Activity
From 02/24/2012 to 03/24/2012
03/24/2012
- 11:07 PM Revision 24910c3b (ceph): add osd-recovery test
- 11:07 PM Revision 6bf9c957 (ceph): renamed backfill -> osd_backfill
- 11:05 PM Revision ca9a5a4a (ceph): rename backfill -> osd_backfill
- 10:36 PM Revision 22e80874 (ceph): put filestore xattr option in [global]
- ...for test_filestore_idempotent's benefit
- 09:41 PM Feature #2134: qa: smoke suite
- 09:04 PM Feature #1802 (Resolved): qa: test to exercise divergent osd logs
- 03:10 PM Bug #2192: ceph-mon hangs consuming 100% CPU
- Is this reproducible? Are you able to connect to the ceph-mon process with gdb?
- 03:06 PM Bug #2185 (Won't Fix): osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_ran...
- 08:13 AM Feature #2087: lightweight filestore workload generator
- Pushed a working version to ceph's git repository, branch wip-2087 [1]. Feedback would be appreciated.
[1] - https...
03/23/2012
- 08:27 PM Revision 2ec8f27f (ceph): rados_bench: generate_object_name now takes a buffer length
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com> - 05:27 PM Bug #2209 (Resolved): osd: read kb stats not tracked?
- 01:21 PM Bug #2196: `rados bench` will write test objects with a constant oid, under-reporting performance.
- 2ec8f27f58adca40d125051a23547b639ee7d5f6
- 01:21 PM Bug #2196 (Resolved): `rados bench` will write test objects with a constant oid, under-reporting ...
- 12:53 PM rgw Bug #2208 (Resolved): rgw: radosgw-admin temp remove failure
- The radosgw-admin temp remove on congress goes into infinite loop when trying to list the .intent-log pool.
- 11:07 AM Bug #2200 (Can't reproduce): mon: not accepting new connections
- Yehuda's indicated that this might be tied in to networking issues that were ongoing at the time. Given the symptoms ...
- 11:04 AM Bug #2199 (Fix Under Review): mon: get_bl osdmap_full/9583 No such file or directory
- I believe this is fixed in misc-fixes-for-review commit:e08b489d094efe384c3db639af0be765665bee23. Sage needs to revie...
03/22/2012
- 11:09 PM Bug #2200: mon: not accepting new connections
- Okay, that appears to not be it (the connections established and terminated match for clients and are only off by 9 o...
- 10:09 PM Bug #2200: mon: not accepting new connections
- There's not a lot I can do to diagnose this with just logs; the Monitors don't refuse connections like that on their ...
- 09:42 AM Bug #2200 (Can't reproduce): mon: not accepting new connections
- Following a networking downtime and monitors restart (as described in #2199), and following a recovery process, all a...
- 10:00 PM Bug #2199 (In Progress): mon: get_bl osdmap_full/9583 No such file or directory
- Looks like the problem is that the Monitor got elected leader, and while it collected all the state it didn't write i...
- 10:00 AM Bug #2199: mon: get_bl osdmap_full/9583 No such file or directory
- My guess/hope is that this is one of the issues solved by the monitor slurp and other fixes since 0.41, but I haven't...
- 09:41 PM Revision 21a170e8 (ceph): doc: dev/peering.rst edits from Greg
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:12 PM Bug #2207 (Resolved): osd: crash when op length is greater than op input data
- This could happen due to a malicious or buggy client. I caused this with an accidentally empty request, with positive...
- 05:10 PM CephFS Documentation #2206 (Resolved): Need a control command to gracefully shutdown an active MDS prior...
- There is currently no way to gracefully shutdown an active MDS and allow a standby to activate or to transfer the act...
- 04:53 PM Bug #2205 (Won't Fix): mkcephfs throws "No such file or directory" errors when the pwd the script...
- When executing mkcephfs on a new cluster the script throws the message "bash: line 0: cd: /home/matthew/forCeph: No s...
- 03:33 PM Revision 8fa904a6 (ceph): doc: update dev/peering document
- - fix discussion of last epoch started
- define terms for current and past intervals
- describe role of pg info
- rem... - 02:55 PM Revision de867632 (ceph): msgr: fix tcp.cc linkage
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:53 PM Revision fd9935b7 (ceph): cephtool: don't prefix log items
- This just makes it hard to read them.
Signed-off-by: Sage Weil <sage@newdream.net> - 02:46 PM Subtask #2201: Document old design
- +1; I have no idea what this bug is for
- 11:39 AM Subtask #2201: Document old design
- Old design of...what?
(I see now that it's connected to the omap stuff, but if you could include a little more con... - 11:34 AM Subtask #2201 (In Progress): Document old design
- 11:33 AM Subtask #2201 (In Progress): Document old design
- 01:08 PM Bug #2196 (In Progress): `rados bench` will write test objects with a constant oid, under-reporti...
- 11:34 AM Subtask #2204 (Rejected): implement upgrade from old design to new design
- 11:33 AM Subtask #2203 (In Progress): implement new design
- 11:33 AM Subtask #2202 (Rejected): Document new design
- 11:33 AM Feature #2149 (In Progress): osd: use omap for snap collections
- 11:17 AM Feature #2198: add an option to force a down osd to be marked immediately out
- Hmm, yeah, I forgot about that.
Somebody was asking about it; I'm not sure if they cared exactly but I'm sure there ... - 11:08 AM Feature #2198: add an option to force a down osd to be marked immediately out
- Not really, a write will still go to N-1 replicas until the new one is backfilled up through the object's position.
... - 11:00 AM Feature #2198: add an option to force a down osd to be marked immediately out
- It guarantees that you always have the set number of copies on-disk when you get a commit, instead of probably having...
- 10:47 AM Feature #2198: add an option to force a down osd to be marked immediately out
- What's the motivation for doing that? Is it any better than setting the out interval to be something very short?
- 09:14 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- see new wip-osd-hb branch
03/21/2012
- 11:41 PM Revision 2e21adf2 (ceph): Objecter: resend linger_ops on any change
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com> - 11:35 PM Revision b47454b6 (ceph): ObjectStore: add COLLECTION_MOVE to dump
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 11:35 PM Revision 23313ee6 (ceph): FileStore: whitelist COLLECTION_MOVE on replay
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 11:35 PM Revision ec52eeb2 (ceph): FileStore: remove src on EEXIST during collection_move replay
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 11:35 PM Revision 52aff487 (ceph): ObjectStore: Add collection_move to generate_instances
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 09:01 PM Revision 3caa4319 (ceph): ceph: define and use a shell_scripts Makefile variable
- Define a variable "shell_scripts" in the Makefile.in, and use it
along with some pattern rules to avoid some duplicat... - 09:01 PM Revision 1b2a0669 (ceph): ceph-kdump-copy: add tools for saving kdumps
- This puts in place an init script and a command it runs to save a
kernel core dump to a remote server when a panic or... - 08:41 PM Bug #2199: mon: get_bl osdmap_full/9583 No such file or directory
- kept logs for the failing monitor under /var/log/ceph/2199
- 08:26 PM Bug #2199 (Resolved): mon: get_bl osdmap_full/9583 No such file or directory
- Happened on congress (afair, off 0.41). One monitor is out for more than a month. Following network outage, both moni...
- 07:00 PM Revision 6f0f250b (ceph): suite: add missing print statement
- 06:58 PM Revision 8a9a5670 (ceph): suite: fix print statement when summary doesn't exist
- 04:59 PM Feature #2198 (New): add an option to force a down osd to be marked immediately out
- 02:25 PM rgw Bug #2197 (Resolved): rgw: need to throttle incoming requests
- In case we can't handle requests, we'd end up accepting requests indefinitely thus we consume fds endlessly. This wil...
- 01:30 PM Revision d0e8f148 (ceph): doc: update list of debian dists
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:28 PM Revision a608a8fe (ceph): Merge branch 'stable'
- 12:52 PM Bug #2196 (Resolved): `rados bench` will write test objects with a constant oid, under-reporting ...
- (As discussed on @#ceph@, 2012/03/21 -- with thanks to @joshd@)
The command @rados bench@ generates a sequence of ... - 08:21 AM Bug #2178: rbd: corruption of first block
- The next object is whatever the MBR points to. You can find the object name from the sector offset that gdisk gives y...
- 02:55 AM Bug #2178: rbd: corruption of first block
- Hi Josh,
thanks for taking the time to investigate this... And yes, many others show the same behaviour. Is "the n... - 06:50 AM Feature #2127: Save kernel core dumps on all of our test machines
- I seem to remember seeing a reference to 'mkcrashrd', a mkinitrd type script that generates the initrd image the cras...
- 02:00 AM Revision 91c08f6e (ceph): Add watch op to rados.py
- Signed-off-by: Samuel Just <sam.just@dreamhost.com>
- 12:51 AM Revision 72361784 (ceph): Objecter: resend linger_ops on any change
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com> - 12:51 AM Revision 3019d460 (ceph): TestRados: Add watch
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com> - 12:20 AM Revision 2998368a (ceph): rgw: remove unused definition
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:20 AM Revision 4760536f (ceph): rgw: keep pool placement info also in cacheable location
- Mirror the pools placement info, so that we can cache it.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 12:00 AM Revision f1563a66 (ceph): Revert "Objecter: add op->resend_on_any_change"
- This reverts commit c53194d75390dd6d5aa4a9a33f741cbd106e3338.
recalc_linger_op_target is used for linger_ops
Signed...
03/20/2012
- 11:11 PM Revision 2daff0e9 (ceph): ReplicatedPG: osd_max_notify_timeout -> osd_default_notify_timeout
- This setting should not override user specified timeout.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 11:11 PM Revision c53194d7 (ceph): Objecter: add op->resend_on_any_change
- lingers must be resent even if the primary does not change.
Signed-off-by: Samuel Just <samuel.just@dreamhost.com> - 11:11 PM Revision fc7a1bda (ceph): ReplicatedPG: return -EBUSY on delete for objects with watchers
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 10:15 PM Revision 6a5cbec3 (ceph): rgw: replace bucket_id generation
- bucket_id is now string: <global instance id>.<num> where
num is increasing monotonically within the current rgw
inst... - 09:07 PM Feature #2127 (In Progress): Save kernel core dumps on all of our test machines
- I finally have crash dumps getting packaged and sent over to a
remote machine reliably. The problem is that it does... - 06:59 PM Bug #2178: rbd: corruption of first block
- I looked at the block you attached, and compared it to the first 4MiB of my desktop's hard drive. It looks like it co...
- 03:58 AM Bug #2178: rbd: corruption of first block
- Hi *,
any update on this topic? Cause we are working for hours and days with three people to rescue as many images... - 06:41 PM Revision cdd5298d (ceph): v0.44
- 05:59 PM Revision e42fbb70 (ceph): rgw: process default alt args before processing conf file
- this fixes #2189
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 05:52 PM Revision e0b8f7a0 (ceph): rgw: process default alt args before processing conf file
- this fixes #2189
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 05:37 PM Revision 51a07339 (ceph): rgw: incrase socket backlog
- 20 is too small
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 05:25 PM Revision 5b331987 (ceph): rgw: fix internal cache api
- This fixes issue #2190
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 05:14 PM rgw Bug #2193 (Resolved): rgw: .pools.avail is not cached
- Fixed, commit:4760536fe573c702bac8fb1d51213d76059e32dc.
We now mirror the info in the object. Still keeping the om... - 09:28 AM rgw Bug #2193 (Resolved): rgw: .pools.avail is not cached
- Probably due to recent omap changes, we don't cache omap operations. Either we cache it, or just keep available pools...
- 03:10 PM rgw Feature #2194 (Resolved): rgw: replace bucket-marker-ver with better, fast, more scalable solution
- Fixed, commit:6a5cbec38b761d524e699e2a7410a340d093ccca.
- 09:32 AM rgw Feature #2194 (Resolved): rgw: replace bucket-marker-ver with better, fast, more scalable solution
- We use this object in order to create unique prefix for bucket objects (we do it at bucket creation). Instead of this...
- 02:50 PM Revision 815fc3e2 (ceph): suite: failed runs might not have durations
- This was one cause of emails not being sent - stale /tmp/cephtest dirs
fail without recording a duration. - 10:47 AM rgw Bug #2189 (Resolved): rgw: can't change debug level through ceph.conf
- Fixed, commit:e0b8f7a0331b0ceee54a911bb9231cb168eb2d0f.
- 10:28 AM rgw Bug #2190 (Resolved): rgw: cache disabled
- Fixed, commit:5b3319870ea9d6c715c671e006e3a772008e3e78.
- 09:43 AM CephFS Feature #2195 (Resolved): Allow removal of last MDS if there's no filesystem
- Right now you can't remove the last MDS from your cluster, which means that if you aren't using it and it's off you w...
- 05:43 AM Bug #2192 (Won't Fix): ceph-mon hangs consuming 100% CPU
- I have a test setup of two nodes each running 0.43 mds, mon and osd. I mount ceph kernel filesystem at /srv/ceph on b...
03/19/2012
- 11:36 PM Cleanup #2191 (Resolved): reexamine simple_spinlock
- We've got a homebrewed spinlock implementation in src/common/simple_spin.h/cc. It was written so we could use dout in...
- 11:10 PM Revision f923b840 (ceph): OSD: do not hold obc lock in disconnect_session_watches
- ObjectContext::lock is used only for implementing read_lock and
write_lock. PG::lock is used to protect the ObjectCo... - 09:16 PM Revision a65d4136 (ceph): suite, coverage: use absolute dirs for isdir checks
- This fixes the results to wait for all jobs to complete again.
- 06:57 PM Revision bdb72c28 (ceph): filestore_idempotent: get coverage and coredumps
- 06:31 PM Revision 6c8db1a8 (ceph): suite: more results logging
- 05:34 PM rgw Bug #2190 (Resolved): rgw: cache disabled
- in master branch only, due to internal api change.
- 05:33 PM rgw Bug #2189 (Resolved): rgw: can't change debug level through ceph.conf
- 05:12 PM Bug #2188 (Resolved): mon: mds rm should be harder to break things with
- If you run ceph mds rm 0 on a healthy cluster, it breaks the Monitor's world. I'm uncomfortable with the command exis...
- 04:04 PM Bug #2183 (Resolved): osd: lockdep cycle with obc lock and watch_lock
- pushed to master f923b840edec79df5791a7fb7fdec8b0b40f25f1
- 03:33 PM Bug #2183: osd: lockdep cycle with obc lock and watch_lock
- I believe it's inappropriate to hold obc->lock there anyway, pg lock serves that purpose.
- 11:07 AM Bug #2185: osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_range()
- In the wip-rbd-bid branch that I pushed last week I added an option to the rbd tool to create images using existing d...
- 11:01 AM Bug #2185: osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_range()
- should be pretty easy to rebuild the xattr, removing the object would corrupt the rbd image
03/18/2012
- 10:36 PM Bug #2173: MDS crash when start with end of buffer
- I have managed to start mds server after resetting the journal. So I can get my data back.
Thanks very much to all o... - 06:56 PM Revision 7173a8af (ceph): ceph.conf: no comment
- 06:06 PM Revision 7de798f6 (ceph): ceph.conf: set 'filestore xattr use omap = true'
- 05:50 PM Revision 7d2e1056 (ceph): fix teuthology-ls isdir check
- 05:48 PM Revision 94f0ba1e (ceph): run valgrind with cwd set to /tmp/cephtest/archive/coredump
- This lets us capture the vgcore.* files, which always go to valgrind's
cwd.
Fixes: #1953 - 04:09 PM Revision fd851304 (ceph): ReplicatedPG: there should be no object_contexts during on_activate
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 04:08 PM Revision 6c17a7b3 (ceph): Merge branch 'next'
- 04:08 PM Revision 77c08f86 (ceph): osd: fix object_info.size mismatch file due to truncate_seq on new object
- If the first write that creates an object includes a truncate_seq and
truncate_size, we were taking the truncte patch... - 01:46 PM CephFS Bug #2187 (Can't reproduce): pjd chown/00.t failed test 97
- on both ceph-fuse and kclient, nightly_coverage_2012-03-17-a,
> 1727 FAIL scheduled_teuthology@teuthology collection... - 01:43 PM CephFS Bug #2159 (Resolved): ceph-fuse: big_writes option not recognized
- 12:09 PM Bug #2080 (Resolved): osd: scrub on disk size does not match object info size
- 12:09 PM Bug #1953: teuthology: core files aren't archived when using valgrind
- 12:07 PM Bug #2164: osd: scrub missing _, snapset attrs
- this was non-btrfs, right after the new idempotent replay stuff was fixed.
- 10:50 AM Bug #2186 (Can't reproduce): osd: shutdown race
- ...
- 10:07 AM Bug #2180 (Resolved): osd/ReplicatedPG.cc: 3381: FAILED assert(obc->watchers.size() == 0)
03/16/2012
- 11:59 PM Revision 619fe730 (ceph): .gitignore: xattr_bench
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:06 PM Revision 3a6c085e (ceph): heartbeatmap: use utimes(2) instead of futimens(2)
- For poor users with ancient glibc. We don't much care about rename races
here anyway.
Signed-off-by: Sage Weil <sag... - 09:36 PM Revision 63ec06b3 (ceph): osd: remove special handline for head recovery from clone
- This breaks because:
- we don't have the head or current snapset
- get_object_context() creates a new snapset, whi... - 08:49 PM Revision d8bcc1b3 (ceph): config: fix recursive locking of md_config_t::lock
- Signed-off-by: Sage Weil <sage@newdream.net>
Reviewed-by: Greg Farnum <gregory.farnum@dreamhost.com> - 08:30 PM Revision 58c5d5a0 (ceph): osd: ReplicatedPG::create_object_context()
- New helper that creates a new object context.
Signed-off-by: Sage Weil <sage@newdream.net> - 08:30 PM Revision d4addf57 (ceph): osd: re-use create_object_context() in get_object_context()
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:30 PM Revision 15d85af4 (ceph): osd: explicitly create new object,snap contexts on push
- We specifically want to use this during recovery to avoid loading the obc
or ssc for a previous version of the object... - 08:28 PM Revision 01924a22 (ceph): disable rbd thrash workload, #2174
- 08:04 PM Revision 96780bd1 (ceph): osd: create_snapset_context()
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:15 PM Revision 872bdd0d (ceph): osd: ensure we don't clobber other *contexts when registering new ones
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:52 PM Revision 9791035d (ceph): Merge branch 'wip_omap_xattrs'
- 06:44 PM Revision 07b97fe7 (ceph): suite: log results and coverage generation
- Need to figure out where and when results emails are failing.
- 06:40 PM Revision 2a593dda (ceph): RadosModel: test xattrs with omap
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:40 PM Revision a49a1972 (ceph): ReplicatedPG,FileStore: clone should copy xattrs as well
- _make_clone (called from make_writeable) and _rollback_to included
attr reads from head or a clone. In that case, an... - 06:40 PM Revision 14506dc6 (ceph): FileStore: add support for omap xattrs
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:31 PM Revision a5f143d2 (ceph): Merge branch 'wip-msgr4'
- Reviewed-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 06:29 PM Revision 983fd190 (ceph): ObjectMap: add interface for storing xattrs
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:29 PM Revision d8325e50 (ceph): DBObjectMap: implement xattr interface
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:29 PM Revision fdb92748 (ceph): test_object_map: update unit test for xattr
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:29 PM Revision 8fc43179 (ceph): config_opts.h: opts for omap_xattrs
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:29 PM Revision ecd875fe (ceph): tests/: Added xattr bench
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:29 PM Revision b09fb15d (ceph): ObjectMap: use Index object for locking rather than path object
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:28 PM Revision 9fd4a12a (ceph): DBObjectMap: add support for storing xattrs
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:18 PM Bug #2185: osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_range()
- strace indicated we had a missing xattr on
2268 stat("/data/osd0/current/164.2_head/rb.0.0.000000000000__head_DA6... - 06:02 PM Bug #2185: osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_range()
- ...
- 03:33 PM Bug #2185: osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_range()
- Here output from osd.3 after recent crash:
root@fcmsnode3:/data/osd3/current# find 0.0_head
0.0_head
0.0_head/10... - 03:22 PM Bug #2185 (Won't Fix): osd/ReplicatedPG.cc: 5938: FAILED assert(r >= 0) in ReplicatedPG::scan_ran...
- ...
- 06:01 PM Bug #2173: MDS crash when start with end of buffer
- Talked more on irc, soft crack is trying to reset his journal since it looks like at least all his metadata objects a...
- 04:43 PM Bug #2173: MDS crash when start with end of buffer
- osd map file for 'ceph osd getmap 3212 -o /tmp/osdmap'
- 01:31 PM Bug #2173: MDS crash when start with end of buffer
- Greg: look at the osd dump above: all pools are rep size 3.
- 01:13 PM Bug #2173: MDS crash when start with end of buffer
- Did all the pools get set to 3x replication, or are the confused PGs all part of the metadata pool?
- 12:26 PM Bug #2173: MDS crash when start with end of buffer
- Could you attach the output of 'ceph osd dump 3212' and the binary version of that osdmap (ceph osd getmap 3212 -o /t...
- 09:56 AM Bug #2173: MDS crash when start with end of buffer
- Unfortunately we can see that this assert too is caused by ENOENT on an object that really ought to be there, which m...
- 08:19 AM Bug #2173: MDS crash when start with end of buffer
- Can you post an mds log with debug mds = 20 leading up to that last crash?
Resetting the journal is not something ... - 08:15 AM Bug #2173: MDS crash when start with end of buffer
- I managed to insert a empty sessionmap. The server continue starting.
And I get an assert error:... - 05:39 PM Revision 0904c7b7 (ceph): configure: fix warnings
- Finally!
Signed-off-by: Sage Weil <sage@newdream.net> - 05:04 PM Revision f2e6b8d7 (ceph): ReplicatedPG: populate_object_context during handle_pull_response
- A cached objectcontext should always have its watchers populated.
Signed-off-by: Samuel Just <samuel.just@dreamhost.... - 04:43 PM Revision 4cfc34f8 (ceph): leveldb: .gitignore TAGS
- Signed-off-by: Sage Weil <sage@newdream.net>
- 04:40 PM Revision 5db6902b (ceph): leveldb: un-revert
- Accidentally reverted by c2af646b38995ba005140e748a21baba4263e53f.
Signed-off-by: Sage Weil <sage@newdream.net> - 02:33 PM Bug #2080: osd: scrub on disk size does not match object info size
- wip-2080
- 01:33 PM Bug #2184 (Resolved): audit calls to populate_obc_watchers and add watch/notify to RadosModel
- 01:32 PM Feature #2125 (Resolved): osd: put large xattrs in leveldb
- 01:20 PM Bug #2183: osd: lockdep cycle with obc lock and watch_lock
- crashed it with this mutl...
- 01:18 PM Bug #2183 (Resolved): osd: lockdep cycle with obc lock and watch_lock
- ...
- 12:04 PM Bug #2180: osd/ReplicatedPG.cc: 3381: FAILED assert(obc->watchers.size() == 0)
- Hi Sage,
here the according log after upgrading and starting 0.43-1...
Hope it helps,
Oliver.
- 08:56 AM Bug #2180 (Resolved): osd/ReplicatedPG.cc: 3381: FAILED assert(obc->watchers.size() == 0)
- ...
- 10:58 AM Bug #2182 (Resolved): audit osd reads for reads from potentially unstable objects
- In particular, there are places we read object_info and snapset outside of the get_object_context and get_snapset_con...
- 10:50 AM Bug #2181 (Won't Fix): 4051: FAILED assert(!missing.is_missing(soid)) in ceph version 0.43-244-g9...
- v0.43 and this commit from master aren't compatible; the final v0.44 will have a protocol rev to prevent this problem.
- 10:21 AM Bug #2181 (Won't Fix): 4051: FAILED assert(!missing.is_missing(soid)) in ceph version 0.43-244-g9...
- Hi Sage,
here u r. This was the version, which failed, too, after all others didn't help either... Similar with al... - 09:13 AM Bug #2132: FAILED assert(!missing.is_missing(soid))
- Oliver Francke wrote:
> Well,
>
> its tagged as resolved, but today another node died...:
>
> osd/ReplicatedPG... - 05:36 AM Bug #2132: FAILED assert(!missing.is_missing(soid))
- Well,
its tagged as resolved, but today another node died...:
osd/ReplicatedPG.cc: In function 'void Replicated... - 04:19 AM Bug #2178: rbd: corruption of first block
- Here is one of many, where the header is missing:
--- 8-< ---
fcms@fcmsnode3:~$ rbd ls 1320396354
vm-451-disk-1.... - 12:34 AM Revision 8fbd087d (ceph): results: make sure email is sent before anything else fails
03/15/2012
- 06:08 PM Bug #2173: MDS crash when start with end of buffer
- Sorry for mistake.
ceph osd dump -o -:
2012-03-16 09:10:04.887611 mon <- [osd,dump]
2012-03-16 09:10:04.888161... - 06:01 PM Bug #2173: MDS crash when start with end of buffer
- ceph -s:...
- 10:43 AM Bug #2173: MDS crash when start with end of buffer
- Well that's exciting; this means it's an OSD bug.
The meaning of that output is that of your 209 PGs, 185 are happy;... - 05:35 PM Revision 89ccd95a (ceph): osd: maybe clear DEGRADED on recovery completion
- We set degraded if we don't have enough "active" replicas, which excludes
the backfill target. We need to recheck th... - 05:32 PM Revision b4572351 (ceph): Revert "disable rbd thrash workload, #2174"
- This reverts commit 1bec416c7c7ff8a6462d94baaba8e7da73e88ab4.
Fixed with #2174 - 12:58 PM rgw Feature #1941 (Rejected): rgw: revisit bucket removal
- 12:57 PM rgw Feature #785 (Rejected): rgw: fix filesystem backend
- 10:29 AM Bug #2160 (Resolved): active+recovering+degraded+backfill becomes active+clean+degraded when reco...
- 09:49 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- The test that reproduced the problem has now run once to completion
without hitting it. Therefore it's ready to shi... - 08:35 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- ...
- 07:57 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- Thanks Alex. I remember thinking it fixed a race initially, but then going back later and being unable to find the ra...
- 07:43 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- That's excellent Josh. I'll use it, it's basically what I was
thinking of doing anyway, now I'll just use yours. D... - 07:38 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- That analysis of the race looks correct to me. The first unapplied patch in wip-rbd would have fixed this (9a3e22a0ce...
- 07:14 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- ...
- 07:12 AM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- I think I can explain this:
[ 265.117432] INFO: trying to register non-static key.
[ 265.149933] the code is ... - 12:16 AM Revision 826d30f1 (ceph): rgw: remove extra layer of RGWAccess
- Not needed, now that we got rid of RGWFS
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
03/14/2012
- 11:33 PM Revision 80e2a5e8 (ceph): msgr: switch all users over to abstract interface
- This will let us transparently swap implementations out.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:29 PM Revision 1e1453c1 (ceph): msgr: introduce static Messenger::create() function
- Create a new messenger, with whatever implementation is appropriate.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:29 PM Revision d26feffd (ceph): msgr: promote more methods to abstract Messenger interface
- This will be everything that people actually use.
Signed-off-by: Sage Weil <sage@newdream.net> - 11:01 PM Revision c2af646b (ceph): rgw: put_obj() uses bufferlist instead of extra alloc/copy
- makes it cleaner.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 11:01 PM Revision 2b3bfd0c (ceph): rgw: remove fs backend
- was broken anyway
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 10:51 PM Revision 1bec416c (ceph): disable rbd thrash workload, #2174
- 08:53 PM Linux kernel client Bug #2174: rbd: iozone thrashing failure
- I tried reproducing the problem, and although I'm not sure I know
how to recognize it my test did end in failure.
... - 09:54 AM Linux kernel client Bug #2174 (Can't reproduce): rbd: iozone thrashing failure
- consistently failing
- ceph:
log-whitelist:
- wrongly marked me down or wrong addr
- objects unfo... - 08:32 PM Revision e14d428c (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 08:32 PM Revision 2b879905 (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 08:01 PM Revision a81b23e2 (ceph): Merge branch 'next'
- 07:59 PM Revision bec47b57 (ceph): introduce CEPH_FEATURE_OMAP
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:55 PM Revision 8c96fd26 (ceph): leveldb: new .gitignore entry
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:14 PM Revision 20d11714 (ceph): osd: rev cluster internal protocol
- This covers:
- the push/pull changes in 0.43 (which we forgot to protect against; see
#2132)
- the new omap stuff ... - 06:23 PM Bug #2173: MDS crash when start with end of buffer
- Thanks for your responses.
I created this ceph file system with 1 mon, 1 osd, 1 mds. It works perferctly, and I wr... - 04:11 PM Bug #2173: MDS crash when start with end of buffer
- Huh. Is this a new filesystem? Have you had any problems with the RADOS cluster (the OSDs)?
What's happening now i... - 04:16 AM Bug #2173: MDS crash when start with end of buffer
- I also tried: 'ceph-mds -i 1 -d --reset-journal 0'.
It just freeze. - 04:14 AM Bug #2173 (Resolved): MDS crash when start with end of buffer
- My system is ubuntu 11.10 64bit. Mds just crashes when startup.
I noticed the message: 'No such file or directory'... - 04:36 PM Revision a0bcab5a (ceph): ceph-fuse: make big_writes optional via 'fuse big writes'
- Fixes: #2159
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 04:35 PM rgw Bug #2001 (Resolved): radosgw memory leak
- At this point I can't see any other leak (I already fixed one). Doesn't mean that there isn't another one, but I'm re...
- 04:08 PM CephFS Bug #2179 (Resolved): mds: don't crash on nonexistent SessionMap
- Inspired by #2173. When the MDS tries to load the SessionMap it unconditionally decodes it, which causes a crash if t...
- 03:46 PM Feature #2127: Save kernel core dumps on all of our test machines
- http://linux.die.net/man/8/netdump
this mechanism looks simpler? - 02:55 PM Feature #2127: Save kernel core dumps on all of our test machines
- Wed Mar 14 11:14:50 CDT 2012
OK, I got kernel core dumps and crash working in Ubuntu 11.10.
A lot of what I use... - 02:54 PM Feature #2127: Save kernel core dumps on all of our test machines
- Oh, I forgot to mention I also wrote a little program that extracts
identifying information from a dump file that "k... - 02:48 PM Feature #2127: Save kernel core dumps on all of our test machines
- I have been able to generate a core dump on an Ubuntu system.
I have transferred the result using scp to another hos... - 02:16 PM Bug #2178 (Resolved): rbd: corruption of first block
- 01:02 PM Bug #2132 (Resolved): FAILED assert(!missing.is_missing(soid))
- 12:01 PM Bug #2132: FAILED assert(!missing.is_missing(soid))
- Aha, that explains it... the 0.42.2 and 0.43 interaction looks like the culprit here. We should have made them expli...
- 11:37 AM Bug #2132: FAILED assert(!missing.is_missing(soid))
- All cephfs workload. It could be a versioning issue, I don't have the syslogs anymore that would show when I updated ...
- 11:19 AM Bug #2132 (Need More Info): FAILED assert(!missing.is_missing(soid))
- Matthew Roy: What was the nature of the workload? rbd? ceph fs?
- 11:06 AM Bug #2132: FAILED assert(!missing.is_missing(soid))
- Josh Durgin wrote:
> stxShadow saw this as well.
It looks like in stxshadow's case, it was a version mismatch (cr... - 11:23 AM CephFS Cleanup #2177 (Resolved): mds: play nicely with omap
- Convert the MDS to use OMAP properly.
There is at least one specific thing: right now it has optimizations for whe... - 10:46 AM Bug #2176 (Resolved): dependencies not checked by autoconf
- I recently resurrected a build of the user-mode and kernel clients on CentOS and found that I was missing a few packa...
- 10:09 AM rgw Feature #2171: rgw: asynchronously calculate md5
- Actually, I think it'll be easier doing it the other way around. As we already write the object asynchronously we can...
- 10:08 AM Documentation #2175 (Resolved): doc: fix doc build errors
- e.g., http://ceph.newdream.net/gitbuilder-doc/log.cgi?log=a0bcab5a583e6c1fd87430252590ec902d1b6b98
It would be gre... - 09:56 AM Bug #2022: osd: misdirectect request
- Just saw this with a different workload:...
- 09:51 AM CephFS Bug #2071: kclient: pjd mkfifo failures
- hit this again:...
- 09:49 AM rgw Cleanup #2166 (Resolved): rgw: make sure librgw doesn't link against libfcgi
- Fixed, commit:e19417ef55c713e60c61edd0de7c2228953407a1.
- 09:48 AM rgw Bug #2170 (Resolved): librgw references g_ceph_context
- Fixed, commit:5912312c14a6214f4318fd7bfb6fd08714458b6f.
- 12:21 AM Revision 5912312c (ceph): rgw: remove some more globals from librgw
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:04 AM Revision 213a3f5e (ceph): rgw: fix identation
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:04 AM Revision d90298de (ceph): ceph-dencoder: don't use rgw types if configured without rgw
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
03/13/2012
- 11:40 PM rgw Feature #2172 (Resolved): rgw: get chunks asynchronously
- Chunks are read synchronously. We need to have a window of chunks that are read asynchronously (as with PUT).
- 11:38 PM rgw Feature #2171 (Rejected): rgw: asynchronously calculate md5
- When doing a PUT we calculate the md5 of the content (used later for the etag) synchronously. We need to be able to c...
- 11:23 PM Revision a9d18975 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 11:22 PM Revision 60524aba (ceph): Added documentation for building the ceph documentation.
- 09:59 PM Revision b9097619 (ceph): rgw: get rid of references to g_ceph_context where required
- trickling down ceph context.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 08:48 PM Revision e6969258 (ceph): global: drop yellow warning on startup
- Fixes: #2143
Signed-off-by: Sage Weil <sage@newdream.net> - 08:48 PM Revision e455d388 (ceph): doc: update project status/stability blurb
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Reviewed-by: Mark Kampe <mark.kampe@dreamhost.com> - 07:55 PM Revision e5934f10 (ceph): qa: kclient/file_layout.sh: ...
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 06:46 PM Revision 0a2068fc (ceph): Merge branch 'librados-cleanup'
- Reviewed-by: Sage Weil <sage.weil@dreamhost.com>
- 06:46 PM Revision 8f278647 (ceph): librados: split into separate files and remove unnecessary headers
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:46 PM Revision 5f92f338 (ceph): librados: move methods that require an IoCtx to IoCtxImpl
- RadosClient still does a few different things, but at least it
no longer does all the work of an IoCtx.
Signed-off-b... - 06:46 PM Revision db126279 (ceph): ObjectCacher: remove unused and crufty atomic sync operations
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:46 PM Revision 095c3a0e (ceph): OSDMap: make get_pools() const
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
- 06:46 PM Revision 16f99606 (ceph): osd_types: use uint64_t for ObjectExtent offsets and lengths
- This is just client in-memory state, and allows us to address objects >4GiB,
to match the existing librados/Objecter ... - 05:49 PM Revision b90354db (ceph): thrash: put client on separate machine from osds
- This allows us to run kenrel clients (kclient, rbd) against the thrashing
cluster. - 05:09 PM Revision 5c9acbd8 (ceph): gitbuilder: put flavor last
- in case we refine the field later
- 05:02 PM Revision 1a01ccaa (ceph): Pull from new gitbuilder.ceph.com locations.
- Simplifies the flavor stuff into a tuple of
<package,type,flavor,dist,arch>
where package is ceph, kenrel, etc.
typ... - 01:56 PM Bug #2132: FAILED assert(!missing.is_missing(soid))
- stxShadow saw this as well.
- 01:45 PM Cleanup #2143 (Resolved): Remove ALL "don't use this product" warnings
- 01:31 PM Feature #2145 (Resolved): doc gitbuilder
- 12:28 PM Linux kernel client Bug #2064: ceph-client: messenger: nocrc flag not implemented correctly
- Update: the commit had to be rebased, so it's id is now: 4d3e7aa992
- 08:09 AM Linux kernel client Bug #2064: ceph-client: messenger: nocrc flag not implemented correctly
- This is fixed by this commit:
086da4c6f8 libceph: fix inverted crc option logic
That is now present in the c... - 12:26 PM Linux kernel client Bug #2157: ceph: xattr: fix nanosecond display on i_rctime
- This has been fixed in this commit:
260ac0e65b ceph: fix three bugs, two in ceph_vxattrcb_file_layout()
The comm... - 12:26 PM Linux kernel client Bug #2156: ceph: xattr: fix a possible buffer overrun bug
- This has been fixed in this commit:
260ac0e65b ceph: fix three bugs, two in ceph_vxattrcb_file_layout()
The comm... - 12:26 PM Linux kernel client Bug #2155: ceph: xattr: wrong value assumed for "no preferred PG"
- This has been fixed in this commit:
260ac0e65b ceph: fix three bugs, two in ceph_vxattrcb_file_layout()
The comm... - 11:01 AM rgw Bug #2170: librgw references g_ceph_context
- Ouch. Mostly through dout, but there are other references.
- 10:40 AM rgw Bug #2170 (Resolved): librgw references g_ceph_context
- 2012-03-13T00:48:30.009 INFO:teuthology.task.workunit.client.0.err:OSError: /tmp/cephtest/binary/usr/local/lib/librgw...
- 09:31 AM rgw Feature #2169 (Resolved): rgw: api to control bucket placement
- It'd be nice to be able to control which pool the bucket would be placed in when creating it.
- 12:02 AM Revision 98792e93 (ceph): rgw: add more meaningful tests instances of encoded objects
- this completes #2140
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
03/12/2012
- 11:46 PM Revision dfe50bcb (ceph): build-doc: use alternate virtualenv dir, if specified
- The docs gitbuilder will use this to avoid rebuilding the virtualenv on
every build.
Signed-off-by: Sage Weil <sage@... - 10:22 PM Revision 096427d5 (ceph): remove dup ceph tasks from new thrash workloads
- 10:12 PM Revision 6869c576 (ceph): test_idempotent: fix global_init call
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:01 PM Revision 401a5716 (ceph): qa: kclient/file_layout.sh poking
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 09:59 PM Revision 7e0e7ce1 (ceph): rgw: modify bucket instance for encoding test
- This makes 'make check' happy, otherwise we need to create
a bucket name that starts with a period. This version is b... - 09:58 PM Revision 9969bba8 (ceph): FileStore: clarify debug/error output
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 09:58 PM Revision 6ca070ad (ceph): FileStore: ignore ERANGE and ENOENT on replay
- The source object may either not exist or be the wrong size
during replay if the destination object was deleted in a ... - 09:58 PM Revision f20f6ea7 (ceph): test: add test_filestore_idempotent2
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 09:41 PM Revision e19417ef (ceph): Makefile.am, rgw: remove fcgi dependency where not needed
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 09:22 PM Revision 3ff5492c (ceph): rgw: add more meaningful test instances of some encoded objects
- still need to add tests for other objects
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 08:22 PM Revision 31578c19 (ceph): rgw: tone down some log messages
- dout(0) -> dout(1)
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 08:21 PM Revision 452b1248 (ceph): rgw: provide different default values for 'debug rgw'
- Currently rgw and radosgw-admin require different chattiness
defaults.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdre... - 08:21 PM Revision 2c88f85c (ceph): config: alternative config options for global_init()
- We want to be able to provide alternative default config values, than
the ones we set in common/config_opts.h. This c... - 08:13 PM Revision 3833ada8 (ceph): Made the example better with multiple roles.
- 07:33 PM Revision 0a61ffad (ceph): Added some example yaml files and an example parallel execution task.
- 07:11 PM Bug #2168 (Resolved): qa: plana won't select correct kernel for boot
- Just need to run chef once before trying to install another kernel.
- 05:38 PM Bug #2168: qa: plana won't select correct kernel for boot
- 04:26 PM Bug #2168 (Resolved): qa: plana won't select correct kernel for boot
- the grub.cfg has default set to the kernel we want, but it boots up into a different one.
no console, so hard to d... - 07:08 PM Feature #2052 (In Progress): librbd: caching
- 07:08 PM Feature #2053 (New): librados: caching
- 07:01 PM Revision 968d29d1 (ceph): qa: use recent kernel for kernel_untar_build.sh
- Happier on oneiric!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 06:43 PM Revision 93164393 (ceph): rgw: switch ops log flag to use ceph config
- It's turned on by default. So now we're using the
'rgw enable ops log' config param in ceph.conf, instead
of RGW_SHOU... - 06:22 PM Revision c9898f43 (ceph): filestore: fix op_num offset/labels
- Start at 0, not 1.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 06:20 PM Revision 7c753498 (ceph): config: tmap to omap upgrade, true by default
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 05:00 PM Feature #2142 (In Progress): Add support for Ubuntu 12.04 (precise pangolin) in deb repository
- 04:58 PM rgw Feature #2140 (Resolved): rgw: use new encode/decode macros
- 03:01 PM rbd Feature #2167 (Duplicate): rbd: report the allocated size/space of a RBD with "rbd info <rbd name>"
- With "rbd info <rbd name>" it reports the provisioned space, but not the allocated space (rbds are thin provisioned).
- 02:58 PM CephFS Bug #1737: ceph-fuse crash in xlist::remove
- ubuntu@teuthology:/a/nightly_coverage_2012-03-12-b/727
- 01:19 PM rgw Cleanup #2089 (Resolved): rgw: less dout(0) noise?
- Fixed, commit:31578c19ffe9276a3e6495707e72180436ef3272. I've also set different 'debug rgw' default for rgw and rados...
- 01:09 PM Bug #2098 (Resolved): xfs/ext4 non-idempotent transaction
- 12:18 PM Feature #2145 (In Progress): doc gitbuilder
- 11:56 AM rgw Feature #2040 (Resolved): rgw: disable rgw log through ceph.conf
- 10:07 AM Feature #2125: osd: put large xattrs in leveldb
- 09:39 AM Feature #1956 (Resolved): rgw: revisit atomic GET/PUT
- 04:50 AM Revision 2b9e7bc5 (ceph): clusters/fixed-3.yaml: 2 -> 6 osds
- plana nodes have 3 scratch disks... use them!
- 04:32 AM Revision 51d817fe (ceph): Revert "disable s3tests on valgrind/lockdep until #2103 is fixed"
- This reverts commit 9f757ca9511374f6565d74263e242c74e39f8a3f.
- 04:28 AM Revision af445189 (ceph): add rbd, kclient workloads to regression thrash collection
- This will get us some kernel osd_client osd restart coverage.
- 04:16 AM Revision 3bba6b72 (ceph): Makefile: link libfcgi to librgw
- Need this to make a linker error go away on my squeeze dev box. We
probably need to make sure librgw doesn't touch f... - 03:36 AM Revision 945218cc (ceph): qa/workunits/kclient/file_layout: escape *
- Escape * so that it is expanded as root.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
03/11/2012
- 10:24 PM Feature #2020 (Duplicate): collectd: submit plugin upstream
- 09:47 PM Bug #2160 (Fix Under Review): active+recovering+degraded+backfill becomes active+clean+degraded w...
- See wip-2160 for a fix.
- 09:41 PM rgw Cleanup #2166 (Resolved): rgw: make sure librgw doesn't link against libfcgi
- Currently it does, and seems to need to to build on squeeze.
- 09:18 PM Bug #2165 (Resolved): osd: recovering ending with missing
- ...
- 09:16 PM Bug #2164 (Resolved): osd: scrub missing _, snapset attrs
- ...
- 08:03 PM Revision 71e6e62e (ceph): fix typo, ceph-fyuse -> ceph-fuse
- 07:31 PM Revision a8497874 (ceph): filejournal: less log noise
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 03:20 PM Feature #2163: qa: full xfstests on rbd
- iirc xfstests normally wants a block device it is free to mount/umount/reformat/etc. we can do this on top of rbd.
- 03:18 PM Feature #2163 (Resolved): qa: full xfstests on rbd
- 02:49 PM Feature #1929 (Resolved): teuthology: log runtime
- 04:01 AM Revision b84897e5 (ceph): use dbench workunit, not the autotest one
- The autotest one uses an old tarball that doesn't build. Workunit assumes
the dbench package is installed. - 03:15 AM Revision 008cf7fd (ceph): autotest: pull from github.com/ceph/autotest
03/10/2012
- 11:34 PM Revision 2124129e (ceph): workunit: include python2.7 path too
- 04:42 PM Feature #2114 (Resolved): old sepia setup on new hardware
- 04:42 PM Feature #2162 (Resolved): change gcov, notcmalloc gitbuilders to oneiric
- 04:55 AM Revision 0851b747 (ceph): filestore: remove unused bool idempotent
- This was from the old broken mechanism.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 01:07 AM Revision 6980ed98 (ceph): filestore: fix arguments
- From a change that was rebased out; missed this caller.
Signed-off-by: Sage Weil <sage@newdream.net> - 12:42 AM Revision ea34aa59 (ceph): Merge remote branch 'gh/wip-2098'
- Reviewed-by: Samuel Just <samuel.just@dreamhost.com>
- 12:34 AM Revision 9b2a5c5d (ceph): filestore: sync object_map on _set_replay_guard()
- We need to sync the object_map too. We can _almost_ check to see if there
are keys for the object and only do it the... - 12:32 AM Revision 51372a76 (ceph): filestore: guard replay of collection_add
- - set guard on apply
- check guard on replay
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 12:32 AM Revision 6613b415 (ceph): filestore: guard collection_remove replay
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision 13afce83 (ceph): filestore: remove old post-idempotent transaction trigger_commit
- The old strategy was to initiate a commit after any non-idempotent
transaction. This only worked if the transaction ... - 12:32 AM Revision c9550c59 (ceph): omap: add sync method to ObjectMap
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 12:32 AM Revision 808812a2 (ceph): filestore: use proper type for readdir_r tmp
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision a6077f6c (ceph): filestore: pass trans_num into _do_transaction
- This gives us the <op_seq, trans_num, op_num> triple to identify every
constituent operation.
Signed-off-by: Sage We... - 12:32 AM Revision babb1e90 (ceph): add SequencerPosition type
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision e81bc971 (ceph): filestore: fgetxattr helpers/wrappers
- Also, do the getxattr using fgetxattr, to avoid duplicating code. This is
slightly slower probably because we open a... - 12:32 AM Revision 3b47c6ba (ceph): filestore: maintain SequencerPosition during _do_transaction
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision f8a047f2 (ceph): filestore: implement _set_replay_guard, _check_replay_guard
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision e99940d1 (ceph): filestore: guard clone replay
- - set guard xattr on clone, clone_range
- check before applying/replaying
Signed-off-by: Sage Weil <sage.weil@dreamh... - 12:32 AM Revision 63d2c93d (ceph): filestore: fix collection_rename error code
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 12:32 AM Revision dd284c4f (ceph): filestore: guard collection_rename replay
- - check guard on replay
- set guard on apply
Signed-off-by: Sage Weil <sage@newdream.net> - 12:32 AM Revision 4ea6e0d2 (ceph): filestore: guard replay of basic collection ops
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
03/09/2012
- 10:24 PM Revision 11844978 (ceph): levedb: fix commit
- This got reverted back to the old commit, somehow.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 10:13 PM Revision 184b1802 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 10:12 PM Revision 7f9cfdd9 (ceph): RadosModel: fix omap_clear case in RemoveAttrsOp
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 10:03 PM Revision fce180df (ceph): Merge branch 'wip-rgw-encode'
- Conflicts:
src/rgw/rgw_cls_api.h
Reviewed-by: Sage Weil <sage@newdream.net> - 10:01 PM Revision b66cdea6 (ceph): Makefile.am: update link dependencies for some unit tests
- 10:01 PM Revision b4f05788 (ceph): test/encoding/import.sh: fix target directory
- Signed-off-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com>
- 10:01 PM Revision b71d814c (ceph): ceph-object-corpus: added 0.43
- Signed-off-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com>
- 10:01 PM Revision 799e6f97 (ceph): rgw: fix rgw_cls_list_ret ctor
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 10:01 PM Revision 09949b3d (ceph): rgw: various encoding related fixes
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 09:34 PM Revision e43546de (ceph): osd: fix watch_lock vs map_lock ordering
- watch_lock is inside map_lock (and pg->lock), which means we need to
drop it to take pg->lock here. That means verif... - 08:26 PM Revision 80d92528 (ceph): osd: update_heartbeat_peers as needed
- Before, we were being very careful about updating the heartbeat peers if
new PGs were created or when certain types o... - 05:05 PM Feature #2162 (Resolved): change gcov, notcmalloc gitbuilders to oneiric
- 04:39 PM Bug #2098: xfs/ext4 non-idempotent transaction
- merged. passing initial tests. will hammer on it more with sam's new thing.
- 03:31 PM Bug #2161 (Resolved): nonlinear scaling for PGMap::pg_stat encode
- ...
- 02:03 PM rgw Feature #2140: rgw: use new encode/decode macros
- we should add some semi-meaningful test instances for these objects, otherwise all looks good
- 01:34 PM Bug #2103 (Resolved): osd: lockdep error on watch_lock
- 11:07 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- Hrm... well, if that's the case then we should merge the wip-2116 as is, then... putting that on my list
- 10:58 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- I'm not willing to say it's completely gone, but it is starting to seem like it.
In the past few days the cluster ... - 09:04 AM Bug #2160 (Resolved): active+recovering+degraded+backfill becomes active+clean+degraded when reco...
- In a configuration with 3 replicas of each PG (I haven't tested with others), when one of the disks is replaces, some...
- 08:16 AM CephFS Bug #2159 (Resolved): ceph-fuse: big_writes option not recognized
- ...
- 08:06 AM Revision 619244d8 (ceph): rgw: implement dump() for encoders
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:58 AM Revision 2277fb45 (ceph): rgw: add stubs for dencoder test
- still need to add some content to the dump methods
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 12:15 AM Revision 71323ffe (ceph): Merge remote branch 'origin/wip-2139'
- Conflicts:
src/cls_rgw.cc
src/rgw/rgw_rados.cc
src/rgw/rgw_rados.h
Signed-off-by: Yehuda Sadeh <yehuda.sadeh@drea... - 12:14 AM Revision ddc1ab0c (ceph): rados.py: include setattr and rmattr
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
03/08/2012
- 11:54 PM Revision 64e3ffb2 (ceph): Merge branch 'master' of ssh://github.com/ceph/ceph
- 11:18 PM Revision ac28b603 (ceph): ceph: document the way files are laid out
- This adds a document that I wrote about how Ceph client file data
is striped across Ceph objects to the repository. ... - 11:09 PM Revision 1ed1d466 (ceph): librados: fix unit test for omap_get_vals_by_key rename
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:06 PM Revision ce43bd53 (ceph): osd: format time nicely in ops_in_flight output
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:06 PM Revision 934ee487 (ceph): librados: fix map -> std::map in header, string -> std::string
- Signed-off-by: Sage Weil <sage@newdream.net>
- 11:02 PM Revision fafbddd9 (ceph): doc: example of diagnosing radosgw hang
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:55 PM Revision 99cb9945 (ceph): doc: explain how unfound objects happen
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:55 PM Revision 47ce7ade (ceph): doc: make osd failure example include >3 osds
- More realistic.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:46 PM Revision 80864a12 (ceph): testrados: fix omap_get_vals_by_keys call
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:30 PM Revision e7e3baeb (ceph): osd: add zero_to field to PG::OndiskLog; track zeroed region of pg log
- Track which region of the log has been zeroed on disk. This may be
different from tail if 'osd preserved trimmed log... - 10:30 PM Revision ed6cc47b (ceph): filestore: use FL_ALLOC_PUNCH_HOLE to zero, when available
- First try the FL_ALLOC_PUNCH_HOLE fallocate() flag. If we get EOPNOTSUPP,
fall back to writing zeros.
Check for fal... - 10:17 PM Bug #2103 (Fix Under Review): osd: lockdep error on watch_lock
- 04:47 PM Bug #2103 (In Progress): osd: lockdep error on watch_lock
- 10:16 PM Revision 1468d951 (ceph): osd: fix op_wq vs pg->lock ordering
- map_lock
-> pg->lock
-> op_wq
Fixes: #2153
Signed-off-by: Sage Weil <sage@newdream.net>
Reviewed-by: Samuel Just... - 04:07 PM rgw Bug #2139 (Resolved): rgw: no cleanup of index update in case of cancelled operations
- Fixed, merged at commit: 71323ffeda665defdd133d9fd3c40e08952082e4.
- 02:57 PM Feature #2158 (Duplicate): cephtool: helpful error/timeout when no monitor quorum
- 02:44 PM Feature #975 (Resolved): osd: use fallocate(FL_PUNCH_HOLE) for zero
- commit:e7e3baebd6d5d9e3dfbddc77a2312e9f8e4e9da8
- 02:34 PM Feature #2088: msgr: refactor 2 threads to one
- Maybe it's a good time to switch from poll to epoll (where available)?
- 02:30 PM Linux kernel client Bug #2157 (Resolved): ceph: xattr: fix nanosecond display on i_rctime
- In ceph_vxattrcb_dir_rctime() the nanoseconds part of the time
displayed does not include leading 0's, which leads t... - 02:25 PM Bug #2153 (Resolved): osd: locking cycle on pg::_lock. op_tp::lock, OSD::map_lock
- commit:1468d95101adfad44247016a1399aab6b86708d2
- 09:27 AM Bug #2153 (Resolved): osd: locking cycle on pg::_lock. op_tp::lock, OSD::map_lock
- ...
- 02:10 PM Linux kernel client Bug #2156 (Resolved): ceph: xattr: fix a possible buffer overrun bug
- In ceph_vxattrcb_file_layout(), if an inode has a preferred PG its
value is added to the formatted output buffer. I... - 01:56 PM rgw Cleanup #2089: rgw: less dout(0) noise?
- sounds good to me!
- 01:40 PM rgw Cleanup #2089: rgw: less dout(0) noise?
- debug rgw = 0 removes almost everything except two:
rgw_main.cc: dout(0) << "====== starting new request req=" <<... - 10:05 AM rgw Cleanup #2089: rgw: less dout(0) noise?
- Actually, those are dout(10). The problem is that the default rgw log level is 20.
- 01:41 PM Linux kernel client Bug #2155 (Resolved): ceph: xattr: wrong value assumed for "no preferred PG"
- In ceph_vxattrcb_file_layout() the layout for a file is printed.
The preferred placement group is extracted from t... - 01:14 PM Bug #2154 (Resolved): rados: bench seq should not segfault when blocksize doesn't match write blo...
- I misunderstood the problem to begin with. The issue is when read size does not match the prior write size (I hadn't...
- 09:50 AM Feature #2149: osd: use omap for snap collections
- 09:40 AM rgw Feature #1739 (Resolved): rgw: multipart upload should use manifest object
- 08:56 AM Feature #1895 (Rejected): osd: detect duplicate requests by tracking per-client last_acked_tid in...
- 08:54 AM Feature #1802: qa: test to exercise divergent osd logs
- the backfill.py exercises a divergent backfill target. we just need to do the same on a non-backfill target.
- 07:46 AM rgw Feature #2066 (Resolved): rgw: make list_objects efficient
- Done, merge in with rgw-omap changes at commit:89648a0d1abe06832f57db2ff8be85749f667094
- 07:37 AM rgw Feature #1715 (Rejected): rgw: use RENAME osd operation to avoid slow CLONE operations
- With new atomic scheme we're not using clone anymore (unless it's an old object for backward compatibility).
- 07:34 AM rgw Feature #2040: rgw: disable rgw log through ceph.conf
- Yeah, this is the rgw user operations log, not the debug log.
- 07:25 AM rgw Feature #1847 (Resolved): rgw: revisit the way we store large objects
- Revisited, solution was merged in commit:5f8bbf1ff2d547023c15628dd0e3a5711e584c2b (rgw-new-atomic).
- 07:23 AM rgw Feature #1872 (Resolved): rgw: only use shadow objects for large objects
- This has long been done.
Pushing acls check to cls_rgw can be done later on, but that's a different issue. - 07:21 AM rgw Bug #2072 (Resolved): rgw: owner cannot change acl if it doesn't have bucket read permission
- Fixed, merged in with swift-acls.
- 07:19 AM rgw Feature #2140 (In Progress): rgw: use new encode/decode macros
- 06:58 AM Revision c0aa3319 (ceph): Merge branch 'master' of ssh://skinny/home/yehudasa/ceph
- 06:53 AM Revision 5f8bbf1f (ceph): Merge branch 'wip-rgw-new-atomic'
- 06:52 AM Revision 465a88ea (ceph): rgw: append the currect bucket marker when removing bucket
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 06:39 AM Revision 8ce3d229 (ceph): Merge branch 'master' of ssh://skinny/home/yehudasa/ceph
- 06:35 AM Revision 89648a0d (ceph): Merge branch 'wip-rgw-omap'
- 06:25 AM Revision 72d678b8 (ceph): cls_rgw: fix rgw_bucket_init_index
- was failing to error in case header already existed
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 06:19 AM Revision eaafc578 (ceph): rgw: remove extra unused params from omap_get()
- and also rename it to omap_get_all()
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 06:18 AM Revision 765962dc (ceph): rgw: add cls_cxx_map_clear
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 05:59 AM Revision afe2598a (ceph): leveldb: drop compaction unit test
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 01:20 AM Revision 4d6578ca (ceph): ReplicatedPG,librados: add filter_prefix to omap_get_vals
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 01:10 AM Revision e0744390 (ceph): rgw: use prefix filter for bucket listing
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 01:03 AM Revision 4c908442 (ceph): objclass, cls_rgw: add prefix to omap_get_vals()
- 01:02 AM Revision a6b524f6 (ceph): librados: add higher level call for omap_get_keys() with prefix
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:46 AM Revision 7a72bf01 (ceph): Merge remote-tracking branch 'origin/wip_prefix' into wip-rgw-omap
- 12:32 AM Bug #2146: Ceph -s crash and reports old ceph version
- I have updated ceph package only. The binary used for getting statistics is in ceph-common. After upgrade it work fin...
- 12:29 AM Revision ffcf62f6 (ceph): rgw: switch to new encoders/decoders
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 12:28 AM Revision ffae4dfe (ceph): enconding: add legacy decoder for 32 bit versions
- In these cases if the version is smaller than the compat ver
we skip 3 bytes.
Signed-off-by: Yehuda Sadeh <yehuda@hq... - 12:05 AM Revision b0c9d58c (ceph): rbd: pass all mon addrs when mapping devices
- Previously this repeated the address of the first monitor.
Fixes: #2152
Signed-off-by: Josh Durgin <josh.durgin@drea...
03/07/2012
- 10:07 PM Revision 4d0bcdc8 (ceph): objectstore: fix collection_move() encoding
- This was broken in the original f43c3d958fe5c32ae647ffa715390ada51ae2650.
Signed-off-by: Sage Weil <sage.weil@dreamh... - 09:54 PM Revision 9dc7c653 (ceph): msgr: remove SimpleMessenger::get_ms_addr() in favor of Messenger::get_...
- And fix the comments on set_ip.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Reviewed-by: Sage Weil <sa... - 09:54 PM Revision 65d170a8 (ceph): msgr: remove declaration of undefined SimpleMessenger::write_pid_file
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Reviewed-by: Sage Weil <sage.weil@dreamhost.com> - 09:21 PM Feature #2114 (In Progress): old sepia setup on new hardware
- 09:20 PM Feature #2087 (In Progress): lightweight filestore workload generator
- 09:20 PM Feature #2088 (In Progress): msgr: refactor 2 threads to one
- 09:20 PM Feature #2053 (In Progress): librados: caching
- 09:20 PM rgw Feature #2066 (In Progress): rgw: make list_objects efficient
- 09:20 PM rgw Feature #1950 (In Progress): rgw: create S3/Swift ACL interoperability suite
- 09:20 PM rgw Feature #830 (Resolved): rgw: swift per-object ACLs
- 09:19 PM rgw Feature #2140 (Resolved): rgw: use new encode/decode macros
- 09:08 PM Revision 0a59d08d (ceph): ReplicatedPG,librados: add filter_prefix to omap_get_vals
- Signed-off-by: Samuel Just <rexludorum@gmail.com>
- 08:55 PM Revision 31762c00 (ceph): lock: Improved logging when there aren't enough nodes available to lock...
- 08:55 PM Revision 05a07dda (ceph): lock: Added a --locked flag to teuthology-lock.
- Can be used to restrict searches based on lock status, e.g.
'teuthology-lock --list -a --locked false --status up' sh... - 08:53 PM rgw Feature #2040: rgw: disable rgw log through ceph.conf
- Dan Mick wrote:
> Yes please! :) rgw debug = 0 doesn't seem to have any effect. (you knew that.)
...but this i... - 08:47 PM rgw Feature #2040: rgw: disable rgw log through ceph.conf
- Yes please! :) rgw debug = 0 doesn't seem to have any effect. (you knew that.)
- 08:34 PM Revision 6bf72019 (ceph): rgw: some minor cleanups
- following a review
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 06:45 PM Revision 5f8ffdee (ceph): objclass: fix cls_cxx_map_write_header
- Claiming the buffer instead of encoding it.
Signed-off-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com> - 06:44 PM Revision 799c8aca (ceph): cls_rgw: fix debug message
- Signed-off-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com>
- 06:32 PM Revision 0b1037da (ceph): Merge remote-tracking branch 'gh/wip-doc'
- Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com>
- 04:56 PM Revision 9ba96c01 (ceph): osd: make degraded pgs count missing replicas as degraded objects
- If a PG is smaller than it should be, make sure the missing replicas are
included in the degraded object count. This... - 04:14 PM Bug #2152 (Resolved): rbd: first monitor address is passed to kernel n times in rbd map
- 02:45 PM Bug #2152 (Resolved): rbd: first monitor address is passed to kernel n times in rbd map
- Using rbd map with mon0 (addr 10.10.10.4:6789) down, this happened:...
- 02:41 PM Linux kernel client Bug #2081: msgr: spinlock badness?
- This:
ubuntu@teuthology:/a/nightly_coverage_2012-02-20-b/12984
does not provide very much useful informatio... - 02:36 PM Feature #2127: Save kernel core dumps on all of our test machines
- Researched this a bit this afternoon. I have used LKCD in the past and
find now it's fairly old. Here someone has ... - 02:11 PM Bug #2151 (Resolved): mon: pg creation retry is slow
- right now if you are creating a pg and the osd crashes, the monitor will retry every once in a while, but that retry ...
- 02:00 PM Messengers Cleanup #2150 (Resolved): repair the Simple/Messenger interface
- I made a start on this with my interface work, but there are still
1) a lot of public functions that ought to be pri... - 10:51 AM Feature #2149 (Resolved): osd: use omap for snap collections
- 09:55 AM Bug #2148 (Resolved): osd: class error return not propagated to client
- 09:49 AM Feature #2147 (Resolved): objclass: add CLS_ERR macro
- Otherwise, dumping errors through CLS_LOG hides them if debug objclass is not set.
- 09:06 AM Bug #2137 (Resolved): osd: refine degraded % calculation
- commit:9ba96c0123c050f7e7c62ea644e240aed0c954fb
- 08:24 AM Bug #2146: Ceph -s crash and reports old ceph version
- I'm curious how you managed to install new packages while keeping around an old binary, though. (Yes, that's definite...
- 07:48 AM Bug #2146 (Rejected): Ceph -s crash and reports old ceph version
- The problem is just that your ceph binary is out of date. You need to run v0.43 or later, due to the structure encod...
- 03:56 AM Bug #2146 (Rejected): Ceph -s crash and reports old ceph version
- # ceph -s
terminate called after throwing an instance of 'ceph::buffer::malformed_input'
what(): buffer::malform... - 05:03 AM Revision 184a9dda (ceph): mon: fix full osd detail
- And use a helper to avoid dup code.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:03 AM Revision bd97923c (ceph): doc: fix misc typos, bad phrasing
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:03 AM Revision a300db39 (ceph): mon: assign severity to each health summary/detail item
- These can be included in the detail dump in the future.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 01:17 AM Revision f266d5a2 (ceph): objclass, cls_rgw: update to use omap
- Signed-off-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com>
- 01:05 AM Revision 2822fe50 (ceph): mon: include unfound count in health detail
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision 2b87d4f2 (ceph): osd: list might_have_unfound locations in query result
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision d72b8217 (ceph): doc: document some osd failure recovery scenarios
- - simple osd failure
- ceph health [detail]
- peering failure ('down') state
- unfound objects
Signed-off-by: Sage W... - 01:05 AM Revision 2bec51a2 (ceph): doc: describe 'stuck' states we check for
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision 956e2e22 (ceph): mon: list nearfull/full osd detail
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision 75ad8979 (ceph): doc: diagnose full osd cluster
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision 25cceca0 (ceph): doc: slow osd requests
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision ab41d675 (ceph): doc: fix link
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision 0becb843 (ceph): doc: talk about mon failures a bit
- Signed-off-by: Sage Weil <sage@newdream.net>
- 01:05 AM Revision b0ed78c3 (ceph): doc: 2 words about radosgw failures
- - restarting the daemon.
- using the admin socket
Signed-off-by: Sage Weil <sage@newdream.net> - 01:05 AM Revision 8b0bd127 (ceph): mon: refactor health, include optional detail
- 'ceph health' to get the usual summary, 'ceph health detail' to
additionally get a comprehensive list of problems fou... - 12:05 AM Revision db223363 (ceph): Merge branch 'wip-collmove'
03/06/2012
- 11:48 PM Revision 85446298 (ceph): rgw: switch to omap api
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 11:15 PM Revision 6c0cb55e (ceph): leveldb: remove flawed unit test for now
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 10:53 PM Revision 7012c20b (ceph): librados: rename omap_get_vals_by_key to omap_get_vals_by_keys
- merge fail
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 10:35 PM Bug #2137 (Fix Under Review): osd: refine degraded % calculation
- wip-2137
- 10:18 PM Revision 1fefb146 (ceph): librados: add high level omap calls
- also rename get_vals_by_key to get_vals_by_keys
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 10:17 PM Revision f85ab71f (ceph): rgw: read bucket through tmap_get
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 10:17 PM Revision 7fc779a6 (ceph): rgw: fix warning
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 07:46 PM Revision 98f8219d (ceph): Merge branch 'wip_omap'
- Reviewed-by: Sage Weil <sage.weil@dreamhost.com>
- 07:44 PM Revision d8dcb28e (ceph): librados: add tmap_put to ObjectWriteOperation
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision b85f7d7b (ceph): ReplicatedPG: add omap_header to recovery
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision d2bf68d1 (ceph): osdc: Add omap operation stubs to Objecter::ObjectOperation
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision 81c22dfb (ceph): librados: Added omap operations to librados
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision 82287986 (ceph): ReplicatedPG: Add omap ops to ReplicatedPG
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision 2abf3776 (ceph): RadosModel: Add omap operations to RadosModel
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision adace1cf (ceph): ReplicatedPG: transparently upgrade TMAP
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision 4c4fcea3 (ceph): osd: testing for tmap auto upgrade
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:44 PM Revision b6c2e839 (ceph): test_rados_api_aio: add omap
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 07:03 PM Revision b52d4087 (ceph): Merge branch 'wip-1796'
- Reviewed-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 07:02 PM Revision 769ef369 (ceph): journaler: add generic write error handler
- Specify a generic callback for any write error the journaler encounters.
This is more helpful than passing up write e... - 07:02 PM Revision 195301ef (ceph): mds: respawn when blacklisted
- If we are blacklisted by the OSD cluster, it's because we were too slow
and were replaced by another ceph-mds. Respa... - 06:49 PM Revision 50682189 (ceph): Merge remote-tracking branch 'gh/wip-2105'
- Reviewed-by: Samuel Just <samuel.just@dreamhost.com>
- 06:24 PM Revision 86186405 (ceph): .gitignore: src/ocf/rbd
- Signed-off-by: Sage Weil <sage@newdream.net>
- 06:23 PM Linux kernel client Bug #2064 (In Progress): ceph-client: messenger: nocrc flag not implemented correctly
- I've been unable to test rigorously today so I analyzed the affected code.
If the "nocrc" flag is supplied, the ce... - 03:22 PM Linux kernel client Bug #2064: ceph-client: messenger: nocrc flag not implemented correctly
- The problem also exists in write_partial_msg_pages(). In other words, it
looks like neither the reader nor the writ... - 05:46 AM Linux kernel client Bug #2064: ceph-client: messenger: nocrc flag not implemented correctly
- This is a trivial fix. The only thing that needs to be done really is
testing the result to make sure things don't ... - 05:34 PM Revision 2a18c3e1 (ceph): nuke: unmount osd data directories
- This helps us avoid reboot to clean up osd data directories that are left
mounted. - 05:19 PM Revision e3b4ba99 (ceph): filestore: create snap_0 on mkfs
- If we create a new filestore, apply one transaction, and then crash, we
want to make sure roll back to a consistent r... - 05:19 PM Revision a14d44fc (ceph): filestore: drop useless read_op_seq() arg
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:14 PM Revision b78b725d (ceph): Merge pull request #9 from fghaas/ocf-ra
- OCF resource agents: add rbd
Reviewed-by: Sage Weil <sage@newdream.net>
Reviewed-by: Tommi Virtanen <tommi.virtanen@... - 04:40 PM Feature #2145 (Resolved): doc gitbuilder
- it can automatically rsync to ceph.newdream.net/docs/<branch or tag name>
- 03:54 PM Bug #2136 (Resolved): leveldb fails unit tests in gitbuilders
- 03:45 PM Subtask #1919 (Resolved): implement the key value interface in terms of leveldb
- 03:45 PM Subtask #1920 (Resolved): Update OSD to use ObjectStore tmap implentation (object recovery must c...
- 03:45 PM Subtask #1917 (Resolved): create interface for backing key-value store and create object map impl...
- 03:45 PM Subtask #1918 (Resolved): create mock key-value store and tests for the related object map implen...
- 03:45 PM Subtask #1915 (Resolved): Create trivial implementation for the object map interface (using curre...
- 03:45 PM Subtask #1916 (Resolved): add tests ObjectStore level tests for tmap operations
- 03:45 PM Subtask #1914 (Resolved): Create interface for object map implementation
- 03:45 PM Subtask #1913 (Resolved): Add tmap operations to ObjectStore interface
- 03:43 PM Feature #1571 (Resolved): osd: non-trivial map object
- 03:42 PM Feature #1571 (Closed): osd: non-trivial map object
- 02:20 PM CephFS Feature #2144 (Resolved): mon: improve mds health checks
- e.g. replay, rejoin, resolve, etc. should be warning, and so forth.
- 11:27 AM Cleanup #2143: Remove ALL "don't use this product" warnings
- should we leave it on ceph-mds startup?
- 11:26 AM Cleanup #2143 (Fix Under Review): Remove ALL "don't use this product" warnings
- wip-2143
- 11:21 AM Cleanup #2143 (Resolved): Remove ALL "don't use this product" warnings
- We are about to push this product out to Open Stack and Canonical, and will be charging for support.
"Do not use thi... - 11:10 AM CephFS Bug #1796 (Resolved): mds: exit cleanly on EBLACKLISTED
- 10:57 AM Bug #2105 (Resolved): filestore: mkfs does not create initial snap
- Fix is merged.. this'll be in v0.44.
Thanks for the bug report (and detailed log!) - 09:33 AM Bug #2105 (Fix Under Review): filestore: mkfs does not create initial snap
- 10:21 AM CephFS Bug #1318: directories disappear across multiple rsyncs
- I've just run into this on 0.43 using the ceph kernel module in 3.2.7. My symptoms are that a repeated rsync from a ...
- 09:34 AM rgw Bug #2139 (Fix Under Review): rgw: no cleanup of index update in case of cancelled operations
- 09:26 AM Feature #1655: gitbuilder aggregator page
- We've been using this script for the past month or so, and it's been pretty handy. Here's an ajax version of the abov...
- 08:58 AM Revision affda7c0 (ceph): rbd OCF RA: fix whitespace inconsistency
- Signed-off-by: Florian Haas <florian@hastexo.com>
- 08:25 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- I ran multiple I/O loads on the cluster last night and performed multiple tests, but this problem didn't come back ye...
- 07:17 AM Feature #2142: Add support for Ubuntu 12.04 (precise pangolin) in deb repository
- I'll do this for v0.44.
- 01:25 AM Feature #2142: Add support for Ubuntu 12.04 (precise pangolin) in deb repository
- This add is quite usefull for me, because I use chef (I will try to improve the current cookbooks) and chef use "node...
- 01:21 AM Feature #2142 (Resolved): Add support for Ubuntu 12.04 (precise pangolin) in deb repository
- Precise Pangolin is in beta now, it can't be used with the current repository.
- 06:48 AM Revision d9d5cf2e (ceph): Merge remote branch 'gh/wip-msgr-interface'
- Reviewed-by: Sage Weil <sage@newdream.net>
- 05:42 AM Revision d36b6a90 (ceph): osd: use new collection_move() operation
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:42 AM Revision 14929e4d (ceph): filestore: implement OP_COLL_MOVE
- Equivalent to OP_COLL_ADD, OP_COLL_REMOVE.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:41 AM Revision f43c3d95 (ceph): objectstore: OP_COLL_MOVE
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:41 AM Revision 5137f64f (ceph): objectstore: use enum for OP_*
- Enforce no dups.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:15 AM Revision d8740094 (ceph): objectstore: remove _fake_writes, _get_frag_stat
- Also only implemented by ebofs.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:12 AM Revision 737132be (ceph): filestore: drop trim_from_cache, is_cached
- These were used for read optimizations in ebofs; I don't think they'll
come back.
Signed-off-by: Sage Weil <sage.wei... - 05:09 AM Revision 3cd5e31a (ceph): objectstore: remove cruft
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:09 AM Revision 97993f6c (ceph): filestore: remove collection, attr faking
- Useless functionality from the dark ages of development, when xattrs were
scarce.
Signed-off-by: Sage Weil <sage.wei... - 01:28 AM Revision d0c6ad0f (ceph): rgw: cancel bucket update if operation failed
- Beforehand the operation was leaking.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 01:27 AM Revision 14857582 (ceph): cls_rgw: add cancel operation
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
03/05/2012
- 11:28 PM Revision 0661ea1d (ceph): Merge branch 'master' of ssh://github.com/ceph/ceph
- 11:00 PM Revision 4e9ebd6b (ceph): rgw: make sure correct locator is used
- Or more correct: locator is not used where not needed.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 11:00 PM Revision e0650ce3 (ceph): rgw: implement copy using new scheme
- for some reason target tail uses locator, this needs to be
fixed.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 11:00 PM Revision 53a2ceb7 (ceph): rgw: don't use locator for multipart uploads
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 11:00 PM Revision dfcb8412 (ceph): rgw: multipart object working with manifest
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 11:00 PM Revision 578c0510 (ceph): rgw: manifest object contains source offset info
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 11:00 PM Revision d409c313 (ceph): rgw: basic functionality of new atomic get/put works
- get/put of objects works. Stuff that is known to be broken:
copy object
Also, going through the code, we can probabl... - 11:00 PM Revision 20244d64 (ceph): rgw: get_obj uses manifest
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 11:00 PM Revision c076e351 (ceph): rgw: atomic objects hold manifest header
- When writing an object we update where all the chunks of this object
reside.
Signed-off-by: Yehuda Sadeh <yehuda@hq.... - 11:00 PM Revision e36940af (ceph): rgw: atomic processor writes to shadow object
- And the first chunk is going to the head object in the end
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 10:51 PM Bug #2126 (Duplicate): osd: recover_primary did nothing when num_missing==1
- 10:45 PM Bug #2105: filestore: mkfs does not create initial snap
- Thanks for the report!
The mkfs doesn't create an initial snap, so if we crash/stop before creating one, our first... - 10:35 PM CephFS Bug #1796 (Fix Under Review): mds: exit cleanly on EBLACKLISTED
- 10:35 PM Revision ed0f6053 (ceph): Merge remote branch 'gh/wip-swift-acls'
- Lightly-reviewed-by: Sage Weil <sage@newdream.net>
- 10:21 PM Revision 3e95dfdf (ceph): osd: delay non-replayed ops during replay
- If we get new (non-replayed) ops during replay, those need to wait until
after the replayed ops are ordered and appli... - 10:21 PM Revision 702f09ea (ceph): librados: close narrow shutdown race
- timer.shutdown() will drop and retake the lock, so set DISCONNECTED first
to avoid a message slipping in and reaching... - 10:21 PM Revision 743da9bd (ceph): osd: don't trust pusher's data_complete
- The pusher doesn't know what clone_overlap we'll see, so it has no idea
if we are data_complete from our perspective,... - 10:20 PM Revision e1a9e18b (ceph): osd: warn if recovery still has missing at end
- We shouldn't get to this point. If we do, recover_primary didn't do what
it needed to. Dump the remaining missing s... - 10:14 PM Bug #2098 (In Progress): xfs/ext4 non-idempotent transaction
- 09:34 PM Revision 14936747 (ceph): Use non-zero exit status if any tests failed
- Fixes: #1989
- 08:30 PM Revision c31b8696 (ceph): OCF resource agents: add rbd
- Add a resource agent for mapping, unmapping and monitoring RBD devices.
Maps an RBD on start, unmaps it on stop. Che... - 03:53 PM Feature #2141 (Resolved): ceph: 'object map <poolname> <objectname>' or similar
- 'ceph pg map 1.2' will tell you what osd handles a pg... having the same thing that lets you provide pool and object ...
- 02:32 PM rgw Feature #2140 (Resolved): rgw: use new encode/decode macros
- so we can safely revise encoding for the structures in a forward/backward compatible way
- 02:18 PM Bug #2135 (Resolved): cephtool: osdc/Objecter.cc: 375: FAILED assert(initialized)
- 02:17 PM Bug #2133 (Resolved): osd: recovery_complete
- 02:17 PM Bug #2082 (Resolved): osd: broken queuing during replay
- 01:23 PM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- I tried to compile the wip-2116 and master branches today, that failed. So I haven't been able to test the new code y...
- 12:39 PM rgw Bug #2120 (Resolved): rgw: atomic write guard doesn't scale well
- 12:37 PM rgw Bug #2120: rgw: atomic write guard doesn't scale well
- A fix for that was already pushed (backing off when identifying a race in atomic write scheme). However, a more compl...
- 11:43 AM Bug #1900 (Resolved): Fix detection and build issues with libcrypto++
- commit:c9e028f4e5287ef6b7b237fca9ee34aa78ae1212
- 10:51 AM Linux kernel client Bug #1600 (Can't reproduce): general protection fault during blogbench
- 10:51 AM Linux kernel client Bug #1615 (Can't reproduce): null pointer dereference in ceph_msg_new
- 10:50 AM Linux kernel client Bug #1597 (Can't reproduce): general protection fault during mount
- 10:50 AM Linux kernel client Bug #2069 (Need More Info): client crash during kernel_untar_build rm -r step
- 10:48 AM Linux kernel client Bug #1793 (Need More Info): NULL pointer dereference at try_write+0x627/0x1060
- 10:45 AM rgw Bug #2063 (Resolved): rgw: access key shouldn't contain chars that need to be url encoded
- 10:43 AM Feature #2087: lightweight filestore workload generator
- *task
- 10:42 AM Feature #2087: lightweight filestore workload generator
- Mark suggested that this would be a good talk for Joao.
- 10:42 AM Bug #1989 (Resolved): teuthology: error in ceph.log didn't make teutholgy return error code
- 10:40 AM CephFS Bug #2071 (Need More Info): kclient: pjd mkfifo failures
- 10:40 AM rgw Bug #2035 (Resolved): rgw: bucket removal fails
- 10:39 AM Bug #2042 (Need More Info): mon: crash in LogMonitor::update_from_paxos
- 10:37 AM Feature #2003: limit XFS extent fragmentation for rbd
- librbd caching will help a lot!
- 10:35 AM rgw Bug #1948 (Resolved): rgw: need to read intent log in chunks
- 10:33 AM rgw Bug #2027 (Need More Info): rgw -> apache miscommunication
- 10:08 AM rgw Bug #1864 (Resolved): rgw: atomic bucket info
- 10:07 AM Bug #1873 (Won't Fix): crush_rule type is inconsistent
- 10:06 AM CephFS Bug #1811 (Need More Info): 2 pjd chown tests failed on cfuse
- 10:02 AM Bug #1627 (Need More Info): ceph-mon memleak if ceph-osd cluster ip is not reachable, but public ...
- 10:01 AM CephFS Bug #1047: mds: crash on anchor table query
- 09:57 AM CephFS Bug #1682 (Resolved): mds: segfault in CInode::authority
- calling this resolved too.
- 09:51 AM CephFS Bug #1549 (Resolved): mds: zeroed root CDir* vtable in scatter_writebehind_finish
- using clean shutdown now, yay
- 09:50 AM rgw Bug #1822 (Closed): radosgw can be slow to respond to requests
- several other bugs are open to track specific problems
- 09:49 AM rgw Bug #2139 (Resolved): rgw: no cleanup of index update in case of cancelled operations
- 09:33 AM Bug #2128 (Rejected): filestore: check() fails during sync
- actually, i hit this running the new code with the filestore transaction leak bug fix reverted (to reproduce the btrf...
- 07:49 AM Linux kernel client Tasks #2138 (Resolved): rbd: run xfstests on a local XFS filesystem over RBD
- This still can't really be done cleanly in a teuthology script, but
I would like to run xfstests on an RBD client sy... - 07:23 AM Bug #2137 (Resolved): osd: refine degraded % calculation
- based on the recent pg state updates...
03/04/2012
- 01:40 PM Bug #2136 (Resolved): leveldb fails unit tests in gitbuilders
- always ...
- 01:36 PM Bug #2082: osd: broken queuing during replay
- Hit this again and dug into the logs. It's a bug on the osd... testrados is using the data, which has replay enabled...
- 05:01 AM Revision 75cbed61 (ceph): DBObjectMap: remove stray ;
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
03/03/2012
- 10:45 PM Revision 0272b590 (ceph): LevelDBStore: #include types.h
- This fixes some compile errors on one of my boxes (squeeze).
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 09:33 PM Bug #2128: filestore: check() fails during sync
- could it be commit:75cbed61e94a7974e40230360c6781d85f47576d ?
- 09:11 PM Bug #2133: osd: recovery_complete
- 02:18 PM Bug #2133 (Resolved): osd: recovery_complete
- pull raced with clones, clone_subset changed, it got confused....
- 09:10 PM Bug #2135: cephtool: osdc/Objecter.cc: 375: FAILED assert(initialized)
- librados shutdown race
- 07:38 PM Bug #2135 (Resolved): cephtool: osdc/Objecter.cc: 375: FAILED assert(initialized)
- ...
- 03:16 PM CephFS Bug #1796: mds: exit cleanly on EBLACKLISTED
- people hit this and it's confusing when ceph-mds crashes...
wip-1796 - 02:38 PM Feature #2134 (Resolved): qa: smoke suite
- pick out some regression tests that run reasonably quickly and have decent coverage.
03/02/2012
- 10:59 PM Revision 004ec667 (ceph): .gitignore: *.tar.bz2
- Signed-off-by: Sage Weil <sage@newdream.net>
- 10:46 PM Revision 6e2a16b8 (ceph): msgr: start re-ordering functions into a better order
- This is the start of making the SimpleMessenger interface legible
to users. In addition to moving the configuration a... - 09:59 PM Bug #2132 (Resolved): FAILED assert(!missing.is_missing(soid))
- Possibly a duplicate of Issue #1191 or Issue #339 (both closed with could not reproduce).
Prior to this assert th... - 09:45 PM Revision 38537ba7 (ceph): Merge branch 'stable'
- 09:36 PM Linux kernel client Bug #2099 (Rejected): messenger: unexpected socket state (4)
- OK, this is not a bug. I caused it by inserting this WARN_ON() message
in a case statement in ceph_state_change(). ... - 09:29 PM Linux kernel client Cleanup #2131 (New): ceph: xattr: use the generic kernel xattr code
- The Linux kernel has a generic set of routines to support
extended attributes. When I posted some recent changes
t... - 09:28 PM Linux kernel client Cleanup #2130: ceph: xattr: complete cleanups following review
- Forgot to assign it to myself
- 09:27 PM Linux kernel client Cleanup #2130 (Rejected): ceph: xattr: complete cleanups following review
- As requested by Mark... I have a number of changes to make to
fs/ceph/xattr.c based on my review of that code last ... - 08:32 PM Revision 29be5282 (ceph): librados: remove gratuitous call to add_dispatcher_head.
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 08:32 PM Revision 26e48f42 (ceph): msgr: Require that init functions are called before bind() and start().
- Fix up callers to handle these constraints.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 08:32 PM Revision 091b1760 (ceph): msgr: make nonce a required part of the SimpleMessenger constructor.
- With that, remove the set_nonce function and the gratuitous passing
of nonce around through layers of functions.
Sig... - 08:32 PM Revision 38bec5da (ceph): msgr: remove refcounting of Messengers.
- This was pretty pointless since each Messenger has a well-defined
exit point and shutdown process.
Signed-off-by: Gr... - 08:32 PM Revision cd174c5e (ceph): msgr: promote the started bool to Messenger.
- Make it a protected member of Messenger instead of a public part of
SimpleMessenger.
Signed-off-by: Greg Farnum <gre... - 08:12 PM Linux kernel client Bug #2129 (New): ceph: xattr: call __build_xattrs() *before* cap check
- While reviewing a change to the xattr code, Sage noticed that some
calls to __build_xattrs() were being made *after*... - 07:20 PM Revision ffa59559 (ceph): msgr: Remove SimpleMessenger::register_entity
- This function has been vestigial for a long time. Remove it and move
its remaining functionality into the constructor... - 07:20 PM Revision ef244773 (ceph): msgr: Remove the SimpleMessenger start/start_with_nonce distinction.
- Instead, have a settable nonce value that you can fill in any time
after construction and that it uses during regular... - 07:20 PM Revision 578bc9c4 (ceph): msgr: Remove the SimpleMessenger::bind() nonce parameter.
- Instead, use the just-established nonce value.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 07:20 PM Revision 3bd1d2ae (ceph): msgr: add start() and wait() stubs to the Messenger interface
- Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 07:00 PM Revision 70360f84 (ceph): github.com/NewDreamNetwork -> github.com/ceph
- 06:55 PM Revision dc1abab2 (ceph): github.com/NewDreamNetwork -> github.com/ceph
- 06:55 PM Revision 1970713a (ceph): github.com/NewDreamNetwork -> github.com/ceph
- 05:50 PM Revision cacf0fde (ceph): filestore: fix rollback safety check
- There is a window in the old check between when current/commit_op_seq is
written and the snapshot is taken. If ceph-... - 05:35 PM Revision 098cd921 (ceph): Merge remote branch 'gh/wip_fs_omap'
- Reviewed-by: Sage Weil <sage.weil@dreamhost.com>
- 04:53 PM Revision 9fa8781c (ceph): v0.43
- 04:27 PM Bug #2128 (Rejected): filestore: check() fails during sync
- ...
- 03:08 PM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- ok, i have a theory what's going on. can you try the new wip-2116, and run with debug ms = 20?
thanks! - 10:07 AM Feature #2127 (New): Save kernel core dumps on all of our test machines
- The claim is that there is a netdump module that will UDP-squirt kernel coredumps to a waiting server, which is proba...
- 09:53 AM Bug #2126 (Duplicate): osd: recover_primary did nothing when num_missing==1
- ...
- 09:46 AM Bug #2118 (Resolved): osd: flawed commit_op_seq check on startup
- 08:43 AM Feature #2125 (Resolved): osd: put large xattrs in leveldb
- either when we fear the fs can't handle them, or unconditionally, or something.
- 07:33 AM Feature #1422: libvirt: rbd storage pool
- Made some more progress on this, code seems to be stable.
Working:
* Single and multiple monitors
* Authenticati... - 06:04 AM Revision 9f757ca9 (ceph): disable s3tests on valgrind/lockdep until #2103 is fixed
- 01:18 AM Revision 3a835172 (ceph): RadosModel: separate initialization and construction
- Several error codes needed to be checked.
Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Samuel... - 01:17 AM Revision 2b176fbe (ceph): Merge branch 'next'
- 01:16 AM Revision cd313885 (ceph): librados: only shutdown objecter after it's initialized
- The objecter is only initialized once the RadosClient state is
CONNECTED from the perspective of a RadosClient::shutd...
03/01/2012
- 10:00 PM Bug #2103: osd: lockdep error on watch_lock
- must reenable this in qa suite when it's fixed!
- 06:11 PM Revision 58a3b7f7 (ceph): Added leveldb submodule
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision d9b130fa (ceph): Added LevelDBStore
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision e9dd01f5 (ceph): os/CollectionIndex: Add debugging constructor and Path::coll()
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision 2ab6f023 (ceph): ObjectStore.h: Initial ObjectStore omap interfaces
- ObjectMap.h defines the interface which will be implemented by
leveldb. store_test now tests basic omap operations.
... - 06:11 PM Revision 82199d5d (ceph): os/: DBObjectMap and KeyValueDB interface with tests
- DBObjectMap is an implementation of ObjectMap in terms of KeyValueDB.
Signed-off-by: Samuel Just <samuel.just@dreamh... - 06:11 PM Revision 6a624b96 (ceph): test: Add KeyValueDB atomicity checker
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision 9331e633 (ceph): MOSDSubOp: Add entry for omap recovery
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision feaf44e7 (ceph): ReplicatedPG: Add omap to recovery
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 06:11 PM Revision 2c275efb (ceph): Makefile: add headers for distcheck
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 05:18 PM Bug #2122 (Resolved): objecter: Asserts if authorization fails
- Fixed by commit:cd313885783a5a69a554139b5b41d21a666c815b
- 08:36 AM Bug #2122: objecter: Asserts if authorization fails
- Ah, I had a patch to fix this in the wip-testrados branch. I'll rebase and merge that today. The new asserts in the o...
- 06:45 AM Bug #2122 (Resolved): objecter: Asserts if authorization fails
- While working on the libvirt RBD storage driver I noticed the following crash:...
- 01:46 PM Tasks #2123 (Closed): Ignore this task - I'm checking out the bug report process.
- 09:02 AM Tasks #2123: Ignore this task - I'm checking out the bug report process.
- using "Update" option in tracker
- 09:00 AM Tasks #2123 (Closed): Ignore this task - I'm checking out the bug report process.
- just using the task ticket to walk through the issue lifecycle.
- 11:45 AM Bug #2124 (Resolved): crash when malformed auth key is provided
- We should guard all calls to decode_base64:...
- 09:52 AM Linux kernel client Bug #2099: messenger: unexpected socket state (4)
- Saw this a couple of times on a client in a small ceph cluster. It seems to be correlated with dd runs using various...
- 08:11 AM Bug #2115 (Rejected): OSD failed to start: Operation not permitted
- 02:13 AM Bug #2115: OSD failed to start: Operation not permitted
- problem resolved. Thank you very much to your hint! I didn't ever think it is caused by communication.
I created a... - 04:46 AM Revision cddcc2d2 (ceph): Makefile: make check-local relative to $(srcdir)
- Signed-off-by: Samuel Just <samuel.just@dreamhost.com>
- 02:48 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- I can almost always reproduce it.
I just upgraded my cluster to:
> ceph version 0.42.2-206-gd77c579 (commit:d77c5... - 12:21 AM Revision 749281ed (ceph): Makefile: add json_spirit headers to tarball
- Signed-off-by: Sage Weil <sage@newdream.net>
02/29/2012
- 11:47 PM Revision a80246c1 (ceph): dump_stuck: note required ceph configuration
- 11:45 PM Revision b2bbede8 (ceph): dump-stuck: set pg stuck threshold to match test
- 10:46 PM Revision 86340655 (ceph): rgw: don't retry certain operations if we raced
- The atomic get/put scheme was retrying writes in case where it lost
races (head object was rewritten by another clien... - 10:46 PM Revision 85d04c6c (ceph): rgw: don't check for ECANCELED in the _impl() functions
- We already check it in the outer functions.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 09:22 PM Bug #2022: osd: misdirectect request
- ...
- 09:22 PM Revision b1f26440 (ceph): msgr: fix race in learned_addr()
- - two connect() threads
- both hit if (need_addr) check
- one takes lock, sets addr, need_addr = false, unlocks
- con... - 09:16 PM Bug #2080: osd: scrub on disk size does not match object info size
- hit this again, ...
- 08:28 PM Revision 8a2b7641 (ceph): msgr: print existing->state before failing assert
- May help with #1378.
Signed-off-by: Sage Weil <sage@newdream.net> - 07:07 PM Revision cbb12809 (ceph): Merge remote-tracking branch 'gh/wip-2121'
- Reviewed-by: Yehuda Sadeh <yehuda.sadeh@dreamhost.com>
- 05:46 PM Revision 052d64e1 (ceph): osd: unregister signal handlers on shutdown
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:46 PM Revision db96831b (ceph): mon: unregister signal handlers on shutdown
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:45 PM Revision 8e9bf611 (ceph): mds: unregister SIGHUP too
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 05:45 PM Revision bb5c7640 (ceph): radosgw: handle SIGHUP
- Fixes: #2121
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 05:23 PM Revision 9c7b63e1 (ceph): init-radosgw: add 'reload' command to send SIGHUP
- Fixes: #2121
Signed-off-by: Sage Weil <sage@newdream.net> - 05:21 PM Revision e8437665 (ceph): osd: fix typo is recovery_state query dump
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:17 PM Revision 0e03e9dd (ceph): osd: add missing space to scrub error
- [ERR] 18.5 osd.3: soid 8a5e37ad/rb.0.0.000000002b99/headextra attr _, extra attr snapset
Signed-off-by: Sage Weil <s... - 05:12 PM Revision 2437ce02 (ceph): msgr: discard the local_pipe's queue on shutdown.
- To facilitate this, we do two things:
1) actually identify the number of special code values we pass around
2) use th... - 05:10 PM Revision 7690f0b9 (ceph): osd: remove down OSDs from peer_info on reset
- If an OSD goes down, remove it from peer_info. In particular, I saw
2012-02-28 11:04:25.851038 12e53700 osd.5 3602 p... - 02:57 PM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- i'm hoping wip-2116 fixes it...
- 02:31 PM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- Wido, are you able to reproduce this reliably? I have an idea what the problem is, but have never reproduced this. ...
- 02:17 PM Bug #2002: osd: racy push/pull for clones
- reenabling this in my thrashing tests. if all goes well, i'll reenable in master under the assumption that sam's cle...
- 02:16 PM Bug #1977 (Can't reproduce): mon: ceph command hang
- we can reopen if this ever pops up again
- 01:59 PM Feature #2111 (In Progress): msgr workloads
- What we're looking for here are basic tests like connect, send message, kill connection, send another message; and ve...
- 01:30 PM Messengers Bug #1747 (Resolved): msgr: osd connection originates from wrong port
- commit:b1f264406f93af35600786f58e75908c393cf2ed
- 12:21 PM Messengers Bug #1747: msgr: osd connection originates from wrong port
- wip-1747
- 11:25 AM Messengers Bug #1747: msgr: osd connection originates from wrong port
- just hit this again. osd.1:...
- 12:48 PM rgw Bug #2121 (Resolved): radosgw: reload command for init script
- 09:48 AM rgw Bug #2121: radosgw: reload command for init script
- 09:25 AM rgw Bug #2121 (Resolved): radosgw: reload command for init script
- 12:48 PM Bug #1458 (Resolved): Run ceph suite with valgrind enabled
- 11:13 AM Bug #1975: btrfs: EINVAL on snap create
- see also this thread: http://marc.info/?t=132768583600004&r=1&w=2
- 10:46 AM Bug #1975: btrfs: EINVAL on snap create
- the EINVAL seems to have come from...
- 10:44 AM Bug #1975: btrfs: EINVAL on snap create
- somehow we end up here in btrfs:...
- 10:39 AM Bug #1975: btrfs: EINVAL on snap create
- quick brain dump:
- last time this reproduced i narrowed it down to a case where there were racing rmdirs with the... - 10:55 AM Bug #2115: OSD failed to start: Operation not permitted
- it looks like you may be having trouble authenticating with the monitor. can you reproduce this with 'debug ms = 1'? ...
- 10:28 AM Bug #2031 (Can't reproduce): paxos: failed assert (begin->last_committed == last_committed)
- 10:09 AM Messengers Bug #2086 (Resolved): msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- merged!
- 10:06 AM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- Sage suggested I could just add a local dispatch to the shutdown or wait functions to test this properly...I did, and...
- 09:18 AM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- 09:27 AM Bug #1873: crush_rule type is inconsistent
- It's __s16 or int so that a negative value can mean undefined/not specified. I'm inclined to just leave this as is...
- 09:18 AM Bug #2119 (Resolved): osd: do_query to !up osd
- 01:04 AM Revision fe94c041 (ceph): Merge branch 'next'
02/28/2012
- 10:05 PM Revision 23a0c039 (ceph): rgw: check for bucket swift permissions only if failed
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 09:55 PM Revision 85cc96c1 (ceph): dump_stuck: verify that 'ceph health' mentions the right number of inac...
- 09:53 PM Revision b9a675a2 (ceph): mon: report pgs stuck inactive/unclean/stale in health check
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Sage Weil <sage.weil@dreamhost.com> - 09:31 PM Revision e73ab2cc (ceph): Merge branch 'master' into wip-swift-acls
- 09:29 PM Revision bc80ba1f (ceph): rgw: fix swift bucket acl verification
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 08:37 PM Revision cc935180 (ceph): rgw: implement swift public group
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 08:29 PM Revision d10e1f46 (ceph): mon: fix slurp_latest to fill in any missing incrementals
- Fixes #1789.
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com> - 06:39 PM Bug #2115: OSD failed to start: Operation not permitted
- See attachment please
- 09:17 AM Bug #2115: OSD failed to start: Operation not permitted
- Can you attach the actual log? I want to make sure there is no subtle difference in the output. Thanks!
- 01:40 AM Bug #2115: OSD failed to start: Operation not permitted
- ceph version 0.42.2 (commit:732f3ec94e39d458230b7728b2a936d431e19322)
- 01:38 AM Bug #2115 (Rejected): OSD failed to start: Operation not permitted
- I'm setting up a new ceph cluster on ubuntu 11.10 with kernel version 3.0.0-16-server x86_64. The osd server failed t...
- 05:57 PM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- To be clear, I didn't try and generate the actual failure condition that was causing an assert before — that should b...
- 05:55 PM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- wip-2086 should fix this.
Ran a simple test:... - 05:27 PM Messengers Bug #2086 (In Progress): msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- 04:51 PM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- Okay, looks like the local_pipe doesn't get its message queue cleared...I'm checking the others and looking at how it...
- 05:50 PM Revision 999e2192 (ceph): peer: ignore +scrubbing portion of pg state
- It can cause the mon state and osd states to not match.
- 05:33 PM Revision 7b48cca1 (ceph): test_osd_types: fix unit test for new pg_t::is_split() prototype
- Signed-off-by: Sage Weil <sage@newdream.net>
- 05:30 PM Revision fd0712df (ceph): Makefile: drop separate libjson_spirit.la
- automake seems to have difficulty with the .la dependency on another .la.
Since libjson_spirit.la is only used by lib... - 05:26 PM Revision edd35c04 (ceph): osd: drop useless ENOMEM check
- new throws exception; doesn't return NULL.
Signed-off-by: Sage Weil <sage@newdream.net> - 05:11 PM Revision a7de459f (ceph): ceph-osd: clarify error messages
- So we know where the error came from. And use real error codes in init().
Signed-off-by: Sage Weil <sage@newdream.net> - 05:10 PM Revision 97926e18 (ceph): init: Actually do start the daemons when 'service ceph start <type>' is...
- A bug in my previous patch prevented any daemon with auto_start set to false from starting.
This patch allows:
* /et... - 04:55 PM rgw Bug #2120: rgw: atomic write guard doesn't scale well
- Implementing #1956 would solve this issue, and would make the entire atomic scheme simpler.
- 03:03 PM rgw Bug #2120: rgw: atomic write guard doesn't scale well
- This was reported by a user through the ml. We should figure out with that user whether it's a real issue, or a red h...
- 02:51 PM rgw Bug #2120: rgw: atomic write guard doesn't scale well
- Do we care? You can't do partial updates to objects IIRC, so many writers pretty much has to be wrong somehow or other.
- 02:35 PM rgw Bug #2120 (Resolved): rgw: atomic write guard doesn't scale well
- shen there is a large number of writers to the same object.
- 04:48 PM rgw Bug #2106 (Resolved): failed s3tests.functional.test_s3.test_100_continue
- Machines were running wrong apache and fastcgi modules.
- 04:23 PM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- This may be a messenger issue, but it's not losing that initial message — notice how osd5 tries to send a ping back t...
- 11:26 AM Bug #2116: Repeated messages of "heartbeat_check: no heartbeat from"
- the other side of this conversation is...
- 11:20 AM Bug #2116 (In Progress): Repeated messages of "heartbeat_check: no heartbeat from"
- looks like a msgr issue?...
- 07:35 AM Bug #2116 (Resolved): Repeated messages of "heartbeat_check: no heartbeat from"
- As discussed on the ml I gathered some logs.
Today I upgraded my whole cluster to 0.42.2 from 0.41.
Due to the ... - 12:54 PM Bug #1789 (Resolved): mon: failed assert(paxosv == pg_map.version)
- Pushed to master in commit:d10e1f46df8cc252f2f1d57cf5e577ea38eee1ae
- 12:48 PM Bug #1789: mon: failed assert(paxosv == pg_map.version)
- Okay, figured it out. Our current slurp code pulls in all the incrementals, then sends off a request for latest_stash...
- 12:01 PM Bug #2119 (Resolved): osd: do_query to !up osd
- ...
- 11:09 AM Bug #2118: osd: flawed commit_op_seq check on startup
- 10:08 AM Bug #2118 (Resolved): osd: flawed commit_op_seq check on startup
- the check that current/commit_op_seq == newest snap is flawed because ceph-osd can write a new current/commit_op-seq ...
- 10:09 AM Bug #2104 (Won't Fix): teuthology: wait_for_clean doesn't wait for last_epoch_started to propagate
- 10:09 AM Bug #2107 (Resolved): teuthology: lost_unfound fails pg state assert
- 09:41 AM devops Feature #2117 (New): qa: gitbuilder that does ENCODE_DUMP
02/27/2012
- 11:41 PM Revision f317028f (ceph): doc: beginnings of documentation of stuck pgs and pg states
- Signed-off-by: Josh Durgin <josh.durgin@dreamhost.com>
Reviewed-by: Sage Weil <sage@newdream.net> - 11:13 PM Revision 19170241 (ceph): filestore: make less noise on ENOENT
- Don't generate high-level log spam on every open error.
Signed-off-by: Sage Weil <sage@newdream.net>
Reviewed-by: Sa... - 10:52 PM Revision 722af1a4 (ceph): no peer as part of lost_unfound
- 10:49 PM Revision 244b7029 (ceph): pg: use get_cluster_inst instead of get_inst in activate
- This was mistakenly broken in 4b3bb5ab37a05fa001d59f24da7d9c30d650321b
Signed-off-by: Greg Farnum <gregory.farnum@dr... - 10:37 PM Revision f02195b4 (ceph): Merge branch 'wip-split2'
- Reviewed-by: Samuel Just <samuel.just@dreamhost.com>
- 10:35 PM Revision b6a04174 (ceph): osd: pg_t::is_split(): make children out param a pointer, and optional
- Also unit test it.
Signed-off-by: Sage Weil <sage@newdream.net> - 10:18 PM Revision 85ed06e9 (ceph): osd: bypass split code
- Until it is fully implemented. It's also disabled in the monitor
currently, but just in case it gets into the OSDMap... - 10:16 PM Revision 15d53249 (ceph): osd: fix pg locking flags
- Two things we need to handle:
- callers who already hold map_lock (split_pg())
- callers who already hold another ... - 10:04 PM Revision fc7b11a9 (ceph): osd: partially refactor pg split
- This partially refactors the OSD split code to do the split synchronously
when processing a new OSDMap. It is incomp... - 07:44 PM Revision 6a081888 (ceph): osd: factor hobject key into child pgid calc during split
- When we calculate the object's new pg, take the locator key into
consideration, to avoid a crash like
osd/OSD.cc: In... - 07:44 PM Revision d9cf3322 (ceph): osd: implement pg_t::is_split()
- Test to determine if a pg has split between two pool sizes, and if so,
what its children are.
Signed-off-by: Sage We... - 07:39 PM Revision ee4d9909 (ceph): journaler: log on unexpected objecter error
- This will help with #2110, #1796, #1640.
Signed-off-by: Sage Weil <sage@newdream.net> - 05:56 PM Revision 91b119a0 (ceph): osd: fix recursive map_lock via check_replay_queue()
- Also drop activate_pg() helper while we're at it, so it's clear that we
are the only user.
recursive lock of OSD::ma... - 04:20 PM Messengers Bug #2086: msgr: msg/SimpleMessenger.h: 203: FAILED assert(!i->second->is_on_list())
- The guards for something like that shouldn't be too complicated to set up...actually, I thought they were at one poin...
- 04:19 PM Bug #1789 (In Progress): mon: failed assert(paxosv == pg_map.version)
- Iiiinteresting. This assert is the post-update check, after loading and running through all the incrementals. (Meanin...
- 01:41 PM Bug #1789: mon: failed assert(paxosv == pg_map.version)
- Shouldn't be related — this is a problem with a single monitor daemon and the other is a write problem that an MDS is...
- 12:35 PM Bug #1789: mon: failed assert(paxosv == pg_map.version)
- Core dump attached. Dumb thought: could this be related to http://tracker.newdream.net/issues/2110, they happened wit...
- 10:14 AM Bug #1789: mon: failed assert(paxosv == pg_map.version)
- Crash occurred on the third monitor when starting after being down for several hours shortly after cluster creation. ...
- 02:07 PM CephFS Bug #2110 (Duplicate): osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- #1796
- 01:40 PM CephFS Bug #2110: osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- can you attach ceph-mds too? or better yet, fire up gdb ceph-mds core and print out the value of r from that frame. ...
- 12:00 PM CephFS Bug #2110: osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- Sage Weil wrote:
> Do you have a core file? I'm curious what the value of 'r' is.
Attached. Probably. (datetime ... - 11:43 AM CephFS Bug #2110: osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- Do you have a core file? I'm curious what the value of 'r' is.
- 11:40 AM CephFS Bug #2110 (Duplicate): osdc/Journaler.cc: 360: FAILED assert(r >= 0)
- Assert in MDS. This cluster was running a CephFS home directory workload with one active MDS and one MDS in standby r...
- 01:49 PM Bug #2045 (Need More Info): osd: dout_lock deadlock
- 01:33 PM Feature #2114 (Resolved): old sepia setup on new hardware
- 01:31 PM Feature #2113 (Resolved): objectcacher perfcounters
- 01:18 PM Feature #2112 (Resolved): msgr fault injection
- 01:18 PM Feature #2111 (Fix Under Review): msgr workloads
- Develop the interfaces which will allow us to break messenger sockets at precisely-defined points.
Allow comparison ... - 11:38 AM Tasks #2109: qa/benchmark: Explore using Filebench for benchmarks / stress testing
- Justification and a good intro: http://cuddletech.com/blog/pivot/entry.php?id=949
- 11:36 AM Tasks #2109 (New): qa/benchmark: Explore using Filebench for benchmarks / stress testing
- http://filebench.sourceforge.net/
"Ships with more than 40 pre-defined personalities, including the one that descr... - 11:05 AM Feature #2108 (New): track object states to inform error injection/testing
- 11:04 AM Feature #1412 (Resolved): qa: spec out messenger testing
- we now have a high-level plan on how to attack msgr testing.
- 10:03 AM Bug #1977: mon: ceph command hang
- Pretty sure you pushed changes the day you filed it (note reference in previous message), although I can't find the e...
- 09:51 AM rgw Bug #2106: failed s3tests.functional.test_s3.test_100_continue
- Strange, I can see the request in the apache logs, but not in the rgw logs....
- 09:12 AM Bug #2107 (Resolved): teuthology: lost_unfound fails pg state assert
- ubuntu@teuthology:/a/nightly_coverage_2012-02-27-a/14063...
- 04:56 AM Revision 402ece5e (ceph): init-ceph: stick with /var/run for the time being
- /run isn't present on older systems. Stick with the old location until it
is more pervasive, or we add an autoconf o... - 04:47 AM Revision 41295b58 (ceph): debian: /var/run/ceph -> /run/ceph
- /run/ceph should exists for creating UNIX domain sockets
ceph uses UNIX domain sockets for internal communication. Cr... - 04:45 AM Revision 0d8b5756 (ceph): debian: build-{indep,arch}
- Signed-off-by: Laszlo Boszormenyi <gcs@debian.hu>
- 04:45 AM Revision 3ad6ccb4 (ceph): debian: sdparm|hdparm, new standards version
- Signed-off-by: Laszlo Boszormenyi <gcs@debian.hu>
- 01:09 AM Revision 9afafdf1 (ceph): move peer to separate test for now
02/26/2012
- 08:56 PM Bug #1977: mon: ceph command hang
- Hmm, I wonder if somehow misdiagnosed this, or inadvertantly fixed it: haven't seen this hang in weeks, and it happen...
- 05:09 PM rgw Bug #2106 (Resolved): failed s3tests.functional.test_s3.test_100_continue
- ...
- 05:02 PM Bug #2022: osd: misdirectect request
- ubuntu@teuthology:/a/nightly_coverage_2012-02-26-a/13876$ grep WRN ceph.log
2012-02-26 01:18:03.166529 osd.1 10.3.1... - 11:19 AM Bug #2105 (Resolved): filestore: mkfs does not create initial snap
- This bug almost the same as this bug:http://tracker.newdream.net/issues/1707
I followed the instruction:http://ceph.... - 05:35 AM Revision 6295578f (ceph): lost_unfound: do peer after, until wait_for_clean propagates last_epoch...
- The peer task does wait_for_clean, and then lost_unfound immediately marks
something down. But the PGs become clean ... - 05:05 AM Revision 84cd4ed6 (ceph): peer: wait for peering to complete, or block
- We need to wait for peering to either complete, or block because it is
waiting for another PG. _Then_ look at all th...
02/25/2012
- 09:33 PM Bug #2104 (Won't Fix): teuthology: wait_for_clean doesn't wait for last_epoch_started to propagate
- 09:06 PM Bug #2103 (Resolved): osd: lockdep error on watch_lock
- ...
- 09:04 PM Bug #2102 (Can't reproduce): osd: pg stuck in backfill
- ...
- 05:39 AM Revision d944e7ee (ceph): fix lockdep.yaml conf syntax
- 01:01 AM Revision 266902a9 (ceph): rgw: initialize bucket_id in bucket structure
- might make valgrind a little bit less noisy.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 12:07 AM Revision 4a5a0911 (ceph): Merge branch 'master' of ssh://github.com/NewDreamNetwork/ceph
02/24/2012
- 11:32 PM Revision f8f6e4d8 (ceph): rgw: _exit(0) on SIGTERM
- We need to do something a bit smarter to get coverage information, but this
is a start.
Signed-off-by: Sage Weil <sa... - 11:20 PM Revision 5d5a022c (ceph): run radosgw through valgrind for s3tests
- 11:05 PM Revision edbb41e1 (ceph): add peer task
- Force a pg to get stuck in 'down' state, verify we can query the peering
state, then start the OSD so it can recover. - 11:04 PM Revision c9c1a4ab (ceph): do peer test along with lost_unfound
- 11:01 PM Revision b8739585 (ceph): peer: remove unused variable
- 10:56 PM Revision 62bda127 (ceph): misc: always return a usable result from get_valgrind_args
- 10:56 PM Revision e4801819 (ceph): rgw: simplify valgrind args
- 09:52 PM Revision 708be0a5 (ceph): Merge remote branch 'gh/wip-crush-adjust'
- Reviewed-by: Tommi Virtanen <tommi.virtanen@dreamhost.com>
- 09:48 PM Revision b0feba56 (ceph): Merge remote branch 'gh/wip-mds-resetter'
- Reviewed-by: Greg Farnum <gregory.farnum@dreamhost.com>
- 09:43 PM Revision 5c6e8b37 (ceph): Merge branch 'wip-pg-query'
- Reviewed-by: Samuel Just <samuel.just@dreamhost.com>
- 09:22 PM Revision 008ce6b2 (ceph): Merge branch 'stable'
- 09:00 PM Revision 732f3ec9 (ceph): v0.42.2
- 09:00 PM Revision 321ba67f (ceph): Merge remote-tracking branch 'gh/stable' into stable
- 08:54 PM Revision be761149 (ceph): Merge branch 'stable'
- 08:49 PM Revision fc531a91 (ceph): rename valgrind -> verify, add in runs under lockdep
- 08:42 PM Revision c43e87d1 (ceph): ceph_manager: list_pg_missing
- List missing objects for the given pgid.
- 08:42 PM Revision 7ac04a42 (ceph): lost_unfound: list missing/unfound for each pg and verify the unfound c...
- This also tests the pg list_missing functionality.
- 08:40 PM Revision d85ed91c (ceph): osd: fix array index
- Signed-off-by: Sage Weil <sage@newdream.net>
- 08:40 PM Revision 722e9e59 (ceph): lockdep: don't make noise on startup
- Who cares!
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 08:40 PM Revision fdaed0a7 (ceph): formatter: fix trailing dump_stream()
- Flush a previous dump_stream() if it was the last thing prior to a
close_section().
Signed-off-by: Sage Weil <sage.w... - 08:05 PM Revision 7bf64b73 (ceph): rgw: accept dict
- e.g.,
tasks:
...
- rgw:
client.0:
client.1: - 08:05 PM Revision e2ea73d1 (ceph): rgw: add valgrind support
- tasks:
- ceph:
- rgw:
client.a:
valgrind: [--tool=memcheck] - 08:05 PM Revision 7af6e46c (ceph): ceph: always try to process valgrind logs
- Check for errors in valgrind logs even if there is no valgrind option
the ceph task config stanza. Other tasks can r... - 08:05 PM Revision 90fdc840 (ceph): ceph: always create valgrind logs dir
- Other tasks use it too. It's more annoying to conditionally create it.
- 08:05 PM Revision 9ec04722 (ceph): refactor all valgrind users to use a get_valgrind_args() helper
- This avoids much annoying, duplicated code.
- 08:05 PM Revision 3bfb8d69 (ceph): ceph, ceph-fuse: simplify valgrind argument additions
- 08:05 PM Revision c93a08ed (ceph): Whitespace and unnecessary formatting fixes
- 08:04 PM Revision 7ad35ce4 (ceph): osd: include timestamps in state json dumps
- Include the time we entered this state in the dump.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 08:00 PM Revision 185c6b1f (ceph): Merge branch 'wip-2007'
- Reviewed-by: Josh Durgin <josh.durgin@dreamhost.com>
- 07:59 PM Revision e22adac2 (ceph): osd: use blocks for readability in list_missing
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:33 PM Revision e22a45a1 (ceph): osd: query recovery state machine
- For now, just append this to the end of the pg <pgid> query json dump.
We definitely want to do something smarter her... - 07:33 PM Revision a7c8bfbe (ceph): osd: query Peering substates
- Signed-off-by: Sage Weil <sage@newdream.net>
- 07:33 PM Revision 6d90a6dd (ceph): osd: dump recovery_state states in json
- Use a formatter. Present a vector of states, inner to outer.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 07:24 PM Revision d3b203af (ceph): osd: add tunable for number of records in osd command replies
- e.g., 'pg <pgid> list_missing [offset]'.
Signed-off-by: Sage Weil <sage@newdream.net> - 07:24 PM Revision 0361a3c4 (ceph): osd: pass in data to do_command
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:24 PM Revision 2677c72f (ceph): add libjson_spirit.la
- This is lightweight and relies on boost spirit, which we already use, so
there are no new dependencies.
There were s... - 07:24 PM Revision 6c257c4d (ceph): hobject_t: decode json
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 07:24 PM Revision 91fbc687 (ceph): osd: 'pg <pgid> list_missing <json hobject_t offset>'
- Dump missing objects in json. If more key is non-zero, user should ask for
more by passing the last object as the of... - 07:24 PM Revision c9416e61 (ceph): osd: 'tell osd.N mark_unfound_lost revert' -> 'pg <pgid> mark_unfound_l...
- More consistent interface.
Fixes: #2030
Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
Reviewed-by: Josh Durgin ... - 07:15 PM Revision 64038524 (ceph): lockdep: warn on stderr (via derr), not stdout
- Otherwise we screw up ceph-conf output and the like.
Signed-off-by: Sage Weil <sage.weil@dreamhost.com> - 07:15 PM Revision 804f243b (ceph): do_autogen.sh: -T for --without-tcmalloc
- Signed-off-by: Sage Weil <sage@newdream.net>
- 03:30 PM Feature #2054 (Resolved): teuthology: run radosgw through valgrind
- ok, this now works with yaml like...
- 01:52 PM Feature #2006 (Resolved): osd: report what is blocking peering completion
- commit:5c6e8b3795d0cf58814619bfc15cb0841e9a4f17
- 01:51 PM CephFS Bug #1792 (Can't reproduce): crash in ceph-mds
- even if we could, we would never know, since there isn't any distinguishing info here, and the teuth archive is gone.
- 01:48 PM RADOS Bug #2096 (Resolved): crush: adjust weight broken for tree, list buckets
- commit:708be0a5abef63a5da8409ad13719adb7bb744f8
- 01:47 PM RADOS Feature #2101 (Resolved): crushtool: check for weight overflow on reweight
- 11:56 AM Feature #2007 (Resolved): osd: enumerate unfound, lost objects, possible locations
- 09:52 AM Feature #2007: osd: enumerate unfound, lost objects, possible locations
- wip-2007
- 11:34 AM Feature #2030 (Resolved): osd: clean up mark_unfound api
- 10:34 AM Messengers Feature #2100 (Resolved): msgr: Prevent throttled clients from slowing down non-throttled connect...
- Right now, it seems a throttled connection will still receive a TCP receive buffer's worth of data, but because the u...
- 09:15 AM Linux kernel client Bug #2099: messenger: unexpected socket state (4)
- I don't think any of these other states are necessarily problematic, as long as the socket eventually ends up in CLOS...
- 08:49 AM Linux kernel client Bug #2099: messenger: unexpected socket state (4)
- This may be related to http://tracker.newdream.net/issues/1803 and http://permalink.gmane.org/gmane.comp.file-systems...
- 08:33 AM Linux kernel client Bug #2099: messenger: unexpected socket state (4)
- Adding that I see more of the same WARNING() messages in the log for
the same state, as well as others for state 5, ... - 08:13 AM Linux kernel client Bug #2099 (Rejected): messenger: unexpected socket state (4)
- Running tests defined by the YAML file below. Note that branch
wip-messenger is 107a8aaf21d01ee6cbc7a638faf1328f2bd... - 07:59 AM CephFS Bug #2092: BUG at fs/ceph/caps.c:999
- mdsc->mutex protects the globalish mds client state (request/session lists), which is different from session->s_mutex...
- 06:57 AM CephFS Bug #2092: BUG at fs/ceph/caps.c:999
- Just a quick look at this.
Here's the code:
static void __queue_cap_release(struct ceph_mds_session *session,
... - 06:10 AM Bug #2091 (Can't reproduce): corrupt v5 inc osdmap
- logs don't go far enough back. :(
moral of the story: next time grab the full mon data dir immediately in case it... - 05:57 AM Linux kernel client Bug #1907 (Resolved): rbd: don't reuse device ids while they're still in use elsewhere
- Committed a couple of weeks ago and has seen no bad effect during the
intervening testing. So I'm marking this one ... - 04:22 AM Revision 5efa821c (ceph): rgw: swift read acls allow bucket listing
- Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
- 04:11 AM Revision f09fb870 (ceph): rgw: fix swift acl enforcement
- we'll also need to make it so that swift read acls allow bucket listing
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdr... - 04:09 AM Revision d40a9b27 (ceph): lost_unfound: new mark_unfound_lost syntax
- 02:58 AM Revision 7c7349ef (ceph): ceph: fix help.t
- Signed-off-by: Sage Weil <sage.weil@dreamhost.com>
- 02:48 AM Revision 730b9ee0 (ceph): ceph-dencoder: man page
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:48 AM Revision f6e42a8b (ceph): ceph.spec.in: add ceph-dencoder
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:48 AM Revision 0281f1c6 (ceph): debian: add ceph-dencoder
- Signed-off-by: Sage Weil <sage@newdream.net>
- 02:48 AM Revision c3e1291d (ceph): v0.42.1
- 02:13 AM Revision cbf79a97 (ceph): ceph-tool: remove reference to "stop" command
- This doesn't exist any more, and I don't think it
ever "cleanly shut down the filesystem" -- certainly not
within my ... - 02:13 AM Revision 3bad945b (ceph): mds: remove unused MDBalancer dump_pop_map() function.
- Commenting it out is not the right answer. ;)
Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>
Reviewed-by:... - 01:22 AM Revision 4dfec574 (ceph): rgw: enforce swift acls
- doesn't work yet, but almost.
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> - 01:07 AM Revision 81a46c46 (ceph): dump_stuck: flush stats before waiting for recovery/clean
- 12:35 AM Revision 159f2b86 (ceph): mds: fix Resetter locking
- We need to hold the lock for ms_dispatch, esp calls into objecter. We
should only drop it when blocking; use distinc... - 12:35 AM Revision 065d6dd8 (ceph): mds: clean up useless block
- Signed-off-by: Sage Weil <sage@newdream.net>
Also available in: Atom