Activity
From 03/10/2014 to 04/08/2014
04/08/2014
- 11:51 PM Bug #8047 (Closed): 0.79: new OSD crashed within minutes
- On 0.79 I added new OSD (on btrfs). Shortly after re-balancing begin newly added OSD crashed:...
- 10:12 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-04-08_14:01:14-rados:thrash-wip-7891-testing-basic-plana/178972
- 08:49 PM Bug #8028 (Fix Under Review): /lib/lsb/init-functions does not exist in latest firefly rc
- 08:49 PM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- The gitbuilders like this fine.. Alfredo, do you want to do a final test with ceph-deploy to make sure yum install fi...
- 05:57 PM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- 05:56 PM Bug #8028 (Fix Under Review): /lib/lsb/init-functions does not exist in latest firefly rc
- 05:03 PM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- This is because of missing depends on "lsb-base". I reckon it (or similar package) should be available on RHEL/CentOS...
- 12:38 PM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- but those do not export the same functions... what is it that we needed from init-functions that we had to add that l...
- 09:34 AM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- the offending commit by the way is commit:012bb5fb5bbc76e5a2c5037dc0c6558f0b1b0a45
- 09:34 AM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- ...
- 08:16 AM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- Ok so this looks like this gets installed with the redhat-lsb package that has this file in it:...
- 07:04 AM Bug #8028: /lib/lsb/init-functions does not exist in latest firefly rc
- Commenting out that one line allows me to start the monitors but I understand this has side-effects that are not enti...
- 06:07 AM Bug #8028 (Resolved): /lib/lsb/init-functions does not exist in latest firefly rc
- ...
- 08:25 PM CephFS Bug #8004: LibCephFS.HardlinkNoOriginal hang
- 06:49 PM rbd Bug #5469 (Fix Under Review): qemu-io: segfault when tried IO with invalid arguments
- https://github.com/ceph/ceph/pull/1632
- 06:36 PM Bug #8046: osd/ReplicatedPG.h: 666: FAILED assert(got) in get_rw_locks()
- 06:31 PM Bug #8046: osd/ReplicatedPG.h: 666: FAILED assert(got) in get_rw_locks()
- The wr locks are held on both head and snapset due to a previous op (delete) that is committed but not yet applied.
- 05:35 PM Bug #8046 (Resolved): osd/ReplicatedPG.h: 666: FAILED assert(got) in get_rw_locks()
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-08_02:30:14-rados-firefly-distro-basic-plana/178780...
- 05:40 PM Bug #8045: osd: deadlock from osdmap feature update
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-08_02:30:14-rados-firefly-distro-basic-plana/178740
- 05:30 PM Bug #8045 (Fix Under Review): osd: deadlock from osdmap feature update
- 05:18 PM Bug #8045 (Resolved): osd: deadlock from osdmap feature update
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-08_02:30:14-rados-firefly-distro-basic-plana/178670...
- 05:01 PM Bug #8044 (Duplicate): osd/ReplicatedPG.cc: 2276: FAILED assert(p != snapset.clones.end())
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-08_02:30:14-rados-firefly-distro-basic-plana/178733...
- 04:11 PM Bug #8043 (Resolved): until we fix it more better, we should disallow split on cache pools
- 03:52 PM Bug #8042 (Resolved): mon: crash decoding incremental osdmap on split firefly/dumpling
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-07_22:35:16-upgrade:dumpling-x:stress-split-firefl...
- 03:24 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Kevin Greenan proposes to expose a static function to reduce the amount of code required from the plugin : https://bi...
- 10:14 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- 10:02 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- the above config.yaml ran 6 times without failing
- 05:47 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- running tests against the proposed change, using the previous config.yaml. Not really hoping that it will failing. Ju...
- 04:30 AM Bug #7914 (Fix Under Review): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer ...
- 03:04 PM Feature #8041 (Resolved): ceph uses GCC-specific strerror_r; easy to make more portable
- GCC's strerror_r returns the string; the POSIX version returns success (the string is returned in the supplied buffer...
- 02:49 PM devops Bug #5835 (Resolved): Change text in package builds
- 02:19 PM devops Bug #5835 (Fix Under Review): Change text in package builds
- 02:46 PM devops Bug #6779 (Resolved): fix typo on the modfastcgi repo for fedora18
- Simple typo fix fixed in ceph-qa-chef commit 1e8ba35
- 02:36 PM devops Feature #8039 (Closed): move to libgoogle-perftools4
- From James on ceph-maintainers:...
- 02:35 PM devops Bug #7552 (Fix Under Review): dregs of mkcephfs still live on
- 02:22 PM devops Feature #8037 (Closed): Test leveldb 1.12 (or newer) and package as necessary
- 02:22 PM devops Bug #7918 (Won't Fix): Mon hangs at start after upgrading to leveldb-1.12.0-3.fc18.x86_64 from th...
- we're not going to worry about fc18 at this point; let's focus on making sure the fc10 and centos/rhel stuff works.
- 02:13 PM Feature #6258 (New): ceph-disk: zap should wipefs
- 02:08 PM Bug #8036: levedb: throws std::bad_allow on 14.04
- ...
- 02:03 PM Bug #8036 (Can't reproduce): levedb: throws std::bad_allow on 14.04
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-07_22:35:16-upgrade:dumpling-x:stress-split-firefl...
- 02:04 PM Bug #7744: osd: assert(last_e.version.version < e.version.version)
- 01:56 PM Bug #3652 (Duplicate): split should not mess up stats
- 01:55 PM Bug #4253 (Can't reproduce): radosgw: segfault in lockdep register
- 01:54 PM Bug #5634: auth startup reports "ObjectNotFound" when keyring file is unreadable
- 01:54 PM Bug #6629 (Won't Fix): fd cache and external changes to recently-modified files don't behave nicely
- 01:53 PM Bug #6686 (Resolved): segfault in prioritized queue dequeue
- commit:44028983
- 01:52 PM Bug #6684 (Rejected): osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log....
- 01:51 PM Bug #6826 (Duplicate): Non-equal performance of 'freshly joined' OSDs
- 01:50 PM Bug #6826: Non-equal performance of 'freshly joined' OSDs
- Probably related to snap trimming on newly clean new osds.
- 01:50 PM Bug #6944: objecter: localized read for missing objects polls replicas instead of waiting for pri...
- Can you ensure this is fixed in your current objecter work?
- 01:49 PM Bug #6833 (Can't reproduce): `/etc/init.d/ceph status` occasionally exists silently
- 01:49 PM Bug #3569 (Can't reproduce): Monitor & OSD failures when an OSD clock is wrong
- 01:48 PM Bug #7044 (Can't reproduce): Segmentation fault rados suite on master
- 01:48 PM Bug #6797 (Won't Fix): ceph osd out does not migrate properly
- 01:47 PM Bug #7161 (Can't reproduce): rados api test LibRadosMisc.Exec failed on next branch
- 01:46 PM Bug #7335 (Won't Fix): librbd does not raise "Object Not Found", instead returning NUL bytes
- 01:45 PM Bug #7350 (Won't Fix): osd: scrub does not detect recently touched and then renamed backend files
- 01:43 PM Bug #7593 (Resolved): Disk saturation during PG folder splitting
- 01:41 PM Bug #7688 (Won't Fix): warn at fs/btrfs/extent-tree.c:5748 __btrfs_free_extent+0x9ce/0xa20
- 01:41 PM Bug #7520 (Resolved): Lock contention during scrubbing which could potentially hang the OSD for a...
- 01:41 PM Bug #7868 (Can't reproduce): "failed to recover before timeout expired" in powercycle-firefly---b...
- 01:39 PM Bug #7936 (Can't reproduce): "failed: rados" in upgrade:dumpling-x:parallel-firefly-distro-basic-...
- 01:37 PM Bug #7957 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-emperor-x:parallel-firefly-testi...
- 01:36 PM Bug #7968 (Won't Fix): ImportError occurred when run command 'ceph -v'
- in order ot get the python stuff installed properly you should use a package. or install teh stuff in ceph.git/src/p...
- 01:34 PM rgw Bug #8016 (Resolved): "testPrefixAndLimit (test.functional.tests.TestContainerUTF8) ... ERROR" in...
- 09:44 AM rgw Bug #8016: "testPrefixAndLimit (test.functional.tests.TestContainerUTF8) ... ERROR" in upgrade:du...
- I think the 120s time just isn't long enough. Let's make it 300s (here and in the other thrashing/upgrade test). git...
- 01:33 PM Bug #7218 (Resolved): Displaying wrong number of pools with ceph -s after removeing a pool
- 01:33 PM Bug #6689 (Resolved): osd: remove_redundant_pg_temp() can be slow on big clusters
- 01:32 PM Bug #7549 (Won't Fix): Mon deadlock
- This is most likely a bug in the older libgoogle-perftools* which is part of the Precise Ubuntu distribution. Either...
- 01:21 PM rgw Bug #7815 (Can't reproduce): Test failed in upgrade:dumpling-x:parallel-firefly-testing-basic-pla...
- 01:19 PM Bug #7068 (Can't reproduce): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset....
- 01:17 PM Bug #6756: journal full hang on startup
- 01:14 PM Bug #7398: osd: ERANGE from clone
- might be dup of #7916
- 01:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
- 01:13 PM Bug #7858 (Resolved): agent with snaps ceph_test_rados error
- 01:13 PM Bug #7916 (Need More Info): ceph_test_rados got ENOENT on ec pool + thrashing
- 01:08 PM Bug #7659 (Resolved): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
- 01:08 PM Bug #8019 (Pending Backport): os/JournalingObjectStore.cc: 121: FAILED assert(op > committed_seq)...
- 01:07 PM Bug #8019 (Resolved): os/JournalingObjectStore.cc: 121: FAILED assert(op > committed_seq) on wheezy
- 12:13 PM Bug #8019 (Fix Under Review): os/JournalingObjectStore.cc: 121: FAILED assert(op > committed_seq)...
- 01:06 PM Bug #7710 (In Progress): Multiple rados bench instance will overwrite the metadata object
- This went through some review and is waiting on a respin.
- 12:49 PM Bug #7891 (In Progress): osd: leaked pg refs on shutdown
- 12:35 PM RADOS Fix #8035 (New): OSD: must guarantee we are newer than Objecter reply send epochs
- Because OSDs are now normal clients of each other in some circumstances, we've broken our map synchronization guarant...
- 12:33 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- There was a problem with our repo generator script for release builds which was causing even the new releases to not ...
- 02:57 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- There should be as saucy/trusty was built for that release as I was involved with it today. I will find out what happ...
- 02:00 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- Sandon Van Ness wrote:
> Since this ticket was opened our release build has been changed to include saucy/trusty so ... - 01:32 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- There might be some confusion here. We have 'gitbuilders' that yes have been building them for some time that do nigh...
- 01:24 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- I understand but that's not the issue. They have always been built, but the problem is that they are not being publis...
- 12:50 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- All new releases are being built for trusty/saucy. It is not super high priority at the moment to rebuild all our old...
- 12:43 AM devops Bug #6726: Official packages do not appear to be available for Saucy
- Any progress on this bug Sandon?
- 12:26 PM Bug #8001 (Fix Under Review): hung recovery; pg 3.f disappeared
- 12:20 PM devops Bug #8034 (Resolved): ceph-deploy should run sudo yum clean all after installing ceph-release rpm
- Otherwise you will get an unexpected old version from a previous ceph-release install after someone attempts to do a ...
- 12:12 PM CephFS Bug #8026 (Resolved): shared pointer completely break multiple mds
- 07:04 AM CephFS Bug #8026: shared pointer completely break multiple mds
- 12:04 AM CephFS Bug #8026 (Resolved): shared pointer completely break multiple mds
- 12:06 PM Feature #7437: EC: add adapt unittest teuthology task and add to nightly
- 12:05 PM devops Bug #5338 (Resolved): need rpm packages built for libapache-mod-fastcgi
- This is complete. We have been doing these in jenkins for a while now.
- 11:52 AM devops Bug #5338: need rpm packages built for libapache-mod-fastcgi
- 12:04 PM rgw Feature #6678 (Resolved): rgw: reject writes to secondary zones
- Pushed to dumpling, commit:b29238729f87c73dfdcf16dddcf293577678dea2
- 11:56 AM devops Feature #7925: Feature: create new download.ceph.com site
- I believe after a discussion with neil/Ian it was decided this was going to be on the back-burner for a bit so unassi...
- 11:55 AM Bug #8031 (Fix Under Review): osd/ReplicatedPG.cc: 405: FAILED assert(needs_recovery)
- 09:37 AM Bug #8031: osd/ReplicatedPG.cc: 405: FAILED assert(needs_recovery)
- 08:28 AM Bug #8031 (Resolved): osd/ReplicatedPG.cc: 405: FAILED assert(needs_recovery)
- ubuntu@teuthology:/a/teuthology-2014-04-07_23:01:05-kcephfs-master-testing-basic-plana/178021...
- 11:53 AM Feature #7792: leveldb 1.12.0 for rhel
- After building 1.12 we later decided to take the package down. Until I get updates what we are doing about this it is...
- 11:50 AM devops Feature #6098: put teuthology.front.sepia.ceph.com apache configuration files under source control
- 10:47 AM Feature #8033 (New): Epic: Kerberos/LDAP Support
- Users with existing LDAP or AD systems would like to integrate them into the cephx system so authentication and autho...
- 10:34 AM Bug #5818: leveldb 1.12: hang on shutdown (mon)
- observed this again on leveldb 1.12:...
- 10:32 AM Bug #8007: osd: hang on shutdown with valgrind on trusty
- nevermind, the second instance is a mon shutdown and it is a leveldb 1.12 compaction vs shutdown race.
- 10:20 AM Bug #8007: osd: hang on shutdown with valgrind on trusty
- saw this on precise:
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-07_23:00:18-rgw-master-test... - 10:09 AM Bug #6789: cannot remove the leader when there only are two monitors
- Cool :-)
- 09:34 AM Bug #6789 (Fix Under Review): cannot remove the leader when there only are two monitors
- 09:32 AM Bug #6789: cannot remove the leader when there only are two monitors
- https://github.com/ceph/ceph/pull/1624
- 09:28 AM Bug #6789: cannot remove the leader when there only are two monitors
- Also, it's relevant to mention that this does not happen only with the leader. Any monitor that is removed from the ...
- 09:23 AM Bug #6789 (In Progress): cannot remove the leader when there only are two monitors
- I was wrong. This does happen on current, and emperor, and dumpling.
The monitor has this features that allows hi... - 09:49 AM Bug #8022 (Duplicate): coredumps found in librbd tests
- 09:49 AM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- ubuntu@teuthology:/a/teuthology-2014-04-06_01:10:23-ceph-deploy-firefly-distro-basic-vps/173432
- 09:40 AM Bug #8021: osd: ENOENT on clone on dumpling
- i think this has been fixed on firefly but not dumpling....
- 09:27 AM Linux kernel client Bug #7954: misdirected op
- teuthology-2014-04-05_23:05:02-krbd-firefly-testing-basic-plana/173341
ubuntu-2014-04-05_23:18:18-kcephfs-master-tes... - 09:18 AM rbd Bug #8030 (Duplicate): krbd,kcephfs: misdirected request
- 09:17 AM rbd Bug #8030: krbd,kcephfs: misdirected request
- To be explicit: the error is -ENXIO, returned by the OSD when the write was not sent to the correct primary (and the ...
- 08:19 AM rbd Bug #8030 (Duplicate): krbd,kcephfs: misdirected request
- ubuntu@teuthology:/a/teuthology-2014-04-07_23:00:55-krbd-master-testing-basic-plana/178000...
- 09:10 AM rgw Bug #7799: Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- Yuri - have we seen this in a while? We believe it's fixed, but want to confirm.
- 09:06 AM devops Feature #7171 (Resolved): rbdmap should be part of ceph-common
- commit:17732dc0c8878ea58813ad543c5359cb811079cc
- 09:04 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- 07:55 AM devops Bug #8027 (Can't reproduce): Ceph v0.79 Firefly RC :: erasure-code-profile command set not presen...
- 07:53 AM devops Bug #8027: Ceph v0.79 Firefly RC :: erasure-code-profile command set not present for CentOS RPM
- This looks like a problem with an unclean upgrade of sorts because I cannot replicate this problem at all.
Package... - 03:07 AM devops Bug #8027 (Can't reproduce): Ceph v0.79 Firefly RC :: erasure-code-profile command set not presen...
- I have been using 0.78 in order to test EC and TP , with 0.78 i was not able to test erasure code profile feature ( ...
- 07:52 AM Bug #7991: ceph-mon crash
- There is no evidence of a crash on the logs.
One of the monitors appears to be working fine.
The other monitor ... - 06:59 AM CephFS Bug #3424: java: Add the correct JUnit package dependencies on supported platforms and ensure the...
- 06:51 AM CephFS Bug #8025: nfs-on-kclient: rm -r failed
04/07/2014
- 10:21 PM Linux kernel client Bug #8024: kclient: misdirected osd request
- Maybe caused by:...
- 09:55 PM Linux kernel client Bug #8024 (Resolved): kclient: misdirected osd request
- teuthology:/a/teuthology-2014-04-06_23:01:04-kcephfs-master-testing-basic-plana/175847...
- 10:08 PM CephFS Bug #8025 (Resolved): nfs-on-kclient: rm -r failed
- teuthology-2014-04-06_23:01:11-knfs-master-testing-basic-plana/175859/...
- 09:26 PM CephFS Bug #7958 (Resolved): ceph-fuse+fsx umount hang on leaked inode reference
- 09:20 PM Bug #7666 (Duplicate): librados: lock cycle on shutdown
- 09:20 PM Bug #7376 (Resolved): mon: >10s spent in remove_redundant_pg_temp
- 208959a0dcacba40116730702021090a24865eb3
- 09:17 PM CephFS Feature #7319 (Resolved): qa: multimds, no failure
- 09:17 PM Feature #5437 (Resolved): ceph-mon performance on ARM
- 09:17 PM Feature #2088 (Rejected): msgr: refactor 2 threads to one
- 09:13 PM CephFS Bug #7739 (Resolved): mds: uninitialized field in message
- 08:55 PM Bug #7997 (Resolved): handle_get_version returns old map epochs
- 08:14 AM Bug #7997 (Pending Backport): handle_get_version returns old map epochs
- 08:53 PM rgw Bug #6889 (Resolved): rgw: usage log: don't log system user operations
- 08:53 PM rgw Bug #7099 (Resolved): Strange Comportments with media files
- 08:49 PM Bug #7994 (Resolved): OSD: share map when sending subops to peers
- 11:02 AM Bug #7994 (Pending Backport): OSD: share map when sending subops to peers
- 10:58 AM Bug #7994: OSD: share map when sending subops to peers
- The simple fix was merged into master in commit:1a9952c60570aa308410c69db0289160f44969b1.
- 10:57 AM Bug #7994 (Resolved): OSD: share map when sending subops to peers
- 08:49 PM Bug #7736 (Resolved): mon: can expose stale state
- 08:49 PM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- 08:49 PM Bug #6992 (Resolved): OSD assert fails after it found it was marked as down by monitor during hig...
- 08:49 PM Bug #6909 (Resolved): Incomplete state should retry on Notify
- 06:03 PM Bug #8022 (Duplicate): coredumps found in librbd tests
- Coredump link http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-06_01:10:23-ceph-deploy-firefly-distro-basic-vps...
- 04:43 PM Bug #7996: 0.78: OSD is not suspend-friendly (unresponsive cluster on OSD crash)
- Sage Weil wrote:
> I suspect that the mon on that machine is the key factor at play here. There was a fix that went... - 09:43 AM Bug #7996: 0.78: OSD is not suspend-friendly (unresponsive cluster on OSD crash)
- I suspect that the mon on that machine is the key factor at play here. There was a fix that went in just after 0.78 ...
- 04:42 PM devops Bug #8017: Redhat Dependencies Unmet
- From John's log it looks like the dumpling ceph-release rpm (http://ceph.com/rpm-dumpling/el6/noarch/ceph-release-1-0...
- 04:39 PM devops Bug #8017: Redhat Dependencies Unmet
- RH packages are dependent upon EPEL. Need to build all missing packages and include in repo.
- 02:57 PM devops Bug #8017 (Duplicate): Redhat Dependencies Unmet
- 02:42 PM devops Bug #8017: Redhat Dependencies Unmet
- This has been verified as a problem when installing dumpling too.
john@admin-host:~/rgw-validation-cluster$ ceph-... - 02:06 PM devops Bug #8017 (Resolved): Redhat Dependencies Unmet
- When attempting to install Ceph Cuttlefish on a bare metal installation of Redhat 6.5, I encountered a series of unme...
- 04:31 PM Bug #8009 (New): librados failing tests for APILock
- I'm totally confused. The test in question *only* runs if osd_max_attr_size != 0, which it is not (defaults to 0, no...
- 10:53 AM Bug #8009 (In Progress): librados failing tests for APILock
- 07:15 AM Bug #8009 (Closed): librados failing tests for APILock
- A few failures on ceph-deploy nightly tests:...
- 04:18 PM CephFS Bug #8005 (Rejected): fuse hang
- no error in client log, looks like mds was killed by someone
- 04:08 PM Bug #8003 (Resolved): head eviction can race with clone promotion
- 03:59 PM Bug #7999: osd: pgs share info that hasn't been persisted
- 01:20 PM Bug #7999: osd: pgs share info that hasn't been persisted
- osd.0 starts a repop:...
- 03:58 PM Bug #7975 (Resolved): osd: handle inconsistent stats in the osd post split
- 03:56 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- "work in progress":https://github.com/ceph/ceph/pull/1621
- 01:16 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Kevin Greenan writes:
> Using the doc and a few special functions in jerasure, you can ensure that the underlying ... - 11:52 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- "gfp_array is a global variable":https://bitbucket.org/jimplank/jerasure/src/80fc5d1d95f06ea4732717b06b42177099cc93c9...
- 11:33 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Interesting : it is in *decode* this time, not *encode*
- 10:54 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 12:38 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Ran 27 times without triggering the problem. Will keep running it 100 times more.
- 03:41 PM Bug #8021 (Duplicate): osd: ENOENT on clone on dumpling
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-06_22:35:23-upgrade:dumpling-x:stress-split-firefl...
- 03:30 PM Bug #8020 (Resolved): evenly split stats on split
- At least it's better than what we currently do.
- 03:30 PM Bug #7967 (Resolved): finish_promote needs to handle the omap flag
- 03:03 PM Bug #8019 (Resolved): os/JournalingObjectStore.cc: 121: FAILED assert(op > committed_seq) on wheezy
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-06_22:35:23-upgrade:dumpling-x:stress-split-firefl...
- 02:22 PM Documentation #7886: What's the policy on URL stability for public documentation?
- We could certainly have a "latest-release" link on the website and legislate that to be our 'stable' doc link...
- 02:15 PM Documentation #7886: What's the policy on URL stability for public documentation?
- Getting off master and using the last named release branch name as the default docs root makes total sense. Does sphi...
- 02:01 PM Documentation #7886: What's the policy on URL stability for public documentation?
- The Ceph.com site uses the master branch by default, which changes somewhat frequently. A more stable approach would ...
- 02:22 PM RADOS Fix #8018 (New): OSD: check if messages are actually handled in ms_dispatch
- OSD::ms_dispatch returns "true" no matter what happens. The _dispatch() function which does the real work doesn't eve...
- 02:17 PM Bug #7937 (Resolved): [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 02:16 PM Bug #7985 (Rejected): 2014-04-02T20:36:41.677 INFO:teuthology.task.rados.rados.0.err:[10.214.131....
- 02:02 PM rgw Bug #8016 (Resolved): "testPrefixAndLimit (test.functional.tests.TestContainerUTF8) ... ERROR" in...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-06_22:35:23-upgrade:dumpling-x:stress-split-firefl...
- 02:02 PM Bug #7904 (Resolved): osd/ReplicatedPG.cc: 10661: FAILED assert(is_active())
- 02:01 PM Bug #7964 (Resolved): ceph_test_rados with snaps and caching stat errors
- 12:57 PM CephFS Bug #8010: It's impossible to remove unused filesystem pools from a cluster
- It's happening with
ceph version 0.78 (f6c746c314d7b87b8419b6e584c94bfe4511dbd4)
Linux access.car.dot.com 3.13.0-... - 10:07 AM CephFS Bug #8010 (Resolved): It's impossible to remove unused filesystem pools from a cluster
- We've inadvertently made it impossible to remove a filesystem from a Ceph cluster. If there is not data in the FS, it...
- 10:38 AM Bug #8011 (Resolved): osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= s...
- osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
ceph version 0.78-600-g19... - 08:37 AM Bug #7706 (Resolved): osd: PrioritizedQueue can starve
- 08:36 AM Bug #7977 (Resolved): cephx has embedded byte-order dependency
- 06:26 AM Bug #8008 (Resolved): osd/ReplicatedPG.cc: 258: FAILED assert(missing_loc.needs_recovery(hoid)) d...
- Here is the log from crashed OSD:...
04/06/2014
- 09:22 PM CephFS Bug #8005: fuse hang
- still looks like MDS was dead
- 01:44 PM CephFS Bug #8005 (Rejected): fuse hang
- ...
- 05:54 PM Bug #8007: osd: hang on shutdown with valgrind on trusty
- ...
- 05:52 PM Bug #8007 (Can't reproduce): osd: hang on shutdown with valgrind on trusty
- have seen several runs hang on osd shutdown. trusty. valgrind. here is the gdb thread dump:...
- 05:40 PM CephFS Bug #8006 (Rejected): fuse hang on flush (icache branch)
- The flush hang is because ceph-fuse was umounting (received signal). umounting can't finish becase MDS was dead at th...
- 01:49 PM CephFS Bug #8006 (Rejected): fuse hang on flush (icache branch)
- ...
- 05:29 PM CephFS Bug #8004: LibCephFS.HardlinkNoOriginal hang
- oh, and the 32-bit pointer thing is because ceph-fuse is running under valgrind.
- 05:27 PM CephFS Bug #8004: LibCephFS.HardlinkNoOriginal hang
- seems easy to reproduce, just hit this again with...
- 01:41 PM CephFS Bug #8004 (Resolved): LibCephFS.HardlinkNoOriginal hang
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-04-05_15:44:13-multimds:verify-wip-ms-dump-testing-basic-pla...
- 04:32 PM Bug #8002 (Resolved): osds down, but not advancing osdmaps
- 04:03 PM Bug #8002 (Fix Under Review): osds down, but not advancing osdmaps
- 03:53 PM Bug #8002: osds down, but not advancing osdmaps
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-06_02:30:05-rados-master-testing-basic-plana/173853
- 04:05 PM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana
- 04:05 PM Bug #7998 (Duplicate): 3.2s1 scrub stat mismatch, got 2000/2001 objects, 0/0 clones, 2000/2001 di...
- #7986
- 01:39 PM Bug #8003 (Resolved): head eviction can race with clone promotion
- _verify_no_head_clones will check copy_ops.
- 01:22 PM CephFS Bug #7739: mds: uninitialized field in message
- 06:39 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Josh, I am now running wip-6480-0.67.7 across our whole infrastructure. No issues yet. Because the race is rare, I th...
- 03:03 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- The workload is slightly different from the previous one:...
- 02:58 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- The teuthology config.yaml...
- 02:39 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- The plana08 machine has been recycled and there is no core archived. See the attachment:ceph-osd.0.log.gz for the ful...
- 02:36 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- SSE4 plugin selected and ECX = *029ee3ff* (this is consistent)...
- 02:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- /var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170763/remote/ubuntu@plana0...
04/05/2014
- 09:07 PM Bug #8002 (Resolved): osds down, but not advancing osdmaps
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170941
... - 08:58 PM Bug #8001 (Resolved): hung recovery; pg 3.f disappeared
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170892
... - 08:48 PM Bug #7891: osd: leaked pg refs on shutdown
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/171097
- 08:33 PM rbd Bug #8000 (Closed): SLAB: Unable to allocate memory on node 0
- I'm getting the following kernel errors with ext4 on rbd:...
- 05:09 PM Bug #7999: osd: pgs share info that hasn't been persisted
- ...
- 05:09 PM Bug #7999 (Resolved): osd: pgs share info that hasn't been persisted
- ubuntu@teuthology:/a/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170880
- 04:59 PM Bug #7997 (Fix Under Review): handle_get_version returns old map epochs
- 04:45 PM Bug #7997 (In Progress): handle_get_version returns old map epochs
- 03:44 PM Bug #7997 (Resolved): handle_get_version returns old map epochs
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170649<pr...
- 03:55 PM Bug #7998 (Duplicate): 3.2s1 scrub stat mismatch, got 2000/2001 objects, 0/0 clones, 2000/2001 di...
- ...
- 03:45 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ubuntu@teuthology:/var/lib/teuthworker/archive/gregf-2014-04-04_22:05:49-rados-wip-7994-testing-basic-plana/170763
04/04/2014
- 08:43 PM Bug #7996 (Won't Fix): 0.78: OSD is not suspend-friendly (unresponsive cluster on OSD crash)
- One machine running MON and OSD got suspended.
Shortly after (within seconds) the whole cluster got unresponsive for... - 07:54 PM Bug #7975 (Fix Under Review): osd: handle inconsistent stats in the osd post split
- 02:08 PM Bug #7975 (In Progress): osd: handle inconsistent stats in the osd post split
- 07:28 PM CephFS Bug #7980: 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- Works as expected, problem solved, thank you.
- 12:18 AM CephFS Bug #7980: 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- Very nice, thank you. I'll test and confirm.
- 12:01 AM CephFS Bug #7980 (Resolved): 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- fixed by https://github.com/ceph/ceph/commit/fb72330fb3514be690dc60598242036aa560e023
- 06:07 PM Bug #7993 (Resolved): ceph-post-file can only accept one option
- 03:26 PM Bug #7993 (Fix Under Review): ceph-post-file can only accept one option
- 03:21 PM Bug #7993 (In Progress): ceph-post-file can only accept one option
- 03:02 PM Bug #7993 (Resolved): ceph-post-file can only accept one option
- currently only looks once at options, uses $1 where it means $2, etc. It needs it some getopts love.
- 05:10 PM Bug #7995 (Can't reproduce): osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs...
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-04_02:30:19-rados-master-testing-basic-plana/168602...
- 05:08 PM Bug #7891: osd: leaked pg refs on shutdown
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-04_02:30:19-rados-master-testing-basic-plana/168600
- 11:07 AM Bug #7891: osd: leaked pg refs on shutdown
- ubuntu@teuthology:/a/teuthology-2014-04-02_02:30:02-rados-master-testing-basic-plana/161303/remote$
- 04:30 PM Bug #7994: OSD: share map when sending subops to peers
- The quick-and-dirty fix is in wip-7994; I'll run it through the suite as soon as it builds. A (at least slightly) mor...
- 04:28 PM Bug #7994 (Resolved): OSD: share map when sending subops to peers
- Right now, the OSD doesn't preemptively share maps when sending subops. Fix it.
- 04:21 PM Bug #7984 (Duplicate): osd/ReplicatedPG.cc: 2273: FAILED assert(p != snapset.clones.end())
- 04:06 PM Bug #7984 (In Progress): osd/ReplicatedPG.cc: 2273: FAILED assert(p != snapset.clones.end())
- 10:29 AM Bug #7984: osd/ReplicatedPG.cc: 2273: FAILED assert(p != snapset.clones.end())
- ubuntu@teuthology:/a/teuthology-2014-04-02_02:30:02-rados-master-testing-basic-plana/161266/remote
- 10:29 AM Bug #7984 (Duplicate): osd/ReplicatedPG.cc: 2273: FAILED assert(p != snapset.clones.end())
ceph version 0.78-522-gedb8a59 (edb8a5965e72b6173d3f88d1a63c8b3ca1b9235c)
1: (ReplicatedPG::trim_object(hobject_...- 03:16 PM Bug #7983 (Resolved): osd: erroneously present object
- 02:07 PM Bug #7983 (Fix Under Review): osd: erroneously present object
- 01:13 PM Bug #7983 (In Progress): osd: erroneously present object
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-04_02:30:19-rados-master-testing-basic-plana/168472
- 08:31 AM Bug #7983 (Resolved): osd: erroneously present object
- ubuntu@teuthology:/a/teuthology-2014-04-03_02:30:03-rados-firefly-distro-basic-plana/166349
- 02:53 PM Bug #7992 (Resolved): ceph-post-file keys are wrong
- 02:37 PM Bug #7992 (Resolved): ceph-post-file keys are wrong
- Snippet of install script in Makefile.am installs the known_hosts file to all three
of known_hosts, id_dsa, and id_d... - 02:28 PM Bug #7991: ceph-mon crash
- Logs have been uploaded via cephdrop@ceph.com in issue7991 folder. Thanks.
Cluster details:
Ubuntu 12.04 - 3 x ... - 02:11 PM Bug #7991 (Rejected): ceph-mon crash
- I've had an issue with crashing ceph-mon. It happened twice over the course of last two weeks. Attached are the ceph-...
- 01:26 PM rgw Feature #7990 (New): RGW: Ldap Integration
- For users with existing LDAP systems, they would like to be able to configure RGW so that authentication and authoriz...
- 01:21 PM Feature #7988 (Resolved): Logs: Log every administrative action taken by a user
- Many enterprise users have strict security policies which require that all events generated by a user are explicitly ...
- 12:59 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- merged to master/firefly. backported to emperor too, along with a release note.
- 12:55 PM Fix #7919 (Resolved): mon: prevent clients with a read cap from reading the full keyring
- 11:59 AM Bug #7987 (Duplicate): osd: backfill/recovery makes no progress
- ubuntu@teuthology:/a/teuthology-2014-04-02_02:30:02-rados-master-testing-basic-plana/161007/remote$
At least, tha... - 11:04 AM Bug #6756: journal full hang on startup
- ubuntu@teuthology:/a/teuthology-2014-04-02_02:30:02-rados-master-testing-basic-plana/161291/remote
- 10:50 AM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- Base pool, issue with copy_from?
- 10:50 AM Bug #7986 (Can't reproduce): 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2...
- duration: 1915.8093299865723
failure_reason: '"2014-04-02 21:31:21.281062 osd.4 10.214.133.26:6812/11657 29 : [ERR]
... - 10:45 AM Bug #7985 (Rejected): 2014-04-02T20:36:41.677 INFO:teuthology.task.rados.rados.0.err:[10.214.131....
- ubuntu@teuthology:/a/teuthology-2014-04-02_02:30:02-rados-master-testing-basic-plana/160986/remote
2014-04-02T20:3... - 09:47 AM devops Bug #7981 (Resolved): chef fails to install libleveldb1
- This was fixed a few hours after that test ran on the 2nd.
- 06:17 AM devops Bug #7981 (Resolved): chef fails to install libleveldb1
- Not sure if this is because the package is just not there or because there was a network hiccup when the tests ran
... - 09:23 AM Bug #7576 (Fix Under Review): osd: large skew in pg epochs (dumpling)
- 09:21 AM Bug #7922 (Resolved): osd: multi-backfill reservation does not release on reject
- 08:58 AM Support #7609: http://tracker.ceph.com/account/register returns 500 Internal error
- someone ran into it again
- 08:30 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- This didn't trigger at all in yesterday's run. :/
- 08:15 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- To find the failed ones:...
- 08:29 AM Bug #7892: osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.length() == 0)...
- ubuntu@teuthology:/a/teuthology-2014-04-03_02:30:03-rados-firefly-distro-basic-plana
- 05:17 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- This may help somehow - recently I`ve started to collect perf samples via endless loop on selected hosts and some hos...
- 12:36 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Just in case, the fix you are running with is now in 3.14. However we
are still working on a better fix, so we'll k... - 12:18 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- I haven't got this problem anymore, it seems really stable for me now. Thanks !
I think the issue can be mark as r...
04/03/2014
- 11:47 PM CephFS Bug #7980 (Resolved): 0.78: MDS crash (segmentation fault) on client wake-up from suspend.
- MDS crashes (segmentation fault) when I wake-up machine with CephFS (mounted using kernel client) from suspend:
<p... - 10:54 PM Bug #7922 (Fix Under Review): osd: multi-backfill reservation does not release on reject
- 06:08 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- ...
- 03:29 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- i reproduced this on my first try with the patch in wip-7922....
- 06:30 PM Bug #7977 (Pending Backport): cephx has embedded byte-order dependency
- 01:56 PM Bug #7977 (Resolved): cephx has embedded byte-order dependency
- Calculation of the original session key is byte-order-dependent; cephx_calc_client_server_challenge gets a message di...
- 05:49 PM Bug #7964: ceph_test_rados with snaps and caching stat errors
- 01:04 PM Bug #7964 (Rejected): ceph_test_rados with snaps and caching stat errors
- 05:43 PM rgw Bug #7978 (Resolved): rgw: infinite loop when iterating multipart object
- 03:17 PM rgw Bug #7978 (Fix Under Review): rgw: infinite loop when iterating multipart object
- 03:13 PM rgw Bug #7978 (Resolved): rgw: infinite loop when iterating multipart object
- This happens when the object created has a final placement rule with part_size > 0, e.g.,...
- 01:55 PM Bug #7976 (Duplicate): 4.8 missing primary copy of ..., unfound (dumpling)
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-04-02_22:35:24-upgrade:dumpling-x:stress-split-firefl...
- 01:38 PM rbd Bug #7973 (Resolved): rbd ls returns error code of 1 on empty pool
- This is the same as #6693. Backported the fix to the dumpling branch in commit:c66b61f9dcad217429e4876d27881d9fb2e7666f
- 11:55 AM rbd Bug #7973 (Resolved): rbd ls returns error code of 1 on empty pool
- Using version 0.67.7 rbd ls is returning an error code of 1 on an empty pool. This is causing OpenStack Havana proble...
- 01:28 PM Bug #7975 (Resolved): osd: handle inconsistent stats in the osd post split
- 01:01 PM Bug #7967: finish_promote needs to handle the omap flag
- 10:24 AM Fix #7919 (Fix Under Review): mon: prevent clients with a read cap from reading the full keyring
- pull request 1597 https://github.com/ceph/ceph/pull/1597
- 06:53 AM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- 05:32 AM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- I guess it's introduce by commit f1c7b4ef0 (client: pin Inode during readahead). Readahead raced with truncate. Objec...
- 12:43 AM Bug #7968 (Won't Fix): ImportError occurred when run command 'ceph -v'
- I. How to reproduce:
1. Clone the latest ceph master code from github
2. From my laptop, install the pre-require...
04/02/2014
- 10:00 PM CephFS Bug #7958: ceph-fuse+fsx umount hang on leaked inode reference
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_23:00:33-fs-firefly-distro-basic-plana/160589
- 10:23 AM CephFS Bug #7958 (Resolved): ceph-fuse+fsx umount hang on leaked inode reference
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-31_23:00:36-fs-master-testing-basic-plana/157636
... - 09:56 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- logs on flab:/more2/t/7922
on osd.9, we see:... - 03:21 PM Bug #7922 (In Progress): osd: multi-backfill reservation does not release on reject
- 01:19 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- All highly-verbose logfiles have been uploaded at Sage's request (4.3GiB): http://www.aarontc.com/logs/ceph-logs-chek...
- 08:07 PM Bug #7965 (Resolved): osd: SEGV in handle_recovery_read_complete
- 04:47 PM Bug #7965: osd: SEGV in handle_recovery_read_complete
- reliably reproduced with lockdep enabled with ceph_test_rados_api_tier. appears to be due to multiple initialization...
- 04:46 PM Bug #7965 (Fix Under Review): osd: SEGV in handle_recovery_read_complete
- 04:08 PM Bug #7965 (Resolved): osd: SEGV in handle_recovery_read_complete
- ...
- 07:34 PM Bug #4185: Python multiprocessing exhibiting odd behaviour with librados
- Some notes for the Next guy that comes across this issue:
You can use the multiprocessing managers to push all the... - 05:28 PM Bug #7967 (Resolved): finish_promote needs to handle the omap flag
- 05:22 PM Bug #7689 (Duplicate): librados: ENOENT on ioctx create
- 05:21 PM Bug #7689: librados: ENOENT on ioctx create
- oh, i think this is a dup of #7736
- 05:19 PM Bug #6429 (Can't reproduce): msg/Pipe.cc: 1029: FAILED assert(m)
- 05:17 PM Bug #7776 (Resolved): client lockdep crash
- 04:28 PM Bug #7776 (In Progress): client lockdep crash
- 03:33 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_02:30:19-rados-firefly-distro-basic-plana/158403...
- 03:32 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-04-01_02:30:19-rados-firefly-distro-basic-plana/158409...
- 04:13 PM Bug #7915 (Resolved): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 04:04 PM Bug #7915 (Fix Under Review): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- 11:55 AM Bug #7915 (Need More Info): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- we've added more debug to master/firefly
- 04:12 PM CephFS Bug #7966 (Resolved): ceph-mds respawn doesn't always work
- ...
- 03:55 PM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- @Yehuda: That code change looks good. I'll try to test by monday and get back to you with confirmation of it working.
- 07:31 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- I pushed some work into wip-7450. It takes care of the default access key generation in the case of subusers, and som...
- 03:54 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Compiled TestErasureCodeJerasure.cc with m=1 https://github.com/ceph/ceph/blob/master/src/test/erasure-code/TestErasu...
- 02:23 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 10:57 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- mira087 has the fisrst 2 failures, mira089 has the earlier one. they all see to crash in teh same place:...
- 10:19 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 09:38 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Ran test for both gf-complete and jerasure and they are valgrind clean ( https://bitbucket.org/jimplank/jerasure/pull...
- 09:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- /a/teuthology-2014-03-31_02:30:03-rados-master-testing-basic-plana/155875/teuthology.log is the only ec_pool test tha...
- 09:10 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- also happened on ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154379 on commi...
- 03:31 PM Bug #7964 (Resolved): ceph_test_rados with snaps and caching stat errors
- 03:21 PM Bug #6681 (Resolved): osd recovery hung
- backported to dumpling
- 01:52 PM Bug #6681 (Pending Backport): osd recovery hung
- /var/lib/teuthworker/archive/teuthology-2014-04-01_19:00:30-rados-dumpling-testing-basic-plana/159217
- 03:15 PM Bug #7576 (In Progress): osd: large skew in pg epochs (dumpling)
- wip-7576
- 03:07 PM Bug #7917 (Resolved): "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Just needed to cherry-pick the fix for #6368 to dumpling.
- 01:38 PM RADOS Feature #7962 (New): allow the user to query inconsistent object status and specify repair strategy
- 12:56 PM Messengers Bug #7888 (Resolved): msgr: keepalive is insufficient
- 10:56 AM devops Feature #7960 (Resolved): backport rpm creation of /usr/lib64/qemu/librbd.so.1 symlink to dumpling
- Backport #7293 to dumpling so it works seamlessly with rhev and rhel-osp as well.
- 10:51 AM Bug #7939 (Resolved): pg role wrong for replicated pools
- 10:42 AM Bug #7805 (Pending Backport): emperor can go active with < min_size non-incomplete peers since we...
- 08:50 AM Bug #7805 (Fix Under Review): emperor can go active with < min_size non-incomplete peers since we...
- 10:41 AM Bug #7907 (Resolved): osd: rollback to head didn't mark_unrollbackable
- 09:45 AM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- ...
- 09:36 AM Bug #7949 (Duplicate): "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefl...
- Dup of 7935
- 09:33 AM Bug #7951 (Duplicate): "test_rbd."* tests failed in upgrade:dumpling-x:parallel-firefly-distro-ba...
- 09:07 AM Bug #7957 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-emperor-x:parallel-firefly-testi...
- Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-04-02_01:54:27-upgrade:dumpling-emperor-x:parallel-firefly...
- 07:53 AM RADOS Feature #7956 (New): osd: implement posix_fadvise/POSIX_FADV_DONTNEED to prevent data caching
- Running Ceph OSDs on commodity hardware often means that servers are not used exclusively for OSDs and may have other...
- 07:24 AM Bug #7931 (Can't reproduce): setcrushmap crashing monitor
- 06:36 AM Bug #7931: setcrushmap crashing monitor
- Hi Greg,
I don't think that was the issue, however it has since been working. The crushmap I've uploaded was the r...
04/01/2014
- 09:46 PM Bug #7952: After aio_read() completes a call to return_value() doesn't return bytes read
- This might be the issue underlying #7822
- 06:02 PM Bug #7952 (Resolved): After aio_read() completes a call to return_value() doesn't return bytes read
When using the rados_aio_read() interface the c.bl bufferlist stores the read data. So the code below will set rva...- 09:38 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- Here's a partial log from osd.3 around the problematic time: http://www.aarontc.com/logs/ceph-osd.3.log.bz2
Please... - 09:22 PM Bug #7922 (Need More Info): osd: multi-backfill reservation does not release on reject
- it would help to see the log from the primary sending the dup backfill request. it is not entirely trivial to determ...
- 09:18 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- We got a duplicate backfill reservation request from osd.3:...
- 08:44 PM Linux kernel client Bug #7954 (Resolved): misdirected op
- Test Run: teuthology-2014-03-31_23:02:09-kcephfs-master-testing-basic-plana
======================================... - 06:59 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- I found another source of race conditions, and hopefully fixed them in the wip-6480-0.67.7 branch. I'm running tests ...
- 04:40 PM Bug #7941: caching needs to be able to enforce snap context on flush even with pool snaps
- 01:11 PM Bug #7941 (Resolved): caching needs to be able to enforce snap context on flush even with pool snaps
- 04:40 PM Bug #7942: promote uses cloneid, but backend may have a different cloneid
- 01:12 PM Bug #7942 (Resolved): promote uses cloneid, but backend may have a different cloneid
- 04:20 PM Bug #7949: "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefly-distro-bas...
- A pretty good chance that this is #7935.
- 03:28 PM Bug #7949 (Duplicate): "s3tests.functional.test_s3"* errors in upgrade:dumpling-x:parallel-firefl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 04:17 PM Bug #7950 (Duplicate): "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgra...
- Duplicate of #7935, failed due to a new test added.
- 03:46 PM Bug #7950: "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgrade:dumpling-...
- May be a duplicate of 7949
- 03:45 PM Bug #7950 (Duplicate): "FAIL: s3tests.functional.test_s3.test_multipart_upload_contents" in upgra...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 03:59 PM Bug #7805: emperor can go active with < min_size non-incomplete peers since we check acting size
- wip-7805-emperor
- 03:59 PM Bug #7938 (Resolved): Coredump generated by upgrade test
- this was a broken commit:b097a237e11b48c47d3fd5484f3449e683e95db0. reverted.
- 11:23 AM Bug #7938 (Resolved): Coredump generated by upgrade test
- The following yaml consistently generates coredumps....
- 03:55 PM Bug #7951 (Duplicate): "test_rbd."* tests failed in upgrade:dumpling-x:parallel-firefly-distro-ba...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 03:29 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- The only difference is that ext4 is used in teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491 an...
- 03:15 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Running 30 more, sequentially.
- 03:09 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Contrary to what I thought (reading the wrong number), plana have SSE3 indeed and the jerasure plugin including SSE4 ...
- 02:59 PM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ran through 20 iterations of the above yaml and did not reproduce.
- 09:35 AM Bug #7914 (In Progress): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer lengt...
- I will run the workload many times, hoping to reproduce the crash.
- 08:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Another run with success, complete logs in attachment:run2.txt
- 06:49 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- I don't see why not locking the erasure-code plugin registry could be a problem in practice but it is a problem in th...
- 06:26 AM Bug #7914 (Can't reproduce): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer l...
- The above teuthology workload ran on two plana machines and did not create a core dump.
- 06:05 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 05:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Trying to trigger the problem again with:...
- 05:16 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- /a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491...
- 03:29 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- both errors show with "thrashers/pggrow.yaml" (one with btrfs, the other with ext4)
- 02:34 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- the /a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491 radosbench completed successfully
<pre... - 02:18 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- Trying to reproduce the problem from the source tree on the current master with...
- 01:49 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- cpuinfo on plana17 (the machine on which the core dump occured) shows:...
- 01:43 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- *-msse3* was not used although it should have and this was fixed "march 30th":https://github.com/ceph/ceph/commit/1c9...
- 01:39 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- "latest jerasure / gf-complete":https://github.com/ceph/ceph/commit/1c92453f748aea48084e57c9c721ee8080caeeb6 submodul...
- 01:23 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ...
- 12:57 AM Bug #7914 (In Progress): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer lengt...
- 02:46 PM Bug #7937: [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 11:05 AM Bug #7937 (Fix Under Review): [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected c...
- 10:48 AM Bug #7937: [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 038e94b51e4945380c4ba771c88c953b6628d0f7 (wip-sam-testing)
- 10:46 AM Bug #7937 (Resolved): [ERR] deep-scrub 5.ds0 79d5820d/burnupi0838757-23/1f7//5 expected clone
- 2014-03-31 17:00:27,792.792 INFO:teuthology.task.internal:Removing archive directory...
2014-03-31 17:00:27,840.840 ... - 02:46 PM rgw Bug #7935 (Resolved): rgw: multipart upload failure with s3cmd
- commit:ed5a5e075544662a12d94e472da55aeb2f0efe5d
- 12:31 PM rgw Bug #7935: rgw: multipart upload failure with s3cmd
- This issue happens when not all parts are the same size. Extended the s3 functional test to check this.
- 10:55 AM rgw Bug #7935 (Fix Under Review): rgw: multipart upload failure with s3cmd
- 10:05 AM rgw Bug #7935 (Resolved): rgw: multipart upload failure with s3cmd
- From ceph-users mailing list:...
- 02:44 PM devops Feature #7171 (Fix Under Review): rbdmap should be part of ceph-common
- https://github.com/ceph/ceph/pull/1581
- 02:25 PM Bug #7907: osd: rollback to head didn't mark_unrollbackable
- the original modify:...
- 02:14 PM devops Feature #7947 (Duplicate): Create separate ceph and ceph-common packages for EL6 and EL7 builds
- No reason why rpm builds shouldn't be the same as for debs...
- 02:07 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- My guess is that this behavior kicked in when we started matching client caps with the expected caps on a per-command...
- 01:27 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- That sounds like the best solution to me. Somebody on the mailing list reported that Dumpling is not exposing user da...
- 01:25 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- My vote is to make 'auth' special and require * to access it (or an explcit grant of auth rw or something). This is ...
- 01:23 PM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- Here's the thing: obviously, allowing anyone with read permission to simply grab the whole keyring is not a good thin...
- 01:10 PM Fix #7919 (In Progress): mon: prevent clients with a read cap from reading the full keyring
- Okay, I was the one at fault here. Was missing to provide a keyring with the client's key thus getting permission de...
- 09:12 AM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- Hum, I didn't validate the issue so maybe it was user error. Should probably poke him on the mailing list to check. *...
- 05:26 AM Fix #7919: mon: prevent clients with a read cap from reading the full keyring
- doesn't seem to happen on latest emperor. checking if anything changed in between 0.72.2 and latest emperor, or if I...
- 01:26 PM Feature #7459 (Rejected): ceph-rest-api: sysvinit and upstart scripts
- 01:06 PM Feature #7459 (Fix Under Review): ceph-rest-api: sysvinit and upstart scripts
- 01:09 PM Feature #7940 (Resolved): add pool snaps to ceph_test_rados
- 01:00 PM Bug #7939: pg role wrong for replicated pools
- 12:16 PM Bug #7939 (Resolved): pg role wrong for replicated pools
- 10:30 AM Bug #7892 (New): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.length()...
- 10:23 AM Bug #7892 (Duplicate): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.le...
- probably dups #7916
- 10:29 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- We looked at this in standup today. There is a queue_null on every PG in OSD::consume_map(), so they should be gettin...
- 10:24 AM Bug #7588 (Can't reproduce): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_co...
- 10:23 AM Bug #7936 (Can't reproduce): "failed: rados" in upgrade:dumpling-x:parallel-firefly-distro-basic-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-31_19:33:26-upgrade:dumpling-x:parallel-firefly-di...
- 10:21 AM Bug #7916 (In Progress): ceph_test_rados got ENOENT on ec pool + thrashing
- 09:43 AM Bug #7934 (Resolved): ceph_test_rados_watch_notify doesn't clean-up all pools it creates
$ ./rados lspools
data
metadata
rbd
$ ./ceph_test_rados_watch_notify
...
$ ./rados lspools
data
metadata
r...- 09:41 AM Bug #7519 (Can't reproduce): upgrade: osd crash on cuttlefish -> v0.67.1 -> emperor
- 09:35 AM devops Bug #7918: Mon hangs at start after upgrading to leveldb-1.12.0-3.fc18.x86_64 from the ceph-extra...
- We've pulled those packages until we can figure what's causing this.
- 09:34 AM Bug #7926 (Resolved): "[ERR] scrub 45.0" in upgrade:dumpling-x:parallel-firefly-distro-basic-vps ...
- commit:e672c52b4f8b945a516f2eec006e33665a08f045
- 09:31 AM rbd Bug #6257 (Resolved): rbd: cp on sparse image allocates objects in dest
- 09:21 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- Also need to ensure that code is backported to Icehouse-based distro (Ubuntu, RDO, RHEL-OSP) products.
- 09:19 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- 09:15 AM rbd Feature #7921: Openstack: live migration for ephemeral volumes
- 09:21 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- Also need to ensure that code is backported to Icehouse-based distro (Ubuntu, RDO, RHEL-OSP) products.
- 09:18 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- 09:14 AM rbd Feature #7920: Openstack: cloning for rbd ephemeral disks
- 09:15 AM rbd Feature #7924: Openstack: make long-running operations async in cinder
- 09:15 AM rbd Feature #7923: Openstack: backup from in-use volume instead of from detached volume
- 09:14 AM Bug #7931: setcrushmap crashing monitor
- You should do this with "debug mon = 20" set, but it appears to be crashing because your crush map is somehow invalid...
- 08:08 AM Bug #7931 (Can't reproduce): setcrushmap crashing monitor
- Following the guides I've created a new crushmap. When I submit this new crushmap the monitor crashes with some infor...
- 09:14 AM rbd Feature #7895: krbd: test cloning, discard, plus regular I/O via fsx
- 09:14 AM Linux kernel client Feature #190: krbd: DISCARD support
- 09:10 AM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
- 09:05 AM rgw Feature #7932 (Resolved): Create design for object versioning, including subtasks and estimates
- 02:09 AM Feature #7928 (Rejected): erasure-code : no SSE3 specific code
- Is it worth compiling with *-msse3* and detecting it at runtime when no HAVE_SSE3 code is being compiled conditionall...
03/31/2014
- 09:44 PM devops Bug #7879 (Resolved): sentry-db is down
- Migration complete!
- 09:38 PM Bug #7927 (Duplicate): Removed pools still show up in "ceph pg dump" output
- Duplicate #7912
This should be fixed as of commit 70d2e1353ecb9d31a394fdac333dbb0de93339d3. - 09:32 PM Bug #7927 (Duplicate): Removed pools still show up in "ceph pg dump" output
Creating new pools 3 and 4 then removing them leaves them behind in ceph pg dump output. Minutes later it is still...- 04:16 PM rbd Bug #6257 (Fix Under Review): rbd: cp on sparse image allocates objects in dest
- Flatten ignores empty objects since commit:bfa106694dc4db97f58c623eafc3c2d0f9a8bff1, which is in dumpling and emperor...
- 03:55 PM Bug #7917: "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Looks like the same issue on
os_type: rhel
os_version: '6.5'
Los are in http://qa-proxy.ceph.com/teuthology/teuth... - 09:15 AM Bug #7917 (Resolved): "ERROR: test_rbd."* in upgrade:dumpling-x:parallel-firefly-distro-basic-vps
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 03:19 PM Bug #7926 (Resolved): "[ERR] scrub 45.0" in upgrade:dumpling-x:parallel-firefly-distro-basic-vps ...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 02:59 PM Bug #7912 (Resolved): Wrong pool count when using "ceph -s" and "ceph -w"
- 05:36 AM Bug #7912 (Resolved): Wrong pool count when using "ceph -s" and "ceph -w"
- Hi,
running ceph version 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
I created a bunch of pools and delet... - 02:58 PM devops Feature #7925 (Rejected): Feature: create new download.ceph.com site
- See https://docs.google.com/a/inktank.com/document/d/1K8pUEZpN5-t1wd0t81MXgooB1Xz_Cgi4jkvo25dysiU/edit
- 02:57 PM Messengers Bug #7888 (Pending Backport): msgr: keepalive is insufficient
- 02:21 PM Bug #7922: osd: multi-backfill reservation does not release on reject
- After the additional logging directives were added and osd.0 was restarted, it quickly crashed again. Here is the log...
- 01:55 PM Bug #7922 (Resolved): osd: multi-backfill reservation does not release on reject
- Several OSDs are crashing quite frequently with this error, at least on version 0.77 and 0.78 (possibly earlier as we...
- 02:15 PM rbd Bug #7577 (Resolved): rbd info displays extra random char in block prefix
- 02:03 PM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- Looking at the first failure:
- PGPool::cached_removed_snaps is empty
- info.purged_snaps = 1~1
hence the fail... - 09:10 AM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154663
- 09:07 AM Bug #7915: ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154509
- 09:06 AM Bug #7915 (Duplicate): ./include/interval_set.h: 385: FAILED assert(_size >= 0)
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154635...
- 01:56 PM rbd Feature #7924 (Closed): Openstack: make long-running operations async in cinder
- - deleting an image takes a long time, and blocks cinder-volume
from doing anything else during that time
... - 01:55 PM rbd Feature #7923 (Resolved): Openstack: backup from in-use volume instead of from detached volume
- Currently, you can take a backup of a detached volume and send to a Swift/RBD backend.
We want to be able to take ba... - 01:55 PM Bug #7804 (Duplicate): backfill racing with a hitset object remove
- 01:55 PM Bug #7893 (Duplicate): osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- 09:16 AM Bug #7893: osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154529
- 01:55 PM Bug #7894 (Duplicate): osd: missing hitset object in cluster log
- 01:51 PM rbd Feature #7921 (Resolved): Openstack: live migration for ephemeral volumes
- - live migration for rbd ephemeral disks
- live migration can easily be truly live with shared storage
- easier mai... - 01:50 PM rbd Feature #7920 (Resolved): Openstack: cloning for rbd ephemeral disks
- As per https://blueprints.launchpad.net/nova/+spec/rbd-clone-image-handler
- 12:42 PM Bug #7849 (Resolved): ceph-conf create empty log files
- commit:fc1a424e837bee139726eec333c9efd65e2abb6a
- 09:39 AM Bug #7849: ceph-conf create empty log files
- Josh - please review the wip branch
- 11:58 AM Linux kernel client Feature #3837: krbd: support format 2 striping
- 10:54 AM Bug #7875: osd: pg_pool_t hitset fields incompat
- If you have a mix of OSDs tracking hitsets in the cluster, your data tracking isn't going to make any sense...what di...
- 10:39 AM Fix #7919 (Resolved): mon: prevent clients with a read cap from reading the full keyring
- From the mailing list thread "[ceph-users] Security Hole?"...
- 09:45 AM Bug #7626 (Closed): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- as far as I can tell, Sage is right. Nothing else seems off. Closing the ticket.
- 02:11 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Jasper Siero wrote:
> I updated all nodes to -0.88- 0.78 and removed the monitor and created a new one ;-)
- 02:10 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- I updated all nodes to 0.88 and removed the monitor and created a new one
- 09:36 AM devops Bug #7918 (Won't Fix): Mon hangs at start after upgrading to leveldb-1.12.0-3.fc18.x86_64 from th...
- I had a working 0.72.2 installation using the standard Fedora 18 RPMs.
I upgraded leveldb from 1.7.0-4.fc18 to 1.1... - 09:33 AM Bug #7908 (Resolved): "osd.3 ... [ERR] scrub" in upgrade:dumpling-x:parallel-firefly-distro-basic...
- 09:09 AM Bug #7914: osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length from 4096 to...
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154491
- 09:03 AM Bug #7914 (Resolved): osd: SEGV on ec write, ErasureCodeJerasure: encode adjusted buffer length f...
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154379...
- 09:09 AM Bug #7916 (Can't reproduce): ceph_test_rados got ENOENT on ec pool + thrashing
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154424
- 08:58 AM Bug #7776: client lockdep crash
- ubuntu@teuthology:/a/teuthology-2014-03-30_02:30:11-rados-master-testing-basic-plana/154676
03/30/2014
- 09:17 AM Bug #7909 (Resolved): warnings during gf-complete/jerasure build
- 04:33 AM Bug #7909: warnings during gf-complete/jerasure build
- "work in progress":https://github.com/ceph/ceph/pull/1568 cherry pick of the above pending pull requests
- 01:25 AM Bug #7909 (In Progress): warnings during gf-complete/jerasure build
- * https://bitbucket.org/jimplank/gf-complete/pull-request/12/fix-void-arithmetic-compilation-warning
* https://bitbu...
03/29/2014
- 09:52 PM Bug #7849 (Fix Under Review): ceph-conf create empty log files
- 09:39 PM Bug #7909 (Resolved): warnings during gf-complete/jerasure build
- http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-saucy-amd64-basic/log.cgi?log=c3292e48483d861148322590ea1f05...
- 09:12 PM Bug #7908 (Resolved): "osd.3 ... [ERR] scrub" in upgrade:dumpling-x:parallel-firefly-distro-basic...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-29_19:33:24-upgrade:dumpling-x:parallel-firefly-di...
- 04:59 PM Bug #7907 (Resolved): osd: rollback to head didn't mark_unrollbackable
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-28_22:35:22-upgrade:dumpling-x:stress-split-firefl...
- 04:18 PM Bug #7744: osd: assert(last_e.version.version < e.version.version)
- Two of my osds are crashing with the same signature:
osd/PGLog.cc: 672: FAILED assert(last_e.version.version < e.v... - 09:19 AM CephFS Bug #7880 (Resolved): multimds: directory gets rsynced twice
- 05:28 AM Subtask #7548 (Resolved): Basic docs for Erasure Coding
03/28/2014
- 07:11 PM rbd Bug #6480 (In Progress): librbd crashed qemu-system-x86_64
- Mike provided a core dump in which structures appear to be normal, though it's hard to tell with the ceph::buffer::ra...
- 06:31 PM Bug #7849: ceph-conf create empty log files
- Socket part was introduced later -- perhaps only socket part shall be reversed?
Log-related change seems safe...
- 06:05 PM Bug #7849 (In Progress): ceph-conf create empty log files
- oops, the previous fix breaks ceph.py, which does ceph-conf --show-config-value to get admin_socket.
- 05:23 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Yes, I'm pretty sure it is.. this bug affected 0.77 and was fixed for 0.78. If I remember correctly, the full osdmap...
- 05:20 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- This sounds like it could be commit:14ea8157eb2883b9f53c234044fe002153212ef8
- 10:18 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- The store attached to the ticket shows the latest 7 full osdmaps as being unable to be decoded, which would explain t...
- 05:18 PM Bug #7902 (Pending Backport): osd/PG.cc: 6803: FAILED assert(!pg->actingbackfill.empty())
- 12:54 PM Bug #7902 (Resolved): osd/PG.cc: 6803: FAILED assert(!pg->actingbackfill.empty())
- this a split dumpling/firefly cluster
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-27_22:35:2... - 05:17 PM Bug #7881 (Resolved): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info...
- 03:37 PM Bug #7881: osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info.last_update))
- 03:16 PM Bug #7881 (In Progress): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == i...
- 09:52 AM Bug #7881: osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info.last_update))
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-27_22:35:20-upgrade:dumpling-x:stress-split-firefly...
- 04:58 PM rgw Bug #7903 (Resolved): radosgw-admin: failing to set default region
- 01:27 PM rgw Bug #7903 (Fix Under Review): radosgw-admin: failing to set default region
- 12:59 PM rgw Bug #7903 (Resolved): radosgw-admin: failing to set default region
- http://pulpito.ceph.com/teuthology-2014-03-27_23:00:17-rgw-firefly-distro-basic-plana/149617/
- 04:00 PM rgw Bug #7837 (Resolved): s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- 03:56 PM CephFS Bug #7867 (Resolved): client/Client.cc: 2087: FAILED assert(!unclean)
- 03:47 PM CephFS Bug #7867 (Pending Backport): client/Client.cc: 2087: FAILED assert(!unclean)
- 03:52 PM Bug #7906 (Duplicate): "adjust-ulimits ... --rgw-region zero'''" filed in rgw-firefly-distro-basi...
- Duplicates #7903
- 03:36 PM Bug #7906 (Duplicate): "adjust-ulimits ... --rgw-region zero'''" filed in rgw-firefly-distro-basi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-27_23:00:17-rgw-firefly-distro-basic-plana/149644/...
- 02:07 PM Bug #7874 (Resolved): clone_range from clone on recovery fails if clone has been evicted
- 02:05 PM Bug #7828 (Resolved): osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_sn...
- 02:05 PM Bug #7835 (Resolved): make_writeable needs to fill in ssc on new clone
- 01:25 PM Bug #7805 (Resolved): emperor can go active with < min_size non-incomplete peers since we check a...
- 01:21 PM Bug #7904 (Resolved): osd/ReplicatedPG.cc: 10661: FAILED assert(is_active())
- We need to dump agent_state even on primary->primary
-69> 2014-03-28 13:07:10.884747 7fdc1660b700 15 journal pr... - 10:43 AM Fix #7890: erasure-code: last stripe is not truncated
- At present, this is by design.
- 01:05 AM Fix #7890 (New): erasure-code: last stripe is not truncated
- When encoding a 10 bytes object with osd_pool_erasure_code_stripe_width = 2048 and k=2 + m=1, the last strip should b...
- 10:05 AM rbd Feature #7895 (Resolved): krbd: test cloning, discard, plus regular I/O via fsx
- This could be another fork of src/test/librbd/fsx.c in ceph.git, or modifications to it to abstract out the I/O more ...
- 09:21 AM Bug #7894 (Duplicate): osd: missing hitset object in cluster log
- failure_reason: '"2014-03-27 16:02:47.849800 osd.4 10.214.131.17:6800/13622 33 : [ERR]
4.0 shard (4,255) missing 0... - 09:20 AM Bug #7893 (Duplicate): osd/ReplicatedPG.cc: 10190: FAILED assert(0 == "erroneously present object")
- ...
- 09:19 AM Bug #7892 (Duplicate): osd/ReplicatedPG.cc: 7881: FAILED assert((data_included.empty() && data.le...
- ...
- 09:18 AM Bug #7891 (Resolved): osd: leaked pg refs on shutdown
- ...
- 08:53 AM Bug #5884: negative num_objects_degraded in pool stats
- Oops, replace 1.3 with 1.30 in previous message....
- 08:50 AM Bug #5884: negative num_objects_degraded in pool stats
Seen on a cluster that's been running for the past 2 weeks on the firefly branch.
Potentially noteworthy things ...- 08:25 AM CephFS Bug #7780 (Resolved): When full flag is set, even MDS writes are blocked
- Fix was merged at c647a03fffb2e1e997dbdb0ff128eeb6efc47deb
03/27/2014
- 10:26 PM CephFS Bug #7880: multimds: directory gets rsynced twice
- 06:54 AM CephFS Bug #7880 (Resolved): multimds: directory gets rsynced twice
- probalby the mtime doesn't get set properly teh first time?...
- 09:31 PM Messengers Bug #7888: msgr: keepalive is insufficient
- wip-7888 handles this for MonClient. We can do the same with Objecter, but this is less critical because we will fin...
- 09:24 PM Messengers Bug #7888 (Fix Under Review): msgr: keepalive is insufficient
- 06:01 PM Messengers Bug #7888 (In Progress): msgr: keepalive is insufficient
- 04:44 PM Messengers Bug #7888 (Resolved): msgr: keepalive is insufficient
- the current keepalive behavior relies on writes triggering a tcp timeout/error, which does not actually happy in many...
- 05:58 PM Bug #7824 (Resolved): LibRadosList.ListObjectsNS failure
- ugh, the test wasn't restarting after the cuttlefish->dumpling upgrade step.
ceph-qa-suite.git commit 5651ee813170... - 05:40 PM devops Bug #7889: IPv6 support with ceph-deploy
- socket.gethostbyname supports only ipv4 and should be replaced with socket.getaddrinfo
next the inet_aton is also ... - 05:36 PM devops Bug #7889 (Resolved): IPv6 support with ceph-deploy
- In ceph-deploy/util/arg_validators.py the hostname function fails "hostname: X is not resolvable" if using ipv6
- 05:14 PM Bug #7885 (Resolved): scrub must not take offence if evicted/unpromoted clones are missing on a c...
- 11:54 AM Bug #7885: scrub must not take offence if evicted/unpromoted clones are missing on a cache pool
- 11:41 AM Bug #7885 (Resolved): scrub must not take offence if evicted/unpromoted clones are missing on a c...
- 04:41 PM Bug #7887 (Resolved): W: shlib-with-executable-stack
- Lintian produced the following warnings after building Debian packages of ceph-0.78:...
- 04:29 PM Bug #7875 (Resolved): osd: pg_pool_t hitset fields incompat
- 10:40 AM Bug #7875 (In Progress): osd: pg_pool_t hitset fields incompat
- 02:48 PM Documentation #7886 (New): What's the policy on URL stability for public documentation?
- We're trying to decide whether to include links to documentation on ceph.com within the UI of the Calamari product. W...
- 01:24 PM Bug #7805 (Fix Under Review): emperor can go active with < min_size non-incomplete peers since we...
- 01:24 PM Bug #7858: agent with snaps ceph_test_rados error
- 12:37 PM Bug #7849 (Resolved): ceph-conf create empty log files
- commit:acc31e75a3e7115c00f9980609948455e3b2d49e
- 11:36 AM Bug #7849 (Fix Under Review): ceph-conf create empty log files
- 11:16 AM Bug #7849: ceph-conf create empty log files
- This should be just a matter of passing the right flags to common_init or global_init
- 11:34 AM Feature #7884 (New): investigate having the messenger (or dispatch q?) in the osd limit the numbe...
- 11:14 AM rgw Bug #7876 (Resolved): rgw: > on char* in rgw_rest_user
- 11:13 AM rgw Bug #7876 (Fix Under Review): rgw: > on char* in rgw_rest_user
- 11:13 AM Bug #7826 (Resolved): osd: illegal instruction in jerasure
- 03:23 AM Bug #7826 (Fix Under Review): osd: illegal instruction in jerasure
- 10:40 AM CephFS Bug #7867: client/Client.cc: 2087: FAILED assert(!unclean)
- 10:37 AM Fix #7560 (Closed): mon: add compat set feature to mark an upgraded pg format in order to disallo...
- The feature was introduced for Dumpling. The only version that does not support it is Cuttlefish, and it will assert...
- 10:20 AM Bug #7860 (Resolved): LibRadosTwoPoolsPP.PromoteSnap failed at line 311
- 08:54 AM Bug #7881 (Resolved): osd/PGLog.cc: 430: FAILED assert(to != olog.log.end() || (olog.head == info...
- mixed dumpling/firefly cluster:...
- 08:54 AM rbd Bug #6628: krbd: BUG during ceph_osdc_stop() sometimes when rbd_add() fails
- 07:18 AM devops Bug #7879: sentry-db is down
- Let's get these services moved over today.
- 06:48 AM devops Bug #7879 (Resolved): sentry-db is down
03/26/2014
- 09:55 PM Bug #7824 (In Progress): LibRadosList.ListObjectsNS failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-25_19:33:06-upgrade:dumpling-x:parallel-firefly---b...
- 07:38 PM Feature #7437 (In Progress): EC: add adapt unittest teuthology task and add to nightly
- 07:00 PM CephFS Bug #5787 (Duplicate): client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- 07:00 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- dup #7867
- 06:09 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- 05:44 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- wip-7837
- 05:28 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- looking
- 06:05 PM rgw Bug #7876 (Resolved): rgw: > on char* in rgw_rest_user
- ...
- 05:57 PM CephFS Bug #7867: client/Client.cc: 2087: FAILED assert(!unclean)
- pushed a simpler version, wip-7867-b, that just pins the Inode* for the duration of the readahead. This avoids a pos...
- 09:13 AM CephFS Bug #7867 (Resolved): client/Client.cc: 2087: FAILED assert(!unclean)
- here is the lsat bit of log, starting with the incomplete readahead that caused the crash...
- 05:54 PM Bug #7875 (Resolved): osd: pg_pool_t hitset fields incompat
- If the hitset fields get used in pg_pool_t the encoding is marked as incompatible. This breaks old clients that don'...
- 05:27 PM Bug #7874: clone_range from clone on recovery fails if clone has been evicted
- wip-7874 disables clone subsets for cache pools. Testing
- 05:26 PM Bug #7874: clone_range from clone on recovery fails if clone has been evicted
- 05:13 PM Bug #7874 (Resolved): clone_range from clone on recovery fails if clone has been evicted
- Options
1) don't allow clone_range from clone on recovery if cache pool
2) detect when the clone has been evicted a... - 05:26 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- 05:25 PM Feature #7831: OSD: track objects with omap entries and don't count toward caps
- 05:18 PM Bug #6910 (Resolved): don't query empty osds for unfound
- 05:15 PM Feature #7871 (Resolved): ceph_test_rados: allow no-omap to be specified seperately from ec-pool
- 11:43 AM Feature #7871 (Resolved): ceph_test_rados: allow no-omap to be specified seperately from ec-pool
- 05:13 PM Bug #7870 (Resolved): only return ENOTSUP on omap write ops for EC pools
- 02:04 PM Bug #7870 (Fix Under Review): only return ENOTSUP on omap write ops for EC pools
- 11:39 AM Bug #7870 (Resolved): only return ENOTSUP on omap write ops for EC pools
- This way redirected ops on objects without omap entries will work.
- 04:59 PM rgw Feature #7589 (Resolved): rgw: configurable chunk size
- commit:98654092fc5a18ef542d294d5696cac86d96229f
- 04:10 PM Bug #7860: LibRadosTwoPoolsPP.PromoteSnap failed at line 311
- 03:33 PM Bug #7826: osd: illegal instruction in jerasure
- For the record, the illegal instruction was on an AVX instruction. It was part of the flags being set at compile time...
- 09:53 AM Bug #7826: osd: illegal instruction in jerasure
- 03:32 AM Bug #7826 (In Progress): osd: illegal instruction in jerasure
- "work in progress":https://github.com/ceph/ceph/pull/1534
- 02:17 PM Feature #7873 (Resolved): pg query: dump peer_info, peer_missing in all states
- This debug info is useful for recovering from incomplete situations.
- 01:21 PM Bug #7872 (Duplicate): PG: all_unfound_are_queried_or_lost must skip dne replicas
- 01:21 PM Bug #7872: PG: all_unfound_are_queried_or_lost must skip dne replicas
- actually, 6910
- 01:17 PM Bug #7872 (Duplicate): PG: all_unfound_are_queried_or_lost must skip dne replicas
- 11:48 AM Bug #7823 (Resolved): osd: copy-get from ec pool returns wrong size
- 11:22 AM Cleanup #7869 (Resolved): arch: use cpuid.h when possible
- Milosz Tanski <milosz@adfin.com>:
Instead of doing cpuid manually you can use builtins provided in gcc
(and in... - 09:47 AM Bug #7868 (Can't reproduce): "failed to recover before timeout expired" in powercycle-firefly---b...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-23_23:55:02-powercycle-firefly---basic-plana/14419...
- 01:32 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- Thanks!
- 12:15 AM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- We did not get to the bottom of this and the hardware is still available. It's cold but not dead ;-)
03/25/2014
- 11:51 PM RADOS Cleanup #7865 (New): erasure-code: fine grain SSE support
- make use of "ifunc":http://gcc.gnu.org/onlinedocs/gcc-4.7.2/gcc/Function-Attributes.html#index-g_t_0040code_007bifunc...
- 05:48 PM rgw Bug #7676 (Resolved): rgw: multi-part upload incompatible with EC backend
- commit:7989cbd418ed8d51348851a39ffa84ac2224f4fe
- 05:17 PM RADOS Feature #7770: "ceph osd crush set" should handle ingestion of non-compiled crush maps
- Stating the obvious: If a user is going to manually modify the crush map, there is always a chance of botching it and...
- 01:11 PM RADOS Feature #7770: "ceph osd crush set" should handle ingestion of non-compiled crush maps
- We probably want a better idea of what they are trying to accomplish.
- 05:03 PM Tasks #7864 (New): please clarify copyright and the license
- Please confirm the licensing information for the following files:
Files: src/test/librbd/fsx.c
Copyright: ??1991,... - 04:44 PM rgw Bug #7818 (Resolved): syncdaemon: error geting op state: list index out of range
- fixed by commit:812e48a14837cc0173a15aafa6fa563bf9fdd6d4 in teuthology.git
- 02:44 PM rgw Bug #7818: syncdaemon: error geting op state: list index out of range
- this actually looks like a test issue after all - trying to run some of the data sync tests across regions
- 04:43 PM rgw Bug #7820 (Resolved): "AssertionError: 404 != 301" in rgw-firefly-distro-basic-plana suite
- fixed by commit:0cb00b1fb9bf6c59d787f340dd50ae16b1473f82 in teuthology.git
- 04:23 PM rgw Bug #7099 (Pending Backport): Strange Comportments with media files
- This one was also already merged, in commit:0427f61544529ab4e0792b6afbb23379fe722de1
- 04:11 PM rgw Bug #7271 (Resolved): container create via swift doesn't register ACL
- This was merged a while ago as commit:bf38bfb2e6511217eaa720811af826fe5498a461
- 04:10 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- One more:...
- 09:05 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
- 04:03 PM Feature #7862 (Resolved): allow backfill/recovery while below min_size
- 04:03 PM Feature #7861 (Closed): osd: allow writes on degraded objects
- 03:57 PM Bug #7860 (Resolved): LibRadosTwoPoolsPP.PromoteSnap failed at line 311
This is even before setting up the tiering doing the following sequence:
Create/write "hi there" to object "baz"...- 03:45 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- nvm
- 02:31 PM Bug #7828: osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_snapset.head_...
- finish_ctx incorrectly sets head_exists for a clone evict operation.
- 03:36 PM Bug #7858 (Resolved): agent with snaps ceph_test_rados error
- 2014-03-25 15:04:11,699.699 INFO:teuthology.run:Summary data:
{duration: 474.998064994812, failure_reason: 'Command ... - 03:22 PM Bug #7824: LibRadosList.ListObjectsNS failure
- And it looks like majority of upgrade:dumpling-x:parallel-firefly tests failed like this
- 02:59 PM Bug #7824: LibRadosList.ListObjectsNS failure
- Still an issue, if you need fresh logs log to yw box (via teuthology), logs are in /home/ubuntu/logs/142441
- 01:14 PM Bug #7824: LibRadosList.ListObjectsNS failure
- Is this the one we are backporting?
- 02:42 PM rgw Bug #7821 (Duplicate): 'S3ResponseError: 301 Moved Permanently' in rgw-firefly-distro-basic-plana...
- 02:31 PM Bug #7843: OSD fails to start
- this is the trace when it fails
ceph version 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
1: /usr/bin/ceph... - 09:57 AM Bug #7843: OSD fails to start
- #6101 has nothing to do with this. :)
Looks like something has gone wrong with the OSD classes or some data passed t... - 07:04 AM Bug #7843 (Can't reproduce): OSD fails to start
- one of our OSD suddenly crashed, after that it no longer starts. the osd was new to the cluster so it was recovering....
- 02:14 PM devops Bug #7645 (Resolved): mira020 is having problems
- It had a hardware issue and has since been long fixed.
- 02:13 PM devops Bug #4887: ceph-disk list: Doesn't list properly devices using dm-mapper
- Alfredo - please confirm this issue no longer exists in current ceph-disk
- 02:11 PM devops Bug #5306: Xen based OSDs fail to start ceph-osd process
- Yan is this still an issue?
- 02:10 PM devops Bug #5811 (Resolved): gperftools-{devel,libs}-2.0.11.el6 appears to be broken (centos6/rhel6)
- 02:09 PM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- Loic - is this still "In Progress"?
- 02:07 PM devops Bug #5193: RHEL6 does not ship with xfsprogs
- Should eventually live in http://www.ceph.com/rpm/rhel6/x86_64/
- 02:05 PM devops Bug #5193: RHEL6 does not ship with xfsprogs
- Build and package xfsprogs.
- 02:04 PM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- I've got osd and rgw logs on metropolis:/home/joshd/teuthology/archive/rgw-ec-pool-7837
- 11:54 AM rgw Bug #7837: s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- This looks like an EC related regression, was working before.
The test first creates an object + xattrs. Then over... - 02:01 PM devops Bug #5479: Append our built packages with some sort of inktank/ceph identifier
- 02:01 PM devops Bug #7312 (Resolved): ERROR: Running exception handlers
- This was a temporary issue that has not repeated.
- 01:41 PM Bug #7804: backfill racing with a hitset object remove
- This appears to have been caused by a backfill racing with a hitset object remove -- probably easiest to block hitset...
- 01:27 PM Bug #7781 (Duplicate): "FAILED assert" in rados-firefly-distro-basic-plana suite
- 11:55 AM Bug #7781: "FAILED assert" in rados-firefly-distro-basic-plana suite
- Looks like Ceph issue.
- 01:21 PM Bug #7495 (Resolved): ENOTEMPTY on collection remove
- 01:20 PM Bug #6003: journal Unable to read past sequence 406 ...
- 01:19 PM Bug #7728 (Resolved): osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- 01:04 PM Bug #7706: osd: PrioritizedQueue can starve
- ms pq max tokens per priority: 16777216 is a good work around
- 12:34 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- As a performance patch that only impacts splitting, I don't think this is really appropriate for a backport.
- 11:43 AM Bug #7849 (Resolved): ceph-conf create empty log files
- `ceph-conf` creates empty log files in "/var/log/ceph". This is unexpected, undesireable (and undocumented) behaviour...
- 10:50 AM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
- Merged into master in commit:83661c273e759837816d5cd7ba27233ded898455
- 10:00 AM Bug #7822: examples/librados/hello_world.cc broken on master
- The read isn't supposed to be null terminated; it's a bufferlist. I was sloppy in giving that to an ostream, but doin...
- 09:57 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 09:47 AM Bug #7826: osd: illegal instruction in jerasure
- ceph/src/unittest_erasure_code_jerasure fails consistently...
- 09:32 AM Bug #7826: osd: illegal instruction in jerasure
- reproduced on https://github.com/dachary/ceph/tree/wip-sse-fix
- 08:01 AM Bug #7826: osd: illegal instruction in jerasure
- Reproduced the bug on master in a kvm without SSE instructions :-)...
- 07:40 AM Bug #7826: osd: illegal instruction in jerasure
- I thought that maybe ...
- 05:27 AM Bug #7826: osd: illegal instruction in jerasure
- On master ( afcf016a8a814167ced178d8a4275fa2a6f94a4d ) it fails in the same way using the set of command above, with ...
- 02:32 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 02:29 AM Bug #7826: osd: illegal instruction in jerasure
- ...
- 09:25 AM rbd Bug #5876 (In Progress): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_re...
- 09:24 AM rbd Bug #7282 (Resolved): Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connect...
- Marking resolved since Wido's patches landed upstream. Thanks!
- 09:24 AM rbd Bug #7577 (In Progress): rbd info displays extra random char in block prefix
- 09:21 AM rgw Bug #7526 (Resolved): "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-di...
- 09:21 AM rgw Bug #6889: rgw: usage log: don't log system user operations
- commit:42ef8ba543c7bf13c5aa3b6b4deaaf8a0f9c58b6
- 09:11 AM rgw Feature #6678 (Pending Backport): rgw: reject writes to secondary zones
- 09:08 AM rgw Bug #7502 (Rejected): S3 API - deleting object always returns 204 regardless of object is existin...
- 06:46 AM CephFS Feature #7761 (In Progress): journal-tool: forwards-search through corrupt regions
- 06:45 AM CephFS Feature #7759 (In Progress): journal-tool: roll in resetter/dumper from MDS
- 06:35 AM devops Feature #7239 (Closed): ceph-deploy: install cephfs java bindings
- Noah, ceph-deploy does have the ability to install a package on remote nodes:...
- 06:25 AM rbd Bug #7790: Kernel panic when creating ZFS pools on CEPH RBD devices
- Steps to reproduce bug:
- create a zpool with default options (@zpool create mypool /dev/rbd/rbdpool/rbddev@)
- w...
03/24/2014
- 07:59 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- What we'll actually need to repair these objects will involve pulling the rgw xattrs out as well as the RADOS ones — ...
- 05:31 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- actually, the salvage tool is useless. since we are throwing out the rados user attrs, we can just do...
- 05:23 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- wip-7779 has a reproducer program, and a 'salvage' target that will copy the known important ceph xattrs to a replace...
- 04:41 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- good news: scrub on a pg with an object with too many xattrs:...
- 06:23 PM rgw Bug #7837 (Resolved): s3tests test_object_metadata_replaced_on_put fails on an erasure coded pool
- Using this configuration:...
- 03:36 PM Bug #7835 (Resolved): make_writeable needs to fill in ssc on new clone
- -1> 2014-03-24 15:29:50.770570 7fac0522e700 10 filestore(/var/lib/ceph/osd/ceph-4) _finish_op 0x5ac6a00 seq 4456 ...
- 02:55 PM rgw Bug #7742 (Resolved): FAIL: s3tests.functional.test_s3.test_region_bucket_create_master_access_re...
- commit:0cb00b1fb9bf6c59d787f340dd50ae16b1473f82 in teuthology.git
- 02:41 PM Bug #7826: osd: illegal instruction in jerasure
- running this teuthology workload on http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-deb-precise-amd64-basic/log.cgi?...
- 08:34 AM Bug #7826: osd: illegal instruction in jerasure
- this is what i triggered it with. note that yo uneed to adjust the branch to be something that doesn't include the w...
- 08:05 AM Bug #7826: osd: illegal instruction in jerasure
- fixed a "few things in gf_complete":https://bitbucket.org/jimplank/gf-complete/pull-request/4/defer-the-decision-to-u...
- 07:40 AM Bug #7826: osd: illegal instruction in jerasure
- "work in progress":https://github.com/ceph/ceph/tree/wip-sse-fix to run teuthology workloads
- 02:09 AM Bug #7826: osd: illegal instruction in jerasure
- It would be helpful to have the config yaml used to trigger this...
- 01:15 AM Bug #7826: osd: illegal instruction in jerasure
- "workaround":https://github.com/ceph/ceph/pull/1524
- 02:21 PM RADOS Fix #7832: PG: do not double-queue pg log entries
- Okay, that code diagnosis is probably not correct, since append_log doesn't set the dirty_from member which _write_lo...
- 02:10 PM RADOS Fix #7832 (New): PG: do not double-queue pg log entries
- PG::_write_log() sends each of the entries in the pg log to the omap. (obviously) Irritatingly, PG::append_log does t...
- 02:20 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
- Two commits resolve this issue:
01b99668abd9aaa65e8864c2dad392d35dd892e1
5a3f6c7c8a01c002e9ff7ad5b49afaf3ae041ead - 02:17 PM Bug #6789: cannot remove the leader when there only are two monitors
- This doesn't currently happen on latest. Haven't tested yet with latest dumpling and latest emperor.
- 12:14 PM Feature #7831 (Resolved): OSD: track objects with omap entries and don't count toward caps
- 10:03 AM Bug #7827 (Resolved): osd: weird slow request warnings
- Merged into master in commit:afcf016a8a814167ced178d8a4275fa2a6f94a4d
- 08:27 AM Bug #7626 (In Progress): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 07:34 AM Bug #6850 (Closed): mon: 'ceph health detail' with formatted output doesn't report low space on d...
- As of today this is no longer valid.
- 07:06 AM Feature #6732 (Rejected): mon: 'mon_status' should provide as much insight as 'ping'
- 'mon_status' has a different scope than that of 'ping'.
'mon_status' reports on monitor's status, via the ceph too...
03/23/2014
- 10:33 PM Bug #7826: osd: illegal instruction in jerasure
- 10:32 PM Bug #7826 (Fix Under Review): osd: illegal instruction in jerasure
- 06:38 PM Bug #7826 (Resolved): osd: illegal instruction in jerasure
- ...
- 10:12 PM Bug #7828 (Resolved): osd/ReplicatedPG.cc: 4984: FAILED assert(ctx->new_obs.exists == ctx->new_sn...
- ...
- 09:34 PM Bug #7827 (Fix Under Review): osd: weird slow request warnings
- 09:27 PM Bug #7827 (Resolved): osd: weird slow request warnings
- ...
- 11:48 AM rgw Feature #6513 (Resolved): rgw: dr: Service scripts for meta/data sync agents
- Added to radosgw-agent.git commit:c8d243f503b39e67a8daec6df40b58fb993cc6e6 and the following few to fix up packaging.
- 05:25 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
- Also, for those who are ailed by this bug, best solution for them is to remove the affected monitor from the cluster ...
- 05:23 AM Bug #5804 (Resolved): mon: binds to 0.0.0.0:6800something port
- My suspicions were right, at least as far as the VMs are concerned. Whereas using 0.67.2 or 0.72.2 would hit this ev...
03/22/2014
- 08:44 PM Bug #7824 (Resolved): LibRadosList.ListObjectsNS failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-22_19:33:22-upgrade:dumpling-x:parallel-firefly---b...
- 03:41 PM Bug #7823: osd: copy-get from ec pool returns wrong size
- wip-ec-copy-get
- 03:19 PM Bug #7823 (Resolved): osd: copy-get from ec pool returns wrong size
- reproduced w/ replicated cache in front of an ec pool and ceph_test_rados
03/21/2014
- 09:50 PM Bug #7822 (Resolved): examples/librados/hello_world.cc broken on master
- Using the example program to test librados ports, I notice that it's currently failing (slightly) on master:...
- 07:30 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- I propose the following:
1. Ubuntu LTS (12.04, 14.04, etc) can (should) stop at the Inktank-supported Ceph release... - 05:11 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Been waiting for a while, one more weekend won't hurt ;)
Don't know about the others but I'll be very happy with e... - 05:01 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Builds take quite a while and we are actually doing a release today so at the very least this will need to wait until...
- 12:01 PM devops Bug #6726: Official packages do not appear to be available for Saucy
- Ok, i was able to sucessfully build for saucy on jenkins. Trusty is giving me trouble as the machines I was using are...
- 05:22 PM rgw Bug #7821 (Duplicate): 'S3ResponseError: 301 Moved Permanently' in rgw-firefly-distro-basic-plana...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-21_14:31:01-rgw-firefly-distro-basic-plana/140962/...
- 05:16 PM rgw Bug #7820 (Resolved): "AssertionError: 404 != 301" in rgw-firefly-distro-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-21_14:31:01-rgw-firefly-distro-basic-plana/140967/...
- 03:00 PM Feature #7757 (Resolved): erasure-code: enable jerasure-2 SSE optimizations
- 07:27 AM Feature #7757: erasure-code: enable jerasure-2 SSE optimizations
- "The problem with enabling that flag is that it apparently also gives the compiler license to use SSE2 instructions i...
- 07:01 AM Feature #7757 (Fix Under Review): erasure-code: enable jerasure-2 SSE optimizations
- "work in progress":https://github.com/ceph/ceph/pull/1512
- 04:58 AM Feature #7757: erasure-code: enable jerasure-2 SSE optimizations
- Waiting for review, K. Greenan may do it this week-end
- 02:51 PM Bug #7212 (Resolved): monitor fails to start
- 01:51 PM rgw Bug #7816 (Resolved): 403 Forbidden while accessing https://github.com/ceph/radosgw-agent.git/inf...
- teuthology.git 752a76fb4860afa8cd385e7103fc2832cdbb4098
- 01:30 PM rgw Bug #7816 (Resolved): 403 Forbidden while accessing https://github.com/ceph/radosgw-agent.git/inf...
- ...
- 01:41 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
- 01:40 PM rgw Bug #7818 (Resolved): syncdaemon: error geting op state: list index out of range
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-21_13:07:49-rgw-firefly-distro-basic-plana/140905<p...
- 01:34 PM rgw Feature #7817 (Resolved): rgw: some support for copy multipart part
- The minimum support should be returning a NotImplemented error code, rather than NoSuchKey.
- 01:29 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
- 12:07 PM rgw Bug #7815 (Can't reproduce): Test failed in upgrade:dumpling-x:parallel-firefly-testing-basic-pla...
- Logs are in http://qa-proxy.ceph.com/teuthology/ubuntu-2014-03-21_11:05:47-upgrade:dumpling-x:parallel-firefly-testin...
- 09:19 AM Feature #7438 (Fix Under Review): EC: adapt watch/notify stress test for EC and add to nightly
- 06:46 AM CephFS Feature #7810 (Resolved): libcephfs: add a test that freezes + unfreezes a client, and then verif...
03/20/2014
- 05:56 PM Bug #7735 (Fix Under Review): osd: priorityqueue debug dump crashes
- 04:54 PM rgw Bug #7702 (Resolved): osd thrashing + rgw = timeouts
- 04:39 PM rgw Bug #7808 (Duplicate): "ERROR: testContainerSerializedInfo" in upgrade:dumpling-x:stress-split-fi...
- # 7799
- 04:37 PM rgw Bug #7808 (Duplicate): "ERROR: testContainerSerializedInfo" in upgrade:dumpling-x:stress-split-fi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_01:35:01-upgrade:dumpling-x:stress-split-firefl...
- 04:25 PM rbd Documentation #7807 (Closed): fix hostname on docu
- http://ceph.com/docs/master/install/upgrading-ceph
ceph-deploy install --stable {stable release} ceph-node1[ ceph-... - 04:23 PM Bug #7805 (Resolved): emperor can go active with < min_size non-incomplete peers since we check a...
- 03:54 PM Bug #7804 (Duplicate): backfill racing with a hitset object remove
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_02:30:02-rados-firefly-distro-basic-plana/13947...
- 12:47 PM devops Bug #7585 (Resolved): ceph-deploy should handle requiretty failures
- Pull request opened https://github.com/ceph/ceph-deploy/pull/171
And merged into ceph-deploy's master branch with ... - 10:04 AM devops Bug #7585 (In Progress): ceph-deploy should handle requiretty failures
- 10:03 AM devops Bug #7585: ceph-deploy should handle requiretty failures
- To replicate the issue, in `/etc/sudoers` the following needs to be present:...
- 11:40 AM rgw Bug #7786: civetweb segfaults with file uploads larger than 2GB
- The patch has been merged.
- 11:17 AM rbd Bug #7790: Kernel panic when creating ZFS pools on CEPH RBD devices
- updated source to support.
- 10:35 AM Bug #7801 (Resolved): warn on ext4 remount journal replay INFO line
- fixed by teuthology commit 7088885ecd739a4006418eb9e7464d2f0128ea5d
- 10:23 AM Bug #7801 (Resolved): warn on ext4 remount journal replay INFO line
- Logs are in http://qa-proxy.ceph.com/teuthology/ubuntu-2014-03-19_17:33:45-powercycle-firefly-testing-basic-plana/138...
- 10:33 AM Bug #7208: CEPH_FEATURE_CRUSH_V2 feature mismatch
- oh, commit:08fa34d94e40f2f7230dec4dabad72107cdee27b removed the default erasure pool from the OSDMap which fixed this...
- 10:25 AM Bug #7208: CEPH_FEATURE_CRUSH_V2 feature mismatch
- workarounds:
ceph osd crush tunables bobtail
works with any kernel > 3.9. or,
ceph osd crush tunables fir... - 10:20 AM rbd Bug #5469: qemu-io: segfault when tried IO with invalid arguments
- we've got the same assertion failure today on 0.67.3. It's rare and random.
osdc/Striper.cc: In function 'static ... - 09:36 AM rgw Bug #7799 (Can't reproduce): Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-20_01:35:01-upgrade:dumpling-x:stress-split-firefl...
- 09:23 AM Bug #7755 (Resolved): auth_log selection depends on the primary identity and can cause a loop
- 09:19 AM Bug #7733 (Resolved): start_new_interval: always notify if !primary
- 09:18 AM Bug #7777 (Resolved): 2014-03-18T12:48:30.368 INFO:teuthology.task.rados.rados.0.err:[10.214.132....
- 08:17 AM rgw Bug #7796 (Resolved): RGW Keystone token auth fails with '411 Length Required' when Keystone usin...
- When using keystone behind apache/wsgi in the following config, radosgw is unable to authenticate tokens:
cat /etc... - 07:28 AM Feature #7792 (Closed): leveldb 1.12.0 for rhel
- It appears libleveldb1 version 1.12.0 is provided for debian/ubuntu here:
http://ceph.com/debian-dumpling/pool/mai... - 05:51 AM devops Bug #7677 (Resolved): Troubleshoot ceph-setup-nightly Jenkins failures
03/19/2014
- 04:39 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
- Not wanting to commit to a full diagnosis just yet, this is looking a lot like a mild case of #7212 with a weird resu...
- 03:39 PM rgw Feature #7791 (Rejected): radosgw-agent should show statistics
- radosgw-agent might be a good method of offering statistics and reporting, such as log version between gateways, spee...
- 03:37 PM rbd Bug #7790 (Resolved): Kernel panic when creating ZFS pools on CEPH RBD devices
- Creating a ZFS pool on top of krbd causes a kernel panic.
From the ZFSonLinux bug tracker (https://github.com/zfso... - 01:18 PM rbd Fix #7787 (Resolved): rbd diff takes longer as images grow larger
- rbd diff will currently take a VERY long time to complete for large images. This is not ideal. Perhaps a counter of s...
- 12:24 PM rgw Bug #7786 (Resolved): civetweb segfaults with file uploads larger than 2GB
- I submitted a pull request to fix this. I'm waiting to hear back from the maintainers of the project.
https://githu... - 11:46 AM Feature #7784: mon osd down out interval = 0 should prevent ceph health from reporting ok
- Perhaps this config option should be converted into the noout flag; that's already plumbed up for such things.
- 11:13 AM Feature #7784 (Resolved): mon osd down out interval = 0 should prevent ceph health from reporting ok
- 11:45 AM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- Sounds like this is a manual repair job to me, then...
I guess we could write tools that know all the xattr name pat... - 10:51 AM Bug #7393 (Duplicate): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whit...
- We don't seem to be seeing this any more, might have been related to the object_info_t leaking. Marking duplicate un...
- 10:36 AM Bug #7781 (Duplicate): "FAILED assert" in rados-firefly-distro-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/13740...
- 08:28 AM CephFS Bug #7780 (Fix Under Review): When full flag is set, even MDS writes are blocked
- 05:12 AM CephFS Bug #7780: When full flag is set, even MDS writes are blocked
- Just tried commenting out the check in objecter and the MDS writes get through, so not too much work to do here.
- 04:05 AM CephFS Bug #7780 (Resolved): When full flag is set, even MDS writes are blocked
We're meant to allow the MDS to write even when the OSDs think they're full, so that we can journal file deletions ...
03/18/2014
- 09:28 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- 08:56 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- Yep. This particular object was written back in November, though, so it predates the fix by some time (and in fact m...
- 08:52 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
- This exact bug is why we made the changes to xattr handling and no longer store unlimited numbers in the filesystem. ...
- 06:44 PM Bug #7779 (Resolved): osd: object file can have too many xattrs, get E2BIG
- if an object has too many xattrs on it, you get E2BIG from listxattr. one such object:...
- 08:07 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
- 03:57 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137408
- 03:03 PM Bug #7776 (Resolved): client lockdep crash
- 2014-03-18T14:50:40.839 INFO:teuthology.task.workunit.client.0.err:[10.214.131.15]: -3> 2014-03-18 14:48:00.14746...
- 03:45 PM Bug #7777 (Resolved): 2014-03-18T12:48:30.368 INFO:teuthology.task.rados.rados.0.err:[10.214.132....
- is_missing_object(snapdir)->wait_for_unreadable
2014-03-18T12:48:27.770 INFO:teuthology.task.thrashosds.thrasher:T... - 02:32 PM rgw Bug #7702: osd thrashing + rgw = timeouts
- this affects the dumpling-x/stress-split tests, and *would* affect rados thrashing if we had an rgw workload in there.
- 02:28 PM rgw Documentation #7434 (In Progress): rgw: doc user/group quota
- I have a local branch where this is in progress. I'll try and put it up at the end of the week after I finish the rel...
- 02:25 PM Bug #7398: osd: ERANGE from clone
- Seems that there is a stale ssc from a previous interval (?) mucking up the calc_clone_subsets process. Testing a br...
- 12:36 PM Bug #7398: osd: ERANGE from clone
- ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137259/remote
With logging. - 01:41 PM Bug #6633: osd: pgls vs osd restart/peering race misses objects
- backported to dumpling.
- 12:40 PM rgw Feature #7774 (Resolved): rgw: cache decoded user and bucket info
- Instead of having to access raw objects and then decode them for each request. Needs an invalidation mechanism that i...
- 12:34 PM Bug #7733: start_new_interval: always notify if !primary
- 12:30 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- 12:30 PM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 11:40 AM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 12:05 PM Feature #7767 (Fix Under Review): messenger:buffer reads
- 08:43 AM Feature #7767 (Resolved): messenger:buffer reads
- The way we read message involves with multiple smallish reads, which can have a big performance impact. Need to buffe...
- 11:22 AM RADOS Feature #7770 (New): "ceph osd crush set" should handle ingestion of non-compiled crush maps
- "ceph osd crush dump" will output a decompiled version of the crush map in a format of choice. It would be nice to be...
- 10:49 AM Bug #6806 (Pending Backport): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 09:42 AM Bug #6806 (Fix Under Review): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 10:08 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
- Yep, you need the xfs-dev headers to build Ceph now.
- 01:45 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- invalidate this bug report
- 01:38 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- in order to avoid these errors, i think we should check xfs lib , not xfs header file
- 01:36 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
- when i used configure.ac to config ceph, i get an error "configure: error: xfs/xfs.h not found (--without-libxfs to d...
- 09:24 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi,
well, there is nothing else in dmesg, except several hours before this hang.
This servers are running about... - 09:07 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi Olivier,
Can you attach the entire dmesg or at least a few minutes worth of
messages prior to the assertion fa... - 09:00 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- and in a 3.13.5 kernel too :...
- 08:47 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Hi,
same thing with a 3.13.5 kernel :... - 08:17 AM Bug #7765: Bogus bandwidth statistics during pg creation
- On the attachment, around 09:40 is some actual client I/O maxing out the cluster. Around 09:55 is where I start crea...
- 08:13 AM Bug #7765 (Can't reproduce): Bogus bandwidth statistics during pg creation
Noticed this while growing the number of PGs in an existing pool on a cluster running firefly branch....- 07:18 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- About the systemd not playing well with ceph-deploy, I am still doubtful because the way ceph-deploy is working with ...
- 07:00 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- I tried to replicate this with ceph-deploy and boy was it a nightmare to get there.
FC19 panics a few seconds afte... - 05:28 AM CephFS Feature #7764 (Resolved): InoTable/SessionMap/ manipulator (cephfs-table-tool)
Some bugs might create a situation where the metadata/journal may be okay but recovery fails because one of the glo...- 05:25 AM CephFS Feature #7763 (Resolved): journal-tool: import
- Given a binary journal dump, insert it back into the metadata pool.
- 05:23 AM CephFS Feature #7762 (Rejected): journal-tool: backwards-search after corrupt regions
- When a corrupt region is encountered, use the start pointers to walk from the end of the log back to the latest valid...
- 05:22 AM CephFS Feature #7352: mds: make classes encode/decode-able
- related, on journal-tool branch have got to a point where dencoder can handle getting the inodes out of .inode object...
- 05:20 AM CephFS Feature #7761 (Resolved): journal-tool: forwards-search through corrupt regions
When corruption is encountered, search forward byte by byte for the next sentinel word.- 05:18 AM CephFS Feature #7760 (Resolved): journal-tool: implement splice
Simple implementation based on new ENoOp event type that allows us to selectively blank out regions in existing log.- 05:17 AM CephFS Feature #7759 (Resolved): journal-tool: roll in resetter/dumper from MDS
To provide the capabilities in one convenient place and remove a few LOC from the MDS.- 05:15 AM CephFS Feature #7758 (Resolved): journal-tool: complete filtering
- Already done:
--path
--range
Remaining to do:
--by-inode <inodeno>
--by-dirfrag <frag id>:[dentry]
--by-... - 02:52 AM Feature #7757 (Resolved): erasure-code: enable jerasure-2 SSE optimizations
- gf-complete, the library used by jerasure-2, decides to use SSE instructions based on CPU features found at compile t...
03/17/2014
- 09:48 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
- Hello Greg,
Can we backport this fix to dumpling? - 08:52 PM Feature #7599 (Resolved): erasure-code : upgrade to jerasure-2
- 08:38 PM Bug #7755 (Resolved): auth_log selection depends on the primary identity and can cause a loop
- calc_ec_acting assumes the first valid osd will be primary, this is not necessarily so with primary affinity. We can...
- 04:33 PM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
- 09:12 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
- "work in progress":https://github.com/ceph/ceph/pull/1477
- 04:22 PM Bug #7736 (Pending Backport): mon: can expose stale state
- 03:29 PM Bug #7736: mon: can expose stale state
- 04:45 AM Bug #7736: mon: can expose stale state
- 04:43 AM Bug #7736: mon: can expose stale state
- This works for me.
Also noticed that a custom crafted message could trigger a commit with the old code. Apparentl... - 04:12 PM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 10:48 AM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 04:04 PM Bug #7738 (Pending Backport): osd: journal crash on startup on wheezy
- 04:04 PM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- 03:40 PM Bug #7738 (Fix Under Review): osd: journal crash on startup on wheezy
- As far as I can tell the problem is that the journal symlink isn't always present when we reopen the journal for writ...
- 03:43 PM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- 10:04 AM Bug #7713: "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:parallel-firef...
- actually, the problem is probably that dumpling still has the bug.
- 10:03 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- this was #7709, now fixed
- 03:37 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
- commit:5e7a98911e6a6db525d65981034d28065a045e47
- 01:53 PM rbd Feature #7746: Capacity Management: rbd df
- Confirmed that this doesn't just affect RBD pools but affects any pool, as the data is generated from reading the off...
- 10:14 AM rbd Feature #7746 (Resolved): Capacity Management: rbd df
- Currently, ceph df shows two sets of statistics: global and pool.
For global, the output is generated from aggrega... - 01:22 PM Bug #7751 (Closed): os: LevelDBStore: needs to check iter->status() during get()
- We are ignoring the status of the iterator during 'LevelDBStore::get()' -- we're also ignoring the state of the itera...
- 01:04 PM CephFS Bug #7750 (Can't reproduce): Attempting to mount a kNFS export of a sub-directory of a CephFS fil...
- Hi,
I have run into the following issue when trying to export a subset of a CephFS filesystem via NFS:
Machine ... - 01:03 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
- This looks like network issues - the run was killed, so there are no logs from radosgw to confirm.
- 01:00 PM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
- Fixed in teuthology commit:ef2edcd3a96a2118d793b7a102688f60fa100f52
- 11:58 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
- A different approach: https://github.com/ceph/teuthology/pull/227
- 11:23 AM rgw Bug #7749 (Fix Under Review): radosgw-agent: worker.DataWorker.wait_for_object() should bail on r...
- 11:22 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
- https://github.com/ceph/radosgw-agent/pull/9
- 11:16 AM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
- Currently, the method will do this forever if a connection goes down:...
- 10:40 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
- 10:09 AM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
- whitelisted this
- 10:03 AM Feature #7717: Per CRUSH bucket used/available space
- 09:22 AM Fix #6780 (Closed): monitor errors when checking for quorum status
- 09:13 AM Fix #6780: monitor errors when checking for quorum status
- can no longer reproduce this on firefly. any objections on closing?
- 08:19 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
- 08:00 AM Bug #7611 (Fix Under Review): All mon nodes crash when running "ceph tell osd.X" and using the "v...
03/16/2014
- 05:32 PM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 31a667918069ac72c70080dcacd6ff3b6d58f07b
- 03:26 PM Feature #7662 (In Progress): add a "ec profiles" map to OSDMap
- 10:36 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
- *ABANDONNED* "work in progress":https://github.com/ceph/ceph/pull/1475
I've set it to urgent so someone can decide... - 12:54 PM Bug #7744 (Can't reproduce): osd: assert(last_e.version.version < e.version.version)
- I currently have 2 OSDs that won't start and it's preventing my
cluster from running my VMs.
My cluster is running ... - 12:11 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 12:10 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133582...
- 12:09 PM rgw Bug #7742 (Resolved): FAIL: s3tests.functional.test_s3.test_region_bucket_create_master_access_re...
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587
this may be a dup of the... - 12:08 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
- ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587...
- 09:36 AM Bug #7719 (Resolved): failed to become clean
03/15/2014
- 08:58 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-15_17:09:08-rados:thrash-firefly-distro-basic-plana...
- 07:39 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
- 05:39 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 05:07 PM Bug #7736 (Fix Under Review): mon: can expose stale state
- 02:15 PM Bug #7736: mon: can expose stale state
- This *is* committed state. Looks like we need to wait for everybody to ack or for leases to expire before responding ...
- 09:52 AM Bug #7736 (Resolved): mon: can expose stale state
- teuthology-2014-03-14_19:00:49-rados-dumpling-testing-basic-plana/130941
here is a deletion on the primary:... - 04:17 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
- 03:30 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 03:30 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 11:15 AM CephFS Bug #7739 (Resolved): mds: uninitialized field in message
- ubuntu@teuthology:/a/teuthology-2014-03-14_23:01:36-multimds-master-testing-basic-plana/131675
hard to map this to... - 10:10 AM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- ubuntu@teuthology:/a/sage-wheezy/130813...
- 10:09 AM Bug #7737 (Resolved): osd: deletes vs backfill makes degraded go negative
- this is the tail end of a rados bench run that was outpacing backfill. once it started to delete objects, the degrad...
- 12:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- I'm 90% sure this is systemd killing everything in the cgroup when ceph-deploy's ssh session closes. The log file ju...
03/14/2014
- 08:26 PM Bug #7735: osd: priorityqueue debug dump crashes
- wip-pq
- 08:21 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
- discovered when doing backfill testing with wip-pq:...
- 06:03 PM Bug #7732: stuck recovering with unfound -- build_might_have_unfound bug
- 05:58 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 05:59 PM Bug #7733 (Resolved): start_new_interval: always notify if !primary
- 05:29 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
- I grabbed and compiled the patched version of FastCGI as a DSO from here:
https://github.com/ceph/mod_fastcgi.git
... - 05:03 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
- I'm not sure we actually require it. You're not using the modified fastcgi module and therefore chunked encoding is n...
- 03:52 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
- We are using the S3 SDK and I am getting a return from RGW claiming that Content-Length must be set. However, accordi...
- 05:05 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan Mick wrote:
> I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is t... - 04:52 PM Bug #7712: osd: ENOENT following copy-from
- it looks like the requeues get in all sorts of weird orders:
grep --color=auto 3\\.2\( remote/*/log/*osd.5* | egre... - 04:45 PM Bug #7712: osd: ENOENT following copy-from
- grep dequeue_op remote/*/log/*osd.5* | grep plana2926152-290
osd.5.3:79 and osd.1.3:681 get reordered
when they... - 10:33 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
- 2014-03-14T09:47:00.894 INFO:teuthology.task.rados.rados.0.out:[10.214.131.11]: 2625: delete oid 290 current snap is ...
- 04:36 PM Bug #7659 (In Progress): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing()....
- 04:20 PM rgw Documentation #7731 (Resolved): Warning about "rgw print continue" should be added to radosgw con...
- Here,
http://ceph.com/docs/dumpling/radosgw/config/
Just as there is a warning to turn off FastCgiWrapper on Ce... - 03:59 PM Documentation #6465: admin/build-doc should have some kind of build check for broken links
- Actually, it seems like the :ref: syntax at least catches a file name mismatch. We should probably begin converting t...
- 03:57 PM Documentation #7558 (Resolved): broken link in install/manual-deployment/
- Fixed. The file name was incorrect. Probably should be using :ref: syntax instead.
- 03:13 PM Documentation #7729 (Closed): CAPS with dot (.) notation can be unquoted
- Authentication documentation should indicate that CAPS with dot notation do not have to be quoted any longer.
htt... - 03:10 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- 01:28 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- ...
- 02:51 PM Bug #7728 (Resolved): osd/ReplicatedPG.cc: 4999: FAILED assert(got)
ceph version 0.77-859-g0bf5b52 (0bf5b52ae035d9893b5d079abee05bb3114ef51e)
1: (ReplicatedPG::finish_ctx(Replicate...- 02:47 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 02:46 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- issue_repop sets the last_update for stored peer_info to repop->v which is eversion_t() for temp objects. Testing fix.
- 12:58 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- ...
- 02:37 PM Feature #7698: Add EC handling to ceph_filestore_dump
- Ready to go into either master or firefly branches.
- 02:17 PM Documentation #7727 (Resolved): CRUSH "chassis" bucket type
- We should note that there is a new "chassis" default bucket type. It might go here:
http://ceph.com/docs/master/ra... - 02:09 PM Documentation #7726 (Resolved): Quick Start Requires Updating
- With size = 3 by default, the cluster as defined by the quick start guide will never get to an active + clean state u...
- 02:06 PM Documentation #7725 (Resolved): osd pool default size need updating
- The default value for size is now 3.
http://ceph.com/docs/master/rados/configuration/pool-pg-config-ref/ - 02:04 PM Documentation #7724: filestore xattr use omap removed
- It's a good idea to doc it, but in general we don't support reverting versions and should not give the appearance of ...
- 02:01 PM Documentation #7724 (Resolved): filestore xattr use omap removed
- Ceph Documentation needs to indicate that filestore xattr use omap was removed and specify the version. Users reverti...
- 01:59 PM Feature #7723 (New): Cancel RADOS Bench writes and still do reads
- Right now in RADOS bench if you write some data out with the --no-cleanup flag but ctrl+c or kill the process before ...
- 01:55 PM devops Cleanup #7722 (Resolved): Make /admin/build-doc distro independent
- The script for building Ceph documentation under admin/build-doc is currently Debian/Ubuntu only. This limits communi...
- 01:52 PM Documentation #7721 (Closed): Document the process to migrate from RBD format 1 to format 2 images
- There is a mention of that in the RBD man page, but I think we should also document it on ceph.com with some warning ...
- 01:08 PM Bug #7719 (Resolved): failed to become clean
- Stuck in remapped due to deleted pg shard clobbering want_pg_temp from primary.
2014-03-14T08:07:26.245 INFO:teuth... - 01:00 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
- Still getting these crashes multiple times a week across a dozen guests on separate hosts. These guests are video sur...
- 12:51 PM Feature #7717 (Closed): Per CRUSH bucket used/available space
- When using multiple pools spread across different failure domains it can be difficult to know how much space is avail...
- 12:30 PM devops Feature #7716 (Resolved): Build debug packages for EL6
- The debug packages for el6 are not available for releases >0.67.3.
http://ceph.com/rpm-dumpling/el6/x86_64/
http:... - 12:07 PM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---...
- 11:51 AM Bug #7216 (Can't reproduce): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 09:43 AM Bug #7216 (New): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 11:35 AM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
- 11:28 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 11:22 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---...
- 11:05 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
- 05:50 AM Bug #7692: mon: monitor fails to form quorum
- We are now seeing a more generalized failure were no monitor is able to form quorum (from ceph-deploy):...
- 10:51 AM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
- 06:02 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- Here's the thing: as is, ceph-mon is being run as a daemon. That entails dissociating it from its running terminal, ...
- 05:10 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- Tools like 'ceph-mon' are used by other tools to abstract ceph management and those tools will almost always check ex...
- 04:48 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
- This only happens when the monitor is running as a daemon, which I would think is the expected result: all output is ...
- 10:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- 09:59 AM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
- 09:57 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- That doesn't seem like it's addressing the issue the right way. We've deliberately set it so that PGs which don't get...
- 09:40 AM Bug #7576: osd: large skew in pg epochs (dumpling)
- How about this: in OSDService, add
Mutex pg_epoch_lock;
Cond pg_epoch_cond;
multiset<epoch_t> pg_epochs;
ma... - 09:50 AM Fix #7711 (New): OpTracker output doesn't include op size for subops
- Been discussing the OpTracker dumps on the mailing list and realized the subops don't contain transaction size inform...
- 09:49 AM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
- d0d21fae483cfaf5556b18b2f0e113c7d418e90c Landed to Firefly
- 09:44 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:44 AM Bug #7626 (New): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:42 AM Bug #7497 (Can't reproduce): timeout waiting to go clean
- 09:34 AM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
- I think we need a log for this.. hopefully we will hit it now that things are cranked up on the nightlies?
- 09:21 AM Bug #7710 (Fix Under Review): Multiple rados bench instance will overwrite the metadata object
- 06:53 AM Bug #7710: Multiple rados bench instance will overwrite the metadata object
- Please help to review the pull request - https://github.com/ceph/ceph/pull/1457
- 06:48 AM Bug #7710 (Resolved): Multiple rados bench instance will overwrite the metadata object
- rados bench is useful to benchmark the cluster, however, there is one user case it does not support: read after write...
- 07:45 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
- So don't forget the patch I got accepted into libvirt a few weeks ago.
If you are running a RBD storage pool it wi... - 04:37 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
03/13/2014
- 10:41 PM Bug #7709 (Fix Under Review): osd: RWORDERED does not order reads ack vs write commit
- 10:02 PM Bug #7709: osd: RWORDERED does not order reads ack vs write commit
- 09:58 PM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
- We just fixed ceph_test_rados to wait for commit, not ack. It turns out that the RWORDERED flag is ordering a
wr... - 09:10 PM Bug #7498 (Resolved): stuck in recovery
- 09:09 PM Bug #7210: mon: does not validate snapshot removal commands
- I would like to see this in the wild before doing the backport.
- 09:08 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- Jasper Siero wrote:
> I submitted the new log with debug mon = 10 added to the ceph.conf.
> The two processes belo... - 05:09 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- I submitted the new log with debug mon = 10 added to the ceph.conf.
The two processes below also keeps running afte... - 09:04 PM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- 09:01 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- ...
- 08:28 PM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- ...
- 11:01 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- And again:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_23:00:26-fs-firefly-testing-basic-plana/127977/... - 04:35 PM Bug #7648 (Won't Fix): ceph-mon corner case denial of service
- This only works on osd.0; for other osds, both dumpling and emperor behave (with bogus output)...
- 04:28 PM Bug #7706 (Pending Backport): osd: PrioritizedQueue can starve
- 01:58 PM Bug #7706 (Resolved): osd: PrioritizedQueue can starve
- starvation caused by pq max token limit
- 04:27 PM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
- 09:30 AM Bug #7704 (In Progress): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-...
- I think this is a manifestation of the full osdmap encoding features, which aren't specified for dumpling and can thu...
- 08:59 AM Bug #7704: "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-plana suite
- Also see in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---...
- 08:55 AM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---...
- 04:10 PM Bug #7635 (Duplicate): failed to recover before timeout expired
- 03:32 PM Bug #7208 (Resolved): CEPH_FEATURE_CRUSH_V2 feature mismatch
- this was fixed when i fixed up the default crush tunables to be firefly not optimal
- 03:27 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats
- 06:53 AM CephFS Bug #7565: Failed assert in check_rstats
- ubuntu@teuthology:/a/teuthology-2014-03-12_04:55:11-multimds-master-testing-basic-plana/127691
failed on trivial_s... - 02:59 PM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- 11:39 AM Bug #7705: ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong version")
- wip-7705
- 10:01 AM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- ...
- 01:14 PM devops Feature #7239: ceph-deploy: install cephfs java bindings
- I deployed Ceph to a cluster that I intended to run Hadoop on. In this case, a typical setup is to have the cephfs cl...
- 12:51 PM devops Feature #7239 (Need More Info): ceph-deploy: install cephfs java bindings
- Could you please elaborate why you think ceph-deploy should be in charge of installing a dependency like java binding...
- 11:54 AM devops Bug #7598 (Need More Info): ceph-disk-activate error with ceph-deploy
- I can't replicate this behavior *at all*. I do know why that is the error that comes about though.
What happens is... - 11:20 AM rgw Bug #7703 (Fix Under Review): rgw: fail to copy object > 512k between buckets
- 10:00 AM rgw Bug #7702 (Need More Info): osd thrashing + rgw = timeouts
- 09:41 AM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
- 09:40 AM Bug #7260 (Can't reproduce): rados api test LibRadosList.ListObjectsNS failed
- reopen if we see this now that the enumerator/iterator changes are in place
- 09:38 AM Bug #7259 (Resolved): ceph mon crash in master branch
- 06:29 AM Bug #7593: Disk saturation during PG folder splitting
- Thanks Sage very much for the comments.
To begin with, I propose a change here - https://github.com/ceph/ceph/pull...
03/12/2014
- 09:02 PM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
- This fails due to issue #7703.
- 08:59 PM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
- The new manifest does not hold bucket marker info which is needed, as when we're copying object between buckets we ne...
- 06:37 PM Bug #7696: osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 10:07 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- Primary and replica disagree on last_backfill for some reason.
-3> 2014-03-12 03:31:58.711369 7feaff6c9700 10 ... - 06:32 PM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
- 05:32 PM Bug #7626 (Need More Info): After updating ceph from 0.75 to 0.77 one of the three monitors can't...
- 05:09 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
- 04:04 PM rgw Bug #7702 (Resolved): osd thrashing + rgw = timeouts
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl...
- 03:45 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
- 02:12 PM Bug #7682: osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first == repop->v)
- 02:46 PM Feature #7701 (Resolved): Filterable querying interface for PGMonitor
On larger clusters with 100,000s or millions of PGs, dumping everything for external tools becomes inefficient.
...- 02:38 PM Feature #7700 (New): Create a health severity between OK and WARN
I think the name we liked best so far was NOTICE.
For each WARN "health check" a la #7192, reconsider its severi...- 02:04 PM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl...
- 01:25 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is that, if the string ...
- 09:55 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> Danny Al-Gaaf wrote:
> > Dan van der Ster wrote:
> > > The other solution would be to co... - 09:32 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Danny Al-Gaaf wrote:
> Dan van der Ster wrote:
> > The other solution would be to copy block_name_prefix to a local... - 09:29 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> The other solution would be to copy block_name_prefix to a local null terminated in the fu... - 09:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- The other solution would be to copy block_name_prefix to a local null terminated in the function where it is printed ...
- 09:20 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Do you take a look at it (or do you have already a fix?) or should I?
The problem is that block_name_prefix in rbd... - 09:08 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Yeah, but I think it's data-dependent; must be max len and not have a zero byte directly after...
- 03:17 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan Mick wrote:
> Why I feel some guilt here: :)
>
> commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
> Author: D... - 03:05 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- I just rebuilt from current git dumpling head on my machine -- cannot reproduce. So I wonder this is something subtle...
- 01:24 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a... - 01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a... - 01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
- So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a 204 even if you atte...
- 11:57 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
- 09:50 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
- ./admin/build-doc runs even if e.g. ditaa or ant isn't installed on the system. The script part checking for the bina...
- 11:31 AM Feature #7192: An easier-to-process health report
- This sounds great to me. I assume we'd keep the 'detail' section as optional as it can get quite (!) big.
- 11:02 AM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 10:46 AM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 10:45 AM Bug #7256 (Duplicate): ceph osd crashed at ReplicatedPG::trim_object on next
- 10:44 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
- 10:06 AM Feature #7662: add a "ec profiles" map to OSDMap
- s/properties/ec profile/g
- 09:24 AM rbd Bug #7693 (Closed): virsh domblkinfo fails with 'Bad file descriptor'
- Found that the 'domblkinfo' command fails while 'domblklist' and 'domblkstat' commands function normally.
## Envir... - 06:35 AM Bug #7692: mon: monitor fails to form quorum
- at first glance, problem has nothing to do with the 0.0.0.0 ip.
This looks like it's early deployment, therefore t... - 06:09 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
- For some reason it is looking at 0.0.0.0 and of course that fails:...
- 01:13 AM CephFS Bug #1318: directories disappear across multiple rsyncs
- please check if there was file recovery involved (MDCache::do_file_recover )
03/11/2014
- 07:30 PM devops Bug #7641 (Fix Under Review): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- It's sort of the other way around. ceph doesn't depend on version of the stuff in ceph-common at all, but ceph-commo...
- 07:24 PM Bug #7689: librados: ENOENT on ioctx create
- downgrading thsi weirdness until i see it again
- 06:05 PM Bug #7689: librados: ENOENT on ioctx create
- actually, no mon_command creating the pool appears in the logs. does not jive with the teuthology log.
- 04:54 PM Bug #7689 (Duplicate): librados: ENOENT on ioctx create
- I think this is a race with pool creation, mon quorum changes, and new client startup getting a not-quite-fresh osdma...
- 07:23 PM rgw Bug #6889 (Pending Backport): rgw: usage log: don't log system user operations
- 09:31 AM rgw Bug #6889 (Fix Under Review): rgw: usage log: don't log system user operations
- 06:22 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:14 PM rgw Bug #7687 (Fix Under Review): rgw: bucket creation time is not set
- 06:09 PM rgw Bug #7687: rgw: bucket creation time is not set
- actually it's set, but then it's overwritten.
- 03:09 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:20 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
- 7635
- 06:19 PM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
- fixed by teuthology commit:57259b54beb746b31b70bb3a92de18d604002b0a
- 06:15 PM Bug #7631 (In Progress): command 'dump_ops_in_flight' not found
- 06:10 PM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
- 05:17 PM Bug #7682 (In Progress): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->fir...
- 12:59 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124761/teutholog...
- 04:41 PM Bug #7688 (Won't Fix): warn at fs/btrfs/extent-tree.c:5748 __btrfs_free_extent+0x9ce/0xa20
- ...
- 04:38 PM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
- 01:01 PM Bug #7663 (Fix Under Review): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10....
- 04:17 PM devops Bug #7617: ceph-deploy uninstall should document why it doesn't remove all relevant packages
- The problem is that qemu-kvm depends on librbd1, and if you remove the latter, that means removing the former. That ...
- 04:11 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Why I feel some guilt here: :)
commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
Author: Dan Mick <dan.mick@inktank... - 04:10 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- True, I don't see any attempt to add a nul. Oddly, it looks like there was half a plan to do so in librbd/internal.c...
- 01:18 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- I'm not current on my c++, but I'm pretty sure Danny's correct. Looking at the code, rbd.cc just does a cout of the 2...
- 01:13 PM rbd Bug #7577: rbd info displays extra random char in block prefix
- Sent this in email, but: u007f sounds like maybe a 0x7f character?.. Which should be legal 7-bit ASCII, but perhaps i...
- 07:22 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Here's a bit more with json format:
{"name":"volume-f529978c-0981-4eba-a5b5-7ba8ecc05e1b","size":5368709120,"objec... - 06:40 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- So this is not a recent regression. I can reproduce on el6.5 with 0.67-0
[root@dvtest1 ceph]# ceph --version
ce... - 06:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Dan van der Ster wrote:
> My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu di... - 06:23 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu difference.
On my ubuntu 0... - 04:11 AM rbd Bug #7577: rbd info displays extra random char in block prefix
- Tried to reproduce, but couldn't. Looks to me like missing '\0' termination. Do you get this from all of your 0.67.7 ...
- 04:05 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
- 01:03 PM Bug #7658 (Fix Under Review): PGLog: _merge_object_divergent_entries: fix the case where prior_ve...
- 04:05 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
- 01:04 PM Bug #7657 (Fix Under Review): PGLog: fix proc_replica_log divergent entry selection
- 03:15 PM rgw Bug #7676 (Fix Under Review): rgw: multi-part upload incompatible with EC backend
- 03:13 PM Bug #7635: failed to recover before timeout expired
- It did eventually recover, as it turns out.
2014-03-06 05:40:41.795123 mon.0 10.214.132.32:6789/0 521 : [INF] pgmap ... - 03:02 PM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
- 12:07 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
- commit:b4fbe4f81348be74c654f3dae1c20a961b99c895 and a later commit fixed feature forwarding, which is needed for the ...
- 12:04 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
- ...
- 10:09 AM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
- ubuntu@teuthology:/a/teuthology-2014-03-10_10:33:21-upgrade:dumpling-x:parallel-firefly---basic-plana/124951
mds r... - 03:00 PM Bug #7686 (Duplicate): osd spinning in agent_work
- 02:37 PM Bug #7686: osd spinning in agent_work
- agent_entry() is hitting a case where there appears to be work to do, but we never evict a hit set archive. In the l...
- 02:08 PM Bug #7686: osd spinning in agent_work
- FYI, this was/is on burnupiX after setting an OSD out and bringing it back in.
- 02:05 PM Bug #7686 (Duplicate): osd spinning in agent_work
- Probably related to the num_dirty/archived hitset issue?
2014-03-11 16:05:15.959964 7fc99340a700 20 osd.0 212 agen... - 02:44 PM devops Feature #7047 (Resolved): rhel7: build process for rbd.ko, ceph.ko kernel modules
- The kmods are built as a part of the Red Hat kmod packaging (#6986) at https://github.com/ceph/ceph-kmod-rpm
Speci... - 02:40 PM Bug #7681: osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 12:52 PM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124677/teuthol...- 02:21 PM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
- 02:21 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
- 09:07 AM rgw Bug #7375: s3_user_quota.pl fails
- 02:20 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
- 09:07 AM rgw Bug #7374: s3_multipart_upload.pl fails
- 02:01 PM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
- 01:59 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
- 01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- I've turned up the timeout in the tests.
- 01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- The non-ec ones are probably just an inadequate timeout -- the cleanup is likely to take longer than the writeout. T...
- 01:57 PM CephFS Bug #7685 (Can't reproduce): hung/failed teuthology test: cfuse_workunit_misc
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_23:00:50-fs-firefly-testing-basic-plana/122094
http://qa-p... - 01:46 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_23:00:25-fs-firefly-testing-basic-plana/124157/
The teut... - 01:37 PM Bug #7093 (Resolved): osd: peering can send messages prior to auth
- Backported to Emperor and Dumpling
- 01:35 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- 01:31 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
- 01:24 PM Bug #5823 (Can't reproduce): cpu load on cluster node is very high, client can't get data on pg ...
- 01:20 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- can you please rerun the monitor with 'debug mon = 10' and attach the resulting log
- 01:20 PM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
- 01:11 PM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
- 01:10 PM Bug #7611 (In Progress): All mon nodes crash when running "ceph tell osd.X" and using the "versio...
- 11:43 AM Bug #7674 (Resolved): Cache pool configuration stalls
- 11:00 AM Bug #7674 (Fix Under Review): Cache pool configuration stalls
- 10:44 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- No, subusers are useful for S3 as well. Maybe this was by accident, but I'm relying on it already in production, for ...
- 09:09 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
- Robin, is that still an issue (considering my previous comment), or should we close this one?
- 10:42 AM rbd Bug #7125: Assertion failure in rbd_img_obj_callback()
- Probably related are:
http://tracker.ceph.com/issues/5876
http://tracker.ceph.com/issues/5662
http://tracker.cep... - 10:29 AM Linux kernel client Bug #7069 (Resolved): CephFS hang when using fscache - several "blocked for more than 120 seconds...
- this is fixed in 8fb883f3e30065529e4f35d4b4f355193dcdb7a2, according to milosz. fixed in kernel 3.13
- 09:48 AM Linux kernel client Bug #7069 (Need More Info): CephFS hang when using fscache - several "blocked for more than 120 s...
- THere are several fscache fixes in the testing branch; perhaps they address this?
- 10:27 AM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 10:18 AM Bug #7592 (Resolved): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7592 (Fix Under Review): hit_set_trim() removal races with backfill
- 10:15 AM rgw Feature #7680 (Resolved): Use new civetweb git repo for ceph
- It seems that the original repo used to fork the ceph civetweb repo from is outdated. The current README on https://g...
- 09:51 AM Linux kernel client Bug #2759: libceph: crush tree algorithm is not understood
- We should be testing CRUSH with multiple algorithms
- 09:44 AM Linux kernel client Bug #2224 (Rejected): Oops in __cfh_to_dentry
- 09:44 AM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
- 09:37 AM rbd Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
- e91fb910653a672560867d4a81aa30f9d5dc0af8
- 09:35 AM rbd Bug #7582 (Resolved): "FAIL: test_rbd.TestImage.test_remove_with_watcher" in upgrade:dumpling-x-f...
- 09:34 AM rbd Bug #7583 (Resolved): "librbd::ImageCtx: error finding header" in upgrade:dumpling-x-firefly---ba...
- 09:33 AM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
- 09:32 AM rbd Bug #6577 (Can't reproduce): arm testing: rbd test segfaults at FAILED assert((bool)_front == (bo...
- 09:21 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
- 09:18 AM rgw Bug #6913 (Duplicate): valgrind issues when running rgw tests
- 09:17 AM rgw Bug #6802 (Rejected): ARM: rgw_swift failure (internal server error, 500)
- 09:17 AM rgw Bug #6696 (Can't reproduce): Upgrade rgw failure in nightly tests. (/home/ubuntu/cephtest/s3-test...
- 09:15 AM rgw Bug #6765 (Rejected): ARM: RGW s3 tests fail.
- 09:13 AM rgw Feature #7589: rgw: configurable chunk size
- Josh - please review wip-7589
- 09:12 AM rgw Feature #7589 (Fix Under Review): rgw: configurable chunk size
- 09:10 AM devops Bug #6453: libapache2-mod-fastcgi Packages for Debian Squeeze have incorrect dependencies
- 09:08 AM rgw Bug #6911: rgw test failure on the arm set up
- this sounds like a 32 bit int (size_t?) overflow
- 09:07 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- 09:06 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
- the mon assert is a dup
- 07:18 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
- This looks like it's the writeback deadlock when trying to flush from the client to the OSD on a single memory-constr...
- 07:17 AM CephFS Bug #6599 (Resolved): client: invalid iterator dereference in Client::trim_caps
- 07:12 AM CephFS Feature #5486: kclient: make it work with selinux
- Hmm, Sage notes that maybe it'll work now we support ACLs. Or maybe we can use a special mount option?
- 07:00 AM CephFS Bug #2187 (Can't reproduce): pjd chown/00.t failed test 97
- 06:59 AM CephFS Bug #2740 (Resolved): mds: crash in Objecter when shutting down too early
03/10/2014
- 05:11 PM Bug #7593: Disk saturation during PG folder splitting
- At a high level, sure, if you know ahead of time how many objects per PG you expect you can pre-hash the PG directori...
- 01:26 AM Bug #7593: Disk saturation during PG folder splitting
- Hi Sage,
If we would like to make the following changes:
# Bring in a new configuration flag which can be used to... - 05:08 PM devops Bug #7677: Troubleshoot ceph-setup-nightly Jenkins failures
- Alfredo - please review.
- 04:57 PM devops Bug #7677 (Fix Under Review): Troubleshoot ceph-setup-nightly Jenkins failures
- Here is the code change to skip the Debian package diffs if they are not present: https://github.com/ceph/ceph-build/...
- 04:55 PM devops Bug #7677 (Resolved): Troubleshoot ceph-setup-nightly Jenkins failures
- h3. Background:
Ceph builds in Jenkins are broken up into three separate jobs: ceph-setup, ceph-build, and ceph-pa... - 05:05 PM devops Tasks #7678 (Resolved): f20 Jenkins slave
- In #7094, we got a new Fedora 20 gitbuilder. We need to add this host to Jenkins as well.
I don't think there are ... - 04:38 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...
- 135c27ec74be352416d06a9d0ad78e63cf477433
- 04:28 PM rgw Bug #7676 (Resolved): rgw: multi-part upload incompatible with EC backend
- multipart upload uses omap on data object. Need to provide a solution for this. Either we switch the data format for ...
- 04:16 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- *wip-doc-prereq* (was "5a811a":https://github.com/ceph/ceph/commit/5a811a0894db2619f5f916c0be85459d0f481265) has been...
- 03:44 PM devops Cleanup #7675 (In Progress): clean up Gary Lowell's WIP branches
- 03:26 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- *wip-build-doc* has been rebased and submitted for merging here: https://github.com/ceph/ceph/pull/1415
- 03:18 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
- For the record, today I've reviewed and deleted the following wip branches from Gary.
*wip-lazy-cuttlefish-gl* (wa... - 03:13 PM devops Cleanup #7675 (Resolved): clean up Gary Lowell's WIP branches
- Gary Lowell had contributed a couple of work-in-progress branches that are still outstanding. Here are the seven that...
- 02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- I believe the error is in the cache pool.
- 02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- [ERR] 4.3 scrub stat mismatch, got 48/48 objects, 0/0 clones, 21/23 dirty, 9/9
We are overestimating dirty now, ... - 02:17 PM Bug #7674: Cache pool configuration stalls
- This was on 0.77-735-gd171418-1saucy which is a couple of days old. I can retest on firefly from today if there have...
- 02:15 PM Bug #7674 (Resolved): Cache pool configuration stalls
- In testing the following cache pool configuration:...
- 02:09 PM Bug #7672: PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 01:32 PM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 02:09 PM Bug #7671: watch should return ENOENT if the object does not exist
- 12:56 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
- Currently, new_obs->exists doesn't get updated, so we create the log entry as a delete which messes everything up.
- 02:08 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
- There are seem to be several of those, so 'major'
- 02:07 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic-plana/1238...
- 12:58 PM CephFS Bug #1318: directories disappear across multiple rsyncs
- By “this” I meant files with different timestamps from what they were last set to, as in the first paragraph of comme...
- 12:51 PM CephFS Bug #1318: directories disappear across multiple rsyncs
- I'm afraid this still occurs quite often with ceph 0.77 and ceph.ko 3.13.6-gnu. I have a slightly better understandi...
- 10:23 AM Bug #7592 (In Progress): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
- 09:40 AM Cleanup #7668: remove custom googletest (gtest) copy from source tree
- I have no expertise here and am down with making this change if it works out better, but when we initially grabbed gt...
- 07:43 AM Cleanup #7668 (Resolved): remove custom googletest (gtest) copy from source tree
- Remove the the potentially outdated gtest code from the source tree to keep it up-to-date:
Needed steps:
- since ... - 09:32 AM devops Bug #7669 (New): obscure traceback when a partition of type TOBE_UUID can't be mounted
- Steps to reproduce:...
- 03:20 AM devops Bug #7605: statup script /etc/init.d/ceph has incorrect slash
- I meant:
the correct line should be:
r = sprintf("%.2f", d) instead of
r = sprintf(\"%.2f\", d) - 02:33 AM Bug #7667 (Resolved): Fix ceph code to build with llvm (clang/clang++)
- Currently the code don't compile with clang++ due to non c++ standard usage of VLAs (http://clang.llvm.org/compatibil...
- 12:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
- Fixing the agent problem did not make the test pass. I don't think the remainder is an agent issue, but haven't looke...
Also available in: Atom