: make methods behave on 'anon' connection
Reviewed-by: John Spray <john.spray@redhat.com> - 01:44 PM Revision f10a1384 (ceph): Merge remote-tracking branch 'origin/next'
- 01:29 PM Revision d0331a96 (ceph): Merge pull request #2254 from ceph/wip-8725
- mds: fix MDSMap encoding to be backward-compatible
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: John Sp... - 01:17 PM rgw Bug #8988 (Resolved): AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- 12:33 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- "the suite runs ok":http://pulpito.ceph.com/loic-2014-08-14_14:25:55-upgrade:firefly-x:stress-split-wip-9025-chunk-re...
- 05:55 AM rgw Bug #8988 (Fix Under Review): AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- "need review":https://github.com/ceph/ceph-qa-suite/pull/87
- 05:36 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- The reason why "the suite fails":http://pulpito.ceph.com/loic-2014-08-14_09:47:05-upgrade:firefly-x:stress-split-wip-...
- 12:53 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- It failed for the same reason. "Rescheduled once more, hoping the problem has been fixed":http://pulpito.ceph.com/loi...
- 01:13 PM Bug #8865 (Resolved): cep osd setmaxosd doesn't check if osds exist
- 01:09 PM Revision ac70490d (ceph): doc: update kernel recommendations (avoid 3.15!)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:53 PM Revision 54a7298c (ceph): rgw: add default_idle_timeout to allow override
- Globally overriding the rgw idle_timeout is not possible because it it
needs to be done on a per client.0, client.1, ... - 12:37 PM Feature #9025: erasure-code: chunk remapping
- Now that the teuthology + MDS bugs are fixed, the following job will be scheduled to exercise remapping:...
- 11:10 AM Bug #9119 (Resolved): READFORWARD ordering bug
- READFORWARD is forwarding RWORDERED reads.
- 11:06 AM devops Feature #9118: ceph-deploy: Add pre-generated keys to a Monitor
- Any keys (client.admin or otherwise) in the keyring file passed to "ceph-mon --mkfs --keyring <foo>" will get seeded ...
- 10:56 AM devops Feature #9118 (Resolved): ceph-deploy: Add pre-generated keys to a Monitor
- ceph-authtool can be used to generate a key and keyring before a Ceph cluster is running, if a user has access to the...
- 10:54 AM Feature #9083 (Closed): Standalone script to generate Ceph keys
- Feature already exists in ceph-authtool
- 09:34 AM Bug #9113: osd: snap trimming eats memory, linearly
- a few notes:...
- 06:40 AM Bug #9113 (Resolved): osd: snap trimming eats memory, linearly
- - rados pool snapshot taken weekly
- trimmed when >30 days old
- trimming makes some osds consume memory linearly
... - 09:06 AM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- ubuntu@teuthology:/a/sage-2014-08-13_15:28:18-rados-next-testing-basic-multi/422862
- 09:05 AM Bug #9114: osd: segv in build_push_op
- note: i manually killed ceph_test_rados to make teuthology clean up
- 07:09 AM Bug #9114 (Duplicate): osd: segv in build_push_op
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-08-13_15:28:18-rados-next-testing-basic-multi/422759...
- 08:57 AM Revision 6237acb3 (ceph): rados.py: avoid CephManager creation race
- gevent may hold the rados.py thread when it has an opportunity. The
if not hasattr(ctx, 'manager'):
must therefo... - 08:33 AM Bug #9102 (Resolved): ceph-disk has undefined variables
- 07:51 AM Bug #9102 (Fix Under Review): ceph-disk has undefined variables
- PR opened https://github.com/ceph/ceph/pull/2251
- 07:58 AM rgw Documentation #9116 (Resolved): rgw: broken link
- From Luis Pabon:...
- 07:21 AM devops Bug #9066 (Rejected): Need ceph-deploy to be able to run to JUST generate ceph.conf and keyring w...
- The initial issue was misunderstood, ceph-deploy already is able to create a ceph.conf and a mon keyring. Other requi...
- 06:47 AM Bug #9062 (Resolved): Mon segfault in waitlist_or_zap_client
- 06:40 AM Bug #9112 (In Progress): (wip-objecter) librados notify calls freezing
- 06:39 AM Bug #9112: (wip-objecter) librados notify calls freezing
- Client log with objecter and librados debug logging at 20 in teuthology:~/jcsp/9112
- 06:28 AM Bug #9112 (Resolved): (wip-objecter) librados notify calls freezing
Hitting this in rbd tests, periodically the ceph_test_rados_fsx process gets stuck inside IoCtxImpl::notify
<pre...- 06:34 AM CephFS Bug #8725 (Resolved): mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- 06:16 AM devops Feature #9103: create a (generic) webservice to handle Sphinx documentation versions
- 1.- Adding something to the Sphinx build is non-trivial. Sphinx extensions (the right way to do this) are very comple...
- 04:47 AM Revision 69ef8545 (ceph): s/apache2/apache
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 03:36 AM Revision 5374386e (ceph): doc: Added user management link to quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:30 AM Revision 5e8eae72 (ceph): doc: Removed cephx intro. Moved details to user management, config, and...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:29 AM Revision 3aa3e96b (ceph): doc: Removed cephx guide. Replaced by user management.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:28 AM Revision aac6aa2a (ceph): doc: Removed auth intro and auth docs and added user management to index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:28 AM Revision 4c651b7d (ceph): doc: Restructured auth configuration reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 3faf37a3 (ceph): doc: Put architectural details of authentication in to architecture doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 118ae726 (ceph): doc: Created a new User Management doc to replace authentication.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 02:48 AM Bug #9111: PG stuck with 'active+remapped' forever with cluster wide change (add/remove OSDs)
- Right after I filed this bug, I got some clue, I found the problem came from those removed OSDs (which has status DNE...
- 02:01 AM Bug #9111 (Won't Fix): PG stuck with 'active+remapped' forever with cluster wide change (add/remo...
- After adding/removing OSDs, some PGs stuck with 'active+remapped' forever.
1. ceph -s
-bash-4.1$ ceph -s... - 01:35 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- Thanks Sage , the issue has been resolved, cluster is Healthy now.
- 12:52 AM Revision 0a49db8e (ceph): msg/PipeConnection: make methods behave on 'anon' connection
- The monitor does a create_anon_connection() to create a pseudo Connection
object for forwarded messages. If we try t... - 12:21 AM Revision 662af7ac (ceph): osd: fix pg epoch floor tracking
- If you call erase() on a multiset it will delete all instances of a value;
we only want to delete one of them. Fix t... - 12:21 AM Revision 289360c5 (ceph): osd: prevent pgs from getting too far ahead of the min pg epoch
- Bound the range of PG epochs between the slowest and fastest pg
(epoch-wise) with 'osd map max advance'. This value ... - 12:21 AM Revision ad82f281 (ceph): osd: add sanity check/warning on a few key configs
- Warn when certain config values are set to bad values.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@in... - 12:21 AM Revision fac5bfaf (ceph): osd: introduce simple sleep during scrub
- This option is similar to osd_snap_trim_sleep: simply inject an optional
sleep in the thread that is doing scrub work... - 12:21 AM Revision 9f29788f (ceph): common/io_priority: wrap ioprio_set() and gettid()
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a2b49110ef65efd526c3430ad03c988ca9dde768) - 12:21 AM Revision b75f85a2 (ceph): common/Thread: allow io priority to be set for a Thread
- Ideally, set this before starting the thread. If you set it after, we
could potentially race with create() itself.
... - 12:21 AM Revision 11858d7e (ceph): common/WorkQueue: allow io priority to be set for wq
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit dd6badcb5eedfec6748b3e6ca4d46e3b266038f6)
Con... - 12:21 AM Revision 9ca451a6 (ceph): osd: allow io priority to be set for the disk_tp
- The disk_tp covers scrubbing, pg deletion, and snap trimming
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pic... - 12:21 AM Revision 229a346d (ceph): osd: track per-pg epochs, min
- Add some simple tracking so that we can quickly determine what the min
pg osdmap epoch is.
Signed-off-by: Sage Weil ...
08/13/2014
- 11:49 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Mark, i can't find the ssd in lab.
And i also can't find the code.But from my two patch, i don't modify code which c... - 07:08 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- hexdump journalblk.txt
0000000 1000 03ce 0000 0000 0001 0000 0000 0000
0000010 bdb9 29ac 51d7 a343 3bbf 1114 622e... - 06:51 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Here's the 4096 bytes of sdc1
- 06:41 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- For the code,there is a logic error.
int r = ::pread(fd, bp.c_str(), bp.length(), 0);
bl.push_back(bp);
try ... - 06:21 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you read the 4096 of /dev/sdc1 and send to me?
The journal header is in first 4096 size. - 06:12 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- The info for the Intel 520:
Re more journal debugging - sure, I already have the following set:
[osd]
debug os... - 06:09 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- The script puts in symlinks (also note slightly different osd data path on the work machine):
$ ls -l /var/lib/cep... - 06:04 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- From you message, I found:
14-08-14 10:58:01.735317 7f944f5e4800 20 journal _check_disk_write_cache: disk write cach... - 05:36 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you send the 520 disk-info using hdparm to me?
I'll search the lab try to find this ssd.
Thanks!
- 05:13 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Can you print more debuginfo about journal?
From the messages:
journal read_header error decoding journal header
... - 03:58 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Doing a secure erase of the 520's changes nothing. Still seeing problem 2/ 'invalid argument' opening the journal.
- 01:55 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- An aside thought - to rule out weird ssd related stuff I had performed a secure erase on the Crucial m4's while inves...
- 01:40 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I'm happy to report that wip-9073 definitely fixes problem 1/ (the hang).
- 01:04 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- to (hopefully) clarify the errors:
- Home machine: osd mkfs hangs (which I've called 1/)
- work machine: osd mkfs... - 12:56 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Interesting... I'm just building wip-9073 on my home machine now, will update you with what I find.
The issue *mig... - 11:36 PM Revision 85129047 (ceph): lttng: Support --with-lttng=check
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 11:17 PM Revision 6411dae9 (ceph): Merge pull request #85 from dachary/wip-rgw-idle-timeout
- overrides: rgw must not be nested in ceph
- 11:01 PM Revision bb046ed0 (ceph): mon/Paxos: put source mon id in a temp variable
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:49 PM Revision f00afcc4 (ceph): overrides: rgw must not be nested in ceph
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:05 PM Revision d74d3f1c (ceph): mds/MDSMap: fix incompat version for encoding
- Back in 8f7900a09c8e490c9cd3a6f92ed1f0eb1f47f2a9 we added the new fields
before the 'extended' section, which made th... - 10:03 PM Revision 369c6392 (ceph): mds/MDSMap: drop trailing else in favor of early return
- This keeps the old-version special cases in one place and make it obvious
what the current/forward-looking path is.
... - 09:17 PM rgw Feature #8473: rgw: Shard bucket index objects to improve single bucket PUT throughput
- Here is the first patch - https://github.com/ceph/ceph/pull/2187
- 09:16 PM Bug #7521 (Won't Fix): Add more events (hold object context) to OpTracker to better analyze perfo...
- With more understanding of the tracker, I found actually the issue being tracked by this but can be achieved by the c...
- 09:14 PM Bug #7710 (Resolved): Multiple rados bench instance will overwrite the metadata object
- 09:11 PM Revision 0f6956b3 (ceph): Merge remote-tracking branch 'upstream/next'
- 09:10 PM Revision e74ad5f8 (ceph): Merge pull request #2252 from ceph/wip-9087
- test/system/systest_runnable.cc: debugging on start and end
Reviewed-by: Sage Weil <sage@redhat.com> - 09:10 PM Revision 473f4bd3 (ceph): Merge remote-tracking branch 'gh/next'
- 09:10 PM Documentation #6142: Ceph needs mor than 32k pids
- John, not sure where this should go in the doc structure...
- 09:08 PM Revision b2c1fa86 (ceph): test/system/systest_runnable.cc: debugging on start and end
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:00 PM Revision d74ed9d5 (ceph): ceph-disk: linter cleanup
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:58 PM Revision c6292416 (ceph): rbd-replay: Convert prep-for-replay.py to rbd-replay-prep.cc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision febcce92 (ceph): rbd-replay: Add man page and package binaries for rbd-replay-prep
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision b5bc14ab (ceph): rbd-replay: Move tracepoints from internal.cc to librbd.cc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 89c38602 (ceph): rbd-replay: Remove extent tracepoints and inline extents
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 520b75b5 (ceph): rbd-replay: Fix bug in rbd-replay-prep, Thread::issued_io with wrong IO
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 3efa30d2 (ceph): lttng: Remove tracing from libcommon
- This is a short-term fix for issues caused by tracepoints in libcommon.
Code crashes at runtime if the same tracepoin... - 08:58 PM Revision 77cf0348 (ceph): rbd-replay: Switch ImageNameMap to using rbd_loc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 6be0c2b3 (ceph): rbd-replay: Switch ImageNameMap from regex to plain string matching
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision a602bd42 (ceph): rbd-replay: Fix compiler warning in unit tests
- Was getting:
test/test_rbd_replay.cc:44:3: warning: converting ‘false’ to pointer type for argument 1 of ‘char testin... - 08:58 PM Revision 86d0b576 (ceph): rbd-replay: Remove boost_regex from LIBADD and LDADD
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision de9327ca (ceph): lttng: Replace Boost dependencies with custom string code
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 95e3b0b7 (ceph): rbd-replay: Remove outdated message that says regexes are used
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision dca21ee8 (ceph): rbd-replay: Add man page, and add binaries to Debian packaging
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision ecd20a35 (ceph): lttng: Preload liblttng-ust-fork.so in TESTS_ENVIRONMENT
- This adds LD_PRELOAD=liblttng-ust-fork.so to TESTS_ENVIRONMENT.
This prevents lttng from complaining when processes a... - 08:58 PM Revision b9151612 (ceph): rbd-replay: Add unit tests
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision d66ee7a3 (ceph): rbd-replay: Use non-zero fake data
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision ee4d2170 (ceph): rbd-replay: Support replaying partial traces
- Tracing may start after the application is started, and image open calls
may missed. To support replaying these trace... - 08:58 PM Revision 11f55de8 (ceph): lttng: Fix ceph_ctf_stringp
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 0b68f01a (ceph): rbd-replay: Use standard image@snap instead of image/snap
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 429a0891 (ceph): rbd-replay: Add rbd_replay::rbd_loc
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision bbdd0dab (ceph): rbd-replay: Add command-line arguments to prep-for-replay.py
- Includes:
--print-on-read
--print-on-write
--window
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 08:58 PM Revision 3a20acb3 (ceph): lttng: Default to not storing buffer content
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 02743766 (ceph): rbd-replay: Add assertions
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision c83856c6 (ceph): rbd-replay: Add --pool option
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision ff2b9f5f (ceph): rbd-replay: Add --map-image option for image name mapping
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision ae4e02a3 (ceph): lttng: Fix 'make check' by setting up fake HOME
- If the HOME variable is not set, LTTng complains, and the extra output
fails to match what the tests expect, so they ... - 08:58 PM Revision c938829b (ceph): lttng: Disable LTTng by default, add --with-lttng configure option
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision a7da7e05 (ceph): rbd-replay: Fix memory leak in PendingIO
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 0a629a9f (ceph): doc: Add usage comment to librbd::RBD::AioCompletion
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision d4e07f03 (ceph): rbd-replay: Add --latency-multiplier option to usage statement
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision b58797e0 (ceph): rbd-replay: Hash completions across multiple mutexes to reduce contention
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 4f6e775c (ceph): rbd-replay: Clean up prep-for-replay.py
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 9a318083 (ceph): rbd-replay: Fix examples/rbd-replay/replay
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 11186aff (ceph): rbd-replay: Add --read-only flag
- Removes ignoreWrites flag in prep-for-replay.py
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 08:58 PM Revision b11ab2ea (ceph): rbd-replay: Fix async writes in prep-for-replay.py
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 9ec70b97 (ceph): rbd-replay: Add rbd_replay subsystem
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision d8a86bfb (ceph): rbd-replay: Bugfix: ensure PendingIOs are added before they're removed
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 84edf375 (ceph): rbd-replay: Printing pending IOs when worker threads waiting to die
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision c4ba9972 (ceph): rbd-replay: Change Worker::m_pending_ios from vector to map
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 0129841f (ceph): rbd-replay: Print "Still waiting for" more judiciously
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision e06e979b (ceph): rbd-replay: Support writing Actions to ostreams
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision a06e347a (ceph): rbd-replay: Check that return values are non-negative
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 289c98df (ceph): lttng: Remove 'ver' from trace in code for CEPH_OSD_OP_NOTIFY
- 'ver' is obsolete and variable exists only for proper deserialization
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 08:58 PM Revision 4001b28d (ceph): lttng: Basic tracing of librbd
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision ef5c30af (ceph): tracing: instrument filestore
- This adds objectstore tracepoints for the filestore. It'd be nice to add
these to the objectstore interface some how ... - 08:58 PM Revision cffb8f3b (ceph): lttng: Add more tracing to librbd
- Includes:
- aio_complete
- aio_discard
- aio_flush
- aio_get_return_value
- aio_is_complete
- aio_read
- aio_wait_for... - 08:58 PM Revision b73af7c0 (ceph): lttng: Add rbd-replay
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision fc712844 (ceph): rbd-replay: Switch logging from cout to dout
- To enable logs, we also have to use global_init to parse our
command-line args, so we now have other standard Ceph go... - 08:58 PM Revision 6d987ce7 (ceph): Add assertf macro
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision fb45d605 (ceph): lttng: Trace ReplicatedPG::do_osd_ops
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 3e21f8e4 (ceph): lttng: Add tracing-common.h
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 1dcf8477 (ceph): examples: Add example for the librados C API
- Simply copied and modified the C++ API example.
Signed-off-by: Adam Crume <adamcrume@gmail.com> - 08:58 PM Revision c4f29afa (ceph): lttng: Trace librados C API
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision be3c9133 (ceph): lttng: Prevent creation of incorrect .o files when generating from .tp
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 50020b06 (ceph): lttng: Prevent deletion of tracing-common.h when cleaning
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 8e238b51 (ceph): lttng: Split up libtracepoints
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 090f63e1 (ceph): lttng: trace mutex::unlock
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 8a28388c (ceph): lttng: add pg and osd tracepoints
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 64fbc28f (ceph): lttng: Check for lttng/tracepoint.h when configuring
- 08:58 PM Revision 2f2d6e1d (ceph): tracing: automake-ify tracepoint generation
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision d5b16e4a (ceph): lttng: Trace OpRequest
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 469c9377 (ceph): lttng: Add rmw_flags to tracepoint in PG::queue_op
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 08:58 PM Revision 7a9eb3fc (ceph): tracing: bootstrap lttng-ust with mutex events
- See src/tracing/README.md
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 08:32 PM Revision aaeebceb (ceph): mon: fix divide by zero when pg_num adjusted and no osds
- Fixes: #9052
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
Manual backport of 239401db7b515... - 08:32 PM Revision 38c3a3c0 (ceph): mon: fix divide by zero when pg_num adjusted and no osds
- Fixes: #9052
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 239401... - 08:31 PM Revision c5687b13 (ceph): mon: fix potential divide by zero on can_mark_{down,out}
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:31 PM Revision 239401db (ceph): mon: fix divide by zero when pg_num adjusted and no osds
- Fixes: #9052
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 08:15 PM Revision f81d2b0e (ceph): mon: fix divide by zero when pg_num adjusted and no osds
- Fixes: #9101
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 08:15 PM Revision 8a647f7d (ceph): mon: fix potential divide by zero on can_mark_{down,out}
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:55 PM Revision 87bf00a2 (ceph): ceph_test_rados_api_tier: fix cache cleanup (ec too)
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit d7fb7bf5f2059f411633751e376c2270e6040fba) - 07:55 PM Revision 3be0d731 (ceph): ceph_test_rados_api: fix cleanup of cache pool
- We can't simply try to delete everything in there because some items may
be whiteouts. Instead, flush+evict everythi... - 07:55 PM Revision 7f511ef7 (ceph): librados/TestCase: inheret cleanup_default_namespace
- No need to duplicate this code.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 1d199fb1173dc9... - 07:54 PM Revision b3fd9612 (ceph): Merge pull request #2236 from ceph/wip-9055
- ceph_test_rados_api_tier: fix cache pool cleanup during test
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:40 PM Revision 14f73e03 (ceph): Merge pull request #2222 from ceph/wip-9029
- mds: Make min/max UID configurable for who is allowed to create a snapsh...
Reviewed-by: Sage Weil <sage@redhat.com> - 07:07 PM Revision 5ed9f4ee (ceph): mds: Revert from mds_mksnap_ setting to mds_snap_ settings
- 07:00 PM Revision 6f7798e3 (ceph): ceph-disk: warn about falling back to sgdisk (once)
- This way the user knows something funny might be up if dmcrypt is in use.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:52 PM Revision c7a1ceba (ceph): ceph-disk: display information about dmcrypted data and journal volumes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:52 PM Revision b75e8a34 (ceph): ceph-disk: add get_partition_base() helper
- Return the base devices/disk for a partition device.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:52 PM Revision b1651afb (ceph): ceph-disk: only fall back to sgdisk for 'list' if blkid seems old
- If the blkid doesn't show us any ID_PART_ENTRY_* fields but we know it is
a GPT partition, *then* fallback. Otherwis... - 06:20 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- Loic, we had disk failed and possibly due to that suite failed (guessing), I re-started it http://pulpito.front.sepia...
- 04:11 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- Waiting for "Shipping apache config":https://github.com/ceph/ceph-qa-suite/blob/master/tasks/rgw.py#L82 with...
- 04:04 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- "running a suite using the new VPS.yaml":http://pulpito.ceph.com/loic-2014-08-14_01:02:11-upgrade:firefly-x:stress-sp...
- 03:47 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- "fix indentation of rgw override":https://github.com/ceph/ceph-qa-suite/pull/85
- 03:35 PM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- To confirm there is a large delay requiring a large idle_timeout:...
- 03:33 PM rgw Bug #8988 (In Progress): AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- 05:48 PM Revision 561208af (ceph): Merge pull request #2249 from ceph/wip-9096
- osd: fix require_same_peer_instance from fast_dispatch
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: ... - 05:35 PM Revision 4a5c93a9 (ceph): osd/ReplicatedPG: only do agent mode calculations for positive values
- After a split we can get negative values here. Only do the arithmetic if
we have a valid (positive) value that won't... - 05:34 PM Revision 5be56ff8 (ceph): osd/ReplicatedPG: only do agent mode calculations for positive values
- After a split we can get negative values here. Only do the arithmetic if
we have a valid (positive) value that won't... - 04:38 PM Revision 7b3714ce (ceph): osd: fix some line wrapping
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:30 PM Bug #9109 (New): ceph CLI: Help is missing -k keyring option
- The ceph command line should provide a -k keyring argument. "ceph --help" does not appear to list the -k option for t...
- 04:28 PM Bug #9087 (Need More Info): ceph_test_rados_list_parallel hang
- 02:21 PM Bug #9087: ceph_test_rados_list_parallel hang
- added some debugging.
- 12:47 PM Bug #9087: ceph_test_rados_list_parallel hang
- Looking
- 04:22 PM Bug #9053: mon/Paxos.cc: 628: FAILED assert(begin->last_committed == last_committed)
- Paxos::handle_last() bug.
the peon:... - 04:17 PM Bug #9053: mon/Paxos.cc: 628: FAILED assert(begin->last_committed == last_committed)
- 04:13 PM Revision 0b2a8472 (ceph): s/apache/apache2
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 04:09 PM Revision 90379e0b (ceph): Added a facet to test both apache and civetweb as frontend for rgw
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 04:05 PM Revision 42d66dee (ceph): Merge pull request #83 from ceph/wip_add_manual_override2
- Added idle_timeout: to fix time-outs problems for some tests
- 03:59 PM Revision b5f7d843 (ceph): bug 8927: enable civetweb testing for rgw
- 03:35 PM CephFS Bug #8964 (Resolved): kcephfs: client does not resend requests on mds restart
- 03:30 PM Revision df945a90 (ceph): osd: fix require_same_peer_instance from fast_dispatch
- The mark-down of old peers needs to take the session_dispatch_lock in order
to safely clear the Session ref cycle. H... - 03:29 PM Revision 74025f91 (ceph): Fixed syntax
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:24 PM Revision 90f647f4 (ceph): Added idle_timeout: to fix time-outs problems for some tests
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:20 PM Revision 3d7e2b35 (ceph): osd: inline require_osd_up_peer
- There is only one caller.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:13 PM CephFS Bug #8725 (Fix Under Review): mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic...
- https://github.com/ceph/ceph/pull/2254
- 03:06 PM Revision 374c3a8e (ceph): Merge pull request #81 from ceph/wip_add_manual_override
- Added overrides for vps time outs
- 02:46 PM Cleanup #9106: ceph-authtool: Modifying user without --gen-key overwrites the key
- Wasn't able to reproduce this after retrying. Maybe just a usage issue.
- 02:24 PM Cleanup #9106 (Resolved): ceph-authtool: Modifying user without --gen-key overwrites the key
- If you are trying to modify a user's caps/permissions using ceph-authtool, and the user has an existing key, specifyi...
- 02:37 PM RADOS Feature #9108 (New): ceph auth get: Get multiple users
- The "ceph auth get <user>" command with the -o option is an ideal way to create a keyring for an individual user. How...
- 02:37 PM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- Hmm, most likely a bug in repair. We should start by creating a teuthology task which reproduces the bug. Once we h...
- 02:27 PM RADOS Feature #9107 (New): ceph-authtool: Delete a user.
- Currently, there is no corresponding "delete" feature that allows a user to delete a user from a keyring. We should h...
- 02:25 PM Feature #8389 (Resolved): osd: clean up old ec objects more aggressively
- 02:25 PM Feature #8480 (Resolved): modify scrub to detect/repair obsolete rollback objects
- 02:15 PM CephFS Bug #9105 (New): ~ObjectCacher behaves poorly on EBLACKLISTED
In ceph master 78dc4df
http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-11_23:00:01-rbd-master-testing-bas...- 01:59 PM devops Feature #9103: create a (generic) webservice to handle Sphinx documentation versions
The calamari docs already include a version (albeit a rather verbose one including the git hash). I guess with a l...- 01:06 PM devops Feature #9103 (Resolved): create a (generic) webservice to handle Sphinx documentation versions
- None of our docs allow a user to:
* Have a visual queue of what version of the docs they are seeing.
* be warned ... - 01:44 PM CephFS Bug #8962: kcephfs: client does not release revoked cap
- ...
- 01:19 PM CephFS Bug #8962: kcephfs: client does not release revoked cap
- ...
- 01:39 PM CephFS Bug #9101: multimds: unlinked file is not pruned from replica mds caches
- looks like the problem is that another mds has the inode in its cache and isn't trimming it (or being asked to trim i...
- 01:13 PM CephFS Bug #9101 (Fix Under Review): multimds: unlinked file is not pruned from replica mds caches
- https://github.com/ceph/ceph/pull/2250
- 11:36 AM CephFS Bug #9101: multimds: unlinked file is not pruned from replica mds caches
- Here is the debug data when using a ceph-fuse client.
We did reproduce the problem - 11:15 AM CephFS Bug #9101 (New): multimds: unlinked file is not pruned from replica mds caches
- as a result, deleted files stay pinned for a long time and space does not get removed.
- 01:35 PM Bug #9055 (Resolved): LibRadosTwoPoolsPP.HitSetWrite (and others) fail on remove of whiteout
- 01:30 PM Bug #9052 (Resolved): ceph-mon crashes with *** Caught signal (Floating point exception) **
- 12:38 PM CephFS Feature #9029 (Resolved): min/max uid for snapshot creation
- 11:59 AM Bug #9102 (Resolved): ceph-disk has undefined variables
- We fail to track them because the build doesn't yell at us, in the meantime, those should be fixed....
- 10:46 AM Bug #9096 (Resolved): OSD::require_same_peer_instance fails to acquire lock
- 10:23 AM Bug #9096 (Fix Under Review): OSD::require_same_peer_instance fails to acquire lock
- https://github.com/ceph/ceph/pull/2249
- 03:38 AM Bug #9096: OSD::require_same_peer_instance fails to acquire lock
- It is the cause of http://tracker.ceph.com/issues/9074
- 03:37 AM Bug #9096 (Resolved): OSD::require_same_peer_instance fails to acquire lock
- It can be reproduced by running a few times (less than 5) *qa/workunits/cephtool/test.sh -t mon_osd*. It will eventua...
- 10:41 AM Revision e86fdefe (ceph): rgw: move generic server usage after all options
- Since generic_server_usage() exits after printing the options, any other
help options should be printed before that. ... - 10:33 AM Bug #9082 (Resolved): Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before ...
- 09:11 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- i've pushed wip-9082-firefly... can you please try this and see if it avoids the crash? i was looking for a divide b...
- 08:34 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- Hello Sage
Thanks for your time checking this bug. As required i have found some PG’s and 3 OSDs which are making... - 08:24 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- Hello Sage
As i have found some PG / OSD that make agent_choose_mode() unhappy. I am attaching logs of 2 differen... - 09:22 AM Feature #9097 (New): request for tools/commands to see hits/misses on cache pools
- request for tools/commands to see hits/misses on cache pools
- 07:23 AM Bug #9085 (Resolved): erasure-code: ISA plugin does not load
- The isa plugin "wip-firefly-isa":https://github.com/ceph/ceph/tree/wip-firefly-isa does not have the bug. It was intr...
- 04:22 AM Revision 0479db8c (ceph): Merge pull request #2233 from majianpeng/fix1
- os/chain_xattr: Remove all old xattr entry when overwrite the xattr.
Reviewed-by: Sage Weil <sage@redhat.com> - 04:17 AM Revision 3da1c711 (ceph): Merge pull request #2230 from ceph/wip-fsx-flatten
- test_librbd_fsx: also flatten as part of randomize_parent_overlap
Reviewed-by: Sage Weil <sage@redhat.com> - 04:15 AM Revision 39bcafa6 (ceph): Merge pull request #2231 from ceph/wip-8944-firefly
- Wip 8944 firefly
Reviewed-by: Sage Weil <sage@redhat.com> - 04:14 AM Revision 3bd1b331 (ceph): Merge pull request #2234 from kevincox/net-docs
- doc: Initial network docs.
Reviewed-by: Sage Weil <sage@redhat.com> - 04:06 AM Revision b06d1b0a (ceph): Merge pull request #2237 from ceph/wip-8560
- mon: instrument paxos
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:05 AM Revision b09b8563 (ceph): mon/Paxos: add perfcounters for most paxos operations
- I'm focusing primarily on the ones that result in IO here.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:01 AM Revision 128aaa50 (ceph): Merge pull request #2242 from majianpeng/fix4
- utime: Because class Clock didn't exist,so remove the declaration in class utime_t
Reviewed-by: Sage Weil <sage@redh... - 03:39 AM devops Bug #9074 (Duplicate): gitbuilder: make check does not complete, sometimes
- It happens because of http://tracker.ceph.com/issues/9096
- 01:57 AM devops Bug #9074: gitbuilder: make check does not complete, sometimes
- Wrong diagnostic, the error is not from here. It loops while waiting for osds to come back up "a few lines below":htt...
- 01:02 AM devops Bug #9074: gitbuilder: make check does not complete, sometimes
- "test.sh":https://github.com/ceph/ceph/blob/ea731ae14216bb479eff1f86ed6bd4a7cb71fb56/qa/workunits/cephtool/test.sh fa...
- 03:17 AM rbd Bug #9078: Removing an RBD is very slow whenever there is write's in other RBD which also belongs...
- RBD's are created with different order parameter
- 02:00 AM rbd Bug #9078: Removing an RBD is very slow whenever there is write's in other RBD which also belongs...
- setup is not available, unable to check "ceph -w", below are information based on IO tool(fio)
before rbd remove: io... - 12:27 AM Bug #9077: Cluster is up in MON node even if Ceph is uninstalled in OSD node
- Mon logs and dmesg logs of mon node are attached
- 12:25 AM Revision f80ed26d (ceph): ceph-disk: move fs mount probe into a helper
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:25 AM Revision 6c77f5f2 (ceph): ceph-disk: use partition type UUIDs, and blkid
- Use blkid to give us the GPT partition type. This lets us distinguish
between dmcrypt and non-dmcrypt partitions. F... - 12:14 AM rbd Bug #9075: Can't create a version 2 images on RHEL 7
- Ok will do :).
08/12/2014
- 11:34 PM Revision ea90d9f4 (ceph): Revert "ReplicatedPG: do not pass cop into C_Copyfrom"
- The ref was introduced in 589b639af7c8834a1e6293d58d77a9c440107bc3
and is actually necessary to keep the buffers arou... - 11:21 PM Revision 300b5e8e (ceph): ReplicatedPG: do not pass cop into C_Copyfrom
- We do not know when the objecter will finally let go of this Context. Thus, we
cannot know whether it will happen be... - 10:51 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- I can't reproduce.
From your messages, i can't find any error info.
Or am i missing something? - 10:28 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Yeah I'm using that commmand.
Sorry - messed up the commit hash : 4eb18dd487da4cb621dcbecfc475fc0871b356ac - 10:23 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Are you using this command "ceph-osd --id 0 --mkjournal --mkfs --osd-data /data1/cephdata --osd-journal /dev/sdc1"?
... - 10:10 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Building wip-9073. Hmmm still getting the invalid argument error and osd down. I'm guessing this means there are two ...
- 09:01 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Very quick work! Will test...
- 08:47 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Mark, I've pushed this as wip-9073.. can you please test?
Thanks, Jianpeng! Sorry I missed the pull request earlier! - 08:36 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Yes, I already found this bug. If journal use aio mode. The bug occur.
The https://github.com/ceph/ceph/pull/2185 c... - 08:28 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- When you say that reverting fixes it, do you mean that it allows an OSD that was erroring out on start to then start,...
- 06:31 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- ...or maybe the ::open()
- 06:14 PM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- On a different machine instead of a hang I am reliably getting:
2014-08-13 12:50:28.253439 7ffc701bb8c0 -1 ** ERR... - 01:40 AM Bug #9073: OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- A correctio - the 'stuck on a mutex' comment is completely wrong - sorry - I'd attached strace to the ceph-osd proces...
- 10:50 PM Revision bb121e41 (ceph): Merge pull request #2246 from ceph/wip-9064
- ReplicatedPG::maybe_handle_cache: do not skip promote for write_ordered
Reviewed-by: Sage Weil <sage@redhat.com> - 10:27 PM Revision 8595e9be (ceph): OSD: introduce require_self_aliveness(OpRequestRef&,epoch_t) function
- Take the self-aliveness checks out of require_same_or_newer_map() and use
the new function for that and for require_u... - 10:27 PM Revision 7da121d2 (ceph): OSD: add require_same_peer_inst(OpRequestRef&,OSDMap&) helper
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit e99acf9810976b1fc74b84ad289773af43be973f)
C... - 10:25 PM Revision d0f2c489 (ceph): OSD: use OpRequestRef& for a few require_* functions
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit eb2f1ea2c33647934af878b504383829f5a198ce) - 10:25 PM Revision 8d395f1c (ceph): OSD: introduce require_up_osd_peer() function for gating replica ops
- This checks both that a Message originates from an OSD, and that the OSD
is up in the given map epoch.
We use it in h... - 10:25 PM Revision 24aeca9c (ceph): ReplicatedPG::maybe_handle_cache: do not skip promote for write_ordered
- We cannot redirect a RW ordered read.
Fixes: #9064
Introduced: 0ed3adc1e0a74bf9548d1d956aece11f019afee0
Signed-off-b... - 10:20 PM Revision 72c2474e (ceph): init-ceph: conditionally update after argparsing
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 44ed1885fb588aad7e4729373e06c593317... - 10:20 PM Revision 8d7fb538 (ceph): make ceph-disk use the new init flag for cluster
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit d0ccb1cbef86b8ccd8967af892e3582ee80... - 10:20 PM Revision 260a9c84 (ceph): allow passing a --cluster flag to the init script
- It will fallback to looking at /etc/ceph/$cluster.conf
otherwise.
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.... - 10:20 PM Revision cb5ecdce (ceph): use cluster name when checking the host
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit bdf5f30010117c71a227855a47fe22ab55b... - 10:20 PM Revision 79452540 (ceph): use name in /var/lib/ceph paths
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 3fb25c28e8e3cc62bc541538cc11f5ed414... - 10:20 PM Revision 92755d10 (ceph): when starting an OSD, pass in the cluster name
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 9e08e3a7794ce007c80c8fdb56e96900eb5... - 10:18 PM Revision 272b26f5 (ceph): osd_types: s/stashed/rollback_info_completed and set on create
- Originally, this flag indicated that the object had already been stashed and
that therefore recording subsequent chan... - 10:18 PM Revision 7b5bcb94 (ceph): osd: use appropriate json types instead of stream when dumping info
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 363496ad878c685008ccd87f26f121d62... - 10:17 PM Revision daec3226 (ceph): osd: have 'tid' dumped as a json unsigned int where appropriate
- Most of the places dumping it would dump it as a string. Others as an int.
Just a couple would dump it as an unsigned... - 10:15 PM Revision 439bce34 (ceph): rgw: need to pass need_to_wait for throttle_data()
- need_to_wait wasn't passed into processor->throttle_data(). This was
broken in fix for #8937.
CID 1229541: (PW.PA... - 10:14 PM Revision fc1a4b5f (ceph): rgw: Don't send error body when it's a HEAD request
- The main 'operation' know not to send any body for HEAD requests.
However for errors, this was not the case, the for... - 10:13 PM Revision e3bc1534 (ceph): osd: prevent old clients from using tiered pools
- If the client is old and doesn't understand tiering, don't let them use a
tiered pool. Reply with EOPNOTSUPP.
Fixes... - 10:12 PM Revision f3113e9a (ceph): mon/OSDMonitor: warn when cache pools do not have hit_sets configured
- Give users a clue when cache pools are enabled but the hit_set is not
configured. Note that technically this will wo... - 10:03 PM Revision aaf732f7 (ceph): osd/ReplicatedPG: improve agent_choose_mode args
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit caf554bf2f752b50670d118c99843b7c4a2967b4) - 10:03 PM Revision 76a519b2 (ceph): osd/ReplicatedPG: evict blindly if there is no hit_set
- If there is no hit set for a PG, blindly evict objects. This avoids an
assert(hit_set) in agent_estimate_atime_temp(... - 10:03 PM Revision 8ff48d79 (ceph): osd/ReplicatedPG: check agent_mode if agent is enabled but hit_sets aren't
- It is probably not a good idea to try to run the tiering agent without a
hit_set to inform its actions, but it is tec... - 10:02 PM Revision e7c5fb58 (ceph): common/LogClient: fix sending dup log items
- We need to skip even the most recently sent item in order to get to the
ones we haven't sent yet.
Fixes: #9080
Backp... - 10:01 PM Revision f98a6194 (ceph): common/LogClient: fix sending dup log items
- We need to skip even the most recently sent item in order to get to the
ones we haven't sent yet.
Fixes: #9080
Backp... - 10:01 PM Revision bbb1e6a3 (ceph): RadosClient: Fixing potential lock leaks.
- In lookup_pool and pool_delete, a lock is taken
before invoking wait_for_osdmap, but is not
released for the failure ... - 09:58 PM Revision cbc9218e (ceph): librbd: fix error path cleanup for opening an image
- If the image doesn't exist and caching is enabled, the ObjectCacher
was not being shutdown, and the ImageCtx was leak... - 09:57 PM Revision e767254c (ceph): librbd: fix error path cleanup for opening an image
- If the image doesn't exist and caching is enabled, the ObjectCacher
was not being shutdown, and the ImageCtx was leak... - 09:38 PM Revision dec028d1 (ceph): Merge remote-tracking branch 'gh/firefly-next' into firefly
- 09:37 PM Revision 7bd67fa1 (ceph): Merge pull request #2245 from dachary/wip-9085-isa-link
- erasure-code: isa plugin must link with ErasureCode.cc
Reviewed-by: Sage Weil <sage@redhat.com> - 09:26 PM Revision 3f18b02c (ceph): Added overrides for vps time outs
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:07 PM Revision 984f6148 (ceph): erasure-code: isa plugin must link with ErasureCode.cc
- Otherwise it will not get the methods it needs. A test is added to check
the plugin loads as expected, from the comma... - 09:03 PM Feature #8560 (Pending Backport): mon: instrument paxos
- 08:53 PM Revision 1088d6cd (ceph): ceph-disk: fix log syntax error
- File "/usr/sbin/ceph-disk", line 303, in command_check_call
LOG.info('Running command: %s' % ' '.join(arguments))... - 07:41 PM Revision afa176e7 (ceph): Merge pull request #2239 from ceph/wip-8912
- librbd: fix error path cleanup for opening an image
Reviewed-by: Sage Weil <sage@redhat.com> - 07:36 PM Revision 41e44611 (ceph): doc/changelog: v0.67.10 notes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:22 PM Revision ce7cd60a (ceph): Merge branch 'wip-8860'
- Reviewed-by: Sage Weil <sage@redhat.com>
- 07:22 PM Revision 44ed1885 (ceph): init-ceph: conditionally update after argparsing
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:30 PM Revision 350b5124 (ceph): doc/release-notes: v0.67.10
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:27 PM Bug #8886: Miss some folders in PG's folder
- I see. Thank you for your reply~
- 01:43 PM Bug #8886 (Closed): Miss some folders in PG's folder
- ./default.4281.322\u\ushadow\u.Ndfi3nAmRHjph\uXyzjJQutltgGi1Dkd\u1__head_17F630A2__1b_ffffffffffffffff_7
appears t... - 06:19 PM Revision 7998c322 (ceph): rgw: call throttle_data() even if renew_state() failed
- Otherwise we're going to leak the aio callback handle.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 06:18 PM Bug #9067 (Resolved): (wip-objecter) Objecter assertion in SIGINT handler
- ...
- 04:43 PM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- 04:20 PM Bug #8894 (Resolved): osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- 12:19 PM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- 12:19 PM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- wip-9054
- 11:25 AM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- I think it's the C_Copyfrom which we gave the objecter in _copy_some. It's got a CopyOpRef.
- 04:35 PM Revision e3e48830 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
PendingReleaseNotes - 04:34 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- This sounds right to me!
- 03:58 PM Bug #9082 (Need More Info): Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub b...
- 10:57 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- I have injected debus osd 20 to one OSD , and and then tried to initiate rados bench on EC pool which is tired with c...
- 09:31 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
- can you reproduce this with debug osd = 20 and attach teh log? thanks!
- 08:27 AM Bug #9082: Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before tier agent ...
I have sent one email to ceph mailing list today , which is related to problem with Ceph pool . ...- 07:59 AM Bug #9082 (Resolved): Ceph Firefly 0.80.5 : PG has invalid (post-split) stats; must scrub before ...
- Hello
Ceph version : 0.80.5
Centos 6.5
Features in use : erasure coding and cache tiering
Few hours back m... - 03:48 PM Bug #9064 (Resolved): RadosModel assertion failure
- 03:48 PM Bug #9064 (Pending Backport): RadosModel assertion failure
- 03:26 PM Bug #9064: RadosModel assertion failure
- 03:26 PM Bug #9064: RadosModel assertion failure
- wip-9064
- 03:25 PM Bug #9064: RadosModel assertion failure
- Got it: 0ed3adc1e0a74bf9548d1d956aece11f019afee0
We're redirecting RW ordered reads due to the second read promote... - 02:00 PM Bug #9064: RadosModel assertion failure
I've now seen this in a case where the client wasn't in the process of handling a new OSD map (but the server was),...- 05:17 AM Bug #9064: RadosModel assertion failure
- This just reproduced on master 78dc4df, so looks like it's not wip-objecter specific.
- 03:24 PM Messengers Bug #8880 (Resolved): msg/Pipe.cc: 1538: FAILED assert(0 == "old msgs despite reconnect_seq featu...
- 03:18 PM Bug #8860 (Resolved): ceph-disk issues with custom cluster name
- 12:21 PM Bug #8860 (Pending Backport): ceph-disk issues with custom cluster name
- 03:16 PM Bug #8625 (Resolved): EC pool - OSD creates an empty file for op with 'create 0~0, writefull 0~xx...
- 03:11 PM rgw Bug #8539 (Resolved): civetweb backend responds with a body when a HEAD request yields an error
- 03:08 PM Revision 7e7afafe (ceph): Merge pull request #2243 from ceph/wip-log-client
- common/LogClient: fix sending dup log items
Reviewed-by: Loic Dachary <loic@dachary.org> - 03:02 PM Bug #8982 (Resolved): cache pool osds crashing when data is evicting to underlying storage pool
- 03:02 PM Bug #8714 (Resolved): we do not block old clients from breaking cache pools
- 03:01 PM Bug #8944 (Resolved): Ceph daemon bad asok used in connection with cluster
- 02:59 PM Bug #9080 (Resolved): LogClient: sends dup messages, misses some
- 01:15 PM Bug #9080 (Pending Backport): LogClient: sends dup messages, misses some
- 07:02 AM Bug #9080 (Resolved): LogClient: sends dup messages, misses some
- noticed where where 'ceph -s' woudln't show the most recent log message. tracing things it turns out that it was alw...
- 02:58 PM Bug #9022 (Resolved): Potential lock leaks in RadosClient
- 02:57 PM Bug #7999 (Resolved): osd: pgs share info that hasn't been persisted
- 02:57 PM rgw Bug #8169 (Resolved): rgw: swift user manifest does not compute etag
- 02:56 PM rgw Bug #8269 (Resolved): rgw: corrupted multipart object
- 02:56 PM Bug #8438 (Resolved): erasure code: object are not cleanup
- 02:56 PM rgw Bug #8442 (Resolved): rgw: does not detect/adapt to erasure pool stripe size
- 02:56 PM rgw Bug #8586 (Resolved): Missing Swift API Header causes RadosGW to segfault
- 02:55 PM rbd Bug #8912 (Resolved): librbd segfaults when creating new image (rbd-ephemeral-clone-stable-icehouse)
- 12:38 PM rbd Bug #8912 (Pending Backport): librbd segfaults when creating new image (rbd-ephemeral-clone-stabl...
- 02:54 PM Bug #8670 (Resolved): Cache tiering parameters can not be displayed for a pool
- 02:48 PM Bug #8696 (Resolved): mon: 'osd pool set' must take into account pool's nature when setting some ...
- 02:48 PM Bug #8701 (Resolved): osd: scrub found obsolete rollback obj
- 02:47 PM rgw Bug #8702 (Resolved): RadosGW incorrectly converting + to space in URLs
- 02:46 PM Bug #8733 (Resolved): OSD crashed at void ECBackend::handle_sub_read
- 02:39 PM Bug #8882 (Resolved): osd: osd tier remove ... leaves incomplete clones behind, confusing scrub
- 02:39 PM Bug #8889 (Resolved): osd/ReplicatedPG.cc: 5162: FAILED assert(got)
- 02:38 PM rbd Bug #8920 (Resolved): rbd/singleton/{all/formatted-output.yaml} fails on trusty due to whitespace
- 02:38 PM rgw Bug #8928 (Resolved): rgw: bad object created if stripe size is not a multiple of chunk size
- 02:38 PM Bug #8931 (Resolved): failed write reply order from ceph_test_rados
- 02:37 PM rgw Bug #8937 (Resolved): rgw: broken large(-ish) objects
- 02:37 PM Bug #8943 (Resolved): "ceph df" cannot show pool available space correctly
- 02:37 PM Bug #8969 (Resolved): PerfCounters.SinglePerfCounters failure on i386
- 02:37 PM rgw Bug #8972 (Resolved): rgw: bucket index log wrong object name in multipart completion
- 02:34 PM Bug #9085 (Pending Backport): erasure-code: ISA plugin does not load
- 09:46 AM Bug #9085 (Fix Under Review): erasure-code: ISA plugin does not load
- "need review":https://github.com/ceph/ceph/pull/2245
- 09:20 AM Bug #9085 (Resolved): erasure-code: ISA plugin does not load
- Because the plugin was not compiled with ErasureCode.cc
- 02:07 PM devops Bug #8160 (Duplicate): multipath-tools does not co-exist with ceph
- If/when we implement multipath support in ceph-deploy, this should be resolved.
- 02:05 PM Revision 057c6808 (ceph): common/LogClient: fix sending dup log items
- We need to skip even the most recently sent item in order to get to the
ones we haven't sent yet.
Fixes: #9080
Backp... - 01:53 PM Revision 07e1ceb5 (ceph): erasure-code: ErasureCodeJerasure::create_ruleset must return a ruleset
- CrushWrapper::add_simple_ruleset does not return a ruleset, it returns
a ruleid that must be converted into a ruleset... - 01:53 PM Revision 96047f1d (ceph): erasure-code: OSDMonitor::crush_ruleset_create_erasure needs ruleset
- When OSDMonitor::crush_ruleset_create_erasure checks the ruleset for
existence, it must convert the ruleid into a rul... - 01:43 PM rgw Bug #9089 (Resolved): rgw: copy_obj_data() does not stripe target object
- copy_obj_data() is as it is now a reminiscent of a very old architecture. It should be modified to create a striped o...
- 01:36 PM Bug #8591 (Resolved): ceph-disk incorrectly colocates journal when using dm-crypt
- wip-ceph-disk
- 01:35 PM Bug #8922: ceph-deploy mon create fails to create additional monitoring nodes.
- does 'hostname' on those machines return the same string, or does it include a domain name, or somethign different?
- 01:34 PM Bug #8985: "[WRN] map e9 wrongly marked me down" in upgrade:dumpling-x-firefly---basic-vps suite
- change the vps.yaml timeout to 90 seconds instead of 40.. these should go away then
- 01:33 PM Bug #8986 (Duplicate): "[WRN] map e62 wrongly marked me down" in upgrade:dumpling-x-firefly---bas...
- 01:33 PM Bug #9012 (Duplicate): "[WRN] map e277 wrongly marked me down" in upgrade:dumpling-x-firefly---ba...
- 01:32 PM Bug #9011 (Duplicate): osd memory leaks on next
- #9023
- 01:27 PM devops Bug #9061 (Resolved): dumpling to firefly upgrade on RH6 restarts the daemons
- 01:26 PM Bug #8974 (Need More Info): osd crashed with merge_log assert due to removal of isds
- 01:25 PM Bug #8974: osd crashed with merge_log assert due to removal of isds
- We can probably make some progress if you reproduce with
debug ms = 1
debug osd = 20
debug filestore = 20
on ... - 01:14 PM Bug #8505 (Resolved): OSD osd/OSD.cc: 6222: FAILED assert(p->second.empty())
- 01:13 PM Bug #8691 (Resolved): osd: PG::_lock, OSD::pg_map_lock lock cycle
- 01:10 PM Bug #8939 (Duplicate): stalled LibRadosTwoPoolsPP.TryFlushReadRace; client failed to reconnect?
- #8891
- 01:09 PM Bug #8940 (Duplicate): 3.22s1 shard 0(2) missing ad166f62/benchmark_data_plana57_30491_object1036...
- 01:06 PM Bug #9069 (Resolved): rgw tests reported as failed in teuthology-2014-08-11_10:35:04-upgrade:dump...
- 01:00 PM Revision 95fbce22 (ceph): Merge pull request #2232 from dachary/wip-9044-use-ruleset
- erasure-code: ErasureCodeJerasure::create_ruleset must return a ruleset
Reviewed-by: Xiaoxi Chen <xiaoxi.chen@intel.... - 12:43 PM rgw Bug #8784: rgw: completion leak
- Note that all the failures are at the copy object across regions path. I did find a missing cleanup at the error hand...
- 10:53 AM Bug #9058: rest-api: long-running process may fail 'tell osd...' due to stale osdmap
- ubuntu@teuthology:/a/teuthology-2014-08-10_02:30:01-rados-next-testing-basic-plana/412468
- 10:16 AM Revision 71e827f0 (ceph): utime: Because class Clock didn't exist,so remove the declaration in cl...
- Signed-off-by: Ma Jianpeng <jianpeng.ma@intel.com>
- 10:08 AM Bug #9087 (Can't reproduce): ceph_test_rados_list_parallel hang
- ...
- 09:09 AM rbd Bug #6631 (Need More Info): disabling writethrough until flush appears to disable RBD cache
- Amit Vijairania wrote:
> More repetition of tests..
>
> // IOPS for Sequential 4KB Write _with_ "rbd cache writet... - 09:07 AM rbd Bug #9078 (Need More Info): Removing an RBD is very slow whenever there is write's in other RBD w...
- it sounds like the cluster is just under heavy load. can you confirm how many ops ceph -w shows before and during th...
- 05:09 AM rbd Bug #9078 (Rejected): Removing an RBD is very slow whenever there is write's in other RBD which a...
- Configuration:
3 node with mon and 3 node with OSD connected via Enclosure/jbod, total 15 OSD's
Steps followed:
... - 09:07 AM Feature #9083 (Closed): Standalone script to generate Ceph keys
- Goal: To allow 3rd party products which will be acting as Ceph clients to be able to install & configure all Ceph-cli...
- 09:04 AM Bug #9077 (Need More Info): Cluster is up in MON node even if Ceph is uninstalled in OSD node
- can you turn up mon logging (if it isn't up already) and attach teh log from the leader? tehse should get marked dow...
- 04:49 AM Bug #9077 (Can't reproduce): Cluster is up in MON node even if Ceph is uninstalled in OSD node
- Configuration:
1 mon and 1 osd node, number of OSD's 7
Steps followed:
1. Make Cluster up in single node and e... - 09:00 AM rbd Bug #8845 (Resolved): Flattening Clones of clone, results in command failure
- 09:00 AM rbd Bug #9075 (Need More Info): Can't create a version 2 images on RHEL 7
- can you retry with the ceph.com package? the 0.81 from fedora is all kinds of busted.
- 02:45 AM rbd Bug #9075 (Resolved): Can't create a version 2 images on RHEL 7
- Hi,
I can't create version 2 images, version 1 works though.
# rbd create -s 10240 --image-format 2 lesebb
20... - 08:56 AM Bug #8595 (In Progress): osd: client op blocks until backfill starts (dumpling)
- with this patch, i see filestore tripping over ENOENT on clone:
ubuntu@teuthology:/a/teuthology-2014-08-11_19:00:0... - 07:35 AM rgw Bug #9002: Creating swift key with --gen-secret in separate step from subuser creation fails
- have meet on Wheezy and Ubuntu with Ceph0.80.5 too.
it can be sucessful when use :
radosgw-admin user create --su... - 07:31 AM CephFS Bug #9056: fuse kmod + ceph-fuse triggers "BUG: sleeping function called from invalid context"
- ...
- 06:51 AM CephFS Bug #9056 (Resolved): fuse kmod + ceph-fuse triggers "BUG: sleeping function called from invalid ...
- 05:10 AM CephFS Bug #9056: fuse kmod + ceph-fuse triggers "BUG: sleeping function called from invalid context"
- This is supposed to be fixed upstream in v3.16-rc6 by commit c55a01d360af, will close this when we've seen a clean fs...
- 07:20 AM Bug #9044: erasure-code: use ruleset instead of ruleid
- "backport to firefly":https://github.com/ceph/ceph/pull/2244
- 05:58 AM Bug #9044 (Pending Backport): erasure-code: use ruleset instead of ruleid
- 05:57 AM Bug #9044 (Resolved): erasure-code: use ruleset instead of ruleid
- 05:55 AM Bug #9044: erasure-code: use ruleset instead of ruleid
- Works. The problems of this run are
* "unrelated MDS decode bug":http://pulpito.ceph.com/loic-2014-08-12_10:00:07-... - 12:58 AM Bug #9044: erasure-code: use ruleset instead of ruleid
- "scheduled upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-12_10:00:07-upgrade:firefly-x:stress-...
- 06:56 AM CephFS Bug #8648: Standby MDS leaks memory over time
- Any change you can run one of these in standby under massif for a while? that will tell us what is leaking!
- 06:55 AM CephFS Bug #8651 (Won't Fix): crashing mds in an active-active mds setup
- this MDS got blacklisted. there is an open issues somewhere to make the shutdown more friendly, but the behavior is ...
- 06:52 AM Bug #9023: valgrind failures in OSD
- The leaks in the init stuff seem likely also to be present on master
- 06:50 AM CephFS Bug #8725: mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- we probably have to do a reencoding trick like we do in MOSDMap?
- 06:48 AM CephFS Bug #8876 (Resolved): kcephfs: hang on read of length 0
- 06:22 AM Bug #9079 (Resolved): osd: bad learned_addr during send_boot
- ...
- 06:10 AM Bug #8520: osd: segv in PushOp::print()
- ...
- 03:27 AM rbd Bug #8385: RBD / QEMU Crash: Invalid fastbin entry (free)
- Any interest in a lookalike bug from Cuttlefish?
/lib/x86_64-linux-gnu/libc.so.6(+0x7e566)[0x7f7cd15ad566]
/usr/... - 02:55 AM rbd Bug #9076 (Resolved): Can't completely remove a version 1 image on RHEL 7
- I can create version 1 image, however the deletion is not complete.
# rbd create -s 10240 --image-format 1 leseb
... - 01:16 AM Revision 78dc4df1 (ceph): doc: Replace [default] with [global].
- Fixes: #8955
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 01:05 AM Revision e5324edb (ceph): doc: Added yum-priorities procedure to manual install.
- Fixes: #8734
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 01:04 AM Revision a01252a4 (ceph): doc: Added priority = 2 to packages.
- Fixes: #8734
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 12:55 AM Revision c24c4eed (ceph): ceph_manager: longer osd restart timeout
- We bumped this on master and dumpling already
Signed-off-by: Sage Weil <sage@redhat.com> - 12:54 AM devops Bug #9074: gitbuilder: make check does not complete, sometimes
- "re-run the build to check if it fails always or sometimes":http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-...
- 12:52 AM devops Bug #9074 (Duplicate): gitbuilder: make check does not complete, sometimes
- It looks like i386 build fails because a timeout interrupts it before it gets a chance to complete.
It could be t...
08/11/2014
- 11:43 PM Revision 3dfa72d5 (ceph): librbd: fix error path cleanup for opening an image
- If the image doesn't exist and caching is enabled, the ObjectCacher
was not being shutdown, and the ImageCtx was leak... - 10:58 PM Revision 2edf01ff (ceph): Revert "Fix for bug #6700"
- This reverts commit 673394702b725ff3f26d13b54d909208daa56d89.
This appears to break things when the journal and data... - 10:57 PM Revision d6e6ba19 (ceph): ceph-disk: fix verify_no_in_use check
- We only need to verify that partitions aren't in use when we want to
consume the whole device (osd data), not when we... - 09:15 PM Bug #9073 (Resolved): OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- Using a src build (and the packages built from it) on Ubuntu 14.04 x86_64. Ceph version is 0.83-399-gf77449c.
In ... - 08:53 PM rbd Bug #9071 (Duplicate): mkfs.ext4 stuck in D state on RBD with kernel client
- This is a bug in 3.15; it is not present in 3.14. The fix will make it into the next stable 3.15 release soon.
- 07:32 PM rbd Bug #9071: mkfs.ext4 stuck in D state on RBD with kernel client
- Please, mark this issue as duplicate of http://tracker.ceph.com/issues/8818
- 06:06 PM rbd Bug #9071: mkfs.ext4 stuck in D state on RBD with kernel client
- Reproducible on all my ceph hosts (all with the same kernel), with any image format (1 or 2). But only with mkfs.ext4...
- 05:47 PM rbd Bug #9071 (Duplicate): mkfs.ext4 stuck in D state on RBD with kernel client
- I tried to create ext4 on newly created and mapped RBD image, but mkfs.ext4 stuck:
# mkfs.ext4 /dev/rbd/docker.rbd... - 07:36 PM Revision 0a2b4c25 (ceph): rgw: Don't send error body when it's a HEAD request
- The main 'operation' know not to send any body for HEAD requests.
However for errors, this was not the case, the for... - 07:30 PM Revision 616cb927 (ceph): Merge pull request #2214 from ceph/wip-rados-df-json
- rados: fix 'rados df --format=json' field names
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:53 PM Revision 5663f91b (ceph): rados: fix {read,write}_bytes value
- Fill this in with kb * 1024 instead of the ops count.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@red... - 06:53 PM Revision b0f5ba95 (ceph): rados: remove {read,write}_kb fields from rados df json output
- Redundant. Do not backport.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:15 PM Documentation #8955 (Resolved): doc refers to [default] section, don't think it exists
- 's/[default]/[global]/'
- 06:10 PM Documentation #8955 (In Progress): doc refers to [default] section, don't think it exists
- 06:05 PM devops Bug #8734 (Resolved): EPEL / Ceph.com package priority issues
- I added priorty=2 to the get packages document example for ceph.repo. I also added an install yum-priorities series o...
- 05:56 PM devops Bug #8734 (In Progress): EPEL / Ceph.com package priority issues
- 05:51 PM Bug #9072: error setting 'mon_pg_warn_min_objects' to '10K': (22) Invalid argument
- ubuntu@teuthology:/a/sage-2014-08-10_18:40:12-rados-firefly-next-distro-basic-multi/414556
- 05:50 PM Bug #9072 (Resolved): error setting 'mon_pg_warn_min_objects' to '10K': (22) Invalid argument
- ...
- 05:25 PM Revision c2e2fc56 (ceph): Merge pull request #2238 from ceph/wip-9057
- msg/Pipe: do not wait for self in Pipe::stop_and_wait()
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:25 PM Bug #9069: rgw tests reported as failed in teuthology-2014-08-11_10:35:04-upgrade:dumpling:rgw-du...
- oh.. it' snot running as root.. or with daemon-helper.
- 05:24 PM Bug #9069: rgw tests reported as failed in teuthology-2014-08-11_10:35:04-upgrade:dumpling:rgw-du...
- 7585 ? Sl 0:05 radosgw -n client.0 -k /etc/ceph/ceph.client.0.keyring --rgw-socket-path /home/ubuntu/ceph...
- 03:57 PM Bug #9069 (Resolved): rgw tests reported as failed in teuthology-2014-08-11_10:35:04-upgrade:dump...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-11_12:05:02-upgrade:dumpling-dumpling---basic-vps/...
- 04:58 PM rbd Bug #8912 (Fix Under Review): librbd segfaults when creating new image (rbd-ephemeral-clone-stabl...
- https://github.com/ceph/ceph/pull/2239
- 01:39 PM rbd Bug #8912: librbd segfaults when creating new image (rbd-ephemeral-clone-stable-icehouse)
- Looks like it was a race condition in a previously little-used error path.
- 01:04 PM rbd Bug #8912 (In Progress): librbd segfaults when creating new image (rbd-ephemeral-clone-stable-ice...
- Excellent report, your reproducer causes the same crash for me.
- 04:14 PM Bug #9044: erasure-code: use ruleset instead of ruleid
- gitbuilder is running
- 03:42 PM Revision b5dafe1c (ceph): osd: allow io priority to be set for the disk_tp
- The disk_tp covers scrubbing, pg deletion, and snap trimming
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pic... - 03:32 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- wip-9054
- 03:07 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- When we go to flush clone 22, all we know is that 22 is dirty, has snaps
[21], and 4 is clean. As part of fl... - 02:24 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- Ok, we start with the following configuration in the cache (all dirty):
30:[29,21,20,15,10,4]:[22(21), 15(15,10), ... - 12:45 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- Actually, looks like this might already be handled correctly, re-consulting the log.
- 12:00 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- Thinking
- 11:52 AM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- Hmm, I think the bug is like this:
Normally, if we get the following op sequence:
- write 1:[]
- delete 10:[3] (... - 03:16 PM Bug #9040: clients can SEGV during package upgrade
- I see no segmentation errors in the latest run: /a/teuthology-2014-08-11_12:05:02-upgrade:dumpling-dumpling---basic-v...
- 12:34 PM rgw Bug #8539: civetweb backend responds with a body when a HEAD request yields an error
- Merged, commit:0a2b4c25541bbd15776d3d35986518e37166910f
- 12:34 PM rgw Bug #8539 (Pending Backport): civetweb backend responds with a body when a HEAD request yields an...
- 12:30 PM Revision 9d446bd4 (ceph): 0.67.10
- 12:24 PM Bug #9064: RadosModel assertion failure
The bug is happening when a new OSD map is received in the middle of the series of transactions. The read transact...- 11:40 AM Bug #9064: RadosModel assertion failure
- Got an even more specific backtrace ...
- 09:57 AM Bug #9064: RadosModel assertion failure
- trying to reproduce locally with objecter logging turned up and ``ms inject socket failures`` enabled as it is in the...
- 09:29 AM Bug #9064: RadosModel assertion failure
- I understand this a little better now: the operations in this WriteOp are 1,2 (writes), 4 (setxattr), 5 (read). So t...
- 07:23 AM Bug #9064: RadosModel assertion failure
- http://qa-proxy.ceph.com/teuthology/john-2014-08-10_02:14:59-rados-wip-mds-contexts-testing-basic-plana/411119/teutho...
- 07:22 AM Bug #9064 (Resolved): RadosModel assertion failure
http://qa-proxy.ceph.com/teuthology/john-2014-08-10_02:14:59-rados-wip-mds-contexts-testing-basic-plana/411119/teut...- 10:41 AM Bug #9057 (Resolved): mark_down from fast dispatch can deadlock
- 09:57 AM rgw Subtask #9068 (Closed): rgw: add rgw setup to vstart
- As part of the development documentation we need to update vstart to create an RadosGW development environment.
- 09:53 AM Bug #9067 (Resolved): (wip-objecter) Objecter assertion in SIGINT handler
@ wip-mds-contexts 2550fc51f30a8a1e581dd9a90511732a3b70ad2a
When I start a "ceph status" while no mon is running...- 09:01 AM devops Bug #9066 (Rejected): Need ceph-deploy to be able to run to JUST generate ceph.conf and keyring w...
- Mirror of issue: https://bugzilla.redhat.com/show_bug.cgi?id=1127852
- 08:37 AM Bug #9065 (Resolved): LibRados* tests failed in upgrade:dumpling-x-firefly---basic-vps
- This should be fixed by https://github.com/ceph/ceph/pull/2236 (in review)
Logs are in http://qa-proxy.ceph.com/te... - 08:33 AM devops Bug #9032 (Rejected): ceph-deploy over proxy
- The `--gpg-url` is only valid if you are pointing to a custom repo.
What you need to do is create a custom repo se... - 08:28 AM Feature #8580: Decrease disk thread's IO priority and/or make it configurable
- Hi,
The backport to dumpling is missing the commit which provides the new configurable: https://github.com/ceph/ce... - 05:04 AM Bug #9062: Mon segfault in waitlist_or_zap_client
- Note that this was wip-mds-clients which doesn't have any messenger changes and doesn't have any mon changes other th...
- 05:01 AM Bug #9062 (Resolved): Mon segfault in waitlist_or_zap_client
http://pulpito.front.sepia.ceph.com/john-2014-08-10_02:14:59-rados-wip-mds-contexts-testing-basic-plana/411054/
...- 04:37 AM Bug #9023: valgrind failures in OSD
Haven't seen the "new Session" one since rebasing on master, so I'm optimistic that it was the same thing as the le...- 04:09 AM CephFS Bug #8878 (In Progress): mds lock cycle (wip-objecter)
- I think all these are OK now in wip-mds-contexts: remaining failures on that branch are all outside MDS.
- 04:09 AM Bug #9009 (Resolved): (wip-objecter) ObjectCacher assert in fs client
- This is all good now in wip-mds-contexts (http://pulpito.ceph.com/john-2014-08-09_14:56:53-fs-wip-mds-contexts-testin...
- 03:22 AM Revision 8180713c (ceph): msg/Pipe: do not wait for self in Pipe::stop_and_wait()
- The fast dispatch code necessitated adding a wait for the fast dispatch
to complete when taking over sockets back in ...
08/10/2014
- 11:43 PM devops Bug #9061 (Resolved): dumpling to firefly upgrade on RH6 restarts the daemons
- Hi,
When I upgrade the RPMs on a RH6 server from 0.67.9 to 0.80.5, the daemons are (cond)restarted. I believe these ... - 09:09 PM Revision fd421b26 (ceph): mon/MonitorDBStore: add get_{keys,bytes}() accounting to Transaction
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:48 PM Revision d7fb7bf5 (ceph): ceph_test_rados_api_tier: fix cache cleanup (ec too)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:48 PM Revision ebbe8aab (ceph): ceph_test_rados_api: fix cleanup of cache pool
- We can't simply try to delete everything in there because some items may
be whiteouts. Instead, flush+evict everythi... - 07:20 PM Linux kernel client Bug #8806: libceph: must use new tid when watch is resent
- meanwhile, the MWatchNotify message now has a return value encoded at the end (s32) when header.version >= 0. See wi...
- 07:19 PM Linux kernel client Bug #8806: libceph: must use new tid when watch is resent
- the bug is with the kernel client: it needs to use a new tid when resending the watch. this was partially fixed on t...
- 06:41 PM Revision 1d199fb1 (ceph): librados/TestCase: inheret cleanup_default_namespace
- No need to duplicate this code.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:04 PM Bug #9057 (Fix Under Review): mark_down from fast dispatch can deadlock
- https://github.com/ceph/ceph/pull/2238
- 10:45 AM Bug #9057: mark_down from fast dispatch can deadlock
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-08-09_14:13:44-rados-next-testing-basic-multi/410713
3 (!... - 08:41 AM Bug #9057 (Resolved): mark_down from fast dispatch can deadlock
- ...
- 04:13 PM Feature #8639 (In Progress): mon: dispatch messages while blocked waiting for IO
- 03:45 PM Bug #8620: rest/test.py occasional failure (dumpling)
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-08-10_13:22:17-rados-dumpling-distro-basic-multi/413788
- 03:18 PM Revision 04a484a4 (ceph): erasure-code: OSDMonitor::crush_ruleset_create_erasure needs ruleset
- When OSDMonitor::crush_ruleset_create_erasure checks the ruleset for
existence, it must convert the ruleid into a rul... - 03:18 PM Revision 0029a358 (ceph): erasure-code: ErasureCodeJerasure::create_ruleset must return a ruleset
- CrushWrapper::add_simple_ruleset does not return a ruleset, it returns
a ruleid that must be converted into a ruleset... - 03:18 PM Revision 3f5d86af (ceph): erasure-code: ErasureCodeIsa::create_ruleset must return a ruleset
- http://tracker.ceph.com/issues/9044 Refs: #9044
Signed-off-by: Loic Dachary <loic@dachary.org> - 03:18 PM Revision 5808d6a6 (ceph): osd: improve ruleno/ruleset consistency
- rename variables to reflect when they hold a ruleset and when they hold
a rule id / ruleno in the hope to avoid bugs ... - 02:07 PM Feature #8560 (Fix Under Review): mon: instrument paxos
- 12:51 PM rgw Bug #8988 (Fix Under Review): AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- Two consecutive run with the increased timeout do not show the bug ("one":http://pulpito.ceph.com/loic-2014-08-10_15:...
- 02:03 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- In a few tickets it is suggested that this may be an idle timeout problem. I "rescheduled a suite":http://pulpito.cep...
- 01:31 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- In the attached file, each part separated with *-----------------------------* is the output between the last success...
- 01:09 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- The errors for each failure are different and suggests the tests are failing for an independent reason such as the cl...
- 01:03 AM rgw Bug #8988: AssertionError(s) in upgrade:firefly-x:stress-split-next---basic-plana
- * http://pulpito.ceph.com/loic-2014-08-08_12:17:30-upgrade:firefly-x:stress-split-wip-9025-chunk-remapping-testing-ba...
- 12:46 PM Bug #9055 (Fix Under Review): LibRadosTwoPoolsPP.HitSetWrite (and others) fail on remove of whiteout
- https://github.com/ceph/ceph/pull/2236
- 11:05 AM Feature #9059 (Resolved): osd: store opportunistic whole-object checksum
- when we deep scrub, we have a whole-object checksums that cover data and omap. store a copy in object_info_t, along ...
- 10:52 AM Bug #8935: operations not idempotent when enabling cache
- sage-2014-08-09_14:13:44-rados-next-testing-basic-multi/410527 and 410528
- 10:51 AM Bug #9058 (Can't reproduce): rest-api: long-running process may fail 'tell osd...' due to stale o...
- sage-2014-08-09_14:13:44-rados-next-testing-basic-multi/410524
- 10:48 AM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-08-09_14:13:44-rados-next-testing-basic-multi/410806
alwa... - 07:51 AM Revision 104440ce (ceph): Merge pull request #2201 from dachary/wip-8496-erasure-code-base-class
- erasure code base class
Reviewed-by: Andreas-Joachim Peters <Andreas.Joachim.Peters@cern.ch> - 02:16 AM CephFS Bug #8725: mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- "same error":http://pulpito.ceph.com/loic-2014-08-10_09:59:49-upgrade:firefly-x:stress-split-wip-9025-chunk-remapping...
- 12:53 AM CephFS Bug #8725: mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- Another "similar crash":http://pulpito.ceph.com/loic-2014-08-08_12:17:30-upgrade:firefly-x:stress-split-wip-9025-chun...
- 12:39 AM CephFS Bug #8725: mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- And the same trace at "upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-08_12:13:20-upgrade:firef...
- 12:33 AM CephFS Bug #8725: mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- Looks like a similar problem at "upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-08_12:13:20-upg...
- 01:04 AM Feature #9025: erasure-code: chunk remapping
- The upgrade suite from firefly had one error related to an independant "MDS problem":http://pulpito.ceph.com/loic-201...
- 12:49 AM Feature #8496 (Resolved): erasure-code: ErasureCode base class
- 12:41 AM Feature #8496: erasure-code: ErasureCode base class
- The "upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-08_12:13:20-upgrade:firefly-x:stress-split-...
- 12:16 AM Bug #8978: ceph ping not working as expected
- I'm experiencing the same (on newly installed ceph-cluster via Ubuntu server 14.04.1):
ceph status
cluster b6...
08/09/2014
- 11:34 PM Revision e087862d (ceph): Add rbdcache max dirty object option
- Librbd will calculate max dirty object according to rbd_cache_max_size, it
doesn't suitable for every case. If user s... - 11:34 PM Revision 5f74fb29 (ceph): librbd/internal.cc: check earlier for null pointer
- Fix potential null ponter deref, move check for 'order != NULL'
to the beginning of the function to prevent a) deref ... - 11:34 PM Revision b2189465 (ceph): librbd: add an interface to invalidate cached data
- This is useful for qemu to guarantee live migration with caching is
safe, by invalidating the cache on the destinatio... - 11:33 PM Revision f7dc5855 (ceph): librbd: check return code and error out if invalidate_cache fails
- This will only happen when shrinking or rolling back an image is done
while other I/O is in flight to the same ImageC... - 10:55 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- Unfortunately converting RBD to image format 2 did not fix it. User returned after being away for a week and her syst...
- 10:50 PM Revision a86e497a (ceph): Add rbdcache max dirty object option
- Librbd will calculate max dirty object according to rbd_cache_max_size, it
doesn't suitable for every case. If user s... - 10:49 PM Revision d0238131 (ceph): librbd/internal.cc: check earlier for null pointer
- Fix potential null ponter deref, move check for 'order != NULL'
to the beginning of the function to prevent a) deref ... - 10:47 PM Revision dda98b9a (ceph): librbd: add an interface to invalidate cached data
- This is useful for qemu to guarantee live migration with caching is
safe, by invalidating the cache on the destinatio... - 10:47 PM Revision d9357951 (ceph): librbd: check return code and error out if invalidate_cache fails
- This will only happen when shrinking or rolling back an image is done
while other I/O is in flight to the same ImageC... - 10:42 PM Revision 61791420 (ceph): Avoid extra check for clean object
- We needn't to check clean object via buffer state, skip the clean object.
Signed-off-by: Haomai Wang <haomaiwang@gma... - 10:36 PM Revision d474443b (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>
(cherr... - 10:36 PM Revision 051d1b4e (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>
(cherry picked ... - 10:30 PM Revision 61e2219d (ceph): rbd: don't forget to call close_image() if remove_child() fails
- close_image() among other things unregisters a watcher that's been
registered by open_image(). Even though it'll tim... - 08:24 PM Revision c7fbf272 (ceph): os/FileStore: dump open fds before asserting
- Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 4e8de1792731cf30f27... - 08:23 PM Revision 2c6c23ce (ceph): os/FileStore: dump open fds before asserting
- Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 4e8de1792731cf30f27... - 08:23 PM Revision 4e8de179 (ceph): os/FileStore: dump open fds before asserting
- Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 07:52 PM Revision 281159bf (ceph): doc: Initial network docs.
- Signed-Off-By: Kevin Cox <kevincox@kevincox.ca>
- 06:51 PM Revision 978f5749 (ceph): ceph_test_rados_api_tier: do fewer writes in HitSetWrite
- We don't need to do quite so many writes. It can be slow when we are
thrashing and aren't doing anything in parallel... - 05:50 PM CephFS Bug #9056: fuse kmod + ceph-fuse triggers "BUG: sleeping function called from invalid context"
http://pulpito.front.sepia.ceph.com/john-2014-08-09_14:56:53-fs-wip-mds-contexts-testing-basic-plana/409236/
http:...- 05:48 PM CephFS Bug #9056 (Resolved): fuse kmod + ceph-fuse triggers "BUG: sleeping function called from invalid ...
kernel 5f740d7e1531099b888410e6bab13f68da9b1a4d
wip-mds-contexts (aka wip-objecter) 7be59771bff09e2b46b5467627cb...- 12:53 PM Bug #9055 (Resolved): LibRadosTwoPoolsPP.HitSetWrite (and others) fail on remove of whiteout
- 2014-08-09T09:03:14.670 INFO:tasks.workunit.client.0.plana70.stdout:test/librados/TestCase.cc:93: Failure
2014-08-09... - 12:26 PM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- 2014-08-08 10:55:12.312751 7f1237847700 10 osd.0 pg_epoch: 462 pg[2.1( v 462'2839 (0'0,462'2839] local-les=422 n=53 e...
- 10:04 AM Bug #9054: ceph_test_rados: FAILED assert(!old_value.deleted())
- almost there. on osd.0, we finish trimming 14a here:
2014-08-08 10:55:12.311901 7f1237847700 10 osd.0 pg_epoch: 4... - 12:03 PM Revision 4f6d5133 (ceph): os/chain_xattr: Remove all old xattr entry when overwrite the xattr.
- Ceph use multiple xattrs to store the value of a single xattr which size
is larger than CHAIN_XATTR_MAX_BLOCK_LEN.
Bu... - 11:43 AM Bug #8894: osd/ReplicatedPG.cc: 9281: FAILED assert(object_contexts.empty())
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-08-08_22:30:19-rados-wip-sage-testing-testing-basic-burnupi/...
- 06:00 AM Revision 4d2d4dd5 (ceph): Merge branch 'next'
- Conflicts:
src/osd/OSD.cc - 05:59 AM Revision 84c96547 (ceph): OSD: add require_same_peer_inst(OpRequestRef&,OSDMap&) helper
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit e99acf9810976b1fc74b84ad289773af43be973f) - 05:59 AM Revision 4a0c9417 (ceph): OSD: introduce require_self_aliveness(OpRequestRef&,epoch_t) function
- Take the self-aliveness checks out of require_same_or_newer_map() and use
the new function for that and for require_u... - 05:59 AM Revision 48c9b384 (ceph): OSD: use OpRequestRef& for a few require_* functions
- Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit eb2f1ea2c33647934af878b504383829f5a198ce) - 05:59 AM Revision f86bf1d8 (ceph): OSD: introduce require_up_osd_peer() function for gating replica ops
- This checks both that a Message originates from an OSD, and that the OSD
is up in the given map epoch.
We use it in h... - 03:08 AM Revision 65706b11 (ceph): Merge remote-tracking branch 'gh/next'
- 02:16 AM Revision 3663233a (ceph): rgw: return error if accessing object in non-existent bucket
- Fixes: #7064
Instead of trying to access the object, which is impossible as we don't
even have a proper bucket info. ... - 02:05 AM Revision 22aa8141 (ceph): Merge remote-tracking branch 'gh/firefly-next' into firefly
- 01:39 AM Bug #9044 (Fix Under Review): erasure-code: use ruleset instead of ruleid
- "associated pull request":https://github.com/ceph/ceph/pull/2232
- 01:17 AM Revision 790f4c23 (ceph): Merge pull request #2228 from ceph/wip-pg-epoch
- osd: fix pg epoch floor tracking
Reviewed-by: Samuel Just <sam.just@inktank.com> - 01:12 AM Revision c5110468 (ceph): mon: add 'osd blocked-by' command
- Print a histogram of how many peers are blocked by each OSD. This is
useful for quickly diagnosing which OSDs are br... - 01:12 AM Revision 6380f478 (ceph): qa/workunits/cephtool: add simple 'ceph osd perf' test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision bee79ec4 (ceph): qa/workunits/cephtool: add trivial 'ceph osd blocked-by' test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision d8627313 (ceph): osd/PG: bound number of blocked_by OSDs we report per PG
- We don't want to include an unbounded-sized vector of OSDs in the pg_stat_t
struct. Cap it, and report a random subs... - 01:12 AM Revision ee790e36 (ceph): osd/osd_types: s/int/int32_t/ in pg_stat_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision 6e96c2d9 (ceph): osd/PG: set blocked_by during peering GetInfo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision ceaca9f1 (ceph): osd/PG: set blocked_by during peering GetLog
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision 6fcdbd21 (ceph): osd/PG: set blocked_by in Incomplete state
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision 47a9af35 (ceph): osd/PG: set blocked_by in GetMissing
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:12 AM Revision d55e9730 (ceph): mon/PGMap: track histogram of pg blocked_by
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:53 AM Revision 448edb19 (ceph): Merge pull request #2209 from somnathr/wip-sd-check-pool-existence
- RadosClient: Adding pool existence checks for pool create interfaces.
Reviewed-by: Sage Weil <sage@redhat.com>
08/08/2014
- 11:57 PM Revision e4b00718 (ceph): RadosClient: Enable pool existence check
- Pool create interfaces would now refer to updated osdmap
for pool existence, such that an appropriate message is
thro... - 11:00 PM Bug #9054 (Resolved): ceph_test_rados: FAILED assert(!old_value.deleted())
- ubuntu@teuthology:/a/teuthology-2014-08-06_02:30:01-rados-next-testing-basic-plana/403383...
- 10:58 PM Bug #8997: ceph_test_rados_watch_notify hangs
- ubuntu@teuthology:/a/teuthology-2014-08-06_02:30:01-rados-next-testing-basic-plana/402968
- 10:55 AM Bug #8997: ceph_test_rados_watch_notify hangs
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-08-06_02:30:01-rados-next-testing-basic-plana/402968
- 10:54 PM Bug #9053 (Resolved): mon/Paxos.cc: 628: FAILED assert(begin->last_committed == last_committed)
- ubuntu@teuthology:/a/teuthology-2014-08-06_02:30:01-rados-next-testing-basic-plana/402965
description: rados/monthra... - 07:36 PM Bug #9052: ceph-mon crashes with *** Caught signal (Floating point exception) **
- With no OSDs in the cluster, the calculations for @pgs_per_osd@ can divide by zero (integer, but that still causes th...
- 07:29 PM Bug #9052 (Resolved): ceph-mon crashes with *** Caught signal (Floating point exception) **
- I've found that I can crash ceph-mon by attempting to change pool values (such as pg_num) before adding OSDs to the c...
- 06:59 PM rgw Documentation #9051 (Closed): Document rgw_defer_to_bucket_acls option
- It appears that the only documentation right now is the commit message of 1d7c2041.
- 06:16 PM Bug #7576: osd: large skew in pg epochs (dumpling)
- ..and when we do, include commit:a52a855f6c92b03dd84cd0cc1759084f070a98c2 !!
- 06:16 PM Bug #7576 (Pending Backport): osd: large skew in pg epochs (dumpling)
- still want to backport this to firefly ...
- 06:04 PM rgw Bug #8621: civetweb frontend fails authentication if URL has special chars
- tested wip-8621 by executing s3tests, there are still a few failures,
logs are copied to ubuntu@mira042.front.sepi... - 04:42 PM Fix #4205: librados: Improve Watch-notify semantics
- http://pad.ceph.com/p/watch-notify
- 03:55 PM devops Feature #9050 (Rejected): Calamari builds for ceph.com
- 03:24 PM devops Feature #6310 (Closed): Get Dumpling into CentOS Ceph repo
- 02:53 PM Revision c34f9352 (ceph): test_librbd_fsx: also flatten as part of randomize_parent_overlap
- With randomize_parent_overlap fsx will randomly truncate base images
after they have been cloned from. This throws f... - 10:31 AM Bug #9046 (Resolved): Limiting the pool object quota stops the IO, however IO does not restart if...
- Issue Title: Limiting the pool object quota stops the IO, however IO does not restart if we rest the pool object quot...
- 10:03 AM Revision 214630b1 (ceph): mds: Also check min/max uid on snap removal
- Not only check if the uid is correct when creating a snapshot, but also
verify if the UID is correct when trying to r... - 09:37 AM Bug #9040: clients can SEGV during package upgrade
- 09:03 AM Bug #9023: valgrind failures in OSD
- Another `new Session` at OSD.cc:3704
http://qa-proxy.ceph.com/teuthology/john-2014-08-07_18:44:20-fs-wip-mds-context... - 06:43 AM Bug #9044 (Resolved): erasure-code: use ruleset instead of ruleid
- When "ruleset is looked up by name":https://github.com/ceph/ceph/blob/firefly/src/mon/OSDMonitor.cc#L2928 when creati...
- 03:15 AM Feature #9025: erasure-code: chunk remapping
- "requeued, for ubuntu 14.04 to get quicker results":http://pulpito.ceph.com/loic-2014-08-08_12:17:30-upgrade:firefly-...
- 03:13 AM Feature #8496: erasure-code: ErasureCode base class
- "requeued, for ubuntu 14.04 to get quicker results":http://pulpito.ceph.com/loic-2014-08-08_12:13:20-upgrade:firefly-...
- 02:43 AM rgw Bug #9043 (Duplicate): rgw:Cannot add object to Ceph using Openstack Dashboard(Horizon) in firefly
- Uploading a new object fails with message "Error: Unable to upload object".
While adding an object using Horizon w... - 01:24 AM Revision a1449506 (ceph): qa/workunits/cephtool/test_daemon.sh: allow local ceph command
- (cherry picked from commit 97a8d5a9fdbd3a25cc922c242ee57da58c57d0bc)
- 01:24 AM Revision 1ac0e543 (ceph): qa/workunits/cephtool/test_daemon.sh: typo
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit 22d20f39b7355966554319d5a1aa888967607569) - 01:24 AM Revision cb48cd47 (ceph): qa/workunits/cephtool/test_daemon.sh: verify ceph -c works with daemon
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit aa9ae1f270293778aa937e7f7e4bcaee3099b9b2) - 01:24 AM Revision 76b593f6 (ceph): ceph.in: Pass global args to ceph-conf for proper lookup
- Fixes: #8944
Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit 6d89a99648630f81b85ad115fe7662... - 12:42 AM Revision a52a855f (ceph): osd: fix pg epoch floor tracking
- If you call erase() on a multiset it will delete all instances of a value;
we only want to delete one of them. Fix t...
08/07/2014
- 10:56 PM Revision de0c7202 (ceph): Merge pull request #2226 from athanatos/wip-8396
- Wip 8396
Reviewed-by: Sage Weil <sage@redhat.com> - 10:54 PM Revision 2120f4bb (ceph): OSD: move waiting_for_pg into the session structures
- Each message belongs to a session. Further, no ordering is implied
between messages which arrived on different sessi... - 10:42 PM Revision f5d6818d (ceph): Merge pull request #2227 from athanatos/wip-8625
- osd_types: s/stashed/rollback_info_completed and set on create
Reviewed-by: Sage Weil <sage@redhat.com> - 10:30 PM Revision 71cb4d3c (ceph): doc: Removed Debian reference from Upstart.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:29 PM Revision 8357cae0 (ceph): doc: Incorporated user feedback to clarify upgrade doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:15 PM Revision b6bf33cd (ceph): doc: Added configuration discussion at end of gateway install with link...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:48 PM Revision 6e7b86a2 (ceph): OSD: fix wake_pg_waiters revert error in _open_lock_pg
- 231fe1b685bfbd3db9c81709ca39a29d696b13ad reintroduced erroneously
this call to wake_pg_waiters. All _create_lock_pg ... - 06:48 PM Revision 20fd714a (ceph): OSD: wake_pg_waiters outside of the pgmap write_lock, pg_lock
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:48 PM Revision 11d6e5ad (ceph): OSD: rename session_waiting_for_map_lock to session_waiting_lock
- This lock will also protect the waiting_for_pg structures in each
session.
Signed-off-by: Samuel Just <sam.just@inkt... - 06:48 PM Revision 6aba9421 (ceph): OSD: clear_session_waiting_on_map in ms_handle_reset
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:48 PM Revision 11cefcab (ceph): OSD::shutdown: actually drop sessions waiting on map
- There might be messages for which we still don't have the
map. Dispatching waiting won't actually help.
Signed-off-... - 06:47 PM Revision 42607679 (ceph): osd_types: s/stashed/rollback_info_completed and set on create
- Originally, this flag indicated that the object had already been stashed and
that therefore recording subsequent chan... - 06:21 PM Revision f95e82b1 (ceph): Merge remote-tracking branch 'gh/wip-filestore-bigxattr'
- 03:56 PM Feature #8276: ceph-filestore-dump import-rados -p <pool> <archive>
- Implemented syntax:
ceph_objectstore_tool import-rados pool [import_file|-]
Import into the specified pool on r... - 03:54 PM Bug #8396 (Resolved): osd: message delayed in Session misdirected after split
- 03:39 PM Bug #8625 (Pending Backport): EC pool - OSD creates an empty file for op with 'create 0~0, writef...
- 03:11 PM Revision d0ccb1cb (ceph): make ceph-disk use the new init flag for cluster
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:48 PM Revision 23b4915f (ceph): allow passing a --cluster flag to the init script
- It will fallback to looking at /etc/ceph/$cluster.conf
otherwise.
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.... - 02:34 PM Bug #9040: clients can SEGV during package upgrade
- https://github.com/ceph/ceph-qa-suite/pull/77 seemed fixing this.
Testing now. - 01:56 PM Bug #9040 (Won't Fix): clients can SEGV during package upgrade
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-06_16:30:35-upgrade:dumpling-dumpling---basic-vps/...
- 02:24 PM Revision 4e1e929f (ceph): Update module references
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision 0e1df3cc (ceph): Import teuthology tasks (master branch)
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision 65060738 (ceph): Merge branch 'teuth_master' into tasks_master
- 02:24 PM Revision ad65d6bb (ceph): Update module references
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision 6f854e12 (ceph): Use newer orchestra API
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision a963e791 (ceph): Use teuthology's DaemonGroup
- It has timeout support.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 02:24 PM Revision 2e9a567d (ceph): Use Remote.user
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision 6967e6c6 (ceph): Merge branch 'teuth_firefly' into tasks_firefly
- 02:24 PM Revision f6a72a3d (ceph): Add wait_until_fuse_mounted()
- This was removed in a refactor in master, but it would take lots of work
to backport the entire refactor.
Signed-off... - 02:24 PM Revision 416f41e2 (ceph): Move write_secret_file() into task_util/kclient.py
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:24 PM Revision 4318e6ee (ceph): Import teuthology tasks (firefly branch)
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:24 PM Revision 6bd2b0fc (ceph): mds: Make min/max UID configurable for who is allowed to create a snapshot
- This way administrators can configure which UIDs are allowed to create
snapshots on CephFS.
In certain situations it... - 01:12 PM Revision a5ecf151 (ceph): powerdns: Update README with better markdown
- 12:37 PM rgw Bug #9039: Using COPY on radosgw to copy object from one bucket to another that's in another pool...
- Well, I think data copy is the right thing to do. If I put bucket in different pool is because they're configured dif...
- 10:40 AM rgw Bug #9039: Using COPY on radosgw to copy object from one bucket to another that's in another pool...
- The problem is that it is implicitly assumed with the new manifest that the tail is going to reside at the same pool ...
- 10:07 AM rgw Bug #9039: Using COPY on radosgw to copy object from one bucket to another that's in another pool...
- Really ? I didn't see anything in the code that checked whether the destination bucket was in the same pool or not an...
- 09:59 AM rgw Bug #9039: Using COPY on radosgw to copy object from one bucket to another that's in another pool...
- That sounds like an issue with the new (firefly) manifest.
- 07:21 AM rgw Bug #9039 (Resolved): Using COPY on radosgw to copy object from one bucket to another that's in a...
- Currently if you copy an object from a bucket to another one which is in another rados pool, things will just break. ...
- 09:34 AM Bug #9035 (Closed): ceph cluster is using more space than actual data after replication
- the used is simply summing the statfs(2) results on all the OSDs. you can see this by doing a df on the osd volumes,...
- 02:24 AM Bug #9035 (Closed): ceph cluster is using more space than actual data after replication
- Ceph cluster is using more space than estimated space to store data after replication.
Total cluster capacity is 5... - 08:43 AM Revision bf9726a2 (ceph): mon/OSDMonitor : Use user provided ruleset for replicated pool
- When creating a replicated pool, currently ceph ignore the ruleset
name provided by user but use a global default rul... - 07:52 AM rgw Bug #9037 (Duplicate): civetweb: error HEAD responses return body
- 07:40 AM rgw Bug #9037: civetweb: error HEAD responses return body
- Ah, sorry, somehow managed to miss it when I looked through the issue list. Please close this then.
- 07:34 AM rgw Bug #9037: civetweb: error HEAD responses return body
- See #8539
- 02:59 AM rgw Bug #9037 (Duplicate): civetweb: error HEAD responses return body
- 0.80.5 radosgw with civetweb frontend returns body data when sending an error response to a HEAD request. This breaks...
- 06:41 AM CephFS Feature #9029: min/max uid for snapshot creation
- 06:00 AM Bug #4254: osd: failure to recover before timeout on rados bench and thrashing; negative stats
- I am seeing this issue again on v0.80.4. I stopped 3 osd processes and marked them as out to trigger data migration (...
- 03:08 AM Feature #8496: erasure-code: ErasureCode base class
- "requeued on vps because plana are very busy":http://pulpito.ceph.com/loic-2014-08-07_12:09:48-upgrade:firefly-x:stre...
- 03:06 AM Feature #9025: erasure-code: chunk remapping
- "queued the suite on vps because plana are very busy":http://pulpito.ceph.com/loic-2014-08-07_12:06:56-upgrade:firefl...
- 12:54 AM Feature #9025: erasure-code: chunk remapping
- "upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-07_09:56:17-upgrade:firefly-x:stress-split-wip-...
- 01:42 AM Revision 9bbd1149 (ceph): Merge pull request #2220 from somnathr/wip-lock-leak-fix
- RadosClient: Fixing potential lock leaks.
Backport: firefly
Reviewed-by: Sage Weil <sage@redhat.com> - 01:30 AM Revision f1aad8bc (ceph): RadosClient: Fixing potential lock leaks.
- In lookup_pool and pool_delete, a lock is taken
before invoking wait_for_osdmap, but is not
released for the failure ... - 01:23 AM Feature #9034 (New): erasure-code: better LRC strategy
- The current LRC recovery strategy does not take advantage of all possibilities and may fail to discover a scenario th...
- 01:17 AM Feature #9033 (Resolved): erasure-code: simplified LRC
- Add implicit parity and simplified LRC as "described by Andreas":https://www.mail-archive.com/ceph-devel@vger.kernel....
- 12:45 AM Revision 0a1cea58 (ceph): os/FileStore: force any new xattr into omap on E2BIG
- If we have a huge xattr (or many little ones), the _fgetattrs() for the
inline_set will fail with E2BIG. The conditi... - 12:28 AM Revision 26750fcf (ceph): os/FileStore: force any new xattr into omap on E2BIG
- If we have a huge xattr (or many little ones), the _fgetattrs() for the
inline_set will fail with E2BIG. The conditi... - 12:11 AM Revision d050cf6c (ceph): Merge pull request #2218 from ceph/wip-rados-xattr
- rados: fix get/setxattr commands up
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 12:06 AM Revision e3819b62 (ceph): qa/workunits/rados/test_rados_tool: add a few xattr tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:06 AM Revision cc3112ef (ceph): rados: use STD{IN,OUT}_FILENO for magic values
- Signed-off-by: Sage Weil <sage@redhat.com>
08/06/2014
- 10:43 PM Revision 189e4a92 (ceph): Removed upgrade/dumpling from master branch as it should be only in dum...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:31 PM Revision 645c28a1 (ceph): rados: optionally read setxattr value from stdin
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:31 PM Revision 59a715a3 (ceph): rados: don't add \n to getxattr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:53 PM Revision e5b67f75 (ceph): Update doc
- File 'sysvinit' is necessary to allow the start of mon at each reboot.
Signed-off-by: François Lafont <francois.lafon... - 08:58 PM Revision 789284c4 (ceph): mon/PGMap: s/osdid/osd/ in 'osd perf' plaintext heading
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:39 PM Revision 1b8a9ec2 (ceph): mon/OSDMonitor: clean up 'osd perf' command placement
- This doesn't need an OSDMap; move it out of that block.
Signed-off-by: Sage Weil <sage@redhat.com> - 08:22 PM Revision 940e42df (ceph): osd/PG: populate pg_stats_t blocked_by
- Keep a PG member for OSDs that current block us, and fill it into the
stats struct when we publish. Use a vector<int... - 08:16 PM Revision ea731ae1 (ceph): qa/workunits/cephtool/test.sh: fix 'ceph df ...' tests
- Broken by ee2dbdb0f5e54fe6f9c5999c032063b084424c4c and friends.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:30 PM Revision bdf5f300 (ceph): use cluster name when checking the host
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:30 PM Revision 3fb25c28 (ceph): use name in /var/lib/ceph paths
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:29 PM Revision 9e08e3a7 (ceph): when starting an OSD, pass in the cluster name
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:40 PM Bug #9022 (Pending Backport): Potential lock leaks in RadosClient
- 02:58 AM Bug #9022: Potential lock leaks in RadosClient
- Pull request on the way.
- 02:58 AM Bug #9022 (Resolved): Potential lock leaks in RadosClient
- While going through RadosClient, identified couple of interfaces librados::RadosClient::lookup_pool() and librados::R...
- 06:37 PM Revision 0bd7c341 (ceph): PendingReleaseNotes: make note about rbd cache default change
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 64d5c406 (ceph): rgw: calc md5 and compare if user provided appropriate header
- Fixes: #8436
Backport: firefly
This was broken in ddc2e1a8e39a5c6b9b224c3eebd1c0e762ca5782. The fix
resurrects and o... - 06:32 PM Revision ebecd80d (ceph): rgw: calculate user manifest
- Fixes: #8169
Backport: firefly
We didn't calculate the user manifest's object etag at all. The etag
needs to be the m... - 06:28 PM Revision 8d8b8b11 (ceph): Merge pull request #2123 from ceph/wip-rbd-flush
- librbd: enable rbd cache by default; writethrough until flush
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:08 PM Revision 7d820123 (ceph): Merge pull request #2205 from ceph/wip-librbd-snap-meta
- librbd: fix crash with a chain of flattened images
Reviewed-by: Sage Weil <sage@redhat.com> - 05:51 PM Revision c0ef8b87 (ceph): rocksdb: fix i386 build
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:44 PM Revision 7a9b986a (ceph): rados: add {read,write}_ops to df json
- Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@redhat.com> - 05:41 PM Revision 0e9f3759 (ceph): Merge remote-tracking branch 'gh/wip-test-ceph-disk'
- 05:33 PM Revision 6168c3c9 (ceph): Merge pull request #2215 from ceph/wip-kb
- mon: clean up _kb fields in json and perf counter output
Reviewed-by: John Spray <john.spray@redhat.com> - 05:33 PM Revision ee2dbdb0 (ceph): mon/PGMonitor: remove {rd,wr}_kb from pool stat dumps
- These fields are replaced with corresponding *_bytes fields.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:33 PM Revision 4c8e3224 (ceph): mon: remove *_kb perf counters
- This is an incompatible change.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:26 PM Revision 1f3f2982 (ceph): rgw: fix crash in swift CORS preflight request
- Fixes: #8586
This fixes error handling, in accordance with commit 6af5a537 that fixed
the same issue for the S3 case... - 05:26 PM Revision 6e492150 (ceph): cls_rgw: fix object name of objects removed on object creation
- Fixes: #8972
Backport: firefly, dumpling
Reported-by: Patrycja Szabłowska <szablowska.patrycja@gmail.com>
Signed-off... - 05:21 PM Revision 53aab689 (ceph): Merge pull request #75 from ceph/wip-readforward
- include readforward cache mode in cache mode cycling test
Reviewed-by: Samuel Just <sam.just@inktank.com> - 04:18 PM Revision 3179bb10 (ceph): mon/PGMonitor: add _bytes perf counters
- Leave the _kb ones in place for now.
Backport: firefly
Signed-off-by: Sage Weil <sage@redhat.com> - 04:14 PM Revision adb2791a (ceph): mon/PGMonitor: add _bytes fields for all usage dumps
- Leave the _kb ones in place for now.
Backport: firefly
Signed-off-by: Sage Weil <sage@redhat.com> - 04:06 PM Revision fce2ed68 (ceph): Remove most ceph-specific tasks. They are in ceph-qa-suite now.
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:50 PM Revision 7dbd4401 (ceph): ignore errors if 'ps aux' fails
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit f9aa9c1e647dc3376a33d0f7147501bffcd... - 03:42 PM Revision d5f26aaf (ceph): Merge pull request #306 from ceph/wip-9024
- ignore errors if 'ps aux' fails
- 03:39 PM Feature #9031: List RADOS namespaces and list all objects in all namespaces
A way to implement this is to enhance the pg_ls_repsonse_t to include the namespace (or change object_t to hobject_...- 02:30 PM Feature #9031 (Resolved): List RADOS namespaces and list all objects in all namespaces
- We can currently create namespaces, but cannot easily view those that have been created. A method of listing namespac...
- 03:23 PM Revision b416446c (ceph): Merge pull request #2165 from dachary/wip-mailmap
- mailmap updates
- 03:23 PM devops Bug #9032 (Rejected): ceph-deploy over proxy
- I have my servers working behind a proxy. When I run the ceph-deploy install command I get an error:
[ceph01][INFO ... - 03:16 PM Revision 895318c0 (ceph): README.md: word wrap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:15 PM Revision 500b95e5 (ceph): README: symlink from README.md
- It looks better as markdown than rendered as text via the markdown tool,
so just symlink it.
Signed-off-by: Sage Wei... - 02:53 PM Revision f9aa9c1e (ceph): ignore errors if 'ps aux' fails
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:46 PM Revision 25b9761e (ceph): Merge pull request #2202 from xinxinsh/enable-rocksdb-log-level
- Enable rocksdb log level
Reviewed-by: Sage Weil <sage@redhat.com> - 02:05 PM Feature #9030 (Fix Under Review): mon: quickly identify 'problem' osds
- 02:05 PM Feature #9030 (Resolved): mon: quickly identify 'problem' osds
- 01:53 PM Revision 0114b335 (ceph): erasure-code: rework ErasureCode*::parse methods
- The ErasureCode::parse virtual function is derived in
ErasureCode{Jerasure,Isa}. It is reworked to share parsing argu... - 01:44 PM Revision 77690f66 (ceph): erasure-code: move to ErasureCode::decode_concat
- It does not belong to ErasureCodeInterface which is supposed to not have
any implementation.
Signed-off-by: Loic Dac... - 01:22 PM Revision 54394fa1 (ceph): erasure-code: move to ErasureCode::to_{int,bool}
- The parameter parser helpers to_int and to_bool are moved from
ErasureCode{Jerasure,Isa} to ErasureCode.
The prototy... - 01:21 PM Revision 4ff981f4 (ceph): erasure-code: move to ErasureCode::{encode,decode}{,chunk}
- The bulk of ErasureCode{Jerasure,Isa}::encode and
ErasureCode{Jerasure,Isa}::decode is dealing with alignment and buf... - 01:21 PM Revision b4b7c51f (ceph): erasure-code: move to ErasureCode::minimum_to_decode*
- The ErasureCode{Jerasure,Isa}::minimum_to_decode and
ErasureCode{Jerasure,Isa}::minimum_to_decode_with_cost methods a... - 01:21 PM Revision 1ebce988 (ceph): erasure-code: ErasureCode base class
- Add the ErasureCode base class for ErasureCodeJerasure and
ErasureCodeIsa, for methods that can be shared among all p... - 12:55 PM Bug #8860 (Fix Under Review): ceph-disk issues with custom cluster name
- PR opened https://github.com/ceph/ceph/pull/2216
- 12:25 PM CephFS Feature #9029 (Resolved): min/max uid for snapshot creation
- On shared systems like shared hosting it might be useful to prevent regular users from creating snapshots on CephFS.
... - 12:20 PM rgw Feature #6747: PowerDNS backend for RGW bucket directing
- 11:06 AM rbd Bug #8845 (Pending Backport): Flattening Clones of clone, results in command failure
- 09:41 AM Bug #9019 (Resolved): Makefile.am: error: required file './README' not found
- fixed it up with a symlink.. other solutions seemed more annoying :(
- 08:39 AM Linux kernel client Bug #8818 (Resolved): IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- OK, thanks everybody....
- 08:09 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- I switched to the good kernel (3.16.0-ceph-00037-g0532581) yesterday and re-ran my scripts overnight. The scripts co...
- 08:39 AM Linux kernel client Bug #8464 (Resolved): krbd: deadlock
- OK, thanks everybody....
- 08:06 AM Feature #8496: erasure-code: ErasureCode base class
- "scheduled upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-06_17:07:04-upgrade:firefly-x:stress-...
- 06:22 AM Feature #8496: erasure-code: ErasureCode base class
- The test "only had one job":http://pulpito.ceph.com/loic-2014-08-05_13:45:56-upgrade:firefly-x:stress-split-wip-8496-...
- 07:12 AM Feature #9025 (Fix Under Review): erasure-code: chunk remapping
- "need review":https://github.com/ceph/ceph/pull/2213
- 06:28 AM Feature #9025 (Resolved): erasure-code: chunk remapping
- Interpret the *mapping* parameter and remap the chunks accordingly. For instance mapping=_DD means the data chunks ar...
- 07:11 AM CephFS Feature #9026 (Resolved): client: vxattr support for rctime, rsize, etc.
- 05:44 AM Bug #9023 (Can't reproduce): valgrind failures in OSD
osd.2 from OSD.cc:462 (SafeTimer::init, pthread_create)
http://pulpito.front.sepia.ceph.com/john-2014-08-01_11:0...
08/05/2014
- 11:48 PM Revision 859944d3 (ceph): test/osd/osd-test-helpers: mkdir -p for ceph-disk
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:38 PM Revision 4b45e25b (ceph): Add handles for the ceph-mon starting with upstart
- 11:22 PM Feature #9021 (Resolved): librbd: shared flag, object map
- we need to consider to make a tradeoff between multi-client support and single-client support for librbd. In practice...
- 10:43 PM Bug #8797: "ceph status" do not exit with python_2.7.8
- For a moment Python maintainer in Debian kindly fixed this issue for us by adding patch to revert problematic change ...
- 10:25 PM Revision 818f5b70 (ceph): Merge pull request #2208 from lpabon/osd_dev_doc
- Developer quick start guide
Reviewed-by: Sage Weil <sage@redhat.com> - 10:11 PM Revision c2f58e66 (ceph): test/ceph-disk.sh: mkdir -p
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:52 PM Revision 511a0597 (ceph): Merge pull request #76 from ceph/wip_tune2_upgrade-firefly
- Added ec-readwrite.yaml to the mix to enable erasure code coverage
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:48 PM Revision 542dbd2a (ceph): Added ec-readwrite.yaml to the mix to enable erasure code coverage
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:06 PM Revision 3f9f135f (ceph): Merge remote-tracking branch 'upstream/next' into wip-sam-testing
- Conflicts:
src/osd/OSD.cc - 07:34 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- The 00036 "bad" kernel started showing the problem in the /var/log/kern.log file within minutes of starting my test s...
- 12:49 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Eric, Greg,
The fix on top of 3.16 + testing is in wip-request-fn.
http://gitbuilder.ceph.com/kernel-deb-precis... - 06:51 PM Revision a923e2c9 (ceph): Renamed README to README.md to render in markdown
- Signed-off-by: Luis Pabón <lpabon@redhat.com>
- 06:48 PM Revision 52cf693e (ceph): Developer quick start guide
- Signed-off-by: Luis Pabón <lpabon@redhat.com>
- 06:16 PM Bug #9019 (Resolved): Makefile.am: error: required file './README' not found
- commit(a923e2c9eb16823fa484c) Renamed README to README.md to render in markdown. After that, i can't generate Makefil...
- 06:15 PM Bug #9008: Objecter: pg listing can deadlock when throttling is in use
- > I'm guessing the request is hung on teh OSD side of things...
Thanks Sage. Sadly after radosgw daemon restarting, ... - 08:28 AM Bug #9008 (Need More Info): Objecter: pg listing can deadlock when throttling is in use
- 08:28 AM Bug #9008: Objecter: pg listing can deadlock when throttling is in use
- please query the admin socket for the process like so:
ceph daemon /var/run/ceph/ceph-client.*.asok objecter_requ... - 02:44 AM Bug #9008 (Resolved): Objecter: pg listing can deadlock when throttling is in use
- In our Ceph cluster (with radosgw), we found that occasionally the processing threads hands forever and eventually ha...
- 06:11 PM Revision c09036ac (ceph): enable info_log_level config option for rocksdb
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 05:21 PM Revision e6935dd4 (ceph): Merge pull request #2206 from ceph/wip-8875
- doc: be a bit more explicit about 'ceph-deploy new' in quickstart
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 04:52 PM Revision 66de51d1 (ceph): be a bit more explicit about 'ceph-deploy new' in quickstart
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 04:15 PM Revision 3876da15 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 04:15 PM Revision bc1d2b83 (ceph): Merge remote-tracking branch 'gh/wip-8880'
- Conflicts:
src/osd/OSD.cc - 03:50 PM Revision 19b9ee94 (ceph): Merge pull request #2204 from osynge/wip-dont-mkdir-by-mistake2
- Do not make directories by mistake.
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 03:50 PM Revision b8c1cabd (ceph): Merge pull request #1883 from ceph/wip-msgr
- messenger refactoring for xio
Reviewed-by: Greg Farnum <greg@inktank.com> - 03:28 PM Revision b4c80e31 (ceph): Do not make directories by mistake.
- Rational: I found I had created a series of OSD directories under "/dev/" when disks I thought existed did not exist....
- 02:57 PM Revision e5b3c093 (ceph): Merge pull request #2200 from theanalyst/typo
- doc: typo s/loose/lose
Reviewed-by: Sage Weil <sage@redhat.com> - 02:33 PM Revision f773b24e (ceph): powerdns: Define a application variable when not invoked from Shell
- This allows to be run directly using mod_wsgi behind Apache.
- 02:24 PM Bug #9018 (Resolved): "LibRadosTwoPoolsPP*" failed in upgrade:dumpling-x-firefly---basic-vps
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-05_09:22:33-upgrade:dumpling-x-firefly---basic-vps...
- 02:13 PM devops Feature #8868: Update Fedora to 0.80.5 packages with ceph-common
- So, there's a PR open for some restructuring of the .spec file now that we need to get in soon to make this more sane...
- 01:21 PM Fix #6278 (Resolved): osd: throttle snap trimming
- 01:20 PM devops Fix #9017 (Rejected): [paddles] implement validation across all controller methods
- paddles has a lot of boilerplate in controllers that look like:...
- 01:15 PM Feature #9015 (Resolved): msgr refactoring to support xio work
- 01:09 PM Feature #9015 (Resolved): msgr refactoring to support xio work
- 01:14 PM Fix #8905 (In Progress): msgr: encode osd epoch in nonce to avoid misc OSD reconnect races
- 01:10 PM Feature #7516 (Fix Under Review): mon: reweight-by-pg
- 01:06 PM Feature #7238 (In Progress): erasure code : implement LRC plugin
- 12:55 PM Bug #8083: erasure-code: fix static code analysis errors found in gf-complete
- 12:28 PM Documentation #8875 (Resolved): `ceph-deploy new` needs to be called for every node, not just the...
- PR https://github.com/ceph/ceph/pull/2206
and merged commit e6935dd into master - 09:37 AM Documentation #8875 (In Progress): `ceph-deploy new` needs to be called for every node, not just ...
- I noted the problem in the docs and will fix that shortly.
You are right, you need to run `ceph-deploy new {NODES}... - 11:19 AM Bug #9011: osd memory leaks on next
- gonna see if this happens on plana too
- 11:13 AM Bug #9011: osd memory leaks on next
- these look like static std::strings. and some other weird leaks that don't make sense...
- 08:00 AM Bug #9011 (Duplicate): osd memory leaks on next
- ubuntu@teuthology:/a/sage-2014-08-04_11:34:19-rgw-next-testing-basic-vps/397606
need to clean these up - 09:26 AM rgw Feature #9013 (Resolved): rgw: set civetweb as a default frontend
- Should add civetweb to the default frontends.
- 09:13 AM Messengers Bug #8880 (Pending Backport): msg/Pipe.cc: 1538: FAILED assert(0 == "old msgs despite reconnect_s...
- 09:11 AM Bug #9012 (Duplicate): "[WRN] map e277 wrongly marked me down" in upgrade:dumpling-x-firefly---ba...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-08-04_14:18:17-upgrade:dumpling-x-firefly---basic-vps...
- 09:05 AM rgw Feature #8218 (In Progress): rgw: object versioning manifest changes
- 09:05 AM rgw Feature #8217 (In Progress): rgw: object versioning object overwrite / delete changes
- 09:05 AM rgw Feature #8216 (In Progress): rgw: object versioning objclass support
- 09:05 AM rgw Feature #8473 (In Progress): rgw: Shard bucket index objects to improve single bucket PUT throughput
- 08:54 AM rbd Bug #8845 (Fix Under Review): Flattening Clones of clone, results in command failure
- https://github.com/ceph/ceph/pull/2205
- 08:52 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- btw, the steps to reproduce this issue are mentioned by Sahana above & it can be reproduced on a single node too.
... - 08:47 AM Fix #8914: osd crashed at assert ReplicatedBackend::build_push_op
- Hi Greg,
No i did not intend to add any comments.
The reason i thought we should assert is, so that we can serv... - 08:25 AM Bug #9007 (Duplicate): Ceph Firefly 0.80.4 : Unable to get some pool values
- you're right. this is fixed in master, and backported to firefly-next.. will be in next firefly point release.
- 01:50 AM Bug #9007 (Duplicate): Ceph Firefly 0.80.4 : Unable to get some pool values
- h1. Hello Developers
I am curious to know if there is something missing from the code for Ceph pool values.
As... - 07:56 AM rgw Bug #8676: md5sum check failed during readwrite.py
- ubuntu@teuthology:/a/sage-2014-08-04_11:34:19-rgw-next-testing-basic-vps/397522
- 05:05 AM Revision 1682e62e (ceph): doc: typo s/loose/lose
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 04:46 AM Feature #8496: erasure-code: ErasureCode base class
- "upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-05_13:45:56-upgrade:firefly-x:stress-split-wip-...
- 12:48 AM Feature #8496 (Fix Under Review): erasure-code: ErasureCode base class
- "pull request":https://github.com/ceph/ceph/pull/2201
- 04:22 AM Bug #9009 (In Progress): (wip-objecter) ObjectCacher assert in fs client
- OK, no big deal, just that there are contexts in the Client, like the MDS, which need updating to take client_lock wh...
- 03:49 AM Bug #9009 (Resolved): (wip-objecter) ObjectCacher assert in fs client
From branch wip-mds-contexts, which is a derivative of wip-objecter.
http://qa-proxy.ceph.com/teuthology/john-20...- 03:21 AM rgw Feature #8911: RGW doesn't return 'x-timestamp' in header which is used by 'View Details' of Open...
- It also doesnot returns "Content-type" header as well. Swift does return this header aswell. So I would love to see r...
- 12:45 AM rgw Documentation #9003: rgw: document development setup for rgw
- Much needed. Great!
- 12:41 AM Revision 541006c8 (ceph): Merge pull request #1875 from dachary/wip-8437
- erasure-code: benchmarking jerasure
Reviewed-by: Sage Weil <sage@redhat.com>
08/04/2014
- 11:33 PM Feature #8496 (In Progress): erasure-code: ErasureCode base class
- Because it needs work to adapt the isa plugin, it deserves a separate patch. Otherwise it mixes two unrelated topics.
- 05:12 AM Feature #8496 (Rejected): erasure-code: ErasureCode base class
- It is part of a "larger pull request":https://github.com/ceph/ceph/pull/1911
- 11:21 PM Bug #8736: thrash and scrub combination lead to error
- http://pulpito.ceph.com/loic-2014-08-04_15:06:02-upgrade:firefly-x:stress-split-wip-8475-testing-basic-plana/396887/
... - 11:16 PM Revision 466aba42 (ceph): osd/osd_types: add blocked_by to pg_stat_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:09 PM Revision b65cef67 (ceph): ceph_test_rados_api_tier: fix [EC] HitSet{Read,Write,Trim} tests
- The hit_set_ fields can only be set on tier pools as of
f131dfbaedf6f451572e7aa3a83f653912122953.
Fixes: #8823
Signe... - 11:02 PM Feature #8475 (Resolved): erasure-code: oversized objects when using the Cauchy technique
- 06:05 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- "scheduled upgrade:firefly-x:stress-split":http://pulpito.ceph.com/loic-2014-08-04_15:06:02-upgrade:firefly-x:stress-...
- 02:07 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- "Rebased and repushed":https://github.com/ceph/ceph/pull/1890 , running gitbuilder
- 10:24 PM Revision b9b022e5 (ceph): add annotation for rocksdb config option
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 10:12 PM Revision dceab8dc (ceph): Merge pull request #2198 from ceph/wip-8998
- fix OSD SEGV in heartbeat()
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:01 PM Revision 8dcfbd8e (ceph): osd: simplify dout_prefix macros
- Use a get_osdmap_epoch() helper that is a bit lighter weight (by avoiding
copying around an OSDMapRef).
Signed-off-b... - 09:57 PM Revision 80829d78 (ceph): osd: reorder OSDService methods under proper dout_prefix macro
- The dout_prefix for OSDService uses get_osdmap() to grab a shared_ptr for
the epoch printout. The OSD one does not, ... - 09:02 PM Revision 97f317d8 (ceph): rados/singleton: make cache mode cycling include readforward mode
- forward -> off -> writeback -> readforward -> ...
Signed-off-by: Sage Weil <sage@redhat.com> - 08:56 PM Revision 0b445e0f (ceph): Merge remote-tracking branch 'gh/next'
- 08:48 PM Revision 047c18db (ceph): doc/release-notes: make note about init-radosgw change
- This changed back in 524aee6f95f9c397b7c8508934f3c0577f9df1dd but
was not mentioned in the release notes.
Signed-off... - 08:38 PM Revision b93abaf5 (ceph): Merge pull request #305 from ceph/wip-8640
- implement `--version` and improve `setup.py`
- 08:00 PM rgw Feature #3454: Support temp URLs for Swift API
- This should be documented somewhere too, at least in the table at http://ceph.com/docs/master/radosgw/swift/
- 07:12 PM Revision fe6f4611 (ceph): create a --version flag for teuthology
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:11 PM Revision 7d0a072d (ceph): pull the version and description in setup.py
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:11 PM Revision a2bb186f (ceph): add an initial version to teuthology
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:47 PM Revision 354c4112 (ceph): doc: Added 'x' to monitor cap.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:50 PM Revision 0d1fe79b (ceph): Tweak usage statement
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:33 PM Revision 18b7a37c (ceph): Merge pull request #2166 from majianpeng/bug-fix
- os/FileJournal: When dump journal, using correctly seq avoid misjudging joural corrupt.
Reviewed-by: Samuel Just <sa... - 05:32 PM Revision 6878e8cd (ceph): Merge pull request #2184 from majianpeng/fix2
- ECBackend: Don't directyly use get_recovery_chunk_size() in RecoveryOp::WRITING state
Reviewed-by: Samuel Just <sam.... - 05:31 PM Revision 6f05ff8f (ceph): Merge pull request #2194 from majianpeng/fix1
- osd/ECBackend: clean up assert(r==0) in continue_recovery_op.
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:30 PM Revision 3897f09a (ceph): Merge pull request #2192 from ceph/wip-8891
- msg/SimpleMessenger: drop msgr lock when joining a Pipe
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:04 PM Revision 7b2c8b33 (ceph): cls_rgw: fix object name of objects removed on object creation
- Fixes: #8972
Backport: firefly, dumpling
Reported-by: Patrycja Szabłowska <szablowska.patrycja@gmail.com>
Signed-off... - 05:03 PM Revision 8519e9ab (ceph): rgw: need to pass need_to_wait for throttle_data()
- need_to_wait wasn't passed into processor->throttle_data(). This was
broken in fix for #8937.
CID 1229541: (PW.PA... - 04:52 PM Revision 06206247 (ceph): rgw: call processor->handle_data() again if needed
- Fixes: #8937
Following the fix to #8928 we end up accumulating pending data that
needs to be written. Beforehand it ... - 04:51 PM Revision 2f44d768 (ceph): Merge pull request #2191 from ceph/wip-rgw-need-to-wait
- rgw: need to pass need_to_wait for throttle_data()
Reviewed-by: Sage Weil <sage@redhat.com> - 04:41 PM Revision 78b2c10a (ceph): Merge pull request #2195 from apeters1971/wip-ec-isa-fast-xor
- EC-ISA: provide a 10% faster simple parity operation for (k, m=1)
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:28 PM Revision b22a8a9e (ceph): Merge pull request #2193 from ceph/wip-ceph-conf
- ceph-conf: flush log on exit
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:10 PM Revision ef210806 (ceph): Merge pull request #304 from ceph/wip-fix-build-matrix
- suite: fix build_matrix when non-yaml present in % dir
- 04:07 PM Revision 21e27637 (ceph): suite: fix build_matrix when non-yaml present in % dir
- First, if we get a non-yaml file, return an empty list.
Second, if we are in a % mode, exclude an empty raw result f... - 03:19 PM Revision dc3ae881 (ceph): add another call to use "ps aux"
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 4686115c4830939ea6c9d7a27fd89d7cec9... - 03:19 PM Revision c949ad1d (ceph): tell us if you are really not running any more
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit ec342d814676d08eb833f478ac7ffdb21cc... - 03:09 PM Bug #8998 (Pending Backport): osd: SEGV in OSD::heartbeat()
- 03:00 PM Bug #8998 (Fix Under Review): osd: SEGV in OSD::heartbeat()
- https://github.com/ceph/ceph/pull/2198
- 09:14 AM Bug #8998: osd: SEGV in OSD::heartbeat()
- ubuntu@teuthology:/a/teuthology-2014-08-03_02:30:01-rados-next-testing-basic-plana/394893
- 02:18 PM rgw Feature #9004 (New): rgw: multi-site: multi-master
- As a user, I want to be able to write to any available RGW and have that file available on other RGWs for read and wr...
- 02:06 PM Bug #8891 (Resolved): rados bench hang during thrashing
- 09:17 AM Bug #8891 (Fix Under Review): rados bench hang during thrashing
- 01:53 PM rgw Documentation #9003: rgw: document development setup for rgw
- While we're at it, beefing up the rgw support in vstart.sh would be great. right now you can pass RGW=1 and it will ...
- 01:49 PM rgw Documentation #9003 (Closed): rgw: document development setup for rgw
- 01:51 PM Revision 516101ae (ceph): EC-ISA: provide a 10% faster simple parity operation for (k, m=1). Add ...
- 11:20 AM rgw Bug #9002 (Duplicate): Creating swift key with --gen-secret in separate step from subuser creatio...
- Customer reported on CentOS with Ceph v0.80.4
Steps to reproduce:
radosgw-admin user create --uid=testuser1 --dis... - 11:00 AM rgw Bug #9001 (Won't Fix): Starting gateway with radosgw init script fails to create socket
- Ceph Version: v0.80.4
Distro: CentOS
Customer reported, unable to reproduce.
/var/run/ceph directory owned by ... - 10:02 AM Revision 985b7c2f (ceph): osd/ECBackend: clean up assert(r==0) in continue_recovery_op.
- After the commit(d9106ce5e4437ab02), the assert(r==0) is no longer
necessary. - 09:42 AM Revision 8363a94a (ceph): erasure-code: HTML display of benchmark results
- The ceph_erasure_code_benchmark output is converted into a JSON series
suitable to display in HTML with the http://ww... - 09:42 AM Revision 3cc72345 (ceph): COPYING: Cloudwatt copyright is inline
- Remove partial list of contributions since Cloudwatt copyright has been
placed in the copyright notices of the files ... - 09:42 AM Revision e11c3fcc (ceph): erasure-code: rework benchmark suite
- Expand the default suite to enumerate all cases that are relevant to the
current code base so that it is easier to co... - 09:42 AM Revision 90592e9d (ceph): erasure-code: properly indent ErasureCodePluginSelectJerasure.cc
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:41 AM Revision be3e1e40 (ceph): erasure-code: control jerasure plugin variant selection
- The jerasure-variant parameter is interpreted as the name of the plugin
variant to be loaded regardless of the availa... - 09:41 AM Revision 5fb4354f (ceph): erasure-code: reduce jerasure verbosity
- Only output a message about adjusting the buffer size when it is
adjusted, not when the size does not need adjustment... - 09:16 AM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- ubuntu@teuthology:/a/teuthology-2014-08-03_02:30:01-rados-next-testing-basic-plana/395219
- 08:54 AM Revision 3987ac2a (ceph): erasure-code: cauchy techniques allow w 8,16,32
- Enforce the restriction at initialization time, the same way it is done
for Reed Solomon. Choosing a w value differen... - 08:54 AM Revision c7daaaf5 (ceph): erasure-code: implement alignment on chunk sizes
- jerasure expects chunk sizes that are aligned on the largest possible
vector size that could be used by SSE instructi... - 07:07 AM Linux kernel client Bug #8979: GPF kernel panics - auth?
- pushed wip-8979 which removes the fixed buffer size. but, we still need to make things not crash when the auth reply...
- 06:57 AM Linux kernel client Bug #8979: GPF kernel panics - auth?
- yeah:
#define TEMP_TICKET_BUF_LEN 256
- 06:48 AM Linux kernel client Bug #8979: GPF kernel panics - auth?
- ...
- 06:52 AM Revision cb54605b (ceph): mailmap: sort entries
- to help avoid duplicates (found one)
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:50 AM Revision accf8c26 (ceph): mailmap: Tommi Virtanen is not with Red Hat
- The entry was added by s/inktank/redhat/ and did not acknowledge that
Tommi Virtanen left Inktank before it was acqui... - 06:50 AM Revision 794f70a8 (ceph): mailmap: Kevin Cox affiliation
- Reviewed-by: Kevin Cox <kevincox@kevincox.ca>
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:50 AM Revision 6652494e (ceph): mailmap: Accela Zhao affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:50 AM Revision 6f238fa0 (ceph): mailmap: Adam Crume affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:50 AM Revision 6f24a049 (ceph): mailmap: Stephen Jahl affiliation
- Reviewed-by: Stephen Jahl <stephenjahl@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:50 AM Revision b1ba72f8 (ceph): mailmap: George Ryall affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:50 AM Revision 2f21a110 (ceph): mailmap: Brian Rak affiliation
- and name normalization
Reviewed-by: Brian Rak <dn@devicenull.org>
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:50 AM Revision ef620cc3 (ceph): mailmap: Sebastien Ponce name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:50 AM Revision f870b344 (ceph): mailmap: João Eduardo Luís name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 06:48 AM Revision d8e64157 (ceph): mailmap: Ma Jianpeng affiliation
- and name normalization
Reviewed-by: Ma Jianpeng <jianpeng.ma@intel.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:36 AM Documentation #8875: `ceph-deploy new` needs to be called for every node, not just the admin one
- I was able to complete install.
The first step above granted sudo rights on each node.
The way I was able to get it... - 05:56 AM Documentation #8875: `ceph-deploy new` needs to be called for every node, not just the admin one
- You still need a user that can call sudo without a password prompt on remote nodes.
And it looks like you only pas... - 05:47 AM devops Bug #8893 (Resolved): ceph-deploy install command on centos 6.5 reports exception
- merged commit eb9ea33 into ceph:master
- 04:00 AM Revision 3230060f (ceph): ceph-conf: flush log on exit
- This makes it deterministic whether we output
2014-08-03 20:59:45.482614 4036c80 -1 did not load config file, using ... - 03:09 AM Revision 076f33af (ceph): ECBackend: Don't directly use get_recovery_chunk_size() in RecoveryOp::... <