Activity
From 03/28/2013 to 04/26/2013
04/26/2013
- 11:57 PM Revision ab353c71 (ceph): upgrade: run blogbench against ceph-fuse
- Otherwise this runs on the local disk, not touching the ceph cluster.
- 11:52 PM Revision 928e241a (ceph): upgrade: run rados python test on bobtail to avoid polluting cluster wi...
- Extra pools from test.sh will make this fail:
2013-04-26T11:06:45.631 INFO:teuthology.task.workunit.client.0.err:tes... - 11:05 PM Revision 50e58b9f (ceph): ceph.spec.in: remove conditional checks on tcmalloc
- tcmalloc is available on all supported platforms now.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 11:05 PM Bug #4837: mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- I've added the logs from mon2 and mon3.
What I did notice, that now mon1 crashed without anything in the logs. mon... - 04:18 PM Bug #4837 (Need More Info): mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- I can't do any more without more logs, unfortunately. :(
In order to increase our odds of getting useful logs, I'v... - 02:23 PM Bug #4837: mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, so mon1, id 0, is leader. Then, suddenly, he's probing and goes into syncing. There's no logging here which is ...
- 01:41 PM Bug #4837: mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, I see part of what's happening here. The sync infrastructure includes a separate forwarding mechanism, and that...
- 01:06 PM Bug #4837 (In Progress): mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Well this is different — the monitor is addressing sync requests to itself!
- 12:50 PM Bug #4837 (Resolved): mon: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- I just upgraded 3 monitors from 0.56.4 to 0.60 (next branch) and saw a monitor crash when I ran:
$ ceph osd unset ... - 11:04 PM Revision 5c1782a5 (ceph): debian/rules: Fix tcmalloc breakage
- Since all currently supported platforms have tcmalloc
available and it is now the default, remove broken check code
t... - 11:04 PM Revision 6d348a1e (ceph): mon: cache osd epochs
- The monitor may get a series of messages from the OSD that prompt it to
send incremental maps (pg_temp updates, failu... - 10:37 PM Revision 1a6b87ea (ceph): ceph.spec.in: put ceph-disk-* et al in correct sbindir
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:29 PM Revision 86337936 (ceph): debian: fix ceph.install
- This got out of sync somewhere in cherry-picking all of these patches.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:27 PM Revision 0650fa95 (ceph): monitor: assert out early if we get our own sync_start back
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 10:24 PM Revision 1e6f02b3 (ceph): mon: update assert for looser requirements
- Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 09:07 PM Revision ba13173b (ceph): doc: Deleted old index. Generates warnings otherwise.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:07 PM Revision 9a7a0753 (ceph): doc: General purpose pre-flight checklist.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:07 PM Revision 9e775f15 (ceph): doc: Modified Ceph deployment landing page.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:06 PM Revision fb8119ce (ceph): doc: Added general pre-flight checklist for ceph-deploy.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:06 PM Revision 3433aa8f (ceph): doc: Removed old ceph-deploy placeholder.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:05 PM Revision 9c0c4c17 (ceph): doc: Removed Chef section. Now appears in new Ceph wiki.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:05 PM Revision c25144e8 (ceph): doc: Added Key Management for ceph-deploy.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:04 PM Revision d0d1554a (ceph): doc: Added "Add/Remove Monitors" section for ceph-deploy.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:04 PM Revision f24dbdef (ceph): doc: Added Create a Cluster section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:03 PM Revision b631cc67 (ceph): doc: Added ceph-deploy package management (install | uninstall ) section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:02 PM Revision d85c6904 (ceph): doc: Added new quick start preamble and index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:01 PM Revision 3ff7eef9 (ceph): doc: Added ceph-deploy preflight.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:01 PM Revision 93656740 (ceph): doc: Added ceph-deploy quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:40 PM Revision 7406981a (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>
(cherry picked fro... - 08:40 PM Revision 9419dca6 (ceph): ceph-disk: add missing space after comma
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 0080d1df7c7950e051840a543fc4bdabe6c... - 08:40 PM Revision 14a348dc (ceph): ceph-disk: fix Redefining name 'uuid' from outer scope
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 058eb923c5b7dab611901fdd1724ce2a7c1... - 08:40 PM Revision 7326ea63 (ceph): ceph-disk: define exception type
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 4c6d6442a89adc5b56e99cb4d2ed572f2ad... - 08:40 PM Revision 0e47d312 (ceph): ceph-disk: merge twice defined function is_mounted(dev)
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit eaf31bf9f90ba9709a57a6870dbafa21142... - 08:40 PM Revision ee452ebe (ceph): ceph-disk: fix naming of local variable in is_mounted()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 3dd8b461219e64bb0f7a210dba5a9ab7c64... - 08:40 PM Revision 1b86b1c7 (ceph): ceph-disk: fix some (local) variable names
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit c4eb7e6ddd593cd45ab8343da01355be738... - 08:40 PM Revision c71fb8d5 (ceph): ceph-disk: CalledProcessError has no output keyword on 2.6
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
(cherry picked from commit a793853850ee135de14b9237f7023cadcdb8... - 08:40 PM Revision 0b42b1ed (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... - 08:40 PM Revision bd8bb984 (ceph): ceph-disk: print subprocess.CalledProcessError on error
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 543327b1f2a9efe8083bb196433c4bcf838... - 08:40 PM Revision d26a0342 (ceph): ceph-disk: add some more docstrings
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 86e55f5448c4b5b46b74d2d89b01d1e64b1... - 08:40 PM Revision 63eb8507 (ceph): ceph-disk: rename some constants to upper case variable names
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 8a999ded088e688fd3f4a7c27127b7c06f0... - 08:40 PM Revision ecb34b81 (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>
(cherry picked from commit 0b5fcfffe6d2f69bd4318cc93ef73195d94... - 08:40 PM Revision d714049d (ceph): ceph-disk: rename some local variabels in list_*partitions
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit b7d7e6894c550a7afa8dfb5bfa2bc54b5d3... - 08:40 PM Revision 153994cd (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>
(cherry picked... - 08:40 PM Revision 0c8efc06 (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>
... - 08:40 PM Revision 9da81e4e (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., /... - 08:40 PM Revision bf3f8702 (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 ... - 08:40 PM Revision 24d729c5 (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... - 08:40 PM Revision 0182973b (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>
(cherry picked from commit 562e1716... - 08:40 PM Revision b9f86d96 (ceph): fix: Redefining name 'uuid' from outer scope (line 14)
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit d3c60dc8cad1db1d5df1c740bc805aaf9ba... - 08:40 PM Revision 01152115 (ceph): ceph-disk: add missing space after >> operator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 0ada43f79d2b1f9f84367e558c6d1a3e90e... - 08:40 PM Revision 9464284f (ceph): ceph-disk: fix except to catch OSError
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 9daf6cfce2d57509d896eae28bb97146a68... - 08:40 PM Revision ffe024b8 (ceph): ceph-disk: remove unused variable key from prepare_journal_dev()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 97b4f8d66bef2328fa53f9e508eb38f8b8d... - 08:40 PM Revision 329f279c (ceph): ceph-disk: there is no os.path.lstat use os.lstat
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 6d3247b5c02c39a66666a5833106dbc2304... - 08:40 PM Revision 690ab6b3 (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... - 08:40 PM Revision 1ffc89af (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 ... - 08:40 PM Revision e92baf50 (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... - 08:40 PM Revision 02d48351 (ceph): ceph-disk: re-add python 2.7 dependency comment
- FIXME!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 6d63752c8fde91cdab306d1ca689690b269fe977) - 08:40 PM Revision 0113e533 (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... - 08:40 PM Revision 970348fc (ceph): ceph-disk: fix indention
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 2d26bcc07162a5176cdbc1748b829e3f396... - 08:40 PM Revision b4176baf (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... - 08:40 PM Revision 3cbc0d0c (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>
(cherry pick... - 08:40 PM Revision 8901e02d (ceph): ceph-disk: simplify command dispatch
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit f287c6f90af0dfdd41358846b069aa3c54b600b3) - 08:40 PM Revision b807d8ba (ceph): ceph-disk: install and package
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit c2602d749023b24ac22d8cfce6e04889078f14d8)
Con... - 08:40 PM Revision 9c46dfb2 (ceph): ceph-disk: rename local variable shadowing builtin
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 57dde5c8b18ff4ccd53a30bb94119c0ffce... - 08:40 PM Revision 0da87db1 (ceph): ceph-disk: remove double defined function get_conf
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit c57daa3c6e03e8974e133d3a2d9bc3d6f06... - 08:40 PM Revision 8dd8cbac (ceph): ceph-disk: remove twice defined function mount
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit ea26ea0d81a23aa76076ad5441c3b1aadfb... - 08:40 PM Revision bd1036dd (ceph): ceph-disk: remove twice defined identical function unmount
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 4adf088107586be7b356d1e963570cdab23... - 08:40 PM Revision 3ec61f85 (ceph): ceph-disk: rename local variable shadowing builtin
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 9bcf5b64f45ab6c4bdedf820ed111319b2d... - 08:40 PM Revision 0b4e85fe (ceph): ceph-disk: fix /dev/dm-[0-9] handling list_all_partitions()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 3af7a1ac5bf24bf832d7180002281d6b585... - 08:40 PM Revision 6fa6cd85 (ceph): ceph-disk: remove unused variables from list_partitions()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 6a8120d4b0c4cfa851d473532eb2366534f... - 08:40 PM Revision ea07b0e1 (ceph): ceph-disk-prepare: use os.path.realpath()
- My janky symlink resolution is broken in various ways.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked fr... - 08:40 PM Revision d05b4391 (ceph): ceph-disk-prepare: clean up stupid check for a digit
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit f03f62697f170d42b4b62c53d2860ff2f24a2d73) - 08:40 PM Revision e4a52002 (ceph): ceph-disk-prepare: verify device is not mounted before using
- Make sure the data and/or journal device(s) are not in use (mounted)
before using them. Make room for additional "in... - 08:40 PM Revision 5ad4120a (ceph): ceph-disk-prepare: verify device is not in use by device-mapper
- Be nice and tell the user which devices/mappings are consuming the device,
too.
Signed-off-by: Sage Weil <sage@inkta... - 08:40 PM Revision 35eac085 (ceph): ceph-disk-prepare: move in-use checks to the top, before zap
- Move the in-use checks to the very top, before we (say) zap!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pic... - 08:40 PM Revision 897413f9 (ceph): ceph-disk-activate: don't override default or configured osd journal path
- There is no reason not to rely on the default or obey any configured
value here.
Fixes: #4031
Signed-off-by: Sage We... - 08:40 PM Revision 739b013c (ceph): ceph-disk-activate: rely on default/configured keyring path
- No reason to override the default or configured value here.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pick... - 08:40 PM Revision 7c1edc0c (ceph): Revert "ceph-disk-activate: don't override default or configured osd jo...
- This reverts commit 813e9fe2b4291a1c1922ef78f031daa9b78fe53b.
We run --mkfs with the osd disk mounted in a temporary... - 08:40 PM Revision a6ecf928 (ceph): Revert "ceph-disk-activate: rely on default/configured keyring path"
- This reverts commit 936b8f20af1d390976097c427b6e92da4b39b218.
This is necessary because we mount the osd in a tempor... - 08:40 PM Revision 568485be (ceph): ceph-disk-activate: abort if target position is already mounted
- If the target position is already a mount point, fail to move our mount
over to it. This usually indicates that a di... - 08:40 PM Revision 19a2cf58 (ceph): ceph-disk-activate: identify cluster .conf by fsid
- Determine what cluster the disk belongs to by checking the fsid defined
in /etc/ceph/*.conf. Previously we hard-code... - 08:40 PM Revision 455cb325 (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>... - 08:40 PM Revision caad1874 (ceph): ceph-disk-prepare: do partprobe after setting final partition type
- This is necessary to kick udev into processing the updated partition and
running its rules.
Signed-off-by: Sage Weil... - 08:40 PM Revision 34fba357 (ceph): ceph-disk-activate: use full paths for everything
- We are run from udev, which doesn't get a decent PATH.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked fr... - 08:40 PM Revision d7084037 (ceph): ceph-disk-activate: pull mount options from ceph.conf
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
(cherry picked from commit e7040f55f01db3de7d5ce... - 08:40 PM Revision 5c5021b4 (ceph): ceph-disk-prepare: add initial support for dm-crypt
- Keep keys in /etc/ceph/dmcrypt-keys.
Identify partition instances by the partition UUID. Identify encrypted
partiti... - 08:40 PM Revision 28d11938 (ceph): udev: trigger on dmcrypted osd partitions
- Automatically map encrypted journal partitions.
For encrypted OSD partitions, map them, wait for the mapped device t... - 08:40 PM Revision 632be442 (ceph): ceph-disk-prepare: always force mkfs.xfs
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
(cherry picked from commit d950d83250db3a179c4b6... - 08:40 PM Revision 405e0ea1 (ceph): debian: fix start of ceph-all
- Tolerate failure, and do ceph-all, not ceph-osd-all.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from... - 08:40 PM Revision d1775daf (ceph): ceph-disk-prepare: -f for mkfs.xfs only
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit fecc3c3abf1176f4c7938e161559ea2db59f1cff) - 08:40 PM Revision abdac6fd (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... - 08:40 PM Revision 3441acf3 (ceph): debian: require cryptsetup-bin
- This is needed for ceph-disk-prepare's dmcrypt support.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked f... - 08:40 PM Revision 8f7e3e7d (ceph): ceph.spec.in: add new Requires from ceph-disk-prepare
- Added new Requires from ceph-disk-prepare: cryptsetup, gptfdisk,
parted and util-linux.
Signed-off-by: Danny Al-Gaaf... - 08:40 PM Revision 181ebdee (ceph): debian: put ceph-mds upstart conf in ceph-mds package
- Fixes: #3157
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 23ad3a46a0099e263f43e0f0c1df1d21c... - 08:40 PM Revision fa23919e (ceph): ceph-disk-activate: factor mounting out of activate
- The activate stuff is generic for any OSD, regardless of whether we want
to mount it or not. Pull that part out.
Si... - 08:40 PM Revision e6d5aa05 (ceph): ceph-disk-activate: add --mark-init INITSYSTEM option
- Do not assume we will manage via upstart; let that be passed down via the
command line.
Signed-off-by: Sage Weil <sa... - 08:40 PM Revision aa428017 (ceph): ceph-disk-activate: detect whether PATH is mount or dir
- remove in-the-way symlinks in /var/lib/ceph/osd
This is simpler. Just detect what the path is and Do The Right Thin... - 08:40 PM Revision 5e0892fd (ceph): ceph-disk-prepare: refactor to support DIR, DISK, or PARTITION for data...
- Lots of code reorganization collapsed into a single commit here.
- detect whether the user gave us a directory, disk... - 08:40 PM Revision 494533a5 (ceph): upstart/ceph-hotplug: tell activate to start via upstart
- This will mark the OSD data dir as upstart-managed.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from ... - 08:40 PM Revision 9ea32e5f (ceph): upstart: ceph-hotplug -> ceph-osd-activate
- This is a more meaningful name.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e011ad128e7f3... - 08:40 PM Revision 74b56270 (ceph): ceph-disk-activate: specify full path for blkid, initctl, service
- /sbin apparently isn't in the path when udev runs us.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked fro... - 08:40 PM Revision ffb0613e (ceph): ceph-disk-activate: auto detect init system
- Look for an option 'init' in ceph.conf. Otherwise, check if we're ubuntu.
If so, use upstart. Otherwise, use sysvin... - 08:40 PM Revision 8b771bf9 (ceph): udev: trigger ceph-disk-activate directly from udev
- There is no need to depend on upstart for this.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from comm... - 08:40 PM Revision 656305f6 (ceph): ceph-disk-activate: catch daemon start errors
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 690ae05309db118fb3fe390a48df33355fd068a0) - 08:40 PM Revision e1624e46 (ceph): debian: start/stop ceph-all event on install/uninstall
- This helps us avoid the confusing situation with upstart where an individual
daemon job is running (like ceph-osd id=... - 08:40 PM Revision 8c4c53ab (ceph): ceph-disk-prepare: align mkfs, mount config options with mkcephfs
- 'osd mkfs ...', not 'osd fs mkfs ...'. Sigh. Support both.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry pic... - 08:40 PM Revision 05efb7ab (ceph): init-ceph: consider sysvinit-tagged dirs as local
- If there is a 'sysvinit' file in the daemon directory in the default
location (/var/lib/ceph/$type/ceph-$id), conside... - 08:40 PM Revision 39df4c81 (ceph): init-ceph: iterate/locate local sysvinit-tagged directories
- Search /var/lib/ceph/$type/ceph-$id and start/stop those daemons if
present and tagged with the sysvinit file.
Signe... - 08:40 PM Revision f43c339d (ceph): upstart/ceph-hotplug: drop -- in ceph-disk-activate args
- We would like to transition to
ceph-disk-activate --mount DEV
and away from a generic multi-definition PATH argume... - 08:40 PM Revision f97f49b1 (ceph): ceph-create-keys: create mds bootstrap key
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 809143f16c70483ba5bb429dea812d31b67f2b49) - 08:40 PM Revision 919b0aed (ceph): debian: include /var/lib/ceph/bootstrap-mds in package
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e80675a0f333c04452d4822fd0eb3c6e92eda3df) - 08:36 PM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- Oh, I actually see a couple of fixes that match this description in subsequent commits that haven't reached gitbuilde...
- 08:33 PM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- So, I tried master, 3cc106453f79a0a0c332b164e282a35234a85659 with
curl -D - -H "X-Auth-Token: ..." 'http://localhost... - 08:31 PM Revision e0c39c1e (ceph): Merge branch 'wip-4822' into next
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 07:42 PM Revision 2211b1d7 (ceph): Fix improperly spaced line.
- 07:37 PM Revision ebbdef29 (ceph): monitor: squash signed/unsigned comparison warning
- This is a safe range to do comparisons against, and we compare
against the signed rank inside the loop.
Signed-off-b... - 07:33 PM Revision 56ac098b (ceph): Merge branch 'wip-4760' into next
- 07:32 PM Revision 5fa3cbf5 (ceph): mon: use brute force to find a sync provider if our first one fails
- We try and select a random monitor first, but if that fails we should
make sure that nobody's available before assert... - 07:24 PM Revision a92b4c75 (ceph): Merge branch 'wip-mon-fwd' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 07:10 PM Revision 1670a2bf (ceph): rgw: trivial cleanups post code review
- Following code review of #4760.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:10 PM Revision 7144ae86 (ceph): rgw: fix bucket count when stating account
- We need to add up the num of buckets and not just set it
as we don't read the entire list of buckets in one operation... - 07:10 PM Revision 960eac26 (ceph): rgw: fix plain formatter flush
- The plain formatter flush needs to append eol if needed, and
not to clear the sections stack.
Signed-off-by: Yehuda ... - 07:10 PM Revision 2264078a (ceph): rgw: swift list containers can return 204
- In order to keep compatibility with swift, if a plain formatter
is being used, we should return 204 when there are no... - 07:10 PM Revision f2df8762 (ceph): rgw: fix bucket listing when reaching limit
- Bucket listing was broken when limit was set.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:10 PM Revision a8b1bfa1 (ceph): rgw: fix list buckets limit
- There was an issue when limit was being set, we didn't
break from the iterating loop if limit was reached. Also,
S3 d... - 07:10 PM Revision c880e957 (ceph): rgw: fix compilation for certain architectures
- Casting.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:06 PM Revision e4c13afa (ceph): Merge branch 'next'
- Get fix for raring builds
- 07:05 PM Revision 98f532e8 (ceph): Makefile.am: Add -lpthread to fix build on newer ld in Raring Ringtail
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 06:25 PM Revision f21dcdc9 (ceph): ceph config data goes in conf, not config
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 06:25 PM Revision df4105b6 (ceph): ceph config data goes in conf, not config
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 06:12 PM Revision 741f4685 (ceph): mon: fix Monitor::pick_random_mon()
- The other arg isn't used, so remove the (broken) handling for that case.
If we re-add it later, model after the MonCl... - 06:10 PM Bug #4815: mon: leveldb grows quickly and without bound
- other mons are 36GB, so it's not done yet. but stuck.
- 06:05 PM Bug #4815: mon: leveldb grows quickly and without bound
- the mon.a is getting stuck in leveldb:...
- 05:29 PM Bug #4815: mon: leveldb grows quickly and without bound
- New logs have been uploaded to cephdrop as "mikedawson/ceph-mon.*.log". They show starting up the three monitors. mon...
- 04:23 PM Bug #4815: mon: leveldb grows quickly and without bound
- can you reproduce with the latest next, capture the mon.a log, and also attach to the process after it stops making p...
- 05:48 PM Revision cbc3b91c (ceph): mon: mark PaxosServiceMessage forward fields deprecated
- These are no longer used; we manage forward state explicitly via the
Monitor sessions instead. Mark them deprecated ... - 05:48 PM Revision 77c068d1 (ceph): mon: fix double-forwarding check
- The PaxosServiceMessage fields are no longer filled in. Use Session::proxy_con
instead.
Signed-off-by: Sage Weil <s... - 05:47 PM devops Feature #4766: ceph-deploy: commands should continue to execute the next argument in case of fail...
- ceph-deploy commands [new, mon create, osd create,...] exit when any given argument fails. it is either in the beginn...
- 05:27 PM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- Greg, checked that and now, hitting this on only one monitor [mon.c on burnupi45].
leaving the test machines burnu... - 04:40 PM Bug #4747 (In Progress): Upgrade monitors from argonaut->bobtail->next fails w/"Existing store ha...
- Looked at this briefly and am having Tamil check it again. From the logs it appears the monitors never formed a quoru...
- 02:02 PM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- upgraded the osds and mds as well. but the monitors are stuck up. one of the monitors seems to be up.
ubuntu@burnu... - 02:01 PM Bug #4747 (New): Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not be...
- I am not sure, why this was marked "cant reproduce" but am hitting this on my local cluster [burnupi39, burnupi45]
... - 05:24 PM Revision e3b602ad (ceph): osd: Fix logic in OSDMap::containing_subtree_is_down()
- Check for up OSDs as we walk up the crushmap hierarchy
fixes: #4822
Signed-off-by: David Zafman <david.zafman@inkta... - 05:19 PM Revision a2a23ccd (ceph): debian/rules: use multiline search to look for Build-Depends
- When Build-Depends was split into multiple lines (in commit
8f5c665744e58d6d51a1e86de55c1399f51cc1c3), the grep for
l... - 05:12 PM Revision f768fbba (ceph): client: re-fix cap releases
- Encode cap releases if NOT replay. <facepalm> Thanks, Greg!
Signed-off-by: Sage Weil <sage@inktank.com> - 04:51 PM Revision 5121e56c (ceph): client: don't embed cap releases in clientreplay
- If the client is sending replay requests, avoid sending embedded caps,
since the mds already has the client's caps fr... - 04:33 PM rbd Bug #4446: librbd: crash from opensolaris vm
- I tried booting in several configurations, and couldn't get it to fail. I used ceph 0.56.4, and qemu 1.0 for ubuntu 1...
- 01:55 PM rbd Bug #4446: librbd: crash from opensolaris vm
- As an ex-Sun employee, I can point out that this is an *ancient* version of S10; there've been many many updates sinc...
- 04:20 PM devops Bug #4823 (Resolved): ceph-deploy: install not implemented for RHEL 6.3
- Resolved with the following commit:
commit c32a80a20ad2e29bf05bb67a244bbc995a31a606
Author: Gary Lowell <glowell@... - 04:16 PM Bug #4810: mon: forwarded messages have weird priorities
- We've discussed this and are not sure if we want to change the way prioritization works or not. The observable sympto...
- 04:12 PM Bug #4810: mon: forwarded messages have weird priorities
- wip-mon-fwd
- 03:44 PM rbd Bug #4827: librbd: use after free of ceph context or something in it
- Segfaults with different backtraces occurred with and without caching enabled. Unfortunately the first core file is c...
- 09:21 AM rbd Bug #4827 (Resolved): librbd: use after free of ceph context or something in it
- From teuthology:/a/teuthology-2013-04-26_02:29:00-rbd-next-testing-basic/1393/teuthology.log:...
- 03:22 PM devops Feature #3255: ceph-disk: allow prepare without activate (for spares)
- 03:13 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Not single commit and not THIS bug commit. I got sure stuck (IMHO 100% last 3 of 3, not second) mon, need "kill" twic...
- 11:10 AM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- That commit doesn't touch the monitor code, and I don't believe those osd types are used in the monitor either. What ...
- 08:42 AM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Post-problems IMHO solved... Upgrading gcc to 4.8.0 & -fno-aggressive-loop-optimizations (but this is black magic and...
- 02:34 PM Tasks #4844 (Resolved): blueprint: stats infrastructure (collectd, statsd, graphite, ...)
- 02:33 PM Tasks #4843: blueprint: crush library, language extensions
- 2 racks, 2 osds on first rack, 1 on second
hosts have 2 ssds 4 spinning, want 3 replicas split by host primary on ss... - 02:32 PM Tasks #4843 (Resolved): blueprint: crush library, language extensions
- 02:30 PM Tasks #4842 (Rejected): blueprint: erasure coded pg infrastructure
- 02:29 PM Tasks #4841 (Resolved): blueprint: rados namespaces
- 02:24 PM Feature #4214 (Duplicate): osd: optionally tolerate and repair EIO on deep scrub reads
- 02:23 PM Fix #4840 (Resolved): mon: transition from old-style allow command to new command descriptions
- 02:20 PM Feature #4107 (Duplicate): Usage quota for rados pools
- 02:12 PM Cleanup #4828: dan: don't respond to e-mail via your phone in the bathroom
- 09:45 AM Cleanup #4828 (Rejected): dan: don't respond to e-mail via your phone in the bathroom
- I had an e-mail exchange with Dan this morning about some
problems with gitbuilder that Mark Nelson reported to me.
... - 02:09 PM Feature #4839 (Resolved): api: make new CLI send old version of commands to old monitors during u...
- 02:06 PM Feature #4455 (In Progress): api: move '--format' into just another command argument
- 02:06 PM rbd Feature #4838 (New): rbd-fuse: use the low level fuse interface
- The low level interface will let us parse custom options (i.e. standard ceph ones).
- 02:05 PM Bug #4822 (Resolved): After 5 minutes a down OSD is NOT marked out
- e3b602adf7527101e4fd198263c8f7c1d4b5d194
- 01:08 PM rgw Feature #4745 (Fix Under Review): rgw: radosgw-admin command to stat object
- 01:08 PM rgw Feature #4573 (Resolved): Create User Quota Blueprint
- 01:07 PM rgw Feature #4312 (Fix Under Review): rgw: multisite: log metadata changes
- 01:06 PM rgw Feature #3274 (Resolved): rgw: RESTful admin api for user admin
- 01:06 PM rgw Feature #4464 (Resolved): rgw: bucket commands and RESTful API
- 12:50 PM Bug #4836 (Resolved): crush_ops failure
- 2013-04-26T02:37:53.631 INFO:teuthology.task.mon_thrash.ceph_manager:quorum is size 2
2013-04-26T02:37:53.632 DEBUG:... - 12:47 PM Bug #4812 (Resolved): mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to c...
- Merged into next in commit:5fa3cbf520f5aeb9e0101c1263f681542d3069a5
Created #4835 to track the other issues I raised. - 12:47 PM RADOS Feature #4835 (Resolved): Monitor: better handle aborted synchronizations
- See #4812. That should not be an assert (graceful shutdowns!), and in that specific case we don't actually want to ex...
- 12:34 PM Bug #4824 (Resolved): msgr: crash in submit_message
- commit:a92b4c7558d936591ca9d7320042b54a68b2962b
- 10:34 AM Bug #4824 (In Progress): msgr: crash in submit_message
- 12:28 PM rgw Bug #4826 (Resolved): rgw: plain formatter does not flush correctly
- Fixed, commit:960eac26004849d6e2fa61cfab6482e9db667c52.
- 09:32 AM rgw Bug #4826 (In Progress): rgw: plain formatter does not flush correctly
- 12:03 PM rbd Feature #4231: librbd: Java bindings
- So I already started work on 'rados-java': https://github.com/wido/rados-java
I'm thinking about combining this to... - 11:49 AM rbd Feature #4231: librbd: Java bindings
- Possible good task for Joe and/or Noah?
- 11:52 AM rbd Feature #4834: Recompile/package qemu with new version of librbd to enable asynchronous flushing ...
- Gary and Josh to work together on this.
- 11:51 AM rbd Feature #4834 (Resolved): Recompile/package qemu with new version of librbd to enable asynchronou...
- 11:39 AM rbd Bug #4833 (Resolved): krbd: fix a bug in resizing a mapping
- When a snapshot context update occurs, rbd_update_mapping_size() is
called to set the capacity of the disk to record... - 11:38 AM rbd Feature #2557: QEMU support for image locking
- Need a blueprint to assist in architectural planning before we can estimate or plan this effort.
- 11:36 AM rbd Feature #4454: openstack: support volume migration in Cinder
- Initially copy from one back end to the other. Instead of using volume migrations blueprint, just use backup? Getting...
- 11:19 AM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- /a/teuthology-2013-04-26_02:29:14-fs-next-testing-basic/1450
- 11:17 AM CephFS Bug #4832 (Resolved): mds: failed auth_unpin assert
- ...
- 11:15 AM Bug #4821 (Resolved): monitor: actually setting an exclusive in _pick_random_mon would break things
- oh i see, i was looking at the MonClient version (that this was probably modeled after).
commit:741f46852380c8e756... - 11:08 AM Bug #4821: monitor: actually setting an exclusive in _pick_random_mon would break things
- max is monmap->size(); there's no modification if other is specified. I guess it would work if we decremented max, an...
- 09:34 AM Bug #4821: monitor: actually setting an exclusive in _pick_random_mon would break things
- no i think it's right. if o is set, max is num_mon-1, and we shift o or greater one to the right to still get a unif...
- 10:44 AM CephFS Bug #4829 (Closed): client: handling part of MClientForward incorrectly?
- (In reference to a backwards check for is_replay when doing encode_cap_releases())...
- 09:52 AM CephFS Bug #4742 (Resolved): mds: stuck clientreplay request
- commit:5121e56c255c079569f02e0ee852e469f38f470e
- 08:07 AM rbd Feature #4013: rbd: openstack: extend nova boot api to support going from image to volume
- 08:06 AM rbd Feature #4017: rbd: openstack: simplify volume booting with new api
- 07:59 AM rbd Bug #4803: krbd: memory leaks while testing layered images
- The following additional set of patches has been posted for
review. They're available in the "review/wip-rbd-cleanu... - 05:15 AM rbd Bug #4803 (Fix Under Review): krbd: memory leaks while testing layered images
- OK, I have some patches ready for review but I think this will
be an ongoing process so I'll probably be bouncing th... - 07:58 AM rbd Bug #4800 (Fix Under Review): krbd: avoid dropping extra reference in rbd_free_disk()
- The following has been posted for review:
rbd: avoid dropping extra reference in rbd_free_disk()
- 05:10 AM rbd Bug #4800 (In Progress): krbd: avoid dropping extra reference in rbd_free_disk()
- 05:09 AM rbd Bug #4800 (Fix Under Review): krbd: avoid dropping extra reference in rbd_free_disk()
- (Nevermind. Will be ready for review shortly.)
- 07:05 AM Revision 89692e09 (ceph): debian/rules: use multiline search to look for Build-Depends
- When Build-Depends was split into multiple lines (in commit
8f5c665744e58d6d51a1e86de55c1399f51cc1c3), the grep for
l... - 05:22 AM rbd Bug #4802: krbd: walk through error paths and fix them
- I think it may be hard to describe exactly what the problems
of this type are. I do a fairly good job of it in the ... - 05:11 AM rbd Bug #4796 (Fix Under Review): krbd: don't create sysfs entries for snapshots of mapped images
The following has been posted for review:
[PATCH] rbd: don't create sysfs entries for non-mapped snapshots
It...
04/25/2013
- 11:47 PM Revision 2146930e (ceph): mon: do not forward other mon's requests to other mons
- The request forwarding infrastructure is there for client requests.
However, we (ab)use it for mon's sending MLog mes... - 11:24 PM Revision a5cade1f (ceph): PG: clear want_acting when we leave Primary
- This is somewhat annoying actually. Intuitively we want to
clear_primary_state when we leave primary, but when we re... - 10:18 PM Revision 3ce35a67 (ceph): mon: get own entity_inst_t via messenger, not monmap
- There are intervals during bootstrap(*) during which we are part of the
monmap, but our name (mon->name) does not mat... - 09:15 PM rgw Bug #4826 (Resolved): rgw: plain formatter does not flush correctly
- This came up with the new changes that stream bucket listing. Previously we never ever flushed data while iterating, ...
- 08:16 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- IMHO problems prior to this commit. Now I happy to get working f4804849b7644f2c1dfd92404682f510a88e9a23 and going to ...
- 07:35 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Now all wrong, but there are at least this log.
- 05:32 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- hmm, according to the log it is in quorum (and leader) and healthy..
- 04:52 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- "killall ceph-mon -w" need twice.
- 04:50 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- PS First time was HEALTH_OK. Not once restart.
- 04:44 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- This mon now not in quorum (but running).
- 04:26 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Can you attach the new startup log?
- 04:19 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- And even "killall ceph-mon -w" waiting long (or infinite)...
- 04:17 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Sage Weil wrote:
> commit:3ce35a6743e050bf0de5abd5ad32f522c5664f3d
Hmm. Now starting good, but silent collapsing ... - 03:19 PM Bug #4811 (Resolved): incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- commit:3ce35a6743e050bf0de5abd5ad32f522c5664f3d
- 03:07 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Sage Weil wrote:
> Just to clarify: this failed startup is happening only *after* you did the manual repair (remove ... - 01:41 PM Bug #4811 (Need More Info): incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- 01:40 PM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Just to clarify: this failed startup is happening only *after* you did the manual repair (remove store.db, replace mo...
- 02:20 AM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Sorry for flooding (this is my morning):
Last failure (on different node then first 2), between power-on and this ... - 01:29 AM Bug #4811: incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- PS About 2 previous failures: I just think about RAM limit. It just was so: busy node, long running, swapoff -a (but ...
- 12:25 AM Bug #4811 (Resolved): incorrect shutdown: mon/MonMap.h: 160: FAILED assert(mon_addr.count(n))
- Monitor unable to start after incorrect shutdown. First happened on busy node with swapoff -a (twice), on older versi...
- 08:11 PM Revision b0ba4123 (ceph): Merge pull request #239 from ceph/wip-4760
- #4760
Second patch Reviewed-by: Sage Weil <sage@inktank.com> - 07:49 PM Revision a0acdcf3 (ceph): Use get('field', default) to assign downburst values for vps.
- Fixes: #4592
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Reviewed by: Dan Mick <dan.mick@inktank.com> - 06:52 PM Revision 42ab1f45 (ceph): Merge pull request #246 from ceph/wip-4793
- #4793
Reviewed-by: Sage Weil <sage@inktank.com> - 06:36 PM Revision 303e739e (ceph): radosgw: receiving unexpected error code while accessing an non-existin...
- This patch fixes a bug in radosgw swift compatibility code,
that is, if a not-owner but authorized user access a non-... - 06:34 PM CephFS Bug #4742: mds: stuck clientreplay request
- Yeah, we've discussed this some on github around wip-4742 and on irc. :)
- 06:31 PM CephFS Bug #4742: mds: stuck clientreplay request
- Looks like a client bug, it may add cap releases to the replay requests. (encode_cap_releases() should be called when...
- 10:38 AM CephFS Bug #4742: mds: stuck clientreplay request
- Logs for two runs, one is stuck in replay from a setattr, the other is stuck in replay from a rename.
- 06:17 PM Revision 407ce132 (ceph): PendingReleaseNotes: these are now in the release-notes.rst
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:17 PM Revision c979d65b (ceph): Merge remote-tracking branch 'gh/next'
- 06:17 PM Revision 4af93dcc (ceph): doc/release-notes: add note about sysvinit script change
- See cd7e52cc76878eed0f084f7b9a6cf7c792b716c6.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:13 PM Revision cd7e52cc (ceph): init-ceph: use remote config when starting daemons on remote nodes (-a)
- If you use -a to start a remote daemon, assume the remote config is present
instead of pushing the local config. Thi... - 05:21 PM Revision ea54e660 (ceph): Merge branch 'wip-4748-b' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 05:13 PM devops Bug #4825 (Resolved): ceph-deploy: install failed on debian-wheezy
- ...
- 04:52 PM Bug #4824 (Resolved): msgr: crash in submit_message
- ...
- 04:30 PM Bug #4813 (Resolved): pgs stuck creating
- This was probably fixed by the fix for 4748
- 09:01 AM Bug #4813: pgs stuck creating
- ubuntu@teuthology:/a/teuthology-2013-04-25_01:00:08-rados-next-testing-basic/584
- 09:01 AM Bug #4813 (Resolved): pgs stuck creating
- 2013-04-25T02:36:57.292 DEBUG:teuthology.misc:with jobid basedir: 584
2013-04-25T02:36:57.292 DEBUG:teuthology.orche... - 04:27 PM devops Bug #4823 (Resolved): ceph-deploy: install not implemented for RHEL 6.3
- ...
- 04:25 PM Bug #3904 (Pending Backport): FAILED assert(want_acting.empty())
- 02:14 PM Bug #3904 (Fix Under Review): FAILED assert(want_acting.empty())
- Sage's scenario is most likely correct, pushed wip_3904.
- 04:14 PM Revision fb17d37f (ceph): Revert "turn on debugging for MDS and Client in FS runs"
- We want to apply debugging and whitelists, not one or the
other -- whoops!
This reverts commit 60e7fb4152a7f42594d86... - 04:14 PM Revision ae00c60b (ceph): temporarily add cephfs debugging to overrides
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 04:14 PM Revision 5d5e0a6e (ceph): Revert "turn on debugging for MDS and Client in FS runs"
- We want to apply debugging and whitelists, not one or the
other -- whoops!
This reverts commit cb1e8ed954c41840f28f5d... - 04:14 PM Revision 35cf1220 (ceph): temporarily add cephfs debugging to overrides
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 04:08 PM Bug #4815 (Need More Info): mon: leveldb grows quickly and without bound
- It's not entirely clear what's going on here with just the messenger logging. If you can get monitor logging (and fro...
- 12:33 PM Bug #4815: mon: leveldb grows quickly and without bound
- Actually, I meant dmesg instead of syslog above. Looking at the syslog, ceph-mon was killed by oom-killer:
Killed ... - 12:17 PM Bug #4815 (Resolved): mon: leveldb grows quickly and without bound
- My mon.a process went away without a core dump or indication in the ceph-mon log or syslog of what happened. mon.b an...
- 04:01 PM Bug #4822 (Resolved): After 5 minutes a down OSD is NOT marked out
Seeing this message:
tick entire containing rack subtree for osd.0 is down; resetting timer
OSDMap::containing_...- 03:14 PM Bug #4812: mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to connect to. ...
- The only way I can see this assert happening is if b randomly selected the previously-chosen monitor (c) or itself 6 ...
- 02:50 PM Bug #4812: mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to connect to. ...
- Yep, bootstrap() calls reset_sync(). So c dropped b's sync on the floor, and then b timed out of course. Was it suppo...
- 02:08 PM Bug #4812: mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to connect to. ...
- Okay, this is sort of what was supposed to happen, I think. mon c stopped responding to mon b's sync queries, and it ...
- 01:31 PM Bug #4812 (In Progress): mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor t...
- 08:56 AM Bug #4812: mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to connect to. ...
- ubuntu@teuthology:/a/teuthology-2013-04-25_01:00:08-rados-next-testing-basic/587/
- 08:55 AM Bug #4812 (Resolved): mon/Monitor.cc: 1107: FAILED assert(0 == "Unable to find a new monitor to c...
- 0> 2013-04-25 05:52:00.052720 7f126a7fc700 -1 mon/Monitor.cc: In function 'void Monitor::sync_timeout(entity_ins...
- 03:10 PM Bug #3214: osdmaptool's usage is incomplete
- The rest of the bug still needs review/update; --test-map-object is indeed in the usage though (I must have been usin...
- 02:44 PM Bug #4821 (Resolved): monitor: actually setting an exclusive in _pick_random_mon would break things
- ...
- 02:08 PM devops Bug #4820 (Resolved): ceph-deploy : intermittent errors during install
- not often, but see this error at the end of install. It would be nice to make this error look better or let the user ...
- 02:02 PM Revision d90b0caf (ceph): gen_state_diagram.py: fix function name
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision 1ee8f390 (ceph): gen_state_diagram.py: fix naming of global variables/constants
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision d9f8de1e (ceph): gen_state_diagram.py: add some missing spaces around operators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision 7cd9d23f (ceph): gen_state_diagram.py: remove unnecessary semicolon
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision eb3350e4 (ceph): test_mon_config_key.py: fix some more naming of local vars
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:02 PM Revision 74365429 (ceph): test_mon_config_key.py: fix naming of local variable opLOG
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:01 PM Revision 9d3b4fd7 (ceph): test_mon_config_key.py: fix naming of local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:00 PM Revision 04075722 (ceph): fix "Instance of 'list' has no 'split' member"
- Cast with str() to fix issue.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 01:57 PM Revision c792ea67 (ceph): test_mon_config_key.py: fix naming of local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:56 PM Revision 912bb82c (ceph): test_mon_config_key.py: fix naming of global variables/constants
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:56 PM Revision 1464169a (ceph): test_mon_config_key.py: add missing space after comma
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:56 PM Revision 16c56506 (ceph): test_mon_config_key.py: remove unnecessary semicolon
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:55 PM Revision f601eb90 (ceph): test_mon_config_key.py: fix bad indentation
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:54 PM Revision 9dd5de26 (ceph): perf-watch.py: fix naming of a local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:53 PM Revision 226ff52a (ceph): perf-watch.py: fix naming of local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:53 PM Revision 148710fb (ceph): perf-watch.py: add missing space after comma
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:52 PM Revision dffa9eeb (ceph): perf-watch.py: remove unnecessary semicolons
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:23 PM rgw Feature #4819 (New): rgw: add a test for #4797
- need to add a test in the swift test suite that checks for issue #4797.
- 01:19 PM rbd Bug #4446: librbd: crash from opensolaris vm
- Even without NIS or NFS, I'm guessing it'll get far enough to hit the error. I'll email you a place to upload the image.
- 04:44 AM rbd Bug #4446: librbd: crash from opensolaris vm
- Thanks for continuing to pursue this.
I can send you the image (about 20GB), but it may have issues booting (depen... - 01:19 PM rgw Bug #4760 (Resolved): rgw: list buckets/containers should be streamlined
- commit:b0ba41235af901bd7e64588e2a247c6a56ec5cfa
- 01:15 PM Bug #4793 (Resolved): mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- It passed and Sage merged it into next with commit:42ab1f4561cde4c724849c41a7929c93d89e89d9
- 10:13 AM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Sage reviewed this; unfortunately schedule_suite and teuthology failed somehow so these tests didn't actually run. :(
- 01:13 PM rbd Bug #4803: krbd: memory leaks while testing layered images
- I've been reviewing the rbd code with an eye toward finding
leaks. I have two small ones that I'll fix, but I have ... - 12:56 PM Bug #4748 (Resolved): mon: failed assert in OSDMonitor::build_incremental
- 12:55 PM Bug #4810: mon: forwarded messages have weird priorities
- which was problematic because of...
- 12:53 PM Bug #4810 (In Progress): mon: forwarded messages have weird priorities
- actually this was the forwards taking the priority from the client msg. fixed that in wip-4748-b and running tests i...
- 12:26 PM Bug #4816 (Can't reproduce): Monitor crashed with signal Aborted in MMonSubscribe::~MMonSubscribe()
- This crash occurred on a non-leader (b) while the leader (a) was experiencing some kind of a memory leak and all mons...
- 11:31 AM rgw Bug #4797 (Resolved): rgw: receiving unexpected error code while accessing an non-existing object...
- Done, merged patch by Li Wang to next, commit:303e739e5b34ad1aaedb0025ffc6da1a9e04c320.
- 10:33 AM rgw Bug #4797 (In Progress): rgw: receiving unexpected error code while accessing an non-existing obj...
- 09:23 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- Oh, I think figured it out. It turns out that we do return sometimes 400 and not 404.
The test itself tries to do ... - 06:24 AM rbd Bug #2654: Stale rbd volume cannot be unmaped
- Hi, thanks for replying. Here's the info:...
- 01:02 AM rbd Bug #2700 (Resolved): blkdeviotune method at libvirt doesn`t work on RBD volumes
- The patch got accepted into libvirt: http://www.libvirt.org/git/?p=libvirt.git;a=commit;h=e3e866aee0f8b0b125da74e1afc...
- 12:39 AM Revision 6b8f1c6b (ceph): repair_test.py: Additional test cases
- Test repair with more than 1 damaged object and with different types of damage
Regression test for bug #4778
Signed-... - 12:33 AM Revision f4804849 (ceph): Merge branch 'wip-4778' into next
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 12:32 AM Revision ac3dda21 (ceph): scrub clears inconsistent flag set by deep scrub
- Add new num_deep_scrub_errors and num_shallow_scrub_errors to object_stat_sum_t
Show deep-scrub error count when outp...
04/24/2013
- 11:46 PM Revision ba527c1e (ceph): doc/release-notes: enospc note
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:42 PM Revision 2075ec60 (ceph): doc/release-notes: 0.61 cuttlefish notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:20 PM Revision 43225220 (ceph): Merge pull request #242 from ceph/wip-objectcacher-enoent
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 10:54 PM Revision 82d5cd60 (ceph): ObjectCacher: remove all buffers from a non-existent object
- Once we're sure an object doesn't exist, we retry all the waiters in
order, and they return -ENOENT immediately. If t... - 10:40 PM Revision fb8bad31 (ceph): mon: be more careful about making sure we're up-to-date on sync check
- We were looking at our own paxos_max_join_drift and using that to
calculate whether we were new enough to join withou... - 10:40 PM Revision fcaabf1a (ceph): mon: when electing, be sure acked leaders have new enough stores to lead
- In general anybody participating in an election should be new enough to
lead thanks to the bootstrap process, but we'... - 10:07 PM Revision 290b5eb0 (ceph): rgw: fix i386 compile error
- error: rgw/rgw_op.cc:665:63: no matching function for call to ‘min(uint64_t, size_t&)’
Signed-off-by: Sage Weil <sag... - 10:05 PM Revision 14f23922 (ceph): FileStore::_split_collection: src or dest may be removed on replay
- If the collection is subsequently removed, the _split_collection
might get replayed and find either src or dest remov... - 09:34 PM Revision 3604c982 (ceph): librados: fix calc_snap_set_diff interval calculation
- When calculating the [a,b] interval over which a given clone is valid, do
not assume that b == the clone id; that is ... - 09:04 PM Revision 5668e5b5 (ceph): Merge remote-tracking branch 'upstream/wip_2476' into next
- Fixes: #2476
Reviewed-by: Greg Farnum <greg@inktank.com> - 08:46 PM devops Feature #4667: ceph-deploy update
- Gary's put a test repo up, and I've fleshed out the code to handle adding that if necessary, and it
seems to be work... - 08:20 PM Revision 81a6165c (ceph): PG: call check_recovery_sources in remove_down_peer_info
- If we transition out of peering due to affected
prior set, we won't trigger start_peering_interval
and check_recovery... - 07:26 PM Revision a9791dae (ceph): mon: send clients away while sychronizing
- When we are out of quorum, we waitlist client messages or (eventually)
send them elsewhere. If we are synchronizing,... - 06:23 PM Revision 12bc9a7a (ceph): mkcephfs: give mon. key 'allow *' mon caps
- This will ease the transition from mkcephfs to ceph-deploy by allowing
ceph-create-keys to use the mon. keyring file ... - 05:58 PM Bug #4778 (Resolved): scrub clears inconsistent flag set by deep scrub
- ac3dda214d52c10206328a92e4373521200c8863
- 05:16 PM Revision cce1c91a (ceph): PendingReleaseNotes: note about rbd resize --allow-shrink
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 05:10 PM rbd Bug #4446: librbd: crash from opensolaris vm
- Sorry for the delay. I've learned that Solaris sector counts could start at 1 instead of 0, so rbd did at least see t...
- 05:00 PM Bug #4810 (Won't Fix): mon: forwarded messages have weird priorities
- While testing #4748, i'm seeing MForward messages between monitors getting lost. they are enqueued by read_message, ...
- 04:24 PM Bug #4784: Two Monitors Concurrently Reporting as Leaders
- Oh, yeah. Looks like there were a bunch of backed up messages, and the second leader was having as much trouble with ...
- 07:28 AM Bug #4784: Two Monitors Concurrently Reporting as Leaders
- Greg, during this state ceph -s hangs for longer than I have waited (several minutes). All RBD volumes are stalled/un...
- 04:22 PM rbd Bug #3664 (Resolved): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- commit:82d5cd601e0fb7cb24dda4ea1f0e9f12e5d18708
- 04:02 PM rbd Bug #3664 (Fix Under Review): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- 08:13 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- ubuntu@teuthology:/a/teuthology-2013-04-23_19:55:59-rbd-next-testing-basic$ less 155/teuthology.log
- 08:13 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- ubuntu@teuthology:/a/teuthology-2013-04-23_19:55:59-rbd-next-testing-basic$ less 148/teuthology.log
- 04:13 PM devops Bug #4498 (Resolved): ceph-deploy osd create doesn't set up symlink for single node
- commit:3a74cfcda2f37550e8f68d0d5b664151225a9244
- 03:56 PM Bug #4793 (Fix Under Review): mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUEST...
- wip-4793. Waiting for it to build so I can kick off some teuthology tests.
- 02:35 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, given that setup the only way to be participating in an election but too far behind is if we've been alive but ...
- 02:17 PM Bug #4793 (In Progress): mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, so mon.a lost quorum leadership for about 13 seconds without noticing; looks like it got stuck waiting for paxo...
- 01:12 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Ah, that would make self-abdication a more palatable solution indeed.
- 01:03 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- One thought: before the election they do the probe step.. maybe a simple flag in the election that says "i think i'm ...
- 12:54 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Actually, we can't just send along the versions because then the voters need global state in order to respond to each...
- 11:06 AM Bug #4793 (In Progress): mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, discussed this a little more and there was some confusion about whether we were discussing the cluster leader o...
- 03:51 PM Revision 14777ec1 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
ceph.spec.in - 03:49 PM Revision 31399d17 (ceph): Fix typo of the keystone service-create command
- Signed-off-by: leseb <sebastien.han@enovance.com>
- 03:49 PM Revision 9abec309 (ceph): rgw: list container only shows stats if needed
- Fixes: #4759
Add a new request param 'stats' for the swift list containers
request. If set to 'false' it disables sta... - 03:46 PM Bug #4703 (Can't reproduce): ceph health hangs when upgrading from bobtail to next branch
- this appears to be resolved; unable to reproduce (whereas it used to be pretty frequently triggered).
- 10:18 AM Bug #4703: ceph health hangs when upgrading from bobtail to next branch
- Greg, can you please take a look at this?
- 03:36 PM Revision c7a0477b (ceph): rbd: fix cli-integration tests for striping change
- We don't set the striping feature when we are using backward-compatible
(default) striping now; fix the test accordin... - 03:22 PM Revision 446641aa (ceph): 95-ceph-osd-alt.rules: Fix missing parent parameter
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 03:14 PM rbd Bug #4526 (Can't reproduce): rbd-fsx: ENOTEMPTY
- 03:14 PM Bug #4348 (Resolved): OSD slow request leads to RBD clients stalled/delayed
- oh, just noticed this is 0.56.2. upgrade to .4 and the stalls will go away.
- 10:04 AM Bug #4348: OSD slow request leads to RBD clients stalled/delayed
- Ivan, are you still seeing this problem?
- 03:06 PM Bug #4806 (Pending Backport): os/FileStore.cc: In function 'void FileStore::_set_replay_guard() f...
- 01:29 PM Bug #4806 (Resolved): os/FileStore.cc: In function 'void FileStore::_set_replay_guard() failure
- ...
- 02:40 PM Cleanup #4809 (Resolved): MMonProbe extra fields
- Looks to me like we have some unused fields in MMonProbe now:...
- 02:35 PM Bug #4785 (Resolved): rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps...
- 02:35 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- merged to next, commit:3604c98232615827812099af27ebc3ed2414c8eb
- 02:30 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Thanks! Diffs completed.
- 01:37 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Perfect, I see the problem now! Can you try wip-4785-b?
- 01:28 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Sage Weil wrote:
> i mean the output from the command 'rados -p rbd listsnaps rb.0.c558.238e1f29.000000000000'
OK... - 01:27 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Or you want output from --snap ... --from-snap ... ?
I in doubts! - 01:16 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- i mean the output from the command 'rados -p rbd listsnaps rb.0.c558.238e1f29.000000000000'
- 01:15 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- HMM. If I right understand, you want console output? IMHO it near same (a bit duplicating) to already attached "foo" ...
- 12:46 PM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Denis: can you attach teh output from the listsnaps command above?
- 11:32 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- ... there was from "--from-snap backup" to active image. To secondary snapshot log differ in not significant details....
- 11:30 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- can you do 'rados -p rbd listsnaps rb.0.c558.238e1f29.000000000000'?
also are you on irc? that would be quicker t... - 11:11 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Sage Weil wrote:
> Denis: can you run the rbd failing command with --log-file foo --log-max 1 --debug-ms 1 --debug-r... - 10:45 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Denis: can you run the rbd failing command with --log-file foo --log-max 1 --debug-ms 1 --debug-rbd 20?
Also, push... - 03:28 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- PS /etc/init.d/ceph restart - on all...
- 03:24 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- Now installing "next" branch on all nodes (as wip-3495 here now):
librados/snap_set_diff.cc: 40: FAILED assert(b =... - 02:35 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- git, wip-3495 branch:
# ceph-osd --version
ceph version 0.60-476-gd3752d2 (d3752d2a09f221f8cee6919ce59d102fd7f2f9... - 02:06 PM Bug #2476 (Resolved): osd: watch timeout depends on operations to an object
- 01:22 PM Bug #2476: osd: watch timeout depends on operations to an object
- 01:21 PM Bug #2476 (Pending Backport): osd: watch timeout depends on operations to an object
- 01:34 PM Documentation #4807 (Closed): Document PG states, possible causes, and possible remedies
- I think it would help people help themselves a lot if we enumerated the various pg states and what could
cause them ... - 01:22 PM Bug #4805 (Pending Backport): ReplicatedPG: pull bug
- 12:22 PM Bug #4805 (Fix Under Review): ReplicatedPG: pull bug
- Reset needs to check_recovery_sources, have patch. wip_4805
- 12:19 PM Bug #4805 (Resolved): ReplicatedPG: pull bug
- -7> 2013-04-23 21:03:12.595110 7fee6572c700 10 osd.5 1119 do_waiters -- finish
-6> 2013-04-23 21:03:12.75589... - 01:08 PM Bug #4521: mon: starting a new osd crashes all mon's
- Samuel Just wrote:
> Evan: what version of leveldb are you using?
leveldb-1.7.0-2.el6.x86_64 - 01:01 PM Bug #4521: mon: starting a new osd crashes all mon's
- the original conversion bug is fixed, and the fixer works for those who need it, modulo this leveldb thing. we shoul...
- 12:50 PM Bug #4521: mon: starting a new osd crashes all mon's
- Evan: what version of leveldb are you using?
- 06:05 AM Bug #4521: mon: starting a new osd crashes all mon's
- The issue appears to be with leveldb's state, which is returning 'Invalid argument: not an sstable (bad magic number)...
- 12:47 PM Bug #4748: mon: failed assert in OSDMonitor::build_incremental
- 11:31 AM Bug #4748: mon: failed assert in OSDMonitor::build_incremental
- last little bit of log:...
- 11:27 AM Bug #4748: mon: failed assert in OSDMonitor::build_incremental
- got logs, ubuntu@teuthology:/a/sage-e1/313
- 09:04 AM Bug #4748: mon: failed assert in OSDMonitor::build_incremental
- kicked of job sage-e1 to try to reproduce this with logs
- 11:25 AM devops Bug #4756: mkcephfs doesn't set up same keys as ceph-deploy
- The transition doc should be something like 'transitioning an existing cluster from mkcephfs to ceph-deploy', and the...
- 11:23 AM devops Bug #4756: mkcephfs doesn't set up same keys as ceph-deploy
- wip-4756 tested out ok, commit:12bc9a7aa9cb2f47c952dee9abb210dc4eacf470
- 09:28 AM devops Bug #4756: mkcephfs doesn't set up same keys as ceph-deploy
- Well ceph-create-keys isn't able to add it because it needs those keys, right? ;)
I think a transition document is... - 09:25 AM devops Bug #4756: mkcephfs doesn't set up same keys as ceph-deploy
- I'll update mkcephfs to do this to ease future users' transition to ceph-deploy.
For existing clusters, the transi... - 10:52 AM rbd Bug #2654 (Need More Info): Stale rbd volume cannot be unmaped
- 10:52 AM rbd Bug #2654 (In Progress): Stale rbd volume cannot be unmaped
- Can you post results from find /sys/bus/rbd/devices -ls and ls -al /dev/rbd* ?
- 12:06 AM rbd Bug #2654: Stale rbd volume cannot be unmaped
- Please consider re-opening this ticket. I am experiencing the same issue, even with the latest kernel version:
<pr... - 10:47 AM rbd Feature #4804 (Rejected): tgt: switch to aio
- Use aio interface for tgt to avoid a workqueue + sync items.
- 10:09 AM rbd Bug #4522 (Need More Info): RBD utility "showmapped" bug
- 10:09 AM rbd Bug #4522: RBD utility "showmapped" bug
- Do you still see this?
What 'showmapped' is looking at is /sys/bus/rbd/devices/*... an ls -al of that directory wo... - 09:23 AM Bug #4194 (Can't reproduce): osd, librados: listing objects got premature ENOENT
- 09:23 AM Linux kernel client Bug #4524 (Can't reproduce): libceph: bad ptr deref in rbtree for kick_requests
- 09:23 AM devops Bug #4520 (Resolved): ceph-disk-prepare intermittently fails on Centos
- commit:9eda8e5d5abf0743a2ad484806cfb2018243515f
- 09:22 AM rbd Bug #4803 (Resolved): krbd: memory leaks while testing layered images
- I have a series of small tests I run to test rbd functionality.
I occasionally run them in a loop in my UML environm... - 09:13 AM Bug #4067 (Won't Fix): Argonaut fails to build on fedora18
- 09:03 AM rbd Bug #4802: krbd: walk through error paths and fix them
- Fixed project.
- 09:02 AM rbd Bug #4802 (Resolved): krbd: walk through error paths and fix them
- I have encountered a few places where the kernel rbd
code does not handle error conditions exactly right.
There app... - 08:57 AM rbd Bug #4800: krbd: avoid dropping extra reference in rbd_free_disk()
- This is basically done.
As I look through the code though I see there are other places
where error handling does ... - 07:43 AM Bug #4801 (Duplicate): osd class path broken on fedora 18?
- https://bugzilla.redhat.com/show_bug.cgi?id=891993
- 03:54 AM Revision a40772be (ceph): osd_types: add last_became_active to pg_stats
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 03:54 AM Revision 1f7ff412 (ceph): ReplicatedPG: timeout watches based on last_became_active
- This way a notify on an object with a single defunct watcher
won't necessarily have to wait the full timeout if the p... - 03:51 AM Revision d44cfc52 (ceph): Merge branch 'wip_4552' into next
- Fixes: #4552
Reviewed-by: Greg Farnum <greg@inktank.com> - 01:27 AM Revision 297c6714 (ceph): DispatchQueue: track queued message arrival times and expose oldest
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:27 AM Revision 49eeaeba (ceph): Messenger: add interface to get oldest queued message arrival time
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:27 AM Revision d196b5ba (ceph): OSD: don't report peers down if hbclient_messenger is backed up
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:10 AM Revision fd750da9 (ceph): Add changes to make teuthology suites work on vms.
- Fixes: #4719
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Reviewed by: Dan Mick <dan.mick@inktank.com> - 12:24 AM Revision a8e7e9df (ceph): init-ceph: fix (and simplify) pushing ceph.conf to remote unique name
- The old code would only do the push once per remote node (due to the
list in $pushed_to) but would reset $unique on e... - 12:23 AM Revision 0cd86dfb (ceph): Merge pull request #237 from ceph/wip-4794
- init-ceph: fix (and simplify) pushing ceph.conf to remote unique name
- 12:17 AM Revision e09efda7 (ceph): Merge pull request #241 from ceph/wip-4798
- #4798
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:16 AM Revision 48631c11 (ceph): mon: revert part of PaxosService::is_readable() change
- In 98e23980f4ab7ba289303f72da06721c84767293 is_readable() was changed to
call is_active(), but that has a check for i...
04/23/2013
- 11:30 PM Revision 97c77985 (ceph): Merge branch 'wip-teuthologyfix4693-wusui'
- 11:28 PM Revision b7aaa198 (ceph): Check downburst paths. Display an appropriate error message if an
- executable downburst cannot be found.
Fixes: #4693
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Reviewed by:... - 11:18 PM Revision 0093d704 (ceph): librbd: fix i386 build
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:11 PM Revision 5349ee30 (ceph): Merge pull request #240 from ceph/wip-4665
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 10:57 PM Revision 857c88e0 (ceph): librbd: add read_iterate2 call with fixed argument type
- The existing read_iterate takes a size_t for the length, which is only 4GB
on 32-bit machines. Instead, take a uint6... - 10:45 PM Revision 6c798ed9 (ceph): librbd: implement read not in terms of read_iterate
- The read() method returns the bytes read, trimmed to the end of the image;
use the other read() variant to do this (w... - 09:06 PM Revision 95ed73a7 (ceph): mon: drop forwarded requests after an election
- On each election, we resend routed requests to the new leader (or
requeue for ourselves). Therefore, if we receive a... - 08:54 PM Bug #4552 (Resolved): osd: temporarily hung box marks down peers
- I think the problem was likely caused by a severely backed up heartbeat client dispatch queue. d44cfc524fc0844c6027c...
- 08:45 PM Revision ab257070 (ceph): mon: requeue routed_requests for self if elected leader
- If we have requests that we have forwarded, and are elected leader,
requeue those requests for ourself and queue them... - 08:40 PM Revision 4b07d692 (ceph): mon: track original Connection* for forwarded requests
- Keep a reference to the source Connection* for forwarded requests. This
makes the reply path slightly cleaner, and w... - 07:50 PM Revision 526863ee (ceph): remove ext4 from rados thrashing for now
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:44 PM Revision 426e3be6 (ceph): Merge pull request #222 from ceph/wip-3495
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 07:28 PM Revision 8402107c (ceph): test_filejournal: adjust corrupt entry tests to force header write
- The journal no longer assumes corruption if it finds a valid entry
after an inavlid entry. Instead, these tests will... - 07:15 PM rbd Bug #4800 (Resolved): krbd: avoid dropping extra reference in rbd_free_disk()
- I found during some failure injection testing that the call to
rbd_free_disk() in the error path of rbd_dev_probe_fi... - 07:04 PM Revision 9374bacc (ceph): Merge pull request #238 from ceph/wip-bobtail-rbd-backports-req-order
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 06:33 PM Revision d86f9b1d (ceph): ObjectCacher: always complete flush_set() callback
- This removes the last remnants of
b5e9995f59d363ba00d9cac413d9b754ee44e370. If there's nothing to flush,
immediately ... - 06:33 PM Revision ee7bf281 (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... - 06:33 PM Revision 3a61d17b (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... - 06:33 PM Revision fb95b800 (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... - 06:33 PM Revision f9bcffa2 (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... - 06:33 PM Revision cbb37fb5 (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... - 06:33 PM Revision f2e490cb (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 ... - 06:33 PM Revision 31a45e8e (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... - 06:33 PM Revision d36c5b5b (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... - 06:33 PM Revision 4a1c27c0 (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... - 06:33 PM Revision 7bc8df1f (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... - 06:33 PM Revision 13ba07a0 (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 ... - 06:33 PM Revision 124f81cc (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... - 06:33 PM Revision 884438fe (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.... - 06:33 PM Revision 7a11c250 (ceph): LibrbdWriteback: removed unused and undefined method
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 909dfb7d183f54f7583a70c05550bec07856d... - 06:33 PM Revision 0e2266db (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... - 06:33 PM Revision aa37726b (ceph): rbd: only set STRIPINGV2 feature when needed
- Only set the STRIPINGV2 feature if the striping parameters are non-default.
Specifically, fix the case where the pass... - 06:33 PM Revision 959bfe90 (ceph): osdc/Objecter: unwatch is a mutation, not a read
- This was causing librados to unblock after the ACK on unwatch, which meant
that librbd users raced and tried to delet... - 06:33 PM Revision d9636faa (ceph): osd: make watch OSDOp print sanely
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit de4fa95f03b99a55b5713911c364d7e2a4588679) - 06:33 PM Revision 9ea4dac1 (ceph): objecter: separate out linger_read() and linger_mutate()
- A watch is a mutation, while a notify is a read. The mutations need to
pass in a proper snap context to be fully cor... - 06:33 PM Revision d8ac6cbf (ceph): objecter: initialize linger op snapid
- Since they are write ops now, it must be CEPH_NOSNAP or the OSD
returns EINVAL.
Signed-off-by: Josh Durgin <josh.dur... - 06:33 PM Revision 9b292199 (ceph): common: add lockers for RWLocks
- This makes them easier to use, especially instead of existing mutexes.
Signed-off-by: Josh Durgin <josh.durgin@inkta... - 06:33 PM Revision 6e6636d5 (ceph): librbd: use rwlocks instead of mutexes for several fields
- Image metadata like snapshots, size, and parent is frequently read,
but rarely updated. During flatten, we were depen... - 06:33 PM Revision 34e9030e (ceph): librbd: make sure racing flattens don't crash
- The only way for a parent to disappear is a racing flatten completing,
or possibly in the future the image being forc... - 06:33 PM Revision 796066b7 (ceph): Merge branch 'wip-4249' into wip-4249-master
- Make snap_rollback() only take a read lock on snap_lock, since
it does not modify snapshot-related fields.
Conflicts:... - 06:33 PM Revision cd989681 (ceph): librbd: fix rollback size
- The duplicate calls to get_image_size() and get_snap_size() replaced
by 5806226cf0743bb44eaf7bc815897c6846d43233 unco... - 06:33 PM Revision f2bcf241 (ceph): test_rbd: move flatten tests back into TestClone
- They need the same setup, and it's easy enough to run specific
subtests. Making them a separate subclass accidentally... - 06:33 PM Revision 1e51be05 (ceph): ObjectCacher: keep track of outstanding reads on an object
- Reads always use C_ReadFinish as a callback (and they are the only
user of this callback). Keep an xlist of these for... - 06:33 PM Revision d9ca1b00 (ceph): ObjectCacher: add a method to clear -ENOENT caching
- Clear the exists and complete flags for any objects that have exists
set to false, and force any in-flight reads to r... - 06:33 PM Revision 1c44b66f (ceph): librbd: invalidate cache when flattening
- The cache stores which objects don't exist. Flatten bypasses the cache
when doing its copyups, so when it is done the... - 06:33 PM Revision 9facdcac (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... - 06:33 PM Revision 7bc1596b (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, ... - 06:33 PM Revision e237dfc7 (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 ... - 06:33 PM Revision 3b0c565d (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... - 06:33 PM Revision 0f2e5d36 (ceph): objectcacher: Remove commit_set, use flush_set
- commit_set() and flush_set() are identical in functionality,
so use flush_set everywhere and remove commit_set from
t... - 06:33 PM Revision 00dfb3f0 (ceph): ObjectCacher: fix flush_set when no flushing is needed
- C_GatherBuilder takes ownership of the Context we pass it. Deleting it
in flush_set after constructing the C_GatherBu... - 06:31 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- huh, forgot to mention that there is one case in which an out-of-quorum monitor must be elected the (sync) leader in ...
- 05:42 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- Okay, this appears to be happening because the elected leader is too far behind, so it starts syncing and the system ...
- 01:53 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-23_11:03:00-rados-next-testing-basic/126
with logs - 01:49 PM Bug #4793: mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- No idea what's going on here, but I'm going to start looking into it.
- 09:30 AM Bug #4793 (Resolved): mon/Monitor.cc: 1126: FAILED assert(!(sync_role & SYNC_ROLE_REQUESTER))
- During the process of attempting to sync a new or behind monitor with 0.60, I have seen mon/Monitor.cc: 1126: FAILED ...
- 06:23 PM Revision 1435cb54 (ceph): Merge branch 'next' of github.com:ceph/teuthology into next
- 06:22 PM Revision 0b50cb5e (ceph): Increase IPMI attempts to try to get around Flakey IPMI.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 06:02 PM Revision 7fbe467f (ceph): ceph.conf: enable full debugging on the mon
- 05:48 PM Revision 556bb649 (ceph): rgw: stream list buckets (containers) request
- Fixes: #4760
Instead of retrieving the entire list of buckets in one
chunk, streamline it. This makes it so that if t... - 05:35 PM Revision 98cc648c (ceph): Increase IPMI attempts to try to get around Flakey IPMI.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 05:27 PM devops Bug #4498 (Fix Under Review): ceph-deploy osd create doesn't set up symlink for single node
- 02:06 PM devops Bug #4498: ceph-deploy osd create doesn't set up symlink for single node
- I ran across this too, and have a fix; the problem is just in the log statement.
- 05:23 PM Bug #4794 (Resolved): init-ceph: fix unique name pushing thing for ceph.conf on remote nodes
- 10:03 AM Bug #4794 (Fix Under Review): init-ceph: fix unique name pushing thing for ceph.conf on remote nodes
- 09:55 AM Bug #4794 (Resolved): init-ceph: fix unique name pushing thing for ceph.conf on remote nodes
- 05:17 PM Bug #4798 (Resolved): mon: message stuck in processing loop
- commit:e09efda
- 04:11 PM Bug #4798 (Fix Under Review): mon: message stuck in processing loop
- 02:30 PM Bug #4798: mon: message stuck in processing loop
- from the logs it looks like starvation from these messages is preventing any new message processing (and thus quorum)
- 02:20 PM Bug #4798: mon: message stuck in processing loop
- Okay, but of course the only reason we're seeing this is that the monitors aren't forming a quorum, right? So that's ...
- 01:49 PM Bug #4798 (In Progress): mon: message stuck in processing loop
- about to test a fix. the problem is that routed_request are resent to the new leader, even if that is us.. so it is p...
- 01:33 PM Bug #4798: mon: message stuck in processing loop
- Is it actually a loop or is the command getting re-sent?
- 01:26 PM Bug #4798 (Resolved): mon: message stuck in processing loop
- ...
- 05:00 PM Revision ccbc4dbc (ceph): init-ceph: fix (and simplify) pushing ceph.conf to remote unique name
- The old code would only do the push once per remote node (due to the
list in $pushed_to) but would reset $unique on e... - 05:00 PM Bug #4784 (Closed): Two Monitors Concurrently Reporting as Leaders
- Yeah, leveldb on mon.a went totally out to lunch — it tried to pass through a transaction and never finished, as best...
- 02:57 PM Bug #4784 (In Progress): Two Monitors Concurrently Reporting as Leaders
- I've got more digging to do to verify my diagnose on the listed times, but so far what I'm seeing looks like the lead...
- 01:26 PM Bug #4784 (Need More Info): Two Monitors Concurrently Reporting as Leaders
- Got Kevin on irc and am waiting for logs of when this first happens, if possible. I'll go review some of the election...
- 04:12 PM rbd Bug #4665 (Resolved): librbd: read_iterate() can overflow its return value
- commit:857c88e017f082b6ef2a81a1890baa7d20672a31
- 12:18 PM rbd Bug #4665 (In Progress): librbd: read_iterate() can overflow its return value
- 03:53 PM CephFS Feature #4799 (Resolved): Client Security for CephFS
- As discussed on the #ceph IRC channel with gregaf and others, I would find some added level of client security in Cep...
- 02:11 PM Bug #4749 (Duplicate): osd: failed to recover before timeout
- oh..this is a dup of #4798. the mon is stuck, so the pg stats appear to make no progress.
- 01:52 PM Bug #4749: osd: failed to recover before timeout
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-04-23_11:03:00-rados-next-testing-basic/120
- 01:34 PM CephFS Bug #4721 (Resolved): libcephfs tests fail when using ceph-deploy
- strange that it works fine on the latest next branch [0.60-624-g426e3be-1precise] ...
- 01:10 PM devops Bug #4632 (Resolved): ceph-deploy: osd create command prepares disk but does not activate in centos
- commit:7ad63d23d74e5bc45c44a0192ab1f49ceb68ffa7
- 12:58 PM Bug #4792: filejournal corrupt tests broken
- with commit:8402107c65874262681f27ff6018b0d405af1a94, for those of you following along via email instead of the auto-...
- 12:54 PM Bug #4792 (Resolved): filejournal corrupt tests broken
- 09:29 AM Bug #4792 (Resolved): filejournal corrupt tests broken
- ...
- 12:54 PM rgw Bug #4797 (Resolved): rgw: receiving unexpected error code while accessing an non-existing object...
- The problem happens when a user has been granted the swift read-objs permission on the bucket.
- 12:54 PM Bug #4791 (Need More Info): osd/ReplicatedPG.cc: 7053: FAILED assert(r >= 0) in scan_range
- This may be an ext4 bug, I suggest we ignore it until we see it again on xfs. I've removed ext4 from the rados and r...
- 09:28 AM Bug #4791 (Can't reproduce): osd/ReplicatedPG.cc: 7053: FAILED assert(r >= 0) in scan_range
- ...
- 12:44 PM Bug #3495 (Resolved): ceph-mon crash
- Merged into next with commit:426e3be64e851947b288e43bc0ee932ae7f214bb
- 12:07 PM rbd Bug #3737 (Resolved): Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Thanks for testing it out everyone. It's now in the bobtail branch too.
- 07:09 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- I just tested the Qemu patch with a cherry-pick to Qemu 1.2 and with the wip-bobtail-rbd-backports-req-order branch a...
- 12:06 PM rbd Bug #4551 (Resolved): librbd: rollback broken for clones
- 12:06 PM rbd Bug #4525 (Resolved): hang during librbd python tests
- 12:05 PM rbd Bug #4364 (Resolved): ObjectCacher: inconsistency after flatten
- 12:05 PM rbd Bug #4531 (Resolved): ObjectCacher: read waiters for parent data during copyup get reordered, cau...
- 11:38 AM rbd Bug #4796 (Resolved): krbd: don't create sysfs entries for snapshots of mapped images
- When an rbd image gets mapped a device entry gets created
for it under /sys/bus/rbd/devices/<id>/. Inside that
dir... - 10:56 AM Bug #2476: osd: watch timeout depends on operations to an object
- This looks okay to me, but Sam doesn't remember it and has gotten nervous so now looking at it is in his queue for la...
- 10:55 AM Bug #4521: mon: starting a new osd crashes all mon's
- current mon directory
- 07:16 AM Bug #4521: mon: starting a new osd crashes all mon's
- Evan, after a closer inspection I figured that your bug is indeed different from Sage's.
Can you confirm you ran t... - 10:29 AM CephFS Bug #4742: mds: stuck clientreplay request
- Attaching mds log from mds stuck on clientreplay. Looks like setattr is gets put on the inode waiting list by the lo...
- 09:23 AM rgw Bug #4755: rgw: assumption of signed char
- Adam, I pushed a different fix to wip-4755 branch. Can you test it and make sure that it fixes the issue for you?
- 08:53 AM Bug #4785 (Need More Info): rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r-...
- Can you confirm what version the OSDs are running? My first guess is they have v0.60 or older code that doesn't have...
- 03:03 AM Bug #4785: rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps[r->snaps.s...
- PS Same without "--snap backup.tmp" - to active image only.
- 03:00 AM Bug #4785 (Resolved): rbd export-diff: librados/snap_set_diff.cc: 40: FAILED assert(b == r->snaps...
- Creating backups. Yesterday created snapshots "backup" for every rbd image. Everyday creating snapshot "backup.tmp" a...
- 08:06 AM rbd Bug #4774: krbd: don't create /dev entries for backing devices
- I'm unfortunately finding what I fought with last year when
working with the initialization and teardown of rbd devi... - 05:30 AM Revision 7ad63d23 (ceph): ceph-disk: OSD hotplug fixes for Centos
- Two fixes for Centos 6.3 and other systems with udev versions
prior to 172. The disk peristant name using the GPT UU... - 04:03 AM Revision 3dd9574b (ceph): doc: Usage requires --num_osds.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:02 AM Revision b71ec9c2 (ceph): doc: Added some detail. Calculating PGs, maps; reorganized a bit.
- fixes: #2968
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 03:59 AM Revision aa16700d (ceph): Merge branch 'next'
- 03:59 AM Revision bbcba292 (ceph): set 'filestore flush min = 0' for all ffsb jobs
- Until we fix #4579
04/22/2013
- 11:18 PM Revision f42fc0e4 (ceph): mon: MDSMonitor: tighter leash on cross-proposals to the osdmon
- Fixes: #3495
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 11:18 PM Revision b73ef010 (ceph): mon: [MDS]Monitor: remove 'stop_cluster' and 'do_stop()'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:22 PM Revision 25019803 (ceph): Merge pull request #234 from ceph/wip-4758
- Fixes #4758.
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:20 PM Revision fa77e1e7 (ceph): mon: PaxosService: add request_proposal() to perform cross-proposals
- Instead of allowing services to directly use 'propose_pending()' on
other services, we instead add two new functions:... - 10:20 PM Revision a634bb17 (ceph): mon: PaxosService: is_writeable() depends on being ready to be written to
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:20 PM Revision 98e23980 (ceph): mon: PaxosService: is_readable/writeable() depending on is_active()
- Instead of depending on individual conditions.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:20 PM Revision b29a5b15 (ceph): mon: PaxosService: consider is_recovering() on is_writeable()
- A service is never writeable while it's recovering.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:12 PM Revision 59d6953c (ceph): mon: set threshold to periodically stash_full
- Set an interval to periodically write a full copy of the map that is lower
than the trim point (which is generally a ... - 10:12 PM Revision b33fae4e (ceph): mon: commit LogSummary on every message
- This moves our version pointer up so that we don't re-log (by re-consuming)
log messages to /var/log/ceph/ceph.log on... - 10:11 PM Revision 5792be81 (ceph): Merge pull request #230 from ceph/wip-mon-paxos-fixes
- Wip mon paxos fixes
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 10:05 PM Revision c200cdb0 (ceph): Merge pull request #225 from ceph/wip-4543
- Fixes #4543
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:03 PM Revision 660752a2 (ceph): doc: Added users to Getting Started.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:55 PM Revision 1164345a (ceph): ceph-mon: Attempt to obtain monmap from several possible sources
- In order of interest/priority:
- our latest monmap version
- a backup monmap version created during sync start, ... - 09:53 PM Revision 9ba32404 (ceph): mon: Monitor: backup monmap prior to starting a store sync
- If by fate we end up attempting a store sync after failing at
least one before, we might not have a monmap to read fr... - 09:01 PM Documentation #3674 (In Progress): Deployment documentation is confusing
- 08:44 PM Revision de5d1da8 (ceph): rgw: don't send tail to gc if copying object to itself
- Fixes: #4776
Backport: bobtail
Need to make sure that when copying an object into itself we don't
send the tail to th... - 08:36 PM Revision cec5282b (ceph): Merge pull request #232 from ceph/wip-4710
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 08:23 PM Bug #2476: osd: watch timeout depends on operations to an object
- Greg, can you please review this wip branch?
- 08:01 PM Revision 86ad464f (ceph): Merge branch 'next'
- 08:01 PM Revision 48d89c61 (ceph): ceph-deploy: fix stop command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:58 PM Revision 70e1e47d (ceph): Merge pull request #233 from ceph/wip-mon-idempotent
- Wip mon idempotent
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 07:50 PM Revision 85fd2ca2 (ceph): mon: make 'osd pool rmsnap ...' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:49 PM Revision 43d62c00 (ceph): mon: make 'osd pool mksnap ...' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:48 PM Revision 08e3ec11 (ceph): mon: make 'osd blacklist rm ...' idempotent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:45 PM Bug #4784 (Closed): Two Monitors Concurrently Reporting as Leaders
- There appears to be a bug in the new Monitor Paxos code in version 0.59 and 0.60. Over the past several days, I have ...
- 07:41 PM Revision 5926ffa5 (ceph): rbd: only set STRIPINGV2 feature when needed
- Only set the STRIPINGV2 feature if the striping parameters are non-default.
Specifically, fix the case where the pass... - 07:38 PM Revision 5446218f (ceph): rbd: fix feature display for --info
- Only include the feature if it is set!
Backport: bobtail
Signed-off-by: Sage Weil <sage@inktank.com> - 06:41 PM Revision 568101fa (ceph): rbd: avoid clobbering return value with udevadm settle
- Fixes: #4707
Signed-off-by: Sage Weil <sage@inktank.com> - 06:32 PM Revision 8db9d0a2 (ceph): FileJournal: a valid entry after invalid entry =/=> corrupt
- Out of order journal entry writes using aio may cause entry
n+2 to be written prior to n. This does not indicate
cor... - 06:19 PM devops Bug #4769 (Resolved): centos reimaging script should also include ntpd restart
- Imager has been updated to run ceph-qa-chef after imaging for CentOS like ubuntu so this should be good in the future.
- 11:54 AM devops Bug #4769: centos reimaging script should also include ntpd restart
- Alrighty. I will work on getting the imager to automatically run this for centOS so its not something you have to thi...
- 11:45 AM devops Bug #4769: centos reimaging script should also include ntpd restart
- oops, i did not run ceph-qa-chef on the newly installed centos systems.
- 11:10 AM devops Bug #4769: centos reimaging script should also include ntpd restart
- Were you seeing this not happen after running ceph-qa-chef? On ubuntu this is handled on ceph-qa-chef (not imaging) a...
- 05:53 PM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Nevermind, the logs were saved after all. Hooray!
- 05:52 PM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Unfortunately the logs aren't there anymore (they weren't saved when a power failure restarted the machine running te...
- 05:16 PM rbd Bug #3664 (In Progress): osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Looking at this again, hopefully will get it fixed tomorrow.
- 05:22 PM rgw Feature #3671: Request for x-amz-grant-full-control support
- Merged into master awhile ago, ID eb0f49d4b68062701b842b9cfdde708868769bef
- 05:21 PM rgw Feature #3670: Request for bucket-owner-read and bucket-owner-full-control grants
- caleb miles wrote:
> Committed to master awhile ago, ID e345dfe04a64fcd0d37c9e0717b6714038c302ae
- 05:13 PM rgw Feature #3670 (Resolved): Request for bucket-owner-read and bucket-owner-full-control grants
- Committed to master awhile ago, ID eb0f49d4b68062701b842b9cfdde708868769bef
- 05:11 PM rbd Bug #4774 (In Progress): krbd: don't create /dev entries for backing devices
- This is what I am now working on; just marking it so.
- 05:09 PM rbd Bug #3847 (Resolved): rbd: figure out correct byte order for watch version
- The following has been committed to the "testing" branch
of the ceph-client git repository:
42c6070 libceph: fix ... - 05:06 PM rbd Feature #4709 (Resolved): krbd: support stripingv2 images that don't require I/O path changes
- The following has been committed to the "testing" branch
of the ceph-client git repository:
09186dd rbd: get and ... - 05:04 PM rbd Bug #4773 (Resolved): rbd: have rbd_obj_method_sync() return transfer count
- The following have been committed to the "testing" branch of
the ceph-client git repository.
3ad6cbd9 libceph: ad... - 04:54 PM devops Feature #4667: ceph-deploy update
- I have a start which installs based on the currently-configured repos (of which, at the moment,
none actually contai... - 03:27 PM devops Feature #4667 (In Progress): ceph-deploy update
- 04:53 PM rbd Feature #4724 (Resolved): krbd: handle layered I/O correctly when the child has been resized
- The following has been committed to the "testing" branch
of the ceph-client git repository:
64548e0 rbd: enforce ... - 04:39 PM Bug #4783 (Resolved): After repairs finish a new deep-scrub should be avoided
The fix for #4778 needs to initiate a deep-scrub after repairs are complete to clear the PG_STATE_INCONSISTENT. We...- 04:14 PM Revision 9b953aa4 (ceph): radosgw: Fix duplicate 'Content-Type' when using 'response-content-type'
- Signed-off-by: Sylvain Munaut <s.munaut@whatever-company.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 04:08 PM Revision 4b9a2a39 (ceph): mon: MonmapMonitor: add function to obtain latest monmap
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:08 PM Revision 41b874cb (ceph): mon: PaxosService: add 'exists_key/version' helper functions
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:47 PM devops Bug #4767 (Pending Backport): ceph-deploy: install should default to picking cuttlefish when cutt...
- wip-4767, ready to merge right when cuttlefish is released.
- 03:39 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- this is not new behavior, so it is not a cuttlefish blocker. feature #4782 is the current proposed fix.
- 03:37 PM Feature #4782 (Resolved): osd: build writeback model to replace async flusher
- build a model that includes
- dirty bytes value
- dirty files values
- a cost function of bytes and inodes
... - 03:34 PM Bug #4552 (In Progress): osd: temporarily hung box marks down peers
- 03:22 PM Bug #4758 (Resolved): monitor: going through all incrementals on startup
- Commit:25019803507114e8ab2082d2c44af6588e5aafc2
- 03:01 PM Bug #4758 (Fix Under Review): monitor: going through all incrementals on startup
- 03:16 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I just hit this again with the current testing branch.
testing e7fce31 rbd: issue a copyup for layered writes
- 03:08 PM Bug #4543 (Resolved): mon: corrupted store if monitor dies mid-sync
- commit: c200cdb08108ae901c4c6f3625d55da707a38e5a
- 11:28 AM Bug #4543 (In Progress): mon: corrupted store if monitor dies mid-sync
- Whoops, wrong one before.
- 11:28 AM Bug #4543 (Need More Info): mon: corrupted store if monitor dies mid-sync
- 11:28 AM Bug #4543: mon: corrupted store if monitor dies mid-sync
- New comments; should be quick to address; have you tested it?
- 09:15 AM Bug #4543 (Fix Under Review): mon: corrupted store if monitor dies mid-sync
- Revised version and comments on github.
- 02:59 PM rbd Feature #4550 (In Progress): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- oops, didn't mean to change the status
- 02:55 PM rbd Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- I'd suggest starting with the latest version of qemu-kvm for centos 6 (the c6 branch of https://nazar.karan.org/summa...
- 12:24 PM rbd Feature #4550 (In Progress): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
It looks like I want to grab the source for the qemu-kvm-0.12.1.2-2.295 package that ships with centos 6.3, rebuild...- 02:55 PM Bug #4765 (Rejected): monitor: sets global version feature but upgrades might not actually have a...
- A-hah! We only need the global versions on those updates which will be involved in syncing during/following the cuttl...
- 02:36 PM rgw Bug #4776 (Resolved): S3 copy part corrupt files >512kb
- Fixed, commit:de5d1da810732ee48f41e8be18257053d862301b. Merged into next, bobtail.
- 09:31 AM rgw Bug #4776 (Need More Info): S3 copy part corrupt files >512kb
- 01:38 AM rgw Bug #4776 (Resolved): S3 copy part corrupt files >512kb
- We are using radosgw and s3 API and we recently needed to update metadata on some files.
So we used the copy part of... - 01:40 PM rbd Bug #4710 (Resolved): rbd: STRIPINGV2 feature specified by default for format 2 images
- 12:46 PM rbd Bug #4710 (Fix Under Review): rbd: STRIPINGV2 feature specified by default for format 2 images
- 11:42 AM rbd Bug #4710 (In Progress): rbd: STRIPINGV2 feature specified by default for format 2 images
- 11:29 AM rbd Bug #4710: rbd: STRIPINGV2 feature specified by default for format 2 images
- Per Josh, this is easy fix, let's get it into Cuttlefish.
- 01:31 PM Bug #4778 (In Progress): scrub clears inconsistent flag set by deep scrub
- 10:22 AM Bug #4778: scrub clears inconsistent flag set by deep scrub
- Can we fix this without adding a separate deep-scrub inconsistent flag? (and is it feasible to do that before Cuttlef...
- 06:45 AM Bug #4778 (Resolved): scrub clears inconsistent flag set by deep scrub
- On my 0.56.4 cluster, I have some pgs marked as inconsistent because of an omap inconsistency that .4 is able to dete...
- 12:46 PM rbd Feature #3419 (Resolved): krbd: copy-up on write to clone
- The following have been committed to the ceph-client
"testing" branch.
b15a1df rbd: implement full object parent ... - 10:08 AM rbd Feature #3419: krbd: copy-up on write to clone
- The following have been committed to the ceph-client
"testing" branch. Still waiting on reviews for the
last two.
... - 11:41 AM rbd Bug #4707 (Resolved): rbd CLI: bad error code masked by udevadm_settle
- commit:568101fa72e29ee960fcf3d704f04edfd50bd072
- 11:39 AM rbd Bug #4707 (In Progress): rbd CLI: bad error code masked by udevadm_settle
- 11:27 AM rbd Bug #4707: rbd CLI: bad error code masked by udevadm_settle
- Let's try to get this into Cuttlefish.
- 11:35 AM Bug #4736 (Resolved): journal Entry at pos 83251200 valid, there are missing sequence numbers pri...
- Created new task for actual solution.
- 10:19 AM Bug #4736 (In Progress): journal Entry at pos 83251200 valid, there are missing sequence numbers ...
- 11:32 AM Feature #4781 (New): Journal entries should record last known committed entry
- This can be used to detect more corrupt journal cases.
- 11:31 AM rbd Bug #4665: librbd: read_iterate() can overflow its return value
- Per Josh, this is another easy fix, let's get it into Cuttlefish.
- 10:57 AM Bug #4757: ceph-disk-prepare will not use all available space with >2TB hard drives
- My suspicion is that Tv ran across this bug, and some version of gdisk wanted to reorder
partitions based on starti... - 10:20 AM Bug #4772: (deep?) scrubbing scheduling misses PGs
- Yes it was and there are no indications of flapping OSDs that I can see.
I think I found the same pgs being scrubb... - 09:33 AM Bug #4772 (Need More Info): (deep?) scrubbing scheduling misses PGs
- Scrubbing skips pgs that are degraded... was the cluster active+clean when you did the scheduling?
- 10:04 AM rbd Bug #4762 (Resolved): libceph: fix two messenger bugs
- The following has been committed to the ceph-client "testing"
branch:
68423cc libceph: fix two messenger bugs
- 09:52 AM Bug #4780: RBD-Enabling Discard Trim
- This strictly speaking isn't true "Note that this uses the IDE driver. The virtio driver does not support discard." p...
- 09:48 AM Bug #4780 (Resolved): RBD-Enabling Discard Trim
- We need to provide examples for configuring libvirt, since we now support SCSI. Virtio and SCSI should be the main ex...
- 09:35 AM Bug #4779 (Resolved): The ceph command and crushtool have differing views on valid characters for...
- Using osd crush move, I can create a bucket with a '/' in the name.
If I then get a crush map, decompile it, and att... - 09:25 AM devops Bug #4752 (Resolved): ceph-create-keys doesn't work on upgraded clusters
- Further update from Dan indicated that EACCES was returned on authentication error after all. I tested the changes b...
- 09:09 AM rgw Bug #4124 (Resolved): Using "response-content-type" arguments causes duplicated Content-Type in r...
- Merged in, commit:9b953aa4100eca5de2319b3c17c54bc2f6b03064
- 05:34 AM rbd Bug #4777 (Resolved): krbd: verify a few things in the zeroing routines
- The kernel rbd driver has a function zero_bio_chain() that's
used to zero out the data in a bio list starting at a g... - 05:08 AM Revision 1a8b30ef (ceph): ceph-create-keys: Don't wait if permission denied
- If get or create keys returns permssion denied, exit
gracefully instead of retrying.
Signed-off-by: Gary Lowell <ga... - 03:02 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Ooops, sorry...,
was a bit misleaded, cause "cache=writeback" was still in the config file.
Oliver.
04/21/2013
- 06:11 PM rgw Support #4775 (Resolved): Why I can created an exsiting bucket
- There is a bucket named abcdef in the ceph. It contains 5 objects.
Then I create a new bucket with the same name a... - 02:56 PM rbd Bug #3847 (Fix Under Review): rbd: figure out correct byte order for watch version
- The following has been posted for review:
[PATCH] libceph: fix byte order mismatch
It is available in the "revi... - 02:39 PM rbd Bug #3847 (In Progress): rbd: figure out correct byte order for watch version
- libceph: fix byte order mismatch
A WATCH op includes an object version. The version that's supplied
is incorrect... - 02:24 PM rbd Bug #4774 (Resolved): krbd: don't create /dev entries for backing devices
- Currently when a layered rbd device gets mapped, the
snapshot device that is its parent gets probed in the
same way... - 02:21 PM rbd Feature #4709 (Fix Under Review): krbd: support stripingv2 images that don't require I/O path cha...
- The following has been posted for review and is available
in the "review/wip-stripe-v2" branch of the ceph-client
g... - 06:50 AM rbd Feature #4709 (In Progress): krbd: support stripingv2 images that don't require I/O path changes
- Starting work on this.
- 02:20 PM rbd Bug #4773 (Fix Under Review): rbd: have rbd_obj_method_sync() return transfer count
- The following have been posted for review, and are
available in the "review/wip-stripe-v2" branch of
the ceph-clien... - 10:28 AM rbd Bug #4773: rbd: have rbd_obj_method_sync() return transfer count
- I've implemented these fixes and will post them for
review after I've done some better testing.
I also made a few... - 07:59 AM rbd Bug #4773 (Resolved): rbd: have rbd_obj_method_sync() return transfer count
- Callers of rbd_obj_method_sync() don't know how many bytes of data
got returned by the class method call. As a resu... - 08:54 AM Bug #4757: ceph-disk-prepare will not use all available space with >2TB hard drives
- We should also get more details about what the original problem was before just assuming it's fixed. I bet Mark has T...
- 06:12 AM CephFS Bug #4753: mds/Locker.cc: 4167: FAILED assert(0)
- Additional: I resolve it runtime, changing assert(0) to some lock (IMHO first in this case) on one node and found for...
04/20/2013
- 10:36 PM rbd Feature #4724 (Fix Under Review): krbd: handle layered I/O correctly when the child has been resized
- The following has been posted for review:
[PATCH] rbd: enforce parent overlap
- 06:10 PM Revision 1fa719d5 (ceph): doc: Aesthetic improvements. Removed unnecessary graphic and overrode m...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:08 PM Revision 3749ffe6 (ceph): doc: Added a scenario to PG troubleshooting.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:06 PM Revision cf915941 (ceph): doc: Changed usage to "bucket-name". Description was okay.
- fixes: #4102
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 11:14 AM Documentation #4102 (Resolved): doc: in crush-map-rules, wrong spec for step take
- http://ceph.com/docs/next/rados/operations/crush-map/ Should appear in master within a week.
- 10:32 AM rbd Feature #3418 (Resolved): krbd: write path (layering)
- The following have been committed to the "testing" branch
of the ceph-client git repository:
a065a13 libceph: kil... - 07:47 AM Bug #4772 (Can't reproduce): (deep?) scrubbing scheduling misses PGs
- I have a 144 OSD (135 in) cluster, partioned in ~10 pools and 16760 pgs in total. The cluster runs Ceph 0.56.4 using ...
- 01:56 AM Feature #4771 (Rejected): Snippet / included configuration
- When managing large systems via Puppet or some other configuration tool it could be very useful to have "snippet" con...
- 01:23 AM Revision 861ac497 (ceph): added ceph.client.admin.keyring on the client to run rbd and rados tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:14 AM Revision c4f8adca (ceph): Merge branch 'wip-4201' into next
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 01:13 AM Revision 2bbac6e4 (ceph): added extra packages required by ceph-deploy for rbd and rados tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:11 AM Revision 870f47c7 (ceph): tools/ceph-filestore-dump: Implement remove, export and import
- Change local names to be clearer
Break real_log() into common function get_log()
Move infos_oid, biginfo_oid and log_... - 12:11 AM Revision 481c532f (ceph): Merge branch 'wip_4662_clean' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 12:10 AM Revision 6ef0f162 (ceph): PG: check for pg change in ~FlushState
- Fixes: #4662
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:10 AM Revision 0e155550 (ceph): ReplicatedPG::_applied_recovered_object*: don't queue scrub if deleting
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:10 AM Revision 88d9ee1d (ceph): ReplicatedPG::_finish_mark_all_unfound_lost: only requeue if !deleting
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:10 AM Revision b8cb9d7e (ceph): PG: bail if deleting in _finish_recovery
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:10 AM Revision 75cb55b4 (ceph): AsyncReserver: delete context in cancel_reservation
- Fixes: #4662
Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com> - 12:08 AM Revision 460db089 (ceph): osd: Add flag to force version write in _write_info()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 12:08 AM Revision 37d2fe2c (ceph): osd: Make clear_temp() public for use by remove
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 12:08 AM Revision d73b9fbe (ceph): tools/ceph-filestore-dump: Error messages lost because stderr is closed
- Use cout instead of cerr for command errors
Use cerr for debug mode because stderr is avail
Output map_epoch in debug... - 12:08 AM Revision da39f911 (ceph): osd: Create static PG::_write_log() function
- Signed-off-by: David Zafman <david.zafman@inktank.com>
04/19/2013
- 10:23 PM Revision ad845e61 (ceph): OSDMonitor: pg split is no longer experimental
- Fixes: #4711
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:16 PM Revision 095dc4f6 (ceph): Merge pull request #228 from alram/next
- Fix journal partition creation
Reviewed-by: Sage Weil <sage@inktank.com> - 10:11 PM Revision 56619ab9 (ceph): Fix journal partition creation
- With OSD sharing data and journal, the previous code created the
journal partiton from the end of the device. A uint3... - 09:37 PM Revision fe9d3260 (ceph): rbd: fix qa tests to use --allow-shrink
- Fixes: #4763
Signed-off-by: Sage Weil <sage@inktank.com> - 09:34 PM Revision b6b4ebed (ceph): osd: an interval can't go readwrite if its acting is empty
- Let's not forget that min_size can be zero.
Fixes: #4159
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked ... - 09:33 PM Revision 055d746c (ceph): mon: restrict pool size to 1..10
- See: #4159
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 30b8d653751acb4bc4be5ca611f154e19af... - 09:28 PM Revision f114fdc4 (ceph): Merge pull request #227 from ceph/wip-4574
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 08:25 PM Linux kernel client Feature #4770 (Resolved): krbd: consider including write data with layered existence check
- Josh suggested we could pass along the data to be written
along with the STAT op sent to the osd for a target object... - 08:08 PM Revision c073bd25 (ceph): init-ceph: do not stop start on first failure
- When starting we often loop over many daemon instances. Currently we stop
on the first error and do not try to start... - 08:05 PM Revision d395aa52 (ceph): init-ceph: do not stop start on first failure
- When starting we often loop over many daemon instances. Currently we stop
on the first error and do not try to start... - 07:34 PM Bug #4757: ceph-disk-prepare will not use all available space with >2TB hard drives
- Really confused by that state; journal should have been partition 2 at the end of the drive, so more is wrong than ju...
- 03:25 PM Bug #4757 (Resolved): ceph-disk-prepare will not use all available space with >2TB hard drives
- 10:51 AM Bug #4757: ceph-disk-prepare will not use all available space with >2TB hard drives
- I ran ceph-disk-prepare with the patch for a disk of 3TB and a disk of 10GB. Multiple times, with and without --zap-d...
- 09:54 AM Bug #4757: ceph-disk-prepare will not use all available space with >2TB hard drives
- hrm, that comment came from tv, so who knows what he was seeing. can you do some testing with the change and see if ...
- 09:50 AM Bug #4757 (Resolved): ceph-disk-prepare will not use all available space with >2TB hard drives
- When sharing the journal with the OSD data, ceph-disk-prepare will not use all the available disk space with disks >2...
- 07:26 PM Revision 9a7d1f51 (ceph): mon: Monitor: fix timechecks get_health clobbering overall status
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 07:20 PM rbd Feature #3419 (Fix Under Review): krbd: copy-up on write to clone
- The following has been posted for review.
This set of patches culminates in providing layered
write functionality... - 07:19 PM rbd Bug #4762 (Fix Under Review): libceph: fix two messenger bugs
- The following has been posted for review:
[PATCH] libceph: fix two messenger bugs - 01:10 PM rbd Bug #4762 (Resolved): libceph: fix two messenger bugs
- While getting copyup functionality working I found two
bugs in the messenger that previously were not triggered.
... - 07:16 PM Revision aa0d5f39 (ceph): mon: fix health monitor calls
- - unconditionally call get_health, regardless of formatter *
- return a meaningful health status code
Signed-off-by:... - 07:03 PM Revision be4807f5 (ceph): global: call observers (and start logging) in global_init
- Call observers so that the logging infrastructure gets initailized and we
start logging. Otherwise, unless a default... - 06:29 PM Revision 52d8240a (ceph): osd: Add OSD::make_infos_oid() as common function to create oid
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:29 PM Revision 76505c28 (ceph): osd: Create new static function PG::_write_info() for use by PG import
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:29 PM Revision 5ffb3ef4 (ceph): filestore, osd: Fixes to comform to programming guidelines
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:26 PM Revision fa89cfd2 (ceph): mon: QuorumService: return health status on get_health()
- This allows us to return the appropriate overall health status on
Monitor::get_health().
Fixes: 4574
Signed-off-by:... - 06:21 PM Feature #4201 (Resolved): osd: data loss: pg export/import/remove
- commit:870f47c7cb24b5da7a7e3a5ba45f140e268c0754
- 06:06 PM Revision 78c9db88 (ceph): OpRequest: don't maintain history if the OSD is shutting down
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:05 PM Revision 1493e7db (ceph): osd/: optionally track every pg ref
- This involves three pieces:
For intrusive_ptr type references, we use TrackedIntPtr instead. This
uses get_with_id ... - 06:05 PM devops Bug #4769 (Resolved): centos reimaging script should also include ntpd restart
- The reimaging script, we currently have for centos should include 'restart ntpd' at the end of the script as the ntpd...
- 06:00 PM Revision 8fe1b9d5 (ceph): ReplicatedPG: use ReplicatedPGRef for C_OSD_OpApplied
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision f03ba5a2 (ceph): ReplicatedPG: use ReplicatedPGRef for C_OSD_OpCommit
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 4090eff8 (ceph): ReplicatedPG: use ReplicatedPGRef for C_PG_MarkUnfoundLost
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision ec6f71bd (ceph): ReplicatedPG: use the ReplicatedPGRef typedef
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 66c007fb (ceph): common/: add tracked_int_ptr.hpp
- TrackedIntPtr acts like intrusive_ptr, but is able to
track a ref id.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:00 PM Revision 220c6512 (ceph): ReplicatedPG: add ReplicatedPGRef
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision b021036b (ceph): PG,ReplicatedPG: move intrusive_ptr declarations to top
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision ce647753 (ceph): PG: do not put() in scrub() if pg is deleting
- scrub() no longer handles the put, this call
must have been missed.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:00 PM Revision 8bd89e12 (ceph): PG: use PGRef in C_PG_ActivateCommitted
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 2f9a35ac (ceph): PG: use PGRef for C_PG_FinishRecovery
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision f45a5413 (ceph): PG: use PGRef for FlushState
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 0b7795ac (ceph): OSD: use PGRef in consume_map
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision c2127a11 (ceph): PG: use PGRef in QueuePeeringEvt
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 1c2b66cf (ceph): OSD: use PGRef in handle_pg_stats_ack
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision c04c3e59 (ceph): OSD: use PGRef in handle_pg_remove
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 07a80ee3 (ceph): FileStore::_do_clone_range: _do_copy_range encodes error in return, not...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:00 PM Revision 016e975a (ceph): FileStore::_do_copy_range: read(2) might return EINTR
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:41 PM devops Bug #4767 (Resolved): ceph-deploy: install should default to picking cuttlefish when cuttlefish i...
- currently, ceph-deploy install defaults to bobtail but when cuttlefish is ready, it should default to cuttlefish.
... - 05:20 PM Revision af5a9b37 (ceph): Merge pull request #224 from ceph/wip-mon-crush
- Wip mon crush
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 05:20 PM devops Feature #4766 (Rejected): ceph-deploy: commands should continue to execute the next argument in c...
- currently, when trying to create multiple osds using the "osd create" command, the command returns failure when the f...
- 05:14 PM Bug #4662 (Resolved): osd/OSD.h: 809: FAILED assert(peering_queue.empty()) on shutdown
- 481c532ff361b21e044621ac13c8f00ebfb1b3dc
- 05:06 PM Bug #4747 (Can't reproduce): Upgrade monitors from argonaut->bobtail->next fails w/"Existing stor...
- Awesome. I made #4758 for the fast-convert story I mentioned.
- 04:46 PM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- It's a manual process so I could have missed something along the way. If I used upgrade instead of dist-upgrade for ...
- 01:41 PM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- Shoot; it looks like this is actually just checking the on-disk features CompatSet; it's not iterating through the ac...
- 10:48 AM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- I'm not currently working on this, so I'm unassigning it from me (but still watching) in case someone else wants to p...
- 10:00 AM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- It pretty much has to, unless it were given separate logic to figure out which commits "matter", which would be not g...
- 09:55 AM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- hmm, could the problem may be that it wants gv values for *everything* in the mon store, not just the recent commits?
- 09:52 AM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- I was able to recreate this twice. The first time included running functional tests in between each installation ie....
- 09:44 AM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- Greg Farnum wrote:
> I believe this is about the pre-Bobtail change which started adding global ordering values to t... - 04:53 PM Bug #4765 (Rejected): monitor: sets global version feature but upgrades might not actually have a...
- We don't check on doing a store conversion that we actually have GV values, only that they've been enabled on the mon...
- 04:30 PM Revision 5e4b8bc4 (ceph): config: clarify 'mon osd down out subtree limit'
- Clarify the description; this is the subtree type that we won't mark out
if it is all down, but anything less than it... - 03:25 PM Bug #4711 (Resolved): mon: remove --enable-experimental-feature on set pg_num
- 03:19 PM Bug #4764 (Can't reproduce): ceph -w sometimes does not reflect clean pgs
- ceph -s reports all pgs clean, but ceph -w does not include an entry for it.
ceph3/src [wip_4711?] » ./ceph -w
... - 03:08 PM Bug #4749 (In Progress): osd: failed to recover before timeout
- 02:39 PM Bug #4699 (Resolved): osd: crash when looking at a map changing pool size from 0 to 2
Cherry-picked changes for bug #4159
commit:80682c88ef71ca4977df83f8d9b82310a76cf93d
commit:aa91dbf11deb02a25f7ff9...- 02:38 PM rbd Bug #4763 (Resolved): rbd test scripts should use --allow-shrink flag when resizing rbd img
- 01:58 PM rbd Bug #4763 (In Progress): rbd test scripts should use --allow-shrink flag when resizing rbd img
- 01:28 PM rbd Bug #4763 (Resolved): rbd test scripts should use --allow-shrink flag when resizing rbd img
- The existing rbd test script rbd/copy.sh fails with the recent inclusion of --allow-shrink flag for the resize comman...
- 02:30 PM Bug #4574 (Resolved): mon: HEALTH_OK even if data health is HEALTH_WARN
- Looks good to me; I tested and merged. commit:f114fdc40a0aac9f38745c50dce18d186e657acd
- 12:23 PM Bug #4574 (Fix Under Review): mon: HEALTH_OK even if data health is HEALTH_WARN
- 12:22 PM Bug #4574: mon: HEALTH_OK even if data health is HEALTH_WARN
- proposed fix on wip-4574
- 01:28 PM Bug #4543 (In Progress): mon: corrupted store if monitor dies mid-sync
- Comments on Github; and this is one that we'll definitely need to test before merging.
- 09:30 AM Bug #4543 (Fix Under Review): mon: corrupted store if monitor dies mid-sync
- wip-4543 has a proposed fix -- haven't tested it yet.
- 01:06 PM Bug #2545 (Resolved): init-ceph: stops if one instance fails to start
- commit:d395aa521e8a4b295ed2b08dd7cfb7d9f995fcf7
- 12:47 PM Bug #2545: init-ceph: stops if one instance fails to start
- Looks good. That was a lot simpler than I expected.
- 09:20 AM Bug #2545: init-ceph: stops if one instance fails to start
- Gary, Can you please review wip-sysvinit?
- 09:19 AM Bug #2545 (Fix Under Review): init-ceph: stops if one instance fails to start
- wip-sysvinit
- 12:25 PM Bug #4748 (In Progress): mon: failed assert in OSDMonitor::build_incremental
- 09:48 AM Bug #4748: mon: failed assert in OSDMonitor::build_incremental
- Possibly related to #4521
- 12:24 PM Bug #4228: mon uses pick_addresses if invoked with mkfs or without mon addr; fails if no cluster ...
- Currently not working on this one, so if anyone wants to pick it up go for it. Otherwise, I'll get back to it as soon...
- 12:04 PM Bug #4676 (Resolved): daemon logs aren't opened until daemonize
- commit:be4807f5b88115bc5a553ecee6f42c0c7d7cfbe2
- 12:03 PM Bug #4676 (Fix Under Review): daemon logs aren't opened until daemonize
- wip-log
- 11:33 AM Bug #4731: PG: don't write out pg epoch on every map activation
- 0d6881c8 does seem to do the trick. Not sure yet whether we want this in bobtail. Shouldn't be a problem in cuttlef...
- 11:29 AM Bug #4009 (Duplicate): osd reports map e6 wrongly marked me down
- I think this is 4579
- 11:26 AM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- I opened 3 issues for this problem:: #4759, #4760, #4761. These will make it so that it'll be possible to list contai...
- 11:02 AM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- Corrected by a colleague of mine: Swift does paginate, at 10.000 items. It would help but not that much in my case as...
- 07:43 AM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- Swift doesn't seem to paginate this. I haven't looked at Swift's internals for this but I doubt it lists all of my co...
- 07:32 AM rgw Bug #4754: GET/HEAD on account is extremely slow, times out
- Right. There are two issues that play together here. One is that we don't paginate the request, the second one is tha...
- 06:22 AM rgw Bug #4754 (Resolved): GET/HEAD on account is extremely slow, times out
- Doing a GET or a HEAD on /swift/v1 times out, even after increasing the timeout to 5 minutes. It's hard to know the e...
- 11:24 AM Bug #4698: osd suicide timed out after 150
- This appears to be a filesystem problem with ext4.
- 08:52 AM Bug #4698: osd suicide timed out after 150
- Any update on this? Is it still happening?
- 11:23 AM rgw Feature #4761 (New): rgw: swift list containers should get stats asynchronously
- 11:23 AM Bug #4686: corrupt or missing osdmap on load_pgs
- I have also not been able to reproduce this one.
- 08:56 AM Bug #4686: corrupt or missing osdmap on load_pgs
- Is this still occurring? Still planning fix for Cuttlefish?
- 11:23 AM Bug #4602: osd/ReplicatedPG.cc: 6487: FAILED assert(latest->is_update())
- I haven't seen it since.
- 08:55 AM Bug #4602: osd/ReplicatedPG.cc: 6487: FAILED assert(latest->is_update())
- Sam - any update on this? Are we still seeing this? Still trying to get this into Cuttlefish?
- 11:23 AM rgw Bug #4760 (Resolved): rgw: list buckets/containers should be streamlined
- 11:22 AM rgw Feature #4759 (Resolved): rgw: option swift list container without container stats
- We'd like to be able to dump container list without required to dump stats for each container.
- 11:04 AM devops Bug #4752: ceph-create-keys doesn't work on upgraded clusters
- ceph CLI currently fails in ceph_tool_common_init and doesn't pass back a failure code that can be interpreted, so re...
- 09:58 AM devops Bug #4752 (In Progress): ceph-create-keys doesn't work on upgraded clusters
- 11:02 AM Bug #4620 (Resolved): mon: Paxos proposals take too long to finish when transaction is huge
- Greg and Jim Schutt took care of this issue (commit:d8a354d511c96f5a1a25ec907f96e77f047b7c01)
Also, increasing the... - 10:48 AM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- That's actually CORS, which already went into cuttlefish.
- 10:45 AM Bug #4758 (Resolved): monitor: going through all incrementals on startup
- Apparently the monitor is incrementing through vast numbers of PGMap and OSDMap incrementals in some cases, and that ...
- 10:42 AM Bug #3495: ceph-mon crash
- 09:34 AM Bug #3495: ceph-mon crash
- Denis, you appear to be using master [1]; the fix is only available on wip-3495.
[1]:... - 09:20 AM Bug #3495: ceph-mon crash
- Fixme if I use wrong branch, but:
0> 2013-04-19 19:06:29.120708 7fb556116700 -1 mon/PaxosService.cc: In funct... - 07:45 AM Bug #3495: ceph-mon crash
- This has been stable for me for >24-hours. I think you've got it. Thanks for all your help!
- 10:17 AM CephFS Bug #4105: mds: fix up the Dumper
- This has annoyed me a couple more times and I think it's now at the top of the queue, so here we go again.
- 10:08 AM CephFS Bug #4746: client: invalidate callback can deadlock
- pushed wip-fuse to ceph-client.git
- 09:46 AM Bug #4521: mon: starting a new osd crashes all mon's
- Sage opened a bug for that one here: http://tracker.ceph.com/issues/4748
- 09:40 AM Bug #4521: mon: starting a new osd crashes all mon's
- debug for ms and mon at 20, log attached.
- 08:31 AM Bug #4521: mon: starting a new osd crashes all mon's
- that store was after i ran the fix(log wip4521.fix_debugA), started the mon, then it crashed.
will run again wit... - 09:42 AM CephFS Bug #4753: mds/Locker.cc: 4167: FAILED assert(0)
- You mean file_eval should just short-circuit if it's scanning? That seems like the most sensible place for it, but I'...
- 09:31 AM CephFS Bug #4753: mds/Locker.cc: 4167: FAILED assert(0)
- yeah, that transition doesn't make sense. i think it should do nothing in the scan state..
- 09:05 AM CephFS Bug #4753: mds/Locker.cc: 4167: FAILED assert(0)
- file_eval is trying to move ifile from "scan" to "mixed" in order to serve up the client caps, and scatter_mix doesn'...
- 09:30 AM devops Bug #4756 (Resolved): mkcephfs doesn't set up same keys as ceph-deploy
- Notably, "mon." doesn't get any permissions associated with it, which can also lead to the problems in #4752. Until w...
- 09:17 AM rgw Bug #4755: rgw: assumption of signed char
- Doh, in the title, s/patch/char/, of course.
- 09:16 AM rgw Bug #4755 (Resolved): rgw: assumption of signed char
- I'm testing ceph on an armhf based server. During compilation (from Debianized sources you provide), it turns out th...
- 08:53 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Josh - any update? Are we still going to get this in Cuttlefish?
- 06:43 AM Bug #4723: FAILED assert(!db->create_and_open(std::cerr)) after IO Error.
- This should probably be closed with can't reproduce. Now that the cluster is healthy I'm not able to produce the same...
- 06:16 AM rgw Feature #4613: Allow bucket data to reside in a separate pool to object data
- This would be especially useful for us, perhaps even a must. We have 200-250 million files split in a number of conta...
- 05:35 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- It appears that, when starting a monitor, we will o through all the pg and osdmap incremental versions and apply them...
- 05:20 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- btw, and as such:...
- 05:18 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- starting monitors with tcmalloc noticed the following (both are peons):...
- 02:13 AM CephFS Bug #4601: symlink with size zero
- I was looking at the <inode>.<frag>_head* file in the osd that held the directory where the link was stored. As it t...
04/18/2013
- 11:22 PM Revision 60e7fb41 (ceph): turn on debugging for MDS and Client in FS runs
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:21 PM Revision e21fdf81 (ceph): ior-cfuse: remove the binary/ dir that make install creates
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:21 PM Revision cb1e8ed9 (ceph): turn on debugging for MDS and Client in FS runs
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:23 PM Revision cd2cabec (ceph): doc: Trimmed toc depth for nicer visual appearance.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:08 PM Revision 44aa696b (ceph): doc: Added new PG troubleshooting use case.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:08 PM Revision 2e3579ed (ceph): doc: Updated title.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:07 PM Revision 304a2343 (ceph): doc: Added PG troubleshooting to toctree.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:51 PM Revision a975f9df (ceph): packaging: Add ceph-test debian package
- The ceph-test package includes optional test and benchmarking programs.
Conflicts:
debian/control
debian/rules - 08:51 PM Revision 2382d9b7 (ceph): deb: Add ceph-coverage to ceph-test deb package
- Teuthology uses the ceph-coverage script extensively
and expects it to be installed by the ceph task. Add
the script... - 08:30 PM Revision d5139ba1 (ceph): doc: Bifurcating OSD and PG Troubleshooting. Updated hyperlink.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:30 PM Revision 3b8057ac (ceph): doc: Bifurcating OSD and PG Troubleshooting. Added PG troubleshooting doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:29 PM Revision 3c4bf83c (ceph): doc: Bifurcating OSD and PG Troubleshooting. Removed PG section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:13 PM rgw Feature #4327 (In Progress): rgw: dr: updated buckets log: create internal API
- 08:07 PM rgw Feature #4573 (In Progress): Create User Quota Blueprint
- 08:07 PM rgw Feature #4745 (In Progress): rgw: radosgw-admin command to stat object
- 06:42 PM Revision 46d8b9f2 (ceph): rgw_bucket: Fix dump_index_check.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 06:20 PM Revision 0d46dc46 (ceph): mon: make 'osd crush link ...' idempotent
- We fixed move in f5ba0fbbe73e11418634bc95e1fc36d17edccf37 but missed this
one.
Signed-off-by: Sage Weil <sage@inktan... - 06:20 PM Revision b0c1001a (ceph): mon: ensure 'osd crush rule ...' commands are idempotent
- Ensure that we return 0 for these cases.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:11 PM Revision decdeadf (ceph): Merge branch 'next'
- 06:09 PM Revision 5f1898d9 (ceph): rgw_bucket: Fix dump_index_check.
- Signed-off-by caleb miles <caleb.miles@inktank.com>
- 05:41 PM Revision 7e4f80b1 (ceph): debian/control: Fix typo in libboost version number
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 05:41 PM Revision f4bc7607 (ceph): build: Add new package dependencies
- Add libboost-system-dev (bug #4725).
Add hdparm to rpm installation requirements. The hdparm
command is used to det... - 05:39 PM Revision efbe2e8b (ceph): Merge branch 'wip-max_size-3637' into next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:38 PM Revision 87634d88 (ceph): mds: journal the projected root xattrs in add_root()
- In EMetaBlob::add_root(), we should log the projected root xattrs
instead of original ones to reflect xattr changes.
... - 05:38 PM Revision f379ce37 (ceph): mds: fix setting/removing xattrs on root
- MDS crashes while journaling dirty root inode in handle_client_setxattr
and handle_client_removexattr. We should use ... - 05:23 PM Bug #4521: mon: starting a new osd crashes all mon's
- Evan, is that store prior or post applying the fix? It doesn't seem fixed at all.
Also, when you have the chance, ... - 09:25 AM Bug #4521: mon: starting a new osd crashes all mon's
- I pulled the updates, I compiled and installed. I ran the fix,( see attached log). I started the new mon, and tried...
- 05:22 PM CephFS Bug #4753 (Resolved): mds/Locker.cc: 4167: FAILED assert(0)
- Every mds crashed after some startup checks: "mds/Locker.cc: 4167: FAILED assert(0)":
mds/Locker.cc: 4167: FAILED ... - 05:15 PM Revision a3c48351 (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>
(cherry picked from com... - 05:15 PM Revision 4efed084 (ceph): ceph-deploy: stop daemons, archive, then purge[data]
- Purge removes logs, and we want to archive those, so explicitly shut down
all daemons before doing the archiving step... - 05:12 PM CephFS Bug #4746: client: invalidate callback can deadlock
- The suggestion from Maxim is to modify fuse to serialize reads and invalidate via a mutex. That ought to do the tric...
- 09:37 AM CephFS Bug #4746: client: invalidate callback can deadlock
- It's not any of our internal locking that are getting stuck; it's the VFS inode mutexes in combination with us. If I ...
- 07:31 AM CephFS Bug #4746: client: invalidate callback can deadlock
- The invalidate is queued in a separate thread, and when we call the invalidate, we don't have the client lock held. ...
- 05:06 PM CephFS Bug #4601: symlink with size zero
- >I looked a bit in the ceph-osd file holding the directory that contains the symlink, and I can see ^Q in the yes_hea...
- 04:57 PM CephFS Bug #1945 (Can't reproduce): blogbench hang on caps
- We haven't seen this in a long time (at least, that's marked here), and there's been a ton of work here over the last...
- 04:39 PM CephFS Bug #4732: uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
- This was in the async invalidate thread, so I'm turning this down. It should probably be investigated alongside/after...
- 04:34 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- Okay, pushed the update for more debugging, and am downgrading this to "High" since it only appears under so many fai...
- 04:17 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- Also, both of these are the same job as the first incident was: fsstress workunit on ceph-fuse, messenger failure inj...
- 04:15 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- Those machines are cleared out again, of course (d'oh!). Next time we see this we need to gather up everything we can...
- 04:03 PM CephFS Bug #4741: MDS: stuck in clientreplay
- Interesting; on #4742 it was clearly waiting on a request because it kept saying "still have 1 active replay requests...
- 03:57 PM CephFS Bug #4741 (Duplicate): MDS: stuck in clientreplay
- This is a duplicate of #4742. It looks like setattr is the culprit. I was able to generate a core file of the mds w...
- 11:13 AM CephFS Bug #4741: MDS: stuck in clientreplay
- Also /a/teuthology-2013-04-18_01:01:07-fs-next-testing-basic/15101
- 03:58 PM CephFS Bug #4721 (Need More Info): libcephfs tests fail when using ceph-deploy
- (Trying to track the responsibility flow more clearly.)
- 03:19 PM CephFS Bug #4721: libcephfs tests fail when using ceph-deploy
- Have you reproduced this, Tamil? Since all the tests are failing I'm pretty sure this is some kind of authentication ...
- 03:57 PM CephFS Bug #4742 (In Progress): mds: stuck clientreplay request
- 03:57 PM CephFS Bug #4742: mds: stuck clientreplay request
- Marked #4741 as a duplicate of this bug. It looks like setattr is the culprit. I was able to generate a core file o...
- 03:47 PM Revision fd678eab (ceph): debian/control: Fix typo in libboost version number
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 03:45 PM Revision 4b34b0e5 (ceph): mon: PaxosService: fix trim criteria so to avoid constantly trimming
- Say a service establishes it will only keep 500 versions once a given
condition X is true. Now say that said conditi... - 03:30 PM Revision 69974a4d (ceph): Merge branch 'wip-4725' Add build dependencies (Bug 4725)
- 03:24 PM Revision 86c1ea11 (ceph): build: Add new package dependencies
- Add libboost-system-dev (bug #4725).
Add hdparm to rpm installation requirements. The hdparm
command is used to det... - 02:59 PM devops Bug #4752: ceph-create-keys doesn't work on upgraded clusters
- Ah. Well that seems easy enough.
- 02:31 PM devops Bug #4752: ceph-create-keys doesn't work on upgraded clusters
- oops, i dropped this ball.
ceph command was update dto return the error code, so it just need sto check if $! is E... - 02:28 PM devops Bug #4752 (Resolved): ceph-create-keys doesn't work on upgraded clusters
- ceph-create-keys requires the "mon." key to have permission to do things to the monitors. Apparently older deployment...
- 02:30 PM Bug #4747: Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has not been con...
- I believe this is about the pre-Bobtail change which started adding global ordering values to the monitor data store;...
- 11:17 AM Bug #4747 (Resolved): Upgrade monitors from argonaut->bobtail->next fails w/"Existing store has n...
- Testing upgrade from Argonaut to Bobtail to Next (cuttlefish). I am using Argonaut and bobtail distros on gitbuilder...
- 02:17 PM Bug #4743 (Can't reproduce): omap deep scrub finds multiple PGs as inconsistent
- I think this was actually caused by one of the journal replay defects from <56.4. I'm marking it can't reproduce unt...
- 01:32 PM Bug #4743: omap deep scrub finds multiple PGs as inconsistent
- the xattrs, however, seem to match
- 01:32 PM Bug #4743: omap deep scrub finds multiple PGs as inconsistent
- osd.133 is missing 3 keys (out of 750k) on object 3.2f2_head/d340c2f2/.dir.10267.612/head//3
- 12:54 PM Bug #4743: omap deep scrub finds multiple PGs as inconsistent
- I got debug filestore = 20 debug osd = 30 debug ms = 1 (turns out it needs 30, not 20) logs from all three replicas o...
- 01:57 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
- I did a checkout of v3.5, and caps.c:1006 is...
- 01:37 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
- I don't believe locking is implemented yet via the Samba VFS bindings, since we don't have a userspace implementation...
- 01:27 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
- On top only:
vfs objects = scannedonly ceph
And if i switching to:
vfs objects = scannedonly
or:
vfs objects = c... - 12:42 PM rbd Documentation #4751 (Closed): Document Live Migration with RBD
- For people migrating to Ceph, some information on migration would be helpful.
Wido "You can do Live Migration with... - 12:36 PM Documentation #4750 (Closed): Improve Unfound Object Documentation
- Monitoring OSDs and PGs doesn't cover unfound objects. Add some description there and link to troubleshooting.
- 12:28 PM Bug #3440: Running OSDs on ZFS on Linux
- Tried with the patch and it works for me. Some comments are on Github: https://github.com/zfsonlinux/zfs/pull/1409
... - 11:26 AM Bug #4749 (Duplicate): osd: failed to recover before timeout
- job was...
- 11:25 AM Bug #4748 (Resolved): mon: failed assert in OSDMonitor::build_incremental
- ...
- 11:03 AM CephFS Bug #3637 (Resolved): client: not issuing caps for with clients doing shared writes
- Merged into next in commit:efbe2e8b55ba735673a3fdb925a6304915f333d8
- 09:41 AM Bug #4543: mon: corrupted store if monitor dies mid-sync
- Updated the original description with further details.
- 08:58 AM Revision 5a5fdfc6 (ceph): mon: Paxos: increase debug levels for proposal listing
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:34 AM devops Bug #4725 (Resolved): ceph package build-depends are incomplete for Ubuntu 12.04 at least
- Resolved with the following commit:
commit 86c1ea1156b25e1a7038132a2319cbf6a47c92da
Author: Gary Lowell <glowell@... - 01:34 AM Revision a0e457ae (ceph): doc: Removed legacy man page index. Generates warning otherwise.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:34 AM Revision d67793c2 (ceph): doc: Clarified that admin-socket is accessed from same host.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:33 AM Revision da7bf677 (ceph): doc: Updated hyperlinks to new tshooting section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:32 AM Revision fb4cba4b (ceph): doc: Removed this doc. Nothing referenced it, and parent directory echo...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:32 AM Revision f7843174 (ceph): doc: Revised top-level ops page.
- Consolidated authentication into high-level operations. Added a
troubleshooting section. Collapsed toc trees to make ... - 01:30 AM Revision 6cf36827 (ceph): doc: Removed link to nowhere. Otherwise generates a warning.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:29 AM Revision 064ec2fb (ceph): doc: Removed top-level tshoot page, and created new index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:29 AM Bug #3495: ceph-mon crash
- Thanks for the update!
- 01:28 AM Revision 0d1e0472 (ceph): doc: Excised community from OSD tshoot, made it stand alone.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:28 AM Revision 23e3fbee (ceph): doc: Moved monitor troubleshooting to troubleshooting section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:27 AM Revision 594580c9 (ceph): doc: Moved troubleshooting OSD to troubleshooting section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:26 AM Revision 78758007 (ceph): doc: Added extraneous rgw settings to rgw conf.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:25 AM Revision 4e6709bf (ceph): doc: Moved memory profiling from operations to troubleshooting.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:25 AM Revision 9e9bd2d8 (ceph): doc: Moved CPU profiling from operations to troubleshooting.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:24 AM Revision f0e3548a (ceph): doc: Set toc depth to 1 level, and added troubleshooting so it appears ...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:23 AM Revision dd7fd2dd (ceph): doc: Moved journal discussion to OSD ref from Ceph config.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:22 AM Revision 9ddc8b90 (ceph): doc: Reordered deployment tools in toc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:21 AM Revision fd8b4d0a (ceph): doc: Removed logging from config index. Set depth to 1 for clean appear...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:20 AM Revision cd4b242d (ceph): doc: Removed logging. Added references. Reorganized and edited.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:19 AM Revision 22a5cb66 (ceph): doc: Removed. Not in toc, and otherwise generates a warning.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:18 AM Revision 84b0ec28 (ceph): doc: Updated hyperlink.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:18 AM Revision 808ad25a (ceph): doc: Removed fragmented logging info. Consolidated into one doc.
- Logging was variously described in the ceph configuration document,
a configuration reference, and a section in opera...
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 (Fix Under Review): 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>
Also available in: Atom