Activity
From 03/19/2013 to 04/17/2013
04/17/2013
- 11:09 PM Revision a629e9ee (ceph): Merge branch 'next'
- Conflicts:
teuthology/lock.py
teuthology/lockstatus.py
teuthology/misc.py
teuthology/task/install.py - 10:43 PM Revision 77cf9f4b (ceph): misc: Fix for case status['description'] == None
- Skip the machine that has a description, but the
value is None.
Signed-off-by: Sam Lang <sam.lang@inktank.com>
Revie... - 10:42 PM Revision 3c144e9b (ceph): rbd: Only allow shrinking an image when --allow-shrink flag is passed
- Signed-off-by: Wido den Hollander <wido@widodh.nl>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin... - 10:41 PM Revision 7b408ece (ceph): client: disable invalidate callbacks :(
- See #4746; it deadlocks right now.
Signed-off-by: Greg Farnum <greg@inktank.com> - 10:37 PM Revision 90a3bb7a (ceph): Merge pull request #219 from ceph/wip-rbd-progress
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 10:31 PM Revision db37bd8e (ceph): rbd: add --no-progress switch
- Disable progress output to stderr.t
Signed-off-by: Sage Weil <sage@inktank.com> - 10:14 PM Revision 8f21beb2 (ceph): leveldbstore: handle old versions of leveldb
- The filter_policy (bloom filter) stuff is fairly new in LevelDB's life,
and it turns out that precise's version is to... - 10:03 PM Revision 4bf24482 (ceph): Merge remote-tracking branch 'gh/wip-4521-fix' into next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 09:43 PM Revision 551860fa (ceph): rgw suite for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:39 PM Revision efe73997 (ceph): mds: pass proper mask to CInode::get_caps_issued
- There is a total of 22 cap bits and file lock uses 8 cap bits.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Rev... - 09:39 PM Revision 085b3ec4 (ceph): mds: change XLOCK/XLOCKDONE's next state to LOCK
- For simplelock and filelock, XLOCK/XLOCKDONE's next state is SYNC.
But filelock in XLOCK/XLOCKDONE state allow Fb cap... - 09:17 PM Revision f25f922b (ceph): mon: Monitor: convert osdmap_full as well
- Store conversion wasn't converting the osdmap_full/ versions, only the
incrementals under osdmap/ and the latest full... - 09:17 PM Revision 12600417 (ceph): mon: PaxosService: add helper function to check if a given version exists
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 09:15 PM Revision 3d4c8797 (ceph): Merge pull request #216 from dalgaaf/wip-da-fix-spec
- ceph.spec.in: use %{_sbindir} macro again
- 08:31 PM Revision 246b8118 (ceph): osd/PG.cc: initialize PG::flushed in constructor
- Initialize PG::flushed in constructor with false as
described in doc/dev/osd_internals/pg.rst .
Signed-off-by: Danny... - 08:31 PM Revision d3afae1f (ceph): Merge pull request #218 from dalgaaf/wip-da-sca-cppcheck
- Two small fixes
Reviewed-by: Sage Weil <sage@inktank.com> - 07:42 PM CephFS Bug #4713 (Resolved): mds: hang related to access from two clients
- The following have been committed to the "testing" branch
of the ceph-client git repository. With them in place
I ... - 07:39 PM CephFS Bug #4706 (Resolved): kclient: Oops when two clients concurrently write a file
- The following have been committed to the ceph-client
"testing" branch:
8f68229 libceph: change how "safe" callbac... - 07:38 PM CephFS Bug #4679 (Resolved): ceph: hang while running blogbench on mira nodes
- Sorry Greg, I should have been in better communication
with you. I have been testing these all afternoon and
Sage ... - 03:48 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- I believe Sage has been over all these now. I'm trying to go over the newest versions off the mailing list as well, n...
- 07:35 PM Bug #4705 (Resolved): rbd: do a safe list traversal in rbd_img_request_submit()
- Sage sent a pull request for this patch today and Linus
accepted it already for Linux 3.9.
46faeed rbd: do a saf... - 07:20 PM CephFS Bug #4726 (Can't reproduce): mds: segv during blogbench in remove_pending_backtraces
- I wasn't able to reproduce this after more than 200 runs, so I'm marking it as Can't reproduce for now.
- 06:41 PM Documentation #3804 (Resolved): Logging section recommends fairly high levels, doesn't stress how...
- Moved the consolidated pages to http://ceph.com/docs/next/rados/troubleshooting/log-and-debug/. Will appear in master...
- 05:56 PM Documentation #3804 (In Progress): Logging section recommends fairly high levels, doesn't stress ...
- Restructuring the entire logging section.
- 06:11 PM devops Documentation #2974 (In Progress): doc: update chef docs for mon key distribution
- This is should be resolved with the new monitor and auth config references. New ceph-deploy docs will cover it too.
... - 06:06 PM Bug #3495: ceph-mon crash
- After running for a few hours the monitors are not dying! I think you might have got it. I'll update this after it ru...
- 10:14 AM Bug #3495: ceph-mon crash
- should be safe!
- 09:14 AM Bug #3495: ceph-mon crash
- Is the gitbuilder build from that WIP branch fairly safe to test until 0.61 (or will using it horrifically break the ...
- 04:17 AM Bug #3495: ceph-mon crash
- Fix has been holding for the last 12 hours or so.
- 06:05 PM Revision 593507ea (ceph): Merge branch 'next'
- Conflicts:
doc/rbd/rbd-cloudstack.rst - 05:37 PM CephFS Bug #3597 (Resolved): ceph-fuse: denying root access
- Oh, this was a bug that got fixed in commit:d87035c0c4ff, included in v0.60.
- 05:05 PM CephFS Bug #4746: client: invalidate callback can deadlock
- Hmm, you're right, this is a more fundamental problem.
- 04:50 PM CephFS Bug #4746: client: invalidate callback can deadlock
- Maybe; we didn't think this through much beyond going "yep, that's broken".
However, I think we can queue up the i... - 04:44 PM CephFS Bug #4746: client: invalidate callback can deadlock
- "We may need to introduce a second locking layer to deal with this, that covers draining out all VFS requests before ...
- 03:04 PM CephFS Bug #4746 (Resolved): client: invalidate callback can deadlock
- I saw this when testing the fix for #3637. We appear to be (correctly) safe against deadlocks on our own locks, but w...
- 04:49 PM Revision f8183c91 (ceph): Merge pull request #215 from ceph/wip-leveldb-config
- os: bring leveldbstore options up to date
Reviewed-by: Sage Weil <sage@inktank.com> - 04:12 PM CephFS Feature #4326: qa: add samba + (kclient|ceph-fuse) to suite
- I think you might have mentioned you were trying to do this while you were working on the samba vfs-based ones? If no...
- 04:09 PM CephFS Bug #1878 (Resolved): ceph.ko doesn't setattr (lchown, utimes) on symlinks
- I've pushed this to our testing branch. It's presently commit:baf0169b77f6a0c384a15fb425e5700fb0239e89, although that...
- 03:59 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- And he gave me a reviewed-by tag. Will merge this tomorrow morning after some more testing.
- 03:53 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- This now appears to be passing (I've got it continuing to loop in the background), but it needs review and merging. S...
- 03:05 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- That latest issue was #4746. Turning off the callback and testing again...
- 05:42 AM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Zheng Yan wrote:
> there are only 4 states that allow Fw caps, they are MIX, MIX_EXCL, EXCL and EXCL_MIX. they all a... - 05:39 AM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Greg Farnum wrote:
> I don't remember how all the locking works when you have multiple writers, but I don't believe ... - 03:53 PM rbd Bug #4739 (Duplicate): Failed assert in librbd with rbd cache enabled
- see #4531
- 03:51 PM rbd Bug #4739: Failed assert in librbd with rbd cache enabled
- Mike Kelly wrote:
> Josh Durgin wrote:
> > The latest cause of this was #4531, whose fix was just merged yesterday.... - 10:25 AM rbd Bug #4739: Failed assert in librbd with rbd cache enabled
- Josh Durgin wrote:
> The latest cause of this was #4531, whose fix was just merged yesterday. If this is reproducibl... - 09:53 AM rbd Bug #4739: Failed assert in librbd with rbd cache enabled
- The latest cause of this was #4531, whose fix was just merged yesterday. If this is reproducible, could you try using...
- 09:36 AM rbd Bug #4739: Failed assert in librbd with rbd cache enabled
- How easy is this to reproduce? We have fixed several causes of this behavior, but I cant' remember offhand if they w...
- 07:44 AM rbd Bug #4739 (Duplicate): Failed assert in librbd with rbd cache enabled
- With librbd, as used by qemu (via libvirt), while using rsync to sync data to a fresh image:
osdc/ObjectCacher.cc:... - 03:49 PM Revision 2bcbf184 (ceph): radosgw-admin-rest: Add task for RESTful admin api.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 03:48 PM Revision 8db7b08e (ceph): radosgw-admin-rest: Add task for RESTful admin api.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 03:44 PM Bug #4521: mon: starting a new osd crashes all mon's
- fix is merged. fix tool should go in next too once we hear from Evan!
- 12:22 PM Bug #4521: mon: starting a new osd crashes all mon's
- Evan, just pushed a rework of the fix, and it looks like your store ought to be fixed by it.
Let me know how it goes. - 03:42 PM Revision a993d256 (ceph): Fix policy handling for RESTful admin api.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 03:36 PM Revision 438410a9 (ceph): lock: Fix import cycle breakage
- fa2049f caused an import cycle between lock.py and misc.py. Move the
needed functions from lock.py to lockstatus.py ... - 03:36 PM Revision 3f78cb0d (ceph): misc: Check for 'None' string from yaml
- The description attribute from the machines yaml returned by the
locker might be the string 'None'. Need to explicit... - 03:34 PM Revision df3d70fd (ceph): Install.py: Prevent prompts from breaking apt
- Change apt commands to prevent prompts from coming up (forcing
non-interactive mode) so things like grub or other stu... - 03:34 PM Revision 1b65b8fe (ceph): Revert "Install.py: Prevent prompts from breaking apt"
- This reverts commit 5995ae7e78dd19f4036f891db9db9fec97d6eab5.
With the changes to ceph-qa-chef and the teuthology ke... - 03:34 PM Revision dc457093 (ceph): Revert "Revert "Install.py: Prevent prompts from breaking apt""
- This reverts commit 67a616a97927efdc4fbcc5edb0d0cf4a724d90e2.
Sigh. As it turns out, /etc/default/grub being hacked... - 03:30 PM Revision 750c69b0 (ceph): misc: Check for 'None' string from yaml
- The description attribute from the machines yaml returned by the
locker might be the string 'None'. Need to explicit... - 03:30 PM Revision 1727d9b3 (ceph): misc: Use pythonic 'is not None' for jobid case
- The conditional 'if global_jobid:' evaluates to true
in some cases even when global_jobid is None.
Signed-off-by: Sa... - 03:30 PM Revision c1d47a2c (ceph): misc: Fix name parsing
- Use last two digits of year.
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 03:28 PM Revision b37f43db (ceph): lock: Fix import cycle breakage
- fa2049f caused an import cycle between lock.py and misc.py. Move the
needed functions from lock.py to lockstatus.py ... - 03:24 PM Revision 72cbf115 (ceph): misc: Use job id and make short path for testdir
- Nightlies run on teuthology currently use a testdir of
/home/ubuntu/cephtest, but this causes stale job errors occasi... - 03:23 PM Revision f3527d4b (ceph): Fix policy handling for RESTful admin api.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 12:54 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- passes with filestore_flush_min = 0.
- 09:38 AM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- We depend on those stamps in other places in order to be able to count throttle time (thus the distinction between re...
- 12:32 PM Bug #3440: Running OSDs on ZFS on Linux
- Looking at the logs again and seeing the posts on the mailinglist today it seems to be something with the xattrs inde...
- 11:19 AM rgw Feature #4745 (Resolved): rgw: radosgw-admin command to stat object
- Get object metadata info.
- 10:26 AM Bug #4675: mon: pg creations don't get queued on mon startup
- Giving this back since you're no longer on vacation.
- 10:26 AM rgw Bug #4497 (Can't reproduce): rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- 09:54 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- We still don't know where this one is coming from. At the time it looked like a client bug (e.g., the swift library b...
- 09:41 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- Yehuda - what's status of this?
- 10:26 AM Bug #4676: daemon logs aren't opened until daemonize
- Giving this back since you're no longer on vacation and I haven't had a chance to try and untangle the issues. :)
- 10:17 AM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- And also /a/teuthology-2013-04-16_01:00:52-fs-next-testing-basic/13665
- 09:26 AM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- This just happened again at /a/teuthology-2013-04-17_01:00:56-fs-master-testing-basic/14248 (it's still running, for ...
- 10:12 AM CephFS Bug #4742: mds: stuck clientreplay request
- Looks like a setattr and a create:
ubuntu@plana72:~$ sudo ceph --admin-daemon /var/run/ceph/ceph-client.0.19374.as... - 09:36 AM CephFS Bug #4742 (Resolved): mds: stuck clientreplay request
- /a/teuthology-2013-04-17_01:00:56-fs-master-testing-basic/14246
It has a single request which isn't completing; wh... - 10:06 AM CephFS Cleanup #4744 (In Progress): mds: pass around LogSegments via std::shared_ptr
- These really ought to be ref-counted in some way to prevent early expiry.
- 09:57 AM Bug #4743 (Can't reproduce): omap deep scrub finds multiple PGs as inconsistent
- I've inquired on IRC a few times about this (my nickname is paravoid) but filing it here since it sounds serious enou...
- 09:49 AM Bug #4653 (Resolved): mon: creation of cluster with many pgs fails within a reasonble time period
- commit:f8183c9
- 09:41 AM Bug #4543: mon: corrupted store if monitor dies mid-sync
- Joao - could you please provide the additional info you promised "asap"?
- 09:40 AM Bug #4543 (Need More Info): mon: corrupted store if monitor dies mid-sync
- 09:37 AM Bug #4735 (Won't Fix): identify ioctl not supported on Centos
- the warning is harmless. it just means we can't warn the user about the writeback cache on the drive.
- 08:43 AM Bug #4735: identify ioctl not supported on Centos
hdparm is used to determine if write-caching is enabled for the journal device. it appears to faile for virtual de...- 09:34 AM CephFS Bug #4741 (Duplicate): MDS: stuck in clientreplay
- /a/teuthology-2013-04-17_01:00:56-fs-master-testing-basic/14249
I can't find any hints, except that it is in fact ... - 09:22 AM Bug #4723: FAILED assert(!db->create_and_open(std::cerr)) after IO Error.
- In that case, maybe the real problem is that the init script didn't kill the other process, this output came from run...
- 04:42 AM Bug #4723: FAILED assert(!db->create_and_open(std::cerr)) after IO Error.
- Missed this bug completely.
It looks as if you had another monitor running when the new monitor was started.
Th... - 09:00 AM CephFS Feature #3243 (In Progress): qa: test samba reexport via libcephfs vfs plugin in teuthology
- 08:58 AM CephFS Feature #3242 (Resolved): samba: push plugin upstream
- Posted patches to mailing list:
https://lists.samba.org/archive/samba-technical/2013-April/091651.html - 08:53 AM rgw Feature #4716: rgw: ability to restrict user to specific operations
- Dependency for quota work.
- 08:50 AM rgw Bug #4740 (Resolved): Cannot retrieve policy through RESTful admin api
- 08:44 AM rgw Bug #4740: Cannot retrieve policy through RESTful admin api
- Resolved, commit f3527d4b514e4c0b4bbdb53c11b9b776a846aaf9 (master)
commit a993d2565f56892992a6e18500037db3... - 08:10 AM rgw Bug #4740 (Resolved): Cannot retrieve policy through RESTful admin api
- Attempting to retrieve bucket/object policy returns permission denied.
- 08:21 AM Bug #4662: osd/OSD.h: 809: FAILED assert(peering_queue.empty()) on shutdown
- ubuntu@teuthology:/a/teuthology-2013-04-17_01:00:51-rgw-master-testing-basic/14226
- 08:01 AM CephFS Bug #4738 (Need More Info): libceph: unlink vs. readdir (and other dir orders)
- Denis,
I've seen similar behavior with the smbtorture dir1 test, but it happens without the vfs_ceph module. Does... - 04:54 AM CephFS Bug #4738 (Closed): libceph: unlink vs. readdir (and other dir orders)
- Combining (stacking) in samba vfs_scannedonly with vfs_ceph, I experienced some bugs, looks like libceph readdir prob...
- 04:22 AM Bug #4737: ceph 0.60 mon crashed: 'void PaxosService::propose_pending()
- Denis kaganovich wrote:
> PS Also I have some issues about libceph, but it generated under samba + tricky stacking v... - 04:21 AM Bug #4737 (Duplicate): ceph 0.60 mon crashed: 'void PaxosService::propose_pending()
- Please see #3495
- 03:57 AM Bug #4737 (Duplicate): ceph 0.60 mon crashed: 'void PaxosService::propose_pending()
- Looks similar to #3260:
ceph version 0.60 (f26f7a39021dbf440c28d6375222e21c94fe8e5c)
1: (PaxosService::propose_p... - 04:16 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- While testing a bug fix, I noticed the leader would starting on a memory consumption rampage right after being starte...
- 03:51 AM Revision e8aa0d8b (ceph): ceph-deploy: purge before archiving
- Purge will uninstall and (in so doing) stop the daemons. This avoids trying
to tar up the mon data or logs while they... - 03:51 AM Revision 4befae4f (ceph): ceph-deploy: purge before archiving
- Purge will uninstall and (in so doing) stop the daemons. This avoids trying
to tar up the mon data or logs while they... - 02:58 AM Revision 33a6693f (ceph): scheduled_suite.sh: check clock skew at start and end of run
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5c80201ec4a4a97367e4d7243cd046a3a8c808fa) - 01:00 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Well,
could it be, that the fix already made it into "ceph version 0.60 (f26f7a39021dbf440c28d6375222e21c94fe8e5c)...
04/16/2013
- 11:40 PM Revision 544eb9bd (ceph): qa: pull qemu-iotests from ceph.com mirror
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:48 PM Revision 4865fb73 (ceph): Merge pull request #214 from ceph/wip-objectcacher-handler-ordered
- keep write responses to clones in order
Reviewed-by: Sage Weil <sage@inktank.com> - 10:46 PM Revision 89945661 (ceph): librbd: flush on diff_iterate
- The diff_iterate() tests fail when caching is enabled because recent writes
aren't visible to listsnaps. Flush from ... - 08:29 PM Revision 103fb9b0 (ceph): Merge branch 'next' of https://github.com/ceph/ceph into next
- 08:28 PM Revision efce39e2 (ceph): doc: Cherry-picked from master to next. Uses ceph-mds package during up...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:26 PM Revision 82aab8dc (ceph): doc: Cherry-picked from master to next. Rewrite of CloudStack document.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:24 PM Revision 97532875 (ceph): doc: Cherry-picked from master to next. Updates config to use virtio.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:23 PM Revision 72b3919c (ceph): doc: Cherry-picked from master to next. Reorders ceph osd create.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:22 PM Revision 3afe84b2 (ceph): doc: Cherry picked from master to next. Adds comments on naming OSDs.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:20 PM Revision 02d3c114 (ceph): os/FileJournal: fix journal completion plug removal
- We plug completions when transitioning from a full to non-full journal
to ensure that we do not complete items before... - 07:01 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- Note that the message recv stamp (which is used by the slow req warnings) is the time stamp *before* Pipe::read_messa...
- 05:03 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- Hmm. The osds aren't suiciding any more, but we still see 30s+ requests. We release filestore throttles when we hit...
- 06:41 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Greg Farnum wrote:
> I don't remember how all the locking works when you have multiple writers, but I don't believe ... - 03:43 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Okay, it's not quite that simple. This (all following the data writeout; I think this is the data check — anyway, thi...
- 02:58 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Reproduced at last. There continues to be a problem with the fix branch too :( but it's not a max_size issue; one of ...
- 01:47 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- And that wasn't working because teuthology was creating working dirs like /tmp/cephtest/gregf@kai-2013-04-16_12-59-21...
- 10:48 AM CephFS Bug #3637 (Fix Under Review): client: not issuing caps for with clients doing shared writes
- Regarding the testing (which I'm doing now), what those warnings turned out to mean is that each instance had their o...
- 10:37 AM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- I don't remember how all the locking works when you have multiple writers, but I don't believe either of those suppos...
- 06:01 PM Bug #4521 (In Progress): mon: starting a new osd crashes all mon's
- Ah! Got it. Thanks for attaching that log file.
It appears that your new store must have seen some versions trimme... - 04:51 PM Bug #4521: mon: starting a new osd crashes all mon's
- i've tried the new fix. attaching some files.
the debug-none argument didnt seem to have much effect. - 05:59 PM Revision d8a354d5 (ceph): config: provide settings for the LevelDB stores we use
- Now that we can set up the LevelDB options internally, provide
config options on the OSD and the Monitor. We leave th... - 05:52 PM Bug #3495 (Fix Under Review): ceph-mon crash
- Pushed wip-3495 to github. So far, the fix appears to be holding up without breaking anything else.
I'm leaving t... - 04:47 PM Bug #4736 (Resolved): journal Entry at pos 83251200 valid, there are missing sequence numbers pri...
- ...
- 04:35 PM rbd Bug #4683 (Resolved): librbd: diff_iterate test failures
- 02:43 PM rbd Bug #4683 (Fix Under Review): librbd: diff_iterate test failures
- see wip.. we need to flush the cache.
- 04:14 PM Revision fb840c8f (ceph): osd/PG.cc: initialize PG::flushed in constructor
- Initialize PG::flushed in constructor with false as
described in doc/dev/osd_internals/pg.rst .
Signed-off-by: Danny... - 04:04 PM Revision 4a84ddbd (ceph): client: Fix inode remove from snaprealm race
- This is a follow on fix to b5ce4d0. Always remove the inode from the
snaprealm's list of inodes_with_caps before the... - 04:02 PM Revision 0dc0f5b7 (ceph): osd/PG.h: remove unused variable prior_set_built
- Commit 540f42ce284d9 removed usage of prior_set_built, remove
also the related protected variable from the header.
S... - 03:49 PM rbd Bug #4531 (Pending Backport): ObjectCacher: read waiters for parent data during copyup get reorde...
- 03:48 PM rbd Bug #4531 (Resolved): ObjectCacher: read waiters for parent data during copyup get reordered, cau...
- 03:33 PM Bug #4735 (Won't Fix): identify ioctl not supported on Centos
- Not sure yet if this causes a problem, but I wanted to document it anyway.
Centos 6.3 and XFS filesystem
[root@... - 01:23 PM Bug #4730 (Resolved): osd: journal completion plug gets stuck, slow io ensues
- 02d3c114ab869b0ddc4d26c68e8b9e3391e7ad1b in next
- 08:26 AM Bug #4730: osd: journal completion plug gets stuck, slow io ensues
- see wip-4730
- 08:25 AM Bug #4730 (Resolved): osd: journal completion plug gets stuck, slow io ensues
- job was...
- 01:16 PM Bug #4653: mon: creation of cluster with many pgs fails within a reasonble time period
- Got reviews from both of them and Sage. Pushed a new version which uses "leveldb" instead of "ldb" in the config name...
- 01:11 PM CephFS Feature #4734: libcephfs: async interfaces
- If when we do this, whoever does so should please be careful to refactor our synchronous interfaces in terms of the a...
- 12:48 PM CephFS Feature #4734 (New): libcephfs: async interfaces
Implement async interfaces to libcephfs, at the least for the write and read calls.
This is motivated by the cep...- 12:53 PM CephFS Bug #4732: uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
- You might want to grab the ceph-fuse binary too so that the core dump is useful.
- 12:37 PM CephFS Bug #4732 (Closed): uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
- ...
- 12:47 PM Bug #4733 (New): Decode exception descriptions don't show function name
Using in progress import code with a bad data file shows that thrown exception has bad description. The __PRETTY_F...- 12:34 PM rbd Bug #4661 (Need More Info): xfstest 139 hung
- 11:49 AM rbd Bug #4661: xfstest 139 hung
- Test 139 does a forceful shutdown of the file system (without syncing)
to check on how well XFS handles it.
In th... - 12:23 PM Bug #4731 (Resolved): PG: don't write out pg epoch on every map activation
- For OSDs with a large number of pgs, this seems to pose significant overhead on bobtail.
- 10:46 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Yeah, the backports should definitely be merged by next week. On your lab cluster, you could try librbd from the 'nex...
- 05:50 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Hi Josh,
sounds promising, unfortunately I'm currently on 0.60... in our lab. We are going to move forward to late... - 09:59 AM CephFS Bug #4729 (Can't reproduce): mds: stuck in clientreplay
- Unfortunately by the time I got in one of the machines had been allocated for another job, and now it looks like the ...
- 07:52 AM CephFS Bug #4729 (Can't reproduce): mds: stuck in clientreplay
- job was...
- 09:31 AM CephFS Bug #4694 (Resolved): client: put_snap_realm assert failure
- Looks good to me; I merged it into next. This was an impressively narrow race so we couldn't get a good reproducer go...
- 04:50 AM Revision 6133ea5e (ceph): librbd: use initialized data for DiffIterateDiscard test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:32 AM Revision 638eb24f (ceph): librbd: print seed for all DiffIterate tests
- This will aid debugging on failures, and give better coverage.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:32 AM Revision 1ddea41f (ceph): Merge pull request #217 from alram/master
- Fix: use absolute path with udev
Reviewed-by: Sage Weil <sage@inktank.com>
04/15/2013
- 11:31 PM Revision b343c525 (ceph): doc: Changed MDS upgrade to use ceph-mds package.
- fixes: #4727
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:57 PM Revision 785b25f5 (ceph): Fix: use absolute path with udev
- Avoids the following: udevd[61613]: failed to execute '/lib/udev/bash'
'bash -c 'while [ ! -e /dev/mapper/....
Signe... - 10:27 PM Revision 1bb7a055 (ceph): ceph-deploy qa suites. moved a level up to make it run in the nightlies.
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:26 PM Revision 90e2a2ef (ceph): misc: Fix close() call to pass in fd
- fd is an int, we need to use os.close().
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 09:16 PM Revision cde1429e (ceph): misc: Fix bug in calling function remote_mktemp()
- Changed the name of the function to get a remote temporary filename,
need to update all the locations where it gets c... - 08:46 PM rbd Feature #3418 (Fix Under Review): krbd: write path (layering)
- I have posted the following for review:
I've broken these patches into three groups.
The first two are so... - 10:43 AM rbd Feature #3418: krbd: write path (layering)
- In order to distinguish this issue from
http://tracker.ceph.com/issues/3419 I'll
call this one complete when I have... - 06:44 PM Revision fe513353 (ceph): Merge pull request #11 from ceph/wip-4717
- misc: Use tempfile.mkstemp() instead of tempnam
- 06:43 PM Revision 3b0d9153 (ceph): misc: Use tempfile.mkstemp() instead of tempnam
- tempnam() is considered an unsafe security risk because the filename
generated is easy to guess and can be symlinked ... - 06:24 PM Revision f69ddafd (ceph): Revert "Revert "Install.py: Prevent prompts from breaking apt""
- This reverts commit 67a616a97927efdc4fbcc5edb0d0cf4a724d90e2.
Sigh. As it turns out, /etc/default/grub being hacked... - 05:45 PM Bug #4521: mon: starting a new osd crashes all mon's
- Evan, the fix was admittedly based on Matt's stores, and apparently I must have missed some other corner case.
Any... - 04:38 PM CephFS Documentation #4727 (Resolved): upgrade doc has to be modified to include upgrading ceph-mds as well
- Changed package to ceph-mds: http://ceph.com/docs/master/install/upgrading-ceph/#upgrading-a-metadata-server
- 04:26 PM CephFS Documentation #4727 (In Progress): upgrade doc has to be modified to include upgrading ceph-mds a...
- 11:42 AM CephFS Documentation #4727 (Resolved): upgrade doc has to be modified to include upgrading ceph-mds as well
- http://ceph.com/docs/master/install/upgrading-ceph/
In the above mentioned doc, in section "upgrading a metadata s... - 02:39 PM Revision b4fc83cc (ceph): doc: Overhauled Wido's CloudStack document.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:58 PM Bug #4703 (In Progress): ceph health hangs when upgrading from bobtail to next branch
- The problem still persists even after upgrading the whole cluster, The commands 'ceph -s' and 'ceph health' seems to ...
- 10:02 AM Bug #4703: ceph health hangs when upgrading from bobtail to next branch
- ah! mon.c (on burnupi14) is still running 0.56. The monitors will be unable to talk to each other unless they are al...
- 12:47 PM CephFS Bug #4713 (Fix Under Review): mds: hang related to access from two clients
- I have tested the commands listed above on a system with the
patches described here:
http://tracker.ceph.com/is... - 11:03 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- I ran the blogbench test with all of the above-mentioned
patches applied on a mira cluster and I never saw it hang.
... - 09:35 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- FYI, these kernel patches (Zheng's and mine) are available on
the ceph-client git repository branch "review/wip-4706... - 09:27 AM CephFS Bug #4679 (Fix Under Review): ceph: hang while running blogbench on mira nodes
- > Found 5 bugs, fixed 4.
I reviewed the four kernel patches (they were posted on the mailing
list). I also provi... - 09:15 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- > The fix for writepages race is easier than I thought, patch is attached.
This is interesting. When I was workin... - 10:59 AM CephFS Bug #4660: mds: segfault in queue_backtrace_update
- *blink*
Of course it's not; sorry about that. - 10:57 AM CephFS Bug #4660 (Resolved): mds: segfault in queue_backtrace_update
- That isn't the same bug. Opening #4726 for that issue.
- 10:52 AM CephFS Bug #4660 (In Progress): mds: segfault in queue_backtrace_update
- ubuntu@teuthology:/a/teuthology-2013-04-13_01:00:48-fs-next-testing-basic/12134
- 10:57 AM CephFS Bug #4726 (Can't reproduce): mds: segv during blogbench in remove_pending_backtraces
ubuntu@teuthology:/a/teuthology-2013-04-13_01:00:48-fs-next-testing-basic/12134
2013-04-13T18:52:50.199 INFO:t...- 10:47 AM Revision d801ca30 (ceph): ceph.spec.in: use %{_sbindir} macro again
- Commit ae71b576a7396bf44f052845af7561cc0436486a change some paths
again to absolute path to /usr/sbin. Use the correc... - 09:33 AM CephFS Bug #4706 (Fix Under Review): kclient: Oops when two clients concurrently write a file
- I have posted two patches, one which resolves the
crash due to an interrupt while waiting and one
that resolves Zhe... - 08:46 AM CephFS Bug #3579: kclient: Use less secure random number generator so we don't consume entropy
- commit 442318d09506d33e811d9d6a7bd2514287df729d
- 05:30 AM rbd Tasks #2853 (Resolved): krbd: read path
- The following have been committed to the ceph-client
"testing" branch:
745c34c rbd: implement layered reads
3c38... - 12:16 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- The branch wip-bobtail-rbd-backports-req-order has the fix for this plus several other bugs backported on top of the ...
04/14/2013
- 10:07 PM devops Bug #4725 (Resolved): ceph package build-depends are incomplete for Ubuntu 12.04 at least
- libboost-dev is listed, but it also requires libboost-system-dev and libboost-thread-dev on Ubuntu 12.04
- 10:32 AM rbd Feature #4724 (Resolved): krbd: handle layered I/O correctly when the child has been resized
- When a child image is shrunk or expanded, the logical section of the child that may inherit the parent's data is no l...
04/13/2013
- 05:02 PM devops Bug #4643: mkcephfs repeated deprecated warning messages can be avoided for -a option
- Neil Levine wrote:
> It could do but I fear that if it is just displayed at the top, people may miss it. It's not pr... - 03:12 PM Revision 50aaece4 (ceph): misc: Use pythonic 'is not None' for jobid case
- The conditional 'if global_jobid:' evaluates to true
in some cases even when global_jobid is None.
Signed-off-by: Sa... - 11:24 AM Bug #4723 (Can't reproduce): FAILED assert(!db->create_and_open(std::cerr)) after IO Error.
- VERY low priority.
Top of console output is below:... - 09:46 AM CephFS Bug #4722 (Can't reproduce): kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
- Top of Call trace:...
- 01:46 AM Revision 26d75372 (ceph): rbd: add qemu-iotests
- Put these in the singleton collection since they have to be run as
client.admin, which is possible when the client an... - 01:46 AM Revision d0a81f63 (ceph): rbd: add qemu-iotests
- Put these in the singleton collection since they have to be run as
client.admin, which is possible when the client an... - 01:33 AM Revision 06a95a6e (ceph): Merge branch 'next'
- 12:59 AM Revision 98de67d4 (ceph): qa: add workunit for running qemu-iotests
- This uses the old stand-alone qemu-iotests repo so it works with the
version of qemu in Ubuntu 12.04. The tests depen... - 12:04 AM Revision 715245e1 (ceph): misc: Fix name parsing
- Use last two digits of year.
Signed-off-by: Sam Lang <sam.lang@inktank.com>
04/12/2013
- 11:29 PM Revision a0ae2ece (ceph): os: bring leveldbstore options up to date
- LevelDB has a lot of options which we don't implement right now. Add
an options struct to the LevelDBStore which user... - 11:10 PM Revision 38e014f7 (ceph): prevent osd warnings from failing CephFS tests
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:10 PM Revision cfcc9c79 (ceph): prevent osd warnings from failing CephFS tests
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:07 PM CephFS Bug #4721: libcephfs tests fail when using ceph-deploy
- I'm able to reproduce this failure.
I'm much less familiar with libceph than I am the libcephfs-java code, so I'm g... - 05:42 PM CephFS Bug #4721: libcephfs tests fail when using ceph-deploy
- and the logs are placed in burnupi06.front.sepia.ceph.com:/home/ubuntu/apr12_cdep_libcephfs/
- 05:41 PM CephFS Bug #4721 (Resolved): libcephfs tests fail when using ceph-deploy
- ceph version : 0.60-467-g6b98162-1precise
config.yaml used to reproduce
tamil@ubuntu:~/test_logs_cuttlefish/apr... - 10:49 PM Revision 67a616a9 (ceph): Revert "Install.py: Prevent prompts from breaking apt"
- This reverts commit 5995ae7e78dd19f4036f891db9db9fec97d6eab5.
With the changes to ceph-qa-chef and the teuthology ke... - 10:49 PM Revision 52cdaae6 (ceph): kernel.py: put submenu name in 01_ceph_kernel if necessary
- We had been writing 01_ceph_kernel with the kernel title, and
relying on the fact that grub.cfg would never have subm... - 10:02 PM Revision 2c7b1f3d (ceph): peer.py: we can't assume pg query state will match mon pg state
- The pg state could easily have changed in the mean time,
for example, from recovery_wait to recovering.
Signed-off-b... - 09:21 PM Revision 98e4c864 (ceph): Merge pull request #205 from dalgaaf/wip-da-md_config-class
- md_config_t: change from class to struct as the name indicates
Reviewed-by: Greg Farnum <greg@inktank.com> - 08:36 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- If Locker::_do_cap_update can't get wrlock for a given client, the client should have no Fw cap. I think we can make ...
- 04:47 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- I'm having difficulty reproducing this at all on current next, but am leaving it churning in the background... :/
... - 08:14 PM Revision 6b98162f (ceph): mds: output error number when failing to load an MDSTable
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:06 PM Revision 35e6db72 (ceph): Merge pull request #10 from ceph/wip-fix-importcycle
- lock: Fix import cycle breakage
Reviewed-by: Warren Usui <warren.usui@inktank.com> - 08:05 PM devops Bug #4643: mkcephfs repeated deprecated warning messages can be avoided for -a option
- It could do but I fear that if it is just displayed at the top, people may miss it. It's not pretty but having it on ...
- 04:43 PM devops Bug #4643: mkcephfs repeated deprecated warning messages can be avoided for -a option
- Actually, is there any reason this isn't just output at the beginning of mkcephfs? Why does it need to be at the end?
- 03:33 PM devops Bug #4643 (Won't Fix): mkcephfs repeated deprecated warning messages can be avoided for -a option
- 1. My previous fix was a 1 liner. Not sure how to make this only appear once only without a fair bit of hacking :-)
... - 07:16 PM rbd Feature #2630 (Resolved): teuthology: add task to run qemu-iotests against rbd
- commit:98de67d424fd4ea972130ac737062aa8c093cbff
- 07:00 PM rbd Bug #4581 (Resolved): qemu: use asychronous flush
- http://patchwork.ozlabs.org/patch/232489/
- 05:57 PM Revision c2b0828b (ceph): Revert "Install.py: Prevent prompts from breaking apt"
- This reverts commit 5995ae7e78dd19f4036f891db9db9fec97d6eab5.
With the changes to ceph-qa-chef and the teuthology ke... - 05:57 PM Revision a6b84a56 (ceph): lock: Fix import cycle breakage
- fa2049f caused an import cycle between lock.py and misc.py. Move the
needed functions from lock.py to lockstatus.py ... - 05:49 PM rbd Bug #4551 (Pending Backport): librbd: rollback broken for clones
- This bisected to 860493e7ff0d87d02069b243fc1c8326ce0721f9. Fortunately, this is going to be backported anyway.
- 12:53 PM rbd Bug #4551 (In Progress): librbd: rollback broken for clones
- I added some tests for various cases of this. They all pass on v0.60 and the next branch consistently in several conf...
- 05:44 PM Documentation #4691 (In Progress): Add OpenNebula integration to doc
- 05:42 PM Documentation #2995 (Resolved): doc: restructure documentation (its getting messy!)
- 05:22 PM Revision a246f1e8 (ceph): Merge pull request #9 from ceph/wip-short-testdir
- misc: Use job id and make short path for testdir
Reviewed-by: Warren Usui <warren.usui@inktank.com> - 04:57 PM Bug #3253: ceph-disk-activate: support clusters not named "ceph"
- Confused; I still see this in mount_activate:
# TODO always using mount options from cluster=ceph for
# n... - 04:28 PM Bug #4521: mon: starting a new osd crashes all mon's
- Can you tell me if I am using this correctly:
root -#src/ceph_mon_kvstore_fix /data/mon/ /data/mon/ ... - 03:08 PM Bug #4662: osd/OSD.h: 809: FAILED assert(peering_queue.empty()) on shutdown
- -43> 2013-04-11 15:36:50.728192 ef4b700 10 filestore hoid: 16ef7597/infos/head//-1 not skipping op, *spos 13058.0....
- 03:04 PM Bug #4720 (Resolved): peer.py failure
- Fixed, removed the assert in teuthology, no reason those two things would be the same any more.
- 02:59 PM Bug #4720 (Resolved): peer.py failure
- "waiting_on_backfill": 0,
"backfill_pos": "0\/\/0\/\/-1",
"backfill_info"... - 02:42 PM devops Bug #4641: ceph-deploy install fails on fedora 18
- RHEL and CentOS to take priority over Fedora.
- 02:15 PM devops Feature #3924 (Resolved): ceph-deploy: package it
- Resolved with the following commit merged to master:
commit f56efde7150f17352912f23f0c749f43dbe09262
Author: Gary... - 01:49 PM rbd Bug #4531: ObjectCacher: read waiters for parent data during copyup get reordered, causing the wr...
- I tried, but I just don't know enough about the cacher or the completion framework to understand this, I'm afraid.
- 01:36 PM CephFS Feature #3242 (In Progress): samba: push plugin upstream
- Sam has been working on this for the last couple days.
- 01:16 PM rgw Feature #4716 (Resolved): rgw: ability to restrict user to specific operations
- e.g., have a read, write, delete mask in the user info. Certain api requests will need to have the specific bit set i...
- 11:28 AM devops Feature #4669 (Resolved): ceph-deploy discover command is not required
- Sage took care of this with commit:
commit a4f4a669a49574790e4137d5158e84f70789946d
Author: Sage Weil <sage@inkta... - 11:06 AM CephFS Bug #3579 (Resolved): kclient: Use less secure random number generator so we don't consume entropy
- 10:55 AM rgw Feature #4311 (In Progress): rgw: dr: radosgw changes: internal bucket changes tracker
- 10:53 AM rgw Feature #4347 (In Progress): rgw: dr: bucket index objclass: fetch changes log
- 10:53 AM rgw Feature #4328: rgw: dr: updated buckets log: tie into internal bucket changes tracker
- 10:48 AM rgw Feature #4328 (In Progress): rgw: dr: updated buckets log: tie into internal bucket changes tracker
- 10:48 AM rgw Feature #4346 (In Progress): rgw: dr: bucket index objclass: changes
- 10:13 AM CephFS Bug #4660 (Resolved): mds: segfault in queue_backtrace_update
- The commit that hit this segv above looks like it was off of master, whereas the fix went into next. I was able to r...
- 10:04 AM devops Feature #4367 (Resolved): ceph-deploy: if host is localhost, don't use ssh but run commands directly
- Resolved with the following commit to master:
commit d5fa55b23120c9e85fdc475e43f9b9b3052d1394
Author: Gary Lowell... - 09:30 AM CephFS Bug #4694 (Fix Under Review): client: put_snap_realm assert failure
- Pushed wip-4694. Still trying to reproduce this reliably so that I can test the proposed fix.
- 09:26 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Zheng Yan wrote:
> The Oops is caused by uninitialized req->r_inode
Already tracked down the Oops. time to sleep,... - 09:07 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- FYI I just reproduced the problem without interrupt
and it matches what I saw before. (So I don't believe
the inte... - 07:39 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- I also proposed a fix: [PATCH 1/4] ceph: add osd request to inode unsafe list in advance
- 07:22 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Zheng I think I have a fix. I'm going to test it first,
but then I'd like to supply it to you to see if it resolves... - 05:23 AM CephFS Bug #4706 (New): kclient: Oops when two clients concurrently write a file
- > Found a potential cause. the request may complete before adding it
> to the unsafe list.
I think that not being... - 12:09 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- The Oops is caused by uninitialized req->r_inode
- 07:35 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- The fix for writepages race is easier than I thought, patch is attached.
- 01:08 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Found 5 bugs, fixed 4. The remaining one is a race between truncate and writepages. Truncate message from MDS can cha...
- 06:02 AM Revision ae71b576 (ceph): init-radosgw.sysv: New radosgw init file for rpm based systems
- Added init-radosgw.sys file for rpm based systems, added it to
the tarball list in the makefile, and updated the spec... - 12:42 AM Revision f875c0c9 (ceph): mds: only go through the max_size change rigamarole if the client reque...
- The previous patch was forcing a new size change even if we were
doing it as part of our regular optimistic settings;... - 12:30 AM Revision 9c18fd67 (ceph): mds: Locker needs to remember requested max_size changes from clients
- Previously, if we received an MClientCaps request containing a change
in the inode's max size, and _do_cap_update() w...
04/11/2013
- 11:04 PM devops Bug #4571 (Resolved): el6: RGW init script failure
- Resolved with the following commit to next:
commit 61a900788b627eac9349ec337e210a130916706d
Author: Gary Lowell <... - 10:44 PM Revision 87ff4af1 (ceph): doc: Added additional note on first step of adding OSD.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:44 PM Revision 2b6719fe (ceph): doc: Added info on OSD naming, and example.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:38 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
- Making AJAX requests will result in an OPTIONS call to the server (RGW), which is currently unsupported. As such, POS...
- 08:41 PM Revision 52aec32a (ceph): kernel.py: put submenu name in 01_ceph_kernel if necessary
- We had been writing 01_ceph_kernel with the kernel title, and
relying on the fact that grub.cfg would never have subm... - 08:26 PM CephFS Bug #4714 (Duplicate): kclient: ceph_sync_{read,write} only accept single buffer.
- So readv and writev are broken for SYNC IO
- 08:00 PM Revision daa6ed2b (ceph): Merge pull request #210 from dalgaaf/wip-da-bobtail-pybind
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 07:36 PM Revision a01bc3d0 (ceph): doc: Moved ceph osd create to first step.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:28 PM CephFS Bug #4713: mds: hang related to access from two clients
- I discovered this while trying to reproduce the issue
in http://tracker.ceph.com/issues/4706.
I documented it the... - 07:24 PM CephFS Bug #4713 (Resolved): mds: hang related to access from two clients
- 07:28 PM Revision 74cdbc3c (ceph): doc: Changed libvirt example to use virtio.
- fixes: #4469
- 07:20 PM rbd Tasks #2853 (Fix Under Review): krbd: read path
- The following series has been posted for review.
This series puts in place code that is able to handle
read r... - 10:18 AM rbd Tasks #2853: krbd: read path
- Double fuckin' A. (Fuckin' double-A?)
I just updated my test to validate snapshot-of-clone and
clone-of-snapshot... - 09:36 AM rbd Tasks #2853: krbd: read path
- Fuckin' A. My test passed with the clone too.
(It should, but I wasn't sure until I ran it.) - 09:29 AM rbd Tasks #2853: krbd: read path
- Sweet, clone of snap of clone of snap of image produced the
same result as the original image. Finally back to wher... - 09:27 AM rbd Tasks #2853: krbd: read path
- OK, that feature bit was my problem. I am now able to
successfully map a version 2 image.
Having done that I cre... - 07:34 AM rbd Tasks #2853: krbd: read path
- I have identified two problems that I was hitting.
First, it was not possible for me to map a format 2 rbd image,
... - 06:59 PM Fix #4712 (New): recovery from partially partitioned networks
- This is a hypothetical but plausible problem.
If a group of monitors and OSDs are partitioned out, they will be de... - 06:53 PM Revision fa2049ff (ceph): misc: Use job id and make short path for testdir
- Nightlies run on teuthology currently use a testdir of
/home/ubuntu/cephtest, but this causes stale job errors occasi... - 06:31 PM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- This crash looks a little bit familiar to me, and I think
I created a bug for it, but at the moment I can't find it.... - 05:52 PM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- OK, well I believe I have reproduced the problem.
I did this on two nodes simultaneously:
dd if=/dev/zero of=... - 09:23 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Yes, test branch of ceph-client. The hint to trigger the Oops is multiple clients write date to a file at the same ti...
- 08:52 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Well, I unfortunately got the same problem using
the "bobtail" branch.
Specifically what I'm doing:... - 08:15 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Well that's interesting.
I haven't been working with the ceph file system much so
I'm not sure what to expect. B... - 07:43 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- > the request may complete before adding it to the unsafe list.
That looks like a reasonable explanation to me. A... - 06:28 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- ...
- 05:56 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- It is a new issue in the sync write path, nothing to do with cap revoke. Alex has made quite a lot of changes in that...
- 05:01 AM CephFS Bug #4706: kclient: Oops when two clients concurrently write a file
- Them doing a sync write is probably correct as their concurrency is being managed by the MDS now, and they aren't goi...
- 06:06 PM CephFS Bug #3637 (In Progress): client: not issuing caps for with clients doing shared writes
- Since I apparently forgot to mention it here, this has nothing to do with #4489; I just pattern-matched a little too ...
- 05:40 PM Bug #4675: mon: pg creations don't get queued on mon startup
- yep, not urgent. i'll take a look later. thanks!
- 04:08 PM Revision d777b8e6 (ceph): Merge pull request #213 from ceph/wip-sessionmap-4644
- mds: fix session_info_t decoding
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 03:52 PM Bug #4711 (Resolved): mon: remove --enable-experimental-feature on set pg_num
- This probably should be done before cuttlefish; just putting in a placeholder so we don't forget.
- 03:45 PM Revision e32849c4 (ceph): Merge pull request #212 from ceph/wip-4451
- 03:25 PM Revision 3a1cf53c (ceph): client: Unify session close handling
- If mds failure causes client reconnect while the
client is unmounting, the client will send a session
close request t... - 03:25 PM Revision 4977f3ea (ceph): mds: Delay export on missing inodes for reconnect
- The reconnect caps sent by the client on reconnect may not have
inodes found in the inode cache until after clientrep... - 03:24 PM Bug #4698: osd suicide timed out after 150
- logs from osds hitting suicide timeout with:
debug ms = 1
debug filestore = 20
debug filejournal = 20
osd.3 a... - 10:55 AM Bug #4698: osd suicide timed out after 150
- So apparently this is pretty consistently suiciding now and it wasn't before. :/ I was trying to figure out if the me...
- 02:36 PM Bug #4705: rbd: do a safe list traversal in rbd_img_request_submit()
- I don't know how to fill in the "Backport" field. But this
may be a bug we should send to Linus for the current
cy... - 01:20 PM Bug #4254 (Resolved): osd: failure to recover before timeout on rados bench and thrashing; negati...
- This hasn't been seen recently, and could have been fixed by d7b7acefc8e106f2563771a721944c57e10d54fb. Marking it re...
- 12:59 PM Bug #4704 (Rejected): clone range short read
- this seems likely to be a btrfs bug.
- 12:33 PM rbd Bug #4531 (Fix Under Review): ObjectCacher: read waiters for parent data during copyup get reorde...
- Dan, can you look this over? https://github.com/ceph/ceph/pull/214
- 12:33 PM Documentation #4469 (Resolved): Use virtio bus instead of ide bus for QEMU example
- 12:25 PM Documentation #4469 (In Progress): Use virtio bus instead of ide bus for QEMU example
- 12:27 PM rbd Bug #4710 (Resolved): rbd: STRIPINGV2 feature specified by default for format 2 images
- There's a check for whether it's really needed, but the defaults are 0 and 0, which are turned into regular striping ...
- 12:03 PM rbd Feature #4709 (Resolved): krbd: support stripingv2 images that don't require I/O path changes
- Currently when the rbd command creates format 2 images, due to a bug it always includes the STRIPINGV2 feature bit un...
- 09:09 AM CephFS Bug #4644 (Resolved): mds crashing after upgrade from 0.58 to 0.60
- Merged into next as of commit:d777b8e66b2e950266e52589c129b00f77b8afc0 (Thanks Sam!).
- 02:25 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- so patch tested, mds is running fine now. thx !
- 02:18 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- Last patch seems work. At least mds dont crash anymore. Also df reports non bogus values.
I'll add this patch to gen... - 12:14 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- let me know if i can test patches for you ! :)
- 09:06 AM CephFS Bug #4451 (Resolved): client: Ceph client not releasing cap
- Merged into next via commit:e32849c4eef2f5d911288aabeac0a6967b1e6ae4
I'm electing not to backport this despite its... - 08:16 AM CephFS Fix #4708 (Rejected): MDS: journaler pre-zeroing is dangerous
- See http://pastebin.com/NJd0UCfF
At first glance it looks like there's a short and a missing log object, and then ... - 08:15 AM CephFS Bug #4105: mds: fix up the Dumper
- Promoting this to high as it can be so useful for gathering important debug data; it would be nice to have done befor...
- 07:16 AM rbd Bug #4707: rbd CLI: bad error code masked by udevadm_settle
- It looks like the other places udevadm settle is called
do not suffer from this problem. - 07:14 AM rbd Bug #4707 (Resolved): rbd CLI: bad error code masked by udevadm_settle
- I found that despite my attempt to map a v2 image the rbd
CLI gave me an exit status of 0.
Looking at the code, I...
04/10/2013
- 11:57 PM Revision 06d05e5e (ceph): LibrbdWriteback: complete writes strictly in order
- RADOS returns writes to the same object in the same order. The
ObjectCacher relies on this assumption to make sure pr... - 11:52 PM CephFS Bug #4706 (Resolved): kclient: Oops when two clients concurrently write a file
- ...
- 09:24 PM Revision a3298713 (ceph): OSD: make pg upgrade logging quiet
- Fixes: #4701
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:00 PM Revision ac720a09 (ceph): Merge branch 'wip_4654' into next
- Fixes: #wip_4654
Reviewed-by: Greg Farnum <greg@inktank.com> - 08:54 PM Revision 351d9b27 (ceph): rbd qa/workunits: add rbd read data test
- This adds a new test script for validating data reads from a mapped
rbd image is what it's expected to be.
See the c... - 08:31 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- The code looks good.
- 01:10 PM CephFS Bug #4644 (Fix Under Review): mds crashing after upgrade from 0.58 to 0.60
- Hurray, I did manage to reproduce so I guess I just missed before, and indeed it works with that patch and fails with...
- 12:38 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- I'm having trouble reproducing this bug, but I'm probably not going through the right steps. A patch that I think sho...
- 12:20 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- if you have some patch that we can test, i'd be glad =)
- 10:27 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- Ah, this looks to be less bad than I thought — the (struct_v == 2) check should be (struct_v <= 2) is all, from the s...
- 09:03 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- update directly from IRC, as alexxy is still having registration issues:
<alexxy> joao: upgrade was from version 0... - 08:23 PM devops Feature #4367: ceph-deploy: if host is localhost, don't use ssh but run commands directly
- A few comments there, but otherwise looks good
- 09:59 AM devops Feature #4367 (Fix Under Review): ceph-deploy: if host is localhost, don't use ssh but run comman...
- Dan, please review the wip branch.
- 07:49 PM Revision bb8d1c98 (ceph): rgw_admin: Create keys for a new user by default.
- Create a new key pair for new users or when --gen-access-key is specified.
Signed-off-by: caleb miles <caleb.miles@i... - 07:48 PM Revision 90c256d7 (ceph): FileJournal: fix off by one error in committed_thru
- journalq.front().first is the sequence number of the entry
at journalq.front().second.
Signed-off-by: Samuel Just <s... - 07:48 PM Revision 170d4a3d (ceph): FileJournal: start_seq is seq+1 if journalq.empty()
- This is also the same as journaled_seq + 1 for writeahead
journaling, but not for parallel journaling.
Signed-off-by... - 07:48 PM Revision a4fa0a82 (ceph): Journal: commits may not include all journaled seqs
- At one point, a commit had to drain the FileStore op
queue. This is no longer the case. Consequently, the
journal m... - 07:47 PM Revision 13474b08 (ceph): Journal: pass the sequence number to commit_start
- A subsequent patch will need to see the committing seq.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 07:46 PM Revision 49bc341f (ceph): rgw_admin: Create keys for a new user by default.
- Create a new key pair for new users or when --gen-access-key is specified.
Signed-off-by: caleb miles <caleb.miles@i... - 07:46 PM Revision a1d9cbe5 (ceph): mds: fix session_info_t decoding
- commit 0bcf2ac081 changes session_info_t's format, but there is
a typo in the code that decodes old format. We also n... - 07:22 PM Revision 909dfb7d (ceph): LibrbdWriteback: removed unused and undefined method
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:06 PM Revision 9d199615 (ceph): LibrbdWriteback: use a tid_t for tids
- An int could be much smaller, leading to overflow and bad behavior.
Signed-off-by: Josh Durgin <josh.durgin@inktank.... - 07:03 PM Revision 870f9cd4 (ceph): WritebackHandler: make read return nothing
- The tid returned by reads is ignored, and would make tracking writes
internally more difficult by using the same id-s... - 06:47 PM Revision f5b81d8d (ceph): ObjectCacher: deduplicate final part of flush_set()
- Both versions of flush_set() did the same thing. Move it into a
helper called from both.
Signed-off-by: Josh Durgin ... - 06:36 PM Revision 4b656730 (ceph): test_stress_watch: remove bogus asserts
- There's no reason to check the duration of a watch. The notify will
timeout after 30s on the OSD, but there's no guar... - 06:29 PM rbd Bug #4531: ObjectCacher: read waiters for parent data during copyup get reordered, causing the wr...
- wip-objectcacher-handler-ordered
- 05:45 PM Revision 1ef0ecfc (ceph): Merge branch 'next'
- 05:43 PM Revision 3888a123 (ceph): test: update rbd formatted-output for progress changes
- Progress output now goes to stderr instead of stdout.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 05:42 PM Bug #4653: mon: creation of cluster with many pgs fails within a reasonble time period
- Asked for reviews from Joao and SamJ; waiting on those and probably some testing from Jim to merge this.
- 05:34 PM Bug #4653 (Fix Under Review): mon: creation of cluster with many pgs fails within a reasonble tim...
- Okay, these defaults at least don't balloon memory usage at startup, and they look comparable when doing comparable a...
- 04:41 PM Bug #4653 (In Progress): mon: creation of cluster with many pgs fails within a reasonble time period
- Preliminary branch in wip-leveldb-config. Going to do some brief tests around it to look at resource consumption.
... - 05:07 PM Bug #4704: clone range short read
- 2013-04-10 12:47:54.368871 7f7b1bfff700 15 filestore(/var/lib/ceph/osd/ceph-3) clone 3.117_head/8dd4a517/mira0375291-...
- 04:59 PM Bug #4704: clone range short read
- In dmesg on mira114 (where osd.3 was):
[ 540.131502] btrfs: unlinked 1 orphans
[ 1467.232908] btrfs: truncated 1... - 04:58 PM Bug #4704: clone range short read
- Of particular interest is the following line:
2013-04-10 13:25:11.539807 7f21d07f8700 10 filestore(/var/lib/ceph/o... - 02:52 PM Bug #4704 (Rejected): clone range short read
- 3:25:12.181924 7fd0257fa700 15 filestore(/var/lib/ceph/osd/ceph-1) get_omap_iterator meta/a468ec03/snapmapper/0//-1
... - 04:31 PM Revision dc1af54c (ceph): Merge pull request #211 from ceph/wip-doc-4697
- pool should be root in osd set syntax for bobtail
- 03:49 PM Bug #4705 (Fix Under Review): rbd: do a safe list traversal in rbd_img_request_submit()
- The following has been posted for review:
[PATCH] rbd: do a safe list traversal in rbd_img_request_submit()
- 03:45 PM Bug #4705 (Resolved): rbd: do a safe list traversal in rbd_img_request_submit()
- It's possible that the reference to the object request dropped
inside the loop in rbd_img_request_submit() will be t... - 03:47 PM Revision 718fa0c7 (ceph): pool should be root in osd set syntax for bobtail
- 02:48 PM Bug #4703: ceph health hangs when upgrading from bobtail to next branch
- hit this issue on burnupi13 and burnupi14 cluster. leaving the setup as it is for now so you can take a look at the l...
- 02:44 PM Bug #4703 (Can't reproduce): ceph health hangs when upgrading from bobtail to next branch
- while upgrading from bobtail to next [ceph version 0.60-451-g3888a12 ] all daemons at once [sudo service ceph -a rest...
- 02:25 PM Bug #4701 (Resolved): osd logs are flooded during the upgrade process
- a3298713bb0078e53071b702cba4530436b7a946
- 11:31 AM Bug #4701 (Resolved): osd logs are flooded during the upgrade process
- during the upgrade process from bobtail to next branch, the osd logs are currently flooded with messages like mention...
- 02:21 PM Bug #4254: osd: failure to recover before timeout on rados bench and thrashing; negative stats
- This could easily have been caused by #4627 d7b7acefc8e106f2563771a721944c57e10d54fb. I suggest we mark it resolved.
- 02:01 PM Bug #4654 (Resolved): FileJournal replay crash -- specific to btrfs/parallel journaling
- 12:58 PM rgw Bug #4702: radosgw-admin doesn't create keys when a user is created
- Fixed in master and next
- 12:58 PM rgw Bug #4702 (Resolved): radosgw-admin doesn't create keys when a user is created
- resolved, commit abf606d40ddb8cea2a1d9f0e44d57fa83eba96c5
- 11:53 AM rgw Bug #4702 (Resolved): radosgw-admin doesn't create keys when a user is created
- Next branch ceph version 0.60-450-g8eb5465 (8eb5465c10840d047a894d1a4f079ff8b8d608b5)
The documentation states tha... - 12:05 PM Bug #4591 (Resolved): test/test_stress_watch.cc:84: Failure
- False positive - these asserts didn't make sense. commit:4b656730ffff21132f358c2b9a63504dfbf0998d
- 11:15 AM rbd Bug #4684 (Resolved): qa: test_formatted_output needs updating for progress going to stderr
- commit:3888a12385aa6fcf35c9cdce9ad82a2cdd3377b7
- 11:13 AM rgw Feature #3668 (Resolved): rgw: support CORS
- merged, commit:01779df17d91df84c77d0d439dc6fe6b5ee05323
- 10:15 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- Yehuda said this looks like a client issue and wasn't sure why it was assigned to me. Assigning it back to you Yehuda...
- 10:10 AM Bug #4698: osd suicide timed out after 150
- There's this:
[1358446.830181] #0: (&type->s_umount_key#22){+++++.}, at: [<ffffffff811b4709>] sys_syncfs+0x49/0x... - 10:05 AM Bug #4698: osd suicide timed out after 150
- Was there anything in dmseg to indicate a hung fs?
- 09:33 AM Bug #4698: osd suicide timed out after 150
- sam - please assess
- 08:53 AM Bug #4698 (Won't Fix): osd suicide timed out after 150
With the following yaml, after running for a while osds start to commit suicide. This is with the latest next bran...- 10:10 AM rgw Bug #2366 (In Progress): rgw: bucket index update rely on pg state
- 10:09 AM rgw Feature #2172 (Resolved): rgw: get chunks asynchronously
- That had been implemented a while ago. commit:278dfe50fd174e9bc8782976aabb09f2cf39d582, duplicate of #2941.
- 09:36 AM Bug #3495: ceph-mon crash
- Well, my above comment is not entirely true. The patch itself was not undone, but rather the patch's focus was on th...
- 08:56 AM Bug #3495 (In Progress): ceph-mon crash
- Matthew Roy, imjustmattew on IRC, stumbled upon this bug yet again, this time on 0.60.
This was reintroduced with ... - 09:33 AM Documentation #4697 (Closed): osd syntax error
- Merged into master
https://github.com/ceph/ceph/pull/211 - 08:45 AM Documentation #4697 (Closed): osd syntax error
- http://ceph.com/docs/master/rados/operations/add-or-rm-osds/ should read root= instead of pool= for bobtail
- 09:16 AM devops Bug #4631 (Resolved): ceph-deploy: install failed on debian system
- Merged into master:
commit e226757b64a15b3ed237dda34e212863bbcea85a
Author: Gary Lowell <gary.lowell@inktank.com>... - 09:11 AM CephFS Bug #3579 (Fix Under Review): kclient: Use less secure random number generator so we don't consum...
- Patches sent to the mailing list and pushed to wip-3579.
- 09:07 AM CephFS Bug #4569: ceph-mds: segfault
- It looks like this fix didn't make it into 0.60. See #4696.
- 09:06 AM Bug #4699 (Resolved): osd: crash when looking at a map changing pool size from 0 to 2
- This is on bobtail. See mailing list report here: http://article.gmane.org/gmane.comp.file-systems.ceph.user/692
I... - 09:06 AM CephFS Bug #4696: MDS Crashes with Segmentation fault near Objecter::handle_osd_op_reply
- Oh you're using 0.60. Looks like that commit didn't make it into the 0.60 release. It will be fixed in the next one!
- 09:04 AM CephFS Bug #4696 (Duplicate): MDS Crashes with Segmentation fault near Objecter::handle_osd_op_reply
- This is a duplicate of #4569. Its fixed in 0.60 if you're willing to upgrade.
- 06:37 AM CephFS Bug #4696 (Duplicate): MDS Crashes with Segmentation fault near Objecter::handle_osd_op_reply
- Limited logs at http://goo.gl/VAIFh...
- 05:23 AM CephFS Bug #4679 (In Progress): ceph: hang while running blogbench on mira nodes
- I reproduced a hang, it is an 'i_mutex + cap revoking' deadlock....
- 12:58 AM CephFS Bug #1878: ceph.ko doesn't setattr (lchown, utimes) on symlinks
- For xattrs, there is no difference between symbol links and regular file. For setattr, I think the only difference is...
04/09/2013
- 11:00 PM Revision 8eb5465c (ceph): Merge branch 'wip-journaler-4618' into next
- Reviewed-by: Sam Lang <sam.lang@inktank.com>
- 08:12 PM Revision e2938f40 (ceph): Fix for kdb: doesn't work on mira nodes
- This is a fix for issue #4677 which was caused by kdb output being
hard-coded to ttyS1 which is fine for all our hard... - 08:09 PM Revision 9c9baef6 (ceph): Fix: kdb: doesn't work on mira nodes
- Change kernel.py to use ttyS2 for kdb output instead of ttyS1 when
the node is a mira machine. This is a fix for issu... - 07:49 PM CephFS Bug #4451: client: Ceph client not releasing cap
- Please review again based on the latest changed pushed to wip-4451.
- 04:27 PM CephFS Bug #4451: client: Ceph client not releasing cap
- Does this need more review or just testing? (I ask because I notice you've got two reviewed-by tags on it, although I...
- 08:48 AM CephFS Bug #4451: client: Ceph client not releasing cap
- Thanks Yan for fixing up that patch and testing it out. The inode check was just cruft from the previous changes, an...
- 06:00 AM CephFS Bug #4451: client: Ceph client not releasing cap
- After removing the path_is_mine check, MDCache::parallel_fetch_traverse_dir() needs skip non-auth dirfrags. The modif...
- 07:11 PM Revision 95374c62 (ceph): config: fix osd_client_message_cap comment
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 07:11 PM Revision cecbb4d8 (ceph): Merge remote-tracking branch 'origin/wip-osd-throttle2' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 06:53 PM rbd Tasks #2853: krbd: read path
- I have the read path code mostly working now. The problem was
that an object request that gets redirected to a pare... - 06:37 PM Bug #4675: mon: pg creations don't get queued on mon startup
- Also also, pretty sure a rare race with an easy workaround is not an urgent bug. :)
- 06:26 PM Bug #4675 (In Progress): mon: pg creations don't get queued on mon startup
- 06:26 PM Bug #4675: mon: pg creations don't get queued on mon startup
- Okay, but an OSD booting creates a new OSD Map, which will lead to PGMonitor::check_pg_map(), which will lead to send...
- 05:34 PM Bug #4675 (Fix Under Review): mon: pg creations don't get queued on mon startup
- the problem is that update_from_apxos() is called on startup when the osdmap isn't loaded yet, so it remaps everythin...
- 06:34 PM CephFS Bug #4644 (In Progress): mds crashing after upgrade from 0.58 to 0.60
- That shouldn't be a problem for v0.58; it included version 2 session_info_t. You sure that's the version you upgraded...
- 06:18 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- The 26th byte of Norbert's sessionmap is 1. If I'm not wrong, it's struct_v for session_info_t. But the oldest versio...
- 10:58 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- alexxy's sessionmap doesn't look anything like a sessionmap should; this won't fix his issue. Norbert's is at least s...
- 06:20 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- alexxy on IRC is reporting that the patch doesn't work. He would have provided his report himself, but it appears th...
- 05:46 PM Revision a48739d9 (ceph): FileJournal: clarify meaning of start_seq and fix initialization
- Second guessing the first sequence number from the FileStore
was silly and broke tests which had the temerity to star... - 04:13 PM CephFS Bug #4618 (Resolved): Journaler: _is_readable() and _prefetch() don't communicate correctly
- Merged into next in commit:8eb5465c10840d047a894d1a4f079ff8b8d608b5. This would apply to bobtail as well if we decide...
- 03:12 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Not off-hand, but I haven't spent any time thinking about it yet. This one could be differences between how aggressiv...
- 03:03 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- We've only seen a certain set of errors at the mds with the kernel client (this one and #4660 - although they may be ...
- 02:57 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- *sigh* Yep...
I've marked this as an MDS issue for now, but it could be a broader protocol change or something as ... - 02:45 PM CephFS Bug #4679 (Rejected): ceph: hang while running blogbench on mira nodes
- I re-ran the blogbench test 10 times using the "bobtail"
branch of ceph and never saw a hang.
I'm going to call t... - 12:13 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- I got another hang without any debug info being dumped
from the MDS. This time I just abandoned it. I'm about
to ... - 02:50 PM CephFS Bug #4694 (Resolved): client: put_snap_realm assert failure
- ...
- 02:18 PM Bug #4579 (Resolved): kclient + ffsb workload makes osds mark themselves down
- Okay, Sam says 100 should be fine since the filestore_queue_max_ops is set at 50. I've merged this into next in commi...
- 01:15 PM Bug #4677 (Resolved): kdb: doesn't work on mira nodes
- This is fixed in commit:
e2938f402606e86f19d64647982d1bebae00428a
in master of teuthology. Mira machines need t... - 12:15 PM devops Bug #4631 (Fix Under Review): ceph-deploy: install failed on debian system
- Proposed fix is in the ceph-deploy wip-4631 branch.
The fix creates a get_lsb_release() function that checks for t... - 12:11 PM Bug #4678 (Resolved): ceph pg dump --format crashes all monitors
- 11:04 AM CephFS Bug #1878: ceph.ko doesn't setattr (lchown, utimes) on symlinks
- I'm actually not sure how the symlink stuff is represented in our kernel client or the VFS — do these functions handl...
- 10:48 AM Bug #4687 (Resolved): ceph_test_filejournal failing
- a48739d9ab69b8372723139f652717709910e4d2
- 09:57 AM Bug #4682 (Duplicate): ceph_test_filejournal tests failed in the nightlies
- 09:50 AM Bug #4627 (Resolved): ReplicatedPG: ooo sub op
- Seems to have done the trick.
- 09:47 AM Revision 9fe57e2b (ceph): rados.py: fix create_pool()
- Call rados_pool_create_with_all() only if auid and crush_rule
are set properly. In case only crush_rule is set call
r... - 08:42 AM rbd Feature #4692: rbd qa: create an rbd lib shell script
- Based on our discussion...
A user's ~/.teuthology.yaml specifies the root of the
test directory by defining the v... - 08:13 AM rbd Feature #4692 (Rejected): rbd qa: create an rbd lib shell script
- I have been repeating big blogs of script code and I'd
like to create a library file that can be incorporated
into ... - 08:38 AM Revision 1d0bf61d (ceph): mon: Use _daemon version of argparse functions
- Allow argparse functions to fail if no argument given by using
special versions that avoid the default CLI behavior o... - 08:31 AM CephFS Bug #4660 (In Progress): mds: segfault in queue_backtrace_update
- 08:30 AM CephFS Bug #4660: mds: segfault in queue_backtrace_update
- Alex hit the same segfault with the next branch yesterday, looks like the commit 3cdc61ec doesn't fix this bug. The ...
- 08:27 AM Revision 3769250a (ceph): ceph_argparse: add _daemon versions of argparse calls
- mon needs to call argparse for a couple of -- options, and the
argparse_witharg routines were attempting to cerr/exit... - 07:06 AM Documentation #4691 (Closed): Add OpenNebula integration to doc
- Create an OpenNebula integration page similar to CloudStack and OpenStack and add a link to it from http://ceph.com/d...
- 05:41 AM Feature #4232: librados: Improve Java bindings
- So I started work on this and am using JNA to do so.
The source can be found here: https://github.com/wido/rados-j... - 02:35 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- I saw this happening again, all 12 OSDs went down with the same backtrace.
What I started to notice is that it hap... - 01:20 AM Revision 88ab8413 (ceph): Revert "global: call config observers on global_init (and start logging!)"
- This reverts commit a30917746614275baeb718e902133f06ef44fba6. This commit
includes calls that involve Mutexes, Locker... - 01:09 AM Revision 7eb09ef3 (ceph): changed "master" to "next"
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:58 AM Revision 42dfc752 (ceph): task yaml for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:49 AM Revision c76bbc2e (ceph): ceph_argparse: add _daemon versions of argparse calls
- mon needs to call argparse for a couple of -- options, and the
argparse_witharg routines were attempting to cerr/exit... - 12:49 AM Revision be801f6c (ceph): mon: Use _daemon version of argparse functions
- Allow argparse functions to fail if no argument given by using
special versions that avoid the default CLI behavior o... - 12:02 AM Revision d7b7acef (ceph): Pipe: call discard_requeued_up_to under pipe_lock
- Fixes: #4627
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
04/08/2013
- 11:52 PM Linux kernel client Feature #4690 (New): krbd: support arbitrary length responses to class operations
- Many class operations have unknown length. Reading the snapshot metadata for rbd, for example, is unbounded in total ...
- 10:53 PM Revision 1a3890a5 (ceph): Merge pull request #202 from ceph/wip-log-boot
- Fixes #4676.
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:43 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- We need to figure out how to set good defaults for this value before putting it in. 100 is likely to not be a very go...
- 09:09 PM Revision 4cb18b5a (ceph): journaler: remove the unused prefetch_from member variable
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:32 PM CephFS Bug #4680 (Closed): mds: log possibly not trimming
- 2013-03-28 10:27:35.154461 7f1fc96b8700 10 mds.0.log trim 2 / 30 segments, 10 / -1 events, 0 (0) expiring, 0 (0) expi...
- 10:32 AM CephFS Bug #4680: mds: log possibly not trimming
- Yeah, it's not a generic never trimming; just not certain about this one. It could also be fine and just that there's...
- 10:27 AM CephFS Bug #4680: mds: log possibly not trimming
- I've seen it trim logs in the tests I've been running, but that's with mds_log_segment_size=16K and mds_log_max_segme...
- 10:04 AM CephFS Bug #4680 (Closed): mds: log possibly not trimming
- Apparently there are a lot of old files showing up in the log replay, and I noticed previously on a different issue t...
- 08:27 PM Bug #4616 (Resolved): libceph: define ceph_decode_pgid() only once
- The following has been committed to the "testing" branch
of the ceph-client git repository:
85b6aab libceph: defi... - 08:25 PM rbd Feature #3761 (Resolved): kernel messenger: need to support multiple ops per request
- The following have been committed to the "testing" branch
of the ceph-client git repository:
b0ae840 libceph: com... - 08:25 PM rbd Feature #2770 (Resolved): krbd: define tasks to add osd_client compound class op support
- The following has been committed to the "testing" branch
of the ceph-client git repository:
436b0c0 libceph: add,... - 08:24 PM rbd Feature #4104 (Resolved): osd_client: support passing page array as data for CALL op
- The following has been committed to the "testing" branch
of the ceph-client git repository:
51122dd libceph: make... - 08:20 PM CephFS Bug #4644 (Fix Under Review): mds crashing after upgrade from 0.58 to 0.60
- there is a typo in session_info_t::decode
- 08:20 PM rbd Bug #4674 (Rejected): messenger: crash in read_partial_message()
- Rejecting this. It was a bug in a patch that had not
yet been committed. I fixed that patch, and it has
now been ... - 08:18 PM Bug #4664 (Resolved): libceph: skip message if too big to receive
- The following has been committed to the "testing" branch
of the ceph-client git repository:
5a0084a libceph: skip... - 08:17 PM rbd Subtask #4658 (Resolved): rbd: don't assume one op per request
- The following have been committed to the "testing" branch
of the ceph-client git repository:
78c8c1a rbd: don't s... - 08:16 PM rbd Subtask #4657 (Resolved): libceph: have each op describe its own data
- The following have been committed to the "testing" branch
of the ceph-client git repository:
73b4c46 libceph: add... - 08:15 PM rbd Subtask #4656 (Resolved): libceph: maintain source rather than wire ops array
- The following have been committed to the "testing" branch
of the ceph-client git repository:
e642226 rbd: define ... - 08:13 PM rbd Bug #4659 (Resolved): rbd: define inbound data size for method ops
- The following has been committed to the "testing" branch
of the ceph-client git repository:
7b67a62 rbd: define i... - 08:13 PM rbd Subtask #4589 (Resolved): libceph: consolidate maintenance of message data length
- The following has been committed to the "testing" branch
of the ceph-client git repository:
0af231f libceph: prov... - 08:04 PM CephFS Bug #4451: client: Ceph client not releasing cap
- Greg Farnum wrote:
> Although I think the MDS would need to have the inode in cache for that to happen — it would ha... - 10:59 AM CephFS Bug #4451: client: Ceph client not releasing cap
- Zheng Yan wrote:
> "Regarding the cap export, is it possible that the client has a cap that it thinks belongs to the... - 09:43 AM CephFS Bug #4451: client: Ceph client not releasing cap
- "Regarding the cap export, is it possible that the client has a cap that it thinks belongs to the mds, but the mds do...
- 09:13 AM CephFS Bug #4451: client: Ceph client not releasing cap
- "After removing the path_is_mine check in Server::handle_client_reconnect(), I think we should also call mdcache->rej...
- 06:54 PM Revision 826ad0d8 (ceph): teuthology: fix for ssh-keys-task
- Resolves an issue where we
were not properly escaping the generated
public key when doing matches against it.
Signed... - 06:51 PM Linux kernel client Bug #4689 (New): libceph: don't have alloc_msg methods limit length
- When an incoming message arrives, the messenger calls the
module it's destined for (osd client, mds client, mod clie... - 06:41 PM Bug #4676: daemon logs aren't opened until daemonize
- That version didn't work; it crashed, I believe because the lockdep infrastructure isn't set up yet and we're descend...
- 03:55 PM Bug #4676 (Pending Backport): daemon logs aren't opened until daemonize
- Merged into next in commit:1a3890a59fd8504176fe987cd3b1401bf721aa3f
Needs a backport but I'm turning down the prio... - 06:37 PM Bug #4688 (Resolved): ceph-mds: daemon fails to start after ceph installation
- Hmm, I just saw it on the monitor, and it makes more sense if it's a global thing. :)
Reverted the patch in questi... - 06:11 PM Bug #4688: ceph-mds: daemon fails to start after ceph installation
- it happens only with mds.
- 06:10 PM Bug #4688 (New): ceph-mds: daemon fails to start after ceph installation
- this started happening from ceph v0.60-438-g1a3890a
- 05:53 PM Bug #4688: ceph-mds: daemon fails to start after ceph installation
- Yeah, I just merged in something for Sage and I guess he didn't test it either — sorry. :/
Does this happen only o... - 05:27 PM Bug #4688: ceph-mds: daemon fails to start after ceph installation
- this started happening from ceph v0.60-438-g1a3890a
- 05:24 PM Bug #4688 (Resolved): ceph-mds: daemon fails to start after ceph installation
- ceph version: ceph version 0.60-439-gd7b7ace (d7b7acefc8e106f2563771a721944c57e10d54fb)...
- 06:18 PM Revision 9c2d017d (ceph): Merge pull request #206 from ceph/wip-4660
- mds: Keep LogSegment ref for openc backtrace
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:45 PM Revision 3cdc61ec (ceph): mds: Keep LogSegment ref for openc backtrace
- The MDRequest is destroyed once the client reply is sent, but
we need the reference to the LogSegment for updating th... - 05:06 PM Bug #4627: ReplicatedPG: ooo sub op
- Caused by messenger race. d7b7acefc8e106f2563771a721944c57e10d54fb. Waiting a bit to mark resolved.
- 04:59 PM Bug #4681 (Duplicate): osd crashed during startup
- oops
- 11:35 AM Bug #4681 (Duplicate): osd crashed during startup
- logs: ubuntu@teuthology:/a/teuthology-2013-04-08_02:44:31-rados-next-testing-basic/10102...
- 04:58 PM Revision c17b1722 (ceph): Merge pull request #203 from dalgaaf/wip-da-pybind-pylint-v2
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 04:57 PM Bug #4687 (Resolved): ceph_test_filejournal failing
- /a/teuthology-2013-04-08_02:44:31-rados-next-testing-basic/10131
Easily reproduced on next... Almost certainly cau... - 04:54 PM Bug #4686 (Can't reproduce): corrupt or missing osdmap on load_pgs
- 2013-04-08 04:06:11.034336 7f73b6ac3780 -1 filestore(/var/lib/ceph/osd/ceph-0) limited size xattrs -- filestore_xattr...
- 04:41 PM CephFS Bug #4685 (Can't reproduce): BUG: unable to handle kernel NULL pointer dereference at
- 0.56.4 ceph, 3.8 kernel...
- 04:10 PM Revision edc9ddfd (ceph): mds: fix journaler to set temp_fetch_len appropriately and read the req...
- The _prefetch() function which intereprets temp_fetch_len interprets
it as the amount of data we need from read_pos, ... - 03:25 PM Bug #4675 (Need More Info): mon: pg creations don't get queued on mon startup
- Okay, I've looked at the patches and I've looked at the bug description and I can't tell what the problem is here. Th...
- 08:17 AM Bug #4675: mon: pg creations don't get queued on mon startup
- Greg - can you please review this wip branch?
- 02:22 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- It looked very promising. 4 successful passes, but the
last one hung again. This time there were two blogbench
ta... - 12:26 PM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- One pass succeeded, so it's looking good.
I'll let it run 5 times and if all are successful, I'll just
close this... - 11:56 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- I talked with Sam Lang who said I should try again with
mds debugging on. That led to more info getting dumped
on ... - 11:01 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- ...
- 10:49 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Actually, the other common theme (maybe more important)
is the involvement of an in-progress ceph_setattr() call.
... - 10:40 AM CephFS Bug #4679 (In Progress): ceph: hang while running blogbench on mira nodes
- Unfortunately it looks like I've reproduced the problem
with my patches. The common theme is ceph_aio_write(), so
... - 10:04 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- I ran those tests a few times with the testing branch and
the problem did not show up. I reduced the test to just
... - 05:49 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Here is an excerpt of the yaml file driving the
tests, leading up to the blogbench run:... - 05:29 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Here are the versions of ceph and teuthology I'm using
while running these tests:
ceph
f5ba0fb mon: make 'osd cr... - 05:26 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Here is a log of the commits in place during these
tests. (I know, quite a few...) The last one is
the current te... - 05:24 AM CephFS Bug #4679: ceph: hang while running blogbench on mira nodes
- Here is an excerpt of the stack trace generated using:
echo t > /proc/sysrq-trigger
[31482.585095] blogbench.... - 05:21 AM CephFS Bug #4679 (Resolved): ceph: hang while running blogbench on mira nodes
- I have seen this only on mira nodes, now twice on two
consecutive attempts. I've run the same set of tests
with th... - 02:04 PM Bug #4678 (Fix Under Review): ceph pg dump --format crashes all monitors
- 10:58 AM Bug #4678: ceph pg dump --format crashes all monitors
- Yikes, worse, it'll voluntarily _exit(1). That's the wrong way to parse that...
- 03:32 AM Bug #4678 (Resolved): ceph pg dump --format crashes all monitors
- reported on ceph-devel. Indeed, it would. No checking for null.
- 01:23 PM rbd Bug #4684 (Resolved): qa: test_formatted_output needs updating for progress going to stderr
- ...
- 01:20 PM rbd Bug #4683 (Resolved): librbd: diff_iterate test failures
- These are probably the same underlying issue.
From ubuntu@teuthology:/a/teuthology-2013-04-08_02:44:59-rbd-next-te... - 12:06 PM Revision 00319494 (ceph): md_config_t: change from class to struct as the name indicates
- Change md_config_t from class to struct to fix some issues
from clang. The name indicates it's a struct so change it ... - 11:42 AM Bug #4682 (Duplicate): ceph_test_filejournal tests failed in the nightlies
- log: ubuntu@teuthology:/a/teuthology-2013-04-08_02:44:31-rados-next-testing-basic/10131...
- 11:29 AM Bug #4009 (In Progress): osd reports map e6 wrongly marked me down
- logs: ubuntu@teuthology:/a/teuthology-2013-04-08_02:44:31-rados-next-testing-basic/10094
ubuntu@teuthology:/a/teut... - 11:17 AM Bug #4671 (Resolved): OSD crashes
- Fixed in 8cb13a195c592fd2f17889e77d717c1864f97dca. Not yet in a point release, but it is in the bobtail branch.
- 11:02 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Said he could look at this for me today.
- 09:29 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Heh, no; that was supposed to be a 10. Re-pushed; thanks!
- 09:34 AM CephFS Bug #3579 (In Progress): kclient: Use less secure random number generator so we don't consume ent...
- 08:48 AM Revision 1734742b (ceph): rados.py: add docstrings for Ioctx::__aio_*_cb()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 07:22 AM Bug #4521 (Fix Under Review): mon: starting a new osd crashes all mon's
- This was caused by a bug in the store conversion, introduced in 0.59, resulting from not converting the osdmap full v...
- 07:16 AM CephFS Bug #4660 (Fix Under Review): mds: segfault in queue_backtrace_update
- Pushed a fix to wip-4660. The mdr was getting deleted before we queued the backtrace for update, so mdr->ls was inva...
- 07:04 AM rgw Feature #4464: rgw: bucket commands and RESTful API
- 07:04 AM rgw Feature #3274: rgw: RESTful admin api for user admin
- 07:03 AM rgw Feature #3992 (Resolved): rgw: refactor internal user API for RGW Admin
- 07:00 AM rgw Feature #4533 (Resolved): rgw: ability to configure zone params
04/07/2013
- 08:14 PM Bug #4677 (Resolved): kdb: doesn't work on mira nodes
- I've hit a few crashes on mira nodes, only to find that
kdb was not working. I thought it may have been due
to VPN... - 04:33 PM Revision 203915cf (ceph): rados.py: add more docstrings
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:33 PM Revision 3daf250c (ceph): rados.py: add docstrings for *Error classes and others
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:31 PM Revision 2124a4b1 (ceph): cephfs.py: add docstring for shutdown() and version()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:31 PM Revision 94a1f25e (ceph): rados.py: fix create_pool()
- Call rados_pool_create_with_all() only if auid and crush_rule
are set properly. In case only crush_rule is set call
r... - 04:27 PM Revision 9adf2e92 (ceph): rados.py: add some docstrings
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:27 PM Revision 29ae388c (ceph): rados.py: chmod -x
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:26 PM Revision 059c512f (ceph): pybind: unify make_ex() code in cephfs.py and rados.py
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:24 PM Revision 5559e1d7 (ceph): pybind: add docstrings for make_ex()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:24 PM Revision 471174bd (ceph): rbd.py: remove unnecessary semicolons
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:07 PM Revision 1e7ddd9e (ceph): global: flush log before stopping/starting on daemonize
- Ensure that we push log data out before we restart logging. This may not
be strictly necessary, but it avoids a whol... - 04:07 PM Revision a3091774 (ceph): global: call config observers on global_init (and start logging!)
- Currently we don't start logging on daemon startup unless the log_file
parameter was adjusted by ceph.conf. Instead,... - 10:48 AM Bug #4675 (Fix Under Review): mon: pg creations don't get queued on mon startup
- wip-mon-pg
- 09:10 AM Bug #4676: daemon logs aren't opened until daemonize
- simple fix is to call observers in global_init(). there is no harm in calling them twice. and note that the config ...
- 09:09 AM Bug #4676 (Fix Under Review): daemon logs aren't opened until daemonize
- wip-log-boot
- 08:54 AM Bug #4653: mon: creation of cluster with many pgs fails within a reasonble time period
- See Jim's patch on the ML. Need to tune leveldb parameters, but only for monitor, and in the ctor (says sam?).
Wh... - 01:46 AM CephFS Bug #1878 (Fix Under Review): ceph.ko doesn't setattr (lchown, utimes) on symlinks
- ceph_symlink_iops does not have getattr/setattr and xattrs related mothods
- 01:25 AM CephFS Bug #4241 (Duplicate): SELinux fails because it can't set xattrs
- This is the same problem as #1878 (ceph_symlink_iops doesn't have setattr method)
04/06/2013
- 11:53 PM Bug #4676 (Resolved): daemon logs aren't opened until daemonize
- This explains by the log banner with the ceph version etc usually does not appear in the log.
We don't call the Lo... - 11:51 PM Bug #4675 (Resolved): mon: pg creations don't get queued on mon startup
- PGMonitor::send_pg_creates *also* divvies up pg creations among the current osds they map to. This happens from upda...
- 08:54 PM Revision f5ba0fbb (ceph): mon: make 'osd crush move ...' idempotent
- If we don't need to move the item, return success.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:37 PM Revision 628e9ae2 (ceph): librbd: fix DiffIterateStress again
- - fix seed
- the array indices are points in time; no need to subtract one from i!
- pick a random seed and print it ... - 03:17 PM Revision f7070e95 (ceph): msgr: add second per-message throttler to message policy
- We already have a throttler that lets of limit the amount of memory
consumed by messages from a given source. Curren... - 03:17 PM Revision aca0aea1 (ceph): osd: throttle client messages by count, not just by bytes
- This lets us put a cap on outstanding client IOs. This is particularly
important for clients issuing lots of small I... - 01:24 PM Bug #4591: test/test_stress_watch.cc:84: Failure
- ubuntu@teuthology:/a/sage-2013-04-06_09:10:56-rados-wip-osd-throttle-testing-basic/9729
- 12:55 PM rbd Bug #4674: messenger: crash in read_partial_message()
- And now that I've looked at it, I see the cause...
It's this commit:
commit 0b809454cd5cd5cf3129a5beb6ba06970fd... - 12:44 PM rbd Bug #4674 (Rejected): messenger: crash in read_partial_message()
- Testing with 3.8.0-ceph-00293-ga39ffbd (which is a test
version of some code I've posted for review) I hit a
crash ... - 12:54 PM Bug #4664 (In Progress): libceph: skip message if too big to receive
- This patch has a bug. See this for more info:
http://tracker.ceph.com/issues/4674
(I'm going to reject that bu... - 11:30 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Confirmed, i tested with my system, and the journal-check can load the journal.
But, there is a line in commit:
<... - 07:36 AM Bug #4672 (Duplicate): multiple (a lot) slow requests on OSD
- 07:36 AM Bug #4672: multiple (a lot) slow requests on OSD
- Please upgrade to 0.56.4. This particular bug was fixed in .3
- 07:06 AM Bug #4672 (Duplicate): multiple (a lot) slow requests on OSD
- Ceph version is:
ceph version 0.56.2 (586538e22afba85c59beda49789ec42024e7a061)
Partial logfile included... - 07:08 AM Bug #4562: OSD fails to start with error assert(values.size() == 2)
- I am seeing this exact issue after upgrading from 0.56.4 to 0.60. How do I get the OSD back online?
- 06:56 AM Bug #4671 (Resolved): OSD crashes
- Logfile is attached. Started to crash after
I have other ceph node buggy and that (buggy) node was restarted.
- 05:28 AM Revision 79b71441 (ceph): librbd: fix DiffIterateStress test
- If we write to an interval that didn't previously exist and then discard
it so that it again doesn't exist, all durin...
04/05/2013
- 10:29 PM rbd Bug #4670 (Resolved): librbd: DiffIterateStress test failing
- commit:79b71441f8c2a1b282fa0e85badcb7d410c8005d
- 09:32 PM rbd Bug #4670 (Resolved): librbd: DiffIterateStress test failing
- it only happens when you do the full test set and not when you run just that test because the random seed is differen...
- 09:10 PM devops Bug #4631: ceph-deploy: install failed on debian system
- I think here we should just exit with a clean error message, with a suggestion to install the appropriate deb or rpm
- 05:27 PM Revision b083dece (ceph): rgw: translate object marker to raw format
- Fixes: #4600
Object marker should be treated as an object, so that name is formatted
correctly when getting the raw o... - 05:26 PM Revision be6961bd (ceph): Allow creation of buckets starting with underscore in RGW
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 05:18 PM Revision fa70eb8f (ceph): radosgw-admin: Test bucket list for bucket starting with underscore.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 04:46 PM Revision debce055 (ceph): Merge pull request #198 from dalgaaf/wip-da-spec
- Fix some install and rpm SPEC issues
Reviewed-by: Gary Lowell <gary.lowell@inktank.com> - 04:40 PM rbd Feature #4104 (Fix Under Review): osd_client: support passing page array as data for CALL op
- Found one small problem in this patch and another
one (probably the real cause) in one of the messenger
patches I p... - 03:34 PM rbd Feature #4104: osd_client: support passing page array as data for CALL op
- I have a patch that resolves this, based on the code just
posted for review for http://tracker.ceph.com/issues/3761.... - 07:29 AM rbd Feature #4104 (In Progress): osd_client: support passing page array as data for CALL op
- Now that I've got the per-op data out for review I can
start looking at this one.
It is going to be my test case ... - 04:36 PM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- I updated one of the patches posted:
[PATCH 5/6, v2] libceph: implement multiple data items in a message
Here's... - 03:31 PM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- Hopefully this will be it.
I have one more patch, which adds a second outgoing data item
for a osd class method C... - 03:28 PM rbd Feature #3761 (Fix Under Review): kernel messenger: need to support multiple ops per request
- The following patches have been posted for review:
[PATCH 1/6] libceph: record bio length
[PATCH 2/6] libceph: mo... - 07:30 AM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- Just to be clear, there is another handful of patches that
I have yet to post for review in order to complete this
... - 07:22 AM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- Here are some patches that I just posted for review which
were part of implementing this, but were more along the
l... - 04:25 PM devops Feature #4669 (Resolved): ceph-deploy discover command is not required
- "ceph-deploy discover" command is not required as "ceph-deploy config pull" does pretty much the same thing. both the...
- 04:02 PM CephFS Bug #4618 (Fix Under Review): Journaler: _is_readable() and _prefetch() don't communicate correctly
- There were a couple related bugs which prevented this from working right. I don't guarantee it's bug-free now, but th...
- 04:32 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Can i continue testing cephfs, or you make the fix quickly for this bug, and i can verify it on my system?
- 03:51 PM devops Feature #4667: ceph-deploy update
- 03:49 PM devops Feature #4667: ceph-deploy update
- No, it will just upgrade the package for you in a super easy way. If debian, it'll run apt-get update and apt-get in...
- 03:47 PM devops Feature #4667: ceph-deploy update
- Is this intended to be used instead of packages?
- 03:41 PM devops Feature #4667 (Rejected): ceph-deploy update
- make 'ceph-deploy update' either git pull or download and install the latest version of ceph-deploy. this will make ...
- 03:37 PM CephFS Bug #4451: client: Ceph client not releasing cap
- After removing the path_is_mine check in Server::handle_client_reconnect(), I think we should also call mdcache->rejo...
- 10:25 AM CephFS Bug #4451 (Fix Under Review): client: Ceph client not releasing cap
- Pushed a proposed fix to wip-4451. The fix is to not adjust the conditional for checking if an inode is auth or not....
- 03:29 PM Bug #4664 (Fix Under Review): libceph: skip message if too big to receive
- The following patch has been posted for review:
[PATCH] libceph: skip message if too big to receive
- 09:46 AM Bug #4664 (Resolved): libceph: skip message if too big to receive
- I've been aware of this for a while but it just occurred
to me I have a solution...
If a message is coming in for... - 03:27 PM rbd Feature #2770 (Fix Under Review): krbd: define tasks to add osd_client compound class op support
- The following patch has been posted for review:
[PATCH 6/6] libceph: add, don't set data for a message
- 02:50 PM rbd Bug #4665 (Resolved): librbd: read_iterate() can overflow its return value
- If the length requested is longer than int64_t, it will wrap around. This happened to someone on irc when doing an rb...
- 11:00 AM rgw Bug #4636 (Resolved): cannot create bucket starting with underscore
- Resolved, commit be6961bd28f11a9e0dde8ebc92d62fbcefc487ea
- 10:55 AM rgw Bug #4600 (Resolved): rgw: list bucket broken when marker start with underscore
- Patch merged into master, unit test created in master branch of teuthology. Commit b083dece36a050ec15ac41a275aeef0ece...
- 10:26 AM CephFS Bug #4660 (In Progress): mds: segfault in queue_backtrace_update
- 09:37 AM CephFS Bug #4660: mds: segfault in queue_backtrace_update
- No wonder this wasn't showing up in my bug queue!
- 08:20 AM CephFS Bug #4660 (Resolved): mds: segfault in queue_backtrace_update
- ...
- 09:36 AM CephFS Bug #4565 (Can't reproduce): MDS/client: issue decoding MClientReconnect on MDS
- I've had this running for more than 24 hours and it still hasn't reproduced. I'll let it keep going, but I don't beli...
- 09:15 AM phprados Feature #4663 (New): ownCloud storage backend
- It would be a great use-case for phprados to integrate in ownCloud: http://www.owncloud.org/
The documentation to ... - 09:13 AM rbd Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- Andrey Korolyov wrote:
> > One thing I noted, which doesn't seem related to RBD is that a Virtual Machine becomes ve... - 08:56 AM rbd Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- > One thing I noted, which doesn't seem related to RBD is that a Virtual Machine becomes very slow and unresponsive w...
- 08:39 AM rbd Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- I've just submitted a patch for this to libvirt (also attached).
I tested it locally with libvirt 1.0.4 and it wor... - 09:02 AM Bug #4662 (Resolved): osd/OSD.h: 809: FAILED assert(peering_queue.empty()) on shutdown
- ...
- 09:00 AM Bug #4579 (Fix Under Review): kclient + ffsb workload makes osds mark themselves down
- 08:24 AM rbd Bug #4661 (Can't reproduce): xfstest 139 hung
- i thought there was a bug open for this (saw it last week) but i guess not...
- 08:21 AM Bug #4627: ReplicatedPG: ooo sub op
- ubuntu@teuthology:/a/teuthology-2013-04-04_19:47:57-kernel-next-testing-basic/9333
- 07:23 AM rbd Subtask #4657 (Fix Under Review): libceph: have each op describe its own data
- Out for review.
- 07:22 AM rbd Subtask #4657: libceph: have each op describe its own data
- The following patches have been posted for review:
[PATCH 10/20] libceph: add data pointers in osd op structures
... - 05:56 AM rbd Subtask #4657 (Resolved): libceph: have each op describe its own data
- Each osd request has an array of osd operations (ops). Each
op can have a data item associated with it.
Currentl... - 07:21 AM rbd Subtask #4658 (Fix Under Review): rbd: don't assume one op per request
- The following patches have been posted for review:
[PATCH 12/20] rbd: don't set data in rbd_osd_req_format_op()
[... - 06:17 AM rbd Subtask #4658 (Resolved): rbd: don't assume one op per request
- I found it became necessary to rework a little of the rbd code
while working through having the osd support multiple... - 07:12 AM rbd Subtask #4656 (Fix Under Review): libceph: maintain source rather than wire ops array
- The following patches have been posted for review:
[PATCH 07/20] rbd: define rbd_osd_req_format_op()
[PATCH 08/20... - 05:49 AM rbd Subtask #4656 (Resolved): libceph: maintain source rather than wire ops array
- The osd client currently maintains the ops array for an osd
request directly in its request message. It formats int... - 07:10 AM rbd Bug #4659 (Fix Under Review): rbd: define inbound data size for method ops
- The following patch has been posted for review:
[PATCH 01/20] rbd: define inbound data size for method ops - 06:25 AM rbd Bug #4659 (Resolved): rbd: define inbound data size for method ops
- When rbd creates an object request containing an object method call
operation it is passing 0 for the size. I origi... - 06:36 AM rbd Subtask #4589 (Fix Under Review): libceph: consolidate maintenance of message data length
- One more patch that probably should have been included has
now been posted for review:
[PATCH] libceph: provide d... - 05:23 AM rbd Subtask #4589 (Resolved): libceph: consolidate maintenance of message data length
- The following have been committed to the ceph-client
"testing" repository:
fb3f962 libceph: record length of bio ... - 05:22 AM Revision 1f2d5bba (ceph): Merge remote-tracking branch 'gh/next'
- 05:15 AM Bug #4647 (Resolved): libceph: kill osd request r_con_filling_msg field
- The following has been committed to the ceph-client
"testing" repository:
ebc6540 libceph: drop ceph_osd_request-... - 05:14 AM Bug #4648 (Resolved): ceph: use page_offset() in ceph_writepages_start()
- The following has been committed to the ceph-client
"testing" repository:
f7464aa ceph: use page_offset() in ceph... - 03:07 AM Bug #4562: OSD fails to start with error assert(values.size() == 2)
- I am seeing this exact issue after upgrading from 0.56.4 to 0.60. How do I get the OSD back online?
- 02:40 AM Revision 41028847 (ceph): Install.py: Prevent prompts from breaking apt
- Change apt commands to prevent prompts from coming up (forcing
non-interactive mode) so things like grub or other stu... - 02:15 AM Revision 5995ae7e (ceph): Install.py: Prevent prompts from breaking apt
- Change apt commands to prevent prompts from coming up (forcing
non-interactive mode) so things like grub or other stu...
04/04/2013
- 11:15 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- sessionmap, command is rados --pool=metadata get mds0_sessionmap /tmp/sessionmap (without -o) :)
- 11:07 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- logfile with debug mds = 20...
- 05:16 PM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- I guess this bug was introduced by commit 0bcf2ac081b8386fe00387b654aa5676a7902c80...
- 11:29 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- I got a SessionMap from alexxy and it somehow has a bad version number attached to it. More importantly when I hexdum...
- 10:36 AM CephFS Bug #4644 (Need More Info): mds crashing after upgrade from 0.58 to 0.60
- It failed to decode the SessionMap properly here, but I can't tell why and the code hasn't changed at all between tho...
- 03:34 AM CephFS Bug #4644: mds crashing after upgrade from 0.58 to 0.60
- alexxy @ IRC also hit this issue. Attaching log.
- 02:37 AM CephFS Bug #4644 (Resolved): mds crashing after upgrade from 0.58 to 0.60
- after upgrade from 0.58 to 0.60, one mds is crashed and still crashing directly after start...
- 10:57 PM Revision 4824dafb (ceph): teuthology: extend Hadoop task to support branches
- Modify the Hadoop task to support branches
being specified for both the Apache and Inktank
Hadoop branches.
Signed-o... - 10:55 PM Revision 4258807b (ceph): teuthology: remove previous test ssh keys
- Updated the ssh-keys task to cleanup
any left-over keys from previous tasks
(indicated by the user being 'ssh-keys-us... - 10:33 PM devops Bug #4632: ceph-deploy: osd create command prepares disk but does not activate in centos
- Debian Precise has version:
glowell@gary-ubuntu-01:~/test2/ceph-deploy$ udevadm --version
175
Centos has versi... - 10:31 PM devops Bug #4632 (In Progress): ceph-deploy: osd create command prepares disk but does not activate in c...
- It looks like centos udev sysbsytem is does not support the ID_PART_ENTRY_TYPE* envirment variables used to trigger t...
- 10:22 PM Bug #4627: ReplicatedPG: ooo sub op
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-04_19:47:08-rados-next-testing-basic/9084
- 07:48 PM Revision 6ef9d87a (ceph): FileJournal: introduce start_seq header entry
- FileStore::header_t::start_seq now encodes the op seq which may be
written at FileStore::header_t::start. This way, ... - 07:48 PM Revision f12a5ed5 (ceph): FileJournal: fill in committed_up_to for old headers
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:32 PM devops Bug #4655 (Resolved): error handling in ceph-deploy could be better for negative tests
- trying to do an uninstall after purge throws inappropriate error message.
tamil@ubuntu:~/ceph-deploy-latest/ceph-d... - 04:38 PM Revision e5cecd76 (ceph): debian/ceph-test.install: add installed but not packaged files
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:30 PM Revision a3a658dc (ceph): ceph.spec.in: add installed but not packaged files to ceph-test
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:27 PM Revision 8cf3319f (ceph): ceph.spec.in: remove some twice created directories
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:23 PM Revision 6bc14889 (ceph): ceph.spec.in: fix udev rules.d files handling
- Move 50-rbd.rules into the ceph base package since the related
ceph-rbdnamer binary is part of this package. Use corr... - 04:21 PM Revision 4b90a958 (ceph): ceph.spec.in: use macros for standard directories
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:18 PM Revision a8362f5c (ceph): ceph.spec.in: reorder and fix ceph file list
- Reorder file list of ceph package. Fix handling of placeholder
directories, make use of directories marcros like %{_l... - 04:13 PM Bug #4654: FileJournal replay crash -- specific to btrfs/parallel journaling
- ubuntu@mira084:~/ceph$ less ceph-osd.4.log
full logs with journal and filestore logging. - 04:10 PM Bug #4654 (Resolved): FileJournal replay crash -- specific to btrfs/parallel journaling
- 2013-04-03 22:36:14.242946 7f43c8e3a780 10 filestore(/var/lib/ceph/osd/ceph-4) queue_flusher ep 0 fd 36 0~4194304 qle...
- 03:52 PM Revision 5b4cb537 (ceph): Merge pull request #176 from dachary/wip-4597
- fix nspace assignment in LFNIndex::lfn_parse_object_name
Reviewed-by: Samuel Just <sam.just@inktank.com> - 03:50 PM Revision ad8a346d (ceph): Merge pull request #8 from ceph/wip_4510
- repair_test: add test for repairing read errs and truncations
- 03:03 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- 02:18 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Okay, so the next entry is >40MB and we have 38MB in our read buffer. I'm not certain, but I think our use of "temp_f...
- 12:54 PM CephFS Bug #4618 (In Progress): Journaler: _is_readable() and _prefetch() don't communicate correctly
- 12:53 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Okay, there's not a lot there so apparently it doesn't have as much data as it thinks it needs in order to read the n...
- 02:00 PM Revision 6b802964 (ceph): debian/ceph.install: no need to move files to usr/sbin/
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:58 PM Revision 61a2be3b (ceph): ceph.spec.in: don't move ceph-disk* and ceph-create-keys around
- Don't move these files around, they get installed now directly to
%{_sbindir}.
Signed-off-by: Danny Al-Gaaf <danny.a... - 01:54 PM Revision 4d16f38f (ceph): Makefile.am: install ceph-* python scripts to /usr/bin directly
- Install ceph-* scripts directly to $(prefix)$(sbindir) (which
normaly would be /usr/sbin) instead of moving it around... - 01:07 PM Bug #4653 (Resolved): mon: creation of cluster with many pgs fails within a reasonble time period
- See Jim Schutt's email thread on ceph-devel
- 12:50 PM Bug #4527 (Resolved): journal Unable to read past sequence 0 but header indicates the journal has...
- 6ef9d87a02872fc7312c1c8f48abf9b48457f6e4
- 12:21 PM Bug #4597 (Resolved): nspace is ignored by LFNIndex::lfn_parse_object_name
- 11:14 AM Linux kernel client Bug #4652 (New): libceph: messages from pool not initialized
- This may not have been a problem until some of my recent
changes to the messenger (and osd client), but...
An osd... - 11:04 AM rgw Bug #3485 (Resolved): rgw: unique user emails not enforced
- 10:52 AM Revision 354c41e7 (ceph): ceph.spec.in: use %{_sbindir} instead of /usr/sbin
- Use %{_sbindir} macro which points to /usr/sbin instead of
hard coded path.
Signed-off-by: Danny Al-Gaaf <danny.al-g... - 10:42 AM devops Bug #4651 (Can't reproduce): ceph-deploy: unfriendly error message
- We should have friendlier--perhaps instructive--error messages for ceph-deploy. I entered the following syntax, which...
- 10:15 AM RADOS Feature #4650 (New): osd: separate OSD names from their IDs
- The MDS and monitors allow you to give each daemon a human-readable name which is distinct from their internal system...
- 09:52 AM rbd Feature #3893: krbd: document the new request code
- It's no longer fresh, and perhaps it's no more (or less)
worthy of documenting than any other piece of code we
have... - 09:49 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I'm updating this because the bug I identified in the
new code while trying to reproduce this has been
committed. ... - 09:32 AM Bug #4648 (Fix Under Review): ceph: use page_offset() in ceph_writepages_start()
- The following patch has been posted for review:
[PATCH 1/9] ceph: use page_offset() in ceph_writepages_start()
- 08:47 AM Bug #4648 (Resolved): ceph: use page_offset() in ceph_writepages_start()
- (I apologize if I already created an issue for this
but I don't see it.)
There's one spot in ceph_writepages_star... - 09:31 AM Bug #4647 (Fix Under Review): libceph: kill osd request r_con_filling_msg field
- The following patch has been posted for review:
[PATCH 2/9] libceph: drop ceph_osd_request->r_con_filling_msg
- 08:46 AM Bug #4647: libceph: kill osd request r_con_filling_msg field
- By the way, I'm calling this a bug because "cleanup"
doesn't allow me to mark things as "Need Review"
(or something... - 08:44 AM Bug #4647 (Resolved): libceph: kill osd request r_con_filling_msg field
- This field was (I think) needed at one time to avoid
a race between a request with a response message
getting relea... - 09:30 AM rbd Subtask #4589 (Fix Under Review): libceph: consolidate maintenance of message data length
- The following patches have been posted for review:
[PATCH 3/9] libceph: record length of bio list with bio
[PATCH... - 09:01 AM rbd Subtask #4589: libceph: consolidate maintenance of message data length
- One more thing. I will be recording the message data length
(in CPU byte order) in a separate field in the message,... - 08:55 AM rbd Subtask #4589: libceph: consolidate maintenance of message data length
- Just a comment on the work that leads up to getting
this to happen.
My aim is to have ceph_osdc_build_request() b... - 08:09 AM rbd Subtask #4125 (Resolved): kernel messenger: support multiple sources of data
- As mentioned, I fixed a simple problem (which was
more a problem for the reader than the computer),
and am therefor... - 08:07 AM rbd Feature #3861 (Resolved): rbd: consider splitting rbd_osd_req_op_create()
- The following have been committed to the ceph-client
"testing" branch:
76aa2dc ceph: move max constant definition... - 08:04 AM Linux kernel client Bug #4646 (Need More Info): kcephfs: writeback pagevec pool size vs stripe unit limit
- This was described here:
http://tracker.ceph.com/issues/4603
But that issue has been closed after fixing the mo... - 08:00 AM Bug #4603 (Resolved): ceph: writeback pagevec pool is created incorrectly
- The following has been committed to the ceph-client
"testing" branch:
df39ef2 ceph: set up page array mempool with ... - 07:59 AM Bug #4615 (Resolved): libceph: drop mutex on error in handle_reply()
- The following has been committed to the ceph-client
"testing" branch:
1fa4194 libceph: drop mutex on error in handl... - 06:53 AM Bug #3440: Running OSDs on ZFS on Linux
- I also tried to remove a object manually:...
- 06:47 AM Bug #3440: Running OSDs on ZFS on Linux
- I just tested it. It boots, but isn't very stable.
You can't run your journal on a file though, since ZoL doesn't ... - 05:58 AM Bug #4645 (Resolved): osd: Adding osd causes long stall without restart
- From the mailing list: http://thread.gmane.org/gmane.comp.file-systems.ceph.user/571/focus=572
Erdem Agaoglu wrot... - 05:01 AM Revision 939223aa (ceph): workunit: sudo rm -rf ...
- Signed-off-by: Sage Weil <sage@inktank.com>
04/03/2013
- 10:46 PM Revision 2f0e31f3 (ceph): Merge pull request #196 from ceph/wip-mon-crush2
- Wip mon crush2
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:45 PM Revision 29f9db19 (ceph): mon: fix crush unit tests for idempotency
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:42 PM Revision 32aac00c (ceph): Merge pull request #197 from ceph/wip-3266
- mds: verify mds tell 'dumpcache <filename>' target does not exist
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:32 PM Revision 336c4ae7 (ceph): mds: verify mds tell 'dumpcache <filename>' target does not exist
- Open target with O_CREAT|O_EXCL to ensure we don't overwrite some other
important file (like, say, /etc/passwd). Thi... - 10:04 PM Revision e6d4582a (ceph): mon: make 'osd crush unlink ..' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:32 PM Revision 3c0debf9 (ceph): Merge pull request #191 from ceph/wip-4582b
- Fixes #4582.
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:04 PM Revision 21d6af23 (ceph): rados: whitelist quota warning in cluster log for pool quota test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:00 PM Revision 5c80201e (ceph): scheduled_suite.sh: check clock skew at start and end of run
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:51 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- Yeah. The only throttling above the filestore queues is the messenger's limit on client bytes.. but these ios are sm...
- 03:57 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- What are the actual things being measured here? The OSDs do throttle the number of ops at least at the journal level ...
- 03:52 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- head explodes:...
- 07:43 PM Revision 0d6ddd92 (ceph): mds: do not go through handle_mds_failure for oneself
- A standby MDS can attempt the handle_mds_failure paths for itself, if
it sees the transition from up to down. This le... - 07:34 PM Revision ba536a83 (ceph): Merge branch 'wip-teuthologyvminstall-wusui'
- 07:29 PM Revision 8129bffb (ceph): Implement full reinstallation of a VM system.
- Downburst create is used to reinstall a VM when it is locked.
Downburst destroy is used to remove a VM when it is unl... - 07:16 PM Revision 2d19ebda (ceph): Merge pull request #194 from ceph/wip-rbd-diff
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:34 PM Revision 17a38593 (ceph): Merge pull request #195 from dalgaaf/wip-da-fix-make
- Makefile.am: fix build of ceph_test_cors
Reviewed-by: Sage Weil <sage@inktank.com> - 06:09 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Greg Farnum wrote:
> Are those logs posted somewhere? That indicates it's waiting to be allowed to read the stuff pa... - 05:41 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Are those logs posted somewhere? That indicates it's waiting to be allowed to read the stuff past where it stopped, b...
- 04:50 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- just a guess: with journaler debug, there is a line:...
- 03:08 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- you said "My off-hand guess is that something isn't getting cleaned up properly with the slave requests, which leads ...
- 03:07 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- I think of it every time i hear "stuck in replay", that's all. I havne't looked at the logs or anything.
- 02:59 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Sorry, but I'm a bit lost about why that might apply here. Are you just speculating or did something in the logs look...
- 02:57 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- see commit 7e04504d3ed119bb43a4eb99ca524b39dc3696bc. But the bug should just make replay slow.
- 02:38 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- here is a logcut with "debug journaler = 20": http://pastebin.com/nrzJg87E
- 01:59 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Yeah, that all looks good too. My off-hand guess is that something isn't getting cleaned up properly with the slave r...
- 01:52 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Don't forget #3351.. if the osd returns a short read on an object before the end of the journal, the Journaler replay...
- 01:35 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- if you tell me (here or irc) where to add new debug/assert lines, we can hunt down this bug.
- 01:15 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Thanks. (For future onlookers, the summary of those links is that everything is perfectly normal and as it should be,...
- 01:02 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Here is the status: http://pastebin.com/x1XEvuWc
Here is the config dump: http://pastebin.com/YTFbY5jW
- 10:09 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- The MDS maintains a journal that it writes metadata into before committing the aggregated updates into the actual ino...
- 02:01 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Greg Farnum wrote:
> Sorry, I mean the mds journal, not the debug logs, when referring to the size.
So the mds jo... - 06:04 PM Revision c8cbec2b (ceph): Makefile.am: fix build of ceph_test_cors
- Fix build of ceph_test_cors: use $(CRYPTO_LIBS) instead of -lcryptopp.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 05:59 PM Revision e8562218 (ceph): Merge pull request #192 from ceph/wip-mon-disk-warn
- mon: limit warnings about low mon disk space
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:56 PM Revision a4c6e2ee (ceph): Merge pull request #193 from ceph/wip-mon-crush
- mon: make 'osd crush rm|unlink ...' idempotent
Reviewed-by: Dan Mick dan.mick@inktank.com - 05:32 PM devops Bug #4643 (Won't Fix): mkcephfs repeated deprecated warning messages can be avoided for -a option
- ceph branch: master [ceph version 0.60-409-g2f0e31f (2f0e31f31ee01158040c3f337a66d1ac0ed2dc5b)]
It would be nice t... - 05:26 PM Revision e2edb9c6 (ceph): Merge remote-tracking branch 'gh/wip-4623'
- 05:03 PM Revision cf4bf09b (ceph): ceph.conf: lower mon disk avail warning threshold
- Only wanr when we hit 90% instead of default 70%
Signed-off-by: Sage Weil <sage@inktank.com> - 04:36 PM Revision 0ce09fad (ceph): client: Kick waiters for max size
- If the mds restarts without successfully logging a max size
cap update, the client waits indefinitely in Client::get_... - 04:31 PM Revision f9b7dff7 (ceph): client: log inode when waiting on max size
- Logging the specific inode that the get_caps()
is waiting for helps during debugging of stuck waiters.
Signed-off-by... - 04:14 PM devops Bug #4642 (Resolved): ceph-deploy: disk zap can throw a better error message
- ceph-deploy zap disk can throw a better error message, when no disks are specified
tamil@ubuntu:~/ceph-deploy-late... - 04:03 PM devops Bug #4641 (Resolved): ceph-deploy install fails on fedora 18
- ceph branch: master
tamil@ubuntu:~/ceph-deploy-fedora/ceph-deploy$ ./ceph-deploy install --dev=master plana07 plan... - 03:46 PM Bug #4624 (Resolved): crush_ops failure
- commit:29f9db19807a1a7f2991deaa6cd3947223c8d42b
- 03:12 PM Bug #4624 (Fix Under Review): crush_ops failure
- 03:43 PM CephFS Bug #3266 (Resolved): "ceph mds tell 0 dumpcache /etc/passwd" is not cool
- Merged in with commit:32aac00c7043aa1564272697879b1c626814b143
- 03:33 PM CephFS Bug #3266 (Fix Under Review): "ceph mds tell 0 dumpcache /etc/passwd" is not cool
- wip-3266
- 03:37 PM Revision 85a77dfd (ceph): mon: limit warnings about low mon disk space
- Only warn once per percentage point per epoch.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:34 PM Bug #4623 (Resolved): rados api test failure, snapshots
- 10:27 AM Bug #4623: rados api test failure, snapshots
- commit:e2edb9c646bc9ba7ff793218fb8df67a7e16d3f9
- 03:34 PM Linux kernel client Bug #4524: libceph: bad ptr deref in rbtree for kick_requests
- downgrading this until we see it again
- 03:25 PM Revision ea7c6c6d (ceph): librados: Fixes to list_snaps test changes
- Add back assert for overlap
Fix snap size and remove unnecessary comments
Fix failing test cases
Signed-off-by: Davi... - 03:12 PM Revision 982e1ed1 (ceph): radosgw-admin: Add test of duplicate user email specification.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 03:02 PM CephFS Bug #4582 (Resolved): mds: Client hang on fsstress with mds_thrasher
- 09:41 AM CephFS Bug #4582 (Fix Under Review): mds: Client hang on fsstress with mds_thrasher
- With the latest changes to the mds merged to master, and the fix from #4637, I was able to get a successful run of fs...
- 02:55 PM RADOS Documentation #4640 (Resolved): rados.8 should document import/export
- I wasn't even aware they existed :)
- 01:50 PM Bug #4527: journal Unable to read past sequence 0 but header indicates the journal has committed ...
- 2013-04-03 13:31:00.938602 7f083ffef700 5 journal submit_entry seq 927 len 4195890 (0x7f082c0126f0)
2013-04-03 13:3... - 01:35 PM CephFS Bug #4489 (New): ceph fs hangs on file stat
- Never mind, forgot the other one involved max size changes.
- 01:05 PM CephFS Bug #4489 (Duplicate): ceph fs hangs on file stat
- All right; that should be more stable for you. :)
Thanks for the steps to reproduce. I'm going to tentatively mark... - 01:31 PM Bug #4639 (Resolved): OSD class load failure log should be on by default and as noticeable as pos...
- Too many people have gotten rbd failures because of some damage to /usr/lib/rados-classes in
their installation: the... - 01:27 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- Starting to look at this now.
- 01:04 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- #4489 is probably a duplicate of this and has steps to reproduce, if we need alternate angles of attack. (And we shou...
- 01:04 PM Revision fb34c383 (ceph): radosgw-admin: Test subuser mask durability when creating new key.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 12:56 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- [Meant to post this yesterday but I guess I forgot to hit submit.]
Sadly, this test didn't slurp up any logs, so all... - 12:53 PM CephFS Bug #4637 (Resolved): mds: standby takeover stuck in rejoin
- Thanks. Don't you ever sleep? :)
Merged into master in commit:0d6ddd926432821842a7e40fdb78d793ab0737bb - 12:37 PM CephFS Bug #4637: mds: standby takeover stuck in rejoin
- Greg's fix looks good, sorry for the bug.
- 10:45 AM CephFS Bug #4637: mds: standby takeover stuck in rejoin
- Pushed that to wip-no-fail-whoami-4637. Sage, Yan, care to check it out? :)
- 10:33 AM CephFS Bug #4637: mds: standby takeover stuck in rejoin
- Can you try this patch instead, and see if that works? (If it does I'll want a review from Sage or Yan; it looks okay...
- 08:43 AM CephFS Bug #4637 (Fix Under Review): mds: standby takeover stuck in rejoin
- Pushed a fix to wip-4637.
- 08:40 AM CephFS Bug #4637 (Resolved): mds: standby takeover stuck in rejoin
- With current master, with one active mds and one standby, if the active fails, the standby gets stuck in rejoin while...
- 12:44 PM CephFS Bug #4638 (Duplicate): client: fsstress and mds_thrasher hangs client on unmount
- This is the same problem as #4451 (client inodes getting disconnected on unmount.
- 09:42 AM CephFS Bug #4638 (Duplicate): client: fsstress and mds_thrasher hangs client on unmount
After a successful run of fsstress and mds_thrasher, the client hangs on unmount and eventually returns EBUSY.- 09:38 AM rgw Bug #4636: cannot create bucket starting with underscore
- is this the same as 4600?
- 07:24 AM rgw Bug #4636 (Resolved): cannot create bucket starting with underscore
- Creating a bucket starting with an underscore returns bad request
- 08:31 AM Bug #4627: ReplicatedPG: ooo sub op
- ubuntu@teuthology:/a/teuthology-2013-04-02_18:35:37-kernel-next-testing-basic/8810
- 08:19 AM rgw Bug #3485: rgw: unique user emails not enforced
- resolved, commit dd19d693e6528c70167958ebc57e075200a08803
- 06:11 AM rgw Bug #2650 (Resolved): rgw: swift key creation overrides subuser access mask
- resolved, commit dd19d693e6528c70167958ebc57e075200a08803
- 06:01 AM Revision a7938538 (ceph): ceph-disk: CalledProcessError has no output keyword on 2.6
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 03:59 AM Revision b48d6b4a (ceph): librados: test for EINVAL on bad list_snaps() ioctx snapid
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:59 AM Revision 65a69750 (ceph): librados: set SNAP_DIR on listsnaps command
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 03:58 AM Revision ccb47fd0 (ceph): osd: fail with EINVAL if bad snapid set on list_snaps
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 03:57 AM Revision ae67d375 (ceph): librados: fix list_snaps() tests
- The ioctx must be set to SNAP_DIR, and the head does not include any
clones.
Bug #4623
Signed-off-by: David Zafman ... - 01:39 AM Revision 8d3c7ffd (ceph): mon: make 'osd crush rm|unlink ...' idempotent
- Return 0 if the item is not there, not -ENOENT.
Fixes: #4624
Signed-off-by: Sage Weil <sage@inktank.com> - 01:13 AM Revision 4e847e8b (ceph): librbd: simplify diff_iterate calls to list_snaps
- We don't need the size. Use the simpler API call.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:51 AM Revision edc46a7f (ceph): Fix comment typos
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 12:41 AM Revision 8ebf26ae (ceph): Merge pull request #185 from dalgaaf/wip-da-fix-misc-2
- Bunch of fixes for issues from SCA
- 12:41 AM Revision 7f19915f (ceph): Merge pull request #186 from dalgaaf/wip-da-pylint
- Fix smaller python issues
- 12:40 AM Revision 04fff0dc (ceph): Merge pull request #187 from imjustmatthew/imjustmatthew_docs2
- Adds "mds fail 0" command to operations commmand reference.
04/02/2013
- 11:38 PM Revision 17a55660 (ceph): Merge pull request #188 from dmick/wip-test-config-key
- test_mon_config_key.py: fix 'del' to clean up correctly internally
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank... - 11:24 PM CephFS Bug #1535 (Resolved): concurrent creating and removing directories crashes cmds
- I think this has been fixed by commit 00025462
- 11:22 PM devops Fix #4532 (Resolved): remove python 2.7 dependency in ceph-disk
- Resolved with the following commit:
commit a793853850ee135de14b9237f7023cadcdb8575c
Author: Gary Lowell <glowell@... - 12:12 PM devops Fix #4532: remove python 2.7 dependency in ceph-disk
- Proposed fix in branch wip-4532
This issue is holding up testing of ceph-deploy on centos. - 10:48 PM CephFS Bug #1945: blogbench hang on caps
- Sorry for the delay, I didn't noticed the notification. I fixed several bugs that may cause hangs of this type, but I...
- 10:09 PM Revision cfd32fff (ceph): test_mon_config_key.py: fix 'del' to clean up correctly internally
- 09:38 PM Revision 3842ff7d (ceph): Merge remote-tracking branch 'origin/wip-4619'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 08:05 PM Revision 5cf0c492 (ceph): mds: initialize tableservers/clients on mds creation
- The handle_mds_recovery(who) path initializes the anchorclients by having
the server send a 'ready' message on recove... - 08:05 PM Revision 1054c87c (ceph): Revert "mds: trigger tableserver active/recovery hook even for self"
- This reverts commit 968c6c0c9408b33904041e5ddbd9ea738e831713.
This will trigger the 'ready' message twice when we re... - 08:01 PM Revision 8a6438fe (ceph): README: fix dependency lists
- 1) automake appeared twice
2) make apt-get command match the list - 07:24 PM CephFS Bug #4489: ceph fs hangs on file stat
- Hm, snapdirname is something obfuscated (but have no use, actually).
I've got the same error one more time, so I bel... - 07:06 PM rgw Bug #4628 (Duplicate): RGW: underscore failing to escape
- Duplicate: http://tracker.ceph.com/issues/4600
- 11:54 AM rgw Bug #4628 (Duplicate): RGW: underscore failing to escape
- (10:24:45 AM) Matt: attempting to enumerate all of his objects with boto goes on forever
(10:42:27 AM) Matt:
from... - 06:48 PM Fix #4635 (Resolved): mon: many ops expose uncommitted state
- The prepare_update() methods are tricky because they need to make changes relative to uncommitted (pending) state. I...
- 06:45 PM rgw Feature #4606 (Rejected): Support s3cmd list buckets
- 06:33 PM rgw Feature #4606: Support s3cmd list buckets
- Confirmed that this was my fault and that s3cmd does indeed work with "s3cmd ls". I'd left off "include fastcgi_param...
- 06:38 PM Fix #4633 (Closed): Deactivating filestore xattr use omap creates inconsistent PG
- As discussed with Sam, this is not yet handled by Ceph.
Steps to reproduce:
- Deploy an OSD with filestore xattr... - 06:32 PM rgw Bug #4625 (Resolved): radowgw-admin.py failure
- fixed by teuthology commit:7b3973fff27d2c55f70a6224fd78ec66c9935db5
- 11:01 AM rgw Bug #4625 (Resolved): radowgw-admin.py failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-01_12:48:27-rados-master-testing-basic/7694
2013... - 06:31 PM devops Bug #3851 (Resolved): chef recipes don't enable upstart
- 06:31 PM devops Bug #3852 (Resolved): chef recipes don't try to start OSDs
- 06:14 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Sorry, I mean the mds journal, not the debug logs, when referring to the size.
- 05:12 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Greg Farnum wrote:
> Strange, it looks like you have an MDS log of about 1236MB, which is...large. What config optio... - 04:28 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- Strange, it looks like you have an MDS log of about 1236MB, which is...large. What config options are you setting?
... - 12:36 PM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- I changed back to max_mds 1. same result:...
- 09:42 AM CephFS Bug #4618: Journaler: _is_readable() and _prefetch() don't communicate correctly
- I'll check my assumptions today (already downloaded the logs), but with multiple active MDSes this doesn't warrant a ...
- 07:14 AM CephFS Bug #4618 (Resolved): Journaler: _is_readable() and _prefetch() don't communicate correctly
- The Journaler has mechanisms to try and read extra data if an event is large enough that it exceeds the current prefe...
- 06:10 PM devops Bug #4632 (Resolved): ceph-deploy: osd create command prepares disk but does not activate in centos
- ceph branch: wip-4532
tamil@ubuntu:~/ceph-dep-centos/ceph-deploy$ ./ceph-deploy osd create burnupi05:sdd --zap-di... - 05:57 PM Revision 0c16b31d (ceph): Adds "mds fail 0" command to operations commmand reference.
- Partially fixes #2206, though better documentation will eventually be needed.
- 05:42 PM devops Bug #4631 (Resolved): ceph-deploy: install failed on debian system
- ceph branch: master
tamil@ubuntu:~/ceph-deploy-debian/ceph-deploy$ ./ceph-deploy install --dev=master plana05 plan... - 04:35 PM Revision 6072f8f7 (ceph): Merge pull request #184 from dachary/wip-4617
- explain what an inline xattr is and how it relates to omap
- 03:58 PM Revision 968c6c0c (ceph): mds: trigger tableserver active/recovery hook even for self
- The tableserver now sends a READY message to clients when they go active;
we need to do this even for our own local t... - 03:54 PM Revision c4eb7e6d (ceph): ceph-disk: fix some (local) variable names
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:36 PM Revision 3dd8b461 (ceph): ceph-disk: fix naming of local variable in is_mounted()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:33 PM Revision eaf31bf9 (ceph): ceph-disk: merge twice defined function is_mounted(dev)
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:26 PM Revision 4c6d6442 (ceph): ceph-disk: define exception type
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:20 PM devops Bug #4629 (Resolved): ceph-deploy: disk zap needs to be fixed
- commit:71c39f617f2bde07b0fe1f82814b41252d481215
- 12:36 PM devops Bug #4629 (Resolved): ceph-deploy: disk zap needs to be fixed
- ceph-deploy zap disk command needs to be fixed. It seems to be confused about the input argument.
tamil@ubuntu:~/c... - 03:17 PM Revision 058eb923 (ceph): ceph-disk: fix Redefining name 'uuid' from outer scope
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:14 PM Revision 0080d1df (ceph): ceph-disk: add missing space after comma
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:11 PM rbd Feature #4211: get good qemu, libvirt versions+patches in CentOS+
- 03:01 PM Revision b99b8cc8 (ceph): rgw/rgw_user.cc: reduce scope of variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:50 PM Revision ee7eae36 (ceph): rgw/rgw_user.h: remove twice initialized purge_keys
- Remove twice initialized purge_keys from RGWUserAdminOpState();
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:48 PM CephFS Bug #4619 (Resolved): mds: anchortable hangs on new cluster
- Merged and pushed to master in commit:3842ff7d677bae98462f7d050f5fda9d85f6273d
- 02:20 PM CephFS Bug #4619: mds: anchortable hangs on new cluster
- Code looks good, Sorry for the bug!.
- 01:06 PM CephFS Bug #4619 (Fix Under Review): mds: anchortable hangs on new cluster
- recovery_done() breaks on a fresh machine because of the populate_mydir() ordering. The problem is that both recover...
- 09:52 AM CephFS Bug #4619 (In Progress): mds: anchortable hangs on new cluster
- Sage said he'd look at the double-send as well.
- 09:27 AM CephFS Bug #4619 (Resolved): mds: anchortable hangs on new cluster
- commit:968c6c0c9408b33904041e5ddbd9ea738e831713
- 09:13 AM CephFS Bug #4619: mds: anchortable hangs on new cluster
- I think this isn't correct. If we restart the table server MDS, it will send two ready messages to the table client. ...
- 09:02 AM CephFS Bug #4619: mds: anchortable hangs on new cluster
- Code looks good, assuming the tests run.
Sorry about that! :( - 08:15 AM CephFS Bug #4619 (Fix Under Review): mds: anchortable hangs on new cluster
- wip-4619
- 08:14 AM CephFS Bug #4619 (Resolved): mds: anchortable hangs on new cluster
- 02:36 PM Revision 6e9f4781 (ceph): test_cors.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:30 PM Revision b4845a69 (ceph): test_cors.cc: use static_cast instead of C-Style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:30 PM CephFS Bug #4621 (Rejected): failed pjd chown/00.t 124
- Okay, all symlink attempts that made it to the MDS were successes, and I can't find any failed ceph-fuse symlink/ll_s...
- 01:59 PM CephFS Bug #4621: failed pjd chown/00.t 124
- Sorry, not an lchown, just a symlink create.
- 01:29 PM CephFS Bug #4621: failed pjd chown/00.t 124
- Well, it's always an adventure to figure out which one is busted, but it looks to be an lchown on a symlink failing. ...
- 09:30 AM CephFS Bug #4621 (Rejected): failed pjd chown/00.t 124
- 2013-04-02T09:04:34.029 INFO:teuthology.task.workunit.client.0.out:../pjd-fstest-20090130-RC-open24/tests/chown/00.t ...
- 02:27 PM CephFS Feature #4630 (New): make lchown work in ceph-fuse for pjd
- pjd doesn't believe that ceph-fuse supports lchown. Maybe this is pjd's fault; maybe it's ours. Figure out why so tha...
- 02:25 PM Revision e2c3511b (ceph): test_cors.cc: use %u to format unsigned in sprintf()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:17 PM Revision bda21f72 (ceph): rgw/rgw_user.cc: use 'true' directly instead of variable
- Instead of passing 'true' via bool defer_user_update variable
in RGWUser::execute_modify() to keys.add() use it direc... - 02:15 PM Revision 84b1914b (ceph): rgw/rgw_user.cc: reduce scope of same_email in execute_modify()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:10 PM Revision 13abf321 (ceph): rgw/rgw_user.cc: remove some unused std::string variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:05 PM Revision 4839cf2a (ceph): rgw/rgw_cors_swift.h: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:03 PM Revision 620ca6c2 (ceph): rgw/rgw_op.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:03 PM Revision 275be105 (ceph): rgw/rgw_op.cc: remove unsused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision 4a35cfdf (ceph): rgw/rgw_op.cc: use static_cast instead of C-Style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:00 PM Revision c662733a (ceph): rgw/rgw_cors_s3.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:57 PM Revision 9850ed14 (ceph): rgw/rgw_cors_s3.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:55 PM Revision 21361708 (ceph): rgw/rgw_cors_s3.cc: use static_cast instead of C-Style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:54 PM Revision 69f60d26 (ceph): explain what an inline xattr is and how it relates to omap
- The logic of the configuration flags related to xattr is clarified to define what an inline xattr is and when storing...
- 01:43 PM Revision 7abba7b1 (ceph): rgw/rgw_cors.cc: fix inefficient usage of string::find()
- Fix warning from cppcheck:
[src/rgw/rgw_cors.cc:70]: (performance) Inefficient usage of
string::find() in condition... - 12:52 PM Revision eb815bb0 (ceph): rgw/rgw_cors.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:47 PM Revision 54797237 (ceph): rgw/rgw_cors.cc: use empty() instead of size() == 0
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:43 PM Revision e1babf47 (ceph): rgw/rgw_bucket.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:42 PM Revision c9be9fff (ceph): rgw/rgw_bucket.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:41 PM Revision 42109d31 (ceph): rgw/rgw_user.h: initialize some bool variables in constructor
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:39 PM Revision a5ce2461 (ceph): rgw/rgw_user.h: move initialization in initialization list
- Move initialization of some variables from constructor body to
the initialization list.
Signed-off-by: Danny Al-Gaaf... - 12:24 PM Revision 9b5f8a4f (ceph): rbd.cc: use static_cast instead of C-Style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:01 PM Revision 07be36c9 (ceph): mds/Migrator.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:49 AM CephFS Documentation #2206: Need a control command to gracefully shutdown an active MDS prior to planned...
- This is partially documented by 0c16b31db7a5ed72a9c306ae91b191c326d0776a on github.
- 11:21 AM Bug #4624: crush_ops failure
- I think the problem here is that many/most of the crush ops aren't framed to be idempotent.. they do things like retu...
- 10:49 AM Bug #4624 (Resolved): crush_ops failure
- "name": "b",
"addr": "10.214.132.18:6789\/0"},
{ "rank": 1,
... - 11:10 AM Revision 574051f8 (ceph): unit tests for FileStore::_detect_fs when running on ext4
- unit tests are added in test/filestore/store_test.cc for the
FileStore::_detect_fs method, when using ext4. It tests ... - 11:07 AM Revision aee65491 (ceph): fix nspace assignment in LFNIndex::lfn_parse_object_name
- The unused ns variable is assigned to the nspace data member of the
parsed hobject_t. It would be nicer to use a cons... - 11:05 AM Bug #4627 (Resolved): ReplicatedPG: ooo sub op
- -3> 2013-04-01 14:11:17.935826 7fe1427fc700 5 --OSD::tracker-- reqid: client.4131.0:27330, seq: 66006, time: 201...
- 11:02 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- I started all OSDs with "debug ms = 1" since it seems like this is messenger related.
It will take some time (days... - 08:47 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- So I had all my OSDs in this cluster go down again.
It's a 3 node cluster with 12 OSDs in total, see all the times... - 10:49 AM Bug #4623: rados api test failure, snapshots
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-01_12:48:27-rados-master-testing-basic/7623
- 10:47 AM Bug #4623 (Resolved): rados api test failure, snapshots
- 2013-04-01T13:06:53.729 INFO:teuthology.task.workunit.client.0.out:[ OK ] LibRadosSnapshots.SelfManagedRollback...
- 09:44 AM Linux kernel client Bug #4614: Root cephfs does not mount at boot on Ubuntu 12.04
- Yes Sage,
I've tried with no success.
I've wrote to mailing list too and Igor Laskovy has confirmed the issue.
htt... - 09:36 AM Linux kernel client Bug #4614 (Need More Info): Root cephfs does not mount at boot on Ubuntu 12.04
- Can you try putting 'netdev' as an option in fstab? That will make it mount after networking has started.
- 05:42 AM Linux kernel client Bug #4614 (Can't reproduce): Root cephfs does not mount at boot on Ubuntu 12.04
- This line does not produce a mount at boot
192.168.21.11:6789,192.168.21.13:6789,192.168.21.12:6789:/ /mnt/ceph ceph... - 09:35 AM Documentation #4617 (Resolved): explain what an inline xattr is and how it relates to omap
- commit:6072f8f
- 06:53 AM Documentation #4617 (Resolved): explain what an inline xattr is and how it relates to omap
- The logic of the "configuration flags related to xattr":https://github.com/ceph/ceph/blob/724d5aaa3bf7e95075176582aa4...
- 09:31 AM devops Feature #4367: ceph-deploy: if host is localhost, don't use ssh but run commands directly
- Branch wip-4367 has a possible workaround by overriding the local transport __init__. There is probably a better way...
- 08:36 AM Bug #4620 (Resolved): mon: Paxos proposals take too long to finish when transaction is huge
- Jim Schutt reported on ceph-devel that a Paxos proposal (on 0.59) was taking about a minute to finish (http://thread....
- 07:00 AM Bug #4616 (Fix Under Review): libceph: define ceph_decode_pgid() only once
- The following has been posted for review:
[PATCH] libceph: define ceph_decode_pgid() only once
This is really a... - 06:36 AM Bug #4616 (Resolved): libceph: define ceph_decode_pgid() only once
- There are two basically identical definitions of __decode_pgid()
in libceph, one in "net/ceph/osdmap.c" and the othe... - 06:36 AM Bug #4615 (Fix Under Review): libceph: drop mutex on error in handle_reply()
- The following has been posted for review:
[PATCH] libceph: drop mutex on error in handle_reply()
- 06:33 AM Bug #4615 (Resolved): libceph: drop mutex on error in handle_reply()
- The osd client mutex is acquired just before getting a reference to
a request in handle_reply(). However the error ... - 03:46 AM Revision 7b3973ff (ceph): radosgw-admin: cluster info -> zone info
- Signed-off-by caleb.miles <caleb.miles@inktank.com>
- 01:44 AM Revision dd19d693 (ceph): rgw: Create RESTful endpoint for user and bucket administration.
- Expose the following operations through a RESTful endpoint:
user create
user modify
user remove
subus... - 01:17 AM Revision aa14da20 (ceph): doc/release-notes: v0.60
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:57 AM Revision 6ffadce6 (ceph): Merge branch 'next'
04/01/2013
- 11:38 PM Revision d81babff (ceph): repair_test: add test for repairing read errs and truncations
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 11:37 PM Revision 502e4397 (ceph): repair_test: add test for repairing read errs and truncations
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:32 PM Revision f861d54c (ceph): Merge pull request #181 from ceph/wip_4510
- Scrub/repair should correctly handle truncation and EIO
Fixes #4510
Reviewed-by: Greg Farnum <greg@inktank.com>
Revi... - 11:27 PM Revision 40070cef (ceph): PG: _scan_list can now handle EIO on read, stat, get_omap_header
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:27 PM Revision 3fa3b676 (ceph): FileStore: rename debug_delete_obj to debug_obj_on_delete
- This should make the method intent less confusing.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 11:27 PM Revision fc13f111 (ceph): PG::_scan_list: assert if error is neither -EIO nor -ENOENT
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:27 PM Revision fcec1a06 (ceph): ObjectStore: add allow_eio to read, stat, get_omap_header
- This will allow enlightened callers to handle EIO.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:57 PM Revision 0e1f5042 (ceph): Merge pull request #183 from ceph/wip-4313-b
- qa: workunits: mon: test 'config-key' store
Reviewed-by: Sage Weil <sage@inktank.com> - 10:56 PM Revision 8b49eb19 (ceph): rados: test mon config keys
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:35 PM Revision 76ad9563 (ceph): librados: test empty ObjectWriteOperation
- Tests that #2673 is fixed.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:56 PM Revision 15bd9802 (ceph): Merge pull request #182 from ceph/wip-no-cors-without-rgw
- Makefile.am: disable building ceph_test_cors when radosgw is not enabled
- 09:43 PM rgw Feature #4613 (Resolved): Allow bucket data to reside in a separate pool to object data
- As an adminstrator, I want to allow the data about the contents of a bucket to be served from a SSD pool while leavin...
- 09:05 PM Revision 690e4df1 (ceph): Makefile.am: disable building ceph_test_cors when radosgw is not enabled
- This test depends on radosgw. Trying to build it without radosgw will
result in a compile error.
Signed-off-by: Josh... - 08:38 PM Fix #4612 (Resolved): unit_to_bytesize(), si_t, prettybyte_t use 'K' for kilo; SI recommends 'k'
- It's a pet peeve, but the abbreviation for "kilo" (or "kibi") is 'k', not 'K'.
I'm happy with making it both, but we... - 08:35 PM Feature #4611 (Duplicate): cephtool: set-quota, no get-quota
- Seems like we'd want a query interface for the new pool quotas; it seems easy
enough to add. - 07:22 PM Revision f26f7a39 (ceph): v0.60
- 06:52 PM Revision db7a0950 (ceph): Merge remote-tracking branch 'gh/next'
- 06:26 PM Revision 557685f3 (ceph): Merge pull request #169 from ceph/wip-rbd-diff
- rbd incremental backup/restore
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:17 PM Revision 267ce0d9 (ceph): librados: don't use lockdep for AioCompletionImpl
- This is a quick workaround for the next branch. A more complete fix
will be done for the master branch. This does not... - 05:04 PM Revision 78acc5c2 (ceph): test: fix signed/unsigned comparison in test_cors
- Signed-off-by: Greg Farnum <greg@inktank.com>
Acked-by: Sage Weil <sage@inktank.com> - 04:48 PM Bug #2476 (Fix Under Review): osd: watch timeout depends on operations to an object
- wip_2476
- 04:38 PM Revision d5b79702 (ceph): PG: don't compare auth with itself
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:38 PM Revision 1940cf3e (ceph): FileStore,OSD: add mechanism for injecting EIO, truncating obj
- This will be used in testing repair.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:38 PM Revision a838965c (ceph): PG: read_error should trigger a repair in _compare_scrub_objects
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:38 PM Revision 39d1a3fb (ceph): PG: pass authoritative scrub map to _scrub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:38 PM Revision 83dbfaea (ceph): PG::_select_auth_object: prefer a peer which did not hit a read error
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:38 PM Revision e61c94e2 (ceph): PG: make _select_auth_object smarter
- Previously, we just picked the first one to have the object in
question. Now, we will attempt to choose one that has... - 04:33 PM Feature #4510 (Resolved): OSD scrub/repair should handle read error and truncate reasonably
- 04:31 PM Revision 5d11c201 (ceph): Merge branch 'wip-mds'
- 04:27 PM Revision a77eaec8 (ceph): mds: bump the protocol version.
- We've changed quite a lot of the restart behavior, as well as one
of the message encodings. This is cheaper and easie... - 04:26 PM Revision 7278f644 (ceph): mds: fix export cancel notification
- The comment says that if the importer is dead, bystanders thinks the
exporter is the only auth, as per mdcache->handl... - 04:26 PM Revision fcf170b8 (ceph): mds: notify bystanders if export aborts
- So bystanders know the subtree is single auth earlier.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by... - 04:26 PM Revision d1602b3b (ceph): mds: don't open dirfrag while subtree is frozen
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 5ceae8ca (ceph): mds: clear dirty inode rstat if import fails
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 9939ced4 (ceph): mds: try merging subtree after clear EXPORTBOUND
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 44db9802 (ceph): mds: eval inodes with caps imported by cache rejoin message
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 3d3d85d8 (ceph): mds: don't replicate purging dentry
- open_remote_ino is racy, it's possible someone deletes the inode's
last linkage while the MDS is discovering the inod... - 04:26 PM Revision 2b0f03cb (ceph): mds: clear scatter dirty if replica inode has no auth subtree
- This avoids sending superfluous scatterlock state to recovering MDS
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com... - 04:26 PM Revision 93ab1edd (ceph): mds: don't roll back prepared table updates
- When table server is recovering, it re-sends 'agree' messages for
prepared table updates. It is possible table client... - 04:26 PM Revision b2342a9c (ceph): mds: take object's versionlock when rejoinning xlock
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 10b1a566 (ceph): mds: share inode max size after MDS recovers
- The MDS may crash after journaling the new max size, but before sending
the new max size to the client. Later when th... - 04:26 PM Revision 7ad7c347 (ceph): mds: issue caps when lock state in replica become SYNC
- because client can request READ caps from non-auth MDS.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-b... - 04:26 PM Revision a4ed7ea8 (ceph): mds: send lock action message when auth MDS is in proper state.
- For rejoining object, don't send lock ACK message because lock states
are still uncertain. The lock ACK may confuse o... - 04:26 PM Revision e072d34f (ceph): mds: add dirty imported dirfrag to LogSegment
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision b4395889 (ceph): mds: avoid double auth pin for file recovery
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 4d532cb6 (ceph): mds: check MDS peer's state through mdsmap
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 27438db5 (ceph): mds: unfreeze subtree if import aborts in PREPPED state
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:26 PM Revision 6862fe7a (ceph): mds: reqid for rejoinning authpin/wrlock need to be list
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 04:25 PM Revision d1a25749 (ceph): mds: handle linkage mismatch during cache rejoin
- For MDS cluster, not all file system namespace operations that impact
multiple MDS use two phase commit. Some operati... - 04:24 PM Revision ce0b74e5 (ceph): mds: encode dirfrag base in cache rejoin ack
- Cache rejoin ack message already encodes inode base, make it also encode
dirfrag base. This allowes the message to re... - 04:22 PM Revision 4f844050 (ceph): Merge pull request #179 from ceph/wip-client-cond
- client: always remove cond from list after waiting
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:22 PM Revision 9f66d045 (ceph): mds: include replica nonce in MMDSCacheRejoin::inode_strong
- So the recovering MDS can properly handle cache expire messages.
Also increase the nonce value when sending the cache... - 04:21 PM Revision cbb38a1c (ceph): mon: OSDMonitor: only output warn/err messages if quotas are set > 0
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:17 PM Revision 13127165 (ceph): mds: unify slave request waiting
- When requesting remote xlock or remote wrlock, the master request is
put into lock object's REMOTEXLOCK waiting queue... - 04:17 PM Revision a6d9eb8c (ceph): mds: don't delay processing replica buffer in slave request
- Replicated objects need to be added into the cache immediately
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Rev... - 04:17 PM Revision 30dbb1d4 (ceph): mds: compose and send resolve messages in batch
- Resolve messages for all MDS are the same, so we can compose and
send them in batch.
Signed-off-by: Yan, Zheng <zhen... - 04:17 PM Revision ed85dd61 (ceph): mds: don't send resolve message between active MDS
- When MDS cluster is resolving, current behavior is sending subtree resolve
message to all other MDS and waiting for a... - 04:17 PM Revision e381bb39 (ceph): mds: set resolve/rejoin gather MDS set in advance
- For active MDS, it may receive resolve/rejoin message before receiving
the mdsmap message that claims the MDS cluster... - 04:17 PM Revision 97bc0d26 (ceph): mds: don't send MDentry{Link,Unlink} before receiving cache rejoin
- The active MDS calls MDCache::rejoin_scour_survivor_replicas() when it
receives the cache rejoin message. The functio... - 04:17 PM Revision 75346d8f (ceph): mds: send cache rejoin messages after gathering all resolves
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:17 PM Revision 3ab86637 (ceph): mds: send resolve acks after master updates are safely logged
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 04:17 PM Revision e62e48bb (ceph): mds: fix MDS recovery involving cross authority rename
- For mds cluster, rename operation may involve multiple MDS. If the
rename source's auth MDS crashes after some witnes... - 04:17 PM Revision 01fd55a6 (ceph): mds: remove MDCache::rejoin_fetch_dirfrags()
- In commit 77946dcdae (mds: fetch missing inodes from disk), I introduced
MDCache::rejoin_fetch_dirfrags(). But it bas... - 04:17 PM Revision ef9a4f66 (ceph): mds: defer eval gather locks when removing replica
- Locks' states should not change between composing the cache rejoin ack
messages and sending the message. If Locker::e... - 04:16 PM Revision 12e7c3d1 (ceph): mds: avoid sending duplicated table prepare/commit
- This patch makes table client defer sending table prepare/commit messages
until receiving table server's 'ready' mess... - 04:16 PM Revision a5dce808 (ceph): mds: make sure table request id unique
- When a MDS becomes active, the table server re-sends 'agree' messages
for old prepared request. If the recoverd MDS s... - 04:16 PM Revision bb83a5d6 (ceph): mds: consider MDS as recovered when it reaches clientreplay state.
- MDS in clientreplsy state already starts servering requests. It also
make MDS::handle_mds_recovery() and MDS::recover... - 04:12 PM Revision 78268140 (ceph): client: always remove cond from list after waiting
- The signal method removes conds from the list after it signals. That's
not okay if the cond triggers for some other ... - 03:58 PM Revision 8267bf56 (ceph): librbd: fix size arg type for diff_iterate
- Fixes build on 32-bit archs.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:56 PM Revision c680531e (ceph): librbd: change diff_iterate interface to be more C-friendly
- Use int instead of bool for the callback, and make it represent
whether the data exists, rather than the opposite, si... - 03:56 PM Revision 6a04a7fa (ceph): rbd: initialize random number generator for bench-write
- Without this, the same seed is used each time, so multiple runs
of bench-write with the same parameters have the same... - 03:56 PM Revision 33d1a2fc (ceph): librbd: return -ENOENT from diff_iterate when the snap doesn't exist
- This is a bit more helpful than -EINVAL.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 03:56 PM Revision 52097d34 (ceph): rbd: add formatted output to diff command
- All the other commands that display information have this.
For consistency, add it to this command too.
Also switch ... - 03:56 PM Revision e83fd3b9 (ceph): librados: don't insert zero length extents in a diff
- They're useless, and trigger an assert in interval_set::inesrt.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 03:56 PM Revision c0e3f642 (ceph): librbd: add C and python bindings for diff_iterate
- The python interface is a bit awkward since it maps directly
to the C interface, but it'll work well enough and not u... - 03:56 PM Revision e88fe3cb (ceph): rbd.py: add some missing functions
- discard, flush, and striping info slipped through the cracks before,
but are useful and trivial to add.
Signed-off-b... - 03:56 PM Revision f1f64072 (ceph): test_librbd: add diff_iterate test including discard
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 03:56 PM Revision b2b1034c (ceph): PendingReleaseNotes: note about rbd progress output
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 03:56 PM Revision d86fb04f (ceph): rbd: make diff banner length depend on the banner
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 03:56 PM Revision 8a1cbf3e (ceph): rbd: remove alway-true else condition in import-diff
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 03:54 PM Revision c499caf5 (ceph): mkcephfs: warn that mkcephfs is deprecated in favor of ceph-deploy
- Signed-off-by: Neil Levine <neil.levine@inktank.com>
- 03:48 PM Revision 3b5f663f (ceph): Merge pull request #178 from ceph/wip-client
- Fix client with cache disabled, and a use-after-free
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 03:35 PM Bug #2673 (Resolved): ReplicatedPG::prepare_transaction: don't crash on empty ops
- added a test, commit:76ad956330048fd2c89e7575acfec0bc7d775f3b
- 03:24 PM Bug #3395 (Closed): ceph osd pool set/get
- 03:22 PM Bug #3440: Running OSDs on ZFS on Linux
- Hey Wido,
Want to give this a go with the latest code? It would be nice to make this work, at least in a basic way! - 03:22 PM Bug #3429 (Resolved): osd: failed assert(oe.soid.snap != ((__u64)(-2)))
- 03:21 PM Bug #3408 (Resolved): scrub encounters object with missing snapset
- 03:21 PM Bug #3379 (Won't Fix): rbd map + rbd mv: couldn't remove old source object
- 03:20 PM Bug #3386 (Resolved): #7 ReplicatedPG::add_object_context_to_pg_stat (this=0x8654000, obc=0xe34...
- 03:18 PM CephFS Bug #3266: "ceph mds tell 0 dumpcache /etc/passwd" is not cool
- Before anybody embarks on solving this, I assume there's a standard way to handle this by outlawing certain kinds of ...
- 03:16 PM Bug #3041 (Resolved): ceph manager down during osd recovery
- 03:16 PM Bug #3269 (Closed): nightly failure-kclient_workunit_suites_fsstress
- 03:14 PM Bug #3238 (Resolved): ceph-client: osd BUG_ON() tripped
- 03:14 PM Bug #3214 (Resolved): osdmaptool's usage is incomplete
- 03:11 PM Revision 677867d0 (ceph): qa: workunits: mon: test 'config-key' store
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:06 PM Bug #4357 (Need More Info): osd: FAILED assert("join on thread that was never started" == 0)
- 03:00 PM rgw Bug #4609 (Resolved): ceph_test_cors build when --without-radosgw configured
- commit:690e4df19a209037ea9bcc2b981fbe797fbd8ec4
- 02:38 PM rgw Bug #4609 (Resolved): ceph_test_cors build when --without-radosgw configured
- ceph_test_cors depends on radosgw.
- 02:53 PM Bug #3720 (Duplicate): Ceph Reporting Negative Number of Degraded objects
- 02:46 PM Bug #4487 (Duplicate): osd: FAILED assert(0 == "FileJournal::read_entry(): corrupt journal")
- 02:44 PM Bug #4254 (Need More Info): osd: failure to recover before timeout on rados bench and thrashing; ...
- 02:42 PM Bug #4579 (In Progress): kclient + ffsb workload makes osds mark themselves down
- 02:26 PM Bug #4608 (Resolved): Incorrect RGW apache conf example
- The example VirtualHost in our RGW quick-start docs didn't work for me. I had to move the rewrite rule into the virt...
- 01:38 PM devops Bug #4571: el6: RGW init script failure
- Gary - please review this
- 01:31 PM devops Feature #4468: ceph-deploy: log everything locally
- commit:fa5678d64a0c8946c1cf65921446e30440dd5c2b
- 01:23 PM CephFS Bug #2657: kclient: direct io write larger than 8MiB fails
- in testing, there is now a test workunit
- 01:23 PM CephFS Bug #2657 (Resolved): kclient: direct io write larger than 8MiB fails
- 01:22 PM CephFS Bug #4434 (Resolved): looping waiting for quorum after upgrade
- Whoops@!
- 01:14 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- I'll look into the code around this today.
- 12:52 PM devops Feature #3347: ceph-deploy: allow setting ssh user
- This item ought to include the local priv user as well; do_root_cmd and rootssh from ceph_common.sh handle most of th...
- 12:48 PM rgw Feature #4606 (Rejected): Support s3cmd list buckets
- The s3cmd package works well with rgw but does not support the bare "s3cmd ls" command for listing buckets.
- 12:41 PM Bug #4595 (Resolved): lockdep error in rados_aio_flush_async()
- commit:267ce0d90b8f3afaaddfdc0556c9bafbf4628426
- 12:07 PM Bug #4596 (Resolved): broken ipmi on plana48
- Something went wrong when the inktank user got setup on this machine. Probably some dropped IPMI commands. I fixed it...
- 11:56 AM rbd Bug #4531 (In Progress): ObjectCacher: read waiters for parent data during copyup get reordered, ...
- 11:55 AM rbd Bug #2608: rbd: hung xfstest 270
- Test 270 now doesn't run because:
270 [not run] fsgqa user not defined.
There are a few tests that require a... - 11:34 AM rbd Bug #2608: rbd: hung xfstest 270
- Trying to run 270 right now.
- 11:30 AM rbd Bug #2608: rbd: hung xfstest 270
- TODO: Try xfstests #270 on recent kernel (current testing
should be fine). - 11:54 AM rbd Feature #4605 (Duplicate): rbd xfstests: define qa user, group, etc.
- Some xfstests require a designated user (and as I recall
a group too) in order to run. I think one example of this
... - 11:48 AM rbd Bug #3701 (Can't reproduce): qemu xfstest hung BUG: unable to handle kernel NULL pointer derefere...
- 11:47 AM rbd Fix #3588: rbd.py's clone should take stripe parms, call rbd_clone2
- 11:47 AM rbd Bug #3871: krbd: initial header read may be out of date
- 11:46 AM Bug #4599: ceph auth import -i <file> is broken
- The mutex issue was my new code. The bug is simply that import should be reenabled.
- 11:26 AM rbd Feature #4444 (Resolved): send/receive rbd snapshots
- 11:26 AM rbd Feature #4084 (Resolved): rbd: incremental backups
- 11:26 AM rbd Feature #4445 (Resolved): librbd: expose changed objects since a given snapshot
- 11:03 AM CephFS Bug #4489: ceph fs hangs on file stat
- Why are you specifying the snapdirname to that weird value when mounting this?
- 11:00 AM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- This dump has 1063591 inodes in the cache, of which only 122104 are non-stray. That doesn't seem quite right.
I do... - 10:14 AM RADOS Feature #4604 (New): osd: read path should detect EIO and initiate repair
- 10:07 AM devops Feature #4546 (Resolved): mkcephfs: add DEPRECATED warnings to all stdout user interactions
- 09:37 AM CephFS Bug #4590 (Resolved): ceph-fuse: fsx fails with 'client oc = false'
- commit:c01e2e42f368ca003e03debe9a7bd5f12eb79d2c
- 09:34 AM Bug #4597 (Fix Under Review): nspace is ignored by LFNIndex::lfn_parse_object_name
- 09:34 AM rgw Bug #4600: rgw: list bucket broken when marker start with underscore
- Is there a new test in S3 tests that verifies this?
- 09:33 AM rgw Bug #4600 (Fix Under Review): rgw: list bucket broken when marker start with underscore
- 09:26 AM rbd Bug #4540 (Resolved): libceph: problem in ceph_osdc_msg_data_set
- 09:21 AM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- It's possible the maximum number of pages we'll ever need
is PAGEVEC_SIZE. But I'm not going to spend any time righ... - 08:50 AM Bug #4603 (Fix Under Review): ceph: writeback pagevec pool is created incorrectly
- The following patch has been posted for review, to
address the two simple problems initially described
in this issu... - 08:42 AM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- I forgot to mention, the other problem is that the number
of pages required in ceph_writepages_start() is computed
... - 08:08 AM Bug #4603 (Resolved): ceph: writeback pagevec pool is created incorrectly
- In ceph_writepages_start() if there are any pages to write back
an array of page pointers is needed, sufficient to h... - 09:17 AM Bug #4598 (Resolved): kernel messenger: fix bogus asserts
- 06:32 AM Revision a0fca080 (ceph): rbd: fix else style in import-diff
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:32 AM Revision 09898ffd (ceph): rbd: complete progress for import-diff from stdin
- The diff format gives us a size, so unlike a normal import, we do update progress.
Signed-off-by: Josh Durgin <josh.... - 06:32 AM Revision c0e5c22d (ceph): rbd: fail import-diff if we reach the end of the stream sooner than exp...
- safe_read() just protects against EINTR, and may return less data than
requested if it reaches the end of the file. U... - 06:32 AM Revision 186ddda5 (ceph): rbd: send import debug noise to dout, not stdout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 4d02e17f (ceph): librbd: handle diff from clone
- If we have a parent image, and the reference is from snap 0 (beginning of
time) we need to look at the diff on the pa... - 06:32 AM Revision fc3f4fda (ceph): rbd: implement simple 'diff' command
- Report extents allocated/changed, and whether they contain data or zeros.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision f2b0880a (ceph): qa: rbd/diff_continuous.sh: base test off a clone
- Get a bit of coverage on clones by starting with a clone.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision 39689fea (ceph): librbd: fix diff_iterate arithmetic for non-standard striping
- This code is confusing because we are moving back and forth between
image offsets, "buffer" offsets (image offsets re... - 06:32 AM Revision 44e295a3 (ceph): qa: rbd/diff_continuous.sh: use non-standard striping
- Exercise the striping arithmetic by using non-standard striping that
varies between the parent and child.
Signed-off... - 06:32 AM Revision 7bbaa71a (ceph): doc/dev/rbd-diff: update incremental file format
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision d0baadb9 (ceph): librbd: uint64_t len for diff_iterate
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision a69532e8 (ceph): librbd: document diff_iterate in header
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision f0c9a200 (ceph): librbd: diff_iterate fromsnapname after the end snap is also invalid
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision be8927f5 (ceph): librbd: drop unused elapsed calc for diff_iterate
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 10dc0ad0 (ceph): librados: document list_snaps
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 6af769a1 (ceph): librados: cleanly define SNAP_HEAD, SNAP_DIR constants
- We were using the internal CEPH_NOSNAP and CEPH_SNAPDIR constants, and
defining a clone_info_t::HEAD (with a differen... - 06:32 AM Revision c5bd978a (ceph): librados: move snap_set_diff to librados/
- This is most closely related to the librados list_snaps API; move it there.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision 3694968a (ceph): librbd: implement image.snap_exists()
- This is a much more convenient way to tell if a snapshot already exists.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision 5b0c68b9 (ceph): doc/dev/rbd-diff: specify that metadata records come before data
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 9946c69c (ceph): rbd: fail import-diff if end snap already exists
- This will prevent a user from inadvertantly reapplying a diff twice.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision f67f62ab (ceph): rbd: prevent import-diff if start snapshot is not already present
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 64a202a7 (ceph): rbd: update man page for import-diff and export-diff
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 325a3372 (ceph): rbd: include 'diff' command in man page
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 88706ab8 (ceph): rbd: send progress info to stderr, not stdout
- This avoids interfering when export is sent to stdout.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision ef493859 (ceph): rbd: fix size change output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision f0ddf6cc (ceph): rbd: remove unused argument from do_diff()
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:32 AM Revision 2ec87e66 (ceph): rbd: update progress as a diff is exported
- This will be jumpy since changed extents probably aren't evenly
distributed, but it's better than nothing.
Signed-of... - 06:32 AM Revision 849a45c6 (ceph): strings: add 'list-watchers' to MOSDOp strings
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision fa5206ce (ceph): osd: make LIST_WATCHERS and LIST_SNAPS print nicely for OSDOp
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 00742289 (ceph): osd: include SnapSet seq in the list snaps response
- It is important to know the latest seq that the object has seen in order
to tell if a response like
clone 2 snaps=[... - 06:32 AM Revision 01b74209 (ceph): osd: clean up some whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision b64bb5f8 (ceph): osd: do not include snaps with head on list_snaps()
- If there is a sequence of snaps 1, 2, 3, 4, 5, and we have a clone
2 with [1,2], and the head reflects content at sna... - 06:32 AM Revision 556d3344 (ceph): osd: direct reads on SNAPDIR to either head or snapdir
- The list_snaps operation needs to look at the SnapSet, and is logically
querying all revisions of the object. Make r... - 06:32 AM Revision ceee218f (ceph): osd: wait for all clones on SNAPDIR requests
- Wait for all clones to be present.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision 941cfc26 (ceph): osd: fix clone snap list for list-snaps
- We need to return the list of snaps that each clone is defined for, not
the list of snaps we know may or may not exis... - 06:32 AM Revision 4ae97743 (ceph): osd: fix error codes for list-snaps
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision ebed0000 (ceph): osdc/Objecter: prval optional for listsnaps
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 6db51091 (ceph): librados: expose snapset seq via list_snaps
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:32 AM Revision 0296c7cd (ceph): librbd: implement diff_iterate
- Implement a diff_iterate() method that will iterate over an image and
report which extents vary between two snapshots... - 06:32 AM Revision cf7d13a7 (ceph): rbd: add --io-pattern <seq|rand> option to bench-write
- Write to random offsets instead of sequentially.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 AM Revision e7167433 (ceph): rbd: implement 'export-diff' and 'import-diff' commands
- Export a diff of an image from a previous snapshot to a file (or stdout).
Import a diff and apply it to an image, an... - 06:32 AM Revision 58c2dedd (ceph): qa: add rbd/diff_continuous.sh stress test
- Stress test that does io on an image while we are mirroring a diff from
earlier snaps to a second copy. At the end, ... - 06:23 AM Revision 945ead5a (ceph): Merge remote-tracking branch 'gh/wip-cors-rebased'
- Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:51 AM Revision e9e86ad1 (ceph): rgw: cors, style fixes, other fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:51 AM Revision d4b22f3e (ceph): rgw: more cors fixes
- Remove the check for read_cors_config in rgw_main.cc, and changes type of 'a' to unsigned from long as max_age cannot...
- 04:51 AM Revision e1a78f98 (ceph): rgw: fix a few warnings
- Adjust data types
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:51 AM Revision 3c52b8bb (ceph): Makefile.am: change some cors rules
- The cors unitest should be a standalone test (not part of the make
unitests) as it requires having a running gateway ... - 04:51 AM Revision 01779df1 (ceph): rgw: add missing include file
- Add missing limits.h, needed for ULONG_MAX.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:51 AM Revision a2956f6f (ceph): rgw: fix warning
- On a 64-bit arch, we still want to make sure it's a 32-bit value. Gcc is
too smart for us to just cast; it will stil... - 04:51 AM Revision f165049c (ceph): rgw: with CORS support
- With CORS test cases
1. Added license headers to the cors files
2. SIWFT POST metadata for cors will replace the old... - 04:44 AM Revision c01e2e42 (ceph): client: do sync read when 'client oc = false'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:43 AM Revision 74c70836 (ceph): client: fix use-after-free on session close and cond signals
- Move the signal into the closed method, before we deallocate the
MetaSession, so that other callers catch it too.
Si...
03/31/2013
- 09:15 PM Bug #4602 (Can't reproduce): osd/ReplicatedPG.cc: 6487: FAILED assert(latest->is_update())
- ...
- 09:13 PM Bug #2691 (Won't Fix): osd/ReplicatedPG.cc: 5888: FAILED assert(latest->is_update())
- this is pre-argonaut
- 07:46 PM Bug #4598: kernel messenger: fix bogus asserts
- I ran several passes through a bunch of fs
tests over the last day or so and there are
no more assertions triggered... - 05:26 PM Bug #4595 (Fix Under Review): lockdep error in rados_aio_flush_async()
- This is a false positive since lockdep wasn't tracking individual instances of locks. Different AioCompletion locks w...
- 02:43 PM Bug #4594 (Resolved): null character in object name triggers segfault
- 01:10 PM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Thanks for your great work! Is there already a way / branch to test this with bobtail?
- 10:33 AM CephFS Bug #4601 (Can't reproduce): symlink with size zero
- Somehow I got into a situation in which a number of symlinks, all of them created and later modified at about the sam...
- 08:57 AM Revision 5cbaae66 (ceph): mds: preserve subtree bounds until slave commit
- When replaying an operation that rename a directory inode to non-auth subtree,
if the inode has subtree bounds, we sh... - 08:57 AM Revision 573a4ae1 (ceph): mds: process finished contexts in batch
- If there are several unstable locks in an inode, current Locker::eval(CInode*,)
processes each lock's finished contex... - 08:57 AM Revision fbcc64df (ceph): mds: fix MDCache::adjust_bounded_subtree_auth()
- There are cases that need both create new bound and swallow intervening
subtree. For example: A MDS exports subtree A... - 08:57 AM Revision 4ad35b2a (ceph): mds: mark connection down when MDS fails
- So if the MDS restarts and uses the same address, it does not get
old messages.
Signed-off-by: Yan, Zheng <zheng.z.y... - 01:22 AM Revision ce8793ce (ceph): Merge pull request #175 from dachary/wip-4594
- fix null character in object name triggering segfault
Reviewed-by: Sage Weil <sage@inktank.com>
03/30/2013
- 11:57 PM rgw Bug #4600 (Resolved): rgw: list bucket broken when marker start with underscore
- 10:02 PM Bug #4598: kernel messenger: fix bogus asserts
- The following has been posted for review:
[PATCH] libceph: account for alignment in pages cursor
Also, the previo... - 09:55 PM Bug #4598: kernel messenger: fix bogus asserts
- One more assertion failure. This one again is a correct
assertion so it's found another real problem in the code.
... - 01:14 PM Bug #4598: kernel messenger: fix bogus asserts
- OK, another assertion failure, but this one caught a problem.
ceph_msg_data_pages_advance() was allowing the page_... - 12:43 PM Bug #4598: kernel messenger: fix bogus asserts
- My initial tests of my fix did not produce the same crash, so
I posted that for review. Now, after a bit longer tho... - 11:44 AM Bug #4598: kernel messenger: fix bogus asserts
- I haven't posted this for review yet, I want to test it first.
[PATCH] libceph: fix broken data length assertion... - 11:42 AM Bug #4598 (Resolved): kernel messenger: fix bogus asserts
- Sage informed me of four crashes in nightly tested last night.
I believe they are due to an erroneous assertion. ... - 05:45 PM Bug #4596: broken ipmi on plana48
- also, alex said on ceph-qa:...
- 05:44 PM Bug #4596 (In Progress): broken ipmi on plana48
- Actually.. hmm. IIRC 6233 also errored out with the same message. After the first error, it should have nuked the n...
- 05:43 PM Bug #4596 (Closed): broken ipmi on plana48
- Makes sense!
- 12:46 PM Bug #4596: broken ipmi on plana48
- IPMI looks ok on that machine however from the error message it had a problem getting 'IPMI console'. Just a guess (a...
- 09:19 AM Bug #4596 (Resolved): broken ipmi on plana48
- ubuntu@teuthology:/a/teuthology-2013-03-30_01:00:05-rados-next-testing-basic
6232/summary.yaml:failure_reason: 'IP... - 03:27 PM Bug #4599 (Resolved): ceph auth import -i <file> is broken
- Digging into history, but: it's not ruled out by preprocess_command, and so never gets to
the code in handle_command... - 01:28 PM Revision c344ff17 (ceph): fix null character in object name triggering segfault
- Parsing \n in lfn_parse_object_name is implemented with
out->append('\0');
which segfaults when using libstdc++ ... - 10:02 AM Bug #4597 (Resolved): nspace is ignored by LFNIndex::lfn_parse_object_name
- "work in progress":https://github.com/dachary/ceph/commit/wip-4597
When the *abababab.KEY/.\0A/B_\C.D/head/NSPACE/... - 09:24 AM Bug #4527: journal Unable to read past sequence 0 but header indicates the journal has committed ...
- ubuntu@teuthology:/a/teuthology-2013-03-30_01:00:30-rbd-next-testing-basic/6357
- 09:17 AM Bug #4527: journal Unable to read past sequence 0 but header indicates the journal has committed ...
- ubuntu@teuthology:/a/teuthology-2013-03-30_01:00:05-rados-next-testing-basic/6250
- 09:13 AM Bug #4527: journal Unable to read past sequence 0 but header indicates the journal has committed ...
- ubuntu@teuthology:/a/teuthology-2013-03-30_01:00:05-rados-next-testing-basic/6231
- 09:17 AM Bug #4595 (Resolved): lockdep error in rados_aio_flush_async()
- ...
- 06:12 AM Bug #4594: null character in object name triggers segfault
- There is no append(charT) method in C++98 or C++11, which means it relies on an implicit conversion that is bugous. I...
- 05:31 AM Bug #4594 (Resolved): null character in object name triggers segfault
- "work in progress":https://github.com/dachary/ceph/commit/wip-4594
Parsing \n in "lfn_parse_object_name":https://... - 01:04 AM Revision b4a276e6 (ceph): rados: test pool quotas when testing api
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:02 AM Revision 2b8eb31b (ceph): Merge branch 'wip-4490'
- 12:59 AM Revision e611937f (ceph): mon: OSDMonitor: add 'osd pool set-quota' command
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:38 AM Revision 95328089 (ceph): doc: Added entries for Pool, PG, & CRUSH. Moved heartbeat link.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:38 AM Revision bcc5c653 (ceph): doc: Added heartbeat configuration settings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:36 AM Revision 6157d683 (ceph): doc: Moved PG info to separate page. Moved heartbeat to mon-osd doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:34 AM Revision ca77aabb (ceph): doc: Rewrote monitor configuration section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:32 AM Revision ea3c833d (ceph): doc: Moved to separate section for parallelism.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:32 AM Revision ba73b830 (ceph): doc: Cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:30 AM Revision e9b3f2e6 (ceph): ceph-disk list: say 'unknown cluster $UUID' when cluster is unknown
- This makes it clearer that an old osd is in fact old.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:05 AM Revision 9e7ddf67 (ceph): config_opts: fix rgw_port comments to be plaintext
- Signed-off-by: Greg Farnum <greg@inktank.com>
03/29/2013
- 11:47 PM Revision 9b090732 (ceph): mon: Monitor: check if 'pss' arg is !NULL on parse_pos_long()
- We already do it all throughout the function, but this one place didn't.
Signed-off-by: Joao Eduardo Luis <joao.luis... - 11:47 PM Revision 3da3129e (ceph): ReplicatedPG: check for full if delta_stats.num_bytes > 0
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:47 PM Revision e2a936d2 (ceph): common: util: add 'unit_to_bytesize()' function
- Converts from a numerical value that may or may not contain an unit
modifier ('1024', '1K', '2M', ..., '1E') and retu... - 11:34 PM Revision 2a1cdda9 (ceph): locker: try to make up for apache timeouts
- If the lock request succeeds in updating the db, but the client gets a
timeout from apache, they can now try again an... - 11:03 PM Revision 23c2fa7f (ceph): osd: osd_types: add pool quota related fields
- 10:06 PM Revision dab3dacf (ceph): osd_types: add read_error flag to Scrubmap::object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:06 PM Revision 655a9508 (ceph): PG::_scan_list: record read errors in the Scrubmap::object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:27 PM Revision aeb1bbe4 (ceph): do not archive on pass if 'archive-on-error: True'
- Optional flag makes us suck down the archive (mostly, the logs, which
might be huge for some debugging tests) unless ... - 09:27 PM Revision a40b850e (ceph): locker: log desc too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:11 PM Bug #4591 (Resolved): test/test_stress_watch.cc:84: Failure
- ...
- 09:05 PM CephFS Bug #4590 (Resolved): ceph-fuse: fsx fails with 'client oc = false'
- ...
- 08:59 PM Revision 562e1716 (ceph): ceph-disk: handle missing journal_uuid field gracefully
- Only lower if we know it's not None.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:22 PM Revision 90544fa3 (ceph): marginal: remove incomplete librbd collection
- Move disabled qemu + iozone task into rbd suite.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:21 PM Revision 9e2ca499 (ceph): marginal: remove partial collection thrash
- Incomplete and broken. The ffsb test is part of the kernel suite now.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:20 PM Revision 95c4a81b (ceph): Merge pull request #170 from ceph/wip-rbd-aio-flush
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 08:20 PM Revision ba4f8de5 (ceph): marginal: add multimds collection
- Lots of stuff here, and several things fail with the export thrashing on,
but usually the others pass.
Signed-off-by... - 08:08 PM Revision 1f3b4917 (ceph): silence logrotate some more
- I was getting email with logrotate error output from “which invoke-rc.d”
on systems without an invoke-rc.d. This pat... - 07:58 PM Revision b504e444 (ceph): Merge remote branch 'origin/next'
- 07:47 PM Revision 4c4d5591 (ceph): librados: move snapc creation to caller for aio_operate
- The common case already has a snapshot context, so avoid duplicating
it (copying a potentially large vector) in IoCtx... - 07:24 PM Revision 43e451f6 (ceph): Merge pull request #166 from ceph/wip-disk-list
- Wip disk list
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 07:19 PM Revision 9f46f47b (ceph): run: clean up machine_type thing
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:14 PM Revision e6eace23 (ceph): Merge remote-tracking branch 'upstream/bobtail-4556' into bobtail
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 07:07 PM Revision 8cb13a19 (ceph): OSD: always activate_map in advance_pgs, only send messages if up
- We should always handle_activate_map() after handle_advance_map() in
order to kick the pg into a valid peering state ... - 06:40 PM rgw Bug #4580 (Resolved): Admin API: RGW Bucket Stats returns no data
- Fixed, commit:346e211030e5709237c99e69881f859cc6d9d116
- 11:09 AM rgw Bug #4580 (Resolved): Admin API: RGW Bucket Stats returns no data
- when asking for bucket stats through the RESTful API the JSON payload is not returned to client but appears in the RG...
- 06:26 PM Revision 3cbd0366 (ceph): client: update cap->implemented when handling revoke
- Fixes #4578
Tested-by: Noah Watkins <noahwatkins@gmail.com> - 06:02 PM Feature #4490 (Resolved): rados per-pool quota
- commit:2b8eb31b854cbae86dbddee73396d85601001b91
- 02:12 PM Feature #4490 (Fix Under Review): rados per-pool quota
- 05:50 PM Revision f9c3bba3 (ceph): Merge pull request #161 from dachary/wip-4560
- unit tests for LFNIndex
- 05:42 PM Revision 4f8ba0e7 (ceph): msgr: allow users to mark_down a NULL Connection*
- Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sam Just <sam.just@inktank.com> - 05:24 PM Revision f8682cb8 (ceph): Merge pull request #150 from ceph/wip-4313
- mon: ConfigKeyService: stash config keys on the monitor
Reviewed-by: Sage Weil <sage@inktank.com
Reviewed-by: Dan Mi... - 04:03 PM rbd Subtask #4589 (Resolved): libceph: consolidate maintenance of message data length
- Right now the total length of the data in a message is
modified in different places throughout the code.
This makes... - 03:38 PM Revision 2fa16422 (ceph): Merge pull request #171 from Elbandi/master
- Run wrap-and-sort and add git to build deps
Reviewed-by: Sage Weil <sage@inkank.com> - 03:37 PM Revision 999b307a (ceph): Merge pull request #172 from ceph/wip-ceph-json
- Wip ceph json
Reviewed-by: Sage Weil <sage@inktank.com> - 03:23 PM Bug #4450 (Resolved): libceph: many socket "socket closed" issues on socket error
- The following has been committed to the ceph-client "testing"
branch:
0267c91 libceph: don't add to crc unless data... - 10:54 AM Bug #4450 (Fix Under Review): libceph: many socket "socket closed" issues on socket error
- I have posted this patch for review:
[PATCH] libceph: don't add to crc unless data sent
In write_partial_messag... - 10:40 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- OK, I found the problem. It was subtle.
The patch in question got rid of the last remaining
piece of the "ceph_m... - 08:15 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- I have confirmed that the osds are reporting crc errors
at the time these repeated connection closes are occurring.
... - 03:22 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- Oh, yeah, we can do the same in the userspace client. I'll do that and re-push. Thanks Yan!
- 03:12 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- FYI:
The kclient deals with this case by calling wake_up_session_caps(). It just clear i_wanted_max_size/i_requested... - 01:04 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- I believe those are okay as truncate size changes should end up actually journaled (as setattrs) so they'll be replay...
- 12:58 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- I spent most of this morning figuring out if it made sense to send the full cap (ceph_mds_caps -- and get rid of the ...
- 12:31 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- I'm not sure this is wrong, but it's confusing me a bit. I thought that the Client sent all capabilities it holds bac...
- 12:14 PM CephFS Bug #4582: mds: Client hang on fsstress with mds_thrasher
- I just pushed wip-4582. Testing it on the fsstress test with mds_thrasher now. I'm not positive this is the right a...
- 11:53 AM CephFS Bug #4582 (In Progress): mds: Client hang on fsstress with mds_thrasher
- 11:53 AM CephFS Bug #4582 (Resolved): mds: Client hang on fsstress with mds_thrasher
While trying to reproduce #4565, fsstress eventually hangs where the client is waiting for a max size update that t...- 03:22 PM Bug #4428 (Resolved): libceph: use cursor for reads
- The following have been committed to the ceph-client "testing"
branch:
ad92e0f libceph: kill last of ceph_msg_pos... - 03:19 PM rbd Fix #4429: libceph: support a list of data items in a message
- Adding a final note that the following has been
committed to the ceph-client "testing" branch:
c658410 libceph: m... - 03:15 PM rbd Feature #2770: krbd: define tasks to add osd_client compound class op support
- OK, here are my plans for finishing this up.
First, http://tracker.ceph.com/issues/3861 defines work that
consoli... - 03:11 PM devops Feature #2416: chef: support mds
- 03:07 PM devops Feature #4456 (Resolved): chef: convert recipes to handle non-upstart environments
- 03:07 PM devops Feature #4375 (Resolved): chef: convert apt recipe to multi-OS install
- 03:07 PM devops Feature #4376 (Resolved): chef: mon recipes
- 03:07 PM devops Feature #4377 (Resolved): chef: osd recipes
- 03:05 PM Feature #4514: packaging: set up git repo with ceph spec file for centos 6
- 03:05 PM devops Feature #4515: packaging: create qemu packages with rbd enabled for centos 6
- 03:01 PM devops Bug #4588 (Resolved): pushy local transport steps on command
Task #3924 is blocked by the following behaviour of pushy's local transport. Need to find a work around.
Email ...- 02:56 PM devops Feature #3351 (Resolved): ceph-deploy: Support upgrades
- 01:04 PM devops Feature #3351 (In Progress): ceph-deploy: Support upgrades
- 02:43 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I'm seeing this one on one of my OSDs right now.
It seems to be working properly for some time, but then it sudden... - 02:40 PM rbd Feature #3861 (Fix Under Review): rbd: consider splitting rbd_osd_req_op_create()
- 02:39 PM rbd Feature #3861: rbd: consider splitting rbd_osd_req_op_create()
- I have posted the following patches for review. The first
two are really cleanup leading to the third, which
actua... - 01:29 PM rbd Feature #3861 (In Progress): rbd: consider splitting rbd_osd_req_op_create()
- I implemented this a few weeks ago. I'm finally getting
back to updating it to match the latest code, so this
time... - 02:23 PM devops Feature #4546 (In Progress): mkcephfs: add DEPRECATED warnings to all stdout user interactions
- 02:02 PM Feature #4313 (Resolved): mon: generic key/value service
- 01:55 PM CephFS Feature #4583 (Resolved): libcephfs: add test that kills a client and verifies mds cleans it up
- 01:42 PM rbd Bug #3737 (Pending Backport): Higher ping-latency observed in qemu with rbd_cache=true during dis...
- 01:29 PM rbd Bug #3737 (Resolved): Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- commit:95c4a81be1af193786d0483fcbe81104d3da7c40 Note that the qemu patch still needs to get merged upstream (#4581).
- 11:16 AM rbd Bug #3737 (Fix Under Review): Higher ping-latency observed in qemu with rbd_cache=true during dis...
- 01:34 PM rbd Subtask #4091 (Resolved): ObjectCacher: optionally make readx/writex calls never block
- commit:95c4a81be1af193786d0483fcbe81104d3da7c40
- 11:17 AM rbd Subtask #4091 (Fix Under Review): ObjectCacher: optionally make readx/writex calls never block
- 01:28 PM CephFS Feature #4022 (In Progress): client: qa: test non-cached operation (force sync mode)
- 01:24 PM CephFS Fix #4191 (Resolved): qa: mulitiple mds in nightly (non-failure case)
- 01:09 PM Bug #4556 (Resolved): OSDs crash with OSD::handle_op during recovery
- 01:04 PM devops Feature #3120 (Resolved): provide command "ceph-disk-list" that lists osd data/journal disks and ...
- 12:58 PM devops Bug #4571: el6: RGW init script failure
- I don't think we want ceph to be a dependency for the radosgw package, do we? It should be possible to install separa...
- 12:54 PM devops Bug #4571: el6: RGW init script failure
- Seems like the branch failed to build.
I tested the init script by pulling it from git.
It works.
Forgot to men... - 12:48 AM devops Bug #4571: el6: RGW init script failure
- The wip-init-radosgw has been updated by removing -x bash option, and by adding ceph as a dependency for the radosgw ...
- 12:34 PM Revision 2da57d76 (ceph): debian: Add git to Build-Depends (need by check_version script)
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:34 PM Revision 8f5c6657 (ceph): debian: Run wrap-and-sort from devscripts
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:16 PM Bug #4572 (Resolved): osd crash with: 0 == "we got a bad state machine event"
- Fix merge into the bobtail branch. Wido, can you test that the current bobtail branch resolves the issue?
- 11:12 AM Bug #4572: osd crash with: 0 == "we got a bad state machine event"
- It's probably due to the is_booting() check in advance_pg().
- 09:30 AM Bug #4572: osd crash with: 0 == "we got a bad state machine event"
- -175> 2013-03-28 17:21:36.478885 7f2f93c01700 10 osd.2 pg_epoch: 26482 pg[0.1f0( empty local-les=0 n=0 ec=1 les/c 7...
- 04:03 AM Bug #4572: osd crash with: 0 == "we got a bad state machine event"
- This cluster is kind of stable again:...
- 11:46 AM rbd Feature #3416 (Resolved): krbd: open parent on open
- 11:44 AM rbd Feature #3417 (Duplicate): krbd: read path (layering)
- 11:41 AM rbd Feature #2531 (Resolved): rbd: fencing broken clients
- 11:41 AM rbd Feature #4211 (In Progress): get good qemu, libvirt versions+patches in CentOS+
- 11:41 AM rbd Feature #4211: get good qemu, libvirt versions+patches in CentOS+
- See 4514 / 4515 for further details.
- 11:40 AM rbd Feature #3472 (Resolved): make it possible to get the watchers out of an object
- 11:36 AM rbd Bug #4581 (Resolved): qemu: use asychronous flush
- To fix #3737. This task is to track the upstream patch.
- 11:31 AM CephFS Bug #4578 (Resolved): client: hangs on unlink
- 11:16 AM CephFS Bug #4578: client: hangs on unlink
- This patch solves the problem :)
- 12:51 AM CephFS Bug #4578: client: hangs on unlink
- yes, patch is also attached
- 11:11 AM CephFS Feature #4442 (Resolved): java: add topology API support
- Err, forgot to close. Thanks. ebc3abaf6dc62678f5ef5914862e9d8f216fffbf
- 11:05 AM CephFS Feature #4442: java: add topology API support
- I think this already got reviewed and merged, right? Or is there something else we need?
- 11:05 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- Not a problem with RGW, bug occurs somewhere else. Non-deterministic error.
- 11:02 AM CephFS Bug #4569 (Resolved): ceph-mds: segfault
- commit:4f8ba0e7756a1b0647867db0e9b5549b3e82f6b1 in master. This wasn't a bug in any released versions, so no backports.
- 10:50 AM CephFS Bug #4569: ceph-mds: segfault
- In case it matters at all, the segfault was happening when I was furiously sigterm'n my hung-on-unlink client.
- 10:33 AM CephFS Bug #4569: ceph-mds: segfault
- Yep, the problem here is that the Session was created during replay and it never had a Connection associated with it ...
- 10:20 AM CephFS Bug #4569: ceph-mds: segfault
- In the logs the session in question is one that failed to reconnect. Was there a different event that caused the MDS ...
- 08:46 AM Revision 972f0eb0 (ceph): unit test LFNIndex::remove_object and LFNIndex::lfn_unlink
- When the object name is short, check that the corresponding file is
::unlink()ed. When the object name is long, there... - 08:26 AM Bug #4579 (Resolved): kclient + ffsb workload makes osds mark themselves down
- The ffsb workload hammers the server side with small requests sufficiently hard that the osds get marked down. I'm g...
- 07:25 AM Revision d15c1527 (ceph): ceph_json: add missing include file
- Needed for LONG_MAX and friends
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:25 AM Revision 9a07ee37 (ceph): ceph_json: add template specializations
- Missing template specializations for data types that
needed for 32 bit compilation
Signed-off-by: Yehuda Sadeh <yehu... - 03:49 AM Revision 6a65b913 (ceph): ceph-disk: implement 'list'
- This is based on Sandon's initial patch, but much-modified.
Mounts ceph data volumes temporarily to see what is insi... - 12:14 AM Revision b9825163 (ceph): ceph.spec.in: Add python-argparse dependency
- The python-argparse package is needed by ceph-create-keys script.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
03/28/2013
- 11:36 PM Revision a021ce62 (ceph): mon: ConfigKeyService: stash config keys on the monitor
- Building up on the Single-Paxos and our existing k/v store that backs
the monitor, we now introduce a simple service ... - 11:12 PM Revision e950ed07 (ceph): ceph.spec.in: Move four scripts from sbin to usr/bin
- The ceph-create-keys, ceph-disk, ceph-disk-activate, and
ceph-disk-prepare scripts are built in sbin, but debian inst... - 10:26 PM Revision 06a1e9c0 (ceph): ceph: propagate do_command()'s return value to user space
- We were returning '1' regardless of what do_command() returned in case
of error. This would make building tools rely... - 10:25 PM Revision b815268b (ceph): run: machine-type: foo, not machine_type: foo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:25 PM Revision e8afa454 (ceph): ceph_manager: retry set_pool_property on EAGAIN
- Retry indefinitely, for now.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:55 PM Revision e91405d5 (ceph): ceph: propagate do_command()'s return value to user space
- We were returning '1' regardless of what do_command() returned in case
of error. This would make building tools rely... - 09:19 PM Revision d89ab0ea (ceph): PG: update PGPool::name in PGPool::update
- Fixes: #4471
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry pick... - 09:15 PM Revision 807487c6 (ceph): Merge pull request #168 from athanatos/wip_4471
- Wip 4471
Reviewed-by: Sage Weil <sage@inktank.com> - 09:09 PM Revision f804892d (ceph): PG: update PGPool::name in PGPool::update
- Fixes: #4471
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:01 PM Revision 1993c2a2 (ceph): PG: use int64_t for pool id in PGPool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:47 PM CephFS Bug #4578 (Resolved): client: hangs on unlink
- Looks like somebody accidentally deleted #4570 (and there's no undelete in Redmine best I can tell), so this ticket w...
- 08:41 PM Bug #4577 (Resolved): ceph pg dump_stuck dumps output even if none
- pg dump_stuck always tries to output a list of pgs, even if there are none stuck in
the category requested; in 'plai... - 08:09 PM rbd Subtask #4125: kernel messenger: support multiple sources of data
- Another status update, based on the history in this issue.
Sage straightened me out about the "data_off" field. I... - 08:02 PM rbd Subtask #4125: kernel messenger: support multiple sources of data
- I should have updated this before I guess.
It turns out I implemented something fairly similar to what
was origin... - 08:01 PM Revision 9a8ea420 (ceph): Merge pull request #164 from dalgaaf/wip-da-fix-misc-1
- some SCA related fixes
- 07:55 PM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- I forked off another bug one day for some work I was
doing related to this--basically layout a specific
plan once i... - 07:55 PM rbd Fix #4429 (Duplicate): libceph: support a list of data items in a message
- We decided that there was no benefit to having
both this asnd 3761, so I'm marking this as a
duplicate.
http:/... - 07:50 PM Bug #3433 (Resolved): Error: Store.__init__() takes no parameters
- Sorry for the delay in response - active development of obsync has moved over to https://github.com/dreamhost/obsync ...
- 07:48 PM Bug #4428: libceph: use cursor for reads
- All of the patches mentioned above except two have now been
committed to the ceph-client "testing" branch:
516c7b... - 07:42 PM Bug #4427 (Resolved): libceph: record residual bytes for all message data types
- This has been committed to the ceph-client "testing" branch:
95e3dca libceph: record residual bytes for all mess... - 07:41 PM Bug #4426 (Resolved): libceph: no outbound zero data
- This has been committed to the testing branch:
db32373 libceph: no outbound zero data
- 06:58 PM Revision 75062610 (ceph): ReplicatedPG: send entire stats on OP_BACKFILL_FINISH
- Otherwise, we update the stat.stat structure, but not the
stat.invalid_stats part. This will result in a recently
sp... - 06:58 PM CephFS Feature #4576 (Rejected): java: support ByteBuffer interface for NIO and NIO.2 high-perf I/O
- ByteBuffer interface in NIO avoids needless copying, and is used by NIO.2 and the new VFS infrastructure in Java 7. T...
- 06:56 PM Revision 91a8d93c (ceph): OSD: flush pg osr on shutdown prior to put()
- Fixes: #4538
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:46 PM Revision 553aaac8 (ceph): ObjectCacher: remove unneeded var from flush_set()
- The gather will only have subs if there is something to flush. Remove
the safe variable, which indicates the same thi... - 05:46 PM Revision fa271565 (ceph): librados: increase version number to indicated new functions
- Listing snaps and listing watchers were added to the C++ api.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 05:46 PM Revision 7cc0940f (ceph): librados: add async flush interface
- Sometimes you don't want flush to block, and can't modify
already scheduled aio_writes. This will be useful for a
lib... - 05:46 PM Revision f06debef (ceph): librados: add versions of a couple functions taking explicit snap args
- Usually the snapid to read from or the snapcontext to send with a write
are determined implicitly by the IoCtx the op... - 05:46 PM Revision 2ae32068 (ceph): librbd: add an is_complete() method to AioCompletions
- Mainly this is useful for testing, like flushing and checking that
all pending writes are complete after the flush fi... - 05:46 PM Revision 860493e7 (ceph): librbd: use the same IoCtx for each request
- Before we were duplicating the IoCtx for each new request since they
could have a different snapshot context or read ... - 05:46 PM Revision 302b93c4 (ceph): librbd: add an async flush
- At this point it's a simple wrapper around the ObjectCacher or
librados.
This is needed for QEMU so that its main th... - 05:46 PM Revision f1d1f119 (ceph): librbd: increment version for new functions is_complete() and aio_flush()
- This done in a separate commit since the increased version number
should not be backported.
Signed-off-by: Josh Durg... - 05:46 PM Revision c2125040 (ceph): ObjectCacher: optionally make writex always non-blocking
- Add a callback argument to writex, and a finisher to run the
callbacks. Move the check for dirty+tx > max_dirty into ... - 05:46 PM Revision 03ac01fa (ceph): librbd: make aio_writes to the cache always non-blocking by default
- When the ObjectCacher's writex blocks, it affects the thread requesting
the aio, which can cause starvation for other... - 05:46 PM Revision 92db06c0 (ceph): ObjectCacher: always complete flush_set() callback
- This removes the last remnants of
b5e9995f59d363ba00d9cac413d9b754ee44e370. If there's nothing to flush,
immediately ... - 05:46 PM Revision 41568b90 (ceph): ObjectCacher: remove NULL checks in flush_set()
- Callers will always pass a callback, so assert this and remove the
checks for it being NULL.
Signed-off-by: Josh Dur... - 05:32 PM Revision 4fafedc9 (ceph): Merge pull request #167 from dmick/master
- Reviewed-by: Alex Elder <elder@inktank.com>
- 05:10 PM Revision bf7cbdfe (ceph): rados: remove confusing argument echo on error
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:51 PM devops Feature #4468 (Resolved): ceph-deploy: log everything locally
- 03:27 PM Bug #4528 (Resolved): ceph cli split command fails during rados api tests
- fixed in teuthology commit:e8afa454d8ad51fe07667ecb3498ee5a5f90c6e4, depends on ceph commit:e91405d540ce11b9996e49772...
- 10:46 AM Bug #4528: ceph cli split command fails during rados api tests
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-28_01:01:45-rados-next-testing-basic/4904
- 03:00 PM devops Bug #4571: el6: RGW init script failure
- I was puzzled by this so I took a look further:
The -u or --user option for start-stop-daemon do not launch the pr... - 09:50 AM devops Bug #4571: el6: RGW init script failure
- bash -x is set.
ceph-conf is called, ceph (no ceph-common for EL) package is not set as a radosgw dependency.
The... - 09:03 AM devops Bug #4571: el6: RGW init script failure
- Alexandre - can you review Gary's fix and see if it resolves this issue?
- 08:59 AM devops Bug #4571 (Fix Under Review): el6: RGW init script failure
- 02:50 PM Bug #4471 (Resolved): osd: pool name for each pg not updated in memory after pool rename
- 02:45 PM Bug #4450: libceph: many socket "socket closed" issues on socket error
- OK, I screwed up, and that's why I was taking notes.
The bad commit was this one, NOT the one I said before:
... - 08:34 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- After a few iterations I have concluded it's this patch
where the problems start to appear:
811fde6 libceph: us... - 06:50 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- Verified that I reproduced the problem when reducing the list of
tests to this (again, while running test 74):
... - 06:22 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- I am bisecting this today. I'm going to take notes here to
make sure I don't screw it up.
I started with the "wi... - 02:33 PM Revision 7c5a36af (ceph): Merge pull request #163 from ceph/wip-rbd-snapset-cache
- librbd: flush cache when set_snap() is called
Reviewed-by: Sage Weil <sage@inktank.com> - 02:24 PM Bug #4574 (Resolved): mon: HEALTH_OK even if data health is HEALTH_WARN
- ...
- 02:16 PM Fix #4567: mon: refactor mon caps; allow restriction of key/value storage by prefix
- 09:01 AM Fix #4567: mon: refactor mon caps; allow restriction of key/value storage by prefix
- probably something similar the osdcap, like...
- 08:57 AM Fix #4567: mon: refactor mon caps; allow restriction of key/value storage by prefix
- Anything in mind for how this could work on an interface level?
- 12:30 PM rgw Feature #4573 (Resolved): Create User Quota Blueprint
- 12:24 PM Revision f891d5a5 (ceph): rgw_json_enc.cc: use static_cast instead of C-Style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:22 PM Revision 8d957c11 (ceph): rgw/rgw_admin.cc: remove double checks from get_cmd()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM rgw Feature #4332 (In Progress): rgw: multisite: metadata-changes log: tie into metadata update opera...
- 12:15 PM rgw Feature #4331 (In Progress): rgw: multisite: metadata-changes log: create internal API
- 12:11 PM rgw Feature #4533: rgw: ability to configure zone params
- As an admin, i can configure which pools RGW will use to use as part of a zone via the rados-gateway itself.
- 12:07 PM rgw Feature #3668: rgw: support CORS
- 12:06 PM rgw Feature #3102 (Need More Info): rgw: dedup
- 11:32 AM rgw Feature #3102: rgw: dedup
- 12:03 PM Bug #4538 (Resolved): os/FileStore.h: 191: FAILED assert(q.empty()) on shutdown
- 12:00 PM Bug #4557 (Resolved): inconsistent during deep scrub
- 11:33 AM Feature #2539 (Duplicate): ceph should issue timeout message when it can't connect to mon
- #2158
- 11:29 AM rgw Tasks #4154: gather configuration files for non-Apache RGW deployments
- 11:28 AM rgw Feature #1485: rgw: support google storage api
- 11:28 AM rgw Feature #3081 (Duplicate): radosgw: asynchronous read-only replication mechanism
- Duplicate of 4340, 4341 etc.
- 11:27 AM Bug #3275 (Can't reproduce): Monitors unable to recover after network line card replacement
- 11:24 AM rgw Feature #4432 (Need More Info): Develop plan for multi-user / multi-tenancy
- 11:06 AM Bug #4572 (Resolved): osd crash with: 0 == "we got a bad state machine event"
- This seems like #4042 but the backtrace seems different.
After resolving #4556 I tried to recover the cluster, but... - 11:03 AM rgw Feature #418: rgw: object versioning
- 10:42 AM Bug #4527: journal Unable to read past sequence 0 but header indicates the journal has committed ...
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-28_01:01:45-rados-next-testing-basic/4834
- 10:21 AM CephFS Bug #4569: ceph-mds: segfault
- It looks like the session is getting closed because its stale, and then killed, but the session->connection field pas...
- 10:00 AM CephFS Feature #4354 (In Progress): mds: add an equivalent to the OSD OpTracker
- 09:28 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- For the hell of it I tried this using the 3.7 kernel and
found that I don't see the crash. That puts a bound
on wh... - 12:23 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- Just awake now: I'll respond to #7: yes, the crash happens like 2-3 seconds after I run rbd map.
FYI: after today ... - 07:58 AM Revision c8ac1ee9 (ceph): unit test LFNIndex::lfn_get_name
- The escape logic is tested for
* leading . => \.
* / => \s
* \ => \\
* leading DIR_ => \d
The file names fo... - 07:51 AM rbd Bug #4525 (Pending Backport): hang during librbd python tests
- commit:613b7085bb48cde1e464b7a97c00b8751e0e917f
- 07:31 AM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- Update on trying to track this down...running this test in teuthology, I don't hit the same assertion, but I do see t...
- 07:24 AM Revision b9c8d4f8 (ceph): librados.h: fix comment describing rados_pool_list
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:10 AM Revision 613b7085 (ceph): librbd: flush cache when set_snap() is called
- If there are writes pending, they should be sent while the image
is still writeable. If the image becomes read-only, ... - 05:48 AM Tasks #4321: unit tests for FileStore::_detect_fs
- Rebase to help with the pull request and submit a pull request. The patch http://marc.info/?l=ceph-devel&m=1362484390...
- 05:42 AM Tasks #4542 (Resolved): fix append to uninitialized buffer in FlatIndex::created and unit tests f...
- 04:35 AM Revision 24294464 (ceph): radosgw-admin: fix help clitest
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:27 AM Revision fe0a0e6f (ceph): Merge remote-tracking branch 'gh/next'
- 04:20 AM Revision f4d21c5a (ceph): Merge pull request #159 from ceph/wip-4564
- mds: Delay session close if in clientreplay
Reviewed-by: Sage Weil <sage@inktank.com> - 01:59 AM Revision 10626f7b (ceph): mon: MonitorDBStore: add 'get_iterator()' method to iterate over a prefix
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:44 AM Revision 20d594a8 (ceph): ceph-disk: reimplement is_partition
- Previously we were assuming any device that ended in a digit was a
partition, but this is not at all correct (e.g., /... - 01:44 AM Revision d3e49047 (ceph): ceph-disk: reimplement list_all_partitions
- Use /dev/disk/by-id to list disks and their partitions. This is more
accurate and correct than the previous (as-yet ... - 12:25 AM Revision 3c3969de (ceph): rados test suite for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:13 AM Revision d89a63ca (ceph): doc: Updated usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:00 AM Revision d2a021be (ceph): rbd test suites for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
03/27/2013
- 11:50 PM Revision bc724927 (ceph): doc: Updated usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:30 PM Revision 98445009 (ceph): upstart: try udevadm settle if osd journal isn't present
- Wait briefly for the journal to appear if it isn't there yet, then give up.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:30 PM Revision 2ae297cc (ceph): ceph-disk: ignore udevadm settle return code
- If we time out, just continue and let the next step fail.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:30 PM Revision 4362934a (ceph): ceph-disk: conditionally remove mount path
- umount removes it on success; only remove it here if it is still there.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:44 PM Revision e86273e1 (ceph): fs test suite for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:19 PM devops Bug #4571: el6: RGW init script failure
- There is a centos init script in the ceph wip-init-radosgw. It's ready to go, just needs review.
- 05:27 PM devops Bug #4571 (Resolved): el6: RGW init script failure
- The current radosgw init script provided with CentOS package uses Debian specific init-functions.
The default apac... - 09:23 PM CephFS Bug #4308 (Won't Fix): ceph-fuse crashed during blogbench test (argonaut)
- this is most likely memory corruption in argonaut's ceph-fuse.
- 09:21 PM CephFS Bug #4564 (Resolved): client: Close session doesn't wait for outstanding requests
- 09:09 AM CephFS Bug #4564 (Fix Under Review): client: Close session doesn't wait for outstanding requests
- Pushed a fix to wip-4564.
- 07:13 AM CephFS Bug #4564 (Resolved): client: Close session doesn't wait for outstanding requests
Ran into another failure related to testing #4451 on the client where the following occurs:
client sends create/...- 09:21 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- my guess is we are putting too many references to the socket, and some lingering state is trying to call the socket s...
- 09:04 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- OK, clearly if you run the command with the additional
arguments specifying the pool, id, and keyring you get
a ker... - 07:53 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- OK, I did some more tests. Running this command by itself is fine:
strace rbd map afs254-vicepa
(Note, I haven't... - 04:22 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- A few notes.
I just ran this, without any other setup, and *that* caused
a crash:
strace rbd map afs254-vice... - 02:17 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- Not a lot can be immediately seen from the specifics
of the crash. But I suspect there's some memory
corruption, l... - 02:10 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- OK, I've reproduced *something* using 3.8.4, but I don't
understand it yet. But it seems similar, the crash occurre... - 07:30 AM rbd Bug #4559 (Fix Under Review): krbd: kernel BUG when mapping unexisting rbd device
- I have posted the following patch for review:
[PATCH] rbd: don't zero-fill non-image object requests
Sage, th... - 06:45 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- Thanks. Without looking at the code, what I don't understand is why the user-mode rbd tool sends anything to the kern...
- 06:36 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I think I know why the crash is occurring. I don't
fully understand the big picture yet, but here's
the problem I ... - 06:25 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- Here is another trace of the BUG another slightly different way. It could be the lack of a keyring that causes the BU...
- 06:08 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I think I have reproduced the problem. I don't know
much more but it appears to have something to do with
the use ... - 08:22 PM Revision 15074432 (ceph): osd: disallow classes with flags==0
- They must be RD, WR, or something....
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 89c6901... - 08:22 PM Revision 6b6e0cef (ceph): osd: EINVAL when rmw_flags is 0
- A broken client (e.g., v0.56) can send a request that ends up with an
rmw_flags of 0. Treat this as invalid and retu... - 08:22 PM Revision 4bdd3749 (ceph): osd: fix detection of non-existent class method
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 50b831e3641c21cd5b145271688189e199f432d1) - 08:21 PM Revision 76a5ee3e (ceph): Merge remote-tracking branch 'gh/wip-4556'
- Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:19 PM Revision 89c69016 (ceph): osd: disallow classes with flags==0
- They must be RD, WR, or something....
Signed-off-by: Sage Weil <sage@inktank.com> - 08:12 PM Revision f28800f8 (ceph): osd: tolerate rmw_flags==0
- We will let OSD return a proper error instead of asserting.
This is effectively a backport of c313423cfda55a2231e000... - 08:09 PM Revision 50b831e3 (ceph): osd: fix detection of non-existent class method
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:09 PM Revision f2dda43c (ceph): osd: EINVAL when rmw_flags is 0
- A broken client (e.g., v0.56) can send a request that ends up with an
rmw_flags of 0. Treat this as invalid and retu... - 08:04 PM Revision 21a09b14 (ceph): Merge pull request #141 from ceph/wip-rgw-zone-config
- Wip rgw zone config
Reviewed-by: Sage Weil <sage@inktank.com> - 08:03 PM Revision ac505d0a (ceph): suites for upgrade
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 07:39 PM Feature #4313: mon: generic key/value service
- Dozed off in front of the TV and forgot to push the branches.
repushed code can still be found on https://github.c... - 06:11 PM Revision b0103abd (ceph): OSD fails to start with error assert(values.size() == 2)
- Remove redundant setting of dirty_info
Fix PG::upgrade() to conform to programming style
Set dirty_big_info in PG::wr... - 06:10 PM Revision 26a9b132 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 06:00 PM Revision c8317dde (ceph): Merge pull request #148 from dachary/wip-4542
- fix append to uninitialized buffer in FlatIndex::created
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:48 PM devops Feature #4468 (Fix Under Review): ceph-deploy: log everything locally
- wip-log3
- 05:08 PM Revision 4485cb87 (ceph): Merge pull request #153 from dalgaaf/wip-da-java
- Fix some small java issues
- 04:59 PM Revision 0d98815b (ceph): Merge pull request #160 from alram/master
- Fix radosgw upstart job
Reviewed-by: Sage Weil <sage@inktank.com> - 04:31 PM Revision 4db4a022 (ceph): Fix radosgw upstart job
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 04:18 PM Revision d4961e0c (ceph): Merge pull request #158 from alram/master
- Change ceph apt recipe to repo in doc
- 04:13 PM Revision 94321ccd (ceph): test_librbd_fsx: fix image closing
- Always close the image we opened in check_clone(), and check the
return code of the rbd_close() called before cloning... - 04:06 PM Revision 5aa5bc2c (ceph): mds: Delay session close if in clientreplay
- If the mds is in clientreplay, a session close
request needs to be delayed until it reaches
active. Otherwise, the s... - 04:01 PM Revision 9369f918 (ceph): Change ceph::apt -> ceph::repo in doc
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 03:56 PM Revision 7dca4aee (ceph): Merge pull request #6 from ceph/wip-mds-thrasher-logging
- task/mds_thrash: Log mds dump after long delay
- 03:52 PM Revision 54f53853 (ceph): Merge pull request #156 from dalgaaf/wip-da-fix-mkcephfs
- Fix issues in mkcephfs
Reviewed-by: Sage Weil <sage@inktank.com> - 03:50 PM Revision 98f6a25c (ceph): mkcephfs.in: use 32 chars for mktemp to be more unique
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:28 PM Revision 68901575 (ceph): Merge pull request #152 from dalgaaf/wip-da-fix-misc
- MDS.cc: remove double is_clientreplay() check in active_start()
Reviewed-by: Sage Weil <sage@inktank.com> - 03:26 PM Revision 295c92ce (ceph): Merge pull request #157 from ceph/wip-4539
- mds: Clear backtrace updates on standby_trim_seg
Reviewed-by: Sage Weil <sage@inktank.com> - 03:03 PM Revision 2cb9f963 (ceph): mkcephfs.in: cleanup rdir in MON case
- Remove $rdir in MON case of 'mkcephfs -a' as soon as it's no
longer needed.
Signed-off-by: Danny Al-Gaaf <danny.al-g... - 02:55 PM Revision a8338ee1 (ceph): mkcephfs.in: provide a valid rdir for MONs on -a
- Provide also a valid rdir for ssh as in case of OSD/MDS hosts if
mkcephfs -a is called.
Signed-off-by: Danny Al-Gaaf... - 02:40 PM Revision 38f845de (ceph): mkcephfs.in: use mktemp instead of dd+md5sum+awk
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:35 PM Revision 0e009b1b (ceph): mds: Clear backtrace updates on standby_trim_seg
- If the mds is standby, when a segment is trimmed, we need
to clear the backtrace updates list to avoid the following
... - 01:50 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Another 100 iterations of these tests without reproducing
the original problem:
214 221 222 236 241 243 245 246 247... - 05:46 AM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- 150 iterations of running this set of tests and I haven't
seen the problem reproduce:
214 221 222 236 241 243 245 2... - 01:48 PM Revision 6fd7ebd4 (ceph): task/mds_thrash: Log mds dump after long delay
- In cases where the mds thrasher continuously loops
waiting for an mds to be removed from the map, or
for a new mds to... - 01:37 PM Revision 0c43ac32 (ceph): ceph_common.sh: fix typo in comment
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:26 PM Bug #3816 (Resolved): osd/OSD.cc: 3318: FAILED assert(osd_lock.is_locked())
- This second set of crashes in handle_op is #4556, now fixed.
The osd_lock issue has been fixed earlier as well. T... - 01:23 PM Bug #4556 (Pending Backport): OSDs crash with OSD::handle_op during recovery
- commit:76a5ee3e214cb5187d85d45d4316adc4f3642182
- 12:35 PM Bug #4556: OSDs crash with OSD::handle_op during recovery
- I just saw osd.0 (and a couple of other) crash and have a core-file.
This is what the backtrace tells me:... - 10:37 AM Bug #4556 (Need More Info): OSDs crash with OSD::handle_op during recovery
- 10:37 AM Bug #4556: OSDs crash with OSD::handle_op during recovery
- Wido-
This is the same assert we say on #3816. Is it possible to reproduce this iwth some logging so we can see t... - 12:50 PM rgw Feature #4511: RGW: Reject requests containing invalid characters.
- 11:45 AM CephFS Bug #4569 (Resolved): ceph-mds: segfault
- I started receiving this segfault in ceph-mds with the latest master today....
- 11:38 AM Revision 17029a6c (ceph): java libcephfs: add serialVersionUID to some Exception classes
- Fix for: "The serializable class does not declare a static final
serialVersionUID field" warning.
Signed-off-by: Dan... - 11:37 AM Revision 10191a9c (ceph): CephMount.java: remove unused import
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:20 AM Bug #4562 (Resolved): OSD fails to start with error assert(values.size() == 2)
- commit:b0103abdee1fecaa9d906efce8e1e8c3325d9ef5
- 10:40 AM Bug #4562 (In Progress): OSD fails to start with error assert(values.size() == 2)
This was caused by the termination of an OSD while it was still running load_pgs() dealing with an upgrade from 0.5...- 10:52 AM RADOS Documentation #4568 (Closed): FAQ entry for changing journal size/moving journal
- It's easy if you know how: prevent the cluster from rebalancing on missing
OSD with 'noout', stop the OSD, flush hi... - 10:42 AM Fix #4567 (Resolved): mon: refactor mon caps; allow restriction of key/value storage by prefix
- 10:35 AM Bug #4297 (Rejected): OSD: memory leak, do_notifies
- This was most likely due to a large past intervals set due to a degraded pg, rather than a leak.
- 10:31 AM Bug #4421 (Duplicate): osd: deep-scrub stat mismatch errors seen
- 10:29 AM Bug #4372 (Can't reproduce): osd/ReplicatedPG.cc: 4620: FAILED assert(!missing.is_missing(soid))
- 10:05 AM Revision 8c962b5e (ceph): MDS.cc: remove double is_clientreplay() check in active_start()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:35 AM CephFS Bug #4565 (Resolved): MDS/client: issue decoding MClientReconnect on MDS
- ...
- 09:30 AM rbd Bug #4525: hang during librbd python tests
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-27_01:01:29-rbd-master-testing-basic/4331
- 09:25 AM rbd Bug #4525: hang during librbd python tests
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-26_15:10:17-rbd-master-testing-basic/3828
- 08:26 AM CephFS Bug #4539 (Resolved): include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::standby_trim_...
- commit:295c92c
- 07:47 AM CephFS Bug #4539 (Fix Under Review): include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::stand...
- Yep. There's no state bit, and the cache is unchanged by the backtrace updates list. The standby mds is free to cle...
- 08:04 AM CephFS Bug #4555 (Resolved): The CephFileSystem class is missing the createNonRecursive method
- 0a5175722a8444579715c1871c09c246969e7890
- 07:05 AM rbd Fix #4429: libceph: support a list of data items in a message
- I hit the problem described here http://tracker.ceph.com/issues/4450
while testing this. So before committing these... - 06:00 AM rbd Fix #4429: libceph: support a list of data items in a message
- This ran these tests, along with a "full" xfstests run
overnight with no problems:
- kernel_untar_build.sh
... - 07:03 AM Bug #4450: libceph: many socket "socket closed" issues on socket error
- I seem to have hit this problem again while attempting to test
my most recent changes. It arose while running xfste... - 05:50 AM rbd Bug #4563 (Closed): rbd xfstests: test 167 failing
- I believe this can be fixed by increasing the size of the
device (not sure if it's test or the scratch) used for tes... - 05:47 AM Revision 3f2e7116 (ceph): mon: fix crush_ops.sh tests
- Make it work. Also, make note that these aren't handled idempotently by
the mon currently. Doh!
Signed-off-by: Sag... - 01:19 AM Revision ae993c47 (ceph): Merge remote-tracking branch 'gh/next'
- 12:21 AM Revision 76b296f0 (ceph): ReplicatedPG: send entire stats on OP_BACKFILL_FINISH
- Otherwise, we update the stat.stat structure, but not the
stat.invalid_stats part. This will result in a recently
sp... - 12:05 AM Revision 8eb22740 (ceph): Merge remote-tracking branch 'gh/next'
03/26/2013
- 11:08 PM Revision 503ed9ee (ceph): testing: fix hadoop-internal-test
- Remove now superfluous directory changes
that are causing tests to fail.
This code should have been removed when we t... - 10:35 PM devops Feature #4468 (In Progress): ceph-deploy: log everything locally
- i give up; see wip-log2
- 03:56 PM devops Feature #4468 (Fix Under Review): ceph-deploy: log everything locally
- 10:22 PM CephFS Bug #4539: include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::standby_trim_segments()
- I think this is as simple as...
- 10:13 PM Revision 75bf1937 (ceph): Merge pull request #149 from ceph/wip-4530
- #4530
Reviewed-by: Sage Weil <sage@inktank.com> - 10:09 PM Revision ebc3abaf (ceph): Merge pull request #139 from ceph/wip-topo-java
- Merging in Noah's branch for adding topology calls. This passes existing libcephfs, libcephfs-java and hadoop tests.
- 10:08 PM Revision 7c1e9be0 (ceph): client: Don't signal requests already handled
- The assertion failure reported in #4530 is triggered
by the following:
1. client sends request
2. mds sends unsafe r... - 08:28 PM Revision 77230d43 (ceph): fix append to uninitialized buffer in FlatIndex::created
- The long_name variable is not initialized. When the append_oname
function is called, it will strlen(long_name) and ge... - 08:27 PM Revision bc54a8bf (ceph): locker: make desc optional
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:47 PM Feature #4510 (In Progress): OSD scrub/repair should handle read error and truncate reasonably
- 07:38 PM Feature #4313: mon: generic key/value service
- pull request: https://github.com/ceph/ceph/pull/150
Pushing it up for review only.
Needs to be thoroughly teste... - 07:21 PM Revision 07e324ae (ceph): ceph.conf: osd debug op order = true
- Debug the osd op ordering by default. Most of the runs have a small number
of clients, which makes the STL maps chea... - 07:06 PM Revision b8160018 (ceph): Merge pull request #144 from dalgaaf/wip-da-ceph-disk
- Fix some issues in ceph-dsk
Reviewed-by: Sage Weil <sage@inktank.com> - 06:44 PM Revision 1baf66b9 (ceph): Merge pull request #143 from ceph/wip-mds-health
- improve mds health checks
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 06:40 PM Revision 8eabe1bb (ceph): locker/api: fix DELETE
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:34 PM Revision 86230f15 (ceph): Merge branch 'wip-lock'
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 06:31 PM devops Feature #3120 (Fix Under Review): provide command "ceph-disk-list" that lists osd data/journal di...
- Ok I pushed this out to wip-disk-list
I am probably doing some stupid stuff but seems to work ok. Example output:
... - 10:11 AM devops Feature #3120 (In Progress): provide command "ceph-disk-list" that lists osd data/journal disks a...
- 06:31 PM Revision 9eda8e5d (ceph): ceph-disk: udevadm settle before partprobe
- After changing the partition table, allow the udev event to be
processed before calling partprobe. This helps preven... - 05:32 PM Bug #4557 (Pending Backport): inconsistent during deep scrub
- 12:25 PM Bug #4557 (Resolved): inconsistent during deep scrub
- interactive-on-error: true
roles:
- - mon.0
- osd.0
- osd.1
- osd.2
- client.0
- - osd.3
- osd.4
... - 05:22 PM Bug #4562 (Resolved): OSD fails to start with error assert(values.size() == 2)
- The problem occurred after an upgrade to master (67c696dfac0a2343ec7530ca68e5ea9b2d3d31d0).
Error from log is:
... - 04:54 PM rbd Bug #4559 (In Progress): krbd: kernel BUG when mapping unexisting rbd device
- I've requested more information. At this point though
my first step is reproducing the problem.
I did reproduce ... - 01:46 PM rbd Bug #4559 (Resolved): krbd: kernel BUG when mapping unexisting rbd device
- Taken from the ceph-users mailing list.
I told Dan I'd take a look at this.
-------- Original Message --------
... - 04:29 PM Revision 23faa9f0 (ceph): Merge pull request #147 from ceph/wip-4537
- mds: CInode::build_backtrace() always incr iter
Reviewed-by: Sage Weil <sage@inktank.com> - 04:14 PM Revision 14cef276 (ceph): mds: CInode::build_backtrace() always incr iter
- Always increment the iterator when adding old pools
to the backtrace. This fixes a bug on files where
the layout had... - 04:06 PM Revision bb68a20f (ceph): java: fix test name typo
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:04 PM CephFS Feature #4277 (Closed): Move built hadoop artificats to download URL
- 04:03 PM CephFS Feature #4277: Move built hadoop artificats to download URL
- For now, we're manually posting Hadoop bindings to http://ceph.com/download/. I'll close this for now and we can revi...
- 03:58 PM rbd Fix #4429: libceph: support a list of data items in a message
- (The following really applies to this issue as well
as 4428, 4427, and 4426.)
The patch(es) for this were posted ... - 03:52 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I have been running tests all afternoon on two different
clusters with some code in place to catch this sort
of err... - 03:15 PM Revision 67c696df (ceph): Merge pull request #145 from dalgaaf/wip-da-c_str
- CrushWrapper.cc: remove some std::string::c_str() calls
Reviewed-by: Sage Weil <sage@inktank.com> - 03:13 PM CephFS Bug #4530 (Resolved): client: Assert failure on session close
- 10:19 AM CephFS Bug #4530: client: Assert failure on session close
- I went to file another bug for the client reconnect triggering a session close, but the log indicates that its not ac...
- 02:52 PM Tasks #4560: unit tests for src/os/LFNIndex.cc
- ...
- 02:09 PM Tasks #4560 (Closed): unit tests for src/os/LFNIndex.cc
- "work in progress":https://github.com/dachary/ceph/commits/wip-4560
Create a set of unit tests in *src/test/os/Tes... - 02:25 PM Revision b9141e94 (ceph): client: Cleanup request signaling
- Split up the conditionals handling unsafe reply
and signaling the caller to improve readability.
The overall behavior... - 02:25 PM Revision 4dda138b (ceph): client: Remove got_safe from MetaRequest
- Once a safe reply is received, we remove the
request from the mds_requests map, so checking that
it might be a duplic... - 02:25 PM Revision dfb46b9a (ceph): client: Always cleanup request after safe
- The client MetaRequest should always be cleaned up
and removed from the mds_requests map once the client
gets a safe ... - 02:25 PM Revision 3b520b51 (ceph): client: Handle duplicate safe replies
- If the mds sends a duplicate safe reply, the mds_requests
map won't contain a matching request id (tid). Instead of
... - 02:23 PM CephFS Fix #4191 (In Progress): qa: mulitiple mds in nightly (non-failure case)
- 01:16 PM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- It may not be the right status, but I'm marking
this "testing" for now. - 01:15 PM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- This commit has been pushed to the ceph-client "testing" branch.
d51342b libceph: initialize data fields on last... - 01:11 PM Linux kernel client Bug #4524: libceph: bad ptr deref in rbtree for kick_requests
- I am fairly sure the bad pointer dereference is this line
in rb_next():
/*
* If we have a right... - 12:52 PM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- There's no way around it - we need an async flush in librbd. Using coroutines vs callbacks doesn't matter in this cas...
- 01:04 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Looks like I finally found a fix - using an explicitly asynchronous flush (instead of the sync flush made async by qe...
- 12:32 PM rbd Bug #4392 (Resolved): kclient: libceph: osd ops send out of order
- The following changes have been committed to the ceph-client
"testing" branch:
0518f43 libceph: send queued reque... - 07:51 AM rbd Bug #4392: kclient: libceph: osd ops send out of order
- The following updated patches have been posted for review:
[PATCH 3/6, v2] libceph: requeue only sent requests whe... - 06:44 AM rbd Bug #4392: kclient: libceph: osd ops send out of order
- Sage explained something to me yesterday after taking a
quick look at my posted patches:
- the requirement for requ... - 05:20 AM rbd Bug #4392: kclient: libceph: osd ops send out of order
- I tested (am testing) these patches overnight.
I ran my xfstests over rbd task with this in it:
- ceph:
br... - 12:18 PM Bug #4556 (Resolved): OSDs crash with OSD::handle_op during recovery
- While tracking down #3816 I stumbled upon this one multiple times.
I tried the upgrade to 0.56.4 to be sure, but t... - 12:16 PM Linux kernel client Bug #4553: kclient: lockdep report, crash involving ceph fs and libceph
- OK, after this I'm done with this problem.
I just wanted to point out that I think there are two
distinct problem... - 11:12 AM Linux kernel client Bug #4553: kclient: lockdep report, crash involving ceph fs and libceph
- I have run this same test (only "suites/ffsb.sh") with the
"testing" branch twice. I got the same lockdep warning,
... - 11:02 AM Linux kernel client Bug #4553: kclient: lockdep report, crash involving ceph fs and libceph
- Let's see if this one doesn't exceed the maximum size
something added.... - 10:32 AM Linux kernel client Bug #4553: kclient: lockdep report, crash involving ceph fs and libceph
- I just noticed the end of the kernel messages, leading up
to the hard crash, was not captured in what I initially
a... - 09:47 AM Linux kernel client Bug #4553: kclient: lockdep report, crash involving ceph fs and libceph
- I just got (I think) the same lockdep report, running only
the "suites/ffsb.sh" test using the ceph-client "testing"... - 09:24 AM Linux kernel client Bug #4553 (Can't reproduce): kclient: lockdep report, crash involving ceph fs and libceph
- I really don't know what to assign this to, but it looks like
a big complex potential deadlock so I thought I should... - 12:09 PM CephFS Bug #4555 (Resolved): The CephFileSystem class is missing the createNonRecursive method
- This is needed by HBase
There is a pull request here: https://github.com/ceph/hadoop-common/pull/1 - 11:46 AM Revision f957e723 (ceph): CrushWrapper.cc: remove some std::string::c_str() calls
- Passing the result of c_str() to a function that takes
std::string as argument is slow and redundant.
Signed-off-by:... - 11:45 AM CephFS Feature #2144: mon: improve mds health checks
- commit:1baf66b
- 11:45 AM CephFS Feature #2144 (Resolved): mon: improve mds health checks
- 11:38 AM Bug #4521: mon: starting a new osd crashes all mon's
- Logs as per IRC. Thanks.
- 12:19 AM Bug #4521: mon: starting a new osd crashes all mon's
- log of commands attached.
this was following the update to 0.59
- 11:19 AM rgw Feature #4533: rgw: ability to configure zone params
- I am having major deja-vu here as I think we may have discussed this elsewhere, but this feature is to allow multiple...
- 07:19 AM rgw Feature #4533: rgw: ability to configure zone params
- Currently it is not possible to configure more than a single set of pools to be used on a single ceph cluster. That m...
- 11:14 AM Bug #4297: OSD: memory leak, do_notifies
- this could just be that oen peers are way behind and do_notifies is sending a very large set of past intervals. the ...
- 11:11 AM CephFS Bug #4545 (Can't reproduce): error creating empty object store. Invalid argument.
- 09:33 AM CephFS Bug #4545: error creating empty object store. Invalid argument.
- i've seen this regularly in the qa runs over the last week or so
- 11:00 AM devops Feature #3302: ceph-disk: activate-journal, and matching udev rule
- 09:41 AM CephFS Bug #4537 (Resolved): mds: hang on rmdir, unlink
- 07:04 AM CephFS Bug #4537 (Fix Under Review): mds: hang on rmdir, unlink
- Fix pushed to wip-4537.
- 09:12 AM Bug #4552: osd: temporarily hung box marks down peers
- I haven't. The only semi-related config option I have is "mon osd down out interval = 600".
- 09:09 AM Bug #4552: osd: temporarily hung box marks down peers
- Hmm, did you change any of the config around the num_reports stuff?
Or do we in fact have the OSD sending multiple f... - 09:05 AM Bug #4552: osd: temporarily hung box marks down peers
- (I'm paravoid -- thanks for opening the bug report)
Attached is the mon log which shows the turn of events quite w... - 08:58 AM Bug #4552 (Resolved): osd: temporarily hung box marks down peers
- paravoid reports that a single machine that was being administered via megacli hung for a while, and was marked down,...
- 03:31 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- I've seen this one again on a 0.56.3 cluster last week.
12 OSDs went down with exactly the same backtrace. I didn'... - 02:06 AM rbd Bug #4446: librbd: crash from opensolaris vm
- Yes, the same disk image boots and runs just fine from local storage (that's how we're running it now). FYI - here i...
- 01:19 AM rbd Bug #4446: librbd: crash from opensolaris vm
- The error the guest is seeing is not actually a short read - it's just a bad error message from the solaris disk driv...
- 01:27 AM rbd Bug #4551 (Resolved): librbd: rollback broken for clones
- Reported on ceph-devel: http://comments.gmane.org/gmane.comp.file-systems.ceph.devel/13979
03/25/2013
- 11:47 PM Revision 6208af93 (ceph): locker: clear desc on unlock
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:47 PM Revision 56820b3b (ceph): locker: set desc on lock
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:47 PM Revision 0b72c8db (ceph): lock: pass desc to lock operation; leave on unlock
- Pass the desc to the lock operation.
The unlock operation now clears desc for us; no need to do it outselves.
Signe... - 11:29 PM Revision ffe8235f (ceph): Merge remote-tracking branch 'gh/wip-crush'
- The non-crush bits
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 11:24 PM Revision 7f65c512 (ceph): doc/release-notes: extra note for v0.56.4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:09 PM Revision 82b129ff (ceph): doc/release-notes: v0.56.4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:52 PM Revision 7fbc1ab6 (ceph): rbd: remove fiemap use from import
- On some kernels and filesystems fiemap can be racy and provide
incorrect data even after an fsync. Later we can use S... - 10:42 PM Revision e594fcb3 (ceph): locker: log updates
- Note whenever locks are acquired/released, or a machine's description is updated.
Under apache, these will go to erro... - 10:39 PM Revision c50b143e (ceph): thrashosds: add test_backfill_full
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:39 PM Revision 97a5c051 (ceph): thrashosds.py: fix line length
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 07:35 PM rbd Bug #4392 (Fix Under Review): kclient: libceph: osd ops send out of order
- The following patches have been posted for review.
[PATCH 1/6] libceph: slightly defer registering osd request
[P... - 07:35 PM rbd Bug #4392 (In Progress): kclient: libceph: osd ops send out of order
- I have a series of patches I'm now testing that I believe
will address this. They don't do exactly what I suggested... - 07:23 PM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- Ok, I did
ceph mds tell 0 dumpcache /tmp/dump.txt
http://91.226.13.93/dump.txt.gz - 07:16 PM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- ...
- 09:20 AM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- If you run "ceph mds 0 dumpcache <filename>" then the MDS will dump everything it has in cache to the filename you sp...
- 06:42 PM Revision 491795e2 (ceph): Improve test by getting cloneid from my_snaps vector
- Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Sam Just <sam.just@inktank.com> - 06:02 PM Revision 63b0f854 (ceph): v0.56.4
- 05:22 PM Feature #4549: api: Incorporate and respond to comments on DRAFT REST API
- Yes. Can one express story dependencies here?
- 02:37 PM Feature #4549: api: Incorporate and respond to comments on DRAFT REST API
- 02:37 PM Feature #4549: api: Incorporate and respond to comments on DRAFT REST API
- Shouldn't this come after #3984?
- 01:58 PM Feature #4549 (Resolved): api: Incorporate and respond to comments on DRAFT REST API
- 05:21 PM Feature #4547: api: implement self-description for --admin-daemon commands
- In order to make some definable progress on the ceph CLI, we're deferring complete reimplementation
of "--admin-daem... - 02:37 PM Feature #4547 (Need More Info): api: implement self-description for --admin-daemon commands
- 01:32 PM Feature #4547 (Resolved): api: implement self-description for --admin-daemon commands
- 05:20 PM Feature #4548: api: implement self-description for osd/mon tell commands
- 05:19 PM Feature #4548: api: implement self-description for osd/mon tell commands
- In order to make some definable progress on the ceph CLI, we're deferring complete reimplementation
of "ceph tell <o... - 02:37 PM Feature #4548 (Need More Info): api: implement self-description for osd/mon tell commands
- 01:34 PM Feature #4548 (Resolved): api: implement self-description for osd/mon tell commands
- 05:20 PM Revision 90ab120a (ceph): rgw: bucket index ops on system buckets shouldn't do anything
- Fixes: #4508
Backport: bobtail
On certain bucket index operations we didn't check whether
the bucket was a system buc... - 04:55 PM Revision 70e0ee8b (ceph): rgw: bucket index ops on system buckets shouldn't do anything
- Fixes: #4508
Backport: bobtail
On certain bucket index operations we didn't check whether
the bucket was a system buc... - 04:45 PM Revision b7d7e689 (ceph): ceph-disk: rename some local variabels in list_*partitions
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:33 PM Feature #4299 (Resolved): crush: command to set additional parents for an interior node or leaf
- commit:ffe8235f3469503ca415c85d83567a01bd261618
- 04:30 PM rbd Feature #4550 (Resolved): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- The Ceph packages will be in EPEL which makes them suitable for Red Hat users deploying either RADOS, RGW or the Ceph...
- 04:04 PM Revision b8657fa0 (ceph): systest: restrict list error acceptance
- Only ignore errors after the midway point if the midway_sem_post is
defined.
Signed-off-by: Josh Durgin <josh.durgin... - 04:04 PM Revision 5af3d64f (ceph): systest: fix race with pool deletion
- The second test have pool deletion and object listing wait on the same
semaphore to connect and start. This led to er... - 03:24 PM Revision 0b5fcfff (ceph): ceph-disk: fix naming of a local variable in find_cluster_by_uuid
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:18 PM Revision 8a999ded (ceph): ceph-disk: rename some constants to upper case variable names
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:15 PM Revision 86e55f54 (ceph): ceph-disk: add some more docstrings
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:34 PM devops Feature #3924: ceph-deploy: package it
- Initial versions of rpm spec file and debian control file have been committed. Still need to move the package insta...
- 02:27 PM Feature #3984: api: Send Out DRAFT REST API for Review
- 02:27 PM Feature #3983: api: create initial DRAFT REST API Design
- 02:10 PM rgw Feature #4533 (Need More Info): rgw: ability to configure zone params
- 02:02 PM devops Feature #4376: chef: mon recipes
- 02:02 PM devops Feature #4377: chef: osd recipes
- 02:02 PM devops Feature #4468: ceph-deploy: log everything locally
- 02:02 PM devops Feature #3120: provide command "ceph-disk-list" that lists osd data/journal disks and their state
- 01:44 PM Bug #4320 (Resolved): ceph-deploy: getaddrinfo needs further change
- right, Dan. This is done.
- 01:12 PM Bug #4320 (Need More Info): ceph-deploy: getaddrinfo needs further change
- I think this turned into "update the test cluster hosts files", and I assume it was a lab task that's been done? Any...
- 01:40 PM Cleanup #2078: ceph tool: only output response data to stdout
- This will have bigger implications, as teuthology already has workarounds for the existing
broken behavior; need to ... - 01:37 PM CephFS Bug #4537 (In Progress): mds: hang on rmdir, unlink
- 01:36 PM Revision 543327b1 (ceph): ceph-disk: print subprocess.CalledProcessError on error
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:06 PM CephFS Bug #4530 (Fix Under Review): client: Assert failure on session close
- I pushed some fixes to wip-4530 for the client side part of this. Needs review.
- 09:49 AM CephFS Bug #4530 (In Progress): client: Assert failure on session close
- 12:57 PM CephFS Bug #4545: error creating empty object store. Invalid argument.
- Alright, I no longer think the apache2 signature is related. This seems like a proper bug in its own right.
- 12:04 PM CephFS Bug #4545: error creating empty object store. Invalid argument.
- This may be failing due to a package signing issue that I thought had been resolved. I'll hold onto this ticket until...
- 12:02 PM CephFS Bug #4545: error creating empty object store. Invalid argument.
- Added the yaml file I was using (needs 3 locked hosts) and the teuthology output as attachments.
- 12:00 PM CephFS Bug #4545 (Can't reproduce): error creating empty object store. Invalid argument.
- While running a teuthology test, mkcephfs failed with this error:
INFO:teuthology.task.ceph:Running mkfs on osd node... - 12:55 PM Revision 2d26bcc0 (ceph): ceph-disk: fix indention
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:48 PM devops Feature #4546 (Resolved): mkcephfs: add DEPRECATED warnings to all stdout user interactions
- We need to clearly indicate the mkcephfs is no longer the supported tool for doing ceph deployments and that users sh...
- 11:31 AM rbd Tasks #4210 (Resolved): get ceph and all libraries versions+patches in EPEL
- https://admin.fedoraproject.org/updates/FEDORA-EPEL-2013-0487/
- 11:25 AM rbd Tasks #4453 (Rejected): patch rhel 6.5 libvirt as necessary
- libvirt 0.10.2 and later is new enough already.
- 11:01 AM RADOS Feature #4544 (New): ReplicatedPG:: better handle read waiting on write case
- We currently block while holding the pg lock. We could probably be more clever about it.
- 10:41 AM Bug #4543 (Resolved): mon: corrupted store if monitor dies mid-sync
- This came to my attention after spending some time figuring out what rzerre's (@ #ceph) issue with the monitor was.
... - 10:36 AM rgw Bug #4508 (Resolved): Removing a bucket displays error
- Fixed, commit:70e0ee8ba955322832f0c366537ddf7a0288761e. Also cherry picked into bobtail (commit:90ab120a3c08f30654207...
- 09:39 AM rgw Bug #4508 (In Progress): Removing a bucket displays error
- 10:28 AM Linux kernel client Bug #2429 (Resolved): ceph-client: verify_authrizer_reply con method never called
- 10:28 AM Bug #4282 (Resolved): auth: could not find secret_id=0
- 10:07 AM Tasks #4542 (Resolved): fix append to uninitialized buffer in FlatIndex::created and unit tests f...
- "work in progress":https://github.com/dachary/ceph/commits/wip-4542
Create a set of unit tests in *src/test/os/Fla... - 10:01 AM Bug #4534 (Resolved): GetMissing must wait check for need_up_thru after receiving Missing
- commit:1cd51eb63a91fa0aa395c41572cfee4d53fbc7f5
- 09:57 AM rbd Bug #4540 (Fix Under Review): libceph: problem in ceph_osdc_msg_data_set
- Posted for review. And, uh, whoops, I didn't mark this "in progress."
From 50688843c0a8f4a7bd56a27f943972351c4b... - 09:52 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- OK I have a fix, and it doesn't do what I said it should...
Basically it just re-initializes the message when the ... - 09:25 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- I have dropped my connection to the plana66 console. I
think I'm done with it and will pursue a fix for this.
I'... - 09:23 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- I think the problem is that the message data fields
need to be initialized. That happens if the message
is allocat... - 09:20 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- I should probably talk with someone about what's going on
in ceph_osdc_start_request(). It has some logic that's
a... - 09:08 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- It is the data out field in the request message that's
being set more than once. (What I expected, but I've
verifi... - 09:05 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- I took the liberty of connecting to the console of plana66, which
appears to have been left in this state for that p... - 08:52 AM rbd Bug #4540: libceph: problem in ceph_osdc_msg_data_set
- Is there any chance this problem started with the addition
of that last commit:
06fb6a9f ceph: fix buffer pointer... - 09:47 AM CephFS Bug #4517 (Resolved): ceph_rename fails success case
- 09:38 AM Bug #4521: mon: starting a new osd crashes all mon's
- Evan, did this happen after a store conversion? The logs don't show it, but I suspect that there might be some corne...
- 07:23 AM Bug #4521 (In Progress): mon: starting a new osd crashes all mon's
- 09:11 AM Linux kernel client Feature #534 (Resolved): support CEPH_FEATURE_RECONNECT_SEQ in klibceph
- 08:23 AM rgw Cleanup #4541 (Resolved): refactor RGWUser class
- Per Yehuda's suggestion:
> Make RGWUser class look like librados::ObjectOperation, and librados::IoCtx::operate()....
03/24/2013
- 10:12 PM Revision 5d3fed47 (ceph): ceph-deploy: purge /var/lib/ceph data on finish
- The install task does this now that the package doesn't; we
need to too.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:03 PM Revision 9db05a25 (ceph): java: pretty print Ceph extent
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:51 PM Revision 60fe1367 (ceph): java: support ceph_get_file_extent_osds
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:51 PM Revision bc65ace0 (ceph): java: support ceph_get_osd_crush_location
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:51 PM Revision 486e5b99 (ceph): java: support ceph_get_osd_addr
- Adds a few JNI utilities from the Android project (license: Apache) to
help with IP address conversions. These functi... - 05:34 PM CephFS Bug #4537: mds: hang on rmdir, unlink
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-24_08:45:56-kernel-master-testing-basic/2501
cro... - 05:33 PM CephFS Bug #4537: mds: hang on rmdir, unlink
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-24_08:45:56-kernel-master-testing-basic/2503
<pr... - 03:18 PM CephFS Bug #4537: mds: hang on rmdir, unlink
- similar hang:...
- 02:41 PM CephFS Bug #4537 (Resolved): mds: hang on rmdir, unlink
- ...
- 05:31 PM rbd Bug #4540 (Resolved): libceph: problem in ceph_osdc_msg_data_set
- ...
- 04:06 PM Fix #1857: osd: reimplement shutdown()
- What about also flushing the journal on a graceful shutdown?
- 03:22 PM CephFS Bug #4539: include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::standby_trim_segments()
- ubuntu@teuthology:/a/sage-2013-03-24_08:29:36-fs-master-testing-basic/2410
- 03:22 PM CephFS Bug #4539: include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::standby_trim_segments()
- also ubuntu@teuthology:/a/sage-2013-03-24_08:29:36-fs-master-testing-basic/2414
- 03:22 PM CephFS Bug #4539 (Resolved): include/elist.h: 92: FAILED assert(_head.empty()) from MDLog::standby_trim_...
- ...
- 03:15 PM Bug #4538: os/FileStore.h: 191: FAILED assert(q.empty()) on shutdown
- seems to happen more when valgrind is running.. probably changes the timing?
- 03:15 PM Bug #4538 (Resolved): os/FileStore.h: 191: FAILED assert(q.empty()) on shutdown
- ...
- 12:50 PM Feature #3733 (Closed): osd: update leveldb submodule
- Closing this because we decided to use the distros versions of leveldb. See bug #3945.
- 11:16 AM CephFS Bug #4536 (Resolved): hadoop: receiving unexpected filenotfound exceptions
- Fixed by 150e914c7549f7197eff9fe980abd17a921799ce
- 04:10 AM Revision 78fd0965 (ceph): PendingReleaseNotes: mention renamin of cluster to zone
- radosgw-admin now uses the term 'zone'
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:58 AM Revision 4e68c203 (ceph): verify /var/lib/ceph not present on start
- Verify there is no /var/lib/ceph, just like we do with the cephtest
directory. We will need to change this (or make ... - 03:53 AM Revision 466fede7 (ceph): install: need sudo when purging /var/lib/ceph
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:31 AM Revision 8befbca7 (ceph): Merge branch 'next'
- 12:30 AM Revision ece43488 (ceph): client: don't set other if lookup fails in rename
- On rename, only set the other inode if the
lookup for the destination succeeds, otherwise we hit
a segv in set_other_...
03/23/2013
- 06:03 PM Revision 84738791 (ceph): Merge branch 'next'
- 06:03 PM Revision 836b97f3 (ceph): test/libcephfs: Test rename error cases
- Make sure that rename fails with the ENOENT
if the source path doesn't exist.
Signed-off-by: Sam Lang <sam.lang@inkt... - 06:01 PM Revision 8e6a970c (ceph): client: Fix rename returning ENOENT for dest
- Introduced by fc80c1dc6ee315ae5e039986602ffadba46cb43b,
the client should _not_ fail if the lookup for the
destinatio... - 12:39 PM CephFS Bug #4517: ceph_rename fails success case
- All working fine now. Thanks
- 12:19 PM CephFS Bug #4517: ceph_rename fails success case
- Thanks for testing/reporting that Noah. That commit last night was bogus. Pushed wip-4517b.
- 11:04 AM CephFS Bug #4517: ceph_rename fails success case
- I'm testing this branch, and I'm getting a segfault running the LibCephFS.Rename test....
- 11:53 AM CephFS Bug #4536 (Resolved): hadoop: receiving unexpected filenotfound exceptions
- Jobs have started failing with the following trace....
- 11:08 AM rbd Feature #4444 (In Progress): send/receive rbd snapshots
- 11:08 AM rbd Feature #4084 (In Progress): rbd: incremental backups
- 11:08 AM rbd Feature #4445 (In Progress): librbd: expose changed objects since a given snapshot
- 04:04 AM Revision 3f5f4326 (ceph): MDSMap: improve health check
- Note if the cluster is degraded. If so, indicate specifically which MDSs
are degraded and what state they are in.
S... - 01:22 AM Revision e77cd59b (ceph): MDSMap:: constify a bunch of methods
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:46 AM Revision dd670afc (ceph): mkcephfs: make remote temp directory name unique
- The predictable file name is a security problem.
CVE-2013-1882
Reported-by: Michael Scherer <misc@zarb.org>
Signed-... - 12:46 AM Revision 951f7e56 (ceph): init-ceph: push temp conf file to a unique location on remote host
- The predictable file name is a security problem.
CVE-2013-1882
Reported-by: Michael Scherer <misc@zarb.org>
Signed-... - 12:46 AM Revision 901fa435 (ceph): init-ceph: clean up temp ceph.conf filename on exit
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit 6... - 12:46 AM Revision 664ffa7d (ceph): common/MemoryModel: remove logging to /tmp/memlog
- This was a hack for dev purposes ages ago; remove it. The predictable
filename is a security issue.
CVE-2013-1882
... - 12:46 AM Revision 3569489b (ceph): os/FileJournal: fix aio self-throttling deadlock
- This block of code tries to limit the number of aios in flight by waiting
for the amount of data to be written to gro...
03/22/2013
- 10:24 PM Revision 838f1cde (ceph): preserve /var/lib/ceph on deb/rpm purge
- We should clobber configuration and log data, but *not* user data. Leave
/var/lib/ceph alone.
Signed-off-by: Sage W... - 10:22 PM Revision 4a6e3b97 (ceph): install, nuke: explicitly purge /var/lib/ceph
- The packages won't do this anymore.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:15 PM Revision d8f4be6e (ceph): mon: add 'osd crush add-bucket <name> <type>'
- This is (I think) the last missing piece to let you construct an entire
map via the CLI. The add/set commands will c... - 10:15 PM Revision b54db77e (ceph): crush: fix remove_item on bucket removal
- Remove the bucket if there are no references left.
Remove the name from the map even if it is a bucket (not sure why... - 10:15 PM Revision a60d7df4 (ceph): crush, mon: unlink vs remove
- Make an 'unlink' mode of remove that will remove a link to a bucket but
not remove the bucket itself. This refactors... - 10:15 PM Revision eae1532c (ceph): mon, crush: add some tests to build a DAG via the cli
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:15 PM Revision 4f2051c4 (ceph): mon: factor out _get_pending_crush() helper
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:15 PM Revision a54a4117 (ceph): crush: add link_bucket()
- Allow an existing bucket to get linked from a new position in the tree.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:15 PM Revision fe4e86c6 (ceph): crush: prevent formation of a loop
- If we are adding an item, ensure it cannot form a loop in the tree/map/
DAG.
Signed-off-by: Sage Weil <sage@inktank.... - 10:15 PM Revision 6cba563f (ceph): mon: 'ceph osd crush link ...' to add a link to an existing bucket
- Allow a second reference to an existing bucket to be added. This lets
you create a DAG instead of a tree using the C... - 10:15 PM Revision ee6b9937 (ceph): crush: add remove_item_under()
- Remove only instances of item nested beneath a particular ancestor.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:15 PM Revision 751b4bf8 (ceph): mon: add optional ancestor arg to 'ceph osd crush rm <item> [ancestor]'
- Remove only instances of the item underneath a particular ancestor.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:15 PM Revision 683f745c (ceph): crush: change find_roots(); add find_takes()
- The find_roots() was looking for nodes referenced by 'take', but those
aren't necessarily roots, which is what the ca... - 10:15 PM Revision 96e08ef1 (ceph): mon: allow removal of buckets via 'osd crush rm ...'
- No reason to limit this to leaves.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:15 PM Revision 05dac04b (ceph): mon: 'ceph osd crush add ...' to add a second link to an item
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:30 PM Revision 78d8faf4 (ceph): rgw: zone info is configurable
- Also rename RadosParams to ZoneParams
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:15 PM Revision 16063db2 (ceph): Merge remote-tracking branch 'upstream/wip_4435'
- Fixes: #4435
Reviewed-by: David Zafman <david.zafman@inktank.com> - 09:15 PM Revision 1cd51eb6 (ceph): PG::GetMissing: need to check need_up_thru in MLogRec handler
- Backport: bobtail
Fixes: #4534
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank... - 09:15 PM Revision d8668142 (ceph): PG,osd_types: improve check_new_interval debugging
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry... - 09:07 PM Revision 4fe4deaf (ceph): PG::GetMissing: need to check need_up_thru in MLogRec handler
- Backport: bobtail
Fixes: #4534
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank... - 09:06 PM Revision d611eba9 (ceph): PG,osd_types: improve check_new_interval debugging
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 08:35 PM Bug #4450: libceph: many socket "socket closed" issues on socket error
- OK, I've tested this in groups using the current ceph-client
"testing" branch:
06fb6a9 ceph: fix buffer pointer... - 02:14 PM Bug #4450: libceph: many socket "socket closed" issues on socket error
- Just a little update.
I've been testing the "testing" branch with groups of the
xfstests I use to see if I could ... - 12:16 PM Bug #4450 (In Progress): libceph: many socket "socket closed" issues on socket error
- I did a little work bisecting this about a week ago.
I'm not 100% trusting the result though, so I'm going
to try t... - 08:25 PM Revision c524e2e0 (ceph): common/MemoryModel: remove logging to /tmp/memlog
- This was a hack for dev purposes ages ago; remove it. The predictable
filename is a security issue.
CVE-2013-1882
... - 08:25 PM Revision 6a7ad2ea (ceph): init-ceph: clean up temp ceph.conf filename on exit
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 08:25 PM Revision 05173452 (ceph): init-ceph: push temp conf file to a unique location on remote host
- The predictable file name is a security problem.
CVE-2013-1882
Reported-by: Michael Scherer <misc@zarb.org>
Signed-... - 08:25 PM Revision f463ef78 (ceph): mkcephfs: make remote temp directory name unique
- The predictable file name is a security problem.
CVE-2013-1882
Reported-by: Michael Scherer <misc@zarb.org>
Signed-... - 08:07 PM Revision 0d3f065c (ceph): Merge pull request #130 from ceph/wip-fs-rename
- test: add ceph_rename test
Reviewed-by: Sage Weil <sage@inktank.com> - 08:02 PM Revision 2ed9f648 (ceph): teuthology: cleanup client dirs for workunit task
- This patch corrects an issue where a workunit task is
not cleaning up generated directories
if the 'all' key is used ... - 06:52 PM Revision 853dd359 (ceph): doc: Added {id} argument to OSD lost.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:23 PM Revision 020fb1a0 (ceph): rgw: s/cluster/zone
- Old cluster definition is what we'd call zone from now on.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:23 PM Revision 96ad9b14 (ceph): moved rgw/rgw_json.* common/ceph_json.*
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:23 PM Revision b07f3cda (ceph): rgw: add encode_json
- dump() just dumps the internal content of an object, encode_json()
create the object inside its own section. Note tha... - 06:23 PM Revision 8bd79157 (ceph): rgw: generic decode_json for containers
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:23 PM Revision 959b658f (ceph): rgw: introduce decode_json to easily decode json structures
- Introducing a new way to define the json structure of an
object, similar to what we do with bufferlist encode/decode.... - 06:23 PM Revision da337013 (ceph): rgw: decode RGWUserInfo using decode_json
- RGWUserInfo can be decoded using json_decode, and fix
the ->dump() method to match that decoding.
Signed-off-by: Yeh... - 06:23 PM Revision 53ba6c2d (ceph): rgw: rgw_jsonparser changes
- Now testing json_decode functionality.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:09 PM Revision 6d63752c (ceph): ceph-disk: re-add python 2.7 dependency comment
- FIXME!
Signed-off-by: Sage Weil <sage@inktank.com> - 05:06 PM Revision c9157a19 (ceph): Merge pull request #117 from ceph/wip-ceph-disk
- ceph-disk-* refactor
- 04:15 PM Revision 0981e466 (ceph): Merge branch 'next'
- 04:15 PM Revision 38a5acbb (ceph): osd: reenable 'journal aio = true'
- Now that #4079 is resolved. Reverts 1cfc3ae0.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:15 PM Revision e5940da9 (ceph): os/FileJournal: fix aio self-throttling deadlock
- This block of code tries to limit the number of aios in flight by waiting
for the amount of data to be written to gro... - 04:11 PM Feature #4299 (Fix Under Review): crush: command to set additional parents for an interior node o...
- 03:46 PM Revision a35b8650 (ceph): Merge pull request #137 from dalgaaf/wip-da-cleanup-includes
- Cleanup some twice included header
Reviewed-by: Sage Weil <sage@inktank.com> - 03:25 PM Bug #4505 (Resolved): package purge should not remove cluster data
- commit:838f1cde94f7243274a9fbd0742e7eed0c0fa4b1
- 03:17 PM CephFS Feature #4535 (New): mds: add group usage statistics gathering to the MemoryModel
- Once we've updated our MemoryModel (#4502, #4503) and have selected groups of in-memory data that we believe we can s...
- 03:03 PM Revision 6c79604c (ceph): test/test_snap_mapper.cc: remove twice included <tr1/memory>
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:02 PM Revision 00cf8178 (ceph): mon/MDSMonitor.cc: remove twice included MonitorDBStore.h
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:02 PM Revision a583029e (ceph): mon/LogMonitor.cc: remove twice included <sstream>
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:01 PM Revision 9dd5b209 (ceph): mon/AuthMonitor.cc: remove twice included <sstream>
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:01 PM Revision 11442609 (ceph): common/Formatter.h: remove twice included <list>
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:26 PM Fix #4435 (Resolved): backfill on full osd is not being prevented
- 02:16 PM Bug #4534 (Pending Backport): GetMissing must wait check for need_up_thru after receiving Missing
- on wip_bobtail_sam
- 01:36 PM Bug #4534 (Resolved): GetMissing must wait check for need_up_thru after receiving Missing
- The constructor checks, but not the MLogRec handler.
- 02:09 PM CephFS Bug #4517: ceph_rename fails success case
- Indeed. Updated wip-4517.
- 01:49 PM CephFS Bug #4517: ceph_rename fails success case
- I'm just skimming this in the middle of a meeting, but it looks like we're now failing the rename if the destination ...
- 01:31 PM CephFS Bug #4517 (Fix Under Review): ceph_rename fails success case
- 12:21 PM CephFS Bug #4517 (In Progress): ceph_rename fails success case
- 01:27 PM CephFS Feature #4442 (Fix Under Review): java: add topology API support
- 01:19 PM Bug #4421: osd: deep-scrub stat mismatch errors seen
- several other failures...
- 01:12 PM Bug #4282 (Fix Under Review): auth: could not find secret_id=0
- 11:11 AM devops Fix #4532: remove python 2.7 dependency in ceph-disk
- kai has 6.0.7, which is the latest squeeze, and python 2.6.6. <sigh>
- 10:21 AM devops Fix #4532: remove python 2.7 dependency in ceph-disk
- This also impacts debian, unless I don't have the latest version on kai (pretty sure I still do).
- 10:11 AM devops Fix #4532 (Resolved): remove python 2.7 dependency in ceph-disk
- see _check_output
centos has python 2.6.something - 11:07 AM rgw Feature #4533 (Resolved): rgw: ability to configure zone params
- That has been done as a part of the DR/georeplication development. We can make this specific feature available earlier.
- 10:02 AM Bug #4521: mon: starting a new osd crashes all mon's
- Thanks for the logs!
- 08:34 AM Bug #4521: mon: starting a new osd crashes all mon's
- Here are the logs.. I'm not sure mon.b went down this run, but a,c did.. I may not have waited long enough for mon.b...
- 05:31 AM Bug #4521: mon: starting a new osd crashes all mon's
- Can you reproduce this with 'debug mon = 20', 'debug paxos = 20' and 'debug ms = 1' on all monitors, and point me to ...
- 10:01 AM rbd Bug #4531 (Resolved): ObjectCacher: read waiters for parent data during copyup get reordered, cau...
- This assert was seen by several users using clones:...
- 09:42 AM CephFS Bug #4530 (Resolved): client: Assert failure on session close
During testing of #4451:
../../src/common/Cond.h: In function 'int Cond::Signal()' thread 7fe04c36f700 time 2013...- 09:26 AM Bug #4528 (Resolved): ceph cli split command fails during rados api tests
- ...
- 09:23 AM devops Bug #4520: ceph-disk-prepare intermittently fails on Centos
- There are 3 location between sgdisk and partprobe calls. I created a wip-4520 branch that has it.
This fixes the ... - 08:36 AM devops Bug #4520: ceph-disk-prepare intermittently fails on Centos
- where do you put the settle?
- 09:22 AM Bug #4527 (Resolved): journal Unable to read past sequence 0 but header indicates the journal has...
- ...
- 09:19 AM rbd Bug #4525: hang during librbd python tests
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-20_07:49:52-rbd-master-testing-basic/30
- 09:00 AM rbd Bug #4525 (Resolved): hang during librbd python tests
- ...
- 09:17 AM rbd Bug #4364 (Pending Backport): ObjectCacher: inconsistency after flatten
- 09:16 AM Bug #4079 (Resolved): osd: journal aio deadlock
- commit:e5940da9a534821d0d8f872c13f9ac26fb05a0f5
- 09:03 AM rbd Bug #4526 (Can't reproduce): rbd-fsx: ENOTEMPTY
- 2013-03-20T08:49:48.035 INFO:teuthology.orchestra.run.out:rbd_remove image_client.0-clone9: Directory not empty
wi... - 09:01 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-03-20_07:49:52-rbd-master-testing-basic/36
- 08:58 AM Linux kernel client Bug #4524 (Can't reproduce): libceph: bad ptr deref in rbtree for kick_requests
- ...
- 06:15 AM Bug #4523 (Duplicate): osd: read stats not updated
- A week ago I already added to http://tracker.ceph.com/issues/2209#change-18705 but as this bug is still closed I assu...
- 03:40 AM Revision 4d28a657 (ceph): stop ignoring osd leaks
- Note that the mds is the only one left that we are ignoring.
- 01:51 AM Revision 022903bf (ceph): PG: add helper for adding a timer event to retry backfill
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision f9c8190e (ceph): PG: halt backfill on RemoteReservationRejected in Backilling
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision 29a288f9 (ceph): ReplicatedPG: replica should post BackfillTooFull in do_scan if full
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision 000310fd (ceph): ReplicatedPG: add debug flag to skip full check at reservation
- This will make it easier to test the check in do_scan.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 01:51 AM Revision cec3d82e (ceph): OSDService: add too_full_for_backfill
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision 33aaea59 (ceph): PG: use OSDService::too_full_for_backfill in RepWaitBackfillReserved
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision cd735393 (ceph): PG: add helper for rejecting backfill reservation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:51 AM Revision 3ab4a09d (ceph): PG: add BackfillTooFull event for RepRecovering
- Replica will use this to notify Primary to stop backfilling.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 01:46 AM Revision f00f3bc4 (ceph): Merge remote-tracking branch 'upstream/wip_osd_shutdown_notification'
- Fixes: #1857
Fixes: #4267
Reviewed-by: Sage Weil <sage@inktank.com> - 01:46 AM Revision fab0be1f (ceph): Makefile: add MOSDMarkMeDown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:46 AM Revision 7bfaaf7a (ceph): OSD: notify mon prior to shutdown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 8d43a2ec (ceph): OSD: reorder OSD::shutdown
- Reorder teardown:
- pgs
- queues/threadpools
- persist superblock
- filestore
- timers
- messengers
Signed-off-by: S... - 01:37 AM Revision 95e9322c (ceph): ceph_osd: clear client_throttler prior to putting g_ceph_context
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 6119f297 (ceph): shared_cache: clear lru in destructor
- Otherwise, the live references will attempt to extricate
themselves from a disolving SharedLRU instance as the
member... - 01:37 AM Revision 210ecc58 (ceph): FileStore::stat: valgrind: don't read *st on error
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 51ae5098 (ceph): OpRequest: use OpRequestRef for OpHistory
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision bb125221 (ceph): OSD: clear OpHistory on shutdown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision b8929c42 (ceph): messages: add MOSDMarkMeDown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision edebb341 (ceph): OSDMonitor: factor out check_source helper
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision a2dba959 (ceph): Monitor: add MOSDMarkMeDown support
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision eb8dd0d4 (ceph): PG: clarify PG::deleting comment
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 264cd3ef (ceph): ReplicatedPG,OSD: move dequeueing into on_shutdown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 30b7a151 (ceph): OSD: move backfill_request_timer cleanup to OSDService::shutdown
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision e41554da (ceph): OSD: rename timer to tick_timer
- Only used for scheduling ticks - we should keep it
that way.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 01:37 AM Revision 9d076a0e (ceph): OSD: lookup_lock_raw_pg is dead
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:37 AM Revision 505bebbb (ceph): OSD: check for is_stopping after locking osd_lock or heartbeat_lock
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:25 AM Revision 7118df89 (ceph): Merge pull request #135 from ceph/wip-4519
- mon: AuthMonitor: delete auth_handler while increasing max_global_id
Reviewed-by: Sage Weil <sage@inktank.com> - 01:21 AM Revision 71ec9c6b (ceph): mon: AuthMonitor: delete auth_handler while increasing max_global_id
- By not deleting and setting NULL the session's auth_handler, we could
hit a scenario in which we'd end up dispatching... - 01:09 AM Revision 42a71c1d (ceph): FileJournal: quieter debugging on journal scanning
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
(cherry picked... - 01:03 AM Revision 6740d512 (ceph): FileJournal: quieter debugging on journal scanning
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com> - 12:53 AM rbd Bug #4522: RBD utility "showmapped" bug
- If I run rbd map lun-legacy-vm-bw-web01 one more time, It succeeds.
- 12:49 AM rbd Bug #4522: RBD utility "showmapped" bug
- ...
- 12:47 AM rbd Bug #4522: RBD utility "showmapped" bug
- Some new info.
I stopped VM and info about /dev/rbd62 and /dev/rbd/rbd/lun-legacy-vm-bw-web01 was wiped from fs au... - 12:04 AM Revision 7e8cc57d (ceph): doc: Fixed some typos.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
03/21/2013
- 11:49 PM rbd Bug #4522 (Can't reproduce): RBD utility "showmapped" bug
- Hello, my command "rbd showmapped" doesn't show
one rbd volume which is in use:... - 11:41 PM Revision 56183ebc (ceph): Merge pull request #128 from dalgaaf/wip-da-pylint
- Fix some python issues
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:35 PM Bug #4521 (Can't reproduce): mon: starting a new osd crashes all mon's
- While using 0.59 today i wanted to add an ost back in that had crashed its disks. I had told ceph that the osd was lo...
- 11:16 PM Revision 7a4b880f (ceph): Merge pull request #132 from ceph/wip-libcephfs-fix
- libcephfs: fix ceph_get_osd_crush_location
Reviewed-by: Sage Weil <sage@inktank.com> - 11:14 PM Revision 8f27fa61 (ceph): moving client.keyring creation out of ceph task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:32 PM Revision 76985007 (ceph): libcephfs: fix ceph_get_osd_crush_location
- (a) Allow NULL buffer when length is zero to get the target buffer
length. (b) fix edge case where buffer length is t... - 09:05 PM Bug #4505 (Fix Under Review): package purge should not remove cluster data
- 09:05 PM Bug #4519 (Resolved): mon: on auth/none/AuthNoneServiceHandler.h: FAILED assert(0) on v0.59 with ...
- commit:71ec9c6bd54d560cc2bca4b6d0dbb3e6961df135
- 06:24 PM Bug #4519: mon: on auth/none/AuthNoneServiceHandler.h: FAILED assert(0) on v0.59 with auth 'none'
- After some attempts at a successful pull request: https://github.com/ceph/ceph/pull/135
- 06:10 PM Bug #4519: mon: on auth/none/AuthNoneServiceHandler.h: FAILED assert(0) on v0.59 with auth 'none'
- pull request: https://github.com/ceph/ceph/pull/133
- 05:42 PM Bug #4519 (In Progress): mon: on auth/none/AuthNoneServiceHandler.h: FAILED assert(0) on v0.59 wi...
- I've come up with a fix and will push it shortly to wip-4519 for review.
- 05:39 PM Bug #4519 (Resolved): mon: on auth/none/AuthNoneServiceHandler.h: FAILED assert(0) on v0.59 with ...
- Xiaoxi came to us with the following issue both on #ceph and on ceph-devel....
- 08:30 PM devops Bug #4520: ceph-disk-prepare intermittently fails on Centos
- Adding "udevadm settle --timeout=10" appears to help, but I don't know if that is appropriate for all platforms. A 5...
- 07:18 PM devops Bug #4520 (Resolved): ceph-disk-prepare intermittently fails on Centos
- Probably a timing issue.
[ubuntu@gary-centos-01 ceph-deploy]$ ./ceph-deploy osd create gary-centos-01:/dev/sda
DE... - 07:54 PM Revision a72aaff6 (ceph): test: add ceph_rename test
- Triggers bug in ticket #4517
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 07:27 PM Revision fc3406f3 (ceph): FileStore: fix reversed collection_empty return value
- Backport: bobtail
Fixes: #4380
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inkta... - 07:25 PM Revision 9f7c6ad3 (ceph): FileStore: set replay guard on create_collection
- This should prevent sequences like:
rmcoll a
mkcoll a
touch a foo
<crash>
from causing trouble by preventing the rm... - 07:25 PM Revision 9932c9f0 (ceph): FileStore: _split_collection should not create the collection
- This will simplify adding a replay guard to create_collection.
Backport: bobtail
Signed-off-by: Samuel Just <sam.jus... - 06:52 PM Revision 7e7ea826 (ceph): client: use 4MB f_bsize and f_frsize for statfs
- Old stat(1) reports:
Block size: 1048576 Fundamental block size: 1048576
and the df(1) arithmetic works out. ... - 06:48 PM Feature #4267 (Resolved): osd: mark self immediately down on orderly (SIGINT, SIGTERM) shutdown
- 01:32 PM Feature #4267 (Fix Under Review): osd: mark self immediately down on orderly (SIGINT, SIGTERM) sh...
- 06:48 PM Fix #1857 (Resolved): osd: reimplement shutdown()
- 01:33 PM Fix #1857 (Fix Under Review): osd: reimplement shutdown()
- 06:21 PM Revision 49393017 (ceph): Merge pull request #127 from alram/master
- [doc] undisplayed notes, tips, and important sections
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 06:14 PM Revision ebfb81a3 (ceph): Merge pull request #120 from ceph/wip-msgr-acks
- msg/Pipe: fix seq handshake on reconnect
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:47 PM Revision 7ed0be19 (ceph): rados.py: remove unnecessary semicolon
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:46 PM Revision cffc2d50 (ceph): rados.py: fix bad indention
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:43 PM Revision 94966222 (ceph): rados.py: remove lenght modifier 'l' on format string
- Remove length modifier 'l' since it's ignored for python.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:23 PM Revision d81d2c02 (ceph): rados.py: fix 'Rados' has no member 'name'
- Lets store rados_id from __init__ and use this instead of 'name'.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect... - 04:57 PM Revision 14f26745 (ceph): crush: use const string& args
- Compiler will convert const char * to a std::string implicitly.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:57 PM Revision 4e2557a0 (ceph): crush: allow an item to be inserted twice
- Modify insert_item() to let you add an existing item to a new position
in the map.
Signed-off-by: Sage Weil <sage@in... - 04:36 PM Bug #4512 (Closed): librados: inaccessible headers referenced from librado.h[pp]
- This was already fixed in the master branch by commit:0e33490a76b67fea5d89dfea6950715aa7dfade8. The former next branc...
- 04:32 PM devops Bug #4518 (Resolved): ceph-deploy: osd create command fails
- commit:963d83eaf2ef7b682b86c37667d32226dbcaffbf
- 12:58 PM devops Bug #4518 (Resolved): ceph-deploy: osd create command fails
- on the latest master branch of ceph-deploy, osd create command fails
tamil@ubuntu:~/ceph-deploy-latest/ceph-deploy... - 04:14 PM Revision eed8d532 (ceph): rados.py: add missing space after ','
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:13 PM Revision e2df59e2 (ceph): ceph-create-keys: rename log to LOG since it's a constants
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:34 PM Feature #4201 (In Progress): osd: data loss: pg export/import/remove
- 01:33 PM Fix #4435 (In Progress): backfill on full osd is not being prevented
- 12:52 PM CephFS Bug #4517 (Resolved): ceph_rename fails success case
- ceph_rename has started returning -ENONET in the common case (source path exists, dest path doesn't exist). In the cl...
- 11:49 AM Feature #4516 (New): qa: add test to compile a simple program against librados, librbd, and libce...
- This can be a workunit that compiles something very simple that includes types from those libraries, just to verify t...
- 11:44 AM devops Feature #4515 (Duplicate): packaging: create qemu packages with rbd enabled for centos 6
- Set up a git repo with the spec file and any patches, like the ones described at https://nazar.karan.org/blob/nazar-r...
- 11:42 AM Feature #4514 (Closed): packaging: set up git repo with ceph spec file for centos 6
- Model it after the repos described at https://nazar.karan.org/blob/nazar-repos.git/eb4e1a3331197854e56b69cb9c8075ccc7...
- 10:43 AM Documentation #4513 (Won't Fix): blog: update 'monitor changes' article to state v0.59 instead of...
- The Monitor changes were in fact released in v0.59. They were introduced right after the v0.58 freeze, but didn't ma...
- 07:40 AM Revision d67eee1d (ceph): Merge branch 'next'
- 05:11 AM Revision 17d4a7c4 (ceph): doc/release-notes: v0.59
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:52 AM Revision 541cd3c6 (ceph): msg/Pipe: fix seq handshake on reconnect
- We go to the trouble to exchange our seq numbers during the handshake, but
the bit that then avoids resending old mes... - 04:17 AM Revision ac9fa433 (ceph): Fix tips in documentation
- Use of .. tip: instead of .. tip:: resulting in content not
being displayed.
Signed-off-by: Alexandre Marangone <ale... - 04:15 AM Revision cd96dbe2 (ceph): Fix important in documentation
- Use of .. important: instead of .. important:: resulting in content
not being displayed.
Signed-off-by: Alexandre Ma... - 04:10 AM Revision 33051578 (ceph): Fix notes in documentation
- Use of .. note: instead of .. note:: resulting in content not
being displayed
Signed-off-by: Alexandre Marangone <al... - 01:31 AM Revision e7cd598e (ceph): lock: make do_summary() respect --machine-type
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:42 AM Revision 18a782d0 (ceph): qa suites for upgrade task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:40 AM Revision 8ff32eb6 (ceph): stop and restart daemons as restart only starts.
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:07 AM Revision f2141142 (ceph): Merge pull request #126 from alram/master
- Update Chef deployment documentation
Reviewed-by: Sage Weil <sage@inktank.com>
03/20/2013
- 11:49 PM Revision e4854717 (ceph): Update Chef deployment documentation
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 11:43 PM Revision 66dca773 (ceph): os/FileStore: check replay guard on src for collection rename
- This avoids a problematic sequence like:
- rename A/ -> B/
- remove B/1...100
- destroy B/
- cre... - 11:17 PM Revision 131dce6e (ceph): Merge pull request #124 from ceph/wip-4509
- mon: DataHealthService: shutdown mon if failed to obtain disk stats
Reviewed-by: Sage Weil <sage@inktank.com> - 10:19 PM Revision ea570591 (ceph): PG::proc_replica_log: oinfo.last_complete must be *before* first entry ...
- Fixes: #4189
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 2dae6a68ee85a20220ee940dbe3... - 10:19 PM Revision aa38d87c (ceph): osd/PG: fix typo, missing -> omissing
- From ce7ffc34408bf32c66dc07e6f42d54b7ec489d41.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commi... - 10:17 PM Revision ac914834 (ceph): PG::proc_replica_log: adjust oinfo.last_complete based on omissing
- Otherwise, search_for_missing may neglect to check the missing
set for some objects assuming that if the need version... - 08:51 PM Revision 97fd7b61 (ceph): mon: DataHealthService: log to derr instead if we're about to shutdown
- Otherwise the message would -- or could -- be lost.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 08:49 PM Revision 51d62d32 (ceph): mon: DataHealthService: shutdown mon if failed to obtain disk stats
- Being unable to run a ::statfs() may be a symptom of something bigger.
We want to cleanly shutdown the monitor ASAP ... - 07:51 PM Revision b0136f98 (ceph): use ceph.com/git instead of github
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:36 PM Bug #4512 (Closed): librados: inaccessible headers referenced from librado.h[pp]
- This breaks compiling anything against librados.
- 06:34 PM Bug #4509 (Resolved): mon: on DataHealthService: FAILED assert(!stats.empty())
- This should have been resolved with commit commit:51d62d325c93a8aa7c93045d2e28b505f1491f2f being merged into master a...
- 10:15 AM Bug #4509: mon: on DataHealthService: FAILED assert(!stats.empty())
- Ran a monitor with store on dev/foo ; mid-execution moved dev/foo to dev/foo.bar to force statfs(dev/foo) to fail. M...
- 10:05 AM Bug #4509 (Resolved): mon: on DataHealthService: FAILED assert(!stats.empty())
- Tamil hit this last night.
Have been unable to reproduce it, but the only scenario in which this would happen is w... - 05:12 PM Revision 06ae5196 (ceph): Merge pull request #123 from dalgaaf/wip-da-sca-misc-1
- Some smaller misc fixes
Reviewed-by: Sage Weil <sage@inktank.com> - 04:08 PM Revision 5bf0331a (ceph): client/Client.cc: handle error if _lookup() fails
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:56 PM Revision fc41684e (ceph): qa/workunits/direct_io/test_sync_io.c: add proper error handling
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:37 PM Revision a8a5683e (ceph): test_short_dio_read.c: add proper error handling
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:15 PM Revision f9c108c7 (ceph): mds/Locker.cc: prefer prefix ++operator for iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:15 PM Revision 4151630c (ceph): mount/mount.ceph.c: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:48 PM Revision 9f37b49c (ceph): Merge pull request #122 from dalgaaf/wip-da-ceph-disk-1
- More fixes for ceph-disk
Reviewed-by: Sage Weil <sage@inktank.com> - 01:36 PM Revision 87691dc4 (ceph): ceph-disk: cast output of subprocess.Popen() to str()
- Cast output of subprocess.Popen() to str() to be able to use
str.split() and str.splitlines() without warnings from p... - 01:33 PM Revision 45d5544c (ceph): Merge pull request #121 from ceph/wip-4448
- mon: Monitor: clearer output on error during attempt to convert store
Reviewed-by: Sage Weil <sage@inktank.com> - 01:31 PM Revision c29812cd (ceph): mon: Monitor: clearer output on error during attempt to convert store
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:02 PM Revision 3575feb7 (ceph): ceph-disk: fix adjust_symlink() replace 'journal' with 'target'
- Replace 'journal' variable with 'target' since journal doesn't
exist in this function.
Signed-off-by: Danny Al-Gaaf ... - 01:01 PM Revision a27cb85b (ceph): ceph-disk: fix adjust_symlink() replace 'canonical' with 'path'
- Replace 'canonical' variable with 'path' since canonical doesn't
exist in this function.
Signed-off-by: Danny Al-Gaa... - 12:56 PM Revision 6d3247b5 (ceph): ceph-disk: there is no os.path.lstat use os.lstat
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:30 PM Revision 97b4f8d6 (ceph): ceph-disk: remove unused variable key from prepare_journal_dev()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:27 PM Revision 9daf6cfc (ceph): ceph-disk: fix except to catch OSError
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM Revision 0ada43f7 (ceph): ceph-disk: add missing space after >> operator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:54 AM rgw Feature #4511 (New): RGW: Reject requests containing invalid characters.
- Certain characters can break XML. Example.
2013-03-19 01:11:52.828185 7fe2c8de1700 10 RGWRados::cls_bucket_list: g... - 11:33 AM Revision d3c60dc8 (ceph): fix: Redefining name 'uuid' from outer scope (line 14)
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:21 AM Feature #4510: OSD scrub/repair should handle read error and truncate reasonably
- 10:52 AM Feature #4510 (Resolved): OSD scrub/repair should handle read error and truncate reasonably
- Currently, we hand the EIO to the client, which is not great.
- 11:17 AM Revision 6a8120d4 (ceph): ceph-disk: remove unused variables from list_partitions()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:10 AM Revision 3af7a1ac (ceph): ceph-disk: fix /dev/dm-[0-9] handling list_all_partitions()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:50 AM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- 1) I don't use filesystem snapshots at all.
2) I really have 3 big directories with 40000 files total
3) Some days ... - 09:40 AM CephFS Bug #4405: MDCache::populate_mydir can loop forever
- Sorry this got dropped on the floor. I found the problems.
The MDS never finishes the "populate_mydir()" function ... - 09:45 AM CephFS Bug #4451: client: Ceph client not releasing cap
- Uploaded an annotated log with only the lines related to the inode exhibiting the problem. The problem occurs from t...
- 05:27 AM Revision cbae6a43 (ceph): v0.59
- 12:16 AM rgw Bug #4508 (Resolved): Removing a bucket displays error
- Attempting to delete a bucket returns an error, although the bucket has been removed. This has been duplicated on two...
03/19/2013
- 11:35 PM CephFS Bug #4489: ceph fs hangs on file stat
- And MDS reload doesn't fixed problem until I rebooted one of FS clients.
- 11:34 PM CephFS Bug #4489: ceph fs hangs on file stat
- Oh, sorry for that. It seems, I failed with log. I will attach correct log next time problem persist. But the problem...
- 02:05 PM CephFS Bug #4489 (Need More Info): ceph fs hangs on file stat
- That log is from a standby MDS. You'll need to provide the log of the active MDS for us to do anything with it. :)
- 10:38 PM Cleanup #4507 (Resolved): mon: drop atomic_t
- This is not needed; everything is protected by the mon_lock.
Ideally, any boolean state variables would also be fo... - 09:53 PM Revision 7e778397 (ceph): Merge pull request #106 from ceph/wip-crush
- crush: update weights properly for DAG (not tree) maps
Reviewed-by: caleb miles <caleb.miles@inktank.com> - 09:17 PM Revision c3404c62 (ceph): Merge pull request #119 from dalgaaf/wip-da-ceph-disk
- Cleanup and fixes for wip-ceph-disk
- 09:07 PM Revision 9bcf5b64 (ceph): ceph-disk: rename local variable shadowing builtin
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:05 PM Revision 4adf0881 (ceph): ceph-disk: remove twice defined identical function unmount
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:02 PM Revision ea26ea0d (ceph): ceph-disk: remove twice defined function mount
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:00 PM Revision c57daa3c (ceph): ceph-disk: remove double defined function get_conf
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:51 PM Revision 57dde5c8 (ceph): ceph-disk: rename local variable shadowing builtin
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:46 PM Revision fabf36d2 (ceph): task/ceph: Revert extra check for running status
- Don't use exit status info to track daemon state. We need to find
a better way to do this for the restart task.
Sig... - 08:36 PM Revision b7e2a0d4 (ceph): Merge pull request #118 from dalgaaf/wip-da-enum
- QuorumService.h: use enum instead of static const int
Reviewed-by: Sage Weil <sage@inktank.com> - 08:33 PM Revision dfb1fbe7 (ceph): QuorumService.h: use enum instead of static const int
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:02 PM Revision 6a3aa2a2 (ceph): Missed adding rados_types.hpp to package
- Caused by 3bd48cbbadb7908dd833ccde75359f085828fc5c
feature 4207 implementation
Signed-off-by: David Zafman <david.za... - 07:52 PM Revision 20e4ba5c (ceph): ceph-disk: consolidate ceph-disk-* into a single binary
- ceph-disk prepare ...
ceph-disk activate ...
ceph-disk ...
This let's us share code (we were already duplicating a... - 07:52 PM Revision a019753b (ceph): ceph-disk: consolidate exceptions
- Use a single exception type, and catch it at the top level.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:52 PM Revision f287c6f9 (ceph): ceph-disk: simplify command dispatch
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:52 PM Revision c2602d74 (ceph): ceph-disk: install and package
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:12 PM Revision 66e27fa5 (ceph): suite: shorten subject a bit
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:42 PM Revision 2900bf4a (ceph): PendingReleaseNotes: fix typo
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:42 PM Revision 1597b3e3 (ceph): librbd: optionally wait for a flush before enabling writeback
- Older guests may not send flushes properly (i.e. never), so if this is
enabled, rbd_cache=true is safe for them trans... - 06:37 PM Revision c170022b (ceph): radosgw-admin: Adjust garbage collection settings.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 06:30 PM Revision 4e1737b9 (ceph): Merge branch 'wip-4197'
- 06:27 PM Revision 4d7e1e91 (ceph): osd: data loss: low space handling
- Automated test cases for feature #4197
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reported-by: Sam Just ... - 05:43 PM Revision 7f39704b (ceph): osd: fix load_pgs collection handling
- On a _TEMP pg, is_pg() would succeed, which meant we weren't actually
hitting the cleanup checks. Instead, restructu... - 05:43 PM Revision 0a09be99 (ceph): osd: fix load_pgs handling of pg dirs without a head
- If there is a pgid that passes coll_t::is_pg() but there is no head, we
will populate the pgs map but then fail later... - 05:43 PM Revision 2dc25dfd (ceph): OSD::load_pgs: first scan colls before initing PGs
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry... - 05:40 PM Revision 2fd8db29 (ceph): osd: Add digest of omap for deep-scrub
- Add ScrubMap encode/decode v4 message with omap digest
Compute digest of header and key/value. Use bufferlist
to ref... - 05:39 PM Revision 47f1a945 (ceph): Makefile: missing header
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:33 PM Revision ee59f517 (ceph): OSD: split temp collection as well
- Otherwise, when we eventually remove the temp collection, there might be
objects in the temp collection which were in... - 05:32 PM Revision 7ec68e2d (ceph): PG: ignore non MISSING pg query in ReplicaActive
- 1) Replica sends notify
2) Prior to processing notify, primary queues query to replica
3) Primary processes notify an... - 05:32 PM Revision b279b148 (ceph): FileJournal: queue_pos \in [get_top(), header.max_size)
- If queue_pos == header.max_size when we create the entry
header magic, the entry will be rejected at get_top() on
rep... - 05:32 PM Revision 56e0a129 (ceph): OSD: expand_pg_num after pg removes
- Otherwise:
1) expand_pg_num removes a splitting pg entry
2) peering thread grabs pg lock and starts split
3) OSD::con... - 05:30 PM Revision d6e678a6 (ceph): osd: update snap collections for sub_op_modify log records conditionaly
- The only remaining caller is sub_op_modify(). If we do have a non-empty
op transaction, we want to do this update, r... - 05:30 PM Revision 51c2c4d7 (ceph): osd: include snaps in pg_log_entry_t::dump()
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commi... - 05:30 PM Revision f0bf68ff (ceph): osd: unconditionally encode snaps buffer
- Previously we would only encode the updated snaps vector for CLONE ops.
This doesn't work for MODIFY ops generated by... - 05:30 PM Revision aa74fabd (ceph): osd: improve debug output on snap collections
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commi... - 05:21 PM Revision 020d1b16 (ceph): mon: use enum instead of static const int
- This way it compiles.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:15 PM Revision efc4b126 (ceph): mon/Paxos: set state to RECOVERING during restart
- This ensures that the paxos state is not active when the PaxosService
restart() methods run right afterwards, and tha... - 05:03 PM Revision 511f04f2 (ceph): Fixed so that installation works on a brand new CentOS system.
- Do yum install rather than yum reinstall for CentOS.
When exiting CentOS, yum erase the ceph-release rpm.
Signed-off... - 04:31 PM Revision 45843f75 (ceph): Makefile.am: fix misspelt header name
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 02:09 PM Bug #4436 (Resolved): FileJournal: queue_pos must be in [get_top(), header.max_size)
- 02:09 PM Bug #4449 (Resolved): osd/OSD.cc: 4626: FAILED assert(service.splitting(*i))
- 02:09 PM Bug #4050 (Resolved): recovery assert failure, osd/PG.cc: 6255: FAILED assert(query.query.type ==...
- 02:08 PM Bug #4452 (Resolved): PG::proc_primary_info(ObjectStore::Transaction&, const pg_info_t&)' thread ...
- 01:50 PM Bug #4506 (Resolved): teuthology: ceph task fails to stop a daemon
- I've reverted the line that broke this. I'll create a separate ticket to address the problem for the restart task.
- 01:10 PM Bug #4506 (Resolved): teuthology: ceph task fails to stop a daemon
- INFO:teuthology.task.ceph:Shutting down mds daemons...
ERROR:teuthology.task.ceph.mds.a:tried to stop a non-running ... - 01:10 PM Revision 1b0369bd (ceph): task/restart: Handle error from script correctly
- The exitstatus on the process is a gevent.AsyncResult
(not an int). Use the try/except pattern for handling
errors i... - 12:49 PM Bug #4505 (Resolved): package purge should not remove cluster data
- Currently our packages will basically destroy existing ceph clusters on package purge if that cluster is using the st...
- 12:18 PM Bug #4279 (Resolved): mon: received but didn't forward osd boot message
- commit:7aec13f749035b9bef5e398c1ac3d56ceec8eb81 and two follow-on commits.
- 12:17 PM devops Bug #3933 (Resolved): ceph-deploy gatherkeys silently fails if no host is specified
- commit:37d9abb4ba75b95a1d57febe290d8b5573e736bc
- 12:16 PM devops Bug #4420 (Resolved): chef script fails seems that /var/run/ceph is not created
- the fix in the current pull req looks right. we're running ceph-mon manually, so chef needs to create the dir.
- 11:43 AM rbd Feature #3817 (Resolved): librbd: make cache write-through until a flush is encountered
- commit:1597b3e3a1d776b56e05c57d7c3de396f4f2b5b2
- 11:39 AM devops Feature #3921 (Resolved): ceph-deploy: support RPM-based distros
- commit:ff05e605182a8378798d4cf82eb54a8a451270ca
- 10:55 AM Bug #4488 (Rejected): ceph-osd crash on server under heavy load
- that might explain it. 10 minutes is still a really long time!
in any case, this is a problem with the underlyi... - 10:11 AM Bug #4488: ceph-osd crash on server under heavy load
- md raid1 was resyncing at the same time, so i think it's quite likely, that sync/syncfs failed to finish its work
- 09:59 AM Bug #4488: ceph-osd crash on server under heavy load
- some errors like this in dmesg:
[ 6236.985604] INFO: task ceph-osd:3220 blocked for more than 120 seconds.
[ 6236... - 09:34 AM Bug #4488: ceph-osd crash on server under heavy load
- This means that sync(2) or syncfs(2) failed to return after 10 minutes. This is a pathologically loaded system (high...
- 10:38 AM CephFS Feature #4504 (Resolved): mds: trim based on total memory usage
- Right now the MDS only trims based on the count of the dentry cache. We should, based on a config option, optionally ...
- 10:21 AM CephFS Feature #4503 (New): mds: MemoryModel: include the different boost::pools we use
- We use a different boost::pool for each of CDir, CDentry, CInode, Capability. Include these pools, and any others we'...
- 10:19 AM CephFS Feature #4502 (New): mds: Make the MemoryModel useful
- Right now the MDCache's MemoryModel is trying to parse out usage from /proc/self/status. Switch it to use tcmalloc's ...
- 10:08 AM CephFS Tasks #4499: Identify fields in CInode which aren't permanently necessary
- Also, a small one but one that's everywhere: each of the classes in this sequence of bugs has an MDCache pointer. Pro...
- 09:43 AM CephFS Tasks #4499 (Resolved): Identify fields in CInode which aren't permanently necessary
- There are a number of fields in CInode that we don't always need. Examples include everything involved with projectio...
- 10:01 AM CephFS Cleanup #89 (Closed): mds: put inode dirty fields in dirty_bits_t to reduce memory footprint
- This is a less-specific duplicate of #4499 now.
- 10:01 AM CephFS Feature #4501 (Resolved): Identify fields in CDir which aren't permanently necessary
- The CDir has some machinery for handling things like dirty data that isn't always necessary. Audit it for these membe...
- 09:57 AM CephFS Tasks #4500 (New): Identify fields in CDentry which aren't permanently necessary
- CDentry is in far better shape than CInode in this regard, but audit it for things which we don't always need in memo...
- 09:16 AM CephFS Feature #4484: Enable Hadoop bindings to pull configuration options from the monitor
- cdca0babf9145a8f6e7613ab7026cf0968b3bc91
- 09:03 AM devops Bug #4498 (Resolved): ceph-deploy osd create doesn't set up symlink for single node
- > I'm trying to determine the ceph-deploy equivalent to the mkcephfs quick start
> we publish. I?m not sure how it ... - 09:00 AM CephFS Feature #3540 (Resolved): mds: maintain per-file backpointers on first file object
- 8b798867731d298c05d9f93b0c207a541d2b5e90 merged to master
- 08:45 AM Feature #4199 (Resolved): mon: data loss: low disk space handling
- Merged
- 06:09 AM Revision bee50463 (ceph): mon/PaxosService: handle non-zero return values
- If 7aec13f749035b9bef5e398c1ac3d56ceec8eb81 we started passing non-zero
return values to these completions; now we ha... - 05:54 AM Revision 16745191 (ceph): Merge branch 'next'
- 04:13 AM Revision d4775942 (ceph): ceph-disk-prepare: 'mkfs -t' instead of 'mkfs --type='
- Older mkfs (el6) doesn't like --type=.
Fixes: #4495
Reported-by: Alexandre Maragone <alexandre.maragone@inktank.com>... - 04:07 AM Revision 9029b091 (ceph): mds: Handle ENODATA returned from getxattr
- The osds might return ENODATA if we request an
xattr that doesn't exist. In this case, we're
requesting the 'parent'... - 04:00 AM Revision 7aec13f7 (ceph): mon/PaxosService: fix proposal waiter handling
- - Cancel the propsal waiters with EAGAIN on election, etc.
- Drop the wakeup helper and open-code the one caller.
Si... - 01:12 AM Revision 9d2f7f08 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
- 01:12 AM Revision 62cd409b (ceph): ceph-deploy qa suite for fs tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:05 AM Revision 640c1265 (ceph): ceph-deploy qa suite for rbd tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:00 AM Revision 167a26c3 (ceph): ceph-deploy qa suite for rados
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
Also available in: Atom