Activity
From 10/25/2012 to 11/23/2012
11/23/2012
- 07:13 PM Revision 96b82ebf (ceph): mon: Monitor: wake up contexts based on paxos machine's state
- When recovering the leader, only wake up a paxos machine's contexts if
the paxos machine is in a state that can handl... - 07:13 PM Revision 3b061ab9 (ceph): mon: AuthMonitor: increase log levels when logging secrets
- Fixes: #3361
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 07:13 PM Revision 7527a1ea (ceph): auth: Keyring: increase log levels when logging secrets
- Fixes: #3361
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 07:13 PM Revision deabdc8a (ceph): auth: cephx: increase log levels when logging secrets
- We understand that logging secrets may be useful when debugging the root
causes for auth issues. However, logging sec... - 07:12 PM Revision d6cf77dc (ceph): crush: CrushWrapper: don't add item to a bucket with != type than wanted
- We take little consideration about the type of the bucket we are adding
an item to. Although this works for the vast ... - 07:12 PM Revision 95e1fe88 (ceph): mon: PGMonitor: check if pg exists when handling 'pg map <PG>'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:20 PM Bug #3523 (Duplicate): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 06:03 PM Bug #3522 (Duplicate): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 11:30 AM Bug #3495: ceph-mon crash
- Joao, what kind of ceph configuration would make the logs more useful in the future?
Ceph crashes fairly often here,... - 11:21 AM Bug #3495 (Fix Under Review): ceph-mon crash
- wip-mon-misc-fixes contains commit 96b82ebf870bda5af33624f698785bac6ae78234 that should fix this bug.
The approach... - 10:45 AM Bug #3495: ceph-mon crash
- It appears that this crash is somewhat related with an election, and then something made the 'have_pending' variable ...
- 06:34 AM Bug #3361 (Fix Under Review): don't log secrets
- 06:31 AM Bug #3520: Error listing snapshots: (5) Input/output error
- I had checked folder /usr/lib/rados-classes/ , there were all so files including libcls_rbd.so.
- 02:06 AM Bug #3520 (Resolved): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 04:28 AM Bug #3521 (Resolved): windows 2008 kvm guest crashes with "floating point exception" when using r...
- Host: ubuntu 12.10 amd64
Guest: windows 2008 r2
Ceph: 0.48.argonaut2 (the one from the ubuntu repos)
The crash i...
11/22/2012
- 10:59 PM Revision ab8327fe (ceph): Merge remote-tracking branch 'origin/next' into next
- 09:59 PM Revision b2f80359 (ceph): s3tests: fix typo
- 09:59 PM Revision b8e6ce4d (ceph): s3tests: fix typo
- 09:53 PM Revision 1c715a11 (ceph): mds: child directory inherits SGID bit
- Update the inode, not the local variable.
Reported-by: Giorgos Kappes <geokapp@gmail.com>
Signed-off-by: Sage Weil <... - 08:57 PM Revision 3110e5ca (ceph): Merge remote-tracking branch 'origin/next' into next
- 08:55 PM Revision a0e8452a (ceph): Merge branch 'wip-opslog-socket2' into next
- Conflicts:
src/rgw/rgw_main.cc - 05:17 PM Revision 55081c2b (ceph): crush: prevent loops from insert_item
- If the insertion would create a loop, return -EINVAL.
Fixes: #3515
Signed-off-by: Sage Weil <sage@inktank.com> - 04:50 PM Revision b706945a (ceph): Try using syscall() for syncfs if not supported directly by glibc
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:35 PM Feature #3476 (Resolved): mon: fix all leaks
- Haven't been able to trigger any further leaks with master since the merge with wip-mon-leaks-fix.
- 10:28 AM Linux kernel client Bug #3519: rbd map hang during system startup
- https://raw.github.com/gist/4132395/7cb5f0150179b012429c6e57749120dd88616cce/gistfile1.txt
- 09:22 AM RADOS Bug #3515 (Resolved): mon: segfault when 'crush set' with different buckets with the same name
11/21/2012
- 10:19 PM Revision 189d073b (ceph): rgw: fix usage accounting
- bytes_sent and bytes_received are no longer accounted
in the req_state, needed to get them out of the ClientIO
object... - 09:27 PM Revision 5126bd70 (ceph): rbd: make snap purge fail if removing a snap fails
- Otherwise we report 100% removed when some may have failed.
Reported-by: Andrey Korolyov <andrey@xdel.ru>
Signed-off... - 09:12 PM Revision 6c1e2b66 (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit f86522cdfcd81b2d28c581ac8b8de6226bc8d1a4) - 09:11 PM Revision 17e4c0df (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 98a04d76ebffa61c3ba4b033cdd57ac57b2f29f3)... - 08:43 PM Linux kernel client Bug #3519 (Resolved): rbd map hang during system startup
- nick narrowed this down to 50-libceph_resubmit_linger_ops_when_pg_mapping_changes.patch on top of 3.5; everything els...
- 08:34 PM Revision 2b002a8d (ceph): Merge branch 'wip-java-enotdir'
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
Reviewed-by: Joe Buck <jbbuck@gmail.com> - 08:09 PM Revision 5c27bc42 (ceph): rgw: fix cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:09 PM Revision f40f715c (ceph): rgw: signal shuts down fcgi socket
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision 24fde547 (ceph): crypto: fix nss related leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision 7f221a58 (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision b3b77b6c (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:04 PM Revision ddf377a4 (ceph): rgw: fix cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:00 PM Revision 820911b2 (ceph): msgr: use get_myaddr and set_myaddr to set the nonce
- We can't set it directly via get_myaddr as its a const ref. Dur.
Signed-off-by: Greg Farnum <greg@inktank.com> - 06:55 PM Revision c31f94d1 (ceph): set the nonce unconditionally on bind
- 05:48 PM Revision afd4da73 (ceph): doc: Added FAQ back into toc tree.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:34 PM Revision 0dbf6e89 (ceph): test_librbd_fsx: Add OP_FLATTEN
- 04:34 PM Revision 7021f1a2 (ceph): test_librbd_fsx: consume saved-image files as test runs
- Avoid consuming lots of disk space by holding only as many file
copies as needed (compare the n-2 file as we make clo... - 04:29 PM Revision ddcf2089 (ceph): workunit: fix indentation
- 03:44 PM rbd Bug #3518 (Can't reproduce): rbd import file --format 2 creates an image named '--format'
- obviously not what was desired, but moreover, not sure how to delete it
- 03:44 PM Revision ffd19b64 (ceph): run xfstests on 3 parallel clients
- 02:27 PM rgw Bug #3517: rgw: usage does not account bytes_received, bytes_sent
- Fixed by commit:189d073b2554ce32de7d6c759f03e08b25b3512e
- 02:08 PM rgw Bug #3517 (Resolved): rgw: usage does not account bytes_received, bytes_sent
- 11:31 AM rgw Bug #3516 (Resolved): POST /bucket/random throws a 500
- According to Yehuda this is making an init multipart upload request and something is triggering the 500. A 4xx is exp...
- 07:36 AM RADOS Bug #3515 (Resolved): mon: segfault when 'crush set' with different buckets with the same name
- Initially reported by user 'LeaChim' in IRC.
Tracked it down to CrushWrapper::insert_item() that will eventually e... - 12:41 AM Revision b35e37fb (ceph): osdc/Striper: fix handling for sparse reads in add_partial_sparse_result()
- If bl_map begins *after* the first item in buffer_extents, we want to
skip only the first buffer extent before doing ... - 12:30 AM Revision 328d72d7 (ceph): rgw: signal shuts down fcgi socket
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
11/20/2012
- 11:48 PM Revision ca086261 (ceph): xfstests: run in parallel on multiple machines
- xfstests itself still seems to have some global dependencies that
make it hard to run more than one instance per node... - 11:30 PM Revision 4eb50e68 (ceph): crypto: fix nss related leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:30 PM Linux kernel client Bug #3514 (Resolved): support 32-bit placement seed
- The current ceph_pg struct in the kernel uses 16 bits for the placement seed, limiting the total number of pgs.
- 09:57 PM Revision 1c50db6a (ceph): rgw-logsocket: a task to verify opslog socket works
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:57 PM Revision 26df886d (ceph): rgw-logsocket: a task to verify opslog socket works
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:55 PM Revision 436baa0b (ceph): java: add Java exception for ENOTDIR
- This specialization is useful in the Hadoop CephFS shim. An lstat may
return ENOTENT or ENOTDIR or some other IOExcep... - 09:53 PM Revision 700b5c00 (ceph): qa/run_xfstests.sh: drop tests 174 and 181
- These tests are showing intermittent failures so we'll drop them
from the default list for the time being.
Signed-of... - 09:48 PM Revision 8bb3a150 (ceph): rbd_xfstests: fix the test list, drop 181
- The main purpose of this was to eliminate test 181 from the list.
But I also found the test list that was there was b... - 09:12 PM Revision 57c8116c (ceph): doc: filename change to fix a link.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:21 PM Revision 15f77131 (ceph): doc: fixed links that broke due to new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:57 PM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- also:...
- 04:40 PM Bug #2954 (In Progress): osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/2538...
- ubuntu@teuthology:/a/teuthology-2012-11-18_19:00:03-regression-master-testing-gcov/1220
2012-11-18 22:02:46.290679... - 04:52 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- er, commit:b35e37fb73c942c9be6c551d9c52d9507bc7fd7f
- 04:39 PM Bug #3428 (Resolved): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- commit:ba1e2cc68b236e2cd79dc2c5821ed47080746a86
- 03:53 PM Revision df3b1b89 (ceph): task/pexec: Output stderr to teuthology log
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 07:15 AM Bug #3513: rgw log show error
- It looks like you've put spaces in your command line, should be '--bucket=<bucket>' and not '--bucket = <bucket>', etc.
- 01:10 AM Revision f86522cd (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:52 AM Revision 98a04d76 (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:44 AM Revision 394768bc (ceph): doc: Removed "deprecated" from toctree. Confused some users.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:34 AM Revision 739bca15 (ceph): doc: Removing old/unused images.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
11/19/2012
- 11:36 PM Bug #3513 (Resolved): rgw log show error
- hi ,
am using, ubuntu 12.04 lts operating with kernel version '3.2.0-23-generic'
and ceph version '0.52-958-gdb7c... - 04:33 PM Revision d516307d (ceph): task/ceph-fuse: Add log messages for abort
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 04:33 PM devops Tasks #3512 (Closed): Publish our fastcgi packages
- Right now, our fastcgi packages are only available from a gitbuilder address. We should have a pretty-published set o...
- 04:04 PM Revision de12ae98 (ceph): Merge branch 'next'
- 03:49 PM Feature #3511 (New): figure out how to best set the heartbeat grace periods
- In Journal Club today we discussed failure detection, and we realized that while much of our failure detection has so...
- 03:06 PM Bug #3431 (Fix Under Review): ceph fuse crashed during fsx test
With the fixes in place, we now get an assertion on readx path during lru cache eviction. I've pushed proposed fix...- 02:48 PM Messengers Bug #3510 (Resolved): messenger doesn't fill in nonce if port is specified
- A user came into irc this morning have trouble getting rebooted OSDs into the cluster. Sam tracked it down to the dae...
- 02:00 PM Bug #3428 (In Progress): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- 01:31 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- ...and this seems to reproduce it so far:
./test_librbd_fsx -d -W -R -p 10 -t 1 -S 4 -N 300 rbd fsx - 12:55 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- Running test_librbd_fsx I encountered this again (with master, including
the changes in wip-rbd-read):
272 read... - 01:49 PM Feature #3319 (Resolved): java: add unit test target with check:jni,nabounds options
- 01:49 PM CephFS Feature #3338 (Resolved): java: add unit tests for link/unlink/readlink/symlink
- 11:06 AM rgw Feature #3441 (Resolved): rgw: integrate with Keystone
- 11:06 AM rgw Feature #3343 (Resolved): rgw: stripe objects
- 11:06 AM rgw Feature #771 (Resolved): rgw: POST
- 11:06 AM rgw Feature #1717 (Resolved): rgw: support json input
- 05:20 AM Revision f8f452f3 (ceph): Merge remote-tracking branch 'gh/wip-mon-parsing' into next
11/18/2012
- 10:37 PM Revision 34e5f9bb (ceph): Merge branch 'wip-mon-leaks-fix' into next
- 10:35 PM Revision 837ab3c7 (ceph): xfstests: disable 174
- 2012-11-18T11:11:53.032 INFO:teuthology.orchestra.run.out:174 [failed, exit status 1] - output mismatch (see 174.o...
- 10:34 PM Revision 841a2895 (ceph): xfstests: explicitly enumerate test list
- 09:23 PM Bug #3465 (Resolved): Unclear error message when running 'ceph osd rm'
- 05:24 PM Revision 7a602fa1 (ceph): workunit: fix default subdir
- Make subdir argument optional.
- 04:34 PM Revision 288db95a (ceph): mon: shutdown async signal handler sooner
- Before the mon, and lockdep, in particular.
#0 __pthread_mutex_lock (mutex=0x30) at pthread_mutex_lock.c:50
#1 0x0... - 04:29 PM Revision 82042adf (ceph): msg/Pipe: remove useless reader_joining
- We set it but do not read it.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:29 PM Revision 92d6b8e6 (ceph): mon/AuthMonitor: reorder session->put()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:29 PM Revision 45c652d7 (ceph): mon/AuthMonitor: refactor assign_global_id
- Move the failure logic into the caller, where we easier to do something
about it and return the right value to the ca... - 04:29 PM Revision e0e9a2da (ceph): msg/Pipe: don't leak session_security
- Make sure we free old instances of sesseion_security before we reset the
pointer.
Signed-off-by: Sage Weil <sage@ink... - 04:29 PM Revision 6d3afce4 (ceph): mon: sessions get cleaned up before dtor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:29 PM Revision 005967d2 (ceph): mon: drop con->session reference in remove_session()
- This captures all callers.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:29 PM Revision 3e2eb3a1 (ceph): mon: clean up Subsription xlists
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:29 PM Revision 183953e1 (ceph): msg/SimpleMessenger: use put() on local_connection
- This aids leak debugging; not much else.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:29 PM Revision c4caf871 (ceph): msg/DispatchQueue: fix message leak from discard_queue()
- We need to drop the Message ref() here; the msgr owns one ref
independent of those from the intrusive_ptr's in the qu... - 04:29 PM Revision c07c93e0 (ceph): msg/Pipe: join previous reader threads
- We may stop and then restart the reader thread. Join previous threads
before we create new ones.
Signed-off-by: Sag... - 04:28 PM Revision 988f92a7 (ceph): mon: remove all sessions on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:28 PM Revision 900a0fa2 (ceph): mon: Monitor: drop election messages if entity doesn't have enough caps
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:28 PM Revision 9e3ceca0 (ceph): mon: Monitor: finish contexts on shutdown
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:28 PM Revision bbe2e1ad (ceph): mon: Paxos{,Service}: finish contexts and put messages on shutdown
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:28 PM Revision d0057325 (ceph): mon: Monitor: make MSG_MON_PAXOS case a bit more consistent
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:42 PM Revision 5cf6c7e9 (ceph): ceph_mon: cleanup on shutdown
- Properly cleanup the throttlers, 'g_ceph_context' and the
async_singnal_handler.
Signed-off-by: Joao Eduardo Luis <j... - 10:12 AM Bug #2386 (Resolved): xfstests: failed #34
- 09:29 AM Bug #3134 (Can't reproduce): osd: hang in journal?
- 09:27 AM Messengers Feature #3509 (Resolved): msgr: delay injection
- 07:21 AM Revision 68491afc (ceph): rgw: add -lresolv flags to Makefile.am
- radosgw depends on libresolv since since the commit 951c6be. So we need to
add -lresolve flags, or it cannot link rig... - 05:01 AM Revision fa63dd42 (ceph): valgrind: enumerate warnings in log; check leaks from client, mon only
- 12:30 AM Revision 7903aabe (ceph): mon/MonClient: use thread-safe RNG for picking monitors
- Avoid using shared-state rand() when picking monitors. This way we don't
screw with library users like test_librbd_f...
11/17/2012
- 10:45 AM Feature #3508 (Rejected): default to system libs3
- 09:29 AM Bug #3507 (Resolved): rados api system tests failure
- ...
- 05:26 AM Revision f9fd0659 (ceph): Merge remote-tracking branch 'gh/wip-3431' into next
- 01:59 AM Revision 07c831ac (ceph): upstart: fix limit lines
- Two arguments.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:36 AM Revision e85c9e7b (ceph): Merge branch 'wip-coverity' into next
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 01:36 AM Revision 12eb797f (ceph): client: fix lock leak in lazio_*() failure paths
- CID 743400 (#1 of 1): Missing unlock (LOCK)
At (5): Returning without unlocking "this->client_lock._m".
CID 743399 (... - 01:28 AM Revision ff0a44bb (ceph): upstart: make ceph-osd-all, ceph jobs
- This will let you start/stop all daemons.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:28 AM Revision b4a769df (ceph): upstart: add ceph-osd-all-starter.conf
- Starter helper will start all osds that appear in /var/lib/ceph/osd/*,
as we do with the mons and mdss.
This will on... - 01:14 AM Revision 48295a18 (ceph): Merge branch 'next'
- 01:14 AM Revision 3610754a (ceph): Makefile.am: fix LDADD for test_objectcacher_stress
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 12:55 AM Revision 2ab8b388 (ceph): task: benchmark recovery
- Measures latency before and during recovery using smalliobench.
Signed-off-by: Mike Ryan <mike.ryan@inktank.com> - 12:44 AM Revision 59099972 (ceph): Merge branch 'next'
- 12:43 AM Revision 78382fec (ceph): Merge branch 'wip-oc-hang' into next
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 12:19 AM Revision be11c317 (ceph): upstart: set high open file limits
- The default 1024 limit is easily hit on larger clusters.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:10 AM Revision 25f003ba (ceph): msg/Accepter: only close socket if >= 0
- It is possible for rebind() to fail, in which case the OSD will go through
it's shutdown procedure and call stop(). ... - 12:04 AM Revision 30373ce8 (ceph): osd: default journal size to 5GB
- Signed-off-by: Sage Weil <sage@inktank.com>
11/16/2012
- 11:27 PM Revision a562518b (ceph): librbd: take cache lock when discarding data from cache
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 11:22 PM Revision 8c961610 (ceph): ObjectCacher: don't needlessly increment iterator
- This iterator is now reset on each run through the loop,
so there's no point in incrementing it here.
Signed-off-by:... - 11:22 PM Revision 7570e6c8 (ceph): ObjectCacher: debug read waiters
- Now we can tell which ones will be called.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 11:22 PM Revision c054ad6d (ceph): ObjectCacher: assert lock is held everywhere
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 11:22 PM Revision 5d760b77 (ceph): ObjectCacher: more debugging for read completions
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 11:22 PM Revision 20a0c56d (ceph): ObjectCacher: add debug function to check BufferHead consistency
- This isn't called because it's potentially expensive, but calling it
in various places can help future debugging.
Si... - 11:22 PM Revision fdadefe3 (ceph): ObjectCacher: begin at the right place when iterating over BufferHeads
- If the desired offset overlaps a BH, data.lower_bound() will return
the element after it, since it's indexed by the s... - 11:22 PM Revision 2e862f4d (ceph): ObjectCacher: fix off-by-one error in split
- This error left a completion that should have been attached
to the right BufferHead on the left BufferHead, which wou... - 11:22 PM Revision b948e4c9 (ceph): ObjectCacher: retry reads when they are incomplete
- Skipping these callbacks when there's a racing write or
a gap in the results causes the original reads they represent... - 11:17 PM Revision 29a96cf2 (ceph): rgw: ops log can also go to socket
- Adding a new ops log output (into a unix domain socket).
Configuration:
rgw_enable_usage_log : master switch for op... - 11:13 PM Revision 7b96807d (ceph): doc: Added links to APIs.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:58 PM Revision c42af803 (ceph): doc: Added documentation for using CPU profiler.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:57 PM Revision 84eac866 (ceph): doc: Added documentation for installing CPU profiler.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:57 PM Revision 3ccaaa09 (ceph): doc: Added librbd to the RBD toc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:56 PM Revision 9ea2609e (ceph): doc: Added libcephfs to the CephFS section and moved librbd to RBD sect...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:28 PM Revision feb8451f (ceph): doc: don't use 'pool=data' as an example
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 10:19 PM Revision 8da6ddea (ceph): common/ceph_argparse: fix malloc failure check
- CID 743418 (#1 of 1): Dereference before null check (REVERSE_INULL)
Null-checking "argv" suggests that it may be null... - 10:18 PM Revision e82ca0d5 (ceph): mon/MonClient: initialize ptr in ctor
- CID 743433 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
At (2): Non-static class member "authorize_handler_re... - 10:15 PM Revision 8f1f36d5 (ceph): os/FileStore: fix fd leak in _rmattr
- CID 743405 (#2 of 2): Resource leak (RESOURCE_LEAK)
At (16): Handle variable "fd" going out of scope leaks the handle... - 10:14 PM Revision 426b58da (ceph): os/FileStore: fix fd leaks in _setattrs
- CID 743406 (#3 of 3): Resource leak (RESOURCE_LEAK)
At (26): Handle variable "fd" going out of scope leaks the handle... - 10:11 PM Revision 1df38fd7 (ceph): osdc/ObjectCacher: faux use-after-free
- CID 743435 (#1 of 1): Use after free (USE_AFTER_FREE)
At (68): Passing freed pointer "rd" as an argument to function ... - 09:23 PM Revision 9a10ebb2 (ceph): test: add ObjectCacher stress test that does not use a cluster
- Use a fake writeback handler and respond to all requests with -ENOENT.
This tests that all operations will complete, ... - 09:18 PM Feature #3506 (Resolved): mkcephfs: multiple fs optiopns
- 09:18 PM Feature #3505 (Resolved): default to libnss
- 08:11 PM Revision fd928b9b (ceph): ObjectCacher: more debugging for BufferHeads
- This is useful for checking for lost waiters.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 06:51 PM Revision 8b187bd8 (ceph): build: update for boost_thread library.
- There is a difference in naming conventions between debian and
rpm based distributions for this library. In configur... - 06:02 PM Bug #3286: librbd, kvm, async io hang
- I fixed a few bugs that could cause this in the wip-oc-hang branch. This is now merged into the next and master branc...
- 04:11 PM Bug #3504 (Resolved): msg/Accepter.cc: 246: FAILED assert(listen_sd >= 0)
- commit:25f003ba5f8ef9d58b794fb718ef8d637fd67c6a
- 04:07 PM Bug #3504 (Resolved): msg/Accepter.cc: 246: FAILED assert(listen_sd >= 0)
- ...
- 03:30 PM Revision 493049b4 (ceph): mon: OSDMonitor: clarify some command replies
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:30 PM Revision 0b28ef6a (ceph): mon: OSDMonitor: fix spacing when outputting items on command reply
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:42 PM rbd Bug #3503 (Resolved): rbd: import "-" no longer works
- rbd import from stdin was broken at some point in the past, not clear when.
We should probably have a test for this.... - 12:39 PM rbd Bug #3478: rbd: copy destination pool is assumed to be source pool
- But on reflection, this makes no sense, and we should fix it; default destination pool should be "rbd" on Principle o...
- 12:38 PM Feature #3502 (Resolved): rbd export should support stdout
- This comes up every so often in IRC, and should not be hard to implement.
- 10:26 AM Bug #3497 (Resolved): mon: leader segfaults after restarting osds
- Removing said commit fixes the crash.
The patch was putting the Connection back as part of the session cleanup, so... - 09:41 AM Bug #3497 (In Progress): mon: leader segfaults after restarting osds
- After some testing, git bisect reports 19831b979a13f699b0e87125dfcfad3ea607d713 as the first bad commit.
Attemptin... - 08:16 AM Bug #3497: mon: leader segfaults after restarting osds
- Different paxos machine, crashes on the same place after finishing the contexts. Only happens on wip-mon-leaks-fix af...
- 09:54 AM Bug #3501 (Resolved): gitbuilder: rsync out tags
- 09:00 AM Bug #2819: krbd: lockup on large writes, msgr fault injection
- (Sadly, my machine crashed in the middle of a somewhat elaborate
update to this. I'll try to recapture what I had a... - 08:56 AM Revision 27830e2c (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 08:46 AM Revision f0c7bb36 (ceph): build: update for boost_thread library.
- There is a difference in naming conventions between debian and
rpm based distributions for this library. In configur... - 08:38 AM rbd Bug #3427: krbd: unmap does not remove block device properly
- This appears to be using kernel 3.2.23. Lots of work has gone into
rbd in the last year, and I don't believe any of... - 08:35 AM rbd Bug #2522: xfstest #219
- Possibly related to http://tracker.newdream.net/issues/3449
- 08:35 AM rbd Bug #3449: fix xfstest 45 on precise
- Possibly related to http://tracker.newdream.net/issues/2522
- 07:35 AM Bug #3465: Unclear error message when running 'ceph osd rm'
- Thanks for taking care of this Sage.
I've pushed another two patches on top of it. One of them should be merged wi... - 07:07 AM Revision c707568a (ceph): doc: fix crush set syntax
- No commas between parameters, pool is required.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 06:11 AM RADOS Fix #3500 (New): mon: use new MessageRef and intrusive_ptr's throughout the Monitor's message han...
- Using MessageRef and intrusive_ptr's for all the messages should allow us to simplify the code and avoid memory leaks...
- 06:04 AM Revision 43b57dec (ceph): check ceph-mon for leaks
- 12:50 AM Revision 71cfaf1c (ceph): os/FileStore: only try BTRFS_IOC_SUBVOL_CREATE on btrfs
- Only try to create a btrfs subvolume if the fs is btrfs. Otherwise, just
create a directory. Then we can error out ... - 12:35 AM Revision 3ca947e0 (ceph): mon: clean up 'ceph osd ...' list output
- No more 'osd.0 is already inosd.1 is already in' crap.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:32 AM Revision 592a8942 (ceph): mon: use parse_osd_id() throughout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:32 AM Revision 344c4fdc (ceph): mon: correctly identify crush names
- get_item_id() returns 0 if the name already exists; that's not what we
want here. Verify the name exists before chec... - 12:02 AM Revision 918c58c8 (ceph): PrioritizedQueue: remove internal lock, not used
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
11/15/2012
- 11:59 PM Revision b53e06ca (ceph): DispatchQueue: lock DispatchQueue when for get_queue_len()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 11:51 PM Revision 659d4c25 (ceph): run_xfstests.sh: activate more tests that now work
- I've gone through the set of xfstests that were previously found to
not work. Some of those now do work, and with th... - 10:03 PM Revision 22cb1356 (ceph): doc: add Hadoop configuration parameters
- fs.ceph.block.size and fs.ceph.replication.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 07:36 PM Revision 2fd9f4d7 (ceph): Merge remote-tracking branch 'gh/next'
- 06:55 PM Revision 63c51288 (ceph): smalliobench: fix init-only, add don-not-init
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Mike Ryan <mike.ryan@inktank.com> - 06:06 PM Revision b40387de (ceph): msg/Pipe: fix leak of Authorizer
- Reported-by: Joao Luis <joao.luis@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com> - 05:48 PM Revision 0fb23cf8 (ceph): Merge remote-tracking branch 'gh/wip-3477' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 05:22 PM Revision cd18b9f4 (ceph): rgw: don't convert object mtime to UTC
- Fixes: #3452
When we read object info, don't try to convert mtime to
UTC, it's already in UTC.
Signed-off-by: Yehuda... - 04:47 PM Bug #3052 (Resolved): ceph-osd --mkfs fails on ext3
- commit:71cfaf1cc5b1d77676aaf0be6daa15d4ab303386
- 04:40 PM Bug #3052 (Fix Under Review): ceph-osd --mkfs fails on ext3
- 04:42 PM Bug #3465 (Fix Under Review): Unclear error message when running 'ceph osd rm'
- pushed to wip-mon-parse
- 04:05 PM rbd Feature #3499 (Resolved): qemu-rbd: support bdrv_has_zero_init
- Later qemu seems to have added a BlockDriver entry point "bdrv_has_zero_init"; it
looks as though this might control... - 03:57 PM Bug #3459 (Resolved): osd crash in CephXAuthorizer::verify_reply
- this should be fixed by the new guards around decrypt_decode().
- 03:33 PM Bug #3496 (In Progress): doc: have old URL's redirect to new ones
- Patrick McGarry is working with me on this while Ross is out. We have a few more to go for the new IA. Should be done...
- 07:06 AM Bug #3496 (Resolved): doc: have old URL's redirect to new ones
- On IRC, "jefferai" (Jeff Mitchell) pointed out that the first hit
on "ceph add mon" clicks through to a non-existent... - 02:40 PM CephFS Bug #3498 (Resolved): mds: mds assert failure during untar_kernel
- Saw a few mds assertions during testing for #3490, running the untar_kernel script a bunch of times on teuthology. S...
- 02:31 PM CephFS Bug #3490 (In Progress): client: ENOENT during kernel_untar_build.sh over fuse
- 09:21 AM rgw Bug #3400 (Resolved): rgw: multipart upload overwrite broken
- Fixed, commit:84299e16f3b7b74cff814eb9a754b7dfa046a0f9
- 09:19 AM rgw Bug #3487 (Resolved): rgw: detect required RGWCache api changes in build time
- Done, commit:5d27f3da654b2d1b3f90a5758fc47b89f012a8d2
- 09:15 AM rgw Bug #2527 (Resolved): RGW may return 409 Conflict when deleting a bucket
- The problem here was that the bucket was not really empty, there was an issue with cache not being updated (so user s...
- 08:31 AM Bug #3497: mon: leader segfaults after restarting osds
- Might have jumped the gun on this description. Assumed too much from what I did when I wrote the description. The seg...
- 08:14 AM Bug #3497 (Resolved): mon: leader segfaults after restarting osds
- ...
- 07:39 AM Bug #3495 (In Progress): ceph-mon crash
- Thanks for reporting it. Will look into it.
By the way, this is what the crash looks like:... - 07:00 AM Bug #3495 (Resolved): ceph-mon crash
- Have found a core of ceph-mon in /.
Ceph is from "deb http://ceph.com/debian-testing/ wheezy main":
# ceph -v
ce... - 01:34 AM Revision 6ebd6ba4 (ceph): Verifying check-in capability
- 01:24 AM Revision 69e613f0 (ceph): Starting to auto-document this code.
- 01:05 AM Revision 12c2b7fa (ceph): msg/DispatchQueue: release throttle on messages when dropping an id
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:05 AM Revision 5f214b29 (ceph): PrioritizedQueue: allow remove_by_class to return removed items
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:05 AM Revision 4a7a81bb (ceph): objecter: fix leak of out_handlers
- The error paths don't use the handlers. Make sure they get cleaned up.
Fixes: #3446
Signed-off-by: Sage Weil <sage@... - 01:05 AM Revision 98b93b5d (ceph): librbd: use delete[] properly
- ==4986== Mismatched free() / delete / delete []
==4986== at 0x4C2658C: operator delete(void*) (in /usr/lib/valgrin... - 01:00 AM Revision ef4e4c82 (ceph): mon: calculate failed_since relative to message receive time
- Instead of looking at the current time we process the message, look at the
receive time. This gives us a more real f... - 12:45 AM Revision 9267d8a4 (ceph): rgw: update post policy parser
- json parser semantics changed a little bit, so
needed to update the policy parser.
Signed-off-by: Yehuda Sadeh <yehu... - 12:34 AM Revision 7f847024 (ceph): Merge branch 'master' of https://github.com/ceph/teuthology
- 12:27 AM Revision 87e1fc12 (ceph): Added comment explaining how setup is tied to actual code.
- 12:26 AM Revision f6cb0780 (ceph): mon: set default port when binding to random local ip
- Fixes #3135
Signed-off-by: Sage Weil <sage@inktank.com> - 12:22 AM Revision dfeb8ded (ceph): Merge remote-tracking branch 'gh/wip-asok' into next
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
11/14/2012
- 11:51 PM Revision ce284552 (ceph): rgw: relax date format check
- Don't try to parse beyond the GMT or UTC. Some clients use
special date formatting. If we end up misparsing the date
... - 11:49 PM Revision ddb40dec (ceph): rgw: relax date format check
- Don't try to parse beyond the GMT or UTC. Some clients use
special date formatting. If we end up misparsing the date
... - 10:57 PM Revision 0a2a0c07 (ceph): doc: config-cluser move to new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:55 PM Revision 5c302ebb (ceph): doc: Move of cluster ops for new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:49 PM Revision 652c4294 (ceph): workunit: Fix indentation
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 08:51 PM Revision 05065dff (ceph): task/ceph-fuse: If umount fails, abort and cleanup
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 07:46 PM rgw Feature #3494 (Closed): ceph S3 upload slowly
- Hi, there!
Nowadays I have tried some tests on ceph S3 python API, But I have found that it is very slow to update a... - 05:03 PM rbd Bug #3491 (Resolved): test_librbd_fsx: too many open files
- commit:12c2b7fa20be6878bc0763404d2a5c648e5fadbc
- 09:22 AM rbd Bug #3491: test_librbd_fsx: too many open files
- a zillion msgr threasd blocked behind...
- 09:11 AM rbd Bug #3491 (Resolved): test_librbd_fsx: too many open files
- this is probably something runaway in the msgr, but:...
- 04:58 PM rbd Bug #3478: rbd: copy destination pool is assumed to be source pool
- Actually I think this has been the behavior since copy was added in
e0229b0a1f9f46a6f6140873c17420d9bd85c87c - 04:57 PM rbd Bug #3446 (Resolved): Objecter: leaks ObjectOperation::C_ObjectOperation_stat
- 04:52 PM rbd Bug #3446 (Fix Under Review): Objecter: leaks ObjectOperation::C_ObjectOperation_stat
- 04:45 PM Revision cfa2883d (ceph): pexec: Logging each command isn't useful
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 04:35 PM Bug #3129 (Can't reproduce): valgrind reported error on uninitialized osd
- haven't seen this since
- 04:35 PM Bug #3135: mon_host without ports leads to failure
- commit:f6cb0780acc7d56ec1fd932a7bab5ddddb42a481
- 04:34 PM Bug #3135 (Resolved): mon_host without ports leads to failure
- 04:19 PM CephFS Bug #3486 (Resolved): ceph-fuse, mds: admin socket lock cycle
- 09:06 AM CephFS Bug #3486 (Fix Under Review): ceph-fuse, mds: admin socket lock cycle
- 04:12 PM Revision 25964046 (ceph): Add task pexec to run bash commands in parallel
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:59 PM rbd Bug #3493 (Resolved): libvirt: storage pool does not work with cephx disabled
- ...
- 01:34 PM Bug #3287: OSD dies when using zfs
- Mike, did you ever have a chance to try to reproduce this with more debug on?
- 11:40 AM rgw Bug #3492 (Resolved): rgw: relax date parsing
- Some clients use different data format. Arq uses the following (which currently does not parse):
Wed, 14 Nov 2012 ... - 10:06 AM Revision 8430210c (ceph): doc: add-or-rm-mons.rst: fix typo
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 09:06 AM CephFS Bug #3490 (Resolved): client: ENOENT during kernel_untar_build.sh over fuse
- ...
- 07:00 AM Bug #3489 (Resolved): osd: slow request warnings
- ...
- 02:19 AM Bug #3477 (Resolved): mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- AFAICT, that's the osds reporting slow requests; it doesn't have anything to do directly with the monitor or this bug...
- 02:18 AM Revision 4a34965c (ceph): client: register admin socket commands without lock held
- Avoid a lock cycle.
existing dependency Client::client_lock (11) -> AdminSocket::m_lock (16) at:
ceph version 0.54-... - 02:17 AM Revision 4db9442b (ceph): objecter: separate locked and unlocked init/shutdown
- We don't want to hold the lock while we register the admin socket commands
or else we create a lock cycle when we try... - 01:29 AM Revision 7926ef53 (ceph): Merge branch 'next'
- Conflicts:
configure.ac
src/rgw/rgw_common.cc - 01:11 AM Revision d5bc66ac (ceph): doc/release-notes: fix heading
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:09 AM Revision d395131c (ceph): osd/: add config helper for min_size and update build_simple*
- min_size should never be set to 0 on a pool. config.h
now has a helper to determine the correct default value.
Sign... - 12:29 AM Revision 74f7607a (ceph): doc: release-notes for v0.54
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:00 AM Revision 0d42e976 (ceph): doc: update crush weight ramping process
- Signed-off-by: Sage Weil <sage@inktank.com>
11/13/2012
- 11:43 PM Revision 131d15a7 (ceph): rgw: fix warning
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:39 PM Revision 97f65f6e (ceph): Merge branch 'wip-min-size'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 11:34 PM Revision 1a531e50 (ceph): schedule_suite.sh: less noise
- 11:16 PM Revision a0eb8919 (ceph): osd: default pool min_size to 0 (which gives us size-size/2)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:12 PM Revision 735df024 (ceph): mon: helpful warning in 'health detail' output about incomplete pgs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:12 PM Revision 9d979d76 (ceph): osd: default min_size to size - size/2
- size -> min_size:
5 -> 3
4 -> 2
3 -> 2
2 -> 1
Basically, default to tolerating minority down.
Signed-off-by: Sa... - 11:12 PM Revision 1d00f3aa (ceph): mon: default min_size to size-size/2 if min_size default is 0
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:12 PM Revision 1679a556 (ceph): osd: start_boot() after init()
- The previous trigger for start_boot() was racy, depending on whether we
got our rotating keys quickly.
Signed-off-by... - 11:12 PM Revision 65961ca2 (ceph): vstart.sh: support -X by adding 'auth required = none' entries
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:50 PM Revision 6a8a59c5 (ceph): Merge remote-tracking branch 'gh/wip-rgw-integration'
- Conflicts:
src/common/config_opts.h - 10:33 PM Revision 5687555f (ceph): schedule_suite.sh: less noise
- 09:18 PM Revision 60b84b09 (ceph): v0.54
- 09:06 PM Revision 5d27f3da (ceph): rgw: compile with -Woverloaded-virtual
- This will trigger a warning if RGWRados api changes while
RGWCache doesn't.
Signed-off-by: Yehuda Sadeh <yehuda@inkt... - 08:39 PM Revision 1be99237 (ceph): rgw: fix RGWCache api
- RGWCache api diverted form RGWRados, crippling the cache.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:39 PM Revision e0e33d2c (ceph): rgw: fix RGWCache api
- RGWCache api diverted form RGWRados, crippling the cache.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:29 PM Revision 2770ef72 (ceph): peer.yaml: assumes osd_pool_default_min_size is 1
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:29 PM Revision 9a38059a (ceph): osd: remove dead rotating key code from init
- Ancient, dead.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:28 PM Revision eee09822 (ceph): osd: defer boot until we have rotating keys
- Make sure we have our rotating keys before we start booting. This
ensures we can open connections with peers *before... - 06:56 PM Revision b151597e (ceph): Merge branches 'wip_persist_missing' and 'wip_recovery_qos'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:56 PM Revision fcbbebc3 (ceph): PG::merge_old_entry: fix case for divergent prior_version
- Previously, we asserted that a log entry with a divergent
prior_version must be a clone. Consider the following
case... - 06:56 PM Revision 193e2ea5 (ceph): PG: persist divergent_priors in ondisklog
- Consider the following logs:
a) 10'10(5'7) foo
12'11(4'3) bar
b) 10'10(5'7) foo
13'11(4'4) baz
When the osd ... - 06:45 PM Revision d1291125 (ceph): common: add RefCountedObj.cc with intrusive_ptr hooks
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision bbdae981 (ceph): Pipe: we don't queue DispatchQueue codes on an actual pipe
- The dispatch queue event codes are now queued directly and
won't end up in a real Pipe.
Signed-off-by: Samuel Just <... - 06:45 PM Revision 25eb1fb9 (ceph): common: Add PriorititizedQueue
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision f02c75e7 (ceph): WorkQueue: Add WorkQueueVal for passing params by val
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision a62d778e (ceph): OSD: use PrioritizedQueue for OpWQ
- The OpWQ PriorityQueue replaces OSD::op_queue, PG::op_queue,
and PG::qlock. The syncronization is now done as part o... - 06:45 PM Revision 5d47db2d (ceph): OSD: queue ops based on message priority
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision bd4707ad (ceph): msg/: use PrioritizedQueue to handle DispatchQueue queueing
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision 57a62554 (ceph): osd/: de-prioritize recovery ops relative to client ops
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:45 PM Revision 95cb6cf4 (ceph): PrioritizedQueue: avoid double-lookup on create_queue()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:45 PM Revision f299be00 (ceph): PrioritizedQueue: use iterator to streamlink SubQueue::remove_by_class()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 PM Revision da0ea9f9 (ceph): rgw: unquote etag for if-match
- Fixes: #3453
Passed ETag for copy/get request may be quoted.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:32 PM Revision 1c20ea98 (ceph): rgw_cache: change call signature to overwrite rgw_rados put_obj_meta()
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 06:32 PM Revision cc06090f (ceph): rgw: don't convert object mtime to UTC
- Fixes: #3452
When we read object info, don't try to convert mtime to
UTC, it's already in UTC.
Signed-off-by: Yehuda... - 06:32 PM Revision 096c8ac9 (ceph): rgw: use thread safe version of gmtime
- Use gmtime_r instead of gmtime.
Signed-off-by: Sylvain Munaut <s.munaut@whatever-company.com> - 06:08 PM rgw Feature #3488 (Resolved): rgw: dump ops log to a socket
- 05:39 PM Revision c4981b81 (ceph): java: remove redundant src.dir
- Previous wip-fix-javadocs had an oversight, redefining src.dir.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 04:14 PM Revision efdb209b (ceph): doc: reorder some openstack/rbd instructions
- Move client creation to the section on setting up client auth, so you
don't skip it if you already have pools created... - 03:02 PM rbd Bug #3445 (Resolved): ObjectCacher: extra memory leaks with caching enabled in wip-rbd-read
- 02:59 PM Bug #2999 (Resolved): osd: msgr crash in OSD::complete_notify
- fixed this a while ago
- 02:59 PM Bug #2649 (Resolved): osd: log bound mismatch
- 02:59 PM Bug #2462 (Resolved): osd/PG.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log.tail)
- 02:59 PM Bug #3213 (Resolved): PG: we do not persist missing set elements not in the log
- 02:59 PM Bug #3208 (Resolved): osd/PG.cc: 1346: FAILED assert(info.last_complete >= log.tail)
- 02:58 PM Bug #2691 (Resolved): osd/ReplicatedPG.cc: 5888: FAILED assert(latest->is_update())
- 01:42 PM Bug #3431 (Resolved): ceph fuse crashed during fsx test
- Fixed by caed0e917
- 12:02 PM Bug #2176: dependencies not checked by autoconf
- I think we have picked up some, but not all of these. I'll double check with a freshly installed system.
- 12:00 PM Bug #3250: debs don't include Contents-<arch>.gz
- Now building with Contents files for tagged releases. Still need to fix for gitbuilders.
- 11:58 AM Bug #3477: mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- Can't reproduce the crash with this branch.
But when i trigger
ceph osd out 51; ceph osd out 52; ceph osd out 53;... - 09:08 AM Bug #3477: mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- 09:08 AM Bug #3477: mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- Sage pushed a couple of commits that should solve this issue last night. They can be found in wip-3477. I just haven'...
- 11:57 AM Bug #3471 (Resolved): rpm: build src, debuginfo packages
- 11:56 AM Bug #3451 (Resolved): qa: rpm autobuilt packages should get 'git describe' version
- 11:55 AM Bug #3451: qa: rpm autobuilt packages should get 'git describe' version
- Commit ff5ee98f1c97b286a81848dc3b70ea523d8fe95e in master.
- 10:30 AM rgw Bug #3487 (Resolved): rgw: detect required RGWCache api changes in build time
- 10:08 AM Bug #3459: osd crash in CephXAuthorizer::verify_reply
- ubuntu@teuthology:/a/sage-2012-11-12_16:44:02-regression-master-wip-3.4-basic/13948
- 09:43 AM CephFS Bug #3486: ceph-fuse, mds: admin socket lock cycle
- same for ceph-fuse, probably other objecter->init() callers as well.
- 09:41 AM CephFS Bug #3486 (Resolved): ceph-fuse, mds: admin socket lock cycle
- ...
- 09:28 AM rgw Bug #3485 (Resolved): rgw: unique user emails not enforced
- Currently it is possible to create multiple users sharing the same email address. Unique emails should be enforced
- 08:50 AM Bug #3465: Unclear error message when running 'ceph osd rm'
- Will do.
- 08:46 AM Feature #3484 (Resolved): mon: 'ceph df'
- 08:46 AM rbd Feature #3483 (Resolved): use table formatter for other rbd, rados operations
- 08:41 AM Feature #3482 (Resolved): sles gitbuilder; release rpms
- 01:16 AM Bug #3475: ugly formatting of ceph osd tree
- I'm using the latest stable, so argonaut 0.48.2. Great to hear it's already fixed in master, looking forward to bobta...
- 01:01 AM Revision 32fb8eaf (ceph): Merge branch 'wip-client-asok'
- 12:31 AM Revision caed0e91 (ceph): osdc/ObjectCacher: do not take Object ref for bh writes
- This reverts commit 46897fd4ffc2fe2fc2cc0c39b5d4c510df1e6c25.
There is no reason to carry a ref for the writes; it j... - 12:29 AM Revision 8b4bdda5 (ceph): client: Remove object from oset before deleting
- Prevent invalid memory references for cases where
a truncate causes an object to be deleted but the
object set still ...
11/12/2012
- 11:50 PM Revision 0b85e43c (ceph): java: fix build.xml formatting
- set noet ts=2 sw=2 sws=2
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 11:50 PM Revision 8970e81a (ceph): java: fix javadoc builds
- Don't build JavaDoc for tests, and fix the missing src.dir variable.
Signed-off-by: Noah Watkins <noahwatkins@gmail.... - 11:44 PM Revision a11940f5 (ceph): osdc/ObjectCacher: only return ENOENT if ObjectSet is flagged
- The fs client can't handle ENOENT from the cache, but librbd wants it.
Also, the fs client will send down multiple Ob... - 11:06 PM Revision ad3063a4 (ceph): client: dump mds session info
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:06 PM Revision 7d1974c5 (ceph): client: fix null dentry crash on dump_cache
- Dentries can be NULL!
Signed-off-by: Sage Weil <sage@inktank.com> - 11:06 PM Revision 16db00d5 (ceph): client: unregister commands on shutdown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:05 PM Revision 2c28e5dc (ceph): common: dumpers for ceph_{file,dir}_layout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:05 PM Revision fc6b82f0 (ceph): client: add dump_cache asok command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:05 PM Revision ef71f32a (ceph): Makefile: use libclient.la for libcephfs
- Avoid building these files twice!
Signed-off-by: Sage Weil <sage@inktank.com> - 11:05 PM Revision 809d0e56 (ceph): Makefile: fix hadoop lib build
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:05 PM Revision 69c47d3d (ceph): client: add mds_requests asok command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:03 PM Revision bc398c03 (ceph): Merge branch 'next'
- 11:02 PM Revision dc2ced96 (ceph): Merge branch 'wip-client-leaks' into next
- 11:02 PM Revision 2f241685 (ceph): client: fix null put in ~MetaSession
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:59 PM Revision 8b1f5472 (ceph): librbd: fix create existence checking
- cda9e516b8bb09b8846814cc8d4ee2879a53b2d5 made us return 0 when the
image already existed, causing copy to erroneosly ... - 09:57 PM Revision 614cf34b (ceph): librbd: debug when copy occurs
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 09:54 PM Revision 9c31d09f (ceph): mon: kick failures when we lose leadership
- If we were leader and are not anymore, kick any pending failure messages.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:53 PM Revision 763d348c (ceph): mon: ignore failure messages if already pending a failure
- If a failure is already pending, do nothing in check_failure().
Signed-off-by: Sage Weil <sage@inktank.com> - 09:53 PM Revision e43f9d72 (ceph): mon: process failures when osds go down
- If we see an osd go down, process any pending failure_info reports we have.
Reply, and then remove the record from th... - 08:36 PM Revision f63b7711 (ceph): Merge remote-tracking branch 'gh/wip-javadoc'
- 08:30 PM Revision b94037ce (ceph): Merge remote-tracking branch 'gh/wip-librbd-remove-cleanup'
- 08:04 PM Revision 23531c29 (ceph): osd: add 'osd debug drop op probability'
- This is meant to exercise the kclient's timeout and osd reconnect logic
by dropping some client requests on the floor... - 08:01 PM Revision efa03cef (ceph): mon: require pgnum in 'ceph osd pool create <poolname> <pgnum> [<pgp_nu...
- The default of 8 is virtually never the right answer. Require the initial
pg count to be explicitly provided.
Signe... - 07:53 PM Revision e35e7e2b (ceph): ceph-disk-activate: avoid duplicating mounts if already activated
- If the given device is already mounted at the target location, do not
mount --move it again and create a bunch of dup... - 07:53 PM Revision 0c9bbb3b (ceph): ceph-disk-prepare: poke kernel into refreshing partition tables
- Prod the kernel to refresh the partition table after we create one. The
partprobe program is packaged with parted, w... - 07:53 PM Revision b4004806 (ceph): ceph-disk-prepare: fix journal partition creation
- The end value needs to have + to indicate it is relative to wherever the
start is.
Signed-off-by: Sage Weil <sage@in... - 07:53 PM Revision efac1bb1 (ceph): ceph-disk-prepare: assume parted failure means no partition table
- If the disk has no valid label we get an error like
Error: /dev/sdi: unrecognised disk label
Assume any error we ... - 07:24 PM Revision 39b9da40 (ceph): Merge remote-tracking branch 'gh/wip-mds-stable' into stable
- 07:16 PM Revision 25d4f560 (ceph): misc: Show url on get failure
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 07:16 PM Revision cda9e516 (ceph): librbd: return actual error when detecting format fails during creation
- This bit a couple users today, when bad osd caps resulted in a very
confusing error message.
Signed-off-by: Josh Dur... - 07:08 PM Revision a1b950e6 (ceph): Merge remote-tracking branch 'gh/wip-client-symlinks'
- Reviewed-by: Sam Lang <sam.lang@inktank.com>
- 06:45 PM Revision 3d76e677 (ceph): java: add symlink/readlink tests
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:41 PM Revision ca9f93aa (ceph): Merge remote branch 'origin/wip-rbd-read'
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:07 PM Revision 6dd79252 (ceph): test_libcephfs: fix, add symlink loop tests
- The first test did
/a/b/file
/a/b/sym -> /a/b
and opened /a/b/sym/file, which is valid. Change it to
/a/b/file... - 06:07 PM Revision bb2924d4 (ceph): libcephfs_java.yaml: Adding the libcephfs-java test to the suite.
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
- 04:56 PM Revision 3902a018 (ceph): debug: adjust default debug levels
- Trim out most noise, keep things that are interesting.
Notably, we are logging each message sent and received, and w... - 03:24 PM devops Feature #3481 (Resolved): ceph-deploy: remove mon
- 03:23 PM devops Feature #3479 (Resolved): ceph-deploy: uninstall
- 02:46 PM rbd Bug #3478 (Closed): rbd: copy destination pool is assumed to be source pool
- From Andrey Korolyov on ceph-devel:...
- 12:49 PM rbd Feature #3397 (Resolved): librbd: move clone read logic above the cache
- 10:08 AM Bug #3477: mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- i think the fix is to make a clean_osd_failures() fucntion that removes records for down osds, and call that from upd...
- 09:56 AM Bug #3477 (Resolved): mon: 'entity_inst_t OSDMap::get_inst(int)' fails on 'assert(is_up(osd))'
- Reported on the mailing list by Stefan Priebe
http://thread.gmane.org/gmane.comp.file-systems.ceph.devel/10470
... - 09:49 AM CephFS Bug #3424 (In Progress): java: Add the correct JUnit package dependencies on supported platforms ...
- Things seem sorted out for debian and ubuntu. We're not building RHEL at the moment, so we'll need to revisit this wh...
- 08:36 AM Feature #3476 (Resolved): mon: fix all leaks
- make ceph-mon pass valgrind --heap-check=full --show-reachable=yes, and then enable the leak checking in ceph-qa-suit...
- 08:31 AM Bug #3475 (Resolved): ugly formatting of ceph osd tree
- which version are you using? this is fixed in the current master (soon to be bobtail):...
- 04:13 AM Bug #3475 (Resolved): ugly formatting of ceph osd tree
- When having fractional weights like 0.16 ceph osd tree outputs them as 0.159988. This causes the tabbing to be wrong ...
- 08:30 AM devops Bug #3469: ceph-deploy needs to sync with the ceph version it is working with
- We currently rely on fixes in ceph-disk-* that are only in master/next and haven't been backported to stable yet. On...
11/11/2012
- 03:13 PM Revision aabca849 (ceph): fs/verify: check for ceph-fuse leaks
- 03:13 PM Revision 02d62d73 (ceph): valgrind.supp: ceph-fuse leak from libfuse
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:13 PM Revision f9b4efea (ceph): valgrind.supp: deliverate onexit leak
- 03:13 PM Revision a46dd6b6 (ceph): ceph-fuse: apply overrides[ceph-fuse] to config
11/10/2012
- 10:40 AM Revision b17522d7 (ceph): Merge branch 'next'
- 10:38 AM Revision a56c1ca3 (ceph): Merge branch 'wip-client-leaks' into next
- 10:35 AM Revision 6c0be020 (ceph): client: simplify/fix symlink loop check
- Checking that we visit a symlink isn't correct; for example, the below is
valid, and we visit /b twice.
/a/b -> c
... - 10:14 AM Revision d037ff4c (ceph): client: fix path_walk for directory symlinks
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:42 AM Revision cd144534 (ceph): OSDMonitor: remove max_devices and max_osd interdependency
- Higher max_osd than max_devices doesn't hurt anything (and is the
normal way to add more osds). Higher max_devices th... - 09:38 AM Revision ae1f46c3 (ceph): mds: re-try_set_loner() after doing evals in eval(CInode*, int mask)
- Consider a case where current loner is A and wanted loner is B.
At the top of the function we try to set the loner, b... - 03:35 AM Revision 4b94e83f (ceph): Merge branch 'next'
- Pull in types.h fix
- 03:26 AM Revision 07b4f8fa (ceph): si_t was not properly converting values < 100KB
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:39 AM CephFS Bug #3470 (Resolved): ceph-fuse: hang when Fr cap revoked
- fixed by commit:ad4bd4e23e1c3e1d8156e57c83c26e66d475cdd7
- 02:34 AM Revision 8f49de0f (ceph): osdc/ObjectCacher: only call flush callback if we transitions to clean
- If we race with e.g. truncate and are in bh_write_commit but the oset
is already clean, we should not call the flush ... - 01:55 AM Revision 0cfe6320 (ceph): cleaned up scripts
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:03 AM Revision b305fc87 (ceph): osdc/ObjectCacher: fix leak on readahead
- If we initiate io (success == false) but have no waiter, we need to
delete the OSDRead.
This affects libcephfs/ceph-... - 12:03 AM Revision a8053c10 (ceph): ceph-fuse: fix leak of args
- Also fix up the helper we use to have fewer sharp edges.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:03 AM Revision 54f6c17a (ceph): client: ensure we don't leak MClientReply
- We are careful to clear this reference when processing it.
Add an assert here. There's no way we can get 2 quick re...
11/09/2012
- 09:28 PM Revision 1c9ec26e (ceph): ceph.spec.in: Build debuginfo subpackage.
- This is a partial fix for bug 3471. Enable building of debuginfo package.
Some distributions enable this automatical... - 08:17 PM Revision 34ebda2b (ceph): rbd: check for second argument to mv/rename
- Without this check, 'rbd mv foo' crashed trying to use a NULL char* as
a string.
Reported-by: Andrey Korolyov <andre... - 08:17 PM Revision de2cd18c (ceph): test: add cli test for missing args to rbd
- This includes 'rbd mv foo', which used to crash
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:11 PM Revision 9aae0eea (ceph): rbd: check for second argument to mv/rename
- Without this check, 'rbd mv foo' crashed trying to use a NULL char* as
a string.
Reported-by: Andrey Korolyov <andre... - 07:52 PM Revision f1e67d5c (ceph): Merge branch 'wip-java-test'
- 07:43 PM Revision 5ef16edb (ceph): test.sh: Adding LD_LIBRARY_PATH so JUnit can find .so files.
- Removing useless java.library.path references.
Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Noah Watkins ... - 07:34 PM Revision 9e9feffa (ceph): doc/cluster-ops/pools.rst: Added documentation for min_size
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:52 PM Revision f309c33d (ceph): Clean up string interpolation operator spacing ceph_manager.py
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:52 PM Revision f82d4a7b (ceph): Add divergent_priors test
- Tests scenario where merge_old_entry encounters a divergent
entry where the prior_version is prior to log_tail. This... - 06:12 PM Revision b5ce4d0e (ceph): client: fix SnapRealm leak
- Start ref count at 0; get_snap_realm() will increment it after alloc.
Fix the ref drop order so that the xlist is em... - 06:09 PM Revision 56a152b1 (ceph): client: debug SnapRealm reference counting
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:08 PM Revision a34a9af0 (ceph): vstart: allow minimum pool size of one
- A minimum pool size of 2 was introduced by 13486857cf. This sets the
minimum to one so that basic vstart environments... - 06:02 PM Revision 88cdde37 (ceph): client: fix leak of Cap
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:01 PM Revision 5e564f9b (ceph): client: fix leak of session release msg on session close
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:59 PM Revision c352edd3 (ceph): client: only start invalidator thread if cb != NULL
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:52 PM Revision 44a70178 (ceph): ceph-fuse: deallocate messenger, g_ceph_context on stop
- This lets us use valgrind to find leaks.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:36 PM Revision fe6e4265 (ceph): doc: add-or-rm-mons.rst: fix a formatting typo
- (also forgot the John's reviewed-by on the last commit)
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Rev... - 05:12 PM Revision 5b32664a (ceph): doc: add-or-rm-mons.rst: make paths clearer
- Some users have been incurring into problems adding new monitors while
following these steps. Some of these problems ... - 03:38 PM Revision 128fed8e (ceph): client: assert cap refs don't go negative
- This is the root cause of #3470.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:38 PM Revision ad4bd4e2 (ceph): client: do not gratuitously drop FILE_CACHE ref in _read()
- The get_caps() had a confusing out-arg called "got" that is really what
caps we *have*; it only takes a ref on the *n... - 03:38 PM Revision 66e6a636 (ceph): client: give get_caps() out-arg a less confusing name
- No functional change.
Call this arg "have" and not "got", since we only take a ref on what we
need.
Signed-off-by: ... - 02:53 PM Revision 8c115d3e (ceph): mds: re-try_set_loner() after doing evals in eval(CInode*, int mask)
- Consider a case where current loner is A and wanted loner is B.
At the top of the function we try to set the loner, b... - 02:38 PM Bug #3471: rpm: build src, debuginfo packages
- The tools needed to build the debug info package are installed with rpm-build package. The redhat-rpm-config package...
- 05:47 AM Bug #3471 (Resolved): rpm: build src, debuginfo packages
- we need to build debuginfo packages so that users can get debug symbols for debugging issues. it's something like
... - 01:33 PM Revision 1a23bd69 (ceph): CompatSet: users pass bit indices rather than masks
- CompatSet users number the Feature objects rather than
providing masks. Thus, we should do
mask |= (1 << f.id) rath... - 08:58 AM rbd Feature #3472: make it possible to get the watchers out of an object
- This requires #3403, which redmine apparently can't relate, since it's in a different project.
- 07:01 AM rbd Feature #3472 (Resolved): make it possible to get the watchers out of an object
- People would love to be able to look at who has an rbd volume mounted. Including some customers. :)
- 04:36 AM CephFS Bug #3470 (Resolved): ceph-fuse: hang when Fr cap revoked
- the fuse client (0.53-309-gca89880) gets a revoke on Fr, but doesn't respond. processes using the fuse mount hang.
... - 03:28 AM Revision e9043385 (ceph): Merge branch 'next'
- 01:25 AM Revision dc907e28 (ceph): librbd: take parent lock when examining fields it protects
- This hasn't actually caused any problems, I just noticed
while looking through the code.
Signed-off-by: Josh Durgin ... - 01:24 AM Revision 1ba969b1 (ceph): Merge remote-tracking branch 'origin/wip-swift-token' into wip-rgw-inte...
- 01:22 AM Revision a183fe74 (ceph): OSDMap.cc: Add pool name to OSDMap dump
- Otherwise, we can't use ceph osd dump --format=json to map pool name
onto pool id.
Signed-off-by: Samuel Just <sam.j... - 01:19 AM Revision 2475d014 (ceph): Merge branch 'wip-keystone' into wip-rgw-integration
- Conflicts:
debian/control
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:17 AM Revision e5124ced (ceph): Merge branch 'wip-post-cleaned' into wip-rgw-integration
- Conflicts:
src/rgw/rgw_common.cc
src/rgw/rgw_op.cc
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:15 AM rbd Feature #3456: make exit code of ceph status commands status dependent
- Ah ok, I see. I don't know if it would be a good idea to have different exit codes for different failures/ status. I'...
- 01:14 AM Revision faf23caa (ceph): rbd: fix snap unprotect, which was succeeding while clones existed
- 1) use right snap id when forming parent spec to search for children
2) add test case for "unprotect with extant chil... - 01:07 AM Revision b2d4c491 (ceph): Merge branch 'wip-3453' into wip-rgw-integration
- 01:07 AM Revision f89efc9f (ceph): Merge branch 'wip-3452' into wip-rgw-integration
- 01:03 AM Revision b4a2fe46 (ceph): Merge branch 'wip-stripe'
- Conflicts:
src/common/config_opts.h
src/rgw/rgw_op.cc
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 12:57 AM Revision 77b42375 (ceph): librbd: no need to scan snapshots for parents during remove
- At this point we already know no snapshots exist.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 12:06 AM Revision c45a415c (ceph): script clean up
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
11/08/2012
- 11:53 PM Revision 9ea95a0e (ceph): Added a function get_cmd_op
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:24 PM Revision a99b0fac (ceph): rgw: fix build
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:24 PM Revision 5fda39e6 (ceph): rgw: change configurable
- rgw keystone accepted roles
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:24 PM Revision fc0d6d34 (ceph): docs: add keystone documentation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:24 PM Revision 1f05b1af (ceph): rgw: keep pki tokens by hash
- and also fix the token parsing (needed after the json
parser fix).
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:24 PM Revision 02c2c32d (ceph): rgw: invalidate revoked tokens
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:24 PM Revision feb24afb (ceph): rgw: decode pki tokens
- If we can decode pki tokens then we don't need to send them to
the Keystone server for verification.
Signed-off-by: ... - 09:24 PM Revision b69da4b8 (ceph): json_spirit: thread safe
- apparently the library is not thread safe by default.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:24 PM Revision ff8c2380 (ceph): rgw: keystone tokens revocation thread
- Use a thread to invalidate revoked tokens.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:24 PM Revision 8fcd3518 (ceph): rgw: use a different boost thread library
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:24 PM Revision 8249d7b3 (ceph): rgw: decode revocation message
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:13 PM Revision 0d164dac (ceph): rgw: use thread safe version of gmtime
- Use gmtime_r instead of gmtime.
Signed-off-by: Sylvain Munaut <s.munaut@whatever-company.com> - 08:43 PM Revision ff5ee98f (ceph): build: Add RPM release string generated from git describe.
- Fix for bug 3451. Use the commit count and sha1 from git describe to
construct a release string for rpm packages. - 07:59 PM Revision 8db7d2c4 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 07:59 PM Revision 82ebbaba (ceph): doc: Clarified text to reflect requirement for majority, not odd number...
- fixes: 3464
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 07:45 PM Revision 8daecaf9 (ceph): Merge remote-tracking branch 'gh/wip-fix-symlinks'
- Conflicts:
qa/qa_scripts/load-bucket-1000-obj.pl
src/test/libcephfs/test.cc - 07:40 PM Revision 9dcc8a3b (ceph): Merge remote-tracking branch 'gh/wip-mds'
- 07:14 PM Bug #3463 (Rejected): Crash when adding monitor
- 11:45 AM Bug #3463: Crash when adding monitor
- It turns out that the issue was the documentation leading me to believe that I had to populate the kerying and monmap...
- 10:35 AM Bug #3463: Crash when adding monitor
- Backtrace:
Core was generated by `/usr/bin/ceph-mon -i d --pid-file /var/run/ceph/mon.d.pid -c /etc/ceph/ceph.con'... - 10:27 AM Bug #3463 (Rejected): Crash when adding monitor
- I have three monitors now and wanted to add two more for extra reliability. I followed the instructions here http://c...
- 06:31 PM devops Bug #3469 (Won't Fix): ceph-deploy needs to sync with the ceph version it is working with
- I did a git clone of the current ceph-deploy that happened to be the following:
commit 1d125d616559ab1c52a0aeb8f9156... - 05:42 PM Revision 83ab3665 (ceph): ceph.spec.in: Remove ceph version requirement from ceph-fuse package.
- The ceph-fuse rpm package now only requires ceph as a pre-req, not a specific
version. - 05:39 PM Revision a39110db (ceph): ceph.spec.in: Remove ceph version requirement from ceph-fuse package.
- The ceph-fuse rpm package now only requires ceph as a pre-req, not a specific
version. - 05:31 PM Revision e37c1928 (ceph): rgw_admin: do not throw error when start-date and end-date are not
- passed to usage::trim()
Signed-off-by: caleb miles <caleb.miles@inktank.com> - 05:28 PM Revision b7da8bbe (ceph): libcephfs_jni.cc: mtime and atime are Long data types. Changing the acc...
- reflect this fact
Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Noah Watkins <noahwatkins@gmail.com> - 05:28 PM Revision 4f215b0c (ceph): Makefile: remove redundant EXTRA_DIST
- Already set at the beginning of the Makefile.am
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 05:28 PM Revision 74cc2992 (ceph): Makefile: use real file for make target
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:28 PM Revision 55483d78 (ceph): Makefile: only add source files to EXTRA_DIST
- Prevents a make dist on a built tree from including the compiled
bytecode files produced from compiling the Java test... - 05:28 PM Revision 2dfc1030 (ceph): Makefile: include Java unit test runner
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:28 PM Revision a47a9661 (ceph): Makefile: include Java test suite artifacts
- Automake has problems handling the naming convention used by Java for
inner classes (x$y.class).
Signed-off-by: Noah... - 05:28 PM Revision 1581db9b (ceph): configure: fail when missing junit dependency
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:28 PM Revision c3129a27 (ceph): Changing build.xml to produce a jar instead of class files Adding a
- TestSuite class to run all tests
Remove the libcephfs-test.jar when running ant clean
Signed-off-by: Joe Buck <jbbuc... - 05:28 PM Revision 77015424 (ceph): Adding libcephfs-java.jar to .gitignore
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Noah Watkins <noahwatkins@gmail.com> - 05:27 PM Revision 791a8224 (ceph): Adding a simple workunit that executes one libcephfs-java test
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Noah Watkins <noahwatkins@gmail.com> - 05:27 PM Revision 5dec9172 (ceph): Moving test java files into a proper heirarchy. Moving the compilation
- of tests classes from build.xml to Makefile and editing configure.ac to
look for the junit4 jar in the default locati... - 05:22 PM Bug #3468 (Resolved): rbd snap unprotect succeeds with children
- rbd snap unprotect should fail if children of the snap exist. The check
was using the wrong snap_id - 03:53 PM Revision 08ee7364 (ceph): java: fix return type on JNI function
- Return value of declaration was is a JNI specific jlong type, while a
the return type of the definition was long. g++... - 03:09 PM Revision ea02fb74 (ceph): workunit: Add option to use specified subdir
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:09 PM Revision f0080b02 (ceph): workunit: Allow scratch dir to already exist
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:09 PM Revision 96458387 (ceph): workunit: Move cleanup to separate run
- Removing the scratchdir in the remote run command
at the end of the script invocation will do the remove
once the fir... - 02:56 PM Revision 8ccccbbf (ceph): osdmap: make flag names match
- It's 'ceph osd set noup', so make the flag name 'noup', to avoid any
confusion.
Signed-off-by: Sage Weil <sage@inkta... - 02:56 PM Revision b1b9f0a4 (ceph): vstart.sh: allow shorter MON, OSD, MDS count env vars
- This will save me some typing.
Signed-off-by: Sage Weil <sage@inktank.com> - 02:56 PM Revision f2bf7aa7 (ceph): mon: make osdmap flags incur a health warning
- This will ensure that users will see a health warning when, for instance,
NOUP or PAUSE[RD|WR|EXEC] flags are set.
S... - 01:49 PM Bug #3467 (Closed): osd: bad state machine event in start_recoverY_ops
- ...
- 01:26 PM RADOS Documentation #3466 (Closed): rados manpage: bench still documents "read" rather than "seq/rand"
- rados bench read has been replaced with "seq" and "rand", the latter of which is
still unimplemented, and since "ben... - 12:01 PM Documentation #3464 (Resolved): doc: requirements for monitors to form a quorum are wrong
- I've rephrased the text in this document to reflect the requirement for a majority, rather than an odd number of moni...
- 10:58 AM Documentation #3464 (Resolved): doc: requirements for monitors to form a quorum are wrong
- http://ceph.com/docs/master/cluster-ops/add-or-rm-mons/ says this a few ways:...
- 11:30 AM Bug #3465: Unclear error message when running 'ceph osd rm'
- arch, i thought i fixed all of these. joao, there is a helper in OSDMonitor that parses a raw # or osd.#; can you ma...
- 11:12 AM Bug #3465 (Resolved): Unclear error message when running 'ceph osd rm'
- I am new to the ceph project and was using man pages to execute commands. I misunderstood the command, and rather th...
- 11:26 AM Documentation #3438 (In Progress): Adding/Removing Monitor documentation may be wrong
- 11:25 AM Documentation #3438: Adding/Removing Monitor documentation may be wrong
- Have yet to try it with argonaut, but with the latest master (0.53-716-gb7da8bb (b7da8bbe7f7d5bbd8fb9ee59f491f6e3a481...
- 10:29 AM Bug #3451: qa: rpm autobuilt packages should get 'git describe' version
- RPM provides a version and a release field. Currently the version is generated by configure and the release field is...
- 09:51 AM rgw Bug #3452: rgw: Handling of dates in If-UnModified-Since / Last-Modified seems to have issues wit...
- Yeah, definitely need to apply that patch.
- 02:52 AM rgw Bug #3452: rgw: Handling of dates in If-UnModified-Since / Last-Modified seems to have issues wit...
- I can confirm that commit:50d3598b fixes it for me.
I would still apply the patch attached to this issue to the tr... - 08:19 AM rgw Bug #3450: WRITE permission only doesn't allow proper multi-part upload
- As discussed on IRC, this is only the case for subusers with only WRITE permission.
Now looking at the current git... - 07:33 AM CephFS Feature #3462 (New): client: Add null-io debug options to client for testing
- When testing metadata behavior and performance (interaction between mds and client), in most cases we don't care abou...
- 07:11 AM rbd Feature #3456: make exit code of ceph status commands status dependent
- This is intentional: we want to return success in that we are able to successfully report the health (vs not being ab...
- 06:42 AM Revision 93734521 (ceph): doc: Rewrote index for install section per new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:42 AM Revision f2fbe7a7 (ceph): doc: Removed source/index from top-level toc tree per new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:41 AM Revision 6f6df5c2 (ceph): doc: Moved doc/source files to doc/install per new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:19 AM Revision 059294ce (ceph): doc: Syntax cleanup for new IA. Fix tip. Clean up for generating keys.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:18 AM Revision 631075d8 (ceph): doc: Syntax cleanup for new IA. Added reference to repo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:17 AM Revision 7a1e952b (ceph): doc: Syntax cleanup for new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:17 AM Revision e11cafb5 (ceph): doc: Syntax cleanup for new IA. Removed steps for building docs.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:16 AM Revision b5ae387e (ceph): doc: Syntax cleanup for new IA. Removed info for building documentation.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:16 AM Revision 9eb0b2b9 (ceph): doc: Syntax cleanup for new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 02:53 AM rgw Bug #3453: rgw: Resume download fails because of mismatched ETags that should match
- Tested with commit:97c19da45eedb00db4d4cd684824c3adca1fe6bb and it now works nicely.
- 01:24 AM Revision 14730d77 (ceph): Merge remote-tracking branch 'upstream/wip_recovery_reserve'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 01:21 AM Revision cdd73bba (ceph): doc/: document recovery reservation process
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 01:21 AM Revision 0ed0d2a6 (ceph): pg: recovery reservations
- This extends the backfill reservation system to work with log-based
recovery. The Active and RepActive states of the ... - 01:18 AM Revision e144582f (ceph): doc: update the rest of the table for debian wheezy
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 01:17 AM Revision 9d9a222e (ceph): doc: Wheezy is now using kernel 3.2.0; say so
- 01:17 AM Revision e7c02b3a (ceph): doc: Fix per-daemon public/private settings: "network" -> "addr"
- 01:16 AM Revision eac614a7 (ceph): doc: Clarify "pool size", copies, and replicas more
- 01:07 AM Revision 52bada57 (ceph): doc: fix Hadoop config option typo
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
11/07/2012
- 11:42 PM Revision 97c19da4 (ceph): rgw: unquote etag for if-match
- Fixes: #3453
Passed ETag for copy/get request may be quoted.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:11 PM Revision d3553a58 (ceph): doc: Made changes to the CSS to make admonitions more prominent.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:11 PM Revision 067953f9 (ceph): doc: Added lines between title and body. Pre IA cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:10 PM Revision 282ac92a (ceph): doc: Updated syntax for consistent usage prior to IA updates.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:09 PM Revision d1404c34 (ceph): doc: Updated index for removal of legacy openstack install.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:09 PM Revision 9127ebd4 (ceph): doc: Minor edit to admonitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:09 PM Revision 04f661fe (ceph): doc: Updated syntax prior to IA updates.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:08 PM Revision d38df17e (ceph): doc: Updated syntax usage prior to IA updates.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:07 PM Revision ee07b224 (ceph): doc: Added new info per Ross's request.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:07 PM Revision a1b2f584 (ceph): doc: Fix and minor edit for admonitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:07 PM Revision e1195fdf (ceph): doc: Minor edits for admonitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:06 PM Revision 6731b55e (ceph): doc: Edits from Peter Reiher's feedback, and minor edits for admonitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:06 PM Revision 2260e152 (ceph): doc: Minor edits for admonitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:05 PM Revision 07f60d45 (ceph): doc: Added topic for adding OSDs and adjusting CRUSH weights.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:03 PM Revision 764ec365 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 10:02 PM Revision 0a939d04 (ceph): doc: Removed legacy OpenStack installation.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:01 PM Revision 5ef58d3e (ceph): doc: Added topic for adding an OSD and adjusting CRUSH weights.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:21 PM Revision 50d3598b (ceph): rgw: don't convert object mtime to UTC
- Fixes: #3452
When we read object info, don't try to convert mtime to
UTC, it's already in UTC.
Signed-off-by: Yehuda... - 08:56 PM Revision bd83ed70 (ceph): ceph_manager: add test_min_size action
- Thrasher can now with configurable frequency test min_size by
taking down all but one osd, waiting, killing that osd ... - 08:41 PM Revision c357474d (ceph): ceph.spec.in: Remove ceph version requirement from ceph-fuse package.
- The ceph-fuse rpm package now only requires ceph as a pre-req, not a specific
version. - 07:49 PM Revision cca606f4 (ceph): Update log file when rgw is not running
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 07:37 PM Revision 13486857 (ceph): osd/: add pool min_size parameter for min acting set size
- Otherwise, a pg might go active with a single osd in the
acting set. If that osd subsequently dies, we potentially
l... - 07:35 PM Revision 3faefdd2 (ceph): Merge remote-tracking branch 'upstream/wip_lost_unfound_event'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:41 PM Revision 60a9816d (ceph): qa: Script to run fio and template file
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 05:52 PM Revision 3b26a4d9 (ceph): Merge remote-tracking branch 'upstream/wip-xattr'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:52 PM Documentation #3432: move explanation for rbd on libvirt to new docs
- The issue Dan's talking about only matters if you're not using cephx for clients.
- 05:46 PM Documentation #3432: move explanation for rbd on libvirt to new docs
- Also: it has come to light that with the new Ceph behavior of defaulting to
cephx enabled, one must either
1) us... - 05:16 PM Bug #3460 (Resolved): ceph monitor crashed in the nightlies
- Log: ubuntu@teuthology:/a/teuthology-2012-11-06_02:00:02-regression-testing-master-basic/10579...
- 04:44 PM Bug #3459 (Resolved): osd crash in CephXAuthorizer::verify_reply
- Log: ubuntu@teuthology:/a/teuthology-2012-11-05_19:00:02-regression-master-testing-gcov/10108
2012-11-06 21:13:39.... - 04:13 PM Bug #3431: ceph fuse crashed during fsx test
- recent log: ubuntu@teuthology:/a/teuthology-2012-11-05_19:00:02-regression-master-testing-gcov/10001
- 03:21 PM rgw Bug #3400 (In Progress): rgw: multipart upload overwrite broken
- 12:46 PM Revision 456c90b0 (ceph): Makefile: add missing rgw_resolve.h to dist tarball
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:42 PM Revision ca898802 (ceph): client: kick waiters for an mds session to open on mds recovery
- We already kicked waiters for request, but we need to kick waiters on open
too (e.g., a client trying to mount).
Sig... - 12:15 PM Revision f0927cbb (ceph): qa: disable xfstest 45 until mount issue is resolved on precise
- Meh
Signed-off-by: Sage Weil <sage@inktank.com> - 12:14 PM Revision 02527d40 (ceph): qa: disable xfstest 45 until mount issue is resolved on precise
- Meh
Signed-off-by: Sage Weil <sage@inktank.com> - 12:01 PM Bug #3458 (Can't reproduce): aio enabled but not used
- I enabled aio in my config (see http://pastie.org/5342155) but when starting the osds I still see "aio = 0" in the lo...
- 11:37 AM rbd Feature #3456 (Closed): make exit code of ceph status commands status dependent
- When running for example "ceph health" it always returns an exit code of 0, no matter if the cluster is healthy or no...
- 10:58 AM rgw Feature #3454 (Resolved): Support temp URLs for Swift API
- See http://docs.rackspace.com/files/api/v1/cf-devguide/content/TempURL-d1a4450.html
Since the configuration of aut... - 08:53 AM rgw Bug #3453 (Resolved): rgw: Resume download fails because of mismatched ETags that should match
- Trying to resume a download with firefox.
During the initial download I get
@ETag: "a91313a06a1df0ee6b86abf7a8b8a... - 08:48 AM rgw Bug #3452 (Resolved): rgw: Handling of dates in If-UnModified-Since / Last-Modified seems to have...
- So:
- I query an object and I get a header back saying "Last-Modified: Fri, 31 Aug 2012 11:12:49 GMT"
- I reissue... - 04:59 AM Bug #3451 (Resolved): qa: rpm autobuilt packages should get 'git describe' version
- The autobuilt rpm packages currently get the version from the previous release (e.g., '0.53') instead of the git desc...
- 04:24 AM rgw Bug #3450 (Won't Fix): WRITE permission only doesn't allow proper multi-part upload
- In our setup we have a user who only has write permission on a bucket and we wanted to use multi-part uploads.
The p... - 04:20 AM rbd Bug #3449 (Closed): fix xfstest 45 on precise
- need new quota package to fix test 45 issue
- 03:26 AM rbd Feature #3100 (Resolved): rbd-fuse prototype
- 03:25 AM rbd Feature #3416 (Resolved): krbd: open parent on open
- 03:25 AM rbd Feature #3414 (Resolved): librbd: clean up file locations in source tree (esp cls_rbd)
11/06/2012
- 11:52 PM Revision 0c989794 (ceph): Merge branch 'next'
- 11:51 PM Revision 0baa9275 (ceph): cls_rbd: send proper format of key to "last_read" for dir_list
- rbd ls of format-2 images was looping on the first 64 (when more than 64
were present). The key name passed to the o... - 11:49 PM Revision fe9a4410 (ceph): rgw: document cname configurable
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:20 PM Revision c89d85c7 (ceph): Merge remote-tracking branch 'origin/master' into wip-3206
- 11:19 PM Revision 951c6be4 (ceph): rgw: resolve hostname dns cname record
- Implements #3206
This allows using vanity domains. A CNAME record can now
be set for the domain that would point at t... - 09:50 PM Revision 6aa9cff2 (ceph): java: use accessors for mode flag tests
- Add isDir(), isFile(), and isSymlink() for read-only tests corresponding
to the S_ISREG test and friends.
Signed-off... - 06:19 PM Revision 578b5764 (ceph): rgw: fix multipart overwrite
- Fixes: #3400
Removed a few lines of code that prematurely created the head
part of the final object (before creating ... - 06:17 PM Revision 84299e16 (ceph): rgw: fix multipart overwrite
- Fixes: #3400
Removed a few lines of code that prematurely created the head
part of the final object (before creating ... - 06:16 PM Revision be6d5636 (ceph): rgw: don't reset multipart parts when updating their metadata
- Fixes: #3401
The problem was that put_obj_meta() was assuming object is going
to be reset, so it was resetting the ob... - 06:16 PM Revision 488b019a (ceph): rgw: break out of read loop if we got zero bytes
- If the part that we're reading is corrupted and we end up
reading zero bytes, we need to exit, otherwise we'd just
lo... - 05:14 PM Revision 9a1ee028 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 05:13 PM Revision 138262f6 (ceph): doc: fixed some inccorrect syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:56 PM rgw Feature #3206 (Resolved): rgw: resolve vanity CNAMEs
- Done with commit:fe9a441037f221ba09b01c3967f69b3626c99116.
- 03:16 PM CephFS Cleanup #3421 (Closed): Refactor Java tests to use older version of JUnit so that we can use 12.0...
- It turns out that the current shipping version of Junit4 on Ubuntu and Debian will support our tests, as is. No code ...
- 01:58 PM Feature #3448 (New): Minimize recovery time of a degraded cluster
- To minimize the recovery time of the cluster in the event of an OSD failure it would be better to recover to the rema...
- 12:58 PM Bug #3431: ceph fuse crashed during fsx test
- recent logs: ubuntu@teuthology:/a/teuthology-2012-11-04_19:00:03-regression-master-testing-gcov/9298
- 12:01 PM RADOS Documentation #3447 (Closed): doc: how to recover from a failed journal device
- See http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/6377
- 11:11 AM rgw Bug #3401: rgw: multipart upload broken
- Fix corresponds to commit
be6d5636534ffa6e9badca7ddb7d73ad01663f48 (next) - 10:30 AM rgw Bug #3401 (Resolved): rgw: multipart upload broken
- 10:30 AM rgw Bug #3401: rgw: multipart upload broken
- also affects next
- 10:34 AM rgw Bug #3400: rgw: multipart upload overwrite broken
- Fix corresponds to commits:
578b5764d5b26d190c295da88c1be5f0c77682a7 (stable)
84299e16f3b7b74cff814eb9a754b7... - 10:31 AM rgw Bug #3400 (Resolved): rgw: multipart upload overwrite broken
- 10:31 AM rgw Bug #3400: rgw: multipart upload overwrite broken
- also affects stable, next
- 07:27 AM Revision 2a696274 (ceph): mds: move to from loner -> mix if *anyone* wants rd|wr
- We were either going to MIX or SYNC depending on whether non-loners wanted
to read/write, but it may be that the lone... - 07:26 AM Revision 4b3f97d8 (ceph): mds: base loner decision on wanted RD|WR|EXCL, not CACHE|BUFFER
- Observed instance where one client wanted the Fc cap and prevented the
loner from getting RD|WR caps.
Signed-off-by:... - 07:23 AM Revision 307fd243 (ceph): librbd: fix memory leak on read
- We were leaking the rados completion, which includes a reference to actual
data.
Fixes: #3445
Signed-off-by: Sage We... - 07:06 AM Revision b940d775 (ceph): mds: base loner decision on wanted RD|WR|EXCL, not CACHE|BUFFER
- Observed instance where one client wanted the Fc cap and prevented the
loner from getting RD|WR caps.
Signed-off-by:... - 07:06 AM Revision 96888ddf (ceph): mds: move to from loner -> mix if *anyone* wants rd|wr
- We were either going to MIX or SYNC depending on whether non-loners wanted
to read/write, but it may be that the lone... - 05:41 AM Revision 241569c5 (ceph): rbd: allow removal of image even if rbd_children deletion fails
- Users have been seeing failures where rbd rm is half-done; could be
because of outstanding watches on the rbd_header ... - 04:15 AM Revision 4b4e0fa6 (ceph): rbd: allow removal of image even if rbd_children deletion fails
- Users have been seeing failures where rbd rm is half-done; could be
because of outstanding watches on the rbd_header ... - 01:53 AM Revision 3162f136 (ceph): rgw: configurable swift token ttl
- Bump up ttl to 24h, and make it configurable.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
11/05/2012
- 11:19 PM Revision 60e54d67 (ceph): client: Fix path_walk() to support dir symlinks
- Additions to Sage's commits that replace the path walked so
far with the symlinked directory path, rather than the re... - 11:19 PM Revision 0f7dadac (ceph): client: Add symlink loop checking in path_walk()
- If a loop exists in directories due to a symlink: /a/b/c -> /a
We now return -ELOOP from path_walk() instead of loopi... - 11:19 PM Revision beaafe85 (ceph): test: Add tests for symlink pathological cases
- The DirSyms test checks verifies that the new path_walk()
handling code properly walks through symlinked directories
... - 07:02 PM Revision 15b3d98f (ceph): doc: Minor edits and added reference to Cephx intro.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:02 PM Revision 85cd6948 (ceph): osd/: encode LOST_REVERT reverting_to in prior_version pos
- This will allow older osds to interpret the LOST_REVERT event
correctly.
Signed-off-by: Samuel Just <sam.just@inktan... - 06:48 PM Revision bad01145 (ceph): PG: use remove_object_with_snap_hardlinks for divergent objects
- Otherwise, we end up leaving snap hardlinks in the snapshot
index directories. This eventually results in an EEXIST ... - 06:43 PM rbd Bug #3446 (Resolved): Objecter: leaks ObjectOperation::C_ObjectOperation_stat
- I'm guessing this is just leaked from the error path. Found via valgrind in test_librbd_fsx:...
- 06:39 PM rbd Bug #3445 (Resolved): ObjectCacher: extra memory leaks with caching enabled in wip-rbd-read
- It looks like we're leaking some rados completions and some buffers (from the cache?). Attached are two valgrind repo...
- 05:57 PM Revision 699e54df (ceph): rbd: stripe count is not measured in bytes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:23 PM Bug #3444 (Duplicate): Qemu librbd aio
- Commandline:
kvm -drive file=rbd:rbd/vm7:rbd_cache=true:conf=/etc/ceph/ceph.conf,format=raw,id=drive1,if=none -devic... - 10:46 AM rgw Feature #3443 (New): radosgw - Add Log messages to indicate restart, attempt, success and failure
- when radosgw is started/restarted there is currently no message written to /var/log/ceph/radosgw.log if it is success...
- 10:13 AM rgw Feature #3442 (Resolved): rgw: support Keystone tokens revocation
- 10:11 AM rgw Feature #3343 (Fix Under Review): rgw: stripe objects
- 10:11 AM rgw Feature #3441 (Resolved): rgw: integrate with Keystone
- 10:11 AM rgw Cleanup #1716 (Closed): rgw: remove curl use
- Closing this, curl use is needed for Keystone support.
- 08:43 AM rbd Bug #2528 (Resolved): Mounted RBD image appears to go read-only after a snapshot is created
- 06:41 AM rbd Bug #2528: Mounted RBD image appears to go read-only after a snapshot is created
- I just tried to reproduce this problem, but could not.
Josh said he thought it was a problem that had been fixed
... - 08:14 AM Revision 0db11c79 (ceph): chain_xattr: use sys_* methods
- The sys_* wrappers return -errno on error; use those!
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision be438dc8 (ceph): os/chain_xattr: do not double memory buffer (again)
- This appears to be a typo; there is no need to double (again) the size of
the buffer we allocate.
Signed-off-by: Sag... - 08:13 AM Revision 2bf6a2bf (ceph): os/chain_xattr: whitespace, constify *end
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 9cf0be71 (ceph): chain_xattr: comment about how xattrs are named
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:13 AM Revision 8c3481d9 (ceph): os/FileStore: chain_*() methods return error codes; don't check errno
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 1862ddd8 (ceph): os/FileStore: use _fgetattrs() from collection_getattr()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 307fd429 (ceph): os/FileStore: remove unused _getattrs() methods
- We are now using the _fgetattrs() variant everywhere instead.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision b6bfeed9 (ceph): os/FileStore: use _fgetattr() from getattr()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision d59cf332 (ceph): os/FileStore: use new helpers from collection_{get,set,rm}attr[s]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 41bc77f5 (ceph): os/FileStore: drop _getattr() helpers
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 6a6699bd (ceph): os/FileStore: recast _setattrs() on top of chain_f* methods
- This lets us open an fd once and use that.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision 044be916 (ceph): os/FileStore: recast _rmattr on top of chain_f*
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 51d3faaf (ceph): os/FileStore: remove lfn_*xattr helpers
- No longer used!
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision 54966006 (ceph): os/FileStore: introduce lfn_close()
- Match every lfn_open() with lfn_close() (instead of close(2)).
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision b7f89cb7 (ceph): os/chain_xattr: fix listxattr buffer size
- Intenrally allocate 2x the raw listxattr result; tell the user the same.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision 4e553035 (ceph): os/chain_xattr: move chained xattr helpers into separate file/module
- * Rename do_* -> chain_*.
* Move #defines to a header.
* Fix *Index users
* Implement both *xattr() and f*xattr() var... - 08:13 AM Revision bb127bd1 (ceph): os/FileStore: use f*xattr() methods to test xattr support
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision 68377f9c (ceph): os/FileStore: add _fgetattr(), _fgetattrs() helpers
- Introduce new fd-based getattr[s] helpers.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision 769f4732 (ceph): os/FileStore: use _fgetattrs() for GETATTRS op
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:13 AM Revision ad5ac17f (ceph): os/FileStore: use _fgetattrs() for CLONE
- We have the src fd.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:13 AM Revision cab1d635 (ceph): os/FileStore: use _fgetattrs() for _setattrs()
- If we're using omap for spillover, we need to load the xattrs so that
they can be removed if necessary.
Note that we... - 08:13 AM Revision a367e6e9 (ceph): os/FileStore: use _fgetattrs() from _rmattrs()
- Note that we subtly change failure handling to be more strict: if we
fail to open the file, we error out; before we i... - 07:54 AM Bug #3440 (Resolved): Running OSDs on ZFS on Linux
- I just gave it a try to run a small setup on ZFS on Linux (http://zfsonlinux.org/)
The OSDs boot just fine, but wh...
11/04/2012
- 10:59 PM Revision e49969a6 (ceph): test script for s3 tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 03:41 PM Revision 7731d478 (ceph): test_librbd: add additoinal clone test
- Test that reads will trigger a cow both when overlapping and not
overlapping with buffered writes.
Signed-off-by: Sa... - 03:41 PM Revision 8d8726a5 (ceph): osdc/ObjectCacher: wake all rx waiters on ENOENT
- If we discover an object doesn't exist, wake all rx waiters at the same
time. This prevents a situation like:
- rea... - 03:41 PM Revision 7e57c5fd (ceph): librbd: better debug output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:41 PM Revision 87129588 (ceph): librbd: complete Context on error from ObjectCacher::readx
- We were immediately completing for positive (successful) returns, but not
on error. Do errors too, so that we don't ... - 03:41 PM Revision e506362c (ceph): librbd/AioCompletion: ensure read result assembly happens last
- When reading from the cache, we can have a situation where each AioRead
completes as it is added to the completion, c... - 03:41 PM Revision f6d2e9a2 (ceph): osdc/Striper: more debug
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:41 PM Revision 09dc191c (ceph): osdc/WritebackHandler: add may_copy_on_write()
- Implement a new method to tell us whether a read to a particular region
could be affected by a write-triggered copy-o... - 03:41 PM Revision 890e4929 (ceph): librbd: remove parent logic from reads beneath the cache
- Make reads beneath the cache (in the WritebackHandler) read the plain
objects beneath us. Let the read-from-parent l... - 03:41 PM Revision f8e92a1c (ceph): osdc/ObjectCacher: add object exists flag
- Clear it (set to false) on ENOENT.
Reset it (to true) on discard().
Reset it (to true) on write completion.
Reset it... - 03:41 PM Revision 1a7caa46 (ceph): osdc/ObjectCacher: clear complete if may-cow and !exists
- If the object doesn't/didn't exist, and we finish a write, and the write
may have triggered a copy-on-write, clear th... - 03:41 PM Revision cde4dd03 (ceph): osdc/ObjectCacher: remove BufferHeads on ENOENT
- If we try a read and the object doesn't exist, toss out the BufferHead
(instead of keeping useless ZERO bh's around).... - 03:41 PM Revision 674d2665 (ceph): osdc/ObjectCacher: return ENOENT
- If we are given a single ObjectExtent, and the object doesn't exist,
and we don't have any dirty|tx buffers, return E... - 03:41 PM Revision 41812c20 (ceph): osdc/ObjectCacher: trigger copy-on-write before read
- If we are trying to read from an object, and it doesn't exist, but we have
dirty buffers, and a write could trigger c... - 03:14 PM Revision 72a710ac (ceph): client: return EBADF for invalid file desc
- Adds get_filehandle to Client which resolves a file descriptor or
returns NULL if the file descriptor is invalid. Lib... - 02:58 PM CephFS Bug #3439: kernel crash on use of chroot
- I would like to mention that the other kernel crash bug: http://tracker.newdream.net/issues/2445
On the mailinglist ... - 02:54 PM CephFS Bug #3439 (Can't reproduce): kernel crash on use of chroot
- When a chroot is called for a directory which was mounted with cephfs the kernel crashes.
The same happens (or at ... - 02:19 PM Revision 132fb341 (ceph): doc: describe Hadoop configuration options
- Start a document describing Ceph integration with Hadoop, and adds a
description of configuration options that the Ce... - 02:16 PM Revision 342c2c70 (ceph): PG::merge_old_entry: fix case for divergent prior_version
- Previously, we asserted that a log entry with a divergent
prior_version must be a clone. Consider the following
case... - 02:16 PM Revision 7e264678 (ceph): PG: use remove_object_with_snap_hardlinks for divergent objects
- Otherwise, we end up leaving snap hardlinks in the snapshot
index directories. This eventually results in an EEXIST ... - 02:05 PM Documentation #3438: Adding/Removing Monitor documentation may be wrong
- I may not be able to look into this before I get back home, so if anyone believes this is critical feel free to jump ...
- 07:10 AM Documentation #3438 (Resolved): Adding/Removing Monitor documentation may be wrong
- Two users now have reported that following the instructions on:
http://ceph.com/docs/master/cluster-ops/add-or-rm-... - 01:06 PM Revision 004a1fcf (ceph): Merge branch 'wip-reorg'
- 01:06 PM Revision 92604ce4 (ceph): Merge branch 'wip-msgr-ports'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 01:04 PM Revision 623553d2 (ceph): msgr: make bind port range configurable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:04 PM Revision 769bac89 (ceph): msgr: change port range from 6800-6900 -> 6800-7100
- This allows more OSDs per host.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:04 PM Revision 7483d1f9 (ceph): msg/Accepter: use derr
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:45 PM Revision 49bd8ab5 (ceph): librados: move misc tests into test/librados/ dir
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:45 PM Revision 5893dd52 (ceph): librados: test/rados-api/* -> test/librados/*
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:34 PM Revision 80880eef (ceph): client: always follow non-trailing symlinks
- If we are walking /a/b/c and a or b is a symlink, follow it. It's only
c that we don't follow when !followsym.
Sign... - 12:34 PM Revision 4fc67c52 (ceph): client: simplify path_walk() loop
- Most paths were kludging around the for loop's i++. Switch to a while
loop to avoid such tomfoolery.
Signed-off-by:... - 12:25 PM Revision 6f7a632a (ceph): client: Support for fchown
- Implement fchown in libcephfs and client,
which is needed by the samba vfs module.
Signed-off-by: Sam Lang <sam.lang... - 12:17 PM Bug #2508: osdc/ObjectCacher.cc:761: void ObjectCacher::bh_write_commit(int64_t, sobject_t, loff_...
- Sage Weil wrote:
> false alarm; this is librbd with caching enabled, so the tid's are artificially generated by Libr... - 11:54 AM Revision e4aa6d7a (ceph): cls_lock: reorg test_cls_lock
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:52 AM Revision 0eedc78e (ceph): cls_rgw: reorg test_cls_rgw
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:50 AM Revision a1402b5d (ceph): fix cls_rbd reorg
- 11:47 AM Revision ddf096b5 (ceph): librbd: reorg rbd tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:43 AM Revision b749323b (ceph): cls_rbd: move into new location
- Be consistent! Make an example of ourselves!
Signed-off-by: Sage Weil <sage@inktank.com> - 09:10 AM Revision bcefc0e8 (ceph): msg/Pipe: fix leak of AuthSessionHandler
- Init ptr in ctor, delete in dtor.
Reported-by: Yan, Zheng <yan.zheng@intel.com>
Signed-off-by: Sage Weil <sage@inkta... - 08:14 AM Cleanup #432: use STL find() and iterators instead of count()
- The semantic patch tool Coccinelle has an open issue for supporting C++. Something to keep an eye out for, and would ...
- 08:02 AM Revision 2daad206 (ceph): Merge branch 'wip-mds'
- 05:14 AM Messengers Bug #3156 (Resolved): port range is hard-coded
- commit:623553d2b8eab2104baaac3972dd8910c92edb7e
- 02:57 AM CephFS Feature #3437 (Resolved): client: expose mds session state via admin socket
- 02:57 AM CephFS Feature #3436 (Resolved): client: expose mds requests via admin socket
11/03/2012
- 11:54 PM Bug #3435 (Resolved): osdc/ObjectCacher.cc: 764: FAILED assert(ob->last_commit_tid < tid)
- Recent logs: ubuntu@teuthology: /a/teuthology-2012-09-24_19:00:29-regression-master-testing-gcov/29465...
- 11:51 PM Bug #3428 (Resolved): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- fixed in wip-rbd-read branch, commit:40a5cebe26c216443a9c19477287644c22c5a845
- 07:12 PM Revision f67e79a2 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 07:12 PM Revision 4bff87da (ceph): doc: Added qemu caching section.
- fixes: #3332
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 07:10 PM Revision f171aba7 (ceph): doc: Added Commandline Usage and a few fixes.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 02:32 PM Bug #3434 (Won't Fix): Unknown variables in test_xattr_support
- From https://github.com/ceph/obsync/blob/master/obsync#L157
When catching IOError, there are references to @pa@ an... - 02:27 PM Bug #3433 (Resolved): Error: Store.__init__() takes no parameters
- This is on Ubuntu 12.04 obsync, but also appears in git master: https://github.com/ceph/obsync/blob/master/obsync#L90...
- 12:14 PM rbd Documentation #3332 (Resolved): doc: Explain how qemu rbd caching defaults come from qemu config
- Added a section in http://ceph.com/docs/master/rbd/qemu-rbd/
- 10:00 AM Bug #2508 (Resolved): osdc/ObjectCacher.cc:761: void ObjectCacher::bh_write_commit(int64_t, sobje...
- false alarm; this is librbd with caching enabled, so the tid's are artificially generated by LibrbdWriteback, not by ...
11/02/2012
- 08:13 PM Revision f7412fe3 (ceph): crypto: add cms utility function
- Taken from a libnss tool (cmsutil), stripped code so that we
only get the decode functionality that we need.
Signed-... - 06:37 PM Documentation #3432 (Resolved): move explanation for rbd on libvirt to new docs
- http://ceph.com/wiki/QEMU-RBD needs to be documented next to all the other
stuff for rbd in ceph.com/docs, probably ... - 06:33 PM Revision 6c9d45e3 (ceph): schedule: fix var name
- 06:32 PM Revision c51e1f9b (ceph): test script for s3 tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:08 PM Revision 5f4414e0 (ceph): schedule: add option to display jobs in the queue
- beanstalkd doesn't let you list jobs in the queue, but you can
inpsect specific job ids. - 01:17 AM Revision 4cd47c4c (ceph): client: Fix state of symlink with absolute path
- Symlinks that have an absolute path are not getting
properly dereferenced in path_walk() due to a bug
with the cur an... - 01:17 AM Revision a7e13681 (ceph): test: Add symlink test for absolute paths
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
11/01/2012
- 10:56 PM Revision bc4e6b9a (ceph): doc: Changed term "kernel object" to "kernel module". Added hyperlink t...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:30 PM Revision 019fee82 (ceph): doc: Improved the landing page for RBD.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:30 PM Revision 536d7644 (ceph): doc: Clarified text and added reference back to main RBD pages. Added s...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:29 PM Revision 2b2ac137 (ceph): doc: Changed RBD to librbd cache for accuracy.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:00 PM Bug #3431 (Resolved): ceph fuse crashed during fsx test
- Logs:ubuntu@teuthology:/a/teuthology-2012-10-30_19:00:06-regression-master-testing-gcov/5947...
- 07:55 PM Revision a01b112d (ceph): doc: changed --user to --id, and fixed a typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:55 PM Revision a7551e4d (ceph): run_xfstests.sh: add optional iteration count
- This adds a "-c <count>" option to the run_xfstests.sh script so
the full set of tests can be repeated more than once... - 06:49 PM Revision f88a2f73 (ceph): rbd task: support xfstests repeat count
- This adds the ability to use the new repeat count argument to the
run_xfstests.sh script. By default, the test suite... - 05:43 PM Revision dfc57c4f (ceph): doc: minor edits to the index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:41 PM Revision 968b315a (ceph): doc: Added layering to the snapshot section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:20 PM Documentation #3322 (In Progress): doc: Explain multi-tenant CephFS
- 01:19 PM Documentation #3174 (Resolved): Cephx with RBD/Qemu/libvirt
- 09:49 AM rbd Bug #2933 (Resolved): rbd: bio_pair leak in bio_chain_clone()
- A fix for this has been committed to the ceph-client/testing
branch and has survived some days of testing.
commit... - 08:05 AM Revision 614cb509 (ceph): PG: correct sub-state names in ReplicaActive
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 08:05 AM Revision 23dbe3ec (ceph): message: add missing print statement for REJECT message
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 08:05 AM Revision d2c6d44b (ceph): message: add MRecoveryReserve
- This message will be used to reserve and release recovery slots on
replica PGs.
Signed-off-by: Mike Ryan <mike.ryan@... - 08:05 AM Revision 6c5de992 (ceph): osd: add PG state recovery_wait
- Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
- 05:10 AM Revision 15ada1c7 (ceph): doc: update notes on new rpm-based platforms
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:27 AM Revision 45005d3d (ceph): doc: fix os-recommendations table
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:25 AM Revision 2d52d7c9 (ceph): doc: Index entry for OS Recommendations
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:24 AM Revision 049e7fbe (ceph): doc: update os-recommendations
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:14 AM Revision 651cbb54 (ceph): Merge branch 'next'
- 12:14 AM Revision c435d314 (ceph): ceph-disk-activate: avoid duplicating mounts if already activated
- If the given device is already mounted at the target location, do not
mount --move it again and create a bunch of dup...
10/31/2012
- 11:21 PM Revision da9aed99 (ceph): osd/: add pg_log_entry_t::reverting_to for LOST_REVERT
- Previously, we encoded the version to which we were
reverting in the prior_version field. Now, we explicitely
encode... - 11:12 PM Revision 29a03f07 (ceph): rgw: parse keystone token expiration
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:42 PM Revision 3f08e96c (ceph): PG: requeue snap_trimmer after scrub finishes
- Previously the snap_trimmer would continuously requeue itself until the
end of scrub. This degrades performance and f... - 10:34 PM Revision 1bb65373 (ceph): PG: requeue snap_trimmer after scrub finishes
- Previously the snap_trimmer would continuously requeue itself until the
end of scrub. This degrades performance and f... - 09:49 PM Revision c62f3dd8 (ceph): rgw: cache keystone tokens
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:12 PM Revision 310796a9 (ceph): doc: tiny syntax fix.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:11 PM Revision eac443e0 (ceph): doc: Added internal anchor references.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:11 PM Revision 3c034ae1 (ceph): doc: using remote copy
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:37 PM Revision 2857a7f4 (ceph): Merge remote-tracking branch 'upstream/wip_dep_fix'
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:36 PM Revision 1351e76c (ceph): README: add libboost-program-options-dev
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:23 PM Revision f9443865 (ceph): rgw: map keystone tenant id to rgw user
- Instead of mapping the tenant name. Keep the name as the display_name.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:27 PM Revision 6bbe7db7 (ceph): configure.ac: add program_options header check
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:44 PM Bug #3429 (Resolved): osd: failed assert(oe.soid.snap != ((__u64)(-2)))
- This happened on 0.53.
Backtrace:... - 12:34 AM Revision 88f48233 (ceph): rgw: handle keystone roles
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
10/30/2012
- 11:38 PM Revision 421c352e (ceph): rgw: auto create rgw user for new keystone users
- We now also read the user info when authenticating the keystone
user.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:52 PM Revision 845e862a (ceph): rgw: handle keystone tokens
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:52 PM Revision 9df953cd (ceph): rgw: extend rgw json parser api
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:31 PM Revision fd4b839d (ceph): Merge branch 'wip_journal_perf'
- 08:31 PM Revision 542e1344 (ceph): FileStore: don't lock op_tp in queue_op
- Neither caller of queue_op can race.
1) in queue_transactions, already under submit lock
2) in _journaled_ahead, jour... - 08:31 PM Revision 2ed667ae (ceph): FileStore: add op_throttle_lock
- Avoid using op_tp lock for the op throttle.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:31 PM Revision bc91f9dd (ceph): os: instrument submit lock, apply lock, queue_lock, write_lock
- Adds Mutex perfcounter tracking to mutexes of interest.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:31 PM Revision 2646a8fe (ceph): Throttle: reduce lock hold periods
- Previously, we tended to dump a lot of log output under
the Throttle lock. The log level for most log statements
has... - 08:31 PM Revision c6c8fce4 (ceph): FileJournal: break writeq locking from queue_lock
- This prevents the relatively long process of queueing
finishers from preventing op submission.
In submit_entry, we n... - 08:31 PM Revision 1a5b6263 (ceph): FileJournal: write_cond is not used
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 8d27edae (ceph): FileJournal: rename queue_lock to finisher_lock
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 550ef509 (ceph): Finisher: add perf counter for queue len
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 9608a88b (ceph): ReplicatedPG: actually delay op for backfill_pos
- 3f952afe5da644b30015fead8e3d42a129b59989 neglected to
actually delay the op in ReplicatedPG::do_op.
Signed-off-by: S... - 08:31 PM Revision fe2814e4 (ceph): Mutex: Instrument Mutex with perfcouter for Lock() wait
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision e814d8fb (ceph): test/bench: small io benchmarker
- Precreates objects and does writes to random offsets within
random objects.
Includes rados, filestore, and vanilla f... - 08:31 PM Revision a268afa1 (ceph): test/bench: add tp bench
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision f7727dd5 (ceph): FileStore: next_finish is not used
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 5326c221 (ceph): JournalingFileStore: pass -1 as the alignment if unimportant
- Previously, data_align began at 0 and remained that way if no
transaction contained a large data segment. This 0 was... - 08:31 PM Revision c2c912b9 (ceph): FileStore: remove trigger_commit
- This is no longer used.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:31 PM Revision 2d180e7b (ceph): JournalingObjectStore: whitespace fix
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 117ac901 (ceph): JournalingObjectStore: remove force_commit, no longer needed
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:31 PM Revision 1d9f5d27 (ceph): JournalingFileStore: create submit_manager to order op submission
- Previously, we ensured op ordering by queueing for journal and
the op queue under the journal lock. All that is requ... - 08:31 PM Revision 9601b291 (ceph): JournalingFileStore: move apply/commit sequencing to apply_manager
- syncing the filestore requires a stable commit point (i.e., all ops
up to applied_seq must have been applied). Previ... - 08:31 PM Revision a8ac453a (ceph): perf_counters: add dec()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:21 PM Revision 1db4bd9f (ceph): osd: verify authorizers for heartbeat dispatcher
- This was broken with the fixed messenger behavior with missing
verify_authorizer methods in 100fcca3cb54c97c4332328aa... - 08:21 PM Revision 5dd54716 (ceph): msg/Pipe: fix seq # fix
- 02f6262f47f72178a78d410f4facab7bbc97b098 got this all wrong (though it
worked by accident).
Signed-off-by: Sage Weil... - 08:21 PM Revision c830a9b2 (ceph): mon: separate pre- and post-fork init
- Do most init pre-fork, then do the last little bit (start up messenger,
bootstrap) post-fork.
Signed-off-by: Sage We... - 08:21 PM Revision 184a676e (ceph): msg/SimpleMessenger: start accepter in ready()
- Start the accepter thread when the first dispatcher is ready. This ensures
that there will be someone around to veri... - 08:12 PM Revision 6d3cafcc (ceph): rgw: refactor curl functionality
- Move curl stuff into its own class, use it in swift token validation.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:39 PM Revision 44818eb0 (ceph): rgw: configurable swift auth url
- This is relevant when using external swift v1 authentication. The
url was hard coded, now it's configurable.
Signed-... - 07:34 PM Revision a12bc435 (ceph): doc: fix typo in cinder upstart config name
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:20 PM Revision 06c62c52 (ceph): doc: Added syntax fixes to Peter's session authentication doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:40 PM Revision 8921fc7c (ceph): ceph-disk-prepare: assume parted failure means no partition table
- If the disk has no valid label we get an error like
Error: /dev/sdi: unrecognised disk label
Assume any error we ... - 05:40 PM Revision 2e32a0ee (ceph): ceph-disk-prepare: fix journal partition creation
- The end value needs to have + to indicate it is relative to wherever the
start is.
Signed-off-by: Sage Weil <sage@in... - 05:40 PM Revision 402e1f53 (ceph): ceph-disk-prepare: poke kernel into refreshing partition tables
- Prod the kernel to refresh the partition table after we create one. The
partprobe program is packaged with parted, w... - 05:00 PM Revision a4db58fc (ceph): msg/Pipe: whitespace cleanup
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:00 PM Revision 02f6262f (ceph): msg/Pipe: only randomize start seq #'s if MSG_AUTH feature is present
- The kernel client expects seq #'s to start at 1 or else it is unhappy.
So, only randomize these values if the MSG_AUT... - 04:46 PM Revision 3a48cbf2 (ceph): doc: update fs recommendations
- More forceful about recommending XFS. More warning about using btrfs in
production deployments.
Signed-off-by: Sage... - 04:00 PM Revision 7a82a321 (ceph): osd: make pool_snap_info_t encoding backward compatible
- Way back in fc869dee1e8a1c90c93cb7e678563772fb1c51fb (v0.42) when we redid
the osd type encoding we forgot to make th... - 03:46 PM Bug #3428 (Resolved): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- ...
- 08:53 AM Bug #3290 (In Progress): libceph: unable to handle osdmap
- 08:49 AM Bug #3290 (Resolved): libceph: unable to handle osdmap
- 02:24 AM rbd Bug #3427 (Resolved): krbd: unmap does not remove block device properly
- Problem caused by unmapping rbd volume:...
10/29/2012
- 10:48 PM Revision 1a236e16 (ceph): cephx: don't check signature if MSG_AUTH feature isn't present
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:47 PM Revision 56bce3ba (ceph): auth: include features in cephx SessionHandler
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:23 PM CephFS Feature #3426 (Closed): ceph-fuse: build/run on os x
- 10:21 PM Feature #3425 (In Progress): mon workload generator
- 10:21 PM Feature #3425 (Resolved): mon workload generator
- 10:21 PM Feature #3136 (Resolved): for bobtail: Set auth_supported=cephx as default
- 10:20 PM Feature #3377 (Resolved): cephx: sign messages
- 10:18 PM Bug #2712 (Resolved): osd: small write performance regression from 0.47.*
- 10:18 PM Bug #2955 (Can't reproduce): monitors failed to open new election
- 10:16 PM Linux kernel client Bug #3291 (Resolved): rbd: BUG in bio from rbd_rq_fn
- 10:16 PM Bug #3142 (Resolved): osd: crash induced by fsx workload
- 09:47 PM Revision 100fcca3 (ceph): Fixed problem with checking authorizer in accept().
- Signed-off-by: Peter Reiher <reiher@inktank.com>
- 09:16 PM Revision 5324d2d9 (ceph): librbd: Fix 32-bit compilation errors
- Switch size_t in clip_io to uint64_t; it's just easier, and the
alternative would be to limit 32-bit builds to sizes ... - 07:47 PM Revision 343a687d (ceph): Merge branch 'master' of github.com:ceph/ceph
- 07:42 PM Revision 2157bcbf (ceph): Temporary patch to a problem in Pipe related to monitor initialization.
- Signed-off-by: Peter Reiher <reiher@inktank.com>
- 07:37 PM Revision 4ce9da3b (ceph): Merge branch 'wip-oc-neg'
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:05 PM Revision b9eccdf8 (ceph): osd: make pool_snap_info_t encoding backward compatible
- Way back in fc869dee1e8a1c90c93cb7e678563772fb1c51fb (v0.42) when we redid
the osd type encoding we forgot to make th... - 06:00 PM devops Feature #3313 (Resolved): ceph-deploy: some way to initialize GPT on SSD storing multiple journals?
- 06:00 PM devops Feature #3304 (Resolved): ceph-deploy: add "ceph-deploy client HOST", that adds ceph.conf and cli...
- 05:43 PM devops Feature #3303 (Resolved): ceph-deploy: support external journals
- 04:55 PM Revision 7239e806 (ceph): dep-report.sh: ceph package dependency report.
- This script searches the ceph build area for dependent header files and
and libraries to attempt to identify ceph pac... - 03:58 PM Revision 1638f626 (ceph): client: Fix ref counting double free with hardlink
- Peforming a hard link through the libcephfs interface causes
a double free on shutdown, due to the Client::link call ... - 03:40 PM Revision 49ca7d50 (ceph): test: Functional test for hardlink/unmount pattern
- This test currently breaks on libcephfs as reported
in #3367.
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 03:40 PM CephFS Bug #3424 (Rejected): java: Add the correct JUnit package dependencies on supported platforms and...
- The libcephfs-java work has primary been done on Ubuntu. We need to sort out the correct JUnit dependencies on other ...
- 03:27 PM Bug #3286: librbd, kvm, async io hang
- Josh Durgin wrote:
> Unfortunately I haven't been able to reproduce this myself or track down the cause yet. Would i... - 12:10 PM Bug #3286: librbd, kvm, async io hang
- Unfortunately I haven't been able to reproduce this myself or track down the cause yet. Would it be possible to get a...
- 03:24 PM CephFS Cleanup #3423 (Resolved): Install java libraries into the correct directory
- I believe that the Java libraries are getting installed into the wrong directory. Verify that they're ending up in /u...
- 03:22 PM CephFS Feature #3422 (Rejected): Only compile java tests if JUnit is present
- We want to build the java tests as part of the Make process, so that it is delivered to users with the normal install...
- 03:19 PM CephFS Cleanup #3421 (Closed): Refactor Java tests to use older version of JUnit so that we can use 12.0...
- The java tests now require a newer version of JUnit than ships with Ubuntu 12.04. We should rewrite the code to use t...
- 02:24 PM Bug #3420 (Resolved): ceph-deploy osd does not parse argument correctly.
- Simple parsing error; fixed in
commit:18be750d30dfe51c415b5cadfba714cbf57ae569
- 02:02 PM Bug #3420: ceph-deploy osd does not parse argument correctly.
- Anna Tanato wrote:
> As of today, seems like ceph-deploy changed and included an optional JOURNAL argument; but if I... - 02:01 PM Bug #3420 (Resolved): ceph-deploy osd does not parse argument correctly.
- As of today, seems like ceph-deploy changed and included an optional JOURNAL argument; but if I enter only HOST:DISK ...
- 12:24 PM Feature #2254 (Resolved): doc: cephx
- 11:39 AM rbd Feature #2851 (Duplicate): krbd: RBD layering support
- Made subtasks features #3416, #3417, #3418, and #3419 for easier tracking.
- 11:38 AM rbd Feature #3419 (Resolved): krbd: copy-up on write to clone
- 11:38 AM rbd Feature #3418 (Resolved): krbd: write path (layering)
- 11:37 AM rbd Feature #3417 (Duplicate): krbd: read path (layering)
- 11:37 AM rbd Feature #3416 (Resolved): krbd: open parent on open
- 11:28 AM rbd Feature #3398 (Resolved): ObjectCacher: add ZERO BufferHead type
- 11:28 AM rbd Feature #3051 (Resolved): ObjectCacher: negative object caching
- 11:28 AM rbd Feature #3407 (Resolved): qa: add krbd + btrfs + stuff (iozone, fsstress) to suite
- 10:14 AM Bug #3290 (In Progress): libceph: unable to handle osdmap
- The server isn't properly encoding the pool_snap_info_t in a backwards-compatible way. Fixing there.
- 09:06 AM Linux kernel client Bug #3342 (Resolved): con_work crash on bad con pointer or mutex (kclient ffsb + thrashing)
- 08:47 AM CephFS Bug #3367 (Fix Under Review): client: hardlink without original file breaks on unmount
- Proposed fix in wip-3367. The Client::link() call was calling put_inode(dir) on successful completion, instead of le...
- 08:30 AM Linux kernel client Feature #3415: QA: xfstests over rbd failure info
- The teuthology task just needs to stick these files (and whatever else should be saved) in /tmp/cephtest/archive some...
- 07:27 AM Linux kernel client Feature #3415 (Resolved): QA: xfstests over rbd failure info
- When the rbd.xfstests task is run it sets up the tree of
commands and related file in /var/lib/xfstests. (This is
...
10/27/2012
- 08:56 PM Revision 84c7a34b (ceph): osdc/ObjectCacher: remove dead locking code
- This is unused, and mostly broken in that there is no cleanup when there
is a failure. Also, the support in the OSD ... - 01:58 PM rbd Feature #3414 (Resolved): librbd: clean up file locations in source tree (esp cls_rbd)
- 01:58 PM rbd Feature #3398 (Fix Under Review): ObjectCacher: add ZERO BufferHead type
- 01:58 PM rbd Feature #3051 (Fix Under Review): ObjectCacher: negative object caching
- 03:35 AM Revision 17c8589a (ceph): librbd: clip requests past end-of-image.
- Rename check_io to clip_io, which can modify the passed-in length
to clamp it to the device size. This is expected b... - 12:12 AM Revision 86de1faa (ceph): librbd: size max objects based on actual image object order size
- This has to happen after we open the image.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:04 AM Revision 07e7bc3b (ceph): rgw_cache: change call signature to overwrite rgw_rados put_obj_meta()
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
10/26/2012
- 11:55 PM Revision 8d7ca761 (ceph): osd/OSD.cc: Fix typo in OSD::heartbeat_check()
- The check 'p->second.last_tx > cutoff' should always be false
since last_tx is periodically updated by OSD::heartbeat... - 10:58 PM Revision 3384431b (ceph): mds: Fix SnapRealm differ check in CInode::encode_inodestat()
- When checking if inode's SnapRealm is different from readdir
SnapRealm, we should use find_snaprealm() to get inode's... - 10:48 PM Revision eafe0a8a (ceph): mds: allow try_eval to eval replica locks
- Allow try_eval(MDSCacheObject*, int mask) to eval locks on replica objects
so that they don't get stuck in an unstabl... - 10:43 PM Revision f0c2e12c (ceph): mds: Send mdsdir as base inode for rejoins
- Stray dir inodes are no longer base inodes, they are in the mdsdir
and the mdrdir is base inode.
Signed-off-by: Yan,... - 10:43 PM Revision ceeebaf4 (ceph): mds: Fix stray check in Migrator::export_dir()
- Commit f8110c (Allow export subtrees in other MDS' stray directory)
make the "directory in stray " check always retur... - 10:41 PM Revision d2ac024a (ceph): mds: fix stray migration/reintegration check in handle_client_rename
- The stray migration/reintegration generates a source path that will
be rooted in a (possibly remote) MDS's MDSDIR; ad... - 10:32 PM Revision 1b258764 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 09:55 PM Revision 2f09d47d (ceph): mon: fix leading error string from 'ceph report'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:50 PM Revision 0de0772e (ceph): radosgw-admin.py: add test of deleting user with data.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 09:49 PM Revision 818ea4e8 (ceph): radosgw-admin.py: add test of deleting bucket with objects.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 09:49 PM Revision 31284f74 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 09:45 PM Revision 9cea1812 (ceph): doc: updated front page graphic.
- fixes: #3412
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 09:38 PM Revision 6aab4af7 (ceph): Merge branch 'wip-java-cephfs'
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
Reviewed-by: Joe Buck <joe.buck@inktank.com> - 09:31 PM Revision 65ed99be (ceph): PG: Do not discard op data too early
- Under a sustained cephfs write load where the offered load is higher
than the storage cluster write throughput, a bac... - 08:58 PM Revision 7e7e06f4 (ceph): java: mkdirs returns IOException
- For example, CephFileAlreadyExistsException may be returned if mkdirs is
called to create a directory already present... - 08:58 PM Revision 5c914280 (ceph): java: enable ceph_unmount
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision d88c60c6 (ceph): java: enable ceph_release
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 16a4c92d (ceph): java: clean-up in finalize()
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 13f76dfa (ceph): java: remove deprecated ceph_shutdown
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision be94fb42 (ceph): java: add AlreadyMounted exception
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 0a1e0b79 (ceph): java: add tests for double mounting
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 047f58db (ceph): java: use unique directory in test
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:58 PM Revision 9c9c247d (ceph): java: log listdir contents in java client
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:30 PM Revision 712bfa59 (ceph): java: add FileAlreadyExists exception
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:30 PM Revision 1c45775a (ceph): java: add O_WRONLY open flag
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:30 PM Revision 4a5abc60 (ceph): java: remove tabs to fix formatting
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:09 PM Revision d4da4dcf (ceph): doc: fix warning in JavaDoc
- 06:56 PM Revision 94a84d29 (ceph): osdc/ObjectCacher: add ZERO bufferheads from map_read()
- When we add a bufferhead with zeros to the Object data map, use the new
zero type instead of allocating actual zeros.... - 06:56 PM Revision 1de33053 (ceph): osdc/ObjectCacher: handle zero bufferheads on read
- Interpret a zero bufferhead as zeros in _readx().
Signed-off-by: Sage Weil <sage@inktank.com> - 06:55 PM Revision fde7fe68 (ceph): osdc/ObjectCacher: add zero bufferhead state
- Wired up, but not yet used.
Treat these as clean.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:33 PM Revision 45946c2f (ceph): osdc/ObjectCacher: some extra debugging
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:33 PM Revision 4fb6a003 (ceph): test_librbd_fsx: sleep before exit
- This gives the log time to flush to disk. Kludgey!
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision 8920f417 (ceph): osdc/ObjectCacher: make trim() trim Objects
- Pull unpinned objects off the LRU in trim(). This never happens currently
due to all the explicit calls to close_obj... - 06:31 PM Revision 9407046d (ceph): osdc/ObjectCacher: do not close objects explicitly
- Let the trimmer do that.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision e2872965 (ceph): osdc/ObjectCacher: do read completions after assimilating read result
- Wait until we have applied the entire read result to the cache before we
trigger any read completion events. This is... - 06:31 PM Revision f3db940f (ceph): osdc/ObjectCacher: refresh iterator in read apply loop
- The p iterator points to the next bh, but try_merge_bh() at the end of the
loop might merge that into our result and ... - 06:31 PM Revision ab56e419 (ceph): osdc/ObjectCacher: add complete flag
- This is set when we know we have *all* the data for this object.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision 94d2b91d (ceph): osdc/ObjectCacher: clear complete on trim, release
- Clear the complete flag when we are discarding buffers.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision b9b1be6d (ceph): osdc/ObjectCacher: set complete flag when we observe ENOENT
- If we observe an ENOENT on a read, set the complete flag. Any dirty
buffers we have will still be in memory, even if... - 06:31 PM Revision 9dc887d6 (ceph): osdc/ObjectCacher: improve debug output for readx()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:31 PM Revision fdf556a3 (ceph): osdc/ObjectCacher: fill in zero buffers in map_read() on miss if complete
- If we know we have the complete object in cache, fill in zero buffers
when we miss.
Signed-off-by: Sage Weil <sage@i... - 06:31 PM Revision 24d07e87 (ceph): osdc/ObjectCacher: rename lru_* -> bh_lru_*
- We'll be adding LRUs for objects, too.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision a34a8b8b (ceph): osdc/ObjectCacher: add ref count to Object
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:31 PM Revision 57e18a74 (ceph): osdc/ObjectCacher: take Object ref when there are buffers
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:31 PM Revision 21dc0e02 (ceph): osdc/ObjectCacher: take refs for inflight lock ops
- These are all dead/unused; should probably just rip out this code!
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision 46897fd4 (ceph): osdc/ObjectCacher: take Object ref for bh writes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:31 PM Revision cd8e991a (ceph): osdc/ObjectCacher: add LRU for Object
- Incomplete; we aren't trimming yet.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:31 PM Revision f241e22f (ceph): osdc/ObjectCacher: check lru_is_expireable() in can_close()
- We assert that if can_close(), the Object isn't pinned in the LRU. This
assumes we did yur get/put refcounting prope... - 06:30 PM Revision 57a4cbbf (ceph): librbd: fix race in AioCompletion that are still being built
- When caching is enabled, it is possible for the io completion to happen
faster than we call ->finish_adding_requests(... - 05:28 PM Revision e2257673 (ceph): doc: add JavaDoc to Sphinx
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:08 PM rgw Bug #3294 (Rejected): Ceph S3 API test
- Yep.
- 05:07 PM rgw Bug #3410 (Resolved): radosgw-admin suspend user has no effect
- Fixed, commit:07e7bc3b3da978597907c02b26c5687f8acbb8a0 by caleb.
- 04:25 PM Revision a67afa4b (ceph): Merge branch 'wip-msgauth4'
- Conflicts:
src/common/config_opts.h
Added a couple of options related to session authentication, accepted new value... - 04:07 PM Revision e572b4b4 (ceph): Merge branch 'wip-client-unmount'
- Signed-off-by: Noah Watkins <noah.watkins@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 04:00 PM Linux kernel client Bug #2506 (Resolved): ceph: ceph_add_cap: couldn't find snap realm NNN
- Yan found this! by backuppc
- 03:57 PM Revision ffb8c605 (ceph): Various cleanup changes to session authentication code.
- Signed-off-by: Peter Reiher <reiher@inktank.com>
- 03:52 PM Bug #3292: osd crash in handle_osd_ping
- Recent log: ubuntu@teuthology:/a/teuthology-2012-10-25_02:00:04-regression-testing-master-basic/1520
- 03:49 PM Bug #3292: osd crash in handle_osd_ping
- Recent logs: ubuntu@teuthology:/a/teuthology-2012-10-25_02:00:04-regression-testing-master-basic/1516
- 03:38 PM Revision f1eef532 (ceph): client: double mount returns -EISCONN
- Change error code from -EDOM to -EISCONN when mounting an already
mounted ceph_mount_info instance. The current conv... - 03:38 PM Revision 67bc92aa (ceph): client: add ceph_release, ceph_shutdown
- Notes that ceph_shutdown() is now deprecated.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 03:31 PM CephFS Feature #3372 (Closed): java: add finalize() for users that don't do explicit clean-up
- Commit 16a4c92d20ced007b2c62a2d5444550b5308f730
- 03:30 PM CephFS Feature #3368 (Closed): java: add O_WRONLY open flag
- Commit 1c45775a83e955fd1d154c68c8f1304b533cd78e
- 02:50 PM Documentation #3412 (Resolved): doc: update main page arch diagram
- Updated and pushed to master.
- 03:49 AM Revision 1152656c (ceph): Merge branch 'wip-mds'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 03:49 AM Revision 3153ec74 (ceph): mds: fix handling of cache_expire export
- During export, between the warning stage and the final notify, we may
get cache expire messages because the replicas ... - 03:49 AM Revision c9ca3c99 (ceph): client: do not reset session state on reopened sessions
- We can have a sequence one the MDS like:
- queue REQUEST_CLOSE to journal
- force_open, queue open to journal
- r... - 03:49 AM Revision ad839c70 (ceph): mds: use connection on closed sessions in force_open_sessions
- If the have a Connection*, use it.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:49 AM Revision 4ac45200 (ceph): mds: do not mark closed connections disposable
- These will get reused when the client reconnects. If we are going to
clean these up, we need a different strategy.
... - 01:12 AM Revision c16c14b3 (ceph): Merge pull request #4 from ceph/wip-buck
- Use the configured username for _make_scratch_dir
- 12:51 AM Revision 53b354df (ceph): doc: update copyright to include contributors, CC
- Signed-off-by: Ross Turk <ross@inktank.com>
- 12:42 AM Revision 53ff33a7 (ceph): Use the configured username for _make_scratch_dir
- 12:19 AM Revision c33f93d2 (ceph): rgw: abort multipart upload uses part manifest
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
10/25/2012
- 10:42 PM rbd Bug #3413 (Resolved): rbd bench-write fails with assert when rbd caching turned on
- With 1152656c620c347cfd17035ea3e41711a79b86ce (and earlier 59839a8f9030c28391c7f99aa52a8c58a74c0066). Some kind of r...
- 07:00 PM Revision b668ee50 (ceph): Merge branch 'next'
- 06:59 PM Revision c0df8328 (ceph): osd: fix populate_obc_watchers() assert
- There is one case where populate_obc_watchers gets called when the object
is missing: during a revert. And in that c... - 05:26 PM Bug #3300 (In Progress): ceph::buffer::end_of_buffer isn't caught
- 05:21 PM Documentation #3412: doc: update main page arch diagram
- We should replace the homepage diagram with the updated one that we use in our PPT presentations. Contact me (rturk)...
- 05:20 PM Documentation #3412 (Resolved): doc: update main page arch diagram
- 05:16 PM Documentation #3411 (Resolved): doc: add introductory detail to the main doc page (index.rst)
- 05:08 PM Revision e10b99a3 (ceph): Add exit to kcon_most script
- Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 04:41 PM CephFS Bug #3373 (Won't Fix): java: after shutdown() access ceph_* in JNI is not prevented
- Irrelevant after deprecating shutdown(). Users of CephMount can now remount after an unmount, and the backing context...
- 04:40 PM CephFS Bug #3375 (Won't Fix): java: shutdown() doesn't clean-up if unmounted
- Irrelevant after deprecating shutdown().
- 04:40 PM CephFS Feature #3374 (Rejected): java: add unit tests for CephMount use after shutdown
- Irrelevant after deprecating shutdown(). Release() is now used to clean-up during finalize().
- 04:38 PM CephFS Bug #3371 (Won't Fix): java: ldout after ceph_shutdown causes segfault
- This doesn't matter after deprecating shutdown(). It still matters, though, for release().
- 12:00 PM Bug #3405 (Resolved): osd populate_obc_watchers regression
- 08:55 AM rgw Bug #3410: radosgw-admin suspend user has no effect
- the radosgw-admin teuthology task tests this, have it failed? Are you running in a mixed cache environment (gateway c...
- 08:27 AM rgw Bug #3410 (Resolved): radosgw-admin suspend user has no effect
- Suspending a user through the radosgw-admin cli tool currently has no effect, allowing a suspended user to retain all...
- 04:38 AM Documentation #3409 (Rejected): ceph zfs
- Ceph with ZFS
I have been working around ceph quite a long and trying to stitch zfs with ceph. I was able to do it... - 04:34 AM Revision 3eda37aa (ceph): mds: check getcwd() return value
- warning: mds/MDS.cc:1586:27: ignoring return value of ‘char* getcwd(char*, size_t)’, declared with attribute warn_unu...
- 12:04 AM Revision 1afa8ff0 (ceph): leveldb: fix accidental submodule revert
- a5eb72ba01bc74886170f2f6b97278ba5fc251d1
Signed-off-by: Sage Weil <sage@inktank.com>
Also available in: Atom