Activity
From 05/24/2013 to 06/22/2013
06/22/2013
- 05:28 PM Revision 1aca370e (ceph): debian: ceph-common requires matching version of python-ceph
- If they skew the ceph_argparse.py module may be missing.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:15 PM Bug #5401: cuttlefish osd recovery slow
- This one seems to "hide" the problem:
commit 9fe5611fdd7374654ad58185fa3988e216c52f08
Author: Stefan Priebe <s.prie... - 02:04 PM Bug #5401: cuttlefish osd recovery slow
- max may also be negative but there is only a check for == 0 in OSD.cc
- 01:03 PM Bug #5401: cuttlefish osd recovery slow
- It seems locking and unlocking the mutex isn't working correctly. So multiple threads seem to higher recovery_ops_act...
- 12:31 PM Bug #5401: cuttlefish osd recovery slow
- g_conf->osd_recovery_max_active is 5 but on a freshly started osd i'm seeing log messages like these ...2013-06-22 .....
- 06:10 AM Bug #5401: cuttlefish osd recovery slow
- It did defer the recovery again and again. Some example log output:
2013-06-22 15:07:20.187878 7f8c3f49c700 15 osd... - 04:11 AM Bug #5401: cuttlefish osd recovery slow
- I could hide this problem by higher "osd recovery delay start" => 120 but then the overall recovery time is very high...
- 12:04 PM Bug #5424: mon/Paxos.cc: 549: FAILED assert(begin->last_committed == last_committed)
- Greg Farnum wrote:
> Shouldn't that cause LevelDB to block or throw an error or something? I'm not quite sure how it... - 10:22 AM Bug #5424: mon/Paxos.cc: 549: FAILED assert(begin->last_committed == last_committed)
- Shouldn't that cause LevelDB to block or throw an error or something? I'm not quite sure how it leads to us not readi...
- 09:53 AM Bug #5424 (Resolved): mon/Paxos.cc: 549: FAILED assert(begin->last_committed == last_committed)
- all peons died with teh above assert. the leader did this:...
- 04:59 AM Revision d7af5e14 (ceph): rgw: handle bucket creation with specified placement pool
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:46 AM Revision b89d7420 (ceph): Merge branch 'next'
- Conflicts:
src/ceph.in - 01:39 AM Revision 94eada40 (ceph): Add header comments and Inktank copyrights to ceph.in/ceph_argparse.py
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:39 AM Revision 67a3c1e4 (ceph): ceph.in: rip out reusable code to pybind/ceph_argparse.py
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Conflicts:
src/ceph.in
06/21/2013
- 11:50 PM Bug #5195 (In Progress): "ceph-deploy mon create" fails when adding additional monitors
- The problem occurs when a monitor is added on a host that was not in the initial list of cluster members.
Sequence... - 11:22 PM Revision c1198d68 (ceph): debian: update postinst, prerm hooks
- This syncs up the hooks with the latest master versions. In particular,
do not blindly stop/restart daemons on packa... - 11:16 PM Revision 2fcbf2ba (ceph): rgw: user configuration for bucket placement
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:06 PM Revision e5e924ca (ceph): rgw: data structures for new data/index placement rules
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:53 PM Revision d39d648e (ceph): Merge remote-tracking branch 'remotes/origin/wip-sandon-cephdeploy'
- 10:52 PM Revision c4272a17 (ceph): ceph: even shinier
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:50 PM Revision 34ef2f24 (ceph): ceph: do not busy-loop on ceph -w
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:27 PM Revision a6142a64 (ceph): Merge pull request #14 from clee/cleanup
- Clean up nested-if logic
Reviewed-by: Sage Weil <sage@inktank.com> - 09:53 PM Revision 27912e58 (ceph): librados: make cmd test tolerate NXIO for osd commands
- The cluster may be thrashing underneath us; tolerate NXIO in case the OSD
is currently down.
Signed-off-by: Sage Wei... - 09:45 PM Revision f6270a7f (ceph): Wipe out existing id_rsa.pub and id_rsa before pushing ssh keys
- A very simple change. Just touch a file first (to create it if it
doesn't yet exist so the delete doesn't error out) ... - 09:25 PM Revision dcd27531 (ceph): Merge remote-tracking branch 'gh/wip-mds'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 09:23 PM Revision abd0ff64 (ceph): mds: do not assume segment list is non-empty in standby_trim_segments
- If we restart standby replay shortly after startup, before we actually have
any segments, we an trigger a segfault he... - 06:53 PM Revision 241ad073 (ceph): rgw: make replica log object name configurable
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:53 PM Revision d572cf6f (ceph): mds: fix iterator invalidation for backtrace removal
- - Don't increment before we dereference!
- We need to update the iterator before we delete the item.
This code is ch... - 06:50 PM Revision 8e4c292e (ceph): rados: whitelist 'had wrong client addr' for cephtool test
- Recently added stuff to cephtool/test.sh workunit that triggers this.
fd769c0f21aab47cb7faacf7b6122e5288f1156e - 06:47 PM Revision 469900e6 (ceph): RGWReplicaBucketLogger: store bucket replica logs in the .logs pool
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 05:53 PM Revision 409422be (ceph): Merge branch 'wip-rgw-geo-2' into wip-rgw-geo
- Conflicts:
src/test/cli/radosgw-admin/help.t - 05:47 PM rgw Bug #5422 (Resolved): object deletion should log the object tag
- object tags are used to tell one instance of an object from another with the same name (to differentiate a deleted ob...
- 05:07 PM Bug #5414 (Resolved): qa jobs failing with /var/lib/ceph/osd/*/journal root-owned from prior clus...
- 04:30 PM Bug #5414: qa jobs failing with /var/lib/ceph/osd/*/journal root-owned from prior clusters
- 10:29 AM Bug #5414 (Resolved): qa jobs failing with /var/lib/ceph/osd/*/journal root-owned from prior clus...
- this is causing various runs to fail. so far i see it on upgrade runs. maybe the package update is triggering somet...
- 04:35 PM Revision 50957772 (ceph): osd: init test_ops_hook
- CID 1019628 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "test_ops_... - 04:35 PM Revision 17d2745f (ceph): osd: initialize OSDService::next_notif_id
- CID 1019627 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "next_notif... - 03:20 PM Revision 3bebbc09 (ceph): mds: rev protocol
- Commit 18b9e63b4df643e1f2fb8f17416089e5d970bf60 changed the OTW lock
encoding.
Signed-off-by: Sage Weil <sage@inktan... - 03:19 PM Revision ded2e84f (ceph): mds: kill Server::handle_client_lookup_hash()
- Server::handle_client_lookup_ino() is more simple and robust. Use it
to handle both LOOKUPHASH and LOOKUINO requests.... - 03:19 PM Revision 2147c4e3 (ceph): mds: use "open-by-ino" helper to handle LOOKUPINO request
- Fixes #3541
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 02:33 PM rgw Feature #4335 (Resolved): rgw: dr: sync processing state: define datastructures
- Oooh! Oooh! Merged into the integration branch.
- 02:15 PM Feature #5421: mon: add formatter option for various mon commands
- I've done "auth export". The tricky bit is understanding the naming and levels of containers (that end up unnamed in...
- 02:13 PM Feature #5421 (Resolved): mon: add formatter option for various mon commands
- 02:14 PM Feature #4983: OSD: namespaces pt 2 (caps)
- 02:08 PM Feature #3983 (In Progress): api: create initial DRAFT REST API Design
- 02:08 PM Feature #4463 (In Progress): api: RESTful client: demonstrate remaining N-1 commands JSON or XML
- 02:07 PM Feature #4462 (In Progress): api: RESTful client: implement remaining N-1 commands JSON or XML
- 02:07 PM Feature #4459 (In Progress): api: RESTful client: implement remaining commands JSON only
- 02:07 PM Feature #4460 (In Progress): api: RESTful client: demonstrate remaining N-1 commands JSON only
- 02:07 PM Fix #5278 (In Progress): osd: smarter recovery for small objects
- 02:06 PM Feature #4457 (Resolved): api: add JSON schema/output protocol to rados.py
- 02:06 PM Feature #4458 (Resolved): api: RESTful client: prototype 1 command JSON only
- 02:06 PM Feature #4461 (Resolved): api: RESTful client: prototype 1 command JSON or XML
- 02:06 PM Feature #4547 (Resolved): api: implement self-description for --admin-daemon commands
- 02:04 PM Feature #4548 (Resolved): api: implement self-description for osd/mon tell commands
- 02:04 PM Feature #4455 (Resolved): api: move '--format' into just another command argument
- 01:58 PM rgw Feature #5420 (Rejected): rgw: integrate bucket metadata changes with bucket index log
- for the sake of correctness and robustness
- 01:43 PM devops Feature #5013 (In Progress): build internal openstack + ceph cluster out of some burnupi
- 01:43 PM devops Feature #5214 (In Progress): Kernel gitbuilders for rpm distros
- 12:48 PM Feature #5419 (New): cephtool: sanitize extra args before configuring cluster handle
- The '--admin-socket' argument is not a valid ceph tool argument. The option one would actually want is '--admin-daemo...
- 12:02 PM CephFS Bug #5418: kceph: crash in remove_session_caps
- kdb dumpall attached
- 12:02 PM CephFS Bug #5418 (Resolved): kceph: crash in remove_session_caps
- ...
- 11:33 AM rgw Feature #5417 (Resolved): rgw: separate bucket metadata object into pointer object and instance o...
- Instead of having a single bucket metadata object, we'll separate into a bucket 'head' object that will point at the ...
- 11:07 AM rgw Bug #5416: --help output needs --rgw-zone option
- For the ./radosgw-admin command that is.
- 11:07 AM rgw Bug #5416 (Resolved): --help output needs --rgw-zone option
- The new --rgw-zone option needs to be added to the --help output.
- 10:30 AM rgw Bug #5415 (Resolved): rgw: failing valgrind leak checks
- teuthology-2013-06-21_01:00:44-rgw-master-testing-basic/41708 and 41709
- 10:13 AM rgw Feature #5356 (Rejected): rgw: RESTful api for bucket upstream zone + marker info
- As with #5353, we're not doing it at the moment, not clear if we really need it.
- 10:10 AM rgw Feature #5355 (Rejected): rgw: get and set bucket upstream zone + marker info
- We're not doing it atm. Discussed it with Greg, and we think that the replica log already covers this info, so there'...
- 09:36 AM Bug #5413 (Resolved): osd: valgrind issue in watch code (cuttlefish?)
- commit:17d2745f095e7bb640dece611d7824d370ea3b81
- 08:17 AM Bug #5413 (Resolved): osd: valgrind issue in watch code (cuttlefish?)
- teuthology-2013-06-20_20:00:11-rados-cuttlefish-testing-basic/41401...
- 09:25 AM rbd Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- These packages have not been through QA yet.
- 09:13 AM rbd Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- Great, thanks Gary. Have these been QAd?
- 04:57 AM Revision 24e59b43 (ceph): rgw: buffer atomic put handler
- Since we tied the atomic put handler to libcurl output
data, which uses much smaller chunks, we need to buffer
data, ... - 04:57 AM Revision 02de43ad (ceph): rgw: tie opstate into intra-region copy operations
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
06/20/2013
- 11:13 PM Bug #5301: mon: leveldb crash in tcmalloc
- Maciej Galkiewicz wrote:
> debian wheezy (7.0)
ok now it sounds a lot like #5239. i'm not able to reproduce this... - 11:04 PM Revision b7763af4 (ceph): big: enable big cluster (~50 node)
- 11:01 PM Feature #3273 (Need More Info): mon: simple dm-crypt key management
- http://marc.info/?l=ceph-devel&m=137179443405614&w=2
- 10:55 PM Revision e97a2c86 (ceph): Merge remote-tracking branch 'yan/wip-mds' into wip-mds
- 10:40 PM rbd Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- Following the packaging discussions, the redhat packages were respun with the latest redhat sources + the ceph rados ...
- 10:14 PM Revision 69e1a912 (ceph): ceph.in: fix ^C handling in watch (trap exception in while, too)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:14 PM Revision 31d221c3 (ceph): ceph.in: remove some TAB chars
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:04 PM Revision 29f6f277 (ceph): ceph: --version as well as -v
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:51 PM rgw Feature #4340 (In Progress): rgw: dr: data sync agent: implement full sync
- 09:51 PM rgw Feature #5358 (In Progress): rgw: RESTful api for intra-region copy state
- 09:50 PM rgw Feature #5356 (In Progress): rgw: RESTful api for bucket upstream zone + marker info
- 09:50 PM rgw Feature #5341 (Fix Under Review): rgw: keep state for cross-rgw copy operations
- 09:42 PM Revision 234fab09 (ceph): Merge branch 'wip-rgw-geo-enovance' into wip-rgw-geo-2
- 09:41 PM Revision 6d6dc42e (ceph): fixup "radosgw-admin: new commands to look at and clean up replica logs"
- 09:33 PM CephFS Fix #5399: timestamp changes on replayed mds request (pjd link 71)
- probably need to extend the replayed request message to include the timestamps we got for the inode and dir so that t...
- 09:33 PM CephFS Fix #5399: timestamp changes on replayed mds request (pjd link 71)
- - we send a create to mds
- get an ack, but it isn't journaled
- pjd stats the mtime/ctime/ec.
- mds restarts
- w... - 09:12 PM CephFS Bug #5290: mds: crash whilst trying to reconnect
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-06-20_13:32:57-fs-master-testing-basic/41231
logs in ... - 09:10 PM Revision e4ef5c6f (ceph): cls_replica_log: add the actual class
- This class can be applied to any object, and will keep track of
the bounds, matching times, and matching sets of in-p... - 09:10 PM Revision 29df88af (ceph): cls_replica_log: add client with user documentation
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:10 PM Revision 36514731 (ceph): cls_replica_log: add tests.
- We do several good updates, a bad update, a good delete,
a bad delete, several good gets, and a bad get.
Signed-off-... - 09:10 PM Revision ab79ba46 (ceph): cls_replica_log: integrate with RGWRados
- We introduce an implementation class RGWReplicaLogger, and two user
classes RGWReplicaObjectLogger (for the data/meta... - 09:10 PM Revision 59bfdd00 (ceph): radosgw-admin: new commands to look at and clean up replica logs
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:10 PM Revision 22a02e95 (ceph): cls_replica_log: add ops for new class
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:10 PM Revision d1c95943 (ceph): cls_replica_log: add types for new class
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:42 PM Revision 70b54671 (ceph): Clean up nested-if logic
- 08:38 PM Revision 0deb6d40 (ceph): rgw: lock related modifications
- 1. zone-id inclusion in lock/unlock for mdlog and datalog
2. renewal of lock if the locker request lock again
3. modi... - 08:32 PM Revision 3b4c11b2 (ceph): rgw: add max-entries, marker for log operations
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
Conflicts:
src/rgw/rgw_admin.cc
src/rgw/rgw_rest_log.cc - 07:30 PM Revision 4bf5b732 (ceph): Merge remote-tracking branch 'gh/next'
- 07:26 PM Revision 714f2128 (ceph): osdc: re-calculate truncate_size for strip objects
- Feed truncate_size through the striping algorithm so that it reflects the
correct per-object offset (as opposed to th... - 07:19 PM Revision ebb46c45 (ceph): qa/workunits/misc/multiple_rsync.sh: wtf
- 2013-06-15T12:55:29.808 INFO:teuthology.task.workunit.client.0.err:+ rsync -auv --exclude local/ /usr/ usr.1
2013-06-... - 06:45 PM CephFS Bug #5333 (Fix Under Review): mds: segfault in MDLog::standby_trim_segments
- wip-5333
this looks like a simple matter of not crashing if the segment list is empty. that at least covers this ... - 12:53 PM CephFS Bug #5333: mds: segfault in MDLog::standby_trim_segments
- Just a note: maybe we missed a spot, but I remember doing a re-read head object, retry journal read whenever we get a...
- 12:47 PM CephFS Bug #5333: mds: segfault in MDLog::standby_trim_segments
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-06-20_01:00:49-fs-next-testing-basic/40965
with ful... - 06:30 PM Revision ffdb7236 (ceph): mon: more fix dout use in sync_requester_abort()
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d60534b8f59798feaeeaa17adba2a417d7777cbf) - 06:29 PM Revision 38ddae04 (ceph): mon: fix raw use of *_dout in sync_requester_abort()
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 8a4ed58e39b287fd8667c62b45848487515bdc80) - 06:28 PM Revision fd769c0f (ceph): qa/workunits/cephtool/test.sh: fix and cleanup several tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:23 PM Revision f420e5c6 (ceph): mon: drop deprecated 'stop_cluster'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:23 PM Revision 4977b88a (ceph): mds: make 'mds compat rm_*compat' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:15 PM CephFS Bug #5380 (Resolved): osdc/Filer.cc: 163: FAILED assert(probe->known_size[p->oid] <= shouldbe)
- 12:30 PM CephFS Bug #5380: osdc/Filer.cc: 163: FAILED assert(probe->known_size[p->oid] <= shouldbe)
- 06:11 PM Revision 4a038d6d (ceph): mon: make 'log ...' command wait for commit before reply
- Previously we would just dump the command argument to our local log client
and reply immediately, which could lose th... - 06:09 PM Revision 483aa74f (ceph): test: update cli test
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:09 PM Revision 008bdc5e (ceph): radosgw_admin: fixup cli test
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 06:04 PM Revision 7b5ec743 (ceph): cls_rgw: skip namespaced entries when listing bucket
- We added a namespace to the entries, and sadly there can be
valid entries beyond it. Previously we assumed that once ... - 06:04 PM Revision 5de54f6a (ceph): a/workunits/cephtool/test.sh: --no-log-to-stderr when examining stderr
- We can get random messages to stderror from socket reconnects and such;
discard those if we are looking at stderr in ... - 05:42 PM Bug #5412 (Resolved): doc bug: incorrect reference to monitor quorum requirements
- http://ceph.com/docs/master/rados/deployment/ceph-deploy-mon/...
- 04:46 PM Revision d60534b8 (ceph): mon: more fix dout use in sync_requester_abort()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:36 PM Revision 8a4ed58e (ceph): mon: fix raw use of *_dout in sync_requester_abort()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:08 PM Revision c8af85d4 (ceph): doc/release-notes: v0.61.4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:56 PM Bug #4004 (Can't reproduce): Intermittent kernel build failures
- 02:52 PM Bug #4004: Intermittent kernel build failures
- Closing since we haven't seen any problems for a couple months.
- 02:55 PM devops Cleanup #5106 (Resolved): ceph_deploy: install/compile error on wheezy
- The was happening do to syntax in the test programs that wasn't supported on Python 2.6. Not shipping the test direc...
- 02:51 PM Bug #2176 (Resolved): dependencies not checked by autoconf
- We've got all the current dependencies in the configure.ac checks and in the rpm or debian requirements.
- 02:42 PM CephFS Bug #5411 (Resolved): teuthology: bad object dereference
- ...
- 01:30 PM CephFS Fix #5268: mds: fix/clean up file size/mtime recovery code
- See also #4485.
- 01:30 PM CephFS Feature #4485: Improve "needsrecover" handling
- See also #5268.
- 01:24 PM CephFS Feature #1693 (In Progress): libcephfs: Support TRIM (hole punching)
- See "[PATCH] Ceph-fuse: Punch hole support" from Li Wang.
- 01:17 PM CephFS Feature #3541 (In Progress): mds: robust ino lookup using file backpointers
- A bunch of this got done, but Sage isn't sure if the client -> LOOKUPINO messages are wired up to that infrastructure...
- 12:58 PM Feature #4929: Erasure encoded placement group
- the pad is only archived for so long, keep a "pad backup":http://pad.ceph.com/p/Erasure_encoding_as_a_storage_backend...
- 11:31 AM Bug #5409 (Resolved): mon: log command does not wait for commit
- 10:43 AM Bug #5409 (Resolved): mon: log command does not wait for commit
- the mon replies immediately, and may lose the msg if it restarts....
- 10:35 AM rgw Feature #5408 (Resolved): rgw: turn off dr/geo logging
- 10:26 AM Bug #5407 (Resolved): mon: is_writeable doesn't match wait_for_writeable on cuttlefish
- fixes in master.. need a minimal cuttlefish backport.
- 09:58 AM rgw Feature #5406 (Resolved): rgw: a RESTful api to dump region map
- 09:42 AM devops Bug #5405 (Resolved): ceph-deploy: transient pushy exception on install
- ...
- 08:37 AM devops Feature #5403 (Resolved): make ceph.com repos mirrorable
- 08:01 AM Fix #5388: osd: localized reads (from replicas) reordered wrt writes
- Since disabling localized reads I've not seen the problem occur, so thanks :)
- 07:32 AM Bug #5401: cuttlefish osd recovery slow
- Full backtrace (while recovering):
http://pastebin.com/raw.php?i=DWGHiNP6
2nd full backtrace:
http://pastebin.co... - 07:18 AM Bug #5401: cuttlefish osd recovery slow
- Not sure if this helps:
# /etc/init.d/ceph stop osd.24; sleep 15; /etc/init.d/ceph start osd.24; sleep 10; inotif... - 06:59 AM Bug #5401: cuttlefish osd recovery slow
- Some more information. While recoverig i see nearly no CPU load. If i look at the disk activity i see a HUGE amount o...
- 06:53 AM Bug #5401: cuttlefish osd recovery slow
- Lowering osd recovery max active makes it even more worth as the over all recovery takes longer. So it's not the I/O ...
- 01:01 AM Bug #5401 (Can't reproduce): cuttlefish osd recovery slow
- While the peering is fine now (Bug #5232) (latest upstream/cuttlefish) even without wip_cuttlefish_compact_on_startup...
- 06:59 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- Thanks.
- 06:56 AM Bug #5292 (Resolved): mon: monitor crashing due to not being in the monmap (no monmap to be in)
- You hit #5205 -- not the same issue, thus closing this ticket again.
- 06:48 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- Here you go. Please let me know if you need anything else.
Jeff - 06:42 AM Bug #5292 (Need More Info): mon: monitor crashing due to not being in the monmap (no monmap to be...
- Okay, can you post the monitor's logs with 'debug mon = 20' ?
- 02:46 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- I did a reboot, just to make sure :-(
# ceph -v
ceph version 0.61.4 (1669132fcfc27d0c0b5e5bb93ade59d147e23404)
... - 06:48 AM rgw Bug #5402 (Resolved): rgw compilation problem on wip-rgw-geo-2 branch
- The wip-rgw-geo-2 branch does not compile from a2cf14fe27a2da54e44b12a373b15b29c89d31b9.
In fact the method encode... - 03:02 AM Revision 1fccfd8b (ceph): Merge pull request #367 from ceph/wip-ceph-cli
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
- 02:54 AM Revision 84444d0b (ceph): Merge remote-tracking branch 'upstream/next'
- 02:53 AM Revision c39b99cd (ceph): FileStore: handle observers in constructor/destructor
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 02:44 AM Revision 02115830 (ceph): init-radosgw: use radosgw --show-config-value to get config values
- This way we get the correct default values, as reflected by radosgw
itself.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:44 AM Revision 716fc350 (ceph): ceph-conf: make --show-config-value reflect daemon defaults
- We want DAEMON defaults, but we don't want global_init to do anything else
daemonish like print a banner or mkdir /va... - 02:44 AM Revision 88f73c5a (ceph): ceph: fix ceph-conf call to get admin socket path for 'daemon <name> ...'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:15 AM Revision cf3bc251 (ceph): FileStore: apply changes after disabling m_filestore_replica_fadvise
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from co... - 02:14 AM Revision ed8b0e65 (ceph): FileStore: apply changes after disabling m_filestore_replica_fadvise
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 12:58 AM Revision 2a4953b6 (ceph): ceph-disk: use unix lock instead of lockfile class
- The lockfile class relies on file system trickery to get safe mutual
exclusion. However, the unix syscalls do this f... - 12:55 AM Revision cb6bc95a (ceph): Merge remote-tracking branch 'gh/next'
- 12:06 AM Fix #5232: osd: slow peering due to pg log rewrites
- I'm fridudad ;-) Peering works fine but recovery does not. In my initial text of this tracker i also mentioned recove...
06/19/2013
- 11:14 PM Subtask #5213 (Resolved): unit tests for src/osd/PGLog.{cc,h}
- 11:11 PM Revision 8c0daafe (ceph): ceph-disk: make list_partition behave with unusual device names
- When you get device names like sdaa you do not want to mistakenly conclude that
sdaa is a partition of sda. Use /sys... - 10:59 PM Revision c830b704 (ceph): Merge pull request #364 from dachary/wip-5213
- unit tests for PGLog::proc_replica_log
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:57 PM Revision 90564025 (ceph): Merge pull request #366 from dachary/wip-5398
- PGLog::rewind_divergent_log must not call mark_dirty_from on end()
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:48 PM CephFS Bug #5289: mds closing stale session
- Sage Weil wrote:
> this is caused when teh client is not talknig to the mds. can you verify the network is working, ... - 10:24 PM Revision 8a5d989c (ceph): FileStore: get_index prior to taking fdcache_lock in lfn_unlink
- We take the fdcache_lock while holding onto index objects
elsewhere in the code.
Fixes: #5389
Reviewed-by: David Zaf... - 10:16 PM Revision bb2cd9e3 (ceph): task/: add args.py
- The usage doc string for a task is tedious to write and
hard to keep reconciled with the code as defaults are changed... - 10:16 PM Revision 3d9fa225 (ceph): task/peering_speed_test.py: add test which summarizes pg peering speed
- Running this regularly may warn us about slow peering.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:51 PM Revision 1669132f (ceph): v0.61.4
- 08:50 PM Revision 09e869a4 (ceph): PGLog::rewind_divergent_log must not call mark_dirty_from on end()
- PGLog::rewind_divergent_log is dereferencing iterator "p" though it is
already past the end of its container. When en... - 08:35 PM Revision 02aa7d99 (ceph): schedule_suite.sh: specify admin_socket branch in overrides yaml
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:08 PM CephFS Bug #5380: osdc/Filer.cc: 163: FAILED assert(probe->known_size[p->oid] <= shouldbe)
- The patch only fixes the root cause. It doesn't help if objects already have wrong size.
- 07:39 PM Revision b76540f6 (ceph): messages/MOSDMarkMeDown: fix uninit field
- Fixes valgrind warning:
==14803== Use of uninitialised value of size 8
==14803== at 0x12E7614: sctp_crc32c_sb8_64_... - 06:52 PM Revision e11cc1c8 (ceph): add constness to PGLog::proc_replica_log
- The function is made const by replacing a single call to log.objects[]
with log.objects.find. The olog argument is al... - 06:52 PM Revision 4d77443d (ceph): unit tests for PGLog::proc_replica_log
- The tests covers 100% of the LOC of proc_replica_log. It is broken down
in 7 cases to enumerate all the situations it... - 06:33 PM Revision 02b3c552 (ceph): Merge pull request #342 from ceph/wip-mon
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:29 PM Revision a93b4679 (ceph): Include MySQLdb
- Fixes: #5120
- 06:27 PM Revision a9e9c58f (ceph): mon/MonmapMonitor: remove some dead code
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision 3aa61a0b (ceph): mon/PaxosService: simplify readable check
- Recast this in terms of the paxos check and our additional conditions,
which match wait_for_readable().
Signed-off-b... - 06:27 PM Revision f985de28 (ceph): mon/PaxosService: simplify is_writeable
- Recast this in terms of paxos check + our conditions, and make it
match wait_for_writeable().
Signed-off-by: Sage We... - 06:27 PM Revision 7b7ea8e3 (ceph): mon/Paxos: cleanup: drop unused PREPARING state bit
- This is never set when we block, and nobody looks at it.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:27 PM Revision ec2ea86e (ceph): mon/Paxos: not readable when LOCKED
- If we are re-proposing a previously accepted value from a previous quorum,
we should not consider it readable, becaus... - 06:27 PM Revision ee34a219 (ceph): mon: simplify states
- - make states mutually exclusive (an enum)
- rename locked -> updating_previous
- set state prior to begin() to simpl... - 06:27 PM Revision 392a8e21 (ceph): mon/PaxosService: not active during paxos UPDATING_PREVIOUS
- Treat this as an extension of the recovery process, e.g.
RECOVERING -> ACTIVE
or
RECOVERING -> UPDATING_PREVIOUS -... - 06:27 PM Revision a42d7582 (ceph): mon/Paxos: do paxos refresh in finish_proposal; and refactor
- Do the paxos refresh inside finish_proposal, ordered *after* the leader
assertion so that MonmapMonitor::update_from_... - 06:27 PM Revision dc834301 (ceph): mon: safely signal bootstrap from MonmapMonitor::update_from_paxos()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision e68b1bd3 (ceph): mon/Paxos: go active *after* refreshing
- The update_from_paxos() methods occasionally like to trigger new activity.
As long as they check is_readable() and is... - 06:27 PM Revision e832e76a (ceph): mon: simplify Monitor::init_paxos()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision 439e7996 (ceph): mon: debug proposal timers
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision e5658023 (ceph): mon: fix whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision 7229da8a (ceph): mon/MonmapMonitor: fix typo in check to remove mkfs info
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:27 PM Revision cc339c07 (ceph): mon: explicitly refresh_from_paxos() when leveldb state changes
- Instead of opportunistically calling each service's update_from_paxos(),
instead explicitly refresh all in-memory sta... - 06:27 PM Revision 03014a4e (ceph): mon: remove unnecessary update_from_paxos calls
- The refresh() will do this when the state changes; no need to
opportunistically call this method all of the time.
Si... - 06:27 PM Revision d941363d (ceph): mon: no need to refresh from _active
- The refresh is done explicitly by the monitor, independent of the more
fragile PaxosService callbacks.
Signed-off-by... - 06:27 PM Revision 2fccb300 (ceph): mon/PaxosService: cache {first,last}_committed
- Refresh the in-memory values when we are told the on-disk paxos state
may have changed.
Signed-off-by: Joao Eduardo ... - 06:12 PM Revision 778d930d (ceph): Fix to ignore ssh-key checking if running on virtual machines or
- if a line that reads 'sshkey: ignore' is in the yaml file.
Fix #5364
Signed-off-by: Warren Usui <warren.usui@inktank... - 06:12 PM Revision 14417072 (ceph): Make reset of ssh key code conditional on being a virtual machine.
- Add and use is_vm to determine if we are running on a virtual machine.
Fix #5364
Signed-off-by: Warren Usui <warren.... - 06:06 PM rbd Bug #5222 (Resolved): krbd: use per-rbd_dev mutex to protect header updates
- 06:06 PM rbd Bug #3925 (Resolved): krbd: sysfs write lockdep warnings
- 06:04 PM Bug #5398 (Resolved): PGLog::rewind_divergent_log dereferencing iterator "p" past the end of its ...
- 01:58 PM Bug #5398 (Fix Under Review): PGLog::rewind_divergent_log dereferencing iterator "p" past the end...
- "pull request":https://github.com/ceph/ceph/pull/366
- 12:59 PM Bug #5398 (Resolved): PGLog::rewind_divergent_log dereferencing iterator "p" past the end of its ...
- 06:03 PM devops Bug #5161 (Resolved): daemons should create /var/run/ceph if it doesn't already exist
- 06:02 PM Bug #5227 (Can't reproduce): ARM set up: rados test failed
- 07:45 AM Bug #5227: ARM set up: rados test failed
- Been trying to reproduce this on the talas but no joy so far. Still hammering cuttlefish.
- 06:00 PM devops Bug #5387 (Resolved): ceph-disk: lockfile does not detect stale locks (dead parent process)
- 06:00 PM devops Bug #5390 (Pending Backport): ceph-deploy osd create hangs
- 05:28 PM devops Bug #5390: ceph-deploy osd create hangs
- bah, trivial fcntl(2) is all we need here.
- 05:57 PM Revision de8900dc (ceph): os/FileStore: use fdatasync(2) instead of sync_file_range(2)
- This fixes data corruption on XFS. Backported from
ffade3c85dfffa13a16edd9630a52d99eb8a413d.
Fixes: #4976
Signed-of... - 05:57 PM Revision 95bd0480 (ceph): os/FileStore: disable fadvise on XFS
- fadvise(DONTNEED) on XFS can break writeback ordering and zeroing; see
http://oss.sgi.com/archives/xfs/2013-06... - 05:56 PM Revision 2434ecca (ceph): Merge remote-tracking branch 'gh/wip-4976-cuttlefish' into cuttlefish
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:50 PM Revision fd83bc3f (ceph): client: fix warning
- client/Client.cc: In member function 'int Client::_read_sync(Fh*, uint64_t, uint64_t, ceph::bufferlist*)':
warning: c... - 05:45 PM Revision b2f1a1ad (ceph): mds: fix remote wrlock rejoin
- remote wrlock's target is not always inode's auth MDS.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:45 PM Revision 15a5d37a (ceph): mds: fix race between scatter gather and dirfrag export
- If we gather dirty scatter lock state while corresponding dirfrag
is been exporting, we may receive different dirfrag... - 05:37 PM Revision 35f0478e (ceph): use correct branch for admin_socket tests
- 05:36 PM Revision 3649e277 (ceph): admin_socket: fetch test from correct branch
- 05:00 PM rgw Feature #4335 (Fix Under Review): rgw: dr: sync processing state: define datastructures
- We're well beyond "defining" the data structures at this point; there's code and it's undergoing review. But this is ...
- 04:58 PM Revision 1a3f0b3c (ceph): Merge branch 'next'
- 04:58 PM Revision ded0a5f4 (ceph): Revert "client: fix warning"
- This reverts commit 4a3127f48d75121745f81d1aba723cb7f867f790.
Wrong branch. - 04:12 PM devops Bug #5211 (Pending Backport): ceph-disk prepare: list_partitions() shouldn't return disks
- 09:25 AM devops Bug #5211 (Fix Under Review): ceph-disk prepare: list_partitions() shouldn't return disks
- pusehd to wip-ceph-disk
- 04:08 PM Revision 4455f75d (ceph): valgrind: give up and ignore all leveldb leaks
- Hopefully if it is our fault we will have our own struct wrapping the
leveldb resource that we leak. - 04:02 PM CephFS Fix #5399 (New): timestamp changes on replayed mds request (pjd link 71)
- Hmm, Sage points out this might be something else; reopening.
- 03:56 PM CephFS Fix #5399 (Rejected): timestamp changes on replayed mds request (pjd link 71)
- It's a time stamp check for things going backwards, and is failing due to out-of-sync clocks (over a network) being h...
- 03:44 PM CephFS Fix #5399 (Resolved): timestamp changes on replayed mds request (pjd link 71)
- teuthology-2013-06-19_10:46:59-fs-cuttlefish-master-basic 40138 40141
- 03:50 PM Fix #5232: osd: slow peering due to pg log rewrites
- This won't get backported. Some mitigating patches did go into cuttlefish. Also, there is wip_cuttlefish_compact_on...
- 03:45 PM Fix #5232 (Resolved): osd: slow peering due to pg log rewrites
- 03:44 PM RADOS Tasks #5243: osd testing: create peering speed test
- peering_speed_test.py, still needs to be added to ceph-qa-suite somewhere appropriate.
- 03:43 PM Fix #5278: osd: smarter recovery for small objects
- wip-small-object-recovery, in progress
- 03:26 PM Bug #5389 (Resolved): osd: op_tp timeout on big cluster + radosmodel
- 03:11 PM Bug #5389: osd: op_tp timeout on big cluster + radosmodel
- lfn_unfound
- 03:21 PM devops Bug #5306: Xen based OSDs fail to start ceph-osd process
- Here's the output of udevadm test
~ sudo udevadm test --action=add /sys/devices/vbd-51728/block/xvdb/xvdb1
run_c... - 03:04 PM devops Bug #5306: Xen based OSDs fail to start ceph-osd process
- OK, I updated using ceph-deploy to all my nodes to this version:
ceph version 0.61.3-29-g08304a7 (08304a7c46da7517... - 11:43 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I'm still using the cluster with the modified ceph-mds program, it still works. I caused another power outage (this i...
- 11:25 AM rgw Bug #5346: rgw: invalid read from RGWFormatter_Plain::write_data
- well, swift is the only user of the plain formatter I guess.
- 11:14 AM rgw Bug #5346: rgw: invalid read from RGWFormatter_Plain::write_data
- this appears to be triggered by the swift test.. doesn't happen with s3tests or readwrite etc
also present on cutt... - 11:15 AM Bug #4976 (Resolved): osd powercycle triggers object corruption on xfs
- 09:09 AM Bug #4976: osd powercycle triggers object corruption on xfs
- What do you mean "remove fadvise"? And is this a known upstream issue?
- 10:37 AM rbd Documentation #3220 (Resolved): doc: more detail on QEMU+RBD page
- http://ceph.com/docs/master/rbd/qemu-rbd/
- 09:56 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- It was backported to the branch that should soon become 0.61.4. Until then, you'll be able to find it on the gitbuil...
- 08:36 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- I just tried apt-get update and it didn't pull down any cuttlefish updates. Have they been released? Do I need to d...
- 07:43 AM Bug #5292 (Resolved): mon: monitor crashing due to not being in the monmap (no monmap to be in)
- Fix for this went into next and cuttlefish branches as of last night; see #5256.
- 08:59 AM devops Feature #5397 (New): terminate ceph-create-keys when its mon process dies
- Right now, it's easy to build up a bunch of ceph-create-keys processes on a node because it is started when the monit...
- 08:38 AM Bug #5375 (Resolved): squeeze tcmalloc leaks
- i'll send a note to the email list. thanks for tracking this down!
- 06:03 AM Revision 96c9493d (ceph): radosgw-admin: interface to control ops state
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:02 AM Revision 8b1524be (ceph): rgw: OpState internal api
- Add new higher level functions to set, renew, list, and remove
logged operation state.
Signed-off-by: Yehuda Sadeh <... - 06:01 AM Revision 258edfca (ceph): rgw: fix check_state call
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:03 AM Revision f8973bda (ceph): common/Preforker: fix warning
- common/Preforker.h: In member function ‘int Preforker::signal_exit(int)’:
warning: common/Preforker.h:82:45: ignoring... - 05:01 AM Revision 6427985b (ceph): mon: Monitor: make sure we backup a monmap during sync start
- First of all, we must find a monmap to backup. The newest version.
Secondly, we must make sure we back it up before... - 05:01 AM Revision f8f83e78 (ceph): mon: Monitor: obtain latest monmap on sync store init
- Always use the highest version amongst all the typically available
monmaps: whatever we have in memory, whatever we h... - 05:00 AM Revision 41e1a6be (ceph): mon: Monitor: don't remove 'mon_sync' when clearing the store during abort
- Otherwise, we will end up losing the monmap we backed up when we started
the sync, and the monitor may be unable to s... - 04:58 AM Revision 5e6dc4ea (ceph): mon: Monitor: make sure we backup a monmap during sync start
- First of all, we must find a monmap to backup. The newest version.
Secondly, we must make sure we back it up before... - 04:58 AM Revision 6284fdce (ceph): mon: Monitor: obtain latest monmap on sync store init
- Always use the highest version amongst all the typically available
monmaps: whatever we have in memory, whatever we h... - 04:56 AM Revision af5a9861 (ceph): mon: Monitor: don't remove 'mon_sync' when clearing the store during abort
- Otherwise, we will end up losing the monmap we backed up when we started
the sync, and the monitor may be unable to s... - 04:31 AM Revision 3f32ded4 (ceph): os/FileStore: drop posix_fadvise(...DONTNEED)
- On XFS this call is problematic because it directly calls the filemap
writeback without vectoring through xfs. This ... - 04:24 AM Revision ffade3c8 (ceph): os/FileStore: use fdatasync(2) instead of sync_file_range(2)
- The use of sync_file_range(2) on XFS screws up XFS' delicate ordering
of writeback and range zeroing; see #4976 and t... - 03:55 AM Revision baa1c86e (ceph): Merge remote-tracking branch 'upstream/wip-log-rewrite-sam'
- Fixes: #5232
Reviewed-by: Sage Weil <sage@inktank.com> - 03:45 AM Revision d628109f (ceph): rgw: specialized obj zone copy state for statelog
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 03:07 AM Revision 13e03021 (ceph): rgw: internal api for statelog objclass
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:55 AM Revision 3383ba63 (ceph): config: fix run_dir typo
- From 654299108bfb11e7dce45f54946d1505f71d2de8.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commi...
06/18/2013
- 11:38 PM Bug #5375: squeeze tcmalloc leaks
- OK this def. fixes it for me. So the squeeze perftool package seems to have a memory leak.
- 12:39 PM Bug #5375: squeeze tcmalloc leaks
- 12:17 PM Bug #5375: squeeze tcmalloc leaks
- OK backported: google-perftools from wheezy to squeeze, recompiled leveldb and ceph to reflect new google-perftools v...
- 11:18 AM Bug #5375: squeeze tcmalloc leaks
- yeah, try wheezy. they won't update squeeze at this point anyway.
- 11:17 AM Bug #5375: squeeze tcmalloc leaks
- The Debian Maintainer is: Daigo Moriwaki <daigo at debian.org>
Should i first try to use the one from wheezy on sq... - 11:14 AM Bug #5375: squeeze tcmalloc leaks
- Hmm, looks like maybe we need to send a bug to upstream (Debian and/or libgoogle-perftools devs).
Sage, any ideas ... - 11:02 AM Bug #5375: squeeze tcmalloc leaks
- no change. Should i update my tcmalloc on debian squeeze?
[: ~]# pmap -x 11783|tail -n1
total kB 176290... - 10:56 AM Bug #5375: squeeze tcmalloc leaks
- Yes. In particular the "heap release" bit is trying to more aggressively give memory back to the OS. We've observed i...
- 10:48 AM Bug #5375: squeeze tcmalloc leaks
- not should be now
- 10:48 AM Bug #5375: squeeze tcmalloc leaks
- not it's using 1GB should i run these commands again?
- 11:28 PM Revision 0b932bfd (ceph): cls_statelog: pass in timestamp
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:57 PM rgw Feature #4335 (In Progress): rgw: dr: sync processing state: define datastructures
- 10:57 PM rgw Feature #4338 (In Progress): rgw: multisite: metadata sync agent: implement delta changes sync
- 10:56 PM rgw Feature #5341 (In Progress): rgw: keep state for cross-rgw copy operations
- 10:56 PM rgw Bug #5357 (Fix Under Review): rgw: set and retrieve intra-region copy operation state
- 10:44 PM Revision 25749033 (ceph): AuthMonitor: auth export's status message to ss, not ds
- This puts it on stderr, not stdout
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 10:33 PM devops Bug #5390: ceph-deploy osd create hangs
- starting with the mercurial lock implementation, which uses a pid. see wip-ceph-disk-lock, tho still incomplete.
- 08:45 AM devops Bug #5390 (Fix Under Review): ceph-deploy osd create hangs
- care to review teh top patch in wip-ceph-disk?
alternatively, do you know of a replacement for lockfile that will ... - 08:38 AM devops Bug #5390 (In Progress): ceph-deploy osd create hangs
- see also #5387. and i'll add the sigint handler to reduce the probability of this happening!
- 07:36 AM devops Bug #5390 (Resolved): ceph-deploy osd create hangs
- On Ubuntu 13.04 with ceph 0.61.3 .
It hangs when creating a new osd using ceph-deploy.
ceph@ceph-node4:~/mycluste... - 10:24 PM Fix #5279 (In Progress): pipeline large object recovery
- 10:24 PM Feature #4200 (In Progress): mon: break pgmap into separate leveldb keys
- 10:14 PM Revision 75b6c829 (ceph): doc: Fixed OpenStack Keystone instruction.
- fixes: #5178
- 10:14 PM Revision cba4de11 (ceph): cls_statelog: improve unitest
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:13 PM Revision b89f47c8 (ceph): cls_statelog: fix a few issues
- Issues that came up when developed the unitest
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:08 PM Bug #5256 (Resolved): Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- 09:51 PM Revision 41e1416c (ceph): ceph.spec: create /var/run on package install
- The %ghost %dir ... line will make this get cleaned up but won't install
it.
Reported-by: Derek Yarnell <derek@umiac... - 09:51 PM Revision 64ee0148 (ceph): ceph.spec: create /var/run on package install
- The %ghost %dir ... line will make this get cleaned up but won't install
it.
Reported-by: Derek Yarnell <derek@umiac... - 09:45 PM Bug #4976 (Fix Under Review): osd powercycle triggers object corruption on xfs
- the problem is that sync_file_range(2) and posix_fadvaise(..DONTNEED) break xfs's internal write and zero ordering. ...
- 09:28 PM Revision 2df36191 (ceph): global: create /var/run/ceph on daemon startup
- This handles cases where the daemon is started without the benefit of
sysvinit or upstart (as with teuthology or ceph... - 09:27 PM Revision c819dcc2 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 09:26 PM Revision 97f1322c (ceph): doc: Updated deployment preflight.
- fixes: #5266
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 09:23 PM Revision bb799e69 (ceph): test_rados.py: add some tests for mon_command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:22 PM Revision 64b4e4a6 (ceph): rados.py: wrap target in c_char_p()
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:22 PM Revision 54f74325 (ceph): rados.py: return error strings even if ret != 0
- Key rados_free() off returned length, not ret
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil ... - 09:22 PM Revision 81e73c7a (ceph): ceph.in: pass parsed conffile to Rados constructor
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:22 PM Revision 2fc8d864 (ceph): ceph.in: global var dontsplit should be capitalized
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:19 PM Bug #5372 (Duplicate): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- I think this is caused by the same thing as 5269.
- 09:18 PM Revision 38a595ba (ceph): FileStore: optionally compact leveldb on mount
- Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:18 PM Bug #5320 (Resolved): osd/ReplicatedPG.cc: 4753: FAILED assert(!pg_log.get_missing().is_missing(s...
- 09:09 PM Revision 4a3127f4 (ceph): client: fix warning
- signed/unsigned comparison
Signed-off-by: Sage Weil <sage@inktank.com> - 09:00 PM Fix #5388: osd: localized reads (from replicas) reordered wrt writes
- ...
- 10:21 AM Fix #5388: osd: localized reads (from replicas) reordered wrt writes
- 09:33 AM Fix #5388: osd: localized reads (from replicas) reordered wrt writes
- I've just reproduced it with those log levels.
There was 1 master, 1 regionserver.
So I think the writing and readi... - 08:04 AM Fix #5388 (Need More Info): osd: localized reads (from replicas) reordered wrt writes
- Hi Mike,
I gather that the same data was just written by a different node in the cluster? And this is right near/... - 03:40 AM Fix #5388 (New): osd: localized reads (from replicas) reordered wrt writes
- I'm using hbase, with the hadoop-cephfs bindings, on top of a ceph 0.61 cluster.
I'm seeing instances where reading ... - 08:37 PM Bug #5395 (Can't reproduce): arm: osd: big performance differential between read/write
- -- arm --
Raw /dev/rbd device
$ sudo dd if=/dev/zero of=/dev/rbd1 bs=4M count=128 conv=fdatasync
128+0 record... - 08:20 PM Revision efcf6265 (ceph): FileStore::lfn_open: don't call get_index under fdcache_lock
- lfn_open() is called with indexes locked, so we cannot lock
and index under fdcache_lock.
Fixes: #5389
Signed-off-by... - 07:33 PM Revision eace9987 (ceph): PG: don't dirty log unconditionally in activate()
- merge_log and friends all take care of dirtying the log
as necessary.
Fixes: #5238
Signed-off-by: Samuel Just <sam.j... - 06:28 PM Revision bfe4bf9d (ceph): rgw: handle racing default region creation
- If region is not specified and there's no default region set
we try to create a default region. However, we may race ... - 05:43 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- I tried wip_cuttlefish_compact_on_startup today. First, I upgraded one box to 0.61.3-47-g47f1bed-1precise.
Then, w... - 05:26 PM Revision fda618e9 (ceph): mon: OSDMonitor: don't ignore apply_incremental()'s return on UfP [1]
- apply_incremental() may return -EINVAL. Don't ignore it.
[1] UfP = Update from Paxos
Fixes: #5343
Signed-off-by: ... - 05:03 PM Revision ce7b5ea7 (ceph): common/Preforker: fix warning
- common/Preforker.h: In member function ‘int Preforker::signal_exit(int)’:
warning: common/Preforker.h:82:45: ignoring... - 05:02 PM devops Bug #5266 (Closed): the apt-get install instructions are missing an update
- Verified fixes, thanks.
- 02:32 PM devops Bug #5266 (Resolved): the apt-get install instructions are missing an update
- See:
http://ceph.com/docs/master/start/quick-start-preflight/#install-ceph-deploy
http://ceph.com/docs/master/rado... - 05:02 PM Revision 8bd936f0 (ceph): client: fix warning
- client/Client.cc: In member function 'virtual void Client::ms_handle_remote_reset(Connection*)':
warning: client/Clie... - 04:59 PM devops Bug #5306: Xen based OSDs fail to start ceph-osd process
- I will do this tomorrow. The xen box is temporarily down.
- 01:46 PM devops Bug #5306 (Need More Info): Xen based OSDs fail to start ceph-osd process
- can you retest on latest cuttlefish branch? (ceph-deploy install --dev=cuttlefish)
- 04:37 PM Revision 6b52acc8 (ceph): config.h: ensure U64 option defaults are computed as 64 bits
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:35 PM Revision 32c82347 (ceph): Use authorized_keys2 instead of authorized_keys
- Instead of going through the trouble of adding/removing lines
from authorized_keys which has all our normal keys in i... - 04:07 PM Documentation #3391: doc: add instructions on snapshot reversion
- Actually, this isn't a documentation oversight. There's no means of rolling back an entire snapshot on a pool visible...
- 03:52 PM Revision 24fdfd26 (ceph): ceph-deploy: use correct branch for workunits
- 03:29 PM Bug #5226: Some PG stay in "incomplete" state
- Well, I have pools on that clusters which are fines (thanks to 3 copies) ; so how can I recover a HEALTH_OK status, s...
- 01:05 PM Bug #5226 (Won't Fix): Some PG stay in "incomplete" state
- nothing much to be done here if 2 disk were replaced/failed
- 03:18 PM rgw Documentation #5178 (Resolved): rgw: fix keystone openssl to nss conversion
- See http://ceph.com/docs/master/radosgw/config/#integrating-with-openstack-keystone
- 03:17 PM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- Came up with this: https://gist.github.com/alram/33ea3360d5aa6a86e8a4
- 02:38 PM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- i think the right way to do this is to look to see if /sys/block/$disk/$part exist (e.g., /sys/block/sda/sda1) to tel...
- 01:43 PM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- Alexandre, please implement one of the suggestions you mentioned.
- 02:21 PM devops Bug #5182 (Won't Fix): ceph-disk looks like it tries to mark preexisting OSD partitions with the ...
- this is correct.. if you do ceph-disk prepare /dev/sdb1 (a partition) we don't touch the partition type. if you do /...
- 02:14 PM devops Bug #5161 (Pending Backport): daemons should create /var/run/ceph if it doesn't already exist
- 02:02 PM devops Bug #5338 (In Progress): need rpm packages built for libapache-mod-fastcgi
- 01:53 PM devops Bug #5263 (Resolved): Python Error While Installing ceph-deply on debian wheezy
- 01:52 PM devops Bug #5299 (Won't Fix): ceph-deploy fails with cryptic error message if expected directories not f...
- 01:52 PM Bug #5392: osd: unfound objects from thrashing
- There seem to be a lot of threads waiting on throttle. Unfortunately, the test timed out before I could get more inf...
- 01:50 PM Bug #5392: osd: unfound objects from thrashing
- ...
- 11:21 AM Bug #5392 (Resolved): osd: unfound objects from thrashing
- ...
- 01:51 PM devops Bug #5342 (Resolved): Make tcmalloc default on ARM
- 01:51 PM devops Bug #5339 (Resolved): ceph-deploy suite failures, 'insufficient osds'
- 01:50 PM devops Bug #5359 (Resolved): ceph-deploy: install and purge commands on rhel sometimes errors out though...
- 01:49 PM devops Bug #5066 (Resolved): Problems with ceph-deploy debs
- 01:48 PM devops Bug #5199 (Resolved): ceph-deploy: on fedora18, osd create command doesnt seem to mount the disks
- 01:47 PM Bug #5301: mon: leveldb crash in tcmalloc
- debian wheezy (7.0)
- 01:01 PM Bug #5301: mon: leveldb crash in tcmalloc
- what distro are you using? this sounds a bit like #5239
- 01:47 PM devops Bug #5258 (Resolved): ceph-deploy: forgetkeys command could delete existing keyring files without...
- commit:953bee3cc66d19ef9b201299fc82c270587936a9
- 01:46 PM devops Bug #4916 (Resolved): ceph-deploy: mon create fails on bobtail branch in centos 6.3
- 01:45 PM devops Bug #5334 (Resolved): ceph-deploy: "modules not installed"
- 01:40 PM devops Bug #5345 (Need More Info): ceph-disk: handle less common device names
- 01:32 PM Bug #5389 (Resolved): osd: op_tp timeout on big cluster + radosmodel
- 12:18 PM Bug #5389: osd: op_tp timeout on big cluster + radosmodel
- ...
- 07:26 AM Bug #5389 (Resolved): osd: op_tp timeout on big cluster + radosmodel
- no errors in kern.log, so we can't blame this on the kenrel....
- 01:29 PM Bug #4268 (Can't reproduce): mon: timecheck: teuthology task fails due to unreported timecheck fr...
- 01:28 PM Bug #4189 (Resolved): osd/ReplicatedPG.cc: 4994: FAILED assert(log.objects.count(soid) ...
- 01:28 PM Bug #4265 (Won't Fix): ceph-deploy new doesn't support multiple monitors on one host.
- 01:28 PM Bug #4216 (Resolved): osd: dbojectmap incorrectly skipping ops
- 01:27 PM Bug #3683 (Resolved): mon: leak of MMonPaxos
- 01:26 PM Bug #3723 (Can't reproduce): ceph osd down command reports incorrectly
- 01:26 PM Bug #3607 (Resolved): FileStore::_write conditional code for HAVE_SYNC_FILE_RANGE seems wrong
- 01:25 PM Bug #3593 (Can't reproduce): MDS crash in MDCache.cc _recovered()
- 01:25 PM Bug #2563 (Resolved): leveldb corruption
- 01:24 PM Bug #3576 (Resolved): scripe scripts broken after upgrade to 0.55
- 01:24 PM Bug #3182 (Can't reproduce): No JSON object could be decoded - failure in the nightly run
- 01:24 PM Bug #3287 (Resolved): OSD dies when using zfs
- 01:23 PM Bug #3458 (Can't reproduce): aio enabled but not used
- 01:23 PM Bug #3644 (Resolved): ObjectCacher: discard_set ignores waiters
- 01:23 PM Bug #3771 (Resolved): ceph does not have startup scripts in Centos
- 01:23 PM Bug #3537 (Won't Fix): Logs can run root out of space and crash ceph cluster (need more aggressiv...
- 01:21 PM Bug #4041 (Can't reproduce): mon: Single-Paxos: on Paxos, leader didn't trim old versions
- 01:20 PM Bug #2896 (Won't Fix): ceph pg dump has empty hb_out field
- it's vestigal.
- 01:18 PM Bug #4523 (Duplicate): osd: read stats not updated
- 01:18 PM Bug #4723 (Can't reproduce): FAILED assert(!db->create_and_open(std::cerr)) after IO Error.
- 01:15 PM Bug #5052 (Duplicate): kclient_workunit_misc test failed in the nightlies
- 01:14 PM Bug #5074 (Can't reproduce): nightlies: timed out waiting for admin socket of restarted osd
- 01:13 PM Bug #5059 (Won't Fix): PGs can get stuck degraded if OSD removed before being out
- 01:11 PM Bug #5082 (Can't reproduce): OSD wrongly marked as down
- 01:10 PM Bug #4856 (Won't Fix): monitor: upgrades produce "client did not provide supported auth type" in log
- 01:07 PM Bug #3143 (Won't Fix): Obsync object verification takes too long
- https://github.com/dreamhost/obsync
- 01:07 PM Bug #5173 (Can't reproduce): ceph scrub found missing pg object
- 01:04 PM Bug #5205: mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_addresses()
- 01:04 PM Bug #5292 (In Progress): mon: monitor crashing due to not being in the monmap (no monmap to be in)
- Monitor is not in the monmap because there is no monmap. This should be due to a sync bug (related to #5256) that re...
- 12:57 PM Bug #5343 (Resolved): mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- 12:51 PM CephFS Bug #5289 (Can't reproduce): mds closing stale session
- this is caused when teh client is not talknig to the mds. can you verify the network is working, and ceph-fuse is hea...
- 12:50 PM Bug #5288 (Resolved): ceph.py: catch rados errors and print them nicely
- 12:49 PM Bug #4179 (Resolved): osd: memory leak during deep scrub on bobtail
- 12:49 PM Bug #5163 (Can't reproduce): filestore: ENOTEMPTY on object removal
- 12:48 PM Bug #5246 (Resolved): mon crashing on pool/pg creation with wip-mon
- 12:48 PM Bug #5157 (Resolved): install: unable to pull ceph rpm packages on fedora18
- 12:44 PM Bug #3829 (Can't reproduce): new osd added to the cluster is not receiving data
- 12:43 PM Bug #4764 (Can't reproduce): ceph -w sometimes does not reflect clean pgs
- 12:42 PM Bug #5072 (Can't reproduce): mon: segfault on leveldb::Table::Open() during monitor start
- 12:42 PM Bug #4791 (Can't reproduce): osd/ReplicatedPG.cc: 7053: FAILED assert(r >= 0) in scan_range
- 12:35 PM Bug #5238 (Resolved): osd: slow recovery (uselessly dirtying pg logs during peering)
- 12:01 PM devops Feature #5393 (Rejected): ceph-disk: prepare should warn when using partitions
- When using ceph-disk prepare with already created partitions, we do not set the partition uuid, thus the udev rules a...
- 11:11 AM Bug #5383 (Resolved): arm write EFBIG
- 6b52acc8502ec16e2d0b89d8caf6235ec45778cb
- 10:54 AM Bug #5069: monitor crashed during mon thrash in nightlies
- Forgot to mention that the sync flag is set on the store. Sage pointed out that the real issue here is that we're al...
- 10:32 AM Bug #5069: monitor crashed during mon thrash in nightlies
- I've been able to reproduce this on some locked nodes that were hammering the monitors pretty hard for the past week....
- 09:34 AM CephFS Bug #5379 (Resolved): mds/ceph-fuse hang on mount
- 08:26 AM rbd Bug #5391 (Duplicate): krbd: crash in rbd_obj_request_create -> strlen
- ...
- 07:48 AM Bug #5272 (Can't reproduce): Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of ex...
- 12:47 AM Bug #5272: Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of existing cluster
- As I re-encountered the same issue without upgrading, just restarting MDS daemon, I think this tracker issue may be c...
- 07:04 AM Revision e2af5fbe (ceph): test: test for cls_statelog
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:04 AM Revision 1ecec3a1 (ceph): cls_statelog: fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:06 AM Revision 8d5fc708 (ceph): cls_statelog: add client api functions
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:06 AM Revision fbe816a1 (ceph): cls_statelog: fixes and changes to api
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 03:10 AM Revision 7669662b (ceph): cls_statelog: introducing new objclass to handle state tracking
- Somewhat similar to the log objclass, but uses different data for
indexing. Also keeps a dual index. In general an en... - 03:06 AM Revision cbbad5b5 (ceph): chmod +x iogen.sh
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:55 AM Revision 5e9a0a14 (ceph): Merge branch 'next'
- 02:55 AM Revision c14dd154 (ceph): client: handle reset during initial mds session open
- If we get a reset during our attempt to open an MDS session, close out the
Connection* and retry to open the session,... - 02:54 AM Revision df8a3e55 (ceph): client: handle reset during initial mds session open
- If we get a reset during our attempt to open an MDS session, close out the
Connection* and retry to open the session,... - 01:56 AM Revision 2e27f69e (ceph): rgw: move a couple of unitests to a different Makefile rule
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:41 AM Revision f5f83148 (ceph): rgw: object mtime the same for both object and bucket index
- Make sure object mtime that's passed to bucket index is the
same as the one set on the object.
Signed-off-by: Yehuda... - 12:14 AM Revision 7f63baa6 (ceph): rgw: fix inter-region copy (ofs wasn't correct)
- Fixing an issue with data read. Since inter-region copy uses
embedded metadata within the data input, we need to fix ...
06/17/2013
- 11:59 PM Bug #5375: squeeze tcmalloc leaks
- [: ~]# pmap -x 11783|tail -n1
total kB 1547412 688752 685152
[: ~]# ceph -m 10.255.0.100:6789 heap stat... - 09:40 AM Bug #5375: squeeze tcmalloc leaks
- Stefan, could you please try (for your monitor's IP and PORT):...
- 06:31 AM Bug #5375 (Resolved): squeeze tcmalloc leaks
- While running cuttlefish 0.61.3 or 08304a7c46da7517319b7db0b64d1c4f54771472
i'm seeing high memory usage of ceph-mo... - 11:48 PM Revision 8c179f36 (ceph): big: add big suite
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:41 PM Revision d64f264c (ceph): rados: don't use ceph-fuse for workunits
- They can run on the local mount/dir.
- 11:39 PM Revision 92997a49 (ceph): mon: fix 'osd dump <epoch>'
- The optional epoch argument was missing from the command spec.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-... - 11:24 PM Revision 0ff2e42e (ceph): Use authorized_keys2 instead of authorized_keys
- Instead of going through the trouble of adding/removing lines
from authorized_keys which has all our normal keys in i... - 10:52 PM Revision 49e0cfc4 (ceph): powercycle: add ext4 to osd powercycle test matrix
- 10:47 PM Revision aa883483 (ceph): ceph-disk: add some notes on wth we are up to
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 8c6b24e9039079e897108f28d6af58cbc703a15a) - 10:47 PM Revision 261964ad (ceph): ceph-disk: clear TERM to avoid libreadline hijinx
- The weird output from libreadline users is related to the TERM variable.
Signed-off-by: Sage Weil <sage@inktank.com>... - 10:47 PM Revision e36fb326 (ceph): ceph-disk-udev: set up by-partuuid, -typeuuid symlinks on ancient udev
- Make the ancient-udev/blkid workaround script for RHEL/CentOS create the
symlinks for us too.
Signed-off-by: Sage We... - 10:47 PM Revision c3936ebb (ceph): ceph-disk: do not stop activate-all on first failure
- Keep going even if we hit one activation error. This avoids failing to
start some disks when only one of them won't ... - 10:47 PM Revision 3cb783c3 (ceph): ceph.spec: include partuuid rules in package
- Commit f3234c147e083f2904178994bc85de3d082e2836 missed this.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pic... - 10:47 PM Revision 2d771b57 (ceph): ceph.spec: install/uninstall init script
- This was commented out almost years ago in commit 9baf5ef4 but it is not
clear to me that it was correct to do so. I... - 10:47 PM Revision dfe421e4 (ceph): sysvinit, upstart: ceph-disk activate-all on start
- On 'service ceph start' or 'service ceph start osd' or start ceph-osd-all
we should activate any osd GPT partitions.
... - 10:47 PM Revision ef47cf9c (ceph): ceph-disk: add 'activate-all'
- Scan /dev/disk/by-parttypeuuid for ceph OSDs and activate them all. This
is useful when the event didn't trigger on ... - 10:47 PM Revision 65ec1d87 (ceph): udev: /dev/disk/by-parttypeuuid/$type-$uuid
- We need this to help trigger OSD activations.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit... - 10:46 PM Revision 910af074 (ceph): Merge branch 'wip-5194' into next
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Gary Lowell <gary.lowell@inktank.com> - 10:43 PM Revision 8c6b24e9 (ceph): ceph-disk: add some notes on wth we are up to
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:39 PM Revision 94b37005 (ceph): rgw: intra-region copy, preserve mtime
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:50 PM Revision f35bc025 (ceph): PG: move instances of log dirtying in PG into PGLog
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision b16fdf23 (ceph): PGLog: replace dirty_log with mark_dirty_*
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 6dd95c86 (ceph): PG,PGLog: remove dirty_log arguments
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision abac4eab (ceph): test/osd/TestPGLog: fix pglog unittests for dirty_log and ondisklog
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 9b6cb639 (ceph): PGLog: add debug check on written keys, verify on write
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 962b64a8 (ceph): PGLog,PG: use normal log dirtying and writing for append and trim
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 2ad319be (ceph): PGLog: only iterate over dirty portions of the log
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision c6dd60db (ceph): PGLog: rename dirty() to is_dirty()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision f164a325 (ceph): PGLog: check for dirty_to != eversion_t() and dirty_from != eversion_t:...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 29eb333b (ceph): test/osd/TestPGLog: %s/dirty()/is_dirty()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 39245319 (ceph): PGLog: clear missing on backfill reset
- When backfill is reset, the missing set should be cleared
since all objects are >last_backfill.
Fixes: #5320
Signed-... - 09:50 PM Revision 53e1fda0 (ceph): FileStore: add rmkeyrange
- Handling it in DBObjectMap really only has efficiency
advantages if the object is a clone.
Signed-off-by: Samuel Jus... - 09:50 PM Revision 7bc43055 (ceph): PG: remove ondisklog usages from PG
- ondisklog is now only relevant for the divergent priors mapping.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:50 PM Revision a9a41bc0 (ceph): PGLog: pass only divergent_priors, not ondisklog
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision ca1637ff (ceph): PGLog: remove other ondisklog references
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision b73aa30e (ceph): PGLog: remove OndiskLog
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision fb88873c (ceph): osd_types: move code for pg_log_entry_t::get_key_name into eversion_t
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision d77c4ffa (ceph): PGLog: track dirty_to and dirty_from for log
- This allows the log to only write out/clear the keys
which have actually changed.
Signed-off-by: Samuel Just <sam.ju... - 09:46 PM Revision 4c89a2b6 (ceph): rgw: system user get obj returns JSON encoded metadata
- instead of binary encoded metadata
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:20 PM Revision 47ce702c (ceph): *: always include rados.h using types.h
- types.h redefines __le* to ceph_le* to ensure endian
safety.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Revie... - 09:15 PM CephFS Bug #5381: ceph-fuse: stuck with disconnected inodes on shutdown
- This is different from #4850. In issue #4850, disconnected inodes have no cap. In this issue, all disconnected inodes...
- 01:32 PM CephFS Bug #5381: ceph-fuse: stuck with disconnected inodes on shutdown
- Good chance this is a duplicate of #4850 (though that's fsstress, so maybe not).
- 01:22 PM CephFS Bug #5381 (Resolved): ceph-fuse: stuck with disconnected inodes on shutdown
- Seen this at least 2x in the last few days:...
- 08:53 PM Revision ebd003bc (ceph): valgrind: another leveldb leak
- 08:37 PM rgw Bug #5357 (In Progress): rgw: set and retrieve intra-region copy operation state
- 08:36 PM rgw Bug #5351 (Resolved): rgw: make sure wip-rgw-geo passes gitbuilder
- 08:35 PM devops Bug #5387 (Resolved): ceph-disk: lockfile does not detect stale locks (dead parent process)
- python lockfile class does not detect when teh prior lock owner process is gone. we should switch to a class that do...
- 08:29 PM Revision 5cf5f18e (ceph): Merge branch 'next'
- 08:15 PM Revision d46e6c3b (ceph): OSD: we need to check pg ?.0 for resurrection
- Fixes: #5269
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by:... - 07:54 PM Revision 4386d2c8 (ceph): rbd: do not use ceph-fuse to run functional tests
- The workunit task can now do this in a local directory.
- 07:24 PM Revision 5bf08cd5 (ceph): libcephfs: add a couple multiclient tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:24 PM Revision ee40c217 (ceph): client: fix sync read zeroing at EOF
- If we have a read that hits EOF, we need to do a short read. Previously
we would zero the buffer if we were complete... - 07:21 PM Revision 4a739b13 (ceph): rgw: escape prefix correctly when listing objects
- Fixes: #5362
When listing objects prefix needs to be escaped correctly (the
same as with the marker). Otherwise listi... - 07:21 PM Revision 6edba9e9 (ceph): messages/MMonSync: initialize crc in ctor
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit cd1c289b96a874ff99a83a44955d05efc9f2765a) - 06:16 PM Revision d7f7d613 (ceph): ceph-disk-udev: set up by-partuuid, -typeuuid symlinks on ancient udev
- Make the ancient-udev/blkid workaround script for RHEL/CentOS create the
symlinks for us too.
Signed-off-by: Sage We... - 06:16 PM Revision e538829f (ceph): ceph-disk: clear TERM to avoid libreadline hijinx
- The weird output from libreadline users is related to the TERM variable.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision 253069e0 (ceph): ceph.spec: include partuuid rules in package
- Commit f3234c147e083f2904178994bc85de3d082e2836 missed this.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision c9074375 (ceph): ceph-disk: do not stop activate-all on first failure
- Keep going even if we hit one activation error. This avoids failing to
start some disks when only one of them won't ... - 06:09 PM Revision b8d2ba14 (ceph): rgw: set default region as master
- A default region that is automaticall created needs to be
set as the master.
Signed-off-by: Yehuda Sadeh <yehuda@ink... - 06:09 PM Revision 7c729335 (ceph): test: update cli test
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:09 PM Revision 00656dad (ceph): rgw: add 'delete' to signed subresources list
- This fixes a regression that removed 'delete' from the signed
subresources list, thus made it impossible to authentic... - 05:57 PM Revision fcd65139 (ceph): rgw: escape prefix correctly when listing objects
- Fixes: #5362
When listing objects prefix needs to be escaped correctly (the
same as with the marker). Otherwise listi... - 05:57 PM Revision a8f9d57a (ceph): rgw: translate object marker to raw format
- Fixes: #4600
Object marker should be treated as an object, so that name is formatted
correctly when getting the raw o... - 05:55 PM Revision d582ee24 (ceph): rgw: escape prefix correctly when listing objects
- Fixes: #5362
When listing objects prefix needs to be escaped correctly (the
same as with the marker). Otherwise listi... - 05:43 PM CephFS Bug #5380: osdc/Filer.cc: 163: FAILED assert(probe->known_size[p->oid] <= shouldbe)
- see commit a41bad1a9b(ceph: re-calculate truncate_size for strip object)
- 01:18 PM CephFS Bug #5380 (Resolved): osdc/Filer.cc: 163: FAILED assert(probe->known_size[p->oid] <= shouldbe)
- on mds shutdown...
- 05:42 PM Revision 2ad85576 (ceph): client: fix ancient typo in caps revocation path
- If we have dropped all references to a revoked capability, send the ack
to the MDS. This typo has been there since v... - 05:41 PM Revision b7143c2f (ceph): client: fix ancient typo in caps revocation path
- If we have dropped all references to a revoked capability, send the ack
to the MDS. This typo has been there since v... - 05:34 PM rgw Feature #5354 (Fix Under Review): rgw: intra-region object copy should also set mtime on object
- 05:03 PM Revision d3d88983 (ceph): messages/MMonHealth: remove unused flag field
- This was initialized in (one of) the ctor(s), but not encoded/decoded,
and not used. Remove it. This makes valgrind... - 05:03 PM Revision 646d9ccc (ceph): messages/MMonProbe: fix uninitialized variables
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 4974b29e251d433101b699550... - 04:49 PM Revision 13680976 (ceph): sysvinit, upstart: ceph-disk activate-all on start
- On 'service ceph start' or 'service ceph start osd' or start ceph-osd-all
we should activate any osd GPT partitions.
... - 04:49 PM Revision cc9b83a8 (ceph): ceph.spec: install/uninstall init script
- This was commented out almost years ago in commit 9baf5ef4 but it is not
clear to me that it was correct to do so. I... - 04:49 PM Revision d512dc9e (ceph): udev: /dev/disk/by-parttypeuuid/$type-$uuid
- We need this to help trigger OSD activations.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:49 PM Revision 5c7a2368 (ceph): ceph-disk: add 'activate-all'
- Scan /dev/disk/by-parttypeuuid for ceph OSDs and activate them all. This
is useful when the event didn't trigger on ... - 04:44 PM CephFS Bug #5379: mds/ceph-fuse hang on mount
- 12:52 PM CephFS Bug #5379 (Resolved): mds/ceph-fuse hang on mount
- have observed serveral times ceph-fuse hanging on getattr(#1). latest job was...
- 03:55 PM Bug #5373 (Can't reproduce): osd: dump_stuck test fails on tell
- 03:49 PM devops Bug #5194 (Resolved): udev does not start osd after reboot on wheezy or el6 or fedora
- 02:54 PM devops Bug #5194 (Fix Under Review): udev does not start osd after reboot on wheezy or el6 or fedora
- now works on rhel, centos, wheezy, precise. f18 still has the mon start issue.
- 02:16 PM Bug #5383 (Resolved): arm write EFBIG
- 2013-06-17 15:05:31.066237 a6919420 0 -- 10.214.156.115:6800/7870
submit_message osd_op_reply(30
... - 02:09 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
- Sorry, logs at /a/teuthology-2013-06-15_01:00:44-fs-next-testing-basic/36375
- 02:07 PM CephFS Bug #5382 (Can't reproduce): mds: failed objecter assert on shutdown
- I haven't been through this completely, but it looks like the mds went laggy, and then it received a SIGTERM (the tes...
- 01:26 PM Bug #5269 (Resolved): osd: EEXIST on mkcoll
- 10:08 AM Bug #5269: osd: EEXIST on mkcoll
- ubuntu@teuthology:/a/teuthology-2013-06-17_01:00:05-rados-master-testing-basic/37637
- 12:36 PM rgw Bug #5362: rgw: failure when listing objects with prefix that starts with underscore
- I confirmed that this was tested, and I built it on all the branches:
next as of commit:d582ee2438a3bd307324c5f44491... - 12:35 PM rgw Bug #4600: rgw: list bucket broken when marker start with underscore
- Cherry-picked this commit into bobtail as well, in commit:a8f9d57a15ad7a69d53aa8fc6090fd1b394b616a. It got missed in ...
- 12:25 PM Bug #5366 (Resolved): assert in ODSMap::is_blacklisted()
- 09:40 AM Bug #5366: assert in ODSMap::is_blacklisted()
- Sam, please review.
- 12:24 PM CephFS Bug #5368 (Resolved): ceph-fue: fsx-mpi hangs in _sync_read
- commit:ee40c217e373b538e227f7218b09c1c794b4124a
- 11:49 AM rbd Bug #4446: librbd: crash from opensolaris vm
- I just upgraded to KVM 1.4.2 -- same problem.
- 11:14 AM Revision 1d86f77e (ceph): mds: fix cross-authorty rename race
- When doing cross-authorty rename, we need to make sure bystanders
have received all messages sent by inode's original... - 11:14 AM Revision 7f5d6e5c (ceph): mds: don't journal bare dirfrag
- don't journal bare dirfrag when starting scatter. also add debug
code for bare dirfrag modification.
Signed-off-by: ... - 11:14 AM Revision 18b9e63b (ceph): mds: don't update migrate_seq when importing non-auth cap
- We use migrate_seq to distinguish old and new auth MDS. So we should
not change migrate_seq when importing non-auth c... - 11:14 AM Revision 29e6597e (ceph): mds: fix frozen check in Server::try_open_auth_dirfrag()
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 11:14 AM Revision f11ec5cc (ceph): mds: handle undefined dirfrags when opening inode
- When MDS is rejoin stage, cache rejoin message can add undefined
inodes and dirfrags to the cache. These undefined ob... - 11:14 AM Revision aa3e512c (ceph): mds: try purging stray inode after storing backtrace
- Inode is auth pinned and can't be purged while storing backtrace,
so we should try purging stray inode after storing ... - 11:04 AM rgw Bug #5378 (Resolved): make radosgw-admin user rm idempotent
- It would be extremely useful for radosgw-admin user rm to be idempotent, specifically so that it will return success ...
- 09:42 AM Bug #5340 (Resolved): Bad arguments to zero will cause OSD to crash
- 05:42 AM rgw Bug #5374 (Resolved): Avoid relying on keystone's admin token
- The current Keystone integration requires knowledge of the keystone admin token. The keystone admin token is for Keys...
- 03:13 AM Revision f179dc1f (ceph): mon: make mark_me_down asserts match check
- The OSD may have sent a request where the message source does not match
the target in the message. Verify that the t... - 03:12 AM Revision ae04f3c0 (ceph): rados: whitelist 'wrongly marked me down' for cephtool tests
- These test 'ceph osd down ...'; whitelist the resulting log message for
these tests.
06/16/2013
- 11:49 PM Revision e3fb095d (ceph): Merge branch 'next'
- 11:49 PM Revision 2fe4d29f (ceph): ceph: remove space when prefix is blank
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:48 PM Revision 8d9eef23 (ceph): ceph: fix return code for multi-target commands
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:48 PM Revision 84d1847f (ceph): ceph: error out properly when failing to get commands
- If we make ret positive here we miss the failure check below. Instead,
just set outs appropriately.
Signed-off-by: ... - 11:42 PM Revision 8d9272ec (ceph): test/admin_socket/objecter_requests: fix test
- Commit 2bda9db1c24530cbaaa161b7ff0a80efa913aa78 added command_ops
to the result.
Signed-off-by: Sage Weil <sage@inkt... - 09:53 PM Revision 7887f84f (ceph): misc: let clients use any pool
- rados.py, for example, creates new pools for each instance.
- 08:36 PM Bug #5269: osd: EEXIST on mkcoll
- Running with logging overnight to reproduce.
- 08:08 PM Bug #5269: osd: EEXIST on mkcoll
- and...
- 07:58 PM Bug #5269: osd: EEXIST on mkcoll
- don't think this was #5270.. just hit it on...
- 08:36 PM Revision efebdba0 (ceph): ceph: do not print status to output file when talking to old mons
- The old cli would send the status message to stdout instead of stderr;
we try to emulate that behavior when talking t... - 08:11 PM Revision 7177d2e8 (ceph): ceph_manager: fix ceph tell mon.*
- Need -- to make cli stop parsing (or quote the options).
Otherwise, the options will be parsed/applied to the cli's
l... - 08:09 PM Bug #5373 (Can't reproduce): osd: dump_stuck test fails on tell
- ...
- 05:03 PM Revision 38f82f61 (ceph): rados: no cephtool test on ceph-fuse
- 05:00 PM Revision 73413642 (ceph): rados: do not run cli tests on top of ceph-fuse
- Some of the commands we test break teh mds, which break the mount, which
stall teh test.
Fixes: #5370 - 04:52 PM Bug #5372 (Duplicate): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- ...
- 04:10 PM Revision 1ec8ba50 (ceph): no need for ceph --concise argument
- 03:50 PM Revision 80c2d5a8 (ceph): osd/ReplicatedPG: length 0 writes are allowed
- From f1b6bd7988ab964c9167eff7bea51a49573f5175.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:04 AM Bug #5370 (Resolved): ceph tool occasionally hangs
- 10:01 AM Bug #5370: ceph tool occasionally hangs
- fixed by ceph-qa-suite commit:73413642d7a1a1aa09cfa240cadba925b1ba812d
- 05:50 AM CephFS Bug #5367: multiclient tests: kernel mount gets EPERM
- kclient and MDS never return -EACCES. was ior executed with root privilege?
- 05:06 AM Revision 1113ff02 (ceph): rgw: get / set user & bucket meta mtime
- also update infrastructure to be able to set mtime on objects
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:50 AM Revision 719988fa (ceph): marginal: refactor multiclient collection, separate out locktest
- 03:50 AM Revision 50d9738f (ceph): move multiclient tests from marginal -> fs suite
- 03:50 AM Revision c5cf1bd5 (ceph): fs: disable multiclient fsx
- current hangs. fixme!
- 03:50 AM Revision 1dcc0c51 (ceph): fs: disable multiclient tests on kernel
- Currently fails with EPERM.
- 03:48 AM Revision 9ef6041f (ceph): Merge branch 'next'
- 03:48 AM Revision 08304a7c (ceph): common/Preforker: fix broken recursion on exit(3)
- If we exit via preforker, call exit(3) and not recursively back into
Preforker::exit(r). Otherwise you get a hang wi... - 03:48 AM Revision 7e7ff753 (ceph): common/Preforker: fix broken recursion on exit(3)
- If we exit via preforker, call exit(3) and not recursively back into
Preforker::exit(r). Otherwise you get a hang wi... - 03:47 AM Revision f25f2120 (ceph): osd/OSDMap: fix is_blacklisted()
- You can only call set_port() if is_ip() is true (there is an assert in
the accessor).
Fixes: #5366
Signed-off-by: Sa... - 03:42 AM Revision 21e85f90 (ceph): qa/workunits/misc/multiple_rsync.sh: wtf
- 2013-06-15T12:55:29.808 INFO:teuthology.task.workunit.client.0.err:+ rsync -auv --exclude local/ /usr/ usr.1
2013-06-... - 01:41 AM Revision a2cf14fe (ceph): rgw: preserve bucket creation time across different zones / regions
- Keep bucket creation time in RGWBucketInfo, and make use
of it where necessary.
Signed-off-by: Yehuda Sadeh <yehuda@...
06/15/2013
- 11:55 PM Revision 8eae1b8b (ceph): rgw: show mtime for metadata entries
- currently only shows for buckets
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:10 PM rgw Feature #4310 (Fix Under Review): rgw: multisite: radosgw changes: copy across regions
- 10:09 PM rgw Bug #5362 (Fix Under Review): rgw: failure when listing objects with prefix that starts with unde...
- 10:09 PM rgw Feature #5352 (Fix Under Review): rgw: metadata get should also dump mtime
- 10:08 PM rgw Feature #5353 (Fix Under Review): rgw: metadata put should apply mtime if set
- 08:49 PM Bug #5366: assert in ODSMap::is_blacklisted()
- commit:f25f212027294e5107fc9938e67d31879c171088 merged to fix the weekend qa runs. still should get a review.
- 09:10 AM Bug #5366 (Resolved): assert in ODSMap::is_blacklisted()
- wip pushed
- 08:46 PM Bug #5371 (Resolved): idempotent filestore test failure
- ...
- 08:10 PM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- 08:09 PM devops Bug #5363 (Resolved): specfile: ceph does not start on reboot
- 08:09 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- update:
* wheezy is working well.
* fedora is failing only because the mon doesn't start on boot. see #5369
* r... - 07:57 PM Bug #5370 (Resolved): ceph tool occasionally hangs
- "description": "/var/lib/teuthworker/archive/teuthology-2013-06-15_01:00:11-rados-next-testing-basic/36197",
... - 07:50 PM devops Bug #5369 (Resolved): fedora18: sysvinit doesn't start mon on reboot
- mon log indicates it can't bind to the ip, suggesting it is starting before the network. however, note that...
- 07:46 PM CephFS Bug #5367: multiclient tests: kernel mount gets EPERM
- mpi-fsx also gets EPERM.
- 07:15 PM CephFS Bug #5367 (Resolved): multiclient tests: kernel mount gets EPERM
- ...
- 07:45 PM CephFS Bug #5368 (Resolved): ceph-fue: fsx-mpi hangs in _sync_read
- infinite loop in _sync_read() due to a short read. see wip-client-sync.
- 08:19 AM Bug #5365 (Rejected): Massive OSD flaps
- Note that the current development releases include more robust heartbeat checks and a backoff behavior that prevents ...
- 03:10 AM Bug #5365: Massive OSD flaps
- I found networking bug (not full connectivity). Ticket could be closed.
The reason was that new osd host was unable ... - 03:05 AM Bug #5365: Massive OSD flaps
- During upgrade I restarted services on all nodes.
- 02:55 AM Bug #5365: Massive OSD flaps
- I upgraded full cluster to
new: ceph version 0.56.6 (95a0bda7f007a33b0dc7adf4b330778fa1e5d70c)
but it still flap... - 02:31 AM Bug #5365 (Rejected): Massive OSD flaps
- Hi, all.
Today I added one more node to my CEPH and it became unstable, i mean here that it's unable to work with ... - 06:35 AM Revision 8fa4394f (ceph): rgw: fixes for intra-zone object copy
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:58 AM Revision 5df39aa4 (ceph): rgw: set bucket marker and bucket obj version from master
- Make sure that bucket that's created gets the same marker as
the one that the master region generated. Also, for some... - 04:57 AM Revision 622f5002 (ceph): rgw: multiple changes for intra-zone object copy
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:56 AM Revision 17d65716 (ceph): rgw: when setting bucket metadata key, don't override placement
- Bucket placement also contains data and index pools locations in
the source zone. However, we might be applying it on... - 04:05 AM Revision 08c915c8 (ceph): Merge remote-tracking branch 'gh/next'
- 01:20 AM Revision d5679d04 (ceph): rgw: forward amz headers of copy request to remote rgw
- So that if request has any special conditions, it'll be processed
on the remote gateway
Signed-off-by: Yehuda Sadeh ... - 01:06 AM Revision 5ff20597 (ceph): rgw: cleanup, move init_meta_info() into req_info
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:30 AM Revision 9253cd81 (ceph): ceph: pass --format=foo to old monitors
- And --threshold too, although.. really.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviwed-by: Dan Mick <dan.mick@i... - 12:30 AM Revision c35c98d1 (ceph): ceph: add newline when using old monitors
- The old tool would print a newline after outs, e.g. from 'ceph osd create'.
Do the same when we are talking to old mo...
06/14/2013
- 11:58 PM Revision 0d3517b2 (ceph): doc: Added index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:58 PM Revision fb07f9df (ceph): doc: Added index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:57 PM Revision fd423fce (ceph): doc: Added index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:57 PM Revision 8a5b2760 (ceph): doc: Added index tag.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:57 PM Revision d5dbc2f2 (ceph): doc: Updated usage and index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:56 PM Revision ceba9537 (ceph): doc: Updated usage and index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:56 PM Revision 81d4f9d9 (ceph): doc: Added introductory section. Updated usage. Index tags.
- fixes: #3220
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 11:54 PM Revision 0b604fb4 (ceph): doc: Index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:54 PM Revision f851c5d4 (ceph): doc: Update for usage and index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:54 PM Revision 4a79fabd (ceph): doc: Update for usage. Index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:53 PM Revision 20e68b74 (ceph): doc: Updated for glossary usage. Index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:53 PM Revision 44bf35a2 (ceph): doc: Updated index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:52 PM Revision a529882a (ceph): doc: Updated index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:52 PM Revision bb5fae4a (ceph): ceph.in: zero-arg invocation was broken (check array length)
- Also remove stray comment char
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:52 PM Revision 8f8fd7a9 (ceph): doc: Updated index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:28 PM rgw Feature #5349 (Fix Under Review): rgw: intra-region object copy
- 11:01 AM rgw Feature #5349 (Resolved): rgw: intra-region object copy
- This should also include the ability to copy namespaced objects (to be able to copy multipart upload parts).
- 11:06 PM Revision 2be16701 (ceph): doc: Minor updates.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:06 PM Revision b3a143d9 (ceph): doc: Minor updates for usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:39 PM Revision 10c0ae97 (ceph): rgw: remove unused variable
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:17 PM Revision 1bf7a2ca (ceph): rados: thrash under valgrind
- This will get us better coverage in the peering and recovery code.
- 10:11 PM Revision 3474fa83 (ceph): rules: Don't disable tcmalloc on ARM (and other non-intel)
- Fixes #5342
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 10:10 PM Revision f202d332 (ceph): rules: Don't disable tcmalloc on ARM (and other non-intel)
- Fixes #5342
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 10:01 PM Revision 37cc85ed (ceph): rgw: bucket marker contains zone name
- (issue 5347)
We need this so that raw object names on different zones within
the same region don't collide.
Signed-o... - 09:12 PM Revision cbca9232 (ceph): Remove mon socket in post-stop
- If ceph-mon segfault, socket file isn't removed.
By adding a remove in post-stop, upstart clean run directory proper... - 09:12 PM Revision 3f8b3cf1 (ceph): Remove stop on from upstart tasks
- Upstart tasks don't have to concept of 'stop on' as they
are not long running.
(cherry picked from commit 17f6fccabc2... - 09:11 PM Revision 0b9b8368 (ceph): ceph-disk: extra dash in error message
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit f86b4e7a4831c684033363ddd335d2f3fb9a189a) - 09:11 PM Revision ecddd1e0 (ceph): ceph-disk: cast output of _check_output()
- Cast output of _check_output() to str() to be able to use
str.split().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 09:11 PM Revision 43855e37 (ceph): ceph-disk: remove unnecessary semicolons
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 9785478a2aae7bf5234fbfe443603ba22b5... - 09:10 PM Revision 53927f94 (ceph): ceph-disk: fix undefined variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 9429ff90a06368fc98d146e065a7b9d1b68... - 09:10 PM Revision f1beeb26 (ceph): ceph-disk: add missing spaces around operator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit c127745cc021c8b244d721fa940319158ef... - 09:10 PM Revision fe23ae00 (ceph): udev: drop useless --mount argument to ceph-disk
- It doesn't mean anything anymore; drop it.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit bc... - 09:10 PM Revision d99e0a89 (ceph): ceph-disk-udev: activate-journal
- Trigger 'ceph-disk activate-journal' from the alt udev rules.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pi... - 09:10 PM Revision dfbd2010 (ceph): ceph-disk: do not use mount --move (or --bind)
- The kernel does not let you mount --move when the parent mount is
shared (see, e.g., https://bugzilla.redhat.com/show... - 09:09 PM Revision 98a990d7 (ceph): ceph.spec: include by-partuuid udev workaround rules
- These are need for old or buggy udev. Having them for new and unbroken
udev is harmless.
Signed-off-by: Sage Weil <... - 09:09 PM Revision 1504e23f (ceph): ceph-disk: work around buggy rhel/centos parted
- parted on RHEL/Centos prefixes the *machine readable output* with
1b 5b 3f 31 30 33 34 68
Note that the same thing... - 09:09 PM Revision 0b9482bd (ceph): ceph-disk: implement 'activate-journal'
- Activate an osd via its journal device. udev populates its symlinks and
triggers events in an order that is not rela... - 09:09 PM Revision 062b9296 (ceph): ceph-disk: call partprobe outside of the prepare lock; drop udevadm settle
- After we change the final partition type, sgdisk may or may not trigger a
udev event, depending on how well udev is b... - 09:09 PM Revision 9f9dc8b8 (ceph): ceph-disk: add 'zap' command
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 10ba60cd088c15d4b4ea0b86ad681aa57f1051b6) - 09:08 PM Revision 4fab29c1 (ceph): ceph-disk: fix stat errors with new suppress code
- Broken by 225fefe5e7c997b365f481b6c4f66312ea28ed61.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from ... - 09:08 PM Revision 01ba391b (ceph): ceph-disk: add '[un]suppress-activate <dev>' command
- It is often useful to prepare but not activate a device, for example when
preparing a bunch of spare disks. This mar... - 09:04 PM Revision e5ffe0d2 (ceph): ceph-disk: do not use mount --move (or --bind)
- The kernel does not let you mount --move when the parent mount is
shared (see, e.g., https://bugzilla.redhat.com/show... - 09:04 PM Revision b1391520 (ceph): ceph-disk-udev: activate-journal
- Trigger 'ceph-disk activate-journal' from the alt udev rules.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:04 PM Revision bcfd2f31 (ceph): udev: drop useless --mount argument to ceph-disk
- It doesn't mean anything anymore; drop it.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:04 PM Revision f3234c14 (ceph): ceph.spec: include by-partuuid udev workaround rules
- These are need for old or buggy udev. Having them for new and unbroken
udev is harmless.
Signed-off-by: Sage Weil <... - 09:04 PM Revision 1aa7f595 (ceph): ceph.spec: add missing ceph_test_rados_api_cmd to package
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:35 PM Revision b1293ee8 (ceph): ceph: flush stderr, stdout for sane output; add prefix
- Aie.
e.g., ceph tell mon.* injectargs '--debug-ms 1'
mon.a: injectargs:debug_ms=1/1
mon.b: injectargs:debug_ms=1/... - 07:10 PM Revision 82ff72f8 (ceph): ceph-disk: work around buggy rhel/centos parted
- parted on RHEL/Centos prefixes the *machine readable output* with
1b 5b 3f 31 30 33 34 68
Note that the same thing... - 06:22 PM Revision 92b83007 (ceph): mon: OSDMonitor: don't ignore apply_incremental()'s return on UfP [1]
- apply_incremental() may return -EINVAL. Don't ignore it.
[1] UfP = Update from Paxos
Fixes: #5343
Signed-off-by: ... - 06:21 PM Revision 41a15a63 (ceph): upstart: start ceph-all on runlevel [2345]
- Starting when only one network interface has started breaks machines with
multiple nics in very problematic ways.
Th... - 06:21 PM Revision 7e08ed1b (ceph): upstart: start ceph-all on runlevel [2345]
- Starting when only one network interface has started breaks machines with
multiple nics in very problematic ways.
Th... - 06:11 PM rgw Bug #5348 (Fix Under Review): rgw: missing copy constraints checks for inter region user object copy
- 11:00 AM rgw Bug #5348 (Resolved): rgw: missing copy constraints checks for inter region user object copy
- 06:04 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- rhel seems to be working, fedora18 is acting very strange.
- 02:06 PM devops Bug #5194 (In Progress): udev does not start osd after reboot on wheezy or el6 or fedora
- tahnks- i now see the problem (and can reproduce it here, yay!). testing a fix
- 01:09 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Hi Sage,
attached is the current syslog.
I started "partprobe /dev/sdb" at Jun 14 21:57:06 and "partprobe /dev/... - 01:04 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Can you generate and attach a udev log after the reboot? Actually, ideally,
- reboot
- note the time
- run part... - 12:59 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Sage Weil wrote:
> Can you grab
>
> https://github.com/ceph/ceph/blob/master/src/ceph-disk and copy it to /usr/... - 12:43 PM devops Bug #5194 (Need More Info): udev does not start osd after reboot on wheezy or el6 or fedora
- Hi Robert,
Can you grab
https://github.com/ceph/ceph/blob/master/src/ceph-disk and copy it to /usr/sbin
https:... - 12:42 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- 06:02 PM Revision 7503db9a (ceph): ceph: fix mon.*
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:48 PM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- nope wrong ticket; ignore
- 05:32 PM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- Sage, was that reply intended for this ticket? If it was I'm surely missing something...
- 01:03 PM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- Can you generate and attach a udev log after the reboot? Actually, ideally,
- reboot
- note the time
- run part... - 12:44 PM Bug #5343 (Pending Backport): mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- pushed.. will backport once we have done more testing
- 10:45 AM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- I ran the following test for an already existing single-monitor setup:
* generate monmap with random fsid
* injec... - 09:28 AM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- Greg pointed out that it's likely the fsid issue results from messing around with the monmap's fsid. Setting up a te...
- 09:01 AM Bug #5343: mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- Running gdb, looks like the 2810's incremental fsid is different from the OSDMap's fsid:...
- 07:41 AM Bug #5343 (In Progress): mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- 07:33 AM Bug #5343 (Resolved): mon: infinite OSDMonitor::update_from_paxos() on single-monitor setup
- A user on ceph-users shared a log containing a most interesting behavior happening on OSDMonitor::update_from_paxos()...
- 05:32 PM Revision 9cdc60af (ceph): ceph_manager: use new ceph tell mon.* syntax
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:17 PM Revision a2b2f39b (ceph): librados: add tests for too-large objects
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:14 PM Revision 4a1eb3c8 (ceph): osd: fix types for size checks
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:42 PM Revision 2be3c8dd (ceph): remove RELEASE_CHECKLIST
- This ancient document has long since been replaced by
doc/dev/release-process.rst.
Signed-off-by: Sage Weil <sage@in... - 04:40 PM Revision f1b6bd79 (ceph): osd: EINVAL from truncate causes osd to crash
- Maximum object size is 100GB configurable with osd_max_object_size
Error EFBIG if attempt to WRITE/WRITEFULL/TRUNCATE... - 03:44 PM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- sandon put wheezy on these mira for us to test this locally: mira09[456]
- 03:04 PM devops Bug #5363 (Resolved): specfile: ceph does not start on reboot
- testing fix
- 02:54 PM rgw Bug #5347 (Fix Under Review): rgw: bucket marker should include original zone name
- 11:00 AM rgw Bug #5347 (Resolved): rgw: bucket marker should include original zone name
- To avoid marker collisions
- 02:41 PM rgw Bug #5362 (Resolved): rgw: failure when listing objects with prefix that starts with underscore
- 02:40 PM Bug #5062 (Can't reproduce): mon: 0.61.2 asserts on AuthMonitor during monitor start
- 02:39 PM devops Feature #5361 (Resolved): ceph-all should start after networking bug before runlevel [2345]
- just in case other system services rely on it being up.
- 02:38 PM devops Bug #5248 (Resolved): upstart: ceph-all job is starting too soon
- hmm opening a separate bug for the 'start earlier than this' part.
- 12:39 PM devops Bug #5248: upstart: ceph-all job is starting too soon
- changing this to runlevel [2345] for now.
- 02:38 PM devops Feature #3302 (Resolved): ceph-disk: activate-journal, and matching udev rule
- 02:23 PM devops Feature #3302: ceph-disk: activate-journal, and matching udev rule
- commit:a2a78e8d16db0a71b13fc15457abc5fe0091c84c
- 02:18 PM devops Bug #5189 (Resolved): ceph-deploy disk prepare fails silently
- this is now working with the fixes from #4984.
- 02:14 PM devops Bug #4984 (Resolved): ceph_deploy: osd create succeeds with an error message (partprobe returns e...
- woot! tested and backported to cuttlefish!
still issues on reboot with wheezy... #5194 - 01:08 PM Bug #5326 (Resolved): mon: osd crush add ... comamdn broken
- commit:9a7ed0b3f8df5bd74133f216bad61ae71eab0816, tho this actual error was a problem with the ceph cli sometime in te...
- 12:50 PM CephFS Bug #5360 (Rejected): ceph-fuse: failing smbtorture tests
- We're failing the maxfid test when samba is backed by a ceph-fuse mount. It seems to be an inconsistent (this is the ...
- 11:39 AM devops Bug #5359 (Resolved): ceph-deploy: install and purge commands on rhel sometimes errors out though...
- install command on rhel platform errors out though the command is successful and ceph is installed,
the error mess... - 11:09 AM rgw Feature #5358 (Resolved): rgw: RESTful api for intra-region copy state
- 11:08 AM rgw Bug #5357 (Resolved): rgw: set and retrieve intra-region copy operation state
- 11:07 AM rgw Feature #5356 (Rejected): rgw: RESTful api for bucket upstream zone + marker info
- 11:07 AM rgw Feature #5355 (Rejected): rgw: get and set bucket upstream zone + marker info
- 11:06 AM rgw Feature #5354 (Resolved): rgw: intra-region object copy should also set mtime on object
- 11:05 AM rgw Feature #5353 (Resolved): rgw: metadata put should apply mtime if set
- 11:05 AM rgw Feature #5352 (Resolved): rgw: metadata get should also dump mtime
- 11:04 AM rgw Bug #5351 (Resolved): rgw: make sure wip-rgw-geo passes gitbuilder
- 11:03 AM rgw Feature #5350 (New): rgw: copy object metadata should include omap data for object
- That's needed multipart head objects copy
- 10:56 AM devops Bug #5339: ceph-deploy suite failures, 'insufficient osds'
- changing the priority as this has nothing to do with ceph-deploy,
leaving it in this state until the nightlies succ... - 10:18 AM Bug #5252 (Resolved): osd: EINVAL from truncate causes osd to crash
- commit:f1b6bd7988ab964c9167eff7bea51a49573f5175
- 08:50 AM rgw Bug #5346 (Resolved): rgw: invalid read from RGWFormatter_Plain::write_data
- ubuntu@teuthology:/a/teuthology-2013-06-14_01:00:36-rgw-master-testing-basic/35856$ zless ./remote/ubuntu@plana63.fro...
- 08:35 AM devops Bug #5345 (Resolved): ceph-disk: handle less common device names
- /dev/sdaa*
/dev/cciss/c0d0p1
etc. - 08:21 AM rgw Bug #5344 (Resolved): rgw: make list of bucket placement pools index configurable
- The object containing the list of placement pools is hard coded, make it configurable (through ceph.conf).
- 05:48 AM Revision 8730db19 (ceph): rados: fix up for parallel work
- - use a separate pool for each client
- create pool at start, destroy pool at end
- use all clients, if not explicitl... - 05:08 AM Revision bcfbd0a3 (ceph): ceph_test_rados: add --pool <name> arg
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:59 AM Revision 7ec64db4 (ceph): rgw: pass original object attrs through extra request data
- introduce a new mechanism that sends extra data with object
info, and use it to encode source object metadata.
Signe... - 04:33 AM Revision 9b66f1aa (ceph): Merge remote-tracking branch 'gh/next'
- 02:37 AM Revision c672b777 (ceph): Merge pull request #362 from ceph/wip-4984
- ceph-disk: udev/partprobe redo, zap command, activate-journal command
- 01:13 AM Revision 02599c43 (ceph): ceph-fuse: fix uninitialized variable
- There is a delete call in the out_mc_start_failed path.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:01 AM Revision 10ba60cd (ceph): ceph-disk: add 'zap' command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:01 AM Revision 8b3b59e0 (ceph): ceph-disk: call partprobe outside of the prepare lock; drop udevadm settle
- After we change the final partition type, sgdisk may or may not trigger a
udev event, depending on how well udev is b... - 01:01 AM Revision a2a78e8d (ceph): ceph-disk: implement 'activate-journal'
- Activate an osd via its journal device. udev populates its symlinks and
triggers events in an order that is not rela... - 12:47 AM Revision 71402a5d (ceph): Merge pull request #363 from dmick/wip-cli-help
- Reviewed-by: Sage Weil <sage@inktank.com>
- 12:40 AM Revision 06f0b724 (ceph): ceph.in: allow args with -h to limit help to cmds that match partially
- Enables "ceph -h pg" to see just the pg commands
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:38 AM Revision 6ebfd3c9 (ceph): ceph.in: better global description of tool
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:38 AM Revision 821b203c (ceph): ceph.in: less verbosity on error
- Only show 'did you mean?' when in verbose mode
Only show first ten closest matches on error
Signed-off-by: Dan Mick ... - 12:38 AM Revision 99bd5c8f (ceph): librados: add missing #include
- librados/librados.cc: In function 'int rados_mon_command_target(void*, const char*, const char**, size_t, const char*...
- 12:13 AM Revision 0e303865 (ceph): adding a newline to auth key data
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
06/13/2013
- 11:39 PM Revision 93505bb3 (ceph): librados: wait for osdmap for commands that need it
- In commit 7e1cf87b5158c870e2a118ed6d316be8cb9818ce we stopped waiting for
the osdmap on start because the Objecter wi... - 11:38 PM Revision f6a864d0 (ceph): rules: Don't disable tcmalloc on ARM (and other non-intel)
- Fixes #5342
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 11:27 PM Revision 662fd9ec (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 11:26 PM Revision e1daa169 (ceph): modified ceph-deploy to throw appropriate exceptions
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:21 PM Revision 763432a3 (ceph): Merge pull request #356 from ceph/wip-leaks
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 11:15 PM Revision 95aa2e8d (ceph): Merge branch 'wip-objecter' into next
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 11:12 PM Revision 5fb0444c (ceph): Update adminops.rst add capabilities
- Added the necessary user capabilities required for each API call.
Signed-off-by: Adam Twardowski adam.twardowski@gma... - 11:01 PM Revision 2bda9db1 (ceph): osdc/Objecter: dump command ops
- Dump command_ops along with everything else.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:57 PM Revision 6e73d999 (ceph): osdc/Objecter: ping osds for which we have pending commands
- As with ops and linger_ops, this ensures we detect connection resets.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:56 PM Revision e4f9dce7 (ceph): ceph.in: refuse 'ceph <type> tell' commands; suggest 'ceph tell <type>'
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 10:30 PM Revision a6876ad7 (ceph): ceph.in: argparsing cleanup: suppress --completion, add help
- Options -v, --verbose, --concise didn't have helpstrings
Option --completion doesn't quite work yet, and should be hi... - 10:17 PM Revision 392e86fb (ceph): Merge remote-tracking branch 'gh/next'
- 10:16 PM Revision 68a91995 (ceph): osdc/Objecter: kick command ops on osd con resets
- Resend osd/pg commands on the OSDSession, just as we do with other request
types.
Signed-off-by: Sage Weil <sage@ink... - 10:16 PM Revision db7d1210 (ceph): osdc/Objecter: add perfcounters for commands
- This matches the other counters we maintain for other kinds of ops.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:54 PM Revision 05f634cb (ceph): added upgrade tasks for cuttlefish to next and bobtail to cuttlefish to...
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:51 PM Revision f005204f (ceph): stop stripping leading \n from osd commands
- leaving them in for mon command, but not for any good reason.
- 09:42 PM Revision 9a7ed0b3 (ceph): mon: fix idempotency of 'osd crush add'
- If we add an item that already exists in particular position, we should
update instead of inserting it; the CrushWrap... - 09:42 PM Revision 7e1cf87b (ceph): librados: do not wait for osdmap on start
- If we abort while waiting, we incorrect clean up (we switch the state value
incorrectly, and also fail to clean up th... - 09:09 PM Revision 51dae8ad (ceph): doc: Updated with glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:50 PM Revision e1d41901 (ceph): adding iogen.sh
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 07:43 PM CephFS Bug #5333: mds: segfault in MDLog::standby_trim_segments
- I think it's an old race. The standby MDS gets the pos of journal head, then reads the corresponding journal object. ...
- 02:02 PM CephFS Bug #5333: mds: segfault in MDLog::standby_trim_segments
- I see that Yan changed one line in this function recently (which shouldn't have had any impact), but other than that ...
- 06:27 PM Revision 35ea1639 (ceph): mon/MonmapMonitor: remove unused label
- mon/MonmapMonitor.cc: In member function 'bool MonmapMonitor::preprocess_command(MMonCommand*)':
mon/MonmapMonitor.cc... - 06:27 PM Revision 987f175f (ceph): mon/MonCap: bootstrap-* need to subscribe to osdmap, monmap
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:53 PM Revision ea6880f8 (ceph): msg/DispatchQueue: do not discard queued events on stop
- When the shutdown/stop flag is set, continue to work through the queue.
Process events, but discard messages. This a... - 05:53 PM Revision 597e4398 (ceph): msgr: queue reset when marking down pipes on shutdown
- This lets the callbacks clean up ref cycles.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:53 PM Revision 962d1187 (ceph): mon/MonClient: mark_down connection on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:53 PM Revision 0193f885 (ceph): mon/MonClient: mark_down during get_monmap_privately() shutdown
- We explicitly mark_down() and clear cur_con when shutting down; do the same
for get_monmap_privately() to ensure that... - 05:52 PM Revision 77db175c (ceph): mon/MonClient: tear down version requests on shutdown
- Make sure all callers can handle ECANCELED.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:52 PM Revision e96c0cee (ceph): msgr: use ConnectionRef throughout
- Make RefCountedObject a private parent of Connection so that users are
forced to use ConnectionRef whenever reference... - 05:52 PM Revision eea73ab8 (ceph): msg/Pipe: reset replaced pipes
- This gives the ms_handle_reset call a chance to clean up (for example, by
breaking a con->priv <-> session reference ... - 05:52 PM Revision 26e16c00 (ceph): msg/Pipe: include con reef in debug prestring
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision de64bc50 (ceph): msgr: queue reset exactly once on any connection
- Use the atomic pipe link removal as a signal that we are the one failing
the con and use that to queue the reset even... - 05:52 PM Revision cd1c289b (ceph): messages/MMonSync: initialize crc in ctor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision d172c332 (ceph): osd/ReplicatedPG: don't leak Session refs in do_osd_op_effects()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision b56c9654 (ceph): osd: do not leak MOSDPings on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 449bcd6f (ceph): osd: close classes on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 99172c3c (ceph): osd: do not leak HeartbeatSession on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 6630462a (ceph): osd: break con <-> session cycle on reset
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 652c5996 (ceph): mon: shut down Paxos on shutdown
- This cleans up the completions for any paxos waiters.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:52 PM Revision c112fc8e (ceph): mon: add is_shutdown() state helper/accessor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 2818a446 (ceph): mon/PaxosService: discard messages during shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 991d07ac (ceph): vstart.sh: put exports at top
- Where I can 'head vstart.sh' to find them quickly.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:46 PM Revision a3fe2dc4 (ceph): PendingReleaseNotes: notes on CLI changes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:41 PM devops Bug #5339: ceph-deploy suite failures, 'insufficient osds'
- modified ceph-deploy task to throw appropriate exceptions in case of failures.
most of the ceph-deploy tests have ... - 10:48 AM devops Bug #5339 (Resolved): ceph-deploy suite failures, 'insufficient osds'
- The cluster is NOT operational due to insufficient OSDs
- 05:21 PM Revision 314d9c3f (ceph): PendingReleaseNotes: cli changes, and ceph tell ...
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:19 PM Revision cb57c41c (ceph): doc/release-notes: add missed notes for 0.63 and 0.64
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:37 PM devops Bug #5342 (Resolved): Make tcmalloc default on ARM
- tcmalloc usage needs to be enabled on ARM. While packages are not available on all platforms yet, the locally compil...
- 04:27 PM Revision 3abd2d8b (ceph): Merge branch 'wip-tell' into next
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
- 04:26 PM Revision 8adf88a2 (ceph): ceph: add support for 'tell mon.X ...'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:26 PM Revision 6160e503 (ceph): mon: remove support for 'mon tell ...' and 'osd tell ...'
- It doesn't work. The commands the ceph cli sends are vector<string>, and
the mon expects json.
Leave the MDS on in ... - 04:26 PM Revision 420e02e8 (ceph): librados: new rados_mon_command_target to talk to a specific monitor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:03 PM devops Feature #3302 (Fix Under Review): ceph-disk: activate-journal, and matching udev rule
- this was causing unreliable ubuntu activation, at least in my case
- 03:23 PM Revision 47b1e6d6 (ceph): Merge pull request #360 from dachary/master
- add apt-get update to installation instructions
- 03:01 PM rgw Feature #5341 (Resolved): rgw: keep state for cross-rgw copy operations
- Need to implement a new class that'd index the data.
- 01:52 PM devops Bug #5283: Ceph-deploy can't handle /dev/disk/by-* device paths
- With the by-id path which does not have embedded colons:...
- 12:52 PM devops Bug #5283: Ceph-deploy can't handle /dev/disk/by-* device paths
- glowell@gary-ubuntu-01:~/ceph-deploy$ ./ceph-deploy osd create gary-ubuntu-01:/dev/disk/by-path/pci-0000:00:07.0-scsi...
- 12:28 PM devops Bug #5309 (Closed): ceph-deploy mon create fails to start monitor damon
- Issue is no longer occurring after recent commits to ceph-deploy. Not sure which one fixed it but around 10 June.
- 10:49 AM devops Bug #4984 (In Progress): ceph_deploy: osd create succeeds with an error message (partprobe return...
- 10:49 AM Bug #5329 (Resolved): ceph osd tell * injectargs broken
- commit:3abd2d8bc94ab77364345e3f830cfb83124df31d
- 10:49 AM Bug #5340 (Resolved): Bad arguments to zero will cause OSD to crash
- Check offset/len arguments for zero operation so that later fallocate() error doesn't cause OSD to crash.
- 10:41 AM devops Bug #5338 (Resolved): need rpm packages built for libapache-mod-fastcgi
- We currently have libapache-mod-fastcgi packages built for debs. It would be nice to have them built for rpms as well...
- 10:23 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Hi Sage,
this was a clean reboot of the cluster node.
As the filesystems have not been mounted automatically no... - 09:16 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- I see it starting osd.5 and osd.2:...
- 08:40 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Hi,
attached is /var/log/syslog after booting the machine with udev debug level logging.
The filesystems have n... - 10:06 AM Bug #5227 (Need More Info): ARM set up: rados test failed
- This sure looks a lot like #4879 which would have been fixed by 0.61. I thought I had grabbed the stores and the logs...
- 09:37 AM devops Bug #5334: ceph-deploy: "modules not installed"
- Update. I was able to get it installed correctly with the `ceph-deploy-1.0-0.noarch.rpm` package, but my understandin...
- 09:28 AM Bug #5301: mon: leveldb crash in tcmalloc
- Okay, regarding the crash, although I've been unable to figure out what or who (us or leveldb) may be causing it, the...
- 08:28 AM devops Bug #5189: ceph-deploy disk prepare fails silently
- Hi Sage,
We are currently testing with some Debian wheezy VMs on a VMware ESXi host.
root@ceph01-test:~# lsb_re... - 08:02 AM Bug #5336 (Can't reproduce): osd crash triggered by 'rbd rm ...'
- Reported by Florian Wiessner on ML
looks like a stall in the op_tp.. requested detailed logs. - 07:48 AM Bug #5256: Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- Okay, here's what is the likely order of events in this case:
* the monitor was converting when it was killed for ... - 06:59 AM Revision cdd11ea6 (ceph): rgw: a few fixes to copy object across region
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:57 AM Revision 169c5de4 (ceph): add apt-get update to installation instructions
- Without apt-get update the repository added to the sources.list is not taken into consideration and an older version ...
- 06:19 AM Revision 165926bd (ceph): rgw: move most of object put processors implementation
- move code from rgw_op.cc to rgw_rados.cc, so that we could
use it in the lower layer.
Signed-off-by: Yehuda Sadeh <y... - 06:08 AM Revision 0b491e9a (ceph): rgw: separate req_state from object put processors
- At least, for most of them. We'll move this code to rgw_rados.cc,
and we don't want it to have req_state.
Signed-off... - 05:39 AM Revision bcdd4755 (ceph): rgw: organize get_obj handling for copy a bit different
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:26 AM Revision 5fa45f4e (ceph): Update README dependency lists
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 05:22 AM Revision f86b4e7a (ceph): ceph-disk: extra dash in error message
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:56 AM Revision c618cf93 (ceph): OSDMonitor: osd id when id already exists needs to come to stdout too
- Found by qa/workunits/mon/osd.sh
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank... - 04:56 AM Revision ff280b62 (ceph): Clean up CrushWrapper methods that take string: no c_str() necessary
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 04:56 AM Revision a3767010 (ceph): ceph, mon/OSDMonitor: fix up osd crush commands for <osd.N> or <N>
- The new parsing code had been trying to allow flexibility for the
'old form' commands (where id could be different fr... - 04:47 AM Revision e9689ac6 (ceph): config: fix run_dir typo
- From 654299108bfb11e7dce45f54946d1505f71d2de8.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:44 AM Revision d0e65759 (ceph): ceph: implement 'ceph tell osd.* ...'
- Send the command to each target. Do this in series, for now. Error out if
any one fails.
Later, we should do them ... - 04:44 AM Revision d1b83ff4 (ceph): mon/MonClient: send commands to a specific monitor
- This implementation is limited: we direct our command by reopening
a session with the specific monitor. If there is ... - 04:29 AM Revision 6a6025f2 (ceph): rgw: generate read request if source rgw is remote
- in a copy operation
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:26 AM Revision e72e8a30 (ceph): Merge remote-tracking branch 'gh/next'
- 04:24 AM Revision 8c913f14 (ceph): Merge pull request #351 from ceph/wip-var-run
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
- 04:23 AM Revision 3e707da4 (ceph): vstart.sh: set run_dir to out
- This avoids annoying errors about creating /var/run/ceph from
init-ceph.
Fixes: #4036
Signed-off-by: Sage Weil <sage... - 04:21 AM Revision b0b5b1b3 (ceph): rbd image_read.sh: wait for rbd sysfs files to appear
- Poll until they are available for chmoding.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Sage W... - 04:03 AM Revision 8badb904 (ceph): move powercycle tests into a separate suite
- We may not want to run these nightly, or on the same hardware, and we want
to separate out core rados problems from p... - 01:24 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Argh. I spoke too soon. We just had another crash this morning while deleting the benchmark pool. Using the staticall...
- 01:13 AM Revision 8808ca57 (ceph): osdc/Objecter: fix handling for osd_command dne/down cases
- Generalize the map check machinery that the pool dne check uses to also
get the latest map for OSD down/dne checks. ... - 12:47 AM Revision 65429910 (ceph): global: create /var/run/ceph on daemon startup
- This handles cases where the daemon is started without the benefit of
sysvinit or upstart (as with teuthology or ceph... - 12:47 AM Revision 1154b2ab (ceph): init-ceph: look to ceph.conf instead of hard-coding /var/run/ceph
- It could be elsewhere!
Signed-off-by: Sage Weil <sage@inktank.com> - 12:13 AM Revision 11d5c7a2 (ceph): ceph: only use readline when in interactive mode
- A mere
import readline
line is dumping this to stdout on CentOS 6.3:
00000000 1b 5b 3f 31 30 33 34 68 .[?103... - 12:13 AM Revision 862148d5 (ceph): mon: fix read of format_version out of leveldb
- The get_version(string, string) is the wrong method; it combines the two
args into a key that is nested inside prefix... - 12:05 AM Revision 18f2fcd2 (ceph): Merge branch 'wip-RhelFix-wusui'
06/12/2013
- 10:29 PM Revision 1c77be0c (ceph): doc/release-notes: v0.63 and v0.64 notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:00 PM Revision 35ac835f (ceph): Merge branch 'next'
- 09:54 PM Revision b3b0f035 (ceph): ceph: filter out empty lines from osdids()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:53 PM Revision edba9863 (ceph): ceph: accept osd.* as a valid name
- This will be used for 'ceph tell osd.* ...'
Signed-off-by: Sage Weil <sage@inktank.com> - 09:05 PM Revision e5184ea9 (ceph): ceph: make life easier on developers by handling in-tree runs
- If <path-to-ceph> contains pybind and .libs:
- prepend <path-to-ceph>/pybind to PYTHONPATH
- append <path-to-ceph>/.l... - 09:00 PM Revision 701943a2 (ceph): qa/workunits/cephtool/test.sh: look for 'ceph log' via -w, not in log file
- 'ceph-conf ...' doesn't give you final/default values, only what is in the
conf file. Use -w output to test this ins... - 09:00 PM Revision b70f5658 (ceph): ceph: flush stdout on watch print
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:50 PM Revision b89b6cee (ceph): Merge pull request #357 from atwardowski/patch-1
- Usage log and ops log are disabled by defaults since 0.56
- 08:48 PM Revision 299f6a66 (ceph): Usage log and ops log are disabled by defaults since 0.56
- http://ceph.com/docs/next/release-notes/#v0-56-bobtail
- 08:39 PM Revision de172383 (ceph): mon: fix 'pg dump_stuck' stuckops type
- It's a list.
Fixes: #5332
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 08:37 PM rbd Feature #5335 (New): qa: test that kernel rbd and librbd can read images written by each other
- This test would have caught an issue with format 2 object names being different in librbd and the kernel driver.
- 08:31 PM Revision b284e25f (ceph): Merge remote-tracking branch 'gh/wip_5238'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 08:26 PM Revision afa16b48 (ceph): qa: multiple_rsync.sh: more output
- Trying to track down this failure:
2013-06-12T06:11:13.430 INFO:teuthology.task.workunit.client.0.err:+ rsync -auv -... - 06:17 PM Bug #5329 (Fix Under Review): ceph osd tell * injectargs broken
- 12:29 PM Bug #5329 (Resolved): ceph osd tell * injectargs broken
- ...
- 06:13 PM Bug #5331 (Resolved): objecter: osd_command doesn't handle dne/down osd properly
- commit:8808ca57c652502d9cf803b0dc53673ca9dd62af
- 01:02 PM Bug #5331 (Resolved): objecter: osd_command doesn't handle dne/down osd properly
- we return an error but don't trigger the callback or clean up...
- 05:51 PM devops Bug #5259 (Duplicate): osd create command fails inconsistently on ubuntu
- i think we should call this a dup of the other bug.. this is all about udev vs partprobe vs udevadm settle races. se...
- 04:54 PM Revision 42e06c12 (ceph): v0.64
- 04:43 PM Revision 68b5fa9b (ceph): ceph-fuse: older libfuses don't support FUSE_IOCTL_COMPAT
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 04:13 PM devops Bug #5334 (Resolved): ceph-deploy: "modules not installed"
- Using cuttlefish RPM install for CentoOS 6.4. Ceph-deploy is installed on all the nodes. I get the following:
<pre... - 03:40 PM Revision 1577e203 (ceph): ceph-create-keys: Make sure directories for admin and bootstrap keys exist
- Signed-off-by: Peter Wienemann <wienemann@physik.uni-bonn.de>
- 02:00 PM Bug #5327 (Resolved): cephtool/test.sh fails
- commit:701943a27857fcad7fbb405cf95a59c945fea815
- 11:44 AM Bug #5327 (Resolved): cephtool/test.sh fails
- ...
- 01:49 PM Bug #5238 (Pending Backport): osd: slow recovery (uselessly dirtying pg logs during peering)
- 01:46 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Maybe something different i've this one:
http://tracker.ceph.com/issues/5232
and it makes a HUGE difference regar... - 01:44 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- For what it's worth, I also tried it (wip_5238_cuttlefish specifically) per Sam's suggestion while troubleshooting #5...
- 01:33 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- we are going to tset it a bit more in master before putting it in teh cuttlefish branch. good to know this is helpin...
- 01:28 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- This one is missing in upstream/cuttlefish ? It helps a lot.
- 01:39 PM Bug #5332 (Resolved): boost::get: key stuckops is not type std::vector<std::string, std::allocato...
- commit:de1723834cf2cfe51cc991ece1b53624ff56d7d5
- 01:05 PM Bug #5332 (Resolved): boost::get: key stuckops is not type std::vector<std::string, std::allocato...
- 2013-06-12T02:25:15.786 INFO:teuthology.task.ceph.mon.a.err:2013-06-12 02:26:06.734468 7f2e3ef1e700 -1 bad boost::get...
- 01:23 PM CephFS Bug #5333 (Resolved): mds: segfault in MDLog::standby_trim_segments
- ...
- 12:35 PM Bug #5330 (Resolved): ceph daemon <name> ... broken
- it uses ceph-conf to get admin_socket, but taht doesn't work. this does:
ubuntu@plana38:~$ ceph-osd -n osd.0 --s... - 12:23 PM rbd Feature #5168: openstack: cinder: rbd as a backup target
- https://blueprints.launchpad.net/cinder/+spec/cinder-backup-to-ceph
- 12:23 PM rbd Feature #5167: openstack: cinder: differential backups
- https://blueprints.launchpad.net/cinder/+spec/cinder-backup-to-ceph
- 11:42 AM Bug #5326 (Resolved): mon: osd crush add ... comamdn broken
- ...
- 10:21 AM devops Bug #4984: ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- it should have been wip-4984 :)
- 09:33 AM Bug #5312: Skip EXT4StoreTest._detect_fs test if DISK or MOUNTPOINT environment variables not set
- 1577e203f08c3f94c36fd128dda14e8bceeca7a9
- 09:32 AM Bug #5311 (Resolved): Existence of parent directories for admin and bootstrap keys in ceph-create...
- 08:18 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Ok, I tried the ubuntu leveldb package but in ubuntu leveldb is only built as a static library. So what I did was to ...
- 06:10 AM CephFS Bug #5290: mds: crash whilst trying to reconnect
- Hi Zheng,
Is this what you mean? - 02:34 AM Revision d3960967 (ceph): valgrind: make leveldb thread suppression more general
- The thread can get created from a range of callers; ignore them all.
- 01:51 AM Revision 95434d16 (ceph): rgw: propagate mtime from remote rgw on copy
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
06/11/2013
- 11:50 PM Revision 8f29b3f9 (ceph): Use install -d for /var/log/ceph.
- Additional fix needed for #4946
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 11:45 PM Revision 256afa07 (ceph): store_test: create_collection prior to split
- Fixes: #5310
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com> - 11:30 PM Revision 1a9415a0 (ceph): mon: adjust trim defaults
- User testing has shown that smaller values yield better results; see #4917.
Jim's testing has had good results with e... - 11:15 PM Revision 60e4bb0a (ceph): client: set issue_seq (not seq) in cap release
- We regularly have been observing a stall where the MDS is blocked waiting
for a cap revocation (Ls, in our case) and ... - 10:32 PM Revision 5f0007e6 (ceph): doc: Reworked the landing page.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:46 PM Revision dc6cadc3 (ceph): doc: Added a hostname resolution section for local host execution.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:46 PM Revision f6c51b48 (ceph): doc: Added some tips and re-organized to simplify the process.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:14 PM Revision ae74abda (ceph): Fix capitalization of CentOS
- Fixes: #5313
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 08:56 PM Revision 9b012e23 (ceph): client: set issue_seq (not seq) in cap release
- We regularly have been observing a stall where the MDS is blocked waiting
for a cap revocation (Ls, in our case) and ... - 08:54 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- We need to gather some udev logs to diagnose this... can you change teh level in /etc/udev/udev.conf to 'debug', rest...
- 08:50 PM Bug #4698 (Won't Fix): osd suicide timed out after 150
- this was an ext4 bug:...
- 08:45 PM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- Do we have any logs or recent occurrences of this bug to go on, or mon logs of it happening?
If not, I think this ... - 08:43 PM devops Bug #5189 (Need More Info): ceph-deploy disk prepare fails silently
- Hi Robert-
Are you still having this problem? Can you share a bit more information about the environment? What d... - 07:20 PM rgw Bug #5324 (Resolved): radosgw-admin --help missing the --shard-id option
- The new 'mdlog trim' call requires a --shard-id option be specified but that option is not listed in the --help output.
- 07:12 PM Revision c7fb7a3f (ceph): doc: Added some Java S3 API troubleshooting entries.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:11 PM Revision 6c557d56 (ceph): doc: Added install ceph-common instruction.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:11 PM Revision 5543f19c (ceph): doc: Added install ceph-common instruction.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:10 PM Revision 3f3ad61f (ceph): doc: Fixed :term" syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:32 PM devops Bug #4984: ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- pushed wip-4948. works ok on centos/rhel, but we should verify it also behaves on ubuntu and debian.
- 06:19 PM rgw Bug #5323: trim data log lists dates as optional, enforced as required in the current code
- I believe that the offending line is in ceph/src/rgw/rgw_rest_log.cc in the function RGWOp_MDLog_Delete::execute().
... - 06:17 PM rgw Bug #5323 (Resolved): trim data log lists dates as optional, enforced as required in the current ...
- In the wip-rgw-geo branch, the
DELETE /admin/log?id=<shard id>
call lists start-time and end-time as optional. How... - 05:43 PM Revision 00743d50 (ceph): rgw: propagate error from remote gateway when copying object
- Also make sure that we don't continue iterating locally through
the object.
Signed-off-by: Yehuda Sadeh <yehuda@inkt... - 05:41 PM Linux kernel client Bug #4854 (Rejected): read more than they should
- this is due to readahead. readahead can be disabled by posix_fadvise(2)
- 04:49 PM Bug #5310 (Resolved): StoreTest.ColSplitTest1 hits assert in _split_collection()
- 11:13 AM Bug #5310 (Resolved): StoreTest.ColSplitTest1 hits assert in _split_collection()
- $ ./ceph_test_filestore
...
[ RUN ] StoreTest.ColSplitTest1
2013-06-11 11:06:49.332610 7f38942e4780 1 filest... - 04:30 PM Bug #5176 (Resolved): leveldb: Compaction makes things time-out yielding spurious elections
- Sylvain Munaut wrote:
> I can try to do this tomorrow.
>
> But in the mean time I played with the paxos trimming ... - 11:16 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- I can try to do this tomorrow.
But in the mean time I played with the paxos trimming values and made it go away.
... - 08:12 AM Bug #5176 (Need More Info): leveldb: Compaction makes things time-out yielding spurious elections
- Can you capture a debug mon = 20, debug paxos = 20, debug ms = 1 log that includes an election and send us the set of...
- 12:59 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- fyi, I just upgraded from wip-5176 to 0.61.3 and those spurious elections are back.
- 03:54 PM Revision ae522291 (ceph): osd: skip mark-me-down message if osd is not up
- Fixes crash when the OSD has not successfully booted and gets a
SIGINT or SIGTERM.
Signed-off-by: Sage Weil <sage@in... - 03:43 PM Bug #5320 (Resolved): osd/ReplicatedPG.cc: 4753: FAILED assert(!pg_log.get_missing().is_missing(s...
- -901> 2013-06-11 14:02:22.138530 7f9bd4913700 5 filestore(/var/lib/ceph/osd/ceph-1) _do_op 0x1d4bfa0 seq 68202 osr...
- 03:36 PM Revision 77e7bdbb (ceph): upgrade: set workunit branch before and after upgrade
- 03:33 PM Revision 662cafaa (ceph): upgrade/fs: remove unused file
- 03:25 PM Revision 0948624f (ceph): ceph-create-keys: Remove unused caps parameter on bootstrap_key()
- The caps parameter was removed except for one place.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 02:56 PM Linux kernel client Bug #4614: Root cephfs does not mount at boot on Ubuntu 12.04
- I can confirm this problem occurs on Ubuntu 12.04 as well.
- 01:46 PM Bug #5311: Existence of parent directories for admin and bootstrap keys in ceph-create-keys not c...
- Yes, the packages do it right after the installation. But this does not mean that these dirs still exist when you run...
- 01:08 PM Bug #5311: Existence of parent directories for admin and bootstrap keys in ceph-create-keys not c...
- Aren't these directories supposed to be installed by the packages? *Something* is doing it in the normal case or thes...
- 01:06 PM Bug #5311: Existence of parent directories for admin and bootstrap keys in ceph-create-keys not c...
- A fix is available as pull request #355.
- 12:56 PM Bug #5311 (Resolved): Existence of parent directories for admin and bootstrap keys in ceph-create...
- The ceph-create-key script does not check the existence of the parent directories in which the admin and the bootstra...
- 01:32 PM Bug #5312 (Resolved): Skip EXT4StoreTest._detect_fs test if DISK or MOUNTPOINT environment variab...
- I disabled the ColSplitTest1/ColSplitTest2 tests (see bug #5310).
Currently, this test case just crashes with uncl... - 10:57 AM devops Bug #5309 (Closed): ceph-deploy mon create fails to start monitor damon
- This is with current master: 0.63-572-g0948624-1
It appears that somewhere between ceph-deploy and the ceph-mon... - 10:53 AM Bug #5307 (Resolved): ceph_test_filestore crashes
- Needs --filestore-xattr-use-omap=true
- 10:33 AM Bug #5307 (Resolved): ceph_test_filestore crashes
- $ ./ceph_test_filestore
[==========] Running 11 tests from 2 test cases.
[----------] Global test environment set-u... - 10:53 AM devops Bug #5300: ceph-deploy purgedata should give warning if ceph still installed
- I'll retest, I might not have been paying attention to purge vs purge data. In any event the test system was left in...
- 09:37 AM devops Bug #5300: ceph-deploy purgedata should give warning if ceph still installed
- purge is supposed to remove the package files *and* any config files...
- 10:53 AM Bug #5269 (Duplicate): osd: EEXIST on mkcoll
- This is probably the same thing as 5270.
- 10:52 AM Bug #5240 (Resolved): run_seed_to_range failed, probably fdcache
- 10:27 AM devops Bug #5306 (Can't reproduce): Xen based OSDs fail to start ceph-osd process
- After a clean install and ceph-deploy prepare and activate the osd process is running on the node.
After a reboot th... - 10:26 AM Bug #5305 (Resolved): ceph-deploy gatherkeys fails (ceph-create-keys)
- When invoked with ceph-deploy ceph-create-keys fails silently and the only indication of a problem is that the subsqu...
- 10:21 AM Bug #5305 (Resolved): ceph-deploy gatherkeys fails (ceph-create-keys)
- glowell@gary-ubuntu-01:~/ceph-deploy$ sudo /usr/sbin/ceph-create-keys --cluster=ceph -i gary-ubuntu-01
INFO:ceph-cre... - 09:56 AM rgw Bug #5302: rest-bench breaks with XmlParseFailure
- what fastcgi module is being used here? Maybe try:
rgw print continue = false
int your ceph.conf. - 07:26 AM rgw Bug #5302 (Can't reproduce): rest-bench breaks with XmlParseFailure
- This was reported on the mailing list when trying to run rest-bench:...
- 09:39 AM devops Bug #5299: ceph-deploy fails with cryptic error message if expected directories not found
- /etc/ceph should be installed by the package.
did yo uby chance run purgedata without running purge first? that mi... - 09:36 AM Bug #5301 (New): mon: leveldb crash in tcmalloc
- 09:29 AM Bug #5301: mon: leveldb crash in tcmalloc
- Well I could try to reproduce but I am not going to do this because it is my production cluster. I have also experien...
- 08:21 AM Bug #5301: mon: leveldb crash in tcmalloc
- Hi-
The 3.8.y kernel is EOL, but I pushed a branch that has the patch that (I believe) fixes this problem: linux-3... - 06:10 AM Bug #5301 (Can't reproduce): mon: leveldb crash in tcmalloc
- Hello
I have replaced my crushmap:... - 08:55 AM CephFS Bug #5303 (Resolved): OSD segfaults on SIGINT
- This was a missed backport for an old fix. I pushed it to the cuttlefish branch and it will be included in .4. Thanks!
- 08:41 AM CephFS Bug #5303: OSD segfaults on SIGINT
- Without debugger:...
- 08:38 AM CephFS Bug #5303 (Resolved): OSD segfaults on SIGINT
- This is not the first time but interrupting the OSD with SIGINT (CTRL+C) causes a segmentation fault.
Cuttlefish 0... - 08:39 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Ah. Can you please try the ubuntu leveldb package and see if the problem persists? Thanks!
- 07:43 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- I just looked into LevelDB packaging in wheezy and precise. Again it seems that debian ships a newer version of Level...
- 01:06 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Yes, now we seem to have provoked two different errors. Both of them has happened at least twice each but on differen...
- 08:34 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- I think that this is what you want, if not, just let me know.
Jeff - 08:21 AM Bug #5292: mon: monitor crashing due to not being in the monmap (no monmap to be in)
- Can you share the monitor's logs with 'debug mon = 20' set?
- 07:19 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Removing the assert worked around the problem:...
- 06:32 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I noticed that resetting the MDS journal using ceph-mds -i 1 --reset-journal 0 -d hangs there....
- 06:22 AM Revision 4682636f (ceph): Merge branch 'next'
- 06:22 AM Revision 3f2017fb (ceph): osd: fix con -> session ref change after hb reset
- set_priv() expects to be given a reference to own; take one. This fixes
various crashes after we see a hb connection... - 04:59 AM Revision ea3efca3 (ceph): rgw: pass grant headers to target when writeing object
- When writing object to remote gateway.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:58 AM Revision da5e443c (ceph): rgw: head acls target can be quoted
- when passing x-amz-grant-* headers, the target (id, email,
group) may be quoted.
Signed-off-by: Yehuda Sadeh <yehuda... - 04:56 AM Revision a378c4d1 (ceph): common/admin_socket: fix leak of new m_getdescs_hook
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:56 AM Revision 6bab4253 (ceph): common/cmdparse: no need to use (and leak to) the heap
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 01:40 AM Fix #5232: osd: slow peering due to pg log rewrites
- This one misses cuttlefish for backport?
- 01:25 AM Revision 5c945cd1 (ceph): CrushWrapper: dump tunables along with crush map
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 01:09 AM Revision 0e0e896e (ceph): ceph: --keyring must be passed to parse_argv, which means not argparse
- If argparse gets its hands on it, it's not available for parse_argv()
and is therefore ignored.
Signed-off-by: Dan M... - 12:16 AM Revision 8190b439 (ceph): OSD: create collection in handle_pg_create before _create_lock_pg
- Fixes: #5270
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:06 AM Revision a741aa07 (ceph): mon: send "osd create" output to stdout; tests rely on it
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:06 AM Revision af92b9a4 (ceph): Objecter: fail osd_command if OSD is down
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
06/10/2013
- 11:34 PM Bug #5272: Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of existing cluster
- I'm afraid that as long as no one else encounters this issue I am not able to provide more detailed information. The ...
- 05:53 PM Bug #5272 (Need More Info): Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of exi...
- I went through a diff and there's nothing obvious between those two versions that could have caused these feature bit...
- 11:08 PM Revision 01944ab9 (ceph): Merge pull request #349 from dachary/wip-5213
- unit tests for PGLog::merge_log
Reviewed-by: Sam Just <sam.just@inktank.com> - 11:07 PM devops Bug #5283 (In Progress): Ceph-deploy can't handle /dev/disk/by-* device paths
- The fix for this will actually be in ceph-disk, ceph-deploy pretty much passes the device unmodified.
- 10:41 PM Revision 335185d3 (ceph): added support for rhel
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:28 PM CephFS Bug #5290: mds: crash whilst trying to reconnect
- looks like session map corruption.
Damien, please upload the session map. you can find where is it by "ceph osd ma... - 02:16 AM CephFS Bug #5290 (Can't reproduce): mds: crash whilst trying to reconnect
- Hi,
Recently I experienced an issue with the mds servers in my cluster, the cluster storage would be absolutely fi... - 10:15 PM devops Bug #5300 (Resolved): ceph-deploy purgedata should give warning if ceph still installed
- Purge will remove directores needed for continued operation. Probable need to issue a warning in this case since if ...
- 10:10 PM devops Bug #5299 (Won't Fix): ceph-deploy fails with cryptic error message if expected directories not f...
- In this case it's /etc/ceph
glowell@gary-ubuntu-01:~/ceph-deploy$ ./ceph-deploy mon create gary-ubuntu-01
Traceba... - 09:28 PM Revision 31676c59 (ceph): rgw: skeleton for obj copy across regions
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision 72cb5fd6 (ceph): rgw: bucket metadata, ignore ENOENT on put
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision 284f6a20 (ceph): rgw: format put request auth
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision 4849c8c1 (ceph): rgw: stream obj into http request
- still need to figure out curl handle polling, handle client
errors correctly.
Signed-off-by: Yehuda Sadeh <yehuda@in... - 09:28 PM Revision 6f6e425d (ceph): rgw: fix json decoding for swift keys
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision 2237086d (ceph): rgw: minor logging change
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision bf6b80c6 (ceph): rgw: fix logic related to operations on different region
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision be1d84db (ceph): rgw: link bucket to owner on metadata update
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision cbf860fc (ceph): rgw: don't send redirect if copy object has a local source
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision 566315c4 (ceph): rgw: don't busy wait for outgoing rest requests
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:28 PM Revision db0c250f (ceph): rgw: send meta headers with remote PUT request
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:10 PM Revision a3c11226 (ceph): teuthology-lock --summary: allow --machine-type=all
- Somehow this got lost; putting it back
Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit e4e... - 06:54 PM Revision f6c7c0cb (ceph): rgw: metadata lock/unlock implemented with test cases
- metadata lock/unlock implemented with test cases
split Post operations to Lock and Unlock operations, and
checking fo... - 06:34 PM Revision d1afc810 (ceph): RESTful APIs for data changes log implemented with test cases
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 05:51 PM RADOS Bug #5298 (New): mon: "setting" CRUSH tunables to their current values creates a map
- Maybe this is adding pointless churn, maybe it's blocking the user longer than necessary, or maybe it's a great way t...
- 05:45 PM Revision 0911e549 (ceph): ceph: ignore ceph-osd leaks for now :(
- 05:24 PM Bug #5297 (Resolved): Slow requests after restarting an OSD (post peering)
- On my Cuttlefish 0.61.3, when I restart an OSD, besides the effects of #5084, I see a bunch of "slow request" message...
- 05:22 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- Just for the record:
We did a troubleshooting/log collecting session with Sam last week. It seems that the issue i... - 05:17 PM Bug #5270 (Resolved): osd: crash in PG::peek_map_epoch()
- 02:06 AM Bug #5270: osd: crash in PG::peek_map_epoch()
- I've got the same error when some pginfo files have been lost due to XFS corruption. Removing pg collection helped to...
- 04:50 PM Revision 0fe4bc09 (ceph): Merge pull request #350 from ceph/wip-osd-scrub-chunk
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 04:50 PM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- any luck?
- 08:06 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Ok, all our OSD nodes are now running v0.61.3, but built --without-tcmalloc.
We'll try different workloads during ... - 04:46 PM Revision d034e17a (ceph): Merge branch 'wip-teuthVm-wusui'
- 04:24 PM devops Bug #5295 (Resolved): mon keyring path in mon.py not checked properly
- commit:dd9392023da4773c7006ec1fb86fee07a862d8f9
- 02:06 PM devops Bug #5295 (Resolved): mon keyring path in mon.py not checked properly
- In the file mon.py, line 37 ff., of the ceph-deploy code the mon keyring path is not checked properly. Prior to writi...
- 04:20 PM devops Bug #4916: ceph-deploy: mon create fails on bobtail branch in centos 6.3
- commit:96c001021e6dd06b43686de7040f78c484869344 fixes the mkdir -p thing. Does that fix the centos problem too?
- 01:48 PM devops Bug #4916: ceph-deploy: mon create fails on bobtail branch in centos 6.3
- I am having the same problem on Debian wheezy. After some debugging I found that the cause of the problem is in the f...
- 04:15 PM Subtask #5213: unit tests for src/osd/PGLog.{cc,h}
- "related thread":http://thread.gmane.org/gmane.comp.file-systems.ceph.devel/15499...
- 01:29 PM Bug #5294 (Closed): mon upgrade issue 0.61.2 -> 0.61.3
- This was reported on the mailing list by Nelson Jeppesen at Disney. Joao, any idea if we've seen anything else like ...
- 12:08 PM Revision 04e89a40 (ceph): unit tests for PGLog::merge_log
- The tests covers 100% of the LOC of merge_log. It is broken down
in 7 cases to enumerate all the situations it must a... - 12:08 PM Revision 8f141c45 (ceph): unit tests for PGLog::rewind_divergent_log
- The tests covers 100% of the LOC of rewind_divergent_log. There are
three situations :
* throw an assert because th... - 11:31 AM devops Documentation #5293 (Rejected): ceph-osd needs ulimit value to be set otherwise won't start
- I needed to add the following line to my /etc/security/limits.conf otherwise the osd didn't start up correctly and th...
- 11:24 AM Bug #5291: Bug with client naming for Cinder-Volume usage
- The defaults everywhere are client.admin. Perhaps you've got the CEPH_ARGS environment variable specifying --id volum...
- 02:42 AM Bug #5291 (Can't reproduce): Bug with client naming for Cinder-Volume usage
- Hello!
It seems there are bug with naming client for Cinder-Volume usage.
According to this documentation http://... - 09:42 AM CephFS Bug #5287 (Resolved): the permission of file in CephFS
- 06:53 AM rbd Bug #4446: librbd: crash from opensolaris vm
- I've upgraded to Cuttlefish and the newest Promox (KVM 1.4.1) and still have the same problem. The kvm command is:
... - 06:48 AM Bug #5292 (Resolved): mon: monitor crashing due to not being in the monmap (no monmap to be in)
- I run a 4 node CEPH cluster (all are currently running 0.61.3 - upgraded to cuttlefish a few weeks ago) and (3 nodes ...
- 04:29 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Sage Weil wrote:
> what happens if you do 'ceph-disk-active /dev/sdb1' (or whatever the xfs patition is)? what abou...
06/09/2013
- 05:26 AM Revision c41e6ff5 (ceph): valgrind: glibc/boost_thread leak suppressions
- 05:25 AM Revision 48f8d6e3 (ceph): ceph-fuse: create finisher threads after fork()
- The ObjectCacher and MonClient classes both instantiate Finisher
threads. We need to make sure they are created *aft... - 04:39 AM Revision 6ce23541 (ceph): messages/MMonProbe: fix uninit vars (again)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:38 AM Revision 10bfa835 (ceph): osdc/Objecter: clear osd session command ops xlist on close
- Clear the command ops list, just as we do the ops and linger_ops xlists.
This fixes a crash like this on shutdown:
2... - 04:38 AM Revision 81a786e9 (ceph): librados: fix pg command test
- Stat a bunch of (non-existent) random objects in the pool so ensure the
pg exists on the OSD before we assert that we... - 01:54 AM CephFS Bug #5289 (Can't reproduce): mds closing stale session
- Hi all,
I found a stale session in MDS.
$ceph -w
\ health HEALTH_OK
..................
.....................
06/08/2013
- 11:00 PM CephFS Support #5285 (Closed): cephfs give permission to write files
- dup #5287
- 10:37 PM CephFS Bug #5287: the permission of file in CephFS
- so far the only solution is chmod
- 07:55 PM CephFS Bug #5287: the permission of file in CephFS
- Zheng Yan wrote:
> The short answer is no better solution so far. If a given node can mount the FS, it can access to... - 06:24 PM CephFS Bug #5287: the permission of file in CephFS
- The short answer is no better solution so far. If a given node can mount the FS, it can access to the data pool direc...
- 01:43 AM CephFS Bug #5287 (Resolved): the permission of file in CephFS
- Hi all,
I used the CephFS v0.56.3 to store VMs. There're 8 nodes of my cluster, and I mount the cephFS in every node... - 10:24 PM Bug #5200 (Resolved): mon: valgrind leaks
- 10:23 PM CephFS Bug #4832 (Resolved): mds: failed auth_unpin assert
- 09:39 PM Bug #5286 (Resolved): LibRadosCmd.PGCmd fails pg command test
- simpler fix in commit:81a786e9e52ad5168bb7024145ba11f98e35229b
- 08:43 AM Bug #5288 (Resolved): ceph.py: catch rados errors and print them nicely
- ubuntu@plana30:~$ ceph health
Traceback (most recent call last):
File "/usr/bin/ceph", line 1541, in <module>
... - 05:58 AM Revision 00eaf97d (ceph): librados.h: Fix up some doxygen problems
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 05:14 AM Revision e8300d0a (ceph): mds: fix filelock eval_gather
- Broken by a08d62045657713bf0a5372bf14136082ec3b17e
Reported-by: Yan, Zheng <yan.zheng@intel.com>
Signed-off-by: Sage... - 04:58 AM Revision 22532cc8 (ceph): ceph_manager: drop -- before --format=json arg
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:47 AM Revision 2b4157a7 (ceph): .gitignore: add 'ceph', now a generated file
- 04:20 AM Revision 028f1c70 (ceph): valgrind: more leveldb whitelisting
- 02:32 AM Revision a4994e3b (ceph): Support added for running scheduled tasks on virtual machines.
- This included:
A). changes made so that full path names on some files were used
(scheduled tasks started ... - 01:14 AM Linux kernel client Bug #5267: Kernal 3.2.0-23 crashed
- Thx very much, so quickly get reply made me glad. Maybe the kernel is too old, we will update ASAP.
I forget to upd... - 12:40 AM Revision 4eb8f898 (ceph): merged system_value for rpms
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:29 AM Revision 359f456a (ceph): ceph: old daemons output to outs and outbuf, combine
- When talking to old daemons, if a command succeeds, there may be
output on outs, outbuf, or both; combine them if the... - 12:28 AM Revision b3f38f3e (ceph): ceph: handle old OSDs as command destinations, fix status part of -w
- For osd tell or pg <pgid> commands, the CLI sends the command directly
to the OSD; if the OSDs are still old, the com... - 12:28 AM Revision 754301bb (ceph): support install task for fedora
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:24 AM Revision 05d1d027 (ceph): Merge pull request #352 from ceph/wip-4832
- mds: do not double-queue file recovery in eval_gather
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:20 AM Revision 11e1afd8 (ceph): ceph: add -v for version. Makefile processes ceph_ver.h
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:15 AM Revision 32b2f113 (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 12:13 AM Revision 7012d192 (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 12:12 AM Revision 5e5bd665 (ceph): Merge pull request #343 from dalgaaf/wip-da-SCA-cppcheck
- Reviewed-by: Sage Weil <sage@inktank.com>
06/07/2013
- 11:14 PM Bug #5286 (Fix Under Review): LibRadosCmd.PGCmd fails pg command test
- wip-5286
- 10:45 PM Bug #5286 (Resolved): LibRadosCmd.PGCmd fails pg command test
- ...
- 11:10 PM Revision fde536fa (ceph): osd: make scrub chunk size tunable
- It was hard-coded at 5. Make it range from 5-15 by default, for now.
We should still keep this smallish since this ... - 10:59 PM Revision 0bc731ea (ceph): test_filestore_idempotent: use obj name from source coll add
- Fixes: #5240
Reviewed-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:59 PM Revision 637e0ead (ceph): rados: --num-objects will now cause bench to stop after that many objects
- Reviewed-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:04 PM CephFS Bug #4832: mds: failed auth_unpin assert
- aie.. thanks
- 09:36 PM CephFS Bug #4832: mds: failed auth_unpin assert
- that commit breaks filelock eval gather
- 05:23 PM CephFS Bug #4832 (Resolved): mds: failed auth_unpin assert
- commit:a08d62045657713bf0a5372bf14136082ec3b17e
- 10:00 PM Revision ed9af6cd (ceph): Merge branch 'wip-RhelInstall-wusui'
- 09:58 PM Revision 9d6141dd (ceph): Add RHEL support to teuthology
- Fix #4946
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 09:23 PM Revision 7e095077 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/messages/MMonProbe.h - 09:09 PM Revision 5047a4ff (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 09:09 PM Revision 3ea45533 (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 09:00 PM Revision c75760e3 (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 08:59 PM Revision bd12e81e (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 08:59 PM Revision b1d436e7 (ceph): rgw: add 'cors' to the list of sub-resources
- Fixes: #5261
Backport: cuttlefish
Add 'cors' to the list of sub-resources, otherwise auth signing
is wrong.
Signed-o... - 08:52 PM Revision ad3934e3 (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 08:52 PM Revision 8d55b87f (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 08:51 PM Revision 9a0a9c20 (ceph): rgw: add 'cors' to the list of sub-resources
- Fixes: #5261
Backport: cuttlefish
Add 'cors' to the list of sub-resources, otherwise auth signing
is wrong.
Signed-o... - 08:13 PM Linux kernel client Bug #5267: Kernal 3.2.0-23 crashed
- Thx very much, so quickly get reply made me glad. Maybe the kernel is too old, we will update ASAP.
I forget to upd... - 09:35 AM Linux kernel client Bug #5267 (Won't Fix): Kernal 3.2.0-23 crashed
- please try kernel 3.4 or later.. we aren't backproting fixes as far back as 3.2!
- 07:39 PM CephFS Support #5285 (Closed): cephfs give permission to write files
- Hi all,
I used the CephFS v0.56.3 to store VMs. There're 8 nodes of my cluster, and I mount the cephFS in every n... - 06:05 PM Bug #4698: osd suicide timed out after 150
- log: ubuntu@teuthology:/a/teuthology-2013-06-07_01:30:04-upgrade-master-testing-basic/32963...
- 06:05 PM Revision f4f6758b (ceph): Merge branch 'wip-ceph-cli'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:58 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- 08:38 AM Bug #4179 (Fix Under Review): osd: memory leak during deep scrub on bobtail
- 05:41 PM Bug #5273 (Rejected): osd: ops waiting a long time for osdmaps
- sam points out that the 'waiting for osdmap' status is misleading here..
- 10:24 AM Bug #5273 (Rejected): osd: ops waiting a long time for osdmaps
- mark nelson is observing this.. diagnose and track down.
- 05:38 PM devops Bug #5248 (Need More Info): upstart: ceph-all job is starting too soon
- waiting to hear back from jamespage ... he's conferring with the upstart people
- 05:37 PM devops Bug #5194 (Need More Info): udev does not start osd after reboot on wheezy or el6 or fedora
- can you confirm whether 'partprobe /dev/...' will start the osd?
- 05:34 PM CephFS Bug #5236 (Resolved): mds assert when starting file scan
- no more failures, yay!
- 05:24 PM Documentation #5284: crushtool's manpage is very out of date
- see crushtool --help
- 05:24 PM Documentation #5284 (Closed): crushtool's manpage is very out of date
- 05:00 PM Revision 0b036ecd (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 04:51 PM Revision dea8c2d1 (ceph): doc: Updated for glossary terms and added indexing.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:50 PM Revision 8e24328d (ceph): doc: Added indexing and did a bit of cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:54 PM Revision 03b12b8a (ceph): rados: add btrfs to osd powercycle tests
- So we can get some testing coverage on btrfs, and identify whether the
xfs corruption issues are related to the fs or... - 03:39 PM devops Bug #5283 (Won't Fix): Ceph-deploy can't handle /dev/disk/by-* device paths
- If you try to create a new osd with ceph-deploy using /dev/disk/by-* path instead of the /dev/* path the osd creation...
- 03:37 PM devops Feature #5282 (Closed): Get Dumpling into EPEL
- 03:35 PM devops Feature #4515 (Duplicate): packaging: create qemu packages with rbd enabled for centos 6
- Duplicates 4550
- 03:33 PM devops Documentation #5253 (Resolved): Update Pre-Flight docs to use ceph-deploy package
- 03:31 PM devops Feature #5015 (Resolved): ceph-deploy: push packages to all ceph repos
- 03:29 PM devops Feature #5019 (Resolved): arm: gitbuilder for ARM
- 03:28 PM devops Feature #5018: arm: ceph-deploy: push packages to ARM
- 03:26 PM rbd Feature #4834 (Resolved): Recompile/package qemu with new version of librbd to enable asynchronou...
- 02:56 PM devops Feature #5089 (Resolved): ceph-deploy install fails on arm
- It works.
Needed python-pushy and ceph-deploy built on arm added to the repos. - 02:54 PM devops Feature #5016: ceph-deploy: gitbuilders for release packages
- Opened ticket #5281 for the gitbuilder vms. This task may have fallen off the radar.
- 02:25 PM RADOS Feature #5280 (New): osd/client: messages should be tagged with the earliest sane map
- A client at epoch e should not have to wait for an osd to catch up to epoch e unless the mapping changed in epoch e. ...
- 02:17 PM Fix #5279 (In Progress): pipeline large object recovery
- currently pushes for large objects are syncronous: push->reply->push etc.
should be push->push->push
... - 02:17 PM rgw Bug #5262 (Resolved): rgw: can't access buckets with names that start with 'auth'
- Backported to cuttlefish in commit:bd12e81e48014024171c55f5984c9183c8e363cb and commit:c75760e39d8df5b1971343e9f9186f...
- 01:59 PM rgw Bug #5262 (Pending Backport): rgw: can't access buckets with names that start with 'auth'
- Fixed in next, commit:8d55b87f95d59dbfcfd0799c4601ca37ebb025f5. Fixed a related issue as well, commit:ad3934e335399f7...
- 02:15 PM Fix #4567 (Resolved): mon: refactor mon caps; allow restriction of key/value storage by prefix
- 02:15 PM Feature #3273: mon: simple dm-crypt key management
- - make sure ceph-deploy and chef can use this
- 02:06 PM Fix #5278 (Resolved): osd: smarter recovery for small objects
- 1) avoid collection move for single write pushes
2) maybe package multiple small objects at once? - 02:05 PM rgw Bug #5261 (Resolved): rgw: 'cors' is not regarded as a sub-resource
- Backported to cuttlefish in commit:b1d436e752c9c20e7dbff91b769cb2ba47383571
- 01:58 PM rgw Bug #5261 (Pending Backport): rgw: 'cors' is not regarded as a sub-resource
- Fixed in next branch, commit:9a0a9c205b8c24ca9c1e05b0cf9875768e867a9e.
Will backport to cuttlefish and update with c... - 10:46 AM rgw Bug #5261: rgw: 'cors' is not regarded as a sub-resource
- Yeah, tested it. I created a new functional test for it. Also, there's no CORS in bobtail, so we don't need it there.
- 10:29 AM rgw Bug #5261: rgw: 'cors' is not regarded as a sub-resource
- Well, that's a simple enough fix. Have you tested it yet?
And it's marked as needing a backport to cuttlefish, but... - 02:03 PM Fix #4840 (Resolved): mon: transition from old-style allow command to new command descriptions
- 02:02 PM Feature #5147 (Resolved): Display unique cluster ID in ceph status
- 01:54 PM Bug #5200 (In Progress): mon: valgrind leaks
- 01:35 PM Bug #5270: osd: crash in PG::peek_map_epoch()
- Very odd. That xattr is written atomically on pg collection creation and never overwritten thereafter.
- 01:29 PM rbd Feature #5005: cinder: switch rbd driver to use librbd instead of the cli tool
- Review: https://review.openstack.org/30792
Commit: http://github.com/openstack/cinder/commit/e2d0e1f479a56d60dc09ae9... - 11:32 AM rbd Feature #5005 (Resolved): cinder: switch rbd driver to use librbd instead of the cli tool
- 01:28 PM rbd Feature #5004: cinder: make rbd configuration easier to use
- Review: https://review.openstack.org/30791
Commit: http://github.com/openstack/cinder/commit/483b84e42b90f2ffe0a09f5... - 11:32 AM rbd Feature #5004 (Resolved): cinder: make rbd configuration easier to use
- 01:14 PM rgw Feature #5164: rgw: multisite: metadata push notifications: design blueprint
- 01:13 PM rgw Feature #4098 (Fix Under Review): rgw: multi-site: Global Bucket Namespace
- 01:13 PM rgw Feature #4329 (Fix Under Review): rgw: dr: updated buckets log: RESTful API
- 01:08 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- They are waiting a bit before the upgrade, however they recently reported back that they put together some custom rul...
- 01:03 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- I'd rather not to do a backport. Do we have a bobtail customer asking for this who can't/won't upgrade to Cuttlefish?
- 01:04 PM rgw Feature #5136 (Need More Info): rgw: revise user stats
- ?
- 01:00 PM rgw Feature #5169: Do not list swift containers when enumerating buckets using S3 API
- 12:58 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- 11:51 AM rbd Documentation #5212: doc: link to recommended kernel version from pages that describe using kerne...
- 11:42 AM rbd Feature #4013 (In Progress): rbd: openstack: extend nova boot api to support going from image to ...
- 11:42 AM rbd Feature #4017 (In Progress): rbd: openstack: simplify volume booting with new api
- 11:30 AM rbd Feature #5275 (Resolved): openstack: port always_use_volumes option to grizzly
- The folsom version is git://github.com/jdurgin/nova wip-volumes.
- 10:52 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I'll try commenting out the assert, and yes, we tried the snapshots feature of the MDS hours before the shutdown.
- 09:44 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- were you using the mds snapshots?
- 09:42 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- probably the workaround is to comment out that assert..
- 07:56 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Is it useful for me to keep the FS in this state much longuer, right now the FS is unusable. Is it possible to clear ...
- 10:20 AM devops Bug #5242 (Resolved): ceph-deploy: reports purgedata as invalid command when purge is not successful
- fixed the mirror!
- 09:47 AM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- any news here, tamil?
- 09:56 AM Bug #5272 (Duplicate): Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of existing...
- I'm running a ceph cluster with three server nodes, each running one MON, one MDS and three OSDs to provide CEPHFS st...
- 09:49 AM devops Bug #5263 (In Progress): Python Error While Installing ceph-deply on debian wheezy
- The version 1.0 pachages should not have included the test directory. I'm double checking the repos to ensure thaey...
- 09:35 AM Bug #5260 (Resolved): mon: FAILED assert(other->is_writeable()) from MDSMonitor on 0.61.2
- 08:47 AM Bug #4999 (Can't reproduce): monitor sync failure
- 08:34 AM Bug #5257 (Resolved): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- The prefork fix is backported to cuttlefish, so closing this one out then.
- 07:34 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Running without tcmalloc would be a very helpful data point, yes. You can get non-tcmalloc packages built for precis...
- 07:16 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- It turns out that the Debian wheezy libgoogle-perftools-dev package and ceph packages depends on libgoogle-perftools4...
- 05:44 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Sorry. s/Gary/Sage/
- 05:43 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Would it be helpful to try and build packages that don't use tcmalloc (using the --without-tcmalloc configure option)...
- 12:40 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- No, unfortunately the latest cuttlefish branch didn't fix it. We had another crash about 6 hours after we upgraded.
... - 04:38 AM Revision a08d6204 (ceph): mds: do not double-queue file recovery in eval_gather
- This fixes a specific case of double-queuing seen in #4832:
- client goes stale, inode marked NEEDSRECOVER
- eval ... - 03:08 AM Revision 3ac6ffe8 (ceph): Merge branch 'wip-ceph-cli' into master
- Conflicts:
src/include/rados/librados.h
src/librados/librados.cc
src/osdc/Objecter.cc
src/pybind/rados.py
Requir... - 01:46 AM Revision faa1ae76 (ceph): MDSMonitor: dead debugging code
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 3f7cac32 (ceph): ceph: improve error reporting on failure to connect to cluster
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 783b7ec8 (ceph): librados, ceph, rados.py: -EINVAL for create with null/invalid name
- Means setting defaults should be more careful throughout as well
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:46 AM Revision 2431bfb6 (ceph): librados: rados_X_command need to assemble a vector from char *cmd
- The old monitors take a vector with words split; new monitors don't
care, but the old ones do
Signed-off-by: Dan Mic... - 01:46 AM Revision b114e11a (ceph): ceph: refactor -s -> status to common code, pass childargs to old mons
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 44466815 (ceph): ceph: error and verbose message improvement
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 37a61028 (ceph): ceph: -v should mean version, not --verbose
- To be implemented soon with ceph_ver.h
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:46 AM Revision 24a5212d (ceph): ceph, librados, rados.py, librados tests: pass cmd as array
- Using ceph to pass commands to the old monitor requires the
message to have words in a vector; this means that we nee... - 01:46 AM Revision 7785fc53 (ceph): rados.py: make exception with errno string instead of int
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:44 AM Revision ead8d89d (ceph): ceph: fix up old-monitor handling
- Finish command after submitting to old monitor, rather than falling
through to new-command handling
Also, translate -... - 01:41 AM Revision 8108c952 (ceph): AuthMonitor: fix signed/unsigned comparison warning
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:41 AM Revision 366de90d (ceph): librados, rados.py: rados_create2: add clustername and future flags
- rados.py also gets "conf_defaults" dict for things you might want to
default in your app differently before ceph.conf... - 01:41 AM Revision 3720b64a (ceph): ceph: collect/use clustername, and set defaults like other utilities
- (defaults like log_to_stderr, err_to_stderr)
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:41 AM Revision b1588bd4 (ceph): ceph: catch/handle exceptions in admin socket commands
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:38 AM Revision f43c9745 (ceph): mon: upgrade auth database on leader
- If we are the leader, and the auth database has not yet been upgraded,
do so. The upgrade consists of translating ol... - 01:38 AM Revision f2177a4d (ceph): mon: AuthMonitor: remove dead code to avoid confusion
- AuthMonitor::election_finished() does nothing.
PaxosService::election_finished() is the one being handled.
Signed-o... - 01:38 AM Revision afebad4f (ceph): auth: CephxKeyServer: add secrets_{begin,end}() getters
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:38 AM Revision 115bb933 (ceph): ceph: Remove connect/command timeouts; too risky for now
- Keep 10s timeout when connecting for help descriptions, however
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:35 AM Revision 5c308447 (ceph): doc: Updated with glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:29 AM Revision 8e13b38c (ceph): doc: Updated with glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:27 AM Revision 7116de35 (ceph): doc: Correction and index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:26 AM Revision ae5aeb1c (ceph): doc: Updates for glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
06/06/2013
- 11:01 PM devops Feature #5018: arm: ceph-deploy: push packages to ARM
- Is this by any chance a duplicate ?
- 10:59 PM devops Feature #5089 (In Progress): ceph-deploy install fails on arm
- Needs a bit more testing.
- 10:57 PM devops Feature #5091 (In Progress): google-perftools for arm
- Need to verify that new upstream package build will work for us.
- 10:56 PM devops Feature #5092 (Closed): libatomic-ops for arm; or use gcc atomics instead
- This does not appear to be an issues. libatomicops is not supported on some arm architectures, but v7 is ok. Early ...
- 10:53 PM devops Feature #5015: ceph-deploy: push packages to all ceph repos
- ceph-deploy is being added to all the testing and named releases.
The is still some automation that could be appli... - 10:51 PM devops Feature #5088 (Resolved): ceph-deploy packages need to install on arm
- Completed. Arm version of ceph-deploy built and added to the repo.
- 10:49 PM devops Feature #5090 (Resolved): ceph-build: Need to support arm in the repos.
- Completed, It was just adding armhf to the architectures in the repo cofnig.
- 10:48 PM devops Feature #5016 (In Progress): ceph-deploy: gitbuilders for release packages
- Waiting for gitbuilder VMs to be instantiated.
- 10:42 PM Revision c9569804 (ceph): task/install.py: extraneous subscript in upgrade() for only some remotes
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:35 PM Bug #5270 (Resolved): osd: crash in PG::peek_map_epoch()
- ...
- 10:33 PM Bug #5269 (Resolved): osd: EEXIST on mkcoll
- ...
- 10:14 PM Revision ce2b686a (ceph): Merge pull request #347 from dalgaaf/wip-da-scripts
- Some smaller fixes for init-radosgw files
- 09:53 PM CephFS Bug #4832: mds: failed auth_unpin assert
- full log attached for posterity. see wip-4832
- 06:27 PM CephFS Bug #4832: mds: failed auth_unpin assert
- ...
- 07:23 AM CephFS Bug #4832: mds: failed auth_unpin assert
- ...
- 09:38 PM CephFS Fix #5268 (Closed): mds: fix/clean up file size/mtime recovery code
- from diagnosing #4832 (see the attached log) it looks like this code needs an overhaul:
* i don't think we should ... - 08:55 PM Revision 4bf75015 (ceph): mon: fix preforker exit behavior behavior
- In 3c5706163b72245768958155d767abf561e6d96d we made exit() not actually
exit so that the leak checking would behave f... - 08:55 PM Revision d398a185 (ceph): rados.py: correct some C types
- trunc was getting size_t instead of uint64_t, leading to bad results
in 32-bit environments. Explicitly cast to the d... - 08:20 PM Linux kernel client Bug #5267 (Won't Fix): Kernal 3.2.0-23 crashed
- I don't know how to descript it. The kernal crashed and the last output on the screen is in attached. Who can tell me...
- 06:58 PM Revision b394edc1 (ceph): doc/release-notes: v0.61.3
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:59 PM Revision 3d6eaf58 (ceph): doc: Added upstart syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:58 PM Revision 2d9a46c2 (ceph): doc: Added link to Upstart syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:00 PM devops Bug #5266 (Closed): the apt-get install instructions are missing an update
- http://ceph.com/docs/master/start/quick-start-preflight/
This section is missing the update:
wget -q -O- 'https... - 04:53 PM devops Documentation #5265: node-name is confusing. hostname is probably more accurate
- I think it might be helpful to have a section of the QSG that describes the basic networking requirements (i.e., host...
- 04:49 PM devops Documentation #5265 (Closed): node-name is confusing. hostname is probably more accurate
- http://ceph.com/docs/master/start/quick-ceph-deploy/
ceph-deploy new {node-name}
ceph-deploy new ceph-node
nod... - 04:28 PM Revision 4ee638cc (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 04:23 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- found it (probably):...
- 04:06 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- ...
- 04:21 PM Revision 595962aa (ceph): Merge branch 'wip_5154'
- Fixes: #5154
Reviewed-by: Sage Weil <sage@inktank.com> - 04:17 PM devops Bug #5263: Python Error While Installing ceph-deply on debian wheezy
- Adding package list just in case:
root@ceph-server:/mnt/my-cluster# dpkg -l
Desired=Unknown/Install/Remove/Purge/... - 04:14 PM devops Bug #5263 (Resolved): Python Error While Installing ceph-deply on debian wheezy
- While trying to install ceph-deploy on a new Debian 7.0/Wheezy with all the latest updates I got the following error:...
- 03:46 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- I updated my cluster from 0.61.2 to 0.61.3 and can tell a noticeable improvement. There are still some I/O stalls whi...
- 11:51 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- I've uploaded slowpeer-ceph-osd.2.log.bz2 (--debug-ms=1 --debug-filestore=5 --debug-osd=20) & slowpeer-osd2-ceph.log ...
- 08:21 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- So, I've upgraded my whole cluster to cuttlefish git (7d549cb), mainly to address this issue. The treee I've installe...
- 02:16 PM rgw Bug #5262 (Resolved): rgw: can't access buckets with names that start with 'auth'
- 01:34 PM Revision 963a9c46 (ceph): init-radosgw*: add all sections to usage output
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:33 PM Revision 4ea24ae7 (ceph): init-radosgw*: add status
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:21 PM Revision 39fff6a1 (ceph): fix init-radosgw* to use the same indentation
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:47 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Sage Weil wrote:
> the problem:
>
> mon.1 and .2 had newer data, mon.0 had older data.
> mon.0 converts, waits t... - 11:16 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- the mon.1 log snippet...
- 11:15 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- the problem:
mon.1 and .2 had newer data, mon.0 had older data.
mon.0 converts, waits to join quorum
mon.1 conve... - 06:31 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- cephdrop:ceph-5257-mondirs.tar.bz2, fetched earlier today.
- 10:51 AM Feature #4982 (In Progress): OSD: namespaces pt 1 (librados/osd, not caps)
- 10:09 AM rgw Bug #5261 (In Progress): rgw: 'cors' is not regarded as a sub-resource
- 10:04 AM rgw Bug #5261 (Resolved): rgw: 'cors' is not regarded as a sub-resource
- 'cors' needs to be regarded as a sub-resource, otherwise auth signing is not being done correctly.
- 09:51 AM Bug #4976: osd powercycle triggers object corruption on xfs
- ubuntu@teuthology:/a/teuthology-2013-06-05_10:57:29-rados-cuttlefish-master-basic/31967
- 09:37 AM Bug #5154 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 09:29 AM Bug #4731 (Resolved): PG: don't write out pg epoch on every map activation
- 08:10 AM Bug #5246: mon crashing on pool/pg creation with wip-mon
- comments on gh
- 07:40 AM Revision 8f9b1470 (ceph): Merge branch 'wip-3527'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 07:23 AM Revision 4b80c5b9 (ceph): rados: Output client address in rados listwatchers request
- Add client entity_addr_t string to list of watchers rados interface
Signed-off-by: David Zafman <david.zafman@inktan... - 07:23 AM Revision 0cbc0a08 (ceph): osd: Add dump_watchers to osd admin socket to examine all watchers
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision 4eb576e3 (ceph): Add test_blacklist_self() librados function for test cases
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision a4dbfa31 (ceph): test: Add blacklisting to test_stress_watch
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision 0bd60f8e (ceph): osd: Add entity_addr_t to watch_info_t and Watch
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision ab0da283 (ceph): osd: Drop watchers from blacklisted clients
- On blackist addition or populate ObjectContext
check watcher address against blacklist
Add dout() of the watcher's... - 07:23 AM Revision 3b0a44d9 (ceph): osd: Add dump_blacklist to admin socket
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:28 AM Bug #5255 (Resolved): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- 06:19 AM Bug #5260 (Resolved): mon: FAILED assert(other->is_writeable()) from MDSMonitor on 0.61.2
- Lack of logging doesn't help that much in assessing what may be going on, but the stack trace might prove itself usef...
- 06:09 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- All our OSD nodes have now been updated to packages built from the latest cuttlefish branch, commit 7d549cb82ab8e..
... - 01:27 AM Feature #3527 (Resolved): osd: blacklist should cancel outstanding watches from blacklisted client
- commit:8f9b1470dd50bab9fa85450306c274b1a70a672c
- 12:44 AM Revision 92d085f7 (ceph): mon: fix preforker exit behavior behavior
- In 3c5706163b72245768958155d767abf561e6d96d we made exit() not actually
exit so that the leak checking would behave f...
06/05/2013
- 11:09 PM Revision 91d54a8f (ceph): Merge remote-tracking branch 'gh/next-leaks' into next
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:09 PM Revision 5deece1d (ceph): PG: don't dirty log unconditionally in activate()
- merge_log and friends all take care of dirtying the log
as necessary.
Fixes: #5238
Signed-off-by: Samuel Just <sam.j... - 09:21 PM CephFS Bug #4832: mds: failed auth_unpin assert
- lgo is here flab:/home/sage/tmp/4832
- 09:21 PM CephFS Bug #4832: mds: failed auth_unpin assert
- it's getting recovered twice:...
- 09:02 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Faidon: can you send a tarball of your mon dirs? IIRC the old files are still present post-conversion, so we should ...
- 06:19 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- from the logs on cephdrop, this looks like a non-deterministic store conversion maybe? the quorum 0,1 is happily chu...
- 06:16 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- 05:39 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I just upgraded another box and I'm not observing the same behavior. OSDs are now down while PGs are upgrading. This ...
- 05:22 PM Bug #5257 (Need More Info): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- do you have a complete mon log for this? if not, can you capture one the next time around? that osd should have bee...
- 04:48 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- There seems to have been a monitor election (without me doing anything) exactly before the "141 up":...
- 04:36 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I'm sure nodown wasn't set. I didn't restart all mons at once, just 12 (one box) out of 141.
This is what "grep os... - 04:30 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- are you sure 'nodown' wasn't set? this upgrade happens in load_pgs(), long before the osd sends a message to the mon...
- 01:05 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Just to give a sense of the size of the issue:...
- 12:54 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- This happened after a while:...
- 11:38 AM Bug #5257 (Resolved): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I upgraded ceph on one of my boxes (12 osds) and the osds came up, printing "183140 PGs are upgrading". During that t...
- 08:07 PM Revision 951fc2fa (ceph): OSD: resurrect a parent if it splits into the pg we want to create
- When attempting to create a new pg object in response to a
peering message, there are 3 cases:
1) That pg is currentl... - 07:58 PM Revision 5a53da3c (ceph): ceph-test: add ceph_test_rados_api_lock to packaging and qa
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:58 PM Revision 30733af9 (ceph): Makefile.am: add -ldl to unittest_pglog
- b70868e007ffa56e0eabf22b4ca836327c5f82d4 broke non-package builds on
ubuntu and debian. This fixes the problem, and i... - 07:58 PM Revision 02946e5e (ceph): qa: stop running xfstests 192 in qemu
- This test is unreliable in a vm since it relies on command timing for
checking access time.
Signed-off-by: Josh Durg... - 07:58 PM Revision 68ccf8eb (ceph): Add RADOS API lock tests
- Add tests for the advisory locking API calls.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Fili... - 07:48 PM Revision d8415663 (ceph): Add RADOS lock mechanism to the librados C/C++ API.
- Add functions to the librados C/C++ API, to take advantage and utilize the
advisory locking system offered by RADOS.
... - 07:05 PM devops Feature #5214: Kernel gitbuilders for rpm distros
- This needed centos 6.4 .I know it said 6.3 or 6.4 but we already needed 6.4 cloud-init support for other things so it...
- 06:45 PM Revision 6f78b6e0 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 06:44 PM Revision d9703117 (ceph): doc: Added key and ceph repository to ceph-deploy install.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:10 PM Revision 92b1e398 (ceph): v0.61.3
- 05:59 PM Bug #5256: Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- Cephdrop now has 5256-ceph-mon.ms-be1005.log.gz, 5256-ceph-mon.ms-fe1001.log.gz, 5256-ceph-mon.ms-fe1003.log.gz.
T... - 01:50 PM Bug #5256 (In Progress): Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- 11:29 AM Bug #5256 (Resolved): Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- ...
- 05:33 PM Revision c76838f6 (ceph): osd: Style corrections
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:33 PM Revision 89524eb5 (ceph): osd: Fix usage of commands supported by TestOpsSocketHook::test_ops()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:33 PM Revision 7acf3de6 (ceph): cls,msg: Fix use of set_in4_quad() to set a entity_addr_t
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:31 PM Revision 7d549cb8 (ceph): os/LevelDBStore: only remove logger if non-null
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ce67c58db7d3e259ef5a8222ef2ebb1febbf7362)
Fixe... - 03:53 PM Revision a99435d0 (ceph): mon: fix leak of loopback Connection
- The accessor returns a reference. Instead of taking+dropping it each
time, take one ref in Monitor ctor and release ... - 03:53 PM devops Bug #5259 (Duplicate): osd create command fails inconsistently on ubuntu
- ubuntu@teuthology:/a/teuthology-2013-06-05_01:01:15-ceph-deploy-master-testing-basic/31847...
- 03:43 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Okay so I tried duplicating this again today. And now I can't. I think it was due to an iptables issue at first, but ...
- 03:42 PM Revision 08bb8d51 (ceph): messages/MMonHealth: remove unused flag field
- This was initialized in (one of) the ctor(s), but not encoded/decoded,
and not used. Remove it. This makes valgrind... - 03:34 PM Revision 4974b29e (ceph): messages/MMonProbe: fix uninitialized variables
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com> - 03:11 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- Don't know since we don't have a design; but probably not as I suspect it will require a (very minor) format change/e...
- 03:06 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- When fixed, will this be backported to bobtail?
- 02:21 PM devops Bug #5258 (Resolved): ceph-deploy: forgetkeys command could delete existing keyring files without...
- From an admin point of view, it would be nice to have 'forgetkeys' command to delete only existing keyring files and ...
- 01:51 PM Bug #5240: run_seed_to_range failed, probably fdcache
- 2013-06-05T04:21:14.657 INFO:teuthology.orchestra.run.err:2013-06-05 04:21:58.389650 7faabeffd700 10 filestore(b) tru...
- 12:31 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- ...
- 12:30 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- as Sam requested, here is the perf dump for each osds on the cluster...
- 11:40 AM Bug #5255: 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- Just tested this and it works as expected.
- 10:39 AM Bug #5255: 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- backported with commit commit:7d549cb82ab8ebcf1cc104fc557d601b486c7635
- 10:29 AM Bug #5255 (Pending Backport): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- Sage had already created a patch for this but it's only on next (commit:ce67c58db7d3e259ef5a8222ef2ebb1febbf7362).
... - 10:27 AM Bug #5255 (In Progress): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- 10:04 AM Bug #5255 (Resolved): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- I upgraded my first mon from 0.56.6 to cuttlefish tip as of now (8544ea7) and it crashes on boot with:...
- 11:32 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- For the slow peering case, I think the first problem is that we unconditionally dirty the log in activate(). Since m...
- 07:51 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Looking more closely it appears that for the qa job the problem is just that the recovery gets very low priority due ...
- 07:50 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Stefan Priebe wrote:
> Hi sage is this related to my one? http://tracker.ceph.com/issues/5232
Only sort of.. one ... - 10:32 AM Fix #5232 (In Progress): osd: slow peering due to pg log rewrites
- 07:34 AM Bug #4999: monitor sync failure
- No, I meant I had hit the original issue again, where a sync failed
due to timeout (see updates 2,3)
I haven't be... - 04:14 AM Bug #5205: mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_addresses()
- Thanks Adam, this provides great insight on what's going on.
- 12:46 AM Revision e4eb4aa2 (ceph): teuthology-lock --summary: allow --machine-type=all
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:24 AM Revision 8c23d8cb (ceph): dev/rbd-diff: make formats into bullet lists (solves linebreak probs)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:22 AM Revision ff8f9d30 (ceph): rados: only 1 client for objectcacher stress test
- Otherwise these may step on each other.
06/04/2013
- 11:39 PM Revision 051f477a (ceph): Merge pull request #346 from ceph/wip-5233
- rados.py: correct some C types
- 11:20 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Hi sage is this related to my one? http://tracker.ceph.com/issues/5232
- 04:49 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- the health checks was a red herring. wait_for_recovery calls assert, but the other thread(s) finish before we see th...
- 09:26 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- I think this might be a teuthology problem: i can't find any ceph process running on the cluster when it hangs. tryi...
- 11:11 PM Revision 188ae890 (ceph): ceph_manager: don't say you have no arguments and then list them
- Calling ceph pg dump --format=json works better without -- before pg
(how did this work before?...)
Signed-off-by: D... - 10:35 PM Revision 09a796d7 (ceph): doc: Removed ceph-deploy git, and added ceph-deploy packages.
- fixes: #5253
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:35 PM Revision d1e2e7b6 (ceph): doc: Modified pre-flight checklist for ceph-deploy packages.
- fixes: #5253
- 10:33 PM Revision 72a6767e (ceph): doc: Added title. Suppresses no title warning messages.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:11 PM Bug #5205: mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_addresses()
- I've also encountered this problem, running 0.61.2 on CentOS 6.4 (uname 2.6.32-220.el6.x86_64 #1 SMP Tue Dec 6 19:48:...
- 08:48 PM Revision 891641e8 (ceph): messages/MMonProbe: remove unused fields
- These fields are no longer used. We already bumped the mon internal
protocol in 5d7dd5ab67922b10351c3c7f57865d2c3e681... - 08:23 PM Revision 6dd7d469 (ceph): rados.py: correct some C types
- trunc was getting size_t instead of uint64_t, leading to bad results
in 32-bit environments. Explicitly cast to the d... - 08:13 PM Revision 6f8b53a0 (ceph): ceph: cleanup: accept --conf *and* -c; suppress stderr if no outs
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:13 PM Revision 24a270a1 (ceph): librados, rados.py: add rados_create2/init2
- librados clients, particularly the ceph tool, need to be able
to specify a full 'name'; rados_create enforced 'client... - 08:12 PM Revision ee0913c2 (ceph): Merge remote-tracking branch 'origin/master' into wip-ceph-cli
- Conflicts:
src/mon/OSDMonitor.cc
src/osd/OSD.cc
src/osd/ReplicatedPG.cc - 08:08 PM Revision 85576dba (ceph): Revert "mds: initialize rejoins_pending"
- This reverts commit 05a57bdd1289a63dcf2d4ca2f0dd3d73aff684ac.
Supplanted by d7fb9b173a163eb2318af5832456f0f236f716fd. - 08:08 PM Revision 0c4ca2ae (ceph): mds: allow purging "dirty parent" stray inode
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 08:08 PM Revision d7fb9b17 (ceph): mds: initialize some member variables of MDCache
- I added some member variables to class MDCache, but forget to
initialize them.
Fixes: #5236
Signed-off-by: Yan, Zhen... - 08:08 PM Revision bbdefe34 (ceph): Merge remote-tracking branch 'gh/next'
- 07:40 PM CephFS Bug #3681: kclient fsx fails nightly
- I think this has already been fixed (a cap revoke bug in the MDS code). When handling truncate request, current MDS ...
- 07:39 PM Revision 38d3c3cb (ceph): Merge pull request #340 from dachary/wip-5213
- PGLog::merge_old_entry unit tests
Reviewed-by: Sam Just <sam.just@inktank.com> - 07:38 PM Revision 8d948f61 (ceph): Merge pull request #327 from dachary/wip-pg_missing_t-tests
- unit tests for pg_missing_t
Reviewed-by: Sam Just <sam.just@inktank.com> - 07:36 PM Revision 96559465 (ceph): OSD: remove created argument from get_or_create_pg()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:36 PM Revision 15a5e099 (ceph): OSD: make get_or_create_pg handle_pg_peering_evt
- handle_pg_peering_evt() includes checking for splitting
and unlocking the pg.
Signed-off-by: Samuel Just <sam.just@i... - 07:36 PM Revision d605eafd (ceph): OSD: add pgid and res_map to DeletingState
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:07 PM Revision 64b3e833 (ceph): Revert "mds: allow purging "dirty parent" stray inode"
- This reverts commit b8f1cb978944a616b69150fdbb3a6b978d75b1dc.
- 06:07 PM Revision 05a57bdd (ceph): mds: initialize rejoins_pending
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:05 PM Revision c2169147 (ceph): Revert "mds: initialize some member variables of MDCache"
- This reverts commit 2d655bde8de9ad255d63718768558399cacd7068.
- 05:44 PM Bug #4999: monitor sync failure
- Jim, you mean you hit the leveldb error again? can you post a complete log for that? The one in the original report...
- 05:42 PM Revision ce67c58d (ceph): os/LevelDBStore: only remove logger if non-null
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:37 PM Revision cdf5785c (ceph): test_filestore_idempotent: make newly created objects globally unique
- The filestore requires hobjects to be globally unique.
Fixes: #5240
Signed-off-by: Samuel Just <sam.just@inktank.com... - 05:13 PM Bug #5246 (Fix Under Review): mon crashing on pool/pg creation with wip-mon
- pushed a simplification of the is_readable/writeable checks to wip-mon
- 08:33 AM Bug #5246: mon crashing on pool/pg creation with wip-mon
- Postponed but not forgotten.
- 07:46 AM Bug #5246 (Resolved): mon crashing on pool/pg creation with wip-mon
- this is using wip-mon when the cluster is first being setup during pool creation. OSDs were (possibly unrelated) goi...
- 04:42 PM Revision 713719a0 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 04:40 PM Bug #5233 (Resolved): python rados tests induce bad filestore truncate on arm
- commit:051f477
- 01:59 PM Bug #5233 (Fix Under Review): python rados tests induce bad filestore truncate on arm
- Added #5252 for the osd error handling part.
- 04:39 PM Revision 8544ea75 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 04:38 PM Revision 8bbd0370 (ceph): Merge pull request #344 from ceph/wip-5220
- Reviewed-by: Sage Weil <sage@inktank.com>
- 04:07 PM Revision 3ec763c4 (ceph): ceph: fix valgrind grep output parsing
- When you pass a single file to zgrep you don't get the filename prefix,
which confuses the split line a few lines down. - 03:56 PM Feature #5147: Display unique cluster ID in ceph status
- oh.. yeah, it's a uuid, e.g. "3cbff3a6-18f6-42e8-8940-febea7eb4282"
also, i didn't backport the change to cuttlefi... - 03:55 PM Feature #5147 (Need More Info): Display unique cluster ID in ceph status
- Can you please confirm the format of the unique string? PS have requested it being something easy to communucate over...
- 03:27 PM Revision b226e117 (ceph): os/LevelDBStore: fix merge loop
- We were double-incrementing p, both in the for statement and in the
body. While we are here, drop the unnecessary el... - 03:09 PM devops Documentation #5253 (Resolved): Update Pre-Flight docs to use ceph-deploy package
- update pre-flight info at http://ceph.com/docs/master/start/ to instruct users to download ceph-deploy package, which...
- 03:04 PM Bug #5225 (Rejected): arm: rbd fsx test failed on the arm set up
- fsx allocates the entire image size in memory. We just need to decrease the image size to make it work on these machi...
- 01:59 PM Bug #5252 (Resolved): osd: EINVAL from truncate causes osd to crash
- If a rados client sends a truncate operation that exceeds the maximum file size, truncate/ftruncate(2) will return EI...
- 01:15 PM Bug #4976: osd powercycle triggers object corruption on xfs
- this is looking more like an xfs bug to me.. sent something to the list.
i also think it is new in 3.9. need to tr... - 12:49 PM Bug #5239 (Need More Info): osd: Segmentation fault in ceph-osd / tcmalloc
- 09:36 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- this is either heap corruption, or a buggy tcmalloc, i think.
are there known problsm with wheezy's tcmalloc versi... - 09:36 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Gary, can you please take a look at this?
- 12:34 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I'm running a single MDS on the same server as a MON and a ODS. We're not using the FS very much, just testing, this ...
- 12:16 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Can you provide the output of "ceph -s" as well, please. And start up an MDS daemon after setting "debug mds = 20" an...
- 11:19 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Full log at pastebin.com : http://pastebin.com/9YPMjw0t
- 11:18 AM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
- After rebooting the whole cluster using the "shut the braker off" method, I had some BTRFS corruption which was fixed...
- 12:32 PM Bug #5247 (Resolved): upgrade suite is hanging
- tested on '0.63-229-g64b3e83-1precise' [sha1: 64b3e833f62f2538ffd7bd565d968decf6584691]
- 12:19 PM Bug #5247: upgrade suite is hanging
- error seen is ...
- 10:47 AM Bug #5247: upgrade suite is hanging
- 09:27 AM Bug #5247 (Resolved): upgrade suite is hanging
- has gottne hung the last 2-3 nights
- 12:27 PM Bug #5251 (Can't reproduce): wrong node messages in mds log
- when upgrading from bobtail to next branch, seeing repeated wrong node messages in the osd logs....
- 11:43 AM Revision b70868e0 (ceph): unit tests for PGLog::merge_old_entry
- The tests covers 100% of the LOC of merge_old_entry. It is broken down
in 13 cases to enumerate all the situations it... - 10:57 AM Bug #5163: filestore: ENOTEMPTY on object removal
- Can we get a recursive ls of 2.363_head on that osd?
- 10:50 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- what happens if you do 'ceph-disk-active /dev/sdb1' (or whatever the xfs patition is)? what about 'partprobe /dev/sd...
- 10:44 AM Bug #5240 (Resolved): run_seed_to_range failed, probably fdcache
- 10:26 AM RADOS Feature #5249 (Resolved): mon: support leader election configuration
- Right now, monitor election is handled by selecting the monitor with the lowest IP that can reach enough peers. This ...
- 10:02 AM devops Bug #5248 (Resolved): upstart: ceph-all job is starting too soon
- The current ceph-all job specifies the following:
start on (local-filesystems and net-device-up IFACE!=lo)
This c... - 09:49 AM Bug #5237 (Duplicate): filestore idempotent tester failure
- 09:39 AM rbd Bug #5220 (Resolved): test_ls_snaps segfaults on the arm test setup
- 09:37 AM CephFS Bug #5236: mds assert when starting file scan
- 09:33 AM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- this is definitely using hte wrong version of ceph-deploy.. discover is not a command any more. somehow pulling from...
- 08:42 AM rgw Bug #5245: Frequent 500s from radosgw
- Yes, there is a single radosgw process:...
- 07:58 AM rgw Bug #5245: Frequent 500s from radosgw
- Can you verify that you only have a single gateway running on that socket, and that the process id does not change wh...
- 07:51 AM rgw Bug #5245: Frequent 500s from radosgw
- This is my Apache config:...
- 07:30 AM rgw Bug #5245: Frequent 500s from radosgw
- Could it be that you let apache spawn the gateways by itself? Or maybe running multiple gateways over the same socket...
- 02:32 AM rgw Bug #5245 (Can't reproduce): Frequent 500s from radosgw
- Hi,
I have roughly 30 clients talking simultaneously to radosgw over 1Gbps link. I use boto library on the client ... - 08:33 AM Bug #5215 (Resolved): mon: hang during sync with mon thrashing
- commit:eb6d5fcf994d2a25304827d7384eee58f40939af
- 07:17 AM Bug #5215 (In Progress): mon: hang during sync with mon thrashing
- Managed to trigger this using the following job:...
- 04:07 AM Revision f6f4f8f7 (ceph): librados cmd tests: mon_status comes to stdout, not stderr
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision fbfdd51a (ceph): ceph: backward-compatibility hack: blank line before JSON output
- Many JSON commands (osd dump, et. al.) used to print a status
line first before the actual output; this has been fixe... - 04:07 AM Revision 51a887a2 (ceph): Add ceph_test_rados_api_cmd to the ceph-test package
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 18f2f194 (ceph): test/librados: remove "set_auid" pool tests
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 21a1c4d3 (ceph): mon: fix POOL_OP_AUID_CHANGE
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision a4b824cd (ceph): PGMonitor: fix pg dump and dump_stuck
- dump needed to default to format plain, not json
dump_stuck was not doing format = plain correctly (coredumping)
Sig... - 04:07 AM Revision 8c674800 (ceph): ceph: various cleanups
- - make base class valid() do useful work
- remove valid from CephPoolname; pool need not exist for create
- add --u... - 04:07 AM Revision 5e90e6c8 (ceph): mon/MonCap: set text in set_allow_all()
- This will let the cap encode/decode to the same value.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:07 AM Revision 0bec7e13 (ceph): mon/MonCap: fix setting of text in parse()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision d4bfce7c (ceph): mon: better debugging of caps messages/values
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision 5bd93b3a (ceph): ceph: refactor help so it can be called after cluster connection
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 6cec9ccc (ceph): librados: fix unsigned vs. signed warning
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:06 AM Revision be1a5124 (ceph): cmdparse, mon: add cmd_vartype_stringify for _allowed_command
- cmd_vartype are not all strings, and need a type-variant function
to turn them into strings for authorization against... - 04:05 AM Revision f1021c9b (ceph): cmdparse: add handle_bad_get(), ceph:: qualifiers, cmdmap_t
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:53 AM Revision b8f1cb97 (ceph): mds: allow purging "dirty parent" stray inode
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:52 AM Revision 2d655bde (ceph): mds: initialize some member variables of MDCache
- I added some member variables to class MDCache, but forget to
initialize them.
Fixes: #5236
Signed-off-by: Yan, Zhen... - 01:26 AM Revision 17029b27 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 12:30 AM Revision df34cff7 (ceph): ceph: use conf_parse_argv to deal with nonspecial Ceph args
- This means parsing argv only once now, so pass arg lists to
new_style_command(). A little cleanup/commenting too.
S... - 12:30 AM Revision 456f96f9 (ceph): ceph: remove global declarations, declare verbose and cluster near top
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision b0469a14 (ceph): cephtool/test.sh: fix "expect failure"
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 8dd36183 (ceph): ceph: finish changing bestsigs to bestcmds
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 98093718 (ceph): ceph: move admin-daemon command before connect()
- Allow admin-daemon commands to work even if we can't connect()
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:30 AM Revision 74f5ea44 (ceph): mon/MonCap: allow osd, mds to write to cluster log
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:30 AM Revision dc73581a (ceph): mon: include cluster fsid/uuid in status output
- Implements: #5147
Signed-off-by: Sage Weil <sage@inktank.com> - 12:30 AM Revision 73a1b216 (ceph): ceph: make ceph -w output 'ceph status' first
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 065b29cd (ceph): librados, rados.py: add conf_parse_argv_remainder()
- New parsing function to extract any known arguments from a vector
and return any unknowns; useful for ceph CLI to all... - 12:24 AM Revision 22660bde (ceph): MDSMonitor, cmdparse: increase resiliency of bad cmd_getval()
- MDSMonitor: check for and handle bad maxmds get
cmdparse.h: Use gcc demangler to print bad boost::variant typenames,
...
06/03/2013
- 10:08 PM Cleanup #4809 (Resolved): MMonProbe extra fields
- 09:53 PM Feature #5147 (Resolved): Display unique cluster ID in ceph status
- don't think we need to backport this one.
- 09:53 PM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- could this simply be:
- start sync
- sync last_committed
- crash before reaching osdmap_$lastcommitted
- osd re... - 09:50 PM CephFS Bug #5236: mds assert when starting file scan
- commit:2d655bde8de9ad255d63718768558399cacd7068
thanks! - 05:53 PM CephFS Bug #5236: mds assert when starting file scan
- looks like I forget to initialize MDCache::rejoins_pending
- 02:17 PM CephFS Bug #5236: mds assert when starting file scan
- Yan, I got as far as identifying that the problem is that rejoin_gather_finish->identify_files_to_recovery is getting...
- 10:00 AM CephFS Bug #5236: mds assert when starting file scan
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-06-03_01:00:48-fs-master-testing-basic/30161
- 07:52 AM CephFS Bug #5236 (Resolved): mds assert when starting file scan
- ...
- 08:45 PM Revision 1cb7dbd9 (ceph): messages/MClientCapRelease: fix string output
- Use the vector size, not what is in the header, which is not yet filled in
for outgoing messages.
Signed-off-by: Sag... - 07:23 PM Revision 27f82ce3 (ceph): ceph: Add missing usage "ceph osd blacklist ls"
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:25 PM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
- ...
- 04:57 PM Revision bd7292b5 (ceph): ceph: debug valgrind error
- File "/var/lib/teuthworker/teuthology-master/teuthology/task/ceph.py", line 215, in valgrind_post
(file, kind) = ... - 04:44 PM RADOS Tasks #5243 (New): osd testing: create peering speed test
- Create teuthology task which generates a deterministic numbers of pg remaps and summarizes the peering "speed".
Th... - 04:23 PM rgw Feature #5170: RGW: Object restriping tool to fix large objects from argonaut.
- 04:09 PM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- ubuntu@teuthology:/a/teuthology-2013-06-02_01:00:44-fs-master-testing-basic/29298
- 04:08 PM devops Bug #5242 (Resolved): ceph-deploy: reports purgedata as invalid command when purge is not successful
- ...
- 03:50 PM CephFS Fix #5241: MDS: not valgrind (leak) clean
- teuthology-2013-06-03_01:00:48-fs-master-testing-basic:
30170, 30172, 30174 - 03:43 PM CephFS Fix #5241 (New): MDS: not valgrind (leak) clean
- Valgrind info at /a/teuthology-2013-06-01_01:00:43-fs-next-testing-basic/28691/remote/ubuntu@plana85.front.sepia.ceph...
- 03:50 PM Bug #5240: run_seed_to_range failed, probably fdcache
- Looks like the tester will place objects with the same name into different collections, fixing test.
- 03:39 PM Bug #5240 (Resolved): run_seed_to_range failed, probably fdcache
- 2013-06-03T04:26:53.232 INFO:teuthology.orchestra.run.err:2013-06-03 04:27:34.948984 7fa652ef5780 0 filestore_diff d...
- 03:40 PM Bug #4976: osd powercycle triggers object corruption on xfs
- two writes to the object, at offset A~B and C~D, then read the whole thing. the original write appears intact, but a...
- 03:35 PM Bug #5156 (Duplicate): OSD: split followed by pg resurrection might leave an object in two collec...
- 02:55 PM Bug #5226: Some PG stay in "incomplete" state
- Well, if I look /var/lib/ceph/osd/ceph-19/current/4.5c_head or /var/lib/ceph/osd/ceph-19/current/4.0_head for example...
- 09:35 AM Bug #5226 (Need More Info): Some PG stay in "incomplete" state
- it sounds as though osd.19 was also missing hte data prior to osd.25 going away. can you look for the pg subdirector...
- 01:22 PM Revision 367e203f (ceph): fusetrace_ll.cc: handle return value of fuse_session_loop()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:07 PM Feature #4107: Usage quota for rados pools
- Duplicated by 4465 and 4466.
- 12:26 PM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- One way to do that would be to use lsblk /dev/<disk> and look for the word "part". I'm not sure lsblk is on every dis...
- 09:42 AM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- the python code that does this is pretty kludgey.. any suggestions for a more robust enumeration strategy should be p...
- 09:26 AM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- More info:
A customer has its OS installed on /dev/sdak.
When running ceph-disk prepare /dev/sda, ceph-disk-pre... - 10:48 AM Revision 541320cf (ceph): mds/MDCache.cc: reduce scope of 'CDir *dir' in _create_system_file_fini...
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:19 AM rbd Bug #5220 (In Progress): test_ls_snaps segfaults on the arm test setup
- 09:55 AM Revision 7aa9b92d (ceph): mds/MDCache.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM Revision f7071b24 (ceph): osd/PG.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM Revision 575652aa (ceph): key_value_store/kv_flat_btree_async.cc: fix some reassign before use va...
- Fix some cases of "(performance) Variable 'err' is reassigned a
value before the old one has been used." issues from ... - 09:55 AM Revision 8afbc280 (ceph): kv_flat_btree_async.cc: fix assigned but unused value issue
- Fix "Variable 'r' is assigned a value that is never used." issue from
cppcheck. Check return value and print warning ... - 09:55 AM Revision 1b70fcd4 (ceph): mds/Migrator.cc: reduce scope of 'in' in handle_export_prep()
- Reduce scope of 'CInode *in' since it's the way it's done already
in other paths of the function.
Signed-off-by: Dan... - 09:55 AM Revision 84dedf5b (ceph): mount/mount.ceph.c: reduce scope of 'value'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM rgw Feature #4310 (In Progress): rgw: multisite: radosgw changes: copy across regions
- 09:55 AM rgw Feature #4337 (In Progress): rgw: multisite: metadata sync agent: implement full sync
- 09:39 AM Bug #5176 (Resolved): leveldb: Compaction makes things time-out yielding spurious elections
- 08:42 AM Fix #5232: osd: slow peering due to pg log rewrites
- Should I post the config?
- 08:37 AM Bug #5239 (Can't reproduce): osd: Segmentation fault in ceph-osd / tcmalloc
- We're still experiencing segmentation faults in the ceph-osd daemons from the 0.61.2-1~bpo70+1 debian packages.
It a... - 08:28 AM Bug #5238 (Resolved): osd: slow recovery (uselessly dirtying pg logs during peering)
- seeing several failures due to slow recovery. it looks like the health checks stop, and teuthology continues on for ...
- 08:26 AM Bug #5237 (Duplicate): filestore idempotent tester failure
- ...
- 04:21 AM Revision 4fa5f99a (ceph): ceph-fuse: create finisher threads after fork()
- The ObjectCacher and MonClient classes both instantiate Finisher
threads. We need to make sure they are created *aft... - 03:59 AM Revision 1e99be15 (ceph): vstart.sh: make client logs unique
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:08 AM Revision eb6d5fcf (ceph): os/LevelDBStore: fix merge loop
- We were double-incrementing p, both in the for statement and in the
body. While we are here, drop the unnecessary el... - 12:27 AM Revision d017afb5 (ceph): msgr: add get_messenger() to Connection
- This was part of commit 27381c0c6259ac89f5f9c592b4bfb585937a1cfc.
Signed-off-by: Sage Weil <sage@inktank.com>
06/02/2013
- 11:34 PM Revision 38f8d850 (ceph): mon: discard messages from disconnected clients
- If the client is not connected, discard the message. They will
reconnect and resend anyway, so there is no point in ... - 11:34 PM Revision ffb87918 (ceph): mon: start lease timer from peon_init()
- In the scenario:
- leader wins, peons lose
- leader sees it is too far behind on paxos and bootstraps
- leader tr... - 11:34 PM Revision 61135964 (ceph): mon/Paxos: adjust trimming defaults up; rename options
- - trim more at a time (by an order of magnitude)
- rename fields to paxos_trim_{min,max}; only trim when there are mi... - 11:34 PM Revision 36d94898 (ceph): msgr: add Messenger reference to Connection
- This allows us to get the messenger associated with a connection.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherr... - 11:29 PM Revision 2dc40281 (ceph): common/Preforker: fix warnings
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a284c9ece85f11d020d492120be66a9f4c997416) - 10:52 PM Revision f7c19440 (ceph): Merge pull request #337 from dalgaaf/wip-da-CID-medium.v2
- Fix several medium impact CID issues V2
Reviewed-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision 44d15138 (ceph): Merge remote-tracking branch 'gh/next'
- 09:09 PM Revision 87dcba2d (ceph): os/LevelDBStore: do compact_prefix() work asynchronously
- We generally do not want to block while compacting a range of leveldb.
Push the blocking+waiting off to a separate th... - 09:09 PM Revision 6543da74 (ceph): os/LevelDBStore: allow compaction of key ranges
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e20c9a3f79ccfeb816ed634ca25de29fc5975ea8) - 09:09 PM Revision dcd9b793 (ceph): mon/MonitorDBStore: allow compaction of ranges
- Allow a transaction to describe the compaction of a range of keys. Do this
in a backward compatible say, such that o... - 09:09 PM Revision d14665e5 (ceph): mon: compact trimmed range, not entire prefix
- This will reduce the work that leveldb is asked to do by only triggering
compaction of the keys that were just trimme... - 09:09 PM Revision 83b1edac (ceph): os/LevelDBStore: merge adjacent ranges in compactionqueue
- If we get behind and multiple adjacent ranges end up in the queue, merge
them so that we fire off compaction on large... - 09:09 PM Revision 0109fa8a (ceph): mon: make compaction bounds overlap
- When we trim items N to M, compact over range (N-1) to M so that the
items in the queue will share bounds and get mer... - 09:09 PM Revision 85d629a5 (ceph): os/LevelDBStore: add perfcounters
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 7802292e0a49be607d7ba139b44d5ea1f98e07e6) - 09:09 PM Revision cc88cdfe (ceph): mon: return instead of exit(3) via preforker
- This lets us run all the locally-scoped dtors so that leak checking will
work.
Signed-off-by: Sage Weil <sage@inktan... - 09:09 PM Revision d284eaf9 (ceph): mon: fix leak of health_monitor and config_key_service
- Switch to using regular pointers here. The lifecycle of these services is
very simple such that refcounting is overk... - 09:09 PM Revision 3372235d (ceph): mon: destroy MonitorDBStore before g_ceph_context
- Put it on the heap so that we can destroy it before the g_ceph_context
cct that it references. This fixes a crash li... - 09:09 PM Revision 48ee9283 (ceph): fix test users of LevelDBStore
- Need to pass in cct.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 446e0770c77de5d72858dcf7... - 07:16 PM Fix #5232: osd: slow peering due to pg log rewrites
- No config changes except the minimum right now. Before I just had changed the osd op thread count.
4096 pgs 24 osd... - 02:40 PM Fix #5232: osd: slow peering due to pg log rewrites
- Stefan, are there any non-default options for in your ceph.conf that might affect pg log size? How many pgs do you h...
- 01:45 PM Fix #5232: osd: slow peering due to pg log rewrites
- even so, it seems like a lot of time is spent just in the removal phase.. perhaps there is something not quite right ...
- 01:43 PM Fix #5232: osd: slow peering due to pg log rewrites
- This looks to me like a lot of time is being spent in leveldb clearing and rewriting the pglog. This is probably jus...
- 11:33 AM Fix #5232: osd: slow peering due to pg log rewrites
- May be a hint or just luck i could reduce the effect and time to recover by lowering osd op threads to 2 (default) in...
- 11:32 AM Fix #5232: osd: slow peering due to pg log rewrites
- Attached you'll find a log with debugging enabled in betweek and two new gdb thread all traces.
- 09:39 AM Fix #5232: osd: slow peering due to pg log rewrites
- stefan: can you also do
ceph --admin-daemon /var/run/ceph/ceph-osd.NNN.asok config set debug_ms 1
ceph --admin-... - 09:38 AM Fix #5232: osd: slow peering due to pg log rewrites
- this thread?...
- 05:08 AM Fix #5232 (Resolved): osd: slow peering due to pg log rewrites
- I noticed that since cuttlefish the osd recovery process is extremely slow. Also client I/o gets stalled to the recov...
- 03:34 PM Bug #5163: filestore: ENOTEMPTY on object removal
- moved tamil's issue to #5233. and mike, i see the output now, but it doesn't make much sense. a more complete log w...
- 03:26 PM Bug #5163: filestore: ENOTEMPTY on object removal
- Tamil- I see, it's the python rados tests. Is this reproducible?
- 03:18 PM Bug #5163 (Need More Info): filestore: ENOTEMPTY on object removal
- Tamil- Yours looks like a different (and easier) bug. what was the workload? It appears to just be a bad trucnation...
- 03:29 PM Bug #5233 (Resolved): python rados tests induce bad filestore truncate on arm
- see #5163
filestore saw... - 10:50 AM Revision 6cdc4f8f (ceph): merge_old_entry arguments info and oe are changed to const because
- there is no side effect.
The PGLog::clear function is added to reset all data members to the
same state they have af... - 06:29 AM Bug #5226: Some PG stay in "incomplete" state
- After replacing OSD.25, near all incompletes PG are [19, 25] or [25, 19] :
> $ ceph health detail
> HEALTH_WARN 1...
06/01/2013
- 08:39 PM Revision bac5720b (ceph): qa: rsync test: exclude /usr/local
- Some plana have non-world-readable crap in /usr/local/samba. Avoid
/usr/local entirely for that and any similar land... - 08:33 PM Revision ed8e3c34 (ceph): rados: increase recovery timeout when powercycling
- Machine reboots take a while, and i've observed recovery making progress
but not finishing in time. - 01:36 PM Bug #4976 (In Progress): osd powercycle triggers object corruption on xfs
- ubuntu@teuthology:/a/teuthology-2013-05-31_20:00:08-rados-cuttlefish-master-basic/28270
trying to reproduce this w... - 04:17 AM Revision 9f1afe1a (ceph): mon: fix uninitialized fields in MMonHealth
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d7e2ab1451e284cd4273cca47... - 04:16 AM Revision d7e2ab14 (ceph): mon: fix uninitialized fields in MMonHealth
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision f1ccb2d8 (ceph): mon: start lease timer from peon_init()
- In the scenario:
- leader wins, peons lose
- leader sees it is too far behind on paxos and bootstraps
- leader tr... - 12:05 AM Revision fb3cd0c2 (ceph): mon: discard messages from disconnected clients
- If the client is not connected, discard the message. They will
reconnect and resend anyway, so there is no point in ... - 12:05 AM Revision 6b8e74f0 (ceph): mon/Paxos: adjust trimming defaults up; rename options
- - trim more at a time (by an order of magnitude)
- rename fields to paxos_trim_{min,max}; only trim when there are mi...
05/31/2013
- 11:22 PM Revision 957b0d00 (ceph): replaced tab with spaces
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:13 PM Revision a03ccf17 (ceph): OSD: *inodes_hard_limit must be less than the fd limit
- Also add a comment explaining that.
Fixes: #5224
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg... - 10:10 PM Revision e12a9c46 (ceph): OSD: tell them they died if they don't exist as well
- OSDMap::get_down_at() asserts that the osd exists.
Fixes: #5223
Signed-off-by: Samuel Just <sam.just@inktank.com>
Re... - 09:48 PM Revision b2e49041 (ceph): Merge branch 'wip-osd-leaks' into next
- Reviewed-by: David Zafman <david.zafman@inktank.com>
- 09:48 PM Revision 9865bb46 (ceph): osd: reset heartbeat peers during shutdown
- This fixes a leak of the Connection's and related structures.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision cec83798 (ceph): osd: fix msg leak on shutdown in ms_dispatch
- Reported-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision 222059ec (ceph): osd: fix leak of MOSDMarkMeDown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:48 PM Revision 923683ff (ceph): mon/MonClient: fix leak of MMonGetVersionReply
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:35 PM Revision 08631e7a (ceph): rgw: some user metadata fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:44 PM Revision d5b67d49 (ceph): PGLog: only add entry to caller_ops in add() if reqid_is_indexed()
- Fixes: #5216
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 08:36 PM Revision a5f6d896 (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 07:48 PM Revision 9aaff149 (ceph): upstart: handle upper case in cluster name and id
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
(cherry picked from commit 851619ab6645967e5d765... - 07:47 PM Revision 0f246a3a (ceph): Merge pull request #338 from alram/next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 07:33 PM Revision 851619ab (ceph): upstart: handle upper case in cluster name and id
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 07:30 PM Revision dfad09b0 (ceph): rgw_admin: modify mdlog functionality
- mdlog list, can handle cases where there is and there's no shard id
specified. mdlog trim requires shard if.
Signed-... - 07:30 PM Revision 2b9ab9f3 (ceph): rgw: set truncated as false if ENOENT when listing mdlog entries
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:28 PM rbd Bug #5040 (Resolved): krbd: record that an parent info refresh has failed
- The following has been committed to the ceph-client
"testing" branch:
93e85fb rbd: clean up a few things in the r... - 07:27 PM rbd Bug #3094 (Resolved): krbd: race between finding existing client and creating new one
- The following has been committed to the "testing" branch
of the ceph-client git repository.
601e01d rbd: protect ... - 07:22 PM Revision e46d7d68 (ceph): Merge branch 'wip-rgw-geo-enovance' into wip-rgw-geo-2
- Conflicts:
src/Makefile.am
src/rgw/rgw_admin.cc
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:23 PM rbd Bug #5222 (Fix Under Review): krbd: use per-rbd_dev mutex to protect header updates
- This patch has been posted for review:
0004-rbd-use-rwsem-to-protect-header-updates.patch
- 02:40 PM rbd Bug #5222 (Resolved): krbd: use per-rbd_dev mutex to protect header updates
- Currently updating header information for an rbd device
is protected by the control lock, which precludes
concurren... - 06:22 PM rbd Bug #3925 (Fix Under Review): krbd: sysfs write lockdep warnings
- I found that avoiding taking the ctl_lock when updating
getting or putting device references got rid of the
problem... - 10:58 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- That sequence reproduces the problem, even in the latest
version of the "testing" branch. (Not all of it may be
re... - 06:15 PM Revision 54d23052 (ceph): doc: Added Java example for setting protocol to HTTP.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:14 PM Revision 145c4808 (ceph): doc: Text of diagram for osd_throttles.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:14 PM rgw Bug #5228 (Duplicate): radosgw-admin bucket list no longer shows all buckets
- It can still list the buckets owned by a specific user when --uid is specified.
The bug was introduced by the foll... - 06:14 PM Revision 8d70c091 (ceph): doc: Omitted text diagram, and used literal include to text file.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:11 PM Bug #5227 (Can't reproduce): ARM set up: rados test failed
- rados_workunit_loadgen_mostlyread.yaml test failed in the ARM test setup [tala002, tala003, tala004]...
- 06:09 PM Revision e6ad9da0 (ceph): PGLog: only add entry to caller_ops in add() if reqid_is_indexed()
- Fixes: #5216
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:59 PM Revision f87a19d3 (ceph): OSDMonitor: skip new pools in update_pools_status() and get_pools_health()
- New pools won't be full. mon->pgmon()->pg_map.pg_pool_sum[poolid] will
implicitly create an entry for poolid causing... - 05:58 PM Revision ddb3a8d6 (ceph): unit tests for pg_missing_t
- All lines of code are tested. The conditions under which some methods
could corrupt the content of a pg_missing_t obj... - 05:39 PM Revision db85c52d (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 05:35 PM Revision 8c6a912a (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:35 PM Revision f42e84ee (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 05:30 PM Revision 34733bdc (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:30 PM Revision 3d91301e (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 05:15 PM Revision 38ee69c2 (ceph): mds/MDCache.cc: fix dereference after null check
- Add assert for 'parent' before call assert on parent->is_auth().
CID 716922 (#1 of 1): Dereference after null check ... - 05:15 PM Revision 91f6b0f0 (ceph): mds/MDCache.cc: fix dereference null return value
- CID 716993 (#1 of 2): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might ... - 05:15 PM Revision c0e3d04b (ceph): mds/MDCache.cc: fix dereference null return value
- Add assert to fix:
CID 716994 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a... - 05:15 PM Revision 578e292b (ceph): mds/Migrator.cc: fix dereference after null check
- Add assert for 'le' to fix:
CID 716923 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Pas... - 05:15 PM Revision 0b78e2bc (ceph): mds/Migrator.cc: fix dereference after null check
- Add asserts to check for 'dir' to fix:
CID 716924 (#1-5 of 5): Dereference after null check (FORWARD_NULL)
var_der... - 05:15 PM Revision d9b00c43 (ceph): mds/Server.cc: fix dereference after null check
- Add assert to fix:
CID 716925 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null... - 05:15 PM Revision e5555582 (ceph): mds/Server.cc: fix dereference after null check
- CID 716926 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing "mdr" to function
"Ser... - 05:15 PM Revision cfdd87ca (ceph): mds/Server.cc: fix dereference after null check
- CID 716927 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "diri->snap... - 05:15 PM Revision 5aa0b129 (ceph): .gitignore: add directory from coverity tools
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:15 PM Revision 39a53e5c (ceph): mds/Server.cc: fix explicit null dereferenced
- CID 716928 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
var_deref_model: Passing null pointer "session" to ... - 05:15 PM Revision 2a024091 (ceph): mds/Locker.cc: fix explicit null dereferenced
- CID 716916 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to funct... - 05:15 PM Revision 679775ae (ceph): small_io_bench_fs.cc: check return value of FileStore::mkfs/mount()
- CID 743398 (#1 of 1): Unchecked return value (CHECKED_RETURN)
check_return: Calling function "FileStore::mount()" w... - 05:15 PM Revision a7a0425d (ceph): bench/dumb_backend.cc: check return value of posix_fadvise()
- CID 743396 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
check_return: Calling function "posix_fa... - 05:15 PM Revision db2fbb1d (ceph): bench/dumb_backend.cc: check return value of lseek()
- CID 743395 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
check_return: Calling function "lseek(fd... - 05:15 PM Revision bb8798e3 (ceph): mds/Locker.cc: fix dereference after null check
- CID 716917 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to fun... - 05:15 PM Revision 3969c695 (ceph): mds/Locker.cc: fix dereference after null check
- CID 716918 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to fun... - 05:15 PM Revision 59cffbab (ceph): mds/Locker.cc: fix dereference after null check
- CID 716919 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "cap" to fu... - 05:15 PM Revision 5d8440e3 (ceph): mds/MDCache.cc: fix dereference after null check
- CID 716921 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "dir" to fu... - 05:10 PM Revision c5fc52ae (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:10 PM Revision b1312f94 (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 04:39 PM Revision 8f3f0537 (ceph): rgw: Do not assum rest connection to be established
- Added a check to verify that rest connection is correctly initialized,
preventing a segmentation fault.
Signed-off-b... - 04:21 PM Bug #5226 (Won't Fix): Some PG stay in "incomplete" state
- Hi,
With bobtail I first loose the OSD.25 : the OSD process was crashing, and when its data are ballanced on other... - 03:55 PM Bug #4855: peek map assert
- root@ceph2:/var/log/ceph# ceph -v
ceph version 0.61.2 (fea782543a844bb277ae94d3391788b76c5bee60)
Hit this rep... - 03:35 PM Bug #5225 (Closed): arm: rbd fsx test failed on the arm set up
- rbd fsx test failed with core dump on the client.
logs are copied to ubuntu@burnupi24:/home/ubuntu/arm_testing_lo... - 03:19 PM Bug #5163: filestore: ENOTEMPTY on object removal
- The teuthology logs are copied to ubuntu@burnupi24.front.sepia.ceph.com:/home/ubuntu/bug5163/testing_logs_rados_python
- 03:16 PM Bug #5163: filestore: ENOTEMPTY on object removal
- This happened when running rados_python test on the arm test setup....
- 03:17 PM Bug #4579 (Resolved): kclient + ffsb workload makes osds mark themselves down
- e21f8df1eb0c459d12911785c69f7427d1ad5689
- 03:16 PM Bug #5216 (Resolved): restarted or failed osd resulted in a lot of caller_ops.size error messages...
- 11:25 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- The stalled I/O seems to come from the freshly started OSDs. They seem to tell ceph hey i can handle I/O but they're ...
- 11:24 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- this is the backport:
commit 2af3f1d40b9c64f58d1a05232c52b2a47426fef5
Author: Samuel Just <sam.just@inktank.com>
... - 11:12 AM Bug #5216 (Pending Backport): restarted or failed osd resulted in a lot of caller_ops.size error ...
- pushed fix to master, needs backport to cuttlefish
Note, this probably did not cause the IO hang. - 06:51 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- So i get the caller_ops.size 3002 > log size 3001 messages while the osd is offline and i get the slow request messag...
- 06:36 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- To me it seems that the osd sets itself online / available before it is really ready which then results in slow I/O.
... - 05:33 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- Then the whole ceph storage became instable until the osd is up and running again and had recovered.
- 05:32 AM Bug #5216 (Resolved): restarted or failed osd resulted in a lot of caller_ops.size error messages...
- I'm running upstream/cuttlefish 85ad65e294f2b3d4bd1cfef6ae613e31d1cea635
I've seen the following today while just ... - 03:16 PM Bug #5223 (Resolved): ./osd/OSDMap.h: 387: FAILED assert(exists(osd))
- 02:59 PM Bug #5223 (Resolved): ./osd/OSDMap.h: 387: FAILED assert(exists(osd))
- 13-05-31 03:07:57.486103 7fe8cc625700 0 -- 10.214.132.10:6801/30895 >> 10.214.131.23:6805/9730 pipe(0x211cc80 sd=70 ...
- 03:16 PM Bug #5224 (Resolved): too many open fds
- 03:11 PM Bug #5224 (Resolved): too many open fds
- 02:37 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- :/
0.61.2
[root@test-ceph-1001 ~]# yum list ceph
Loaded plugins: security
Installed Packages
ceph.x86_64 ... - 09:36 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- This fix landed in 0.61.1. Please try that (or a newer) version and see if you're still hitting it.
- 09:22 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- I hate to kick a dead horse, but did this make it into 0.63 or will it be available in a later release? Ran into this...
- 02:21 PM rbd Bug #5220: test_ls_snaps segfaults on the arm test setup
- recopying the yaml...
- 02:20 PM rbd Bug #5220 (Resolved): test_ls_snaps segfaults on the arm test setup
- Test setup: Tala002, Tala003, Tala004
this happens when trying to run rbd/workloads/c_api_tests.yaml on the arm te... - 01:17 PM rgw Bug #5197: Bucket shows up when listing buckets but does not exist anywhere else.
- And #5219 covers the "user check" not cleaning up.
- 01:09 PM rgw Bug #5197 (Resolved): Bucket shows up when listing buckets but does not exist anywhere else.
- Okay, so the bucket rm didn't work because the object's not on disk, so the initial stat fails, and the radosgw-admin...
- 01:17 PM rgw Feature #5219 (New): "radosgw-admin user check" should handle non-existent buckets in index
- Right now, if "radosgw-admin user check" encounters a bucket whose object doesn't exist it uses default values (becau...
- 01:04 PM rgw Feature #5218 (New): rgw: make bucket removal "atomic"
- Right now, bucket removal consists of two steps:
1) Remove the bucket object (making sure the bucket index doesn't l... - 12:04 PM devops Feature #5019 (In Progress): arm: gitbuilder for ARM
- The arm kernel gitbuilder is now building bootable kernels. No debug yet.
- 12:00 PM Fix #3188 (In Progress): osd: close read hole
- 11:33 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Some more details about my setup:
Hosts are CentOS 6.4 + elrepo kernel-ml. Ceph is cuttlefish (0.61.2) from official... - 10:54 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- I just want to add that I am definitely seeing this behavior on Cuttlefish. We run a number of VM's atop RBD. Any tim...
- 11:01 AM rgw Bug #5209 (Resolved): rgw: crash when head contains unexpected data (when getting range of bytes)
- Fix is reviewed and in the next branch, commit:c5fc52ae0fc851444226abd54a202af227d7cf17. Cherry-picked back to cuttle...
- 11:01 AM Bug #4813 (Resolved): pgs stuck creating
- 11:00 AM rgw Bug #5204 (Resolved): rgw: copy object leaks tail
- Fix is reviewed and in next branch, commit:b1312f94edc016e604f1d05ccfe2c788677f51d1. Cherry-picked to cuttlefish and ...
- 09:58 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
As a work around, the xfsprogs rpm is available from the Centos 6 repository, however installing that may result in...- 09:35 AM devops Feature #5217 (Rejected): Add "Ceph" to all Ceph package descriptions
- A number of the Ceph packages such as librbd and librados do not have "Ceph" in the package title. This makes it har...
- 07:06 AM Bug #4357 (Can't reproduce): osd: FAILED assert("join on thread that was never started" == 0)
- I'm closing this one for now. It hasn't popped up anymore, when it does, I'll re-open.
- 05:39 AM Revision fbf5a242 (ceph): Merge branch 'wip-5046'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:19 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Then a component is missing on my test system (Debian 7 wheezy).
After rebooting the filesystem is not mounted whe... - 05:07 AM Revision 64eb6df9 (ceph): valgrind: add another leveldb suppression
- 04:43 AM Revision df2d06db (ceph): mon: destroy MonitorDBStore before g_ceph_context
- Put it on the heap so that we can destroy it before the g_ceph_context
cct that it references. This fixes a crash li... - 03:28 AM Revision f4eddd7b (ceph): doc: Updated to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 474bb164 (ceph): doc: Updated title and syntax to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 7365d0c3 (ceph): doc: Updated to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:26 AM Revision eb35d739 (ceph): doc: Updated title to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:25 AM Revision 65294bf6 (ceph): doc: Updated conf with ServerAlias for S3 subdomains.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:24 AM Revision 442f082a (ceph): doc: Updated object storage quick start for S3-style subdomains.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:22 AM Revision 5e450baa (ceph): doc: Updated text with new glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:21 AM Revision c4001b12 (ceph): doc: Removed FAQ from the index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:21 AM Revision d52b8055 (ceph): doc: Removed FAQ doc. It's now in the wiki.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:25 AM Revision 131dca7d (ceph): debian: sync up postinst and prerm with latest
- - do not use invoke-rc.d for upstart
- do not stop daemons on upgrade
- misc other cleanups
This corresponds to the ... - 12:23 AM Revision cf9aa7a0 (ceph): debian: guard upstart {start,stop} with -x check
- Sigh.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:17 AM Revision a4001053 (ceph): Merge branch 'wip-deb-removal' into next
- Tested by Tamil, Gary.
05/30/2013
- 11:38 PM Revision 6bac8ac0 (ceph): rbd/kernel.sh: quit looking for snapshot sysfs entries
- The sysfs entries for snapshots went away a while ago, and this
script used them to verify sizes matched what was exp... - 11:27 PM Revision 38ed3e43 (ceph): Merge pull request #334 from ceph/wip-mon
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:22 PM Revision 1d75b49c (ceph): debian: add radosgw.postinst
- Start radosgw-all job.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:22 PM Revision d126a205 (ceph): debian: invoke-rc.d does not work with upstart jobs
- Broken by 19c5ac37ef87aeb3d3c30aa35cd61b6f3a8414bf.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:54 PM CephFS Bug #4753 (Resolved): mds/Locker.cc: 4167: FAILED assert(0)
- fixed this in commit:482733e9603e47a3a427b17bfb9b9189dacd5109
- 10:53 PM Revision 446e0770 (ceph): fix test users of LevelDBStore
- Need to pass in cct.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:44 PM Revision ec7731f7 (ceph): move log, ondisklog, missing from PG to PGLog
- PG::log, PG::ondisklog, PG::missing are moved from PG to a new PGLog
class and are made protected data members. It is... - 10:42 PM Revision d1b3eebd (ceph): os/WBThrottle: remove asserts in clear()
- cur_ios, etc may not be zero due to an in progress
flush.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed... - 10:23 PM Bug #5171 (Resolved): After crash monitor trying to bind to address of other monitor
- Denis reports that #5203 fix should resolve this one as well. Thanks!
- 10:22 PM Bug #5203 (Resolved): mon: backup monmap for sync appears to drop correct monitor names?
- fix is merged, commit:626de387e617db457d6d431c16327c275b0e8a34, and backported to cuttlefish.
Denis, can you open ... - 10:20 PM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Good. Looks like solution for #5171 too (unsure about all cases, but I still too distubed to remember precise - happe...
- 10:24 AM Bug #5203 (Fix Under Review): mon: backup monmap for sync appears to drop correct monitor names?
- 10:23 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- 10:19 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- proposed fix in wip-5203
- 09:15 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Edit: crash log had nothing to do with this bug. It's an entirely different issue regarding pick_addresses().
- 08:43 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Verified by forcing a monitor to sync and to assert out before actually synchronizing (using --mon-sync-requester-kil...
- 08:17 AM Bug #5203 (Resolved): mon: backup monmap for sync appears to drop correct monitor names?
- Came across this one while debugging one of saaby's mon crashes.
Apparently, saaby (@ #ceph) recreated a monitor u... - 10:18 PM Bug #5177 (Rejected): logrotate.conf: "which /etc/init.d/ceph reload"
- Ah, ok. THanks!
- 10:08 PM Bug #5177: logrotate.conf: "which /etc/init.d/ceph reload"
- Oh, sorry, there are not your bug. This is Gentoo ebuild "sed" result.
- 10:04 PM Revision 3cc0f3d8 (ceph): Merge pull request #335 from ceph/wip-5176
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 09:57 PM Revision 7802292e (ceph): os/LevelDBStore: add perfcounters
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:38 PM Bug #5215: mon: hang during sync with mon thrashing
- yeah, this one too:
ubuntu@teuthology:/a/teuthology-2013-05-30_18:12:14-rados-next-testing-basic/26830$ - 09:37 PM Bug #5215 (Resolved): mon: hang during sync with mon thrashing
- mon syncs for a while and then stops/get stuck. i think this job failed yesterday, too, so it is likely easy to repr...
- 09:36 PM Revision a47ca583 (ceph): mon: make compaction bounds overlap
- When we trim items N to M, compact over range (N-1) to M so that the
items in the queue will share bounds and get mer... - 09:28 PM rbd Bug #3925 (In Progress): krbd: sysfs write lockdep warnings
- Well shit.
I unmapped my image and I got a lockdep error.
I'll look some more tomorrow.... - 09:26 PM rbd Bug #3925 (Resolved): krbd: sysfs write lockdep warnings
- I have my answer. The problem does not show up
now that the snapshot sysfs files are gone.
I'm marking this bug ... - 08:48 PM rbd Bug #3925: krbd: sysfs write lockdep warnings
- Well that was fun. I reproduced the problem immediately with:...
- 07:14 PM rbd Bug #3925 (In Progress): krbd: sysfs write lockdep warnings
- Since I've been unable to reproduce this problem with
current code, I'm going to try reproducing it using
code that... - 04:42 PM rbd Bug #3925: krbd: sysfs write lockdep warnings
- I just committed the following change to the
rbd/kernel.sh workunit in the "master" branch
of the ceph git reposito... - 09:05 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- Oh, now I know what's happening. The "kernel.sh" script
was looking at the snapshot sysfs files, which are no
long... - 08:56 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- I have tried to reproduce this a bunch of times, both
manually (as I described, using the refresh sysfs file)
and u... - 09:26 PM Revision f628dd0e (ceph): os/LevelDBStore: merge adjacent ranges in compactionqueue
- If we get behind and multiple adjacent ranges end up in the queue, merge
them so that we fire off compaction on large... - 09:17 PM Revision e9c32b97 (ceph): doc: note openstack changes for Grizzly
- These are just for the cinder configuration, nothing else changed.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:29 PM Revision 743c5287 (ceph): doc: Hadoop clarifications
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:29 PM Revision 352b7b59 (ceph): doc: start Hadoop installation docs
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:20 PM Revision 5fa098f1 (ceph): Added -r option to usage
- Added the -r option, which starts the radosgw and apache2 to access it
to the usage message.
Signed-off-by: Christop... - 06:43 PM Revision 8b7ca687 (ceph): mon: Monitor: backup monmap using all ceph features instead of quorum's
- When a monitor is freshly created and for some reason its initial sync is
aborted, it will end up with an incorrect b... - 06:42 PM Revision 1ba14336 (ceph): Merge pull request #333 from ceph/wip-5203
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:30 PM Revision 61ed69b5 (ceph): use cuttlefish branch instead of master
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:25 PM Revision d029abfa (ceph): valgrind: update suppressions for leveldb, libc leaks from mon
- These result in clean valgrind leak checks on the mon (at least with my
limited vstart testing). - 06:23 PM Revision 02ef6e91 (ceph): osd: do not assume head obc object exists when getting snapdir
- For a list-snaps operation on the snapdir, do not assume that the obc for the
head means the object exists. This fix... - 06:17 PM Revision 3c570616 (ceph): mon: return instead of exit(3) via preforker
- This lets us run all the locally-scoped dtors so that leak checking will
work.
Signed-off-by: Sage Weil <sage@inktan... - 06:17 PM Revision c888d1d3 (ceph): mon: fix leak of health_monitor and config_key_service
- Switch to using regular pointers here. The lifecycle of these services is
very simple such that refcounting is overk... - 06:10 PM Bug #5198 (Duplicate): osd: powercycle testing triggers corrupt object data on xfs
- oh, this is a dup of #4976
- 05:40 PM Feature #3848 (Resolved): osd: gracefully handle cluster network heartbeat failure
- 05:27 PM devops Bug #5210 (Resolved): ceph_deploy: purge and purgedata fails on ceph master branch
- daemons weren't getting stopped. fixed as of commit:cf9aa7a0037e56eada8b3c1bb59d59d0bfe7bba5
- 12:53 PM devops Bug #5210 (Resolved): ceph_deploy: purge and purgedata fails on ceph master branch
- test set up: plana08...
- 05:26 PM Bug #5206 (Resolved): debian: daemons stopped on upgrade
- fixed as of commit:cf9aa7a0037e56eada8b3c1bb59d59d0bfe7bba5
- 09:30 AM Bug #5206 (Resolved): debian: daemons stopped on upgrade
- wip-deb-removal
- 05:21 PM Revision 626de387 (ceph): mon: Monitor: backup monmap using all ceph features instead of quorum's
- When a monitor is freshly created and for some reason its initial sync is
aborted, it will end up with an incorrect b... - 05:17 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
- Need kernel gitbuilders for centos 6.3 or 6.4, Fedora18, OpenSuse 12.2 or 12.3 and sles11sp2.
The centos and fedora ... - 04:27 PM Bug #5200 (Resolved): mon: valgrind leaks
- 11:24 AM Bug #5200 (Fix Under Review): mon: valgrind leaks
- 10:02 AM Bug #5200 (In Progress): mon: valgrind leaks
- 03:53 PM Revision 59916b8e (ceph): debian: stop radosgw daemons on package removal
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:53 PM Revision 9e658f03 (ceph): debian: stop sysvinit ceph-mds daemons
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:51 PM Revision 70a38320 (ceph): debian: only stop daemons on removea; not upgrade
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:29 PM Subtask #5213 (Resolved): unit tests for src/osd/PGLog.{cc,h}
- "work in progress":https://github.com/dachary/ceph/tree/wip-5213
Focus on the functions related to log merging ( m... - 03:10 PM Revision f4025687 (ceph): rbd/concurrent.sh: probe rbd module at start
- There's no guarantee the rbd module is loaded when this script is
run, so add a line that loads it if necessary.
Sig... - 03:06 PM rbd Documentation #5212 (Closed): doc: link to recommended kernel version from pages that describe us...
- Default kernels like 3.2 in ubuntu precise are missing a lot of bug fixes for rbd and cephfs.
The docs recommend k... - 03:05 PM Revision 2957d68c (ceph): rbd_concurrent: add new task to test concurrent.sh
- Add a new kernel task to run the rbd concurrent test.
Signed-off-by: Alex Elder <elder@inktank.com> - 03:04 PM Bug #5176 (Pending Backport): leveldb: Compaction makes things time-out yielding spurious elections
- merged ito next, commit:3cc0f3d803c376167175dd9082dc24f76ee1bd7a
- 11:29 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- sylvain reports:...
- 03:04 PM rgw Bug #5197 (In Progress): Bucket shows up when listing buckets but does not exist anywhere else.
- Looking at the cluster indicates that indeed, there's an orphaned omap entry on the <user>.buckets object, that doesn...
- 12:28 PM rgw Bug #5197: Bucket shows up when listing buckets but does not exist anywhere else.
- This was an empty bucket created under argonaut. It was deleted normally while an argonaut->bobtail upgrade was "in p...
- 02:39 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- Yes, but not trivially.
- 02:31 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- Neil Levine wrote:
> Yehuda, can we close this?
Can this be backported to bobtail?
- 02:08 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- udev shoudl trigger ceph-disk active after the reboot to bring the osd back up; no fstab entry should be necessary (p...
- 12:53 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Something like...
- 01:55 PM devops Bug #5211 (Resolved): ceph-disk prepare: list_partitions() shouldn't return disks
- @# ceph-disk-prepare /dev/sda
ceph-disk: Error: Device is mounted: /dev/sdak1@
list_partitions('/dev/sda') will o... - 01:45 PM Bug #5157 (In Progress): install: unable to pull ceph rpm packages on fedora18
- The install is failing because the epel repository is not configured.
The work around is to configure the repo:
... - 01:41 PM Bug #5188 (Resolved): ceph-deploy nightlies failing
- tested this locally and it works fine.
- 01:14 PM Bug #5188: ceph-deploy nightlies failing
- related to bug#5210
- 01:14 PM Bug #5188: ceph-deploy nightlies failing
- modified the yaml for ceph-deploy to pick cuttlefish branch instead of master.
- 01:18 PM rgw Bug #5209 (In Progress): rgw: crash when head contains unexpected data (when getting range of bytes)
- 12:45 PM rgw Bug #5209 (Resolved): rgw: crash when head contains unexpected data (when getting range of bytes)
- We ended up with a multipart object that had head with data (some old argonaut issue?). A request to retrieve only pa...
- 11:38 AM devops Bug #5208 (Resolved): Debian Wheezy Needs the 'ca-certificates' package before you can wget the p...
- 'ceph-deploy install...' needs the ca-certificates or you get :
pushy.protocol.proxy.ExceptionProxy: Command 'wget -... - 11:23 AM Bug #5183 (Resolved): occasional failure of rbd DiffIterateStress test
- 11:09 AM rgw Feature #5207 (New): rgw: make listing non-standard bucket names through S3 api configurable
- Buckets that were created through the swift api and do not conform to the S3 naming requirements can be listed. Make ...
- 09:37 AM rgw Bug #5204 (In Progress): rgw: copy object leaks tail
- 09:03 AM rgw Bug #5204 (Resolved): rgw: copy object leaks tail
- Problem is that we end up overriding the copied object tag with the original tag.
- 09:24 AM Bug #5205 (Resolved): mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_address...
- This is the crash's log (from saaby @ #ceph):...
- 08:14 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The following has been committed to the ceph-qa-suite
"master" branch:
2957d68 rbd_concurrent: add new task t... - 08:11 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The following has been committed to the ceph "master" branch:
f402568 rbd/concurrent.sh: probe rbd module at s... - 07:40 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The cleanup routine run when concurrent.sh exits is
run after a call to "wait", so all background tasks
should be d... - 05:50 AM rbd Bug #3978 (In Progress): krbd qa: concurrent.sh test leaves something read-only
- I've been running this test this morning and am finding it
is *not* exhibiting the problem that I originally reporte... - 07:35 AM devops Documentation #5202 (Rejected): "ceph osd stop" not available
- The documentation at http://ceph.com/docs/master/rados/troubleshooting/troubleshooting-osd/#stopping-w-out-rebalancin...
- 05:45 AM Revision c410f032 (ceph): Merge pull request #331 from ceph/wip-osd-interfacecheck
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:44 AM Revision bd2ba0e3 (ceph): Merge branch 'next'
- 05:43 AM Revision 0c059551 (ceph): osd: wait for healthy pings from peers in waiting-for-healthy state
- If we are (wrongly) marked down, we need to go into the waiting-for-healthy
state and verify that our network interfa... - 05:43 AM Revision e1dc3fd3 (ceph): osd: augment osd heartbeat peers with neighbors and randoms, to up some...
- - always include our neighbors to ensure we have a fully-connected
graph
- include some random neighbors to get at ... - 05:43 AM Revision b586f4a9 (ceph): osd: factor out _remove_heartbeat_peer
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:43 AM Revision a4d3b47a (ceph): osd: only add pg peers if active
- We will soon be in this method for the waiting-for-healthy state. As
a consequence, we need to remove any down peers... - 05:43 AM Revision 28ea184d (ceph): osd: remove down hb peers
- If a (say, random) peer goes down, filter it out.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:43 AM Revision 04aa2b5e (ceph): osd: distinguish between definitely healthy and definitely not unhealthy
- is_unhealthy() will assume they are healthy for some period after we
send our first ping attempt. is_healthy() is no... - 05:21 AM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- There has been another iteration of this bug happening on PGMonitor (from user saaby on IRC):...
- 05:06 AM Feature #2283: The ceph command should time out
- I'm hitting this too ... I wanted to monitor the health more closely with the recent mon issues unfortunately it oft...
- 04:58 AM Revision d20e30a7 (ceph): flushed the formatter after closing the primary section in MDLOG, BILOG...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 12:04 AM devops Feature #5019: arm: gitbuilder for ARM
- Took some futzing but I got the builds working. Unfortunately it did build an armel image as it looks like the auto d...
05/29/2013
- 11:53 PM Revision d86b9a85 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 11:50 PM Revision 85ad65e2 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 11:50 PM Revision 50ac8917 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 10:54 PM Bug #5201 (Resolved): osd: valgrind leaks
- 10:54 PM Bug #5200 (Resolved): mon: valgrind leaks
- 10:06 PM Revision e21f8df1 (ceph): Merge branch 'wip_osd_throttle'
- Fixes: #4782
Reviewed-by: Sage Weil - 10:05 PM Revision a55e03cd (ceph): WBThrottle: add some comments and some asserts
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:05 PM Revision 4b31c7e7 (ceph): WBThrottle: rename replica nocache
- We may want to influence the caching behavior for other
reasons.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:01 PM Bug #5157: install: unable to pull ceph rpm packages on fedora18
- [ubuntu@burnupi23 ~]$ su -c 'rpm -Uvh http://gitbuilder.ceph.com/ceph-rpm-fc18-x86_64-basic/ref/cuttlefish/RPMS/x86_6...
- 08:51 PM devops Bug #4641 (Resolved): ceph-deploy install fails on fedora 18
- tested and it works fine on ceph version 0.61.2
- 08:50 PM Revision 45873b57 (ceph): rgw: verify bucket location only if exists
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:50 PM devops Bug #5199 (Resolved): ceph-deploy: on fedora18, osd create command doesnt seem to mount the disks
- test setup: burnupi22
while osd create command succeeds with no error, the osd disks are not mounted and the osd p... - 08:48 PM Linux kernel client Bug #4646 (Need More Info): kcephfs: writeback pagevec pool size vs stripe unit limit
- I'd like someone (like Sage) to determine whether
we should just mark this "won't fix." - 05:55 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- I implemented a fix for this, and got all the way to
the end of describing it, when I realized the math
makes this ... - 03:56 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- I think an easy fix for now is just to allocate the pagevec_pool
to have objects sufficient to hold pages that would... - 02:35 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- On the osd, it looks to me like CEPH_MDS_OP_SETLAYOUT uses
ceph_file_layout_is_valid() to verify the layout supplied... - 08:41 PM Revision aac828c2 (ceph): osd: tell peers that ping us if they are dead
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:41 PM Revision c093e5bf (ceph): osd: avoid duplicate mon requests for a new osdmap
- sub_want() returns true if this is a new sub; only renew then.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:41 PM Revision 80942eb0 (ceph): osd: move health checks into a single helper
- For now we still only look at the internal heartbeats.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:41 PM Revision ea2b2329 (ceph): osd: simplify is_healthy() check during boot
- This has a slight behavior change in that we ask the mon for the latest
osdmap if our internal heartbeat is failing. ... - 08:23 PM Linux kernel client Feature #4770: krbd: consider including write data with layered existence check
- Removing myself as assignee, I won't have time to complete this.
- 08:22 PM Linux kernel client Bug #4869: libceph: osd_client: get_reply() generalize for more ops
- Removing myself as assignee, I won't have time to complete this.
- 08:09 PM Revision 81a96086 (ceph): rgw: forward delete_bucket to master region
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:28 PM Revision 482733e9 (ceph): mds: stay in SCAN state in file_eval
- If we are in the SCAN state, stay there until the recovery finishes. Do
not jump to another state from file_eval().
... - 05:27 PM Revision 0071b8e7 (ceph): mds: stay in SCAN state in file_eval
- If we are in the SCAN state, stay there until the recovery finishes. Do
not jump to another state from file_eval().
... - 05:27 PM Revision f71e1b1f (ceph): Makefile: include new message header files
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:26 PM Revision 532dee52 (ceph): Merge remote-tracking branch 'yan/wip-mds'
- Reviewed-by: Sage Weil <sage@inktank.com>
Conflicts:
src/mds/MDCache.cc - 05:25 PM Bug #5198 (Duplicate): osd: powercycle testing triggers corrupt object data on xfs
- ...
- 04:53 PM Bug #4967 (Resolved): Misbehaving OSD sets over half of the cluster as down despite "osd min down...
- committed to next, backported to cuttlefish
- 04:15 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- 04:49 PM Revision 29e4e7e3 (ceph): osd: do not assume head obc object exists when getting snapdir
- For a list-snaps operation on the snapdir, do not assume that the obc for the
head means the object exists. This fix... - 04:40 PM rgw Bug #5197 (Resolved): Bucket shows up when listing buckets but does not exist anywhere else.
There is a bucket which shows up when buckets are listed through the api but exists nowhere else. We need to get th...- 04:37 PM Feature #5147: Display unique cluster ID in ceph status
- 03:40 PM Revision 6da4b20c (ceph): mon: compact trimmed range, not entire prefix
- This will reduce the work that leveldb is asked to do by only triggering
compaction of the keys that were just trimme... - 03:35 PM Revision ab09f1e5 (ceph): mon/MonitorDBStore: allow compaction of ranges
- Allow a transaction to describe the compaction of a range of keys. Do this
in a backward compatible say, such that o... - 03:34 PM Revision e20c9a3f (ceph): os/LevelDBStore: allow compaction of key ranges
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:32 PM Revision f03a6f21 (ceph): Fixed default region creation issue
- If the default region did not exist, it is created,
but the previously created RGWDefaultRegionInfo object is not upd... - 03:14 PM Revision 1d0aa2ad (ceph): Merge pull request #329 from javacruft/wip-fuse-deps
- Use new fuse package instead of fuse-utils
- 03:11 PM Revision 3e5cead0 (ceph): rgw: user master region's version of bucket
- When creating a bucket, retrieve the bucket object
version from the master region and use it.
Signed-off-by: Yehuda ... - 03:07 PM Feature #4782 (Resolved): osd: build writeback model to replace async flusher
- 02:47 PM Bug #5195 (Resolved): "ceph-deploy mon create" fails when adding additional monitors
- When trying to add another monitor to an existing cluster with "ceph-deploy mon create <hostname>" the operation fail...
- 02:35 PM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- Whoops, mean to update http://tracker.ceph.com/issues/4646.
- 02:33 PM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- On the osd, it looks to me like CEPH_MDS_OP_SETLAYOUT uses
ceph_file_layout_is_valid() to verify the layout supplied... - 01:59 PM devops Bug #5194 (Resolved): udev does not start osd after reboot on wheezy or el6 or fedora
- ceph-deploy creates a partition with a filesystem (XFS by default) and mounts it to /var/lib/ceph/osd/<clustername>-<...
- 01:53 PM rbd Bug #5040 (Fix Under Review): krbd: record that an parent info refresh has failed
- The following has been posted for review:
[PATCH] rbd: clean up a few things in the refresh path - 01:51 PM rbd Bug #3094 (Fix Under Review): krbd: race between finding existing client and creating new one
- The following has been posted for review:
[PATCH] rbd: protect against duplicate client creation - 08:49 AM rbd Bug #3094 (In Progress): krbd: race between finding existing client and creating new one
- I've been able to reproduce this problem by simply running
five instances of an "rbd map" command for the same image... - 01:43 PM Feature #3848 (Fix Under Review): osd: gracefully handle cluster network heartbeat failure
- 01:39 PM Bug #4801 (Duplicate): osd class path broken on fedora 18?
- 01:35 PM devops Bug #4984 (New): ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- 01:35 PM devops Bug #4984: ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- yes, the problem still exists....
- 01:23 PM devops Bug #5193 (Resolved): RHEL6 does not ship with xfsprogs
- The following commit adds an rpm package dependency on xfsprogs,
https://github.com/ceph/ceph/commit/b2501e91bb8... - 12:42 PM rgw Bug #5192 (Won't Fix): RGW: radosgw-admin user rm --access-key not working on bobtail
- access-key should stil be able to lookup the uid, but the command is failing.
radosgw-admin user rm --access-key=$... - 12:11 PM devops Bug #5047 (Closed): ceph build needs libboost 1.50 for debian sid
- The boost library issue seems to have been resolved upstream.
- 11:48 AM devops Feature #5191 (Rejected): Create gitbuilder for Hadoop v2.x compatible Ceph plugin
- We need a gitbuilder to build the Hadoop / Ceph plugin that is compatible with the Hadoop 2.x line (this is distinct ...
- 11:47 AM rbd Feature #4834 (In Progress): Recompile/package qemu with new version of librbd to enable asynchro...
- QEMU packages built against bobtail (0.56.6) and cuttlefish (0.61.2) with and without the async flush patch are avail...
- 11:45 AM devops Feature #5190 (Rejected): Create Apache Hadoop 2.x gitbuilder
- We need another gitbuilder for the Apache Hadoop 2.x line so that we can develop and test against it.
Let's call it ... - 11:22 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Faidon, it shouldn't affect cuttlefish as much, though that is not clear. That patch would need to be installed on a...
- 11:17 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Igur, a main problem is that we are writing out the pg epoch to the filestore when we don't need to. The second prob...
- 10:40 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- We wrote a test that sequentially reads 1M blocks spreaded by 64Mb offsets (i.e. from different placement groups) an...
- 11:19 AM Bug #5183 (Pending Backport): occasional failure of rbd DiffIterateStress test
- 09:45 AM Bug #5183: occasional failure of rbd DiffIterateStress test
- Looks good.
- 11:18 AM rbd Feature #5005: cinder: switch rbd driver to use librbd instead of the cli tool
- 11:18 AM rbd Feature #5004: cinder: make rbd configuration easier to use
- 11:18 AM rbd Feature #5003: cinder/nova: don't require ceph.conf on a compute host / support multiple clusters
- 10:07 AM devops Feature #5019: arm: gitbuilder for ARM
- Need various flavors of kernel gitbuilders for ARM - both debug and performance
- 10:05 AM devops Bug #5189: ceph-deploy disk prepare fails silently
- When I add another disk to the test VM (/dev/sdc) and create a partition /dev/sdc1 ceph-deploy succeeds with:
ceph... - 09:10 AM devops Bug #5189: ceph-deploy disk prepare fails silently
- Ceph was installed from the cuttlefish Debian/Ubuntu repo (including ceph-deploy).
ceph-deploy was used to create ... - 09:09 AM devops Bug #5189 (Resolved): ceph-deploy disk prepare fails silently
- $ ceph-deploy disk list ceph01-test
/dev/sda :
/dev/sda1 other, ext2, mounted on /boot
/dev/sda2 other
/dev/sd... - 09:58 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- Sylvain, I have a wip-5176 branch that makes us compact in a background thread, and over smaller ranges. Can you giv...
- 09:57 AM Revision e634d9d6 (ceph): Use new fuse package instead of fuse-utils
- The fuse-utils package was deprecated a while ago.
Switch the primary dependency for fuse tools to use
the preferred... - 09:35 AM Bug #4179 (In Progress): osd: memory leak during deep scrub on bobtail
- 08:56 AM Bug #5188 (Resolved): ceph-deploy nightlies failing
- 08:47 AM rbd Feature #5187 (Resolved): rbd: allow unmap using mapped image name
- The umount(8) command has a very useful feature that allows
one to specify *either* the device *or* the directory th... - 08:44 AM rbd Bug #5186 (Won't Fix): krbd: mapping same image produces ambiguous /dev file
- Since it's possible to map the same image more than once,
the mechanism of putting an entry in /dev/rbd/rbd/<image>
... - 08:38 AM rbd Bug #5185 (Closed): rbd: nothing prevents concurrent write mappings
- While attempting to test http://tracker.ceph.com/issues/3094
I learned that nothing prevented me from mapping the sa... - 08:16 AM rbd Bug #5184 (Resolved): libceph: create_singlethread_workqueue() error handling
- In ceph_osdc_init() there are these lines of code:...
- 07:39 AM rbd Bug #5146 (Resolved): krbd: wait for safe callback for writes
- The following has been committed to the ceph-client
"testing" branch:
70c725f rbd: wait for safe callback for... - 07:39 AM rbd Bug #3859 (Resolved): osd_client: define ceph_osdc_clear_request_linger()
- The following has been committed to the ceph-client
"testing" branch:
ebd8324 libceph: add lingering request ... - 07:33 AM Bug #4999: monitor sync failure
- I've been unable to reproduce this while using the debugging info patch.
Finally, yesterday I tried the cuttlefish... - 07:32 AM rbd Bug #4777 (Resolved): krbd: verify a few things in the zeroing routines
- The following has been committed to the "testing" branch
of the ceph-client git respository:
81d7ac5 rbd: flu... - 05:13 AM Revision 1bb4e743 (ceph): mon: disable tdump by default
- Grr.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:10 AM Revision 6afc22a1 (ceph): Merge remote-tracking branch 'gh/last'
- 03:44 AM Revision b6be7857 (ceph): Merge branch 'wip-5172'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 03:40 AM Revision 4af917d4 (ceph): os/LevelDBStore: do compact_prefix() work asynchronously
- We generally do not want to block while compacting a range of leveldb.
Push the blocking+waiting off to a separate th... - 03:39 AM Revision dd35c26e (ceph): osd: fix note_down_osd
- Fix bug introduced in 27381c0c6259ac89f5f9c592b4bfb585937a1cfc.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:39 AM Revision 45b84f39 (ceph): osd: fix hb con failure handler
- Fix a few bugs introduced by 27381c0c6259ac89f5f9c592b4bfb585937a1cfc:
- check against both front and back cons; eit... - 03:26 AM Feature #4929: Erasure encoded placement group
- maybe use erasure encoding from "rozofs":https://github.com/rozofs/rozofs
- 03:24 AM Subtask #5046: Factor out PG logs, PG missing
- Write "tests for pg_missing_t":https://github.com/dachary/ceph/tree/wip-pg_missing_t-tests
- 02:52 AM Revision ce6fc2ed (ceph): Merge pull request #319 from dalgaaf/wip-da-pylint-3
- Fix some smaller Python issues
- 12:51 AM Revision 260179b6 (ceph): Merge branch 'master' into merge
- 12:06 AM Revision 8f4de687 (ceph): Rhel support added
- Fixes: #4946
Signed-off-by: Warren Usui <warren.usui@inktank.com>
05/28/2013
- 10:48 PM Revision 648dcb92 (ceph): Merge pull request #326 from dalgaaf/wip-da-CID-727978
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 10:17 PM Feature #685 (Duplicate): libcephmon: interact with ceph monitors via a library
- 08:58 PM Revision 054e96cf (ceph): v0.63
- 08:48 PM Bug #5183 (Resolved): occasional failure of rbd DiffIterateStress test
- wip-osd-obc-snapdir
- 08:45 PM Bug #5172 (Resolved): wrongly marked down heartbeat issues
- commit:b6be785775442af1999b2543bd07a0d28391dbc5
- 08:39 PM Revision 64d1178f (ceph): rgw: mdlog, bilog RESTful api cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:00 PM Revision fabe7237 (ceph): ceph: first cut at --completion
- Factor out parsing JSON to sigdict; use from both main and completion
Currently invoking from bash completion with
... - 07:57 PM Revision 2dcc266f (ceph): ceph, MonCommands.h: code format/help format tweaks
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:57 PM Revision 65236a4a (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 07:56 PM Revision fca54bfb (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 07:47 PM Revision 5bca9c38 (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 05:41 PM Revision 1c35556b (ceph): doc/dev/osd_internals: add wbthrottle.rst
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:41 PM Revision 4d53e9c9 (ceph): WBThrottle: add perfcounters
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:27 PM Revision e8f52840 (ceph): Merge pull request #325 from dalgaaf/wip-da-CID-727980
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 05:27 PM Revision 16e6b081 (ceph): Merge pull request #324 from dalgaaf/wip-da-CID-727979
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 04:39 PM devops Bug #5182 (Won't Fix): ceph-disk looks like it tries to mark preexisting OSD partitions with the ...
- ceph-disk prepare_dev says, near the end: if not is_partition(data), mark the partition as an OSD
type, udevadm set... - 04:38 PM Bug #5176 (Fix Under Review): leveldb: Compaction makes things time-out yielding spurious elections
- wip-5176
- 04:37 PM Documentation #5181 (Closed): need to explain what does and doesn't work with ceph-deploy and pre...
- ceph-deploy with preexisting partitions is weird; first, they may not be GPT, in which case
ceph-disk activate from ... - 04:17 PM Revision b528a915 (ceph): osd/OSDMap: fix Incremental dump
- The front hb addr entry may not be present.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:43 PM Revision 8e982071 (ceph): Merge pull request #322 from guilhem/patch-1
- Reviewed-by: Sage Weil <sage@inktank.com>
- 01:15 PM Bug #5180 (Resolved): start_split, start_col_split, start_merge must fsync after tagging the in p...
- 11:10 AM Bug #5180 (Resolved): start_split, start_col_split, start_merge must fsync after tagging the in p...
- 10:43 AM Revision 478b576a (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer needed.
CID 727978 (#1-2 of 2): Resource leak (RESOURCE... - 10:38 AM Revision e6efc39f (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer needed.
CID 727979 (#1-2 of 2): Resource leak (RESOURCE... - 10:27 AM Revision 6939b124 (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer
needed.
CID 727980 (#1-4 of 4): Resource leak (RESOURCE... - 09:55 AM rgw Feature #5169: Do not list swift containers when enumerating buckets using S3 API
- Can you provide some more logs for this issue, just to make sure that what we think happens actually happens?
- 09:49 AM Bug #5177 (Need More Info): logrotate.conf: "which /etc/init.d/ceph reload"
- I can't figure out which version has this problem... where do you see the borken reload line?
Thanks! - 09:08 AM Bug #5177 (Fix Under Review): logrotate.conf: "which /etc/init.d/ceph reload"
- 08:57 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- Okay, so you have a 15G monitor store? Is that it? If so, you might have been bit by #4895 and restarting the monito...
- 07:51 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- PPS
1) fix: 15G->30G->15G;
2) In theory, can be fixed by "--inject-monmap", but repair is slow or infinite... - 07:05 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- PS One more issue (I will not open new by same reason): in time of 2 of 3 monitors up and repair after (or in time) t...
- 06:43 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- OK, now I see: sync is tooo slow, but seems to be ready in future. Somebody can answer to this sync speed (fix or wan...
- 03:33 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- No. First I trying to purge/recreate monitor. Now it infinite syncing and not going up. I just in panic (I have ticke...
- 08:51 AM rgw Documentation #5178 (Resolved): rgw: fix keystone openssl to nss conversion
- as specified in here:
[[http://thread.gmane.org/gmane.comp.file-systems.ceph.user/1637]] - 08:35 AM Revision 554b41b1 (ceph): Remove mon socket in post-stop
- If ceph-mon segfault, socket file isn't removed.
By adding a remove in post-stop, upstart clean run directory proper... - 06:08 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- See https://code.google.com/p/leveldb/issues/detail?id=158 and the discussion https://groups.google.com/forum/#!msg/...
- 04:28 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I just disabled compact-on-trim, and it doesn't look good :( It grew about 1GB in 2 hours.
On the plus side, there i... - 05:57 AM Revision 26effc0e (ceph): mds: warn on unconnected snap realms
- When there are more than one active MDS, restarting MDS triggers
assertion "reconnected_snaprealms.empty()" quite oft... - 05:57 AM Revision 03c0fe93 (ceph): mds: reorder EMetaBlob::add_primary_dentry's parameters
- prepare for adding new state parameter such as 'dirty_parent'
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 6c721116 (ceph): mds: journal backtrace update in EMetaBlob::fullbit
- Current way to journal backtrace update is set EMetaBlob::update_bt
to true. The problem is that an EMetaBlob can inc... - 05:57 AM Revision c9d2e256 (ceph): mds: rename last_renamed_version to backtrace_version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision b88c49b7 (ceph): mds: bring back old style backtrace handling
- To queue a backtrace update, current code allocates a BacktraceInfo
structure and adds it to log segment's update_bac... - 05:57 AM Revision 39b5e76c (ceph): mds: update backtraces when unlinking inodes
- unlink moves inodes to stray dir, it's a special form of rename.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 05a7588d (ceph): mds: remove old backtrace handling
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 617f70d2 (ceph): mds: move fetch_backtrace() to class MDCache
- We may want to fetch backtrace while corresponding inode isn't
instantiated. MDCache::fetch_backtrace() will be used ... - 05:57 AM Revision eeb68eb3 (ceph): mds: open inode by ino
- This patch adds "open-by-ino" helper. It utilizes backtrace to find
inode's path and open the inode. The algorithm lo... - 05:57 AM Revision ceaf51f7 (ceph): mds: bump the protocol version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 3120d969 (ceph): mds: open missing cap inodes
- When a recovering MDS enters reconnect stage, client sends reconnect
messages to it. The message lists open files, th... - 05:57 AM Revision 7e0e0963 (ceph): mds: use "open-by-ino" function to open remote link
- Also add a new config option "mds_open_remote_link_mode". The anchor
approach is used by default. If mode is non-zero... - 05:57 AM Revision d7b999be (ceph): mds: don't stop at export bounds when journaling dir context
- We only journal the finish of exporting subtree, so we shouldn't
consider export bounds as subtree root.
Signed-off-... - 05:57 AM Revision 5426c75d (ceph): mds: adjust subtree auth if import aborts in PREPPED state
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 0c1ca8ed (ceph): mds: fix uncommitted master wait
- We may add new waiter while the master is committing. so we should
take the waiters and wake up them when the master ... - 05:57 AM Revision 7a6ec353 (ceph): mds: fix slave commit tracking
- MDS may crash after journalling a slave commit, but before sending
commit ack to the master. Later when the MDS resta... - 05:57 AM Revision 0708d44f (ceph): mds: fix straydn race
- For unlink/rename request, the target dentry's linkage may change
before all locks are acquired. So we need check if ... - 05:57 AM Revision e8497f80 (ceph): mds: fix import cancel race
- Current code uses import state to detect obsolete import discover/prep
message. it does not work for the case: cancel... - 05:57 AM Revision 30c68218 (ceph): mds: fix typo in Server::do_rename_rollback
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 8a1114ce (ceph): mds: remove buggy cache rejoin code
- I previously added code to handle a corner case of cache rejoin:
entire subtree, together with the inode subtree root... - 05:57 AM Revision 38fb2ec7 (ceph): mds: unfreeze inode after rename rollback finishes
- we should not wake up the unfreeze waiter while the inode is still
linked to a non-auth dirfrag.
Signed-off-by: Yan,... - 05:57 AM Revision 882be6b1 (ceph): mds: send slave request after target MDS is active
- when failure of peer is detected, MDCache::handle_mds_failure()
checks if there are requests waiting for slave replie... - 05:57 AM Revision e21f328f (ceph): mds: export CInode::STATE_NEEDSRECOVER
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision fc94f47b (ceph): mds: export CInode:mds_caps_wanted
- CInode:mds_caps_wanted is used to keep track of caps wanted by non-auth
MDS. The auth MDS checks it when choosing loc... - 05:57 AM Revision 2b1b6cae (ceph): mds: notify auth MDS when cap_wanted changes
- So the auth MDS can choose locks' states base on our cap_wanted.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision a918e611 (ceph): mds: fix Locker::request_inode_file_caps()
- After sending cache rejoin message, replica need notify auth MDS when
cap_wanted changes. But it can send MInodeFileC... - 05:57 AM Revision 3962a751 (ceph): mds: defer releasing cap if necessary
- When inode is freezing or frozen, we defer processing MClientCaps
messages and cap release embedded in requests. The ... - 05:57 AM Revision c9707f63 (ceph): mds: Fix replica's allowed caps for filelock in SYNC_LOCK state
- For replica, filelock in LOCK_LOCK state doesn't allow Fc cap. So
filelock in LOCK_SYNC_LOCK/LOCK_EXCL_LOCK state sho... - 05:57 AM Revision 9424298f (ceph): mds: fix check for base inode discovery
- If a MDiscover message is for discovering base inode, want_base_dir
should be false, path should be empty.
Signed-of... - 05:57 AM Revision f3a9f474 (ceph): mds: slient MDCache::trim_non_auth()
- No need to output the function's debug message to console.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 8b4e9911 (ceph): mds: journal new subtrees created by rename
- this avoids creating bare dirfrags during journal replay.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 81d073fe (ceph): mds: fix underwater dentry cleanup
- If the underwater dentry is a remove link, we shouldn't mark the
inode clean
Signed-off-by: Yan, Zheng <zheng.z.yan@... - 04:17 AM Revision a6df7644 (ceph): PendingReleaseNotes: notes about enabling HASHPSPOOL
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:17 AM Revision aa0649c6 (ceph): osdmaptool: fix cli tests
- Now that the default pool flags have changed.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:31 AM Documentation #3808 (Resolved): Block device quick start page need update
- This was verified as working with cuttlefish and ceph-deploy.
- 01:29 AM rgw Documentation #2990 (Resolved): doc: expand/complete RGW S3 API reference
- This is complete now. Todo: A path between Quick Start and using the APIs. S3 subdomain configuration still needs to ...
- 12:28 AM Revision 07408117 (ceph): With mdlog lock and unlock functionality, listing and trimming base on ...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
05/27/2013
- 09:06 PM Revision 8cec56dd (ceph): valgrind: select notcmalloc ceph install flavor
- 08:55 PM Revision f0958c36 (ceph): Merge pull request #321 from dalgaaf/wip-da-CID-727981
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 08:55 PM Revision 35a8c616 (ceph): Merge pull request #320 from dalgaaf/wip-da-CID-727983
- kv_flat_btree_async.cc: fix resource leak
- 07:55 PM Bug #5172 (Fix Under Review): wrongly marked down heartbeat issues
- or wip-5172, don't see wip_5172 :)
- 07:44 PM Revision 0e127dc4 (ceph): mon: Paxos: get rid of the 'prepare_bootstrap()' mechanism
- We don't need it after all. If we are in the middle of some proposal,
then we guarantee that said proposal is likely... - 07:44 PM Revision f29206bd (ceph): mon: Paxos: finish queued proposals instead of clearing the list
- By finishing these Contexts, we make sure the Contexts they enclose (to be
called once the proposal goes through) wil... - 07:44 PM Revision b73d7c6b (ceph): mon: Paxos: finish_proposal() when we're finished recovering
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 2ff23fe784245f3b86bc98e0434b21a53... - 02:54 PM Fix #3188: osd: close read hole
- pushed wip-osd-readhole with some old incomplete work on this. here's a brain dump of where my thinking is/was on th...
- 01:44 PM Bug #5175: leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- i wonder if turning off the compaction will make this grow slowly enough to not be an issue. strangely, i still get ...
- 08:16 AM Bug #5175: leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- Work around for LOG is to use this config :...
- 07:29 AM Bug #5175 (Resolved): leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- leveldb has two files that seem to grow without bound and are only cleared on db open.
The first is the LOG file w... - 01:24 PM Bug #4895 (Resolved): leveldb: mon workload makes store.db grow without bound
- awesome. Sylvain, can you try setting 'mon compact on trim = false' and seeing if it continues to not grow? the ori...
- 01:22 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I've been testing this for the last 5 days and I haven't seen any uncontrolled/fast growth of the mon store like I us...
- 01:19 PM devops Bug #5174 (Resolved): df: ‘/media/osd.0/.’: No such file or directory
- fixed by commit:d81d0ea5c442699570bd93a90bea0d97a288a1e9, backported to cuttlefish branch, but not yet in a cuttlefis...
- 12:29 PM Bug #5171 (Need More Info): After crash monitor trying to bind to address of other monitor
- Do you have the full log for this monitor?
- 10:25 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- > As we can assume client ops are waiting for new OSD map that is issued only after peering finishes.
> It seems tha... - 08:28 AM Bug #5177 (Rejected): logrotate.conf: "which /etc/init.d/ceph reload"
- logrotate.conf: "which /etc/init.d/ceph reload". It always false (if no file "reload" in "."). New log always zero.
... - 07:56 AM Bug #5176 (Resolved): leveldb: Compaction makes things time-out yielding spurious elections
- It seems that compaction can take a few seconds (despite running on 10k SAS disks) and can cause peons to not renew t...
- 07:05 AM Tasks #4560 (Closed): unit tests for src/os/LFNIndex.cc
- There is still more work to be done but another ticket can be re-opened if someone wants to work on it.
- 04:51 AM CephFS Bug #5162: File is locked unexpected and not released anymore
- I tried restart all ceph services by issuing # /etc/init.d/ceph -a restart but didn't solve the problem. However I di...
- 12:44 AM CephFS Bug #5105: mds/CInode.cc: 1996: FAILED assert(auth_pins >= 0)
- I think uncomment MDS_AUTHPIN_SET in src/mds/mdstypes.h would help
05/26/2013
- 10:43 PM CephFS Bug #5162: File is locked unexpected and not released anymore
- >ceph: check_caps ffff880117288848 file_want pFscr used p dirty - flushing - issued pAsLsXsFcb revoking - retain pAsx...
- 08:09 PM CephFS Bug #5162: File is locked unexpected and not released anymore
- Hi Zheng,
Sorry for reply late. Here is the kernel msg.
[ 219.824078] ceph: mdsc delayed_work
[ 219.82... - 07:45 PM devops Bug #5174 (Resolved): df: ‘/media/osd.0/.’: No such file or directory
- In my cluster, there are two machine:
host1: mon/mds
host2: two osd/mon
When i exec" service ceph -a start' on h... - 08:14 AM Subtask #5046: Factor out PG logs, PG missing
- "Ceph placement groups backfilling":http://dachary.org/?p=2009
- 04:16 AM Bug #5173: ceph scrub found missing pg object
- Run ceph pg repair 2.df
Finally, I umounted all osds one by one and checked XFS and mounted back with barriers (we... - 03:27 AM Bug #5173: ceph scrub found missing pg object
- All files have equal md5 sums equal to:...
- 02:34 AM Bug #5173 (Can't reproduce): ceph scrub found missing pg object
- I'm using ceph version 0.56.4 (63b0f854d1cef490624de5d6cf9039735c7de5ca)
All data is 3-times replicated (pools Size ...
05/25/2013
- 11:17 PM Bug #4608 (Resolved): Incorrect RGW apache conf example
- http://ceph.com/docs/master/start/quick-rgw/#create-a-gateway-configuration-file
- 10:13 PM Revision 615b54c6 (ceph): doc: Updated rgw.conf example.
- fixes: #4608
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:11 PM Revision 6f935419 (ceph): doc: Updated RGW Quickstart.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:11 PM Revision e59897c8 (ceph): doc: Updated index for newer terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:27 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Update: seems to work fine if I turn writeback caching back on again (previously turned off before patching).
- 12:24 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Using ceph 0.61.2 and qemu 1.4.2 or earlier versions with the patch:
The following hangs after a few iterations:
... - 03:36 AM Revision b4f63cee (ceph): ceph: --help-all
- Ask first extant daemon of each for its command descriptions and
daemon command descriptions. Suppress commands with... - 03:01 AM Revision ec0371c7 (ceph): ceph: print parameter name for CephString in concise_sig
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:01 AM Revision 99d7bcec (ceph): ceph: fix format strings for Py2.6 compatibility
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:01 AM Revision 1e0222a0 (ceph): ceph: Clean up/add missing docstrings
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:54 AM Revision 52b23b5e (ceph): rgw: propagate region on bucket creation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 02:12 AM Revision 3044fa8b (ceph): rgw: determine owner after effetctive user
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:57 AM Revision 4dafea43 (ceph): rgw: forward request params through upstream REST
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:21 AM Revision aee6665b (ceph): mon: Refactor
- Move some common code into JSON-command-description functions;
switch from char * to string & args
Signed-off-by: Da...
05/24/2013
- 11:21 PM Revision 6d1e14e0 (ceph): pg_pool_t: enable FLAG_HASHPSPOOL by default
- Fixes: #5160
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-b... - 09:27 PM Revision 51876499 (ceph): rgw: enable data sending via http client
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:57 PM Revision f9b58e00 (ceph): rados.py: don't access returned buffers if error/SIGINT
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:57 PM Revision ef4eb4c3 (ceph): PGMonitor: dead code removal
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:56 PM Revision 2c51b91d (ceph): MonCap: add pg r/w to osd capability profile
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 05:56 PM Bug #5172 (In Progress): wrongly marked down heartbeat issues
- wip_5172, going to test later
- 05:22 PM Bug #5172: wrongly marked down heartbeat issues
- 2013-05-23 10:35:22.200882 7fe1668a1700 1 -- 10.214.131.15:0/14951 <== osd.4 10.214.131.14:6803/14730 11 ==== osd_pi...
- 05:20 PM Bug #5172 (Resolved): wrongly marked down heartbeat issues
- ubuntu@teuthology:/a/samuelj-2013-05-23_10:20:47-rados-wip_osd_throttle-master-basic/20593/remote
Despite the bran... - 04:23 PM Bug #5160 (Resolved): Enable good pool behavior FLAG_HASHPSPOOL
- 04:02 PM Bug #5171: After crash monitor trying to bind to address of other monitor
- After it other 2 monitors working (answering) only after restart mon.3
- 03:58 PM Bug #5171 (Resolved): After crash monitor trying to bind to address of other monitor
- Rebooted cluster (3 nodes, 3 monitors). After it one of monitors sync, update database, then die (assertion) and then...
- 02:43 PM Cleanup #4828 (Rejected): dan: don't respond to e-mail via your phone in the bathroom
- I claim this is not a bug, and the behavior is expected. Closing as Rejected; submitter can appeal if he wants to co...
- 02:36 PM Feature #4457: api: add JSON schema/output protocol to rados.py
- 02:36 PM Feature #4547 (In Progress): api: implement self-description for --admin-daemon commands
- 02:36 PM Feature #4548: api: implement self-description for osd/mon tell commands
- 02:33 PM Feature #4455: api: move '--format' into just another command argument
- 02:32 PM Feature #4839: api: make new CLI send old version of commands to old monitors during upgrade
- 02:31 PM Feature #4315: api: create python CLI wrapper for ceph tool; read command descriptions and valida...
- 02:30 PM Feature #4314: api: modify ceph tool to describe own commands
- 02:29 PM rgw Feature #5170 (Resolved): RGW: Object restriping tool to fix large objects from argonaut.
- DHO needs a object restriping tool to read in the extremely large objects from argonaut and write them back into rado...
- 02:28 PM Feature #3849: Track slow PGs and times OSDs marked down
- 02:26 PM Bug #3143: Obsync object verification takes too long
- Apparently DH are maintaining the obsync code more than Inktank now . Perhaps check with them if they want to fix thi...
- 02:26 PM Feature #4982: OSD: namespaces pt 1 (librados/osd, not caps)
- The CRUSH bit of this is just for including the namespace when choosing the PG an object hashes into, right? (ie, the...
- 02:17 PM Feature #4982: OSD: namespaces pt 1 (librados/osd, not caps)
- crush needs to take into account the namespace argument in such a way that hobjects with an empty namespace hash the ...
- 02:03 PM rgw Feature #5169 (New): Do not list swift containers when enumerating buckets using S3 API
- If a user has created containers over swift protocol, they show up in bucket listing over S3, causing problems for an...
- 02:03 PM Feature #4782: osd: build writeback model to replace async flusher
- 12:50 PM Revision 0f547483 (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer
needed to free the resources.
CID 727981 (#3 of 3): Res... - 12:43 PM Revision 7b438e13 (ceph): kv_flat_btree_async.cc: fix resource leak
- Call AioCompletion::release() if the completion is no longer
needed to free the resources.
CID 727983 : Resource lea... - 12:03 PM rbd Feature #4454: openstack: support volume migration in Cinder
- https://blueprints.launchpad.net/cinder/+spec/volume-migration
- 11:59 AM rbd Feature #4085: qemu-rbd: allow storing snapshot of ram associated with snapshot of disk
- 11:59 AM Linux kernel client Feature #4888: krbd: support boot from root file system on an rbd image
- 11:50 AM rbd Feature #5167: openstack: cinder: differential backups
- 11:26 AM rbd Feature #5167 (Resolved): openstack: cinder: differential backups
- Update the backup service in cinder to support a differential backup format, and the rbd driver to output differentials.
- 11:49 AM rbd Documentation #5009: doc: explain how to get qemu packages for each distro
- 11:49 AM rbd Documentation #5006: doc: openstack configuration changes for havana
- 11:48 AM rbd Feature #5168: openstack: cinder: rbd as a backup target
- 11:30 AM rbd Feature #5168 (Resolved): openstack: cinder: rbd as a backup target
- This would allow using a different pool as a backup instead of an object store.
- 11:17 AM rgw Documentation #5166 (Resolved): rgw: dr: async repl and DR documentation
- 11:17 AM rgw Documentation #5165 (Resolved): rgw: multisite: regions and global namespace documentation
- 11:12 AM rgw Feature #4335: rgw: dr: sync processing state: define datastructures
- This is so that agents which get restarted have durable information about what work they were doing before restart, a...
- 11:10 AM rgw Feature #5164 (Closed): rgw: multisite: metadata push notifications: design blueprint
- 10:49 AM rgw Feature #4334 (Fix Under Review): rgw: dr: bucket index log API: implement RESTful API
- 10:49 AM rgw Feature #4333 (Fix Under Review): rgw: multisite: metadata-changes log: implement RESTful API
- 10:49 AM rgw Feature #5008 (Fix Under Review): rgw: bucket metadata changes should be reflected in mdlog
- 10:46 AM Revision 9785478a (ceph): ceph-disk: remove unnecessary semicolons
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:41 AM Revision 16ecae15 (ceph): ceph-disk: cast output of _check_output()
- Cast output of _check_output() to str() to be able to use
str.split().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 10:33 AM Revision 9429ff90 (ceph): ceph-disk: fix undefined variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:29 AM Revision c127745c (ceph): ceph-disk: add missing spaces around operator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:53 AM devops Cleanup #5106 (In Progress): ceph_deploy: install/compile error on wheezy
- commit 61b610fbc841c6943e41f23569ed5f6835d8caed
Author: Gary Lowell <glowell@inktank.com>
Date: Thu May 23 09:23:... - 08:12 AM Linux kernel client Cleanup #2438 (Closed): ceph-client: use BUG_ON() for null auth_client->ops pointers
- Sage added this commit:
27859f9 libceph: wrap auth ops in wrapper functions
...which neatened up the auth calls... - 07:59 AM rbd Bug #3889 (Won't Fix): krbd: handle zero-length requests
- OK, after a little more discussion... We're going to
go the easy route and just close this issue. We'll
continue ... - 07:54 AM Bug #5163: filestore: ENOTEMPTY on object removal
- The object in question was part of an rbd image that a vm was doing a fstrim on when the crash happened.
- 07:46 AM Bug #5163 (Can't reproduce): filestore: ENOTEMPTY on object removal
- I had an osd crash during normal opperation, this could possibly be related to 4927. I was able to restart the osd a...
- 07:23 AM rbd Bug #5146: krbd: wait for safe callback for writes
- Josh has reviewed this patch and the two others I posted
with it. I was testing the three of them together yesterda... - 06:14 AM Revision 580a08c6 (ceph): rgw: multiple fixes and cleanups
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:13 AM Revision 2655c1e4 (ceph): utime: add asctime()
- dump time in a useful format
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:09 AM Revision 79eb61c4 (ceph): Merge branch 'wip_scrub_tphandle' into cuttlefish
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 03:08 AM Revision 8c1c2d98 (ceph): Merge branch 'wip_scrub_tphandle' into next
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 02:42 AM Revision b8a25e08 (ceph): OSD,PG: pass tphandle down to _scan_list
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:42 AM Revision d62716dd (ceph): PG: reset timeout in _scan_list for each object, read chunk
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:42 AM Revision 86822485 (ceph): PG: ping tphandle during omap loop as well
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:30 AM Revision ac6c7783 (ceph): Merge remote-tracking branch 'upstream/wip_scrub_tphandle_bobtail' into...
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 01:52 AM CephFS Bug #5162: File is locked unexpected and not released anymore
- looks like client's fault. try following command on client.5898 and upload debug.txt:
# echo module ceph +p >/sys/... - 12:41 AM Revision 0b50d073 (ceph): PG: ping tphandle during omap loop as well
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:02 AM Revision bb407bfd (ceph): doc: Updated Ceph FS Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:01 AM Revision 7c497d95 (ceph): doc: Added troubleshooting to Ceph FS index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:01 AM Revision 3dda794a (ceph): doc: Added separate troubleshooting for MDS and Ceph FS.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Also available in: Atom