Activity
From 03/16/2015 to 04/14/2015
04/14/2015
- 01:14 PM Bug #6613: samba is crashing in teuthology
https://github.com/ceph/ceph-qa-suite/pull/403
04/13/2015
- 10:34 PM Bug #11053 (Resolved): "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrad...
- Yeah, we're not doing anything with this. I'm confused why cuttlefish is running at all though, since it's pre-dumpli...
- 10:32 PM Bug #11053: "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrade:dumpling-...
- The stack trace appears to be from Cuttlefish, to which the fix wasn't backported.
It's annoying that we would hav... - 09:53 PM Bug #11053 (New): "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrade:dum...
- Still see in
Run: http://pulpito.ceph.com/teuthology-2015-04-10_19:13:01-upgrade:dumpling-x-firefly-distro-basic-vps... - 02:29 PM Bug #6613: samba is crashing in teuthology
- Still happening: http://qa-proxy.ceph.com/teuthology/teuthology-2015-04-08_23:14:01-samba-master-testing-basic-multi/...
- 03:33 AM Bug #11356 (Fix Under Review): failed LibCephFS.MulticlientSimple unit test
04/11/2015
- 02:51 AM Bug #11356: failed LibCephFS.MulticlientSimple unit test
- The issue is in ReplicatedPG::do_xattr_cmp_u64(). For CEPH_OSD_CMPXATTR_MODE_U64, OSD expects the u64 in osd_op be en...
04/10/2015
- 10:16 AM Bug #11300: client-limits and mds-full failures on clog warning/errors
- * hammer backport: https://github.com/ceph/ceph-qa-suite/pull/401
- 08:46 AM Bug #11356: failed LibCephFS.MulticlientSimple unit test
- client log shows client did send read/write request to OSD.2.
The strange thing in OSD log is that 'uninline' oper...
04/09/2015
- 07:42 PM Bug #11356 (Resolved): failed LibCephFS.MulticlientSimple unit test
- http://pulpito.ceph.com/teuthology-2015-04-07_23:04:03-fs-hammer-testing-basic-multi/840725/...
- 01:43 AM Bug #11339 (Fix Under Review): ceph-fuse failing to drop cap on unlinked dir
04/08/2015
- 11:26 PM Bug #10624: hung samba tests after lsof failure
- Also, still showing up: http://pulpito.ceph.com/teuthology-2015-04-01_23:14:02-samba-master-testing-basic-multi/833959/
- 09:06 PM Bug #10624: hung samba tests after lsof failure
- Last time I looked into this, it appeared the Samba gitbuilder wasn't actually using our Ceph samba repo — it's dead....
- 12:55 PM Bug #11316 (Fix Under Review): "ceph-fuse not mounted, got fs type 'ext2/ext3" looping in ceph-de...
Putting the call in to initialize the FS is straightforward, but the because the ceph-deploy task doesn't populate ...- 11:31 AM Bug #11316 (In Progress): "ceph-fuse not mounted, got fs type 'ext2/ext3" looping in ceph-deploy-...
04/07/2015
- 01:19 PM Bug #11339: ceph-fuse failing to drop cap on unlinked dir
- looks like commit 0c6bd2775fe43274e07c5b10586565d6170d8ea9 client: Hold on to exclusive caps on directories we "own"'...
- 10:01 AM Bug #11339 (Resolved): ceph-fuse failing to drop cap on unlinked dir
- Shown up in the test_strays:...
- 01:45 AM Feature #9338 (Resolved): A read timeout argument for cephfs mounts (fuse client especially)
- by commit 485d139015b835ec7038799c51e43f4694e6981f
- 01:32 AM Feature #9557 (Resolved): mds: verify backtrace on fetch_dir
04/03/2015
- 12:55 PM Bug #3935 (Can't reproduce): kclient: Big directory access bugs (multiple), mixed 32- and 64-bit ...
- 09:41 AM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- There no longer are backports to dumpling Unless this problem could cause problems for people upgrading from giant, t...
- 08:24 AM Bug #6741 (Can't reproduce): failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
- 08:20 AM Bug #6613: samba is crashing in teuthology
- need to update our samba repository.
- 08:07 AM Bug #4134: mds: request locking hang under snaptests
- by commit 6cb9b01fb68eeb1449af0d145f31ee813a5316d2
- 07:40 AM Bug #4134 (Resolved): mds: request locking hang under snaptests
- 08:05 AM Bug #4248: mds: replay does not correctly update CInode::first and ::last members
- by commit 1479300a68209688b97c60210b37f330f178819c
- 07:33 AM Bug #4248 (Resolved): mds: replay does not correctly update CInode::first and ::last members
- 07:56 AM Bug #4188 (Can't reproduce): mds crashes when cow-ing entries in formerly snapshotted dir
- 07:48 AM Bug #3439 (Can't reproduce): kernel crash on use of chroot
- 07:48 AM Bug #2179 (Resolved): mds: don't crash on nonexistent SessionMap
- fixed by john' damaged state PR
- 07:45 AM Bug #926 (Resolved): mds: fix rename between snaprealms
- 07:39 AM Bug #3596 (Can't reproduce): ceph-fuse: crash in mds rejoin
- 07:27 AM Bug #1181 (Can't reproduce): mds: old_inodes crash
- 07:25 AM Bug #4213 (Resolved): mds: old_parents is never cleaned up
- fixed by commits 635d79251540aaecea40b40e9ba8bd7f8d3e4731
- 07:15 AM Bug #10624: hung samba tests after lsof failure
- our samba branch is not updated for a long time. could you update it. (I have no write permission to that repository
- 06:33 AM Bug #11120 (Resolved): Bogus layout settings are accepted, crash fuse client
- by commit ad15f7d795c5eb5beb3fe85bb63912524dffbd8f
- 04:38 AM Bug #11316: "ceph-fuse not mounted, got fs type 'ext2/ext3" looping in ceph-deploy-hammer-distro-...
- i think the fs tests are simply broken; ceph now requires that you do a 'ceph fs new ...' command and the ceph-deploy...
- 02:22 AM Bug #10960 (Resolved): Permission/Access errors when using the ceph_vfs from SAMBA (4.x)
- upstreamed by commit 8a1931413210db79fd671535ec4ba289dee7f710
- 01:11 AM Bug #11294 (Need More Info): samba: DISCONNECTED inode warning
04/02/2015
- 09:43 PM Bug #11314: qa: MDS crashed and the runs hung without ever timing out
- This was mentioned in #10369:
> Once we have that checker method, we should also introduce a check that all the da... - 05:25 PM Bug #11314 (Duplicate): qa: MDS crashed and the runs hung without ever timing out
- http://pulpito.ceph.com/gregf-2015-04-01_20:53:07-fs-greg-fs-testing---basic-multi/
The MDS crashed in many of the... - 09:24 PM Bug #11316 (Resolved): "ceph-fuse not mounted, got fs type 'ext2/ext3" looping in ceph-deploy-ham...
- Run: http://pulpito.front.sepia.ceph.com/teuthology-2015-04-02_10:48:18-ceph-deploy-hammer-distro-basic-vps/
Jobs: m... - 12:31 PM Bug #11294: samba: DISCONNECTED inode warning
- One of the FH which does not get released is 0x7f38741050f0. After opened, the FH was used once for ll_flush, but it ...
- 04:06 AM Bug #11294: samba: DISCONNECTED inode warning
- d'oh.
Okay, one of us will need to see if's possible to track this to a problem with ceph-fuse or if Samba is hold... - 03:35 AM Bug #11294: samba: DISCONNECTED inode warning
- In this test case, samba uses ceph-fuse
- 02:31 AM Bug #11258 (Resolved): cephfs-java ftruncate unit test failure
04/01/2015
- 05:49 PM Bug #11301 (Resolved): mds-full test occasionally fails due to blacklist expiry
- This test watches OSDMap epoch carefully and gets upset if it increments unexpectedly. That occasionally happens as ...
- 05:31 PM Bug #11300 (Fix Under Review): client-limits and mds-full failures on clog warning/errors
- * obsolete https://github.com/ceph/ceph-qa-suite/pull/390
- 05:30 PM Bug #11300 (Resolved): client-limits and mds-full failures on clog warning/errors
- http://pulpito.ceph.com/teuthology-2015-03-31_23:04:02-fs-hammer-testing-basic-multi/831003
http://pulpito.ceph.com/... - 12:33 AM Bug #11294: samba: DISCONNECTED inode warning
- Okay, now I'm just confused because it doesn't seem that the Samba VFS is using the ll calls; it's just using ceph_op...
03/31/2015
- 11:14 PM Bug #11294: samba: DISCONNECTED inode warning
- Yeah, we're performing 16383 ll_opens on inode 10000000091, but only getting 9570 ll_release() calls on it. So this l...
- 08:47 PM Bug #11294 (In Progress): samba: DISCONNECTED inode warning
- The Inode thinks it's opened 6814 times for read. That seems implausible; and I notice that it appears to be monotoni...
- 06:11 PM Bug #11294 (Need More Info): samba: DISCONNECTED inode warning
- This is on the hammer branch.
http://pulpito.ceph.com/teuthology-2015-03-29_23:14:01-samba-hammer-testing-basic-mult... - 03:22 PM Bug #11188 (Resolved): CephFS/NFS lockup
- upstreamed by commit a901125c65544aa05c52e1a7388c3900e8af105f
- 01:17 PM Feature #11276 (Fix Under Review): fuse: Handle per-pool FULL flags (such as set by quota limit)
- https://github.com/ceph/ceph/pull/4226
- 07:53 AM Bug #10217 (Resolved): old fuse should warn on flock
- 07:09 AM Bug #11254 (Fix Under Review): getattr from one client stalls indefinitely while another client k...
03/30/2015
- 10:49 PM Bug #10703 (Duplicate): failures in libcephfs-java tests
- #11258.
- 10:49 PM Bug #11258: cephfs-java ftruncate unit test failure
- See also #10703 for more info.
- 08:26 AM Bug #11258 (In Progress): cephfs-java ftruncate unit test failure
- It's a message order issue
- 10:46 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- Is that just commit:6a348ae1870eb4e22a35f4ea86d897fb6d960b88 ("hadoop: fixup for new replication test")?
- 06:09 PM Bug #11277 (Can't reproduce): hung fsstress run under thrash (no useful logs)
- ...
- 05:32 PM Feature #11276 (Resolved): fuse: Handle per-pool FULL flags (such as set by quota limit)
Currently, if a user sets a pool quota on one of their CephFS data pools, and that quota is reached, they don't fin...- 12:59 PM Bug #11048 (Fix Under Review): Session::completed_requests not reliably persisted
- https://github.com/ceph/ceph/pull/4218
- 03:33 AM Bug #10737 (Resolved): ceph-fuse permits layout changes to files with data
- 03:31 AM Bug #11120 (Fix Under Review): Bogus layout settings are accepted, crash fuse client
03/28/2015
- 07:39 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- This should resolve the native library problem on RHEL (tested on plana64/Rhel7). There are still backports needed fo...
- 06:03 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- Merged and marked for backport (to firefly definitely, plus dumpling and giant if we're still running tests against t...
- 02:39 AM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- The JNI bits are landing in /usr/lib64 on RHEL but the qa workunit only has debian paths added to the library search ...
- 12:49 AM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- Greg Farnum wrote:
> Well, here we are on master with a trusty failure. I'm so confused. :(
>
> http://pulpito.ce... - 02:15 AM Bug #11258: cephfs-java ftruncate unit test failure
- I can't reproduce this (re-ran java test suite 100x). The test is:
1. write some data to a file
2. verify fstat r... - 12:48 AM Bug #11258 (Resolved): cephfs-java ftruncate unit test failure
- http://pulpito.ceph.com/teuthology-2015-03-20_23:04:02-fs-master-testing-basic-multi/814833/...
03/27/2015
- 07:58 PM Bug #11255 (Resolved): nfs: mount failures on ceph-backed NFS share
- http://pulpito.ceph.com/teuthology-2015-03-25_23:10:02-knfs-master-testing-basic-multi/822373/...
- 06:48 PM Bug #11226 (Resolved): client: drops Fx cap on directories when revoking other caps
- 06:28 PM Bug #11226: client: drops Fx cap on directories when revoking other caps
- Merged Zheng's patches to master in commit:413da564d4fd479954da7feb5b27b5d8fade1100, and mine in commit:7721b224c4b0d...
- 06:47 PM Bug #11236 (Resolved): lock inversions in test/libcephfs flock test
- 06:26 PM Bug #11236: lock inversions in test/libcephfs flock test
- Merged to master in commit:413da564d4fd479954da7feb5b27b5d8fade1100
- 06:25 PM Bug #11218 (Resolved): Assertion on MDS rank `in` but without instance
- Merged to master in commit:bd1d11f6eb8225c996bfc7ca00a2083cb9423b51
- 06:09 PM Bug #11254: getattr from one client stalls indefinitely while another client keeps modifying file
- This is odd; did you do any digging into it?
There is some special code around getattr to try and make it not tota... - 06:03 PM Bug #11254 (Resolved): getattr from one client stalls indefinitely while another client keeps mod...
Reproduce with two fuse clients on a vstart cluster.
* Mount client A, and do nothing in it initially.
* Moun...- 02:37 AM Bug #11188: CephFS/NFS lockup
- It's a bug in kernel locking code. sent the attached patch to fs-devel
03/26/2015
- 10:09 PM Bug #10861 (Resolved): mysterious wrapped dd failure
- Fixed this in firefly and giant ceph-qa-suite too.
- 03:40 PM Bug #10861: mysterious wrapped dd failure
- dumpling and giant are end of life
- 08:14 PM Bug #10368 (In Progress): Assertion in _trim_expired_segments
- By sheer coincidence, I've hit this issue again, while no journal flushes were running at all, and much more reproduc...
- 04:43 PM Bug #10703: failures in libcephfs-java tests
- giant is end of life
- 01:20 PM Bug #11218 (Fix Under Review): Assertion on MDS rank `in` but without instance
- It turns out it was already find for an MDS to be 'in' but have no inst (it's the case when we do "ceph mds fail"), b...
- 07:25 AM Bug #11236 (Fix Under Review): lock inversions in test/libcephfs flock test
- this failure happens if we do a fork() while ceph is in-use, then open ceph again in child process.
03/25/2015
- 09:15 PM Bug #11236 (Resolved): lock inversions in test/libcephfs flock test
- ...
- 09:12 PM Bug #11226: client: drops Fx cap on directories when revoking other caps
- Also more bugfixes around this from Zheng at https://github.com/ceph/ceph/pull/4177, in greg-fs-testing and queued up...
- 05:41 AM Bug #11146: BUG at /srv/autobuild-ceph/gitbuilder.git/build/fs/ceph/addr.c:1024
- 04:36 AM Bug #10217: old fuse should warn on flock
- hammer backport in commit:e7e0ea626ecca7c74b76099a0c4fc016ca4e410f from pull request https://github.com/ceph/ceph/pul...
- 04:35 AM Bug #11205 (Resolved): "failed (workunit test fs/misc/filelock_interrupt.py)" in powercycle-hamme...
- commit:e7e0ea626ecca7c74b76099a0c4fc016ca4e410f
- 03:13 AM Bug #11205: "failed (workunit test fs/misc/filelock_interrupt.py)" in powercycle-hammer-distro-ba...
- I created a PR for this https://github.com/ceph/ceph/pull/4170
03/24/2015
- 11:25 PM Bug #11205: "failed (workunit test fs/misc/filelock_interrupt.py)" in powercycle-hammer-distro-ba...
- I am rerunning failed jobs on @'testing'@ kernel and they mostly passed.
http://pulpito.front.sepia.ceph.com/teuthol... - 10:18 PM Bug #11226 (Fix Under Review): client: drops Fx cap on directories when revoking other caps
- https://github.com/ceph/ceph/pull/4168
- 10:11 PM Bug #11226: client: drops Fx cap on directories when revoking other caps
- The naive solution is to try and retain the Fx cap on directories at all times, but that has implications for how we ...
- 10:06 PM Bug #11226 (Resolved): client: drops Fx cap on directories when revoking other caps
- An oddity was reported in the thread "MDS has inconsistent performance" on ceph-devel, starting at http://www.spinics...
- 01:45 PM Bug #11218: Assertion on MDS rank `in` but without instance
- Hmm. Do we need to keep the damaged ranks as members of the "up" set, or could we do something simple to remove them ...
- 11:43 AM Bug #11218 (Resolved): Assertion on MDS rank `in` but without instance
Unintended consequence of an MDS in 'damaged' state: a peer in a multi-MDS environment is confused that the MDS is ...
03/23/2015
- 06:18 PM Feature #10390 (Resolved): mds: throttle deletes in flight
- Merged to master in commit:d684da069987603608ce4bfc44035c2749fab6b4. Hurray!
- 05:57 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- Well, here we are on master with a trusty failure. I'm so confused. :(
http://pulpito.ceph.com/teuthology-2015-03-... - 05:22 PM Bug #11205: "failed (workunit test fs/misc/filelock_interrupt.py)" in powercycle-hammer-distro-ba...
- If we cherry-pick commit 4ececa3dc4a21b98f61a592da9e2be60a0d71625 to hammer then this shouldn't fail again. The commi...
- 03:57 PM Bug #11205 (Resolved): "failed (workunit test fs/misc/filelock_interrupt.py)" in powercycle-hamme...
- Run: http://pulpito.front.sepia.ceph.com/teuthology-2015-03-22_09:17:25-powercycle-hammer-distro-basic-multi/
Jobs: ... - 05:22 PM Bug #10217 (Pending Backport): old fuse should warn on flock
- https://github.com/ceph/ceph/pull/3841
- 02:19 PM Bug #11188: CephFS/NFS lockup
- If it's definitely not a CephFS bug we should probably report the failure somewhere?
- 01:46 PM Bug #11188: CephFS/NFS lockup
- looks like a NFSD bug, let's wait for another rc release
- 02:15 PM Bug #11128 (Resolved): "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Both merged!
- 01:43 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- For making NSS work after fork(), https://github.com/ceph/ceph/pull/4098 is enough. For the libcephfs flock test, we ...
- 06:12 AM Bug #10834: SAMBA VFS module: Timestamps revert back to 01-01-1970
- sound like a libcephfs bug. could you please try the newest development version of ceph (just need to update ceph on ...
03/21/2015
- 12:45 AM Bug #10861 (Pending Backport): mysterious wrapped dd failure
- 12:14 AM Bug #10861 (Fix Under Review): mysterious wrapped dd failure
- https://github.com/ceph/ceph-qa-suite/pull/373
03/20/2015
- 11:46 PM Bug #10861: mysterious wrapped dd failure
- 11:46 PM Bug #10861: mysterious wrapped dd failure
- Ahahahahaha. This test is still broken and was writing into ~ubuntu/foo rather than $TESTDIR/mnt.*/foo, because d'oh ...
- 11:05 PM Bug #10834: SAMBA VFS module: Timestamps revert back to 01-01-1970
- My smb.conf is as follows:
[global]
workgroup = DOMAIN
realm = FQDN
netbios name = samba2
server string = Ubun... - 10:54 PM Bug #10834: SAMBA VFS module: Timestamps revert back to 01-01-1970
- yes they do.
- 03:02 AM Bug #10834: SAMBA VFS module: Timestamps revert back to 01-01-1970
- do both of your samba servers have "store dos attributes" option enabled.
- 10:44 PM Fix #11187: ceph-qa-suite: reduce required machine numbers
- That example is from suites/fs/multiclient/cluster/three_clients.yaml
We've also got suites/knfs/basic/clusters/ex... - 10:02 PM Fix #11187 (Resolved): ceph-qa-suite: reduce required machine numbers
- We've got a lot of tests that frequently get stuck because they can't lock their 4 or 5 nodes needed to run. Many of ...
- 10:14 PM Bug #11188 (Resolved): CephFS/NFS lockup
- From http://pulpito.ceph.com/teuthology-2015-03-18_23:10:01-knfs-master-testing-basic-multi/810664/
The first back... - 06:28 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Zheng, do we need to merge any changes besides https://github.com/ceph/ceph/pull/4098 to make this work?
I think i... - 01:16 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- looks like we need to call NSS init function in both parent and child process. calling NSS init function before fork(...
- 08:45 AM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- replacing libcephfs with librados has the same issue.
- 08:20 AM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Simple c++ code to reproduce this issue....
- 07:01 AM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- I can reliably reproduce this locally when configure ceph with "--with-nss --without-cryptopp"
- 05:57 AM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- after applying following patch...
- 06:08 PM Bug #10368: Assertion in _trim_expired_segments
- Agree about backport, but we can be leisurely about it -- nobody's is likely to hit this bug unless they're hitting t...
- 05:53 PM Bug #10368 (Pending Backport): Assertion in _trim_expired_segments
- This certainly needs to go into hammer as well, but I'm not quite brave enough to do an insta-cherry-pick. :)
- 05:13 PM Bug #10368 (Fix Under Review): Assertion in _trim_expired_segments
https://github.com/ceph/ceph/pull/4116- 12:40 PM Bug #10744 (Resolved): MDS gets stuck in 'stopping' when strays exist
- ...
03/19/2015
- 10:36 PM Bug #11053 (Resolved): "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrad...
- These PRs all got merged.
- 09:16 PM Feature #11174 (New): An MDS-specific assert that dumps cache state
- There are a ton of places where we assert certain thing are consistent within the MDCache+MDLog+etc state. Asserting...
- 09:05 PM Bug #11136: cfuse: 0.80.7 client segfault
- Not a deal breaker as we have a cron job to fix the mount if it dies. Just thought I'd throw this up here in case it ...
- 08:43 PM Bug #11136 (Won't Fix): cfuse: 0.80.7 client segfault
- Hmm, the relevant code here is very different in the Hammer release and I don't think it will be susceptible to this ...
- 04:52 PM Bug #11136: cfuse: 0.80.7 client segfault
- Attached.
- 09:01 PM Feature #11173 (New): Client session filtering on 'dump cache' asok
- It would be useful to see the cached state for everything touched by a particular client session -- we should be able...
- 09:00 PM Feature #11172 (Resolved): mds: inode filtering on 'dump cache' asok
- Sometimes we would like to dump the cache state for a known inode number.
- 08:58 PM Feature #11171 (Resolved): Path filtering on "dump cache" asok
- Sometimes we will want to get a detailed dump of the cache for one particular subtree, so implement a mode that will ...
- 01:03 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- found a race https://github.com/ceph/ceph/commit/15d85a6e4a47f241917e6c1becbe90e21309b711. don't know if it's related...
- 12:52 PM Bug #11146 (In Progress): BUG at /srv/autobuild-ceph/gitbuilder.git/build/fs/ceph/addr.c:1024
- 06:07 AM Feature #11161 (New): snapshots: behave better with remote inodes (hard links)
- If we take a snapshot and the SnapRealm includes a remote hard link, the remote inode doesn't get snapshotted. That's...
03/18/2015
- 11:51 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- The mon log has these lines from one run:...
- 10:21 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Right, I forgot some of what we discussed in standup. That exit code is okay because we exit earlier in process_Concu...
- 09:55 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Uh, these two tests both have one of the threads return with "exit(EXIT_FAILURE);", in what looks like the normal pat...
- 09:10 PM Feature #11154 (New): snapshots: support rstats better
- In commit:c173ceafad9310869edb316185bd3a1e9f99e24b we disabled rstat propagation on snapshots because it didn't reall...
- 06:32 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- It passed on hammer on a trusty host: http://pulpito.ceph.com/teuthology-2015-03-17_23:04:02-fs-hammer-testing-basic-...
- 01:44 PM Bug #11146: BUG at /srv/autobuild-ceph/gitbuilder.git/build/fs/ceph/addr.c:1024
- Linux teuthology 3.16.3-ceph-00306-g76c7fd1 #1 SMP Fri Sep 19 04:59:13 UTC 2014 x86_64 x86_64 x86_64 GNU/Linux
- 01:44 PM Bug #11146 (Resolved): BUG at /srv/autobuild-ceph/gitbuilder.git/build/fs/ceph/addr.c:1024
- ...
- 01:41 PM Bug #10417 (Resolved): snaptest-2.sh is failing
- 01:38 PM Bug #11136: cfuse: 0.80.7 client segfault
- Note: I assume it's the dn->dir member that's uninitialized here or something.
- 01:38 PM Bug #11124: MDSMonitor: refuse to do "fs new" on metadata pools containing objects
- John Spray wrote:
> What about checking pool stats in "fs new" and refusing to operate if either the metadata or dat...
03/17/2015
- 11:27 PM Bug #11136: cfuse: 0.80.7 client segfault
- If you have log files on these nodes, they should contain a bit more information following the crash. Can you upload ...
- 08:16 PM Bug #11136 (Won't Fix): cfuse: 0.80.7 client segfault
- I don't know what other information I can provide other than to say that occasionally some of our clients segfault wi...
- 07:07 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- I haven't looked at the code, but if I were to guess it's fork()ing at a bad time and so hitting authentication issue...
- 03:31 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Sorry, my RP does not work. the failure of "ceph_mount(cmount, __null)" is caused by authentication error. I have no ...
- 02:13 PM Bug #10863: java.lang.UnsatisfiedLinkError: cephfs_jni (Not found in java.library.path) on RHEL7
- Okay, this bug has revived itself on master as well: http://qa-proxy.ceph.com/teuthology/teuthology-2015-03-16_23:04:...
03/16/2015
- 10:42 PM Bug #11128: "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- It looks to me like these tests haven't passed since they were merged. :/ Zheng, please check out the failures!
My... - 09:54 PM Bug #11128 (Resolved): "[ FAILED ] LibCephFS".* tests in smoke-master-distro-basic-multi
- Run: http://pulpito.ceph.com/teuthology-2015-03-14_02:35:02-smoke-master-distro-basic-multi/
Job: 803964
Logs: http... - 10:22 PM Bug #9994: ceph-qa-suite: nfs mount timeouts
- Still happening, http://qa-proxy.ceph.com/teuthology/teuthology-2015-03-11_23:10:01-knfs-master-testing-basic-multi/8...
- 07:01 PM Bug #11124: MDSMonitor: refuse to do "fs new" on metadata pools containing objects
- What about checking pool stats in "fs new" and refusing to operate if either the metadata or data pools already conta...
- 06:24 PM Bug #11124 (Resolved): MDSMonitor: refuse to do "fs new" on metadata pools containing objects
- #11073 involves a user having old FS objects around after running "fs new" and things going horribly wrong. We need t...
- 06:42 PM Support #11073: mds crashing and loop restart
- The monitor fix was backported for v0.87.1, but that doesn't appear to have been at play here anyway (see previous me...
- 06:34 PM Support #11073: mds crashing and loop restart
- Best guess of what's happening here is that an "fs new" was run, the MDSs came up and created a new inotable in which...
- 06:28 PM Support #11073 (Resolved): mds crashing and loop restart
- Okay, that sounds correct. When creating a new FS you need to really mean a new filesystem — it recreates a bunch of ...
- 06:24 PM Support #11073: mds crashing and loop restart
- yes I'm using all 0.87.1 version.
I ended up restarting the whole cluster then deleting my cephfs to create a new on... - 06:21 PM Support #11073: mds crashing and loop restart
- So you had an existing CephFS install and then ran "ceph fs new" without deleting the old one on the monitor, not rem...
- 05:42 PM Bug #11053: "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrade:dumpling-...
- * firefly backport https://github.com/ceph/ceph/pull/3970
* giant backport https://github.com/ceph/ceph/pull/3971
*... - 05:41 PM Bug #11053: "FAILED assert(beacon_seq_stamp[seq] > beacon_last_acked_stamp)" in upgrade:dumpling-...
- 04:58 PM Bug #11120 (Resolved): Bogus layout settings are accepted, crash fuse client
Reproduce:...
Also available in: Atom