Activity
From 06/17/2018 to 07/16/2018
07/16/2018
- 06:17 PM Cleanup #24820 (Fix Under Review): overhead of g_conf->get_val<type>("config name") is high
- https://github.com/ceph/ceph/pull/23045/commits/82fd27f73f790e7fd39917974b283fa13678918a
- 04:00 PM Backport #24254: mimic: kceph: umount on evicted client blocks forever
- Fixing PR
- 04:00 PM Backport #24255: mimic: qa: kernel_mount.py umount must handle timeout arg
- fixing PR
- 01:43 PM Bug #24893 (Fix Under Review): client: add ceph_ll_fallocate
- https://github.com/ceph/ceph/pull/23009
- 08:40 AM Backport #24934 (Resolved): luminous: cephfs-journal-tool: wrong layout info used
- https://github.com/ceph/ceph/pull/24033
- 08:40 AM Backport #24933 (Resolved): mimic: cephfs-journal-tool: wrong layout info used
- https://github.com/ceph/ceph/pull/24583
- 08:40 AM Backport #24932 (Resolved): luminous: client: put instance/addr information in status asok command
- https://github.com/ceph/ceph/pull/23107
- 08:40 AM Backport #24931 (Resolved): mimic: client: put instance/addr information in status asok command
- https://github.com/ceph/ceph/pull/23109
- 08:39 AM Backport #24930 (Rejected): jewel: client: put instance/addr information in status asok command
- 08:39 AM Backport #24929 (Resolved): luminous: qa: test_recovery_pool tries asok on wrong node
- https://github.com/ceph/ceph/pull/25569
- 08:39 AM Backport #24928 (Resolved): mimic: qa: test_recovery_pool tries asok on wrong node
- https://github.com/ceph/ceph/pull/23087
- 12:50 AM Bug #24855 (Fix Under Review): mds: reduce debugging for missing inodes during subtree migration
- https://github.com/ceph/ceph/pull/23063
07/15/2018
- 11:58 PM Bug #24853 (Fix Under Review): mds: dump recent (memory) log messages before respawning due to be...
- https://github.com/ceph/ceph/pull/23062
- 11:12 PM Bug #24852 (Fix Under Review): mds: dump MDSMap epoch to log at low debug
- https://github.com/ceph/ceph/pull/23061
- 10:07 PM Bug #24644 (Pending Backport): cephfs-journal-tool: wrong layout info used
- 10:05 PM Feature #24643 (Resolved): libcephfs: add ceph_futimens support
- 10:04 PM Feature #24724 (Pending Backport): client: put instance/addr information in status asok command
- 08:29 PM Bug #24925 (Rejected): qa: pjd test failed ctime change unexpected result
- ...
07/14/2018
- 05:19 PM Bug #24823: mds: deadlock when setting config value via admin socket
- Zheng Yan wrote:
> how about making md_config_impl release its lock when changing handle_conf_change
+1 - 07:40 AM Bug #24823: mds: deadlock when setting config value via admin socket
- how about making md_config_impl release its lock when changing handle_conf_change
- 01:21 AM Bug #24823: mds: deadlock when setting config value via admin socket
- Venky Shankar wrote:
> Patrick/Zheng,
>
> I'm thinking if we could probably make use of Zheng's changes for track... - 01:17 AM Bug #24858 (Pending Backport): qa: test_recovery_pool tries asok on wrong node
- 12:10 AM Bug #24870 (Fix Under Review): ceph-debug-docker: python3 libraries not installed in docker image
- https://github.com/ceph/ceph/pull/23040
07/13/2018
- 09:09 PM Backport #24912 (New): luminous: qa: multifs requires 4 mds but gets only 2
- 09:08 PM Backport #24912 (In Progress): luminous: qa: multifs requires 4 mds but gets only 2
- 09:00 PM Backport #24912 (Resolved): luminous: qa: multifs requires 4 mds but gets only 2
- https://github.com/ceph/ceph/pull/24328
v12.2.11 follow-up fix: https://github.com/ceph/ceph/pull/25890 - 09:09 PM Backport #24913 (In Progress): mimic: qa: multifs requires 4 mds but gets only 2
- 09:00 PM Backport #24913 (Resolved): mimic: qa: multifs requires 4 mds but gets only 2
- https://github.com/ceph/ceph/pull/22835
- 09:05 PM Backport #24759: luminous: test gets ENOSPC from bluestore block device
- Needs #24912 with backport.
- 09:01 PM Backport #24914 (Resolved): mimic: mon: prevent older/incompatible clients from mounting the file...
- https://github.com/ceph/ceph/pull/23105
- 09:00 PM Bug #24899 (Pending Backport): qa: multifs requires 4 mds but gets only 2
- 04:37 AM Bug #24899 (Fix Under Review): qa: multifs requires 4 mds but gets only 2
- https://github.com/ceph/ceph/pull/23018
- 04:34 AM Bug #24899 (Resolved): qa: multifs requires 4 mds but gets only 2
- http://pulpito.ceph.com/pdonnell-2018-07-12_18:01:13-fs-wip-pdonnell-testing-20180712.152150-distro-basic-smithi/2771...
- 08:57 PM Feature #14456 (Pending Backport): mon: prevent older/incompatible clients from mounting the file...
- 05:05 PM Cleanup #24839: qa: move mds/client config to qa from teuthology ceph.conf.template
- Nathan Cutler wrote:
> @Patrick: this is not straightforward to backport, and at first glance it looks like a cleanu... - 02:45 PM Cleanup #24839: qa: move mds/client config to qa from teuthology ceph.conf.template
- @Patrick: this is not straightforward to backport, and at first glance it looks like a cleanup/refactor. What is the ...
- 02:46 PM Backport #24904 (In Progress): mimic: qa: client socket inaccessible without sudo
- 10:44 AM Backport #24904 (Resolved): mimic: qa: client socket inaccessible without sudo
- https://github.com/ceph/ceph/pull/23030
- 10:56 AM Bug #20593: mds: the number of inode showed by "mds perf dump" not correct after trimming
- Sorry, should have used the PR#16232 merge commit....
- 10:54 AM Bug #20593 (Resolved): mds: the number of inode showed by "mds perf dump" not correct after trimm...
- Master commit was included in the initial luminous v12.2.0 release:...
- 10:55 AM Backport #23642: luminous: mds: the number of inode showed by "mds perf dump" not correct after t...
- Sorry, should have used the merge commit....
- 10:53 AM Backport #23642 (Rejected): luminous: mds: the number of inode showed by "mds perf dump" not corr...
- Master commit was included in the initial luminous v12.2.0 release:...
- 10:47 AM Backport #23642: luminous: mds: the number of inode showed by "mds perf dump" not correct after t...
- Looks like it has already been backported. I can see the commit "MDS: update the mlogger of mds in function check_mem...
- 08:54 AM Bug #24879 (Fix Under Review): mds: create health warning if we detect metadata (journal) writes ...
- 08:54 AM Bug #24879: mds: create health warning if we detect metadata (journal) writes are slow
- https://github.com/ceph/ceph/pull/23022
- 07:44 AM Bug #24900 (Rejected): fs: ceph.file.layout.stripe_count changed after modification
- first i touch en empty file.
> touch /nas/cephfs/zyli.txt
then
> setfattr -n ceph.file.layout.stripe_count -v ... - 04:38 AM Bug #24872 (Pending Backport): qa: client socket inaccessible without sudo
- 02:13 AM Bug #24897 (Rejected): client: writes rejected by quota may truncate/zero parts of file
- I found a BUg as below:
First:setfattr -n ceph.quota.max_bytes -v 5 /nas/cephfs/abc
Second:echo "abc" > /nas/ceph...
07/12/2018
- 11:59 PM Feature #24725 (Fix Under Review): mds: propagate rstats from the leaf dirs up to the specified d...
- 07:46 PM Backport #24190 (In Progress): luminous: fs: reduce number of helper debug messages at level 5 fo...
- 07:45 PM Backport #24136 (In Progress): luminous: MDSMonitor: uncommitted state exposed to clients/mdss
- 07:42 PM Backport #23790 (In Progress): luminous: mds: crash during shutdown_pass
- 07:33 PM Documentation #23427 (Resolved): doc: create doc outlining steps to bring down cluster
- 07:33 PM Backport #23669 (Resolved): luminous: doc: create doc outlining steps to bring down cluster
- 07:30 PM Backport #23642: luminous: mds: the number of inode showed by "mds perf dump" not correct after t...
- Rishabh, please do this backport.
- 07:28 PM Bug #21765 (Resolved): auth|doc: fs authorize error for existing credentials confusing/unclear
- 07:28 PM Backport #23641 (Resolved): luminous: auth|doc: fs authorize error for existing credentials confu...
- 07:25 PM Backport #23015 (In Progress): luminous: client: coredump when nfs-ganesha use ceph_ll_get_inode()
- 07:17 PM Backport #22504: luminous: client may fail to trim as many caps as MDS asked for
- Zheng, please do this backport.
- 07:11 PM Bug #24894 (Resolved): client: allow overwrites to files with size greater than the max_file_size...
- It's confusing to not allow overwrites as the file size is not **further** increasing beyond the limit (which it alre...
- 07:00 PM Feature #24643: libcephfs: add ceph_futimens support
- Jeff Layton wrote:
> I don't think we need this at all. We have a ceph_fsetattrx call which is a superset of all the... - 05:40 PM Feature #24643: libcephfs: add ceph_futimens support
- I don't think we need this at all. We have a ceph_fsetattrx call which is a superset of all the futimes/lutimes calls.
- 06:06 PM Bug #24893 (Resolved): client: add ceph_ll_fallocate
- We have a ceph_fallocate command, but we need an analogous ceph_ll_fallocate command for ganesha. Add a trivial wrapper.
- 10:44 AM Backport #24296 (Resolved): mimic: repeated eviction of idle client until some IO happens
- 10:43 AM Backport #24703 (Resolved): mimic: PurgeQueue sometimes ignores Journaler errors
- 10:42 AM Backport #24537 (Resolved): mimic: common/DecayCounter: set last_decay to current time when decod...
- 10:42 AM Backport #24704 (Resolved): mimic: mds: low wrlock efficiency due to dirfrags traversal
- 10:40 AM Bug #24308 (Resolved): mon: mds health metrics sent to cluster log indpeendently
- 10:39 AM Backport #24330 (Resolved): mimic: mon: mds health metrics sent to cluster log indpeendently
- 10:26 AM Bug #24823: mds: deadlock when setting config value via admin socket
- Patrick/Zheng,
I'm thinking if we could probably make use of Zheng's changes for tracker https://tracker.ceph.com/... - 09:54 AM Feature #24880: pybind/mgr/volumes: restore from snapshot
- I just checked who wrote that "TODO" comment, and it turns out it was me, even though I have no memory of it :-)
I... - 03:17 AM Feature #24880 (Resolved): pybind/mgr/volumes: restore from snapshot
- Old description:
Manila's cephfs driver does not support recovering data from snapshots,The driver uses the ceph_v... - 03:31 AM Bug #24881 (Fix Under Review): unhealthy heartbeat map during subtree migration
- https://github.com/ceph/ceph/pull/22999
- 03:26 AM Bug #24881 (Duplicate): unhealthy heartbeat map during subtree migration
- 02:32 AM Feature #22446: mds: ask idle client to trim more caps
- Rishabh Dave wrote:
> Can I get few implementation specific details to get started working on this issue?
Copying... - 02:26 AM Bug #24867: ceph.file.layout can not set by setfattr
- Patrick Donnelly wrote:
> yuanli zhu wrote:
> > I already know the mistake,the file I set has non-zero size,But i a... - 02:18 AM Bug #24867: ceph.file.layout can not set by setfattr
- yuanli zhu wrote:
> I already know the mistake,the file I set has non-zero size,But i also want to set the non-zero ... - 01:45 AM Bug #24867: ceph.file.layout can not set by setfattr
- I already know the mistake,the file I set has non-zero size,But i also want to set the non-zero size file.I want to d...
- 12:59 AM Bug #24867 (Need More Info): ceph.file.layout can not set by setfattr
- Is the file empty? You cannot set the layout on a file that has non-zero size.
- 02:15 AM Bug #23332 (Closed): kclient: with fstab entry is not coming up reboot
- Closing this as it's a consequence of #24879.
- 02:14 AM Bug #24879 (Resolved): mds: create health warning if we detect metadata (journal) writes are slow
- This can have wide-ranging effects including session establishment taking a long time (sessions are journaled). Let's...
07/11/2018
- 11:25 PM Backport #24296: mimic: repeated eviction of idle client until some IO happens
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22550
merged - 11:25 PM Backport #24703: mimic: PurgeQueue sometimes ignores Journaler errors
- Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/22810
merged - 11:24 PM Backport #24537: mimic: common/DecayCounter: set last_decay to current time when decoding decay c...
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22816
merged - 11:24 PM Backport #24704: mimic: mds: low wrlock efficiency due to dirfrags traversal
- Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/22884
merged - 08:17 PM Backport #24330: mimic: mon: mds health metrics sent to cluster log indpeendently
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22265
merged - 07:58 PM Documentation #22989 (In Progress): doc: add documentation for MDS states
- WIP: https://github.com/ceph/ceph/pull/22996
- 06:29 PM Bug #24872 (Fix Under Review): qa: client socket inaccessible without sudo
- https://github.com/ceph/ceph/pull/22995
- 06:27 PM Bug #24872 (Resolved): qa: client socket inaccessible without sudo
- https://github.com/ceph/ceph/blob/5688476513a78cf9ab2cf3b1f65e6244f05ea73d/qa/tasks/cephfs/fuse_mount.py#L377
glob... - 02:51 PM Bug #24819 (Resolved): "terminate called after throwing an instance of 'ceph::buffer::malformed_i...
- the bug is in master only, no backports needed.
- 04:25 AM Bug #24819 (Fix Under Review): "terminate called after throwing an instance of 'ceph::buffer::mal...
- Sage already pushed a PR for this: https://github.com/ceph/ceph/pull/22968
- 02:35 PM Bug #24870 (Resolved): ceph-debug-docker: python3 libraries not installed in docker image
- ceph_volume_client can not be imported using python3 interpreter on the container built by src/script/ceph-debug-dock...
- 01:44 PM Feature #24444 (In Progress): cephfs: make InodeStat, DirStat, LeaseStat versioned
- 06:27 AM Backport #24862 (New): luminous: ceph_volume_client: allow atomic update of RADOS objects
- 06:13 AM Backport #24862 (In Progress): luminous: ceph_volume_client: allow atomic update of RADOS objects
- 06:22 AM Backport #24860 (In Progress): luminous: cephfs-journal-tool: Importing a zero-length purge_queue...
- 06:18 AM Backport #24861 (In Progress): mimic: cephfs-journal-tool: Importing a zero-length purge_queue jo...
- 05:40 AM Bug #24868 (Resolved): doc: Incomplete Kernel mount debugging
- 1. http://docs.ceph.com/docs/master/cephfs/troubleshooting/#kernel-mount-debugging seems incomplete.
2. http://docs.... - 05:18 AM Bug #24849: client: statfs inode count odd
- How about setting...
- 03:47 AM Bug #24856 (Fix Under Review): mds may get discontinuous mdsmap
- https://github.com/ceph/ceph/pull/22977
- 03:34 AM Bug #24867: ceph.file.layout can not set by setfattr
- How to remove this restriction
- 03:33 AM Bug #24867: ceph.file.layout can not set by setfattr
- When the layout fields of a file are modified using setfattr, this file must be empty, otherwise an error will occur....
- 02:44 AM Bug #24867 (Need More Info): ceph.file.layout can not set by setfattr
- I can get the ceph.file.layout by using getfattr.
[root@node1 ~]# getfattr -n ceph.file.layout /nas/cephfs/test.tx...
07/10/2018
- 08:29 PM Backport #24863 (Resolved): mimic: ceph_volume_client: allow atomic update of RADOS objects
- https://github.com/ceph/ceph/pull/23878
- 08:29 PM Backport #24862 (Resolved): luminous: ceph_volume_client: allow atomic update of RADOS objects
- https://github.com/ceph/ceph/pull/24084
- 08:29 PM Backport #24861 (Resolved): mimic: cephfs-journal-tool: Importing a zero-length purge_queue journ...
- https://github.com/ceph/ceph/pull/22981
- 08:29 PM Backport #24860 (Resolved): luminous: cephfs-journal-tool: Importing a zero-length purge_queue jo...
- https://github.com/ceph/ceph/pull/22980
- 08:26 PM Bug #24239 (Pending Backport): cephfs-journal-tool: Importing a zero-length purge_queue journal b...
- 08:26 PM Bug #24173 (Pending Backport): ceph_volume_client: allow atomic update of RADOS objects
- 08:25 PM Feature #24465 (Resolved): client: allow client to leave state intact on MDS when tearing down ob...
- 08:18 PM Bug #24858 (Fix Under Review): qa: test_recovery_pool tries asok on wrong node
- https://github.com/ceph/ceph/pull/22971
- 08:06 PM Bug #24858 (Resolved): qa: test_recovery_pool tries asok on wrong node
- https://github.com/ceph/ceph/blob/fdb1e142c17d84f40232a8e739f344fb607ca15a/qa/tasks/cephfs/test_recovery_pool.py#L196...
- 02:11 PM Bug #24856 (Resolved): mds may get discontinuous mdsmap
- steps to reproduce. two active mds, no standby
- gdb attach mds.0, wait until 'ceph -w' shows it's laggy
- restar... - 02:05 PM Bug #24855 (Resolved): mds: reduce debugging for missing inodes during subtree migration
- We often see:...
- 02:01 PM Feature #24854 (New): mds: if MDS fails internal heartbeat, then debugging should be increased to...
- This should incrementally increase to 20 as the timeout reaches mds_beacon_grace.
- 01:53 PM Bug #24853 (Resolved): mds: dump recent (memory) log messages before respawning due to being remo...
- If the MDS has been stuck working on something and consequently gets removed from the MDSMap, we'd like to know what ...
- 01:50 PM Bug #24852 (Resolved): mds: dump MDSMap epoch to log at low debug
- Production deployments use low debugging but it'd be useful to always know what MDSMap epoch the MDS is currently pro...
- 12:22 PM Bug #24849: client: statfs inode count odd
- We set f_ffree to -1 because it's not meaningful (unlike e.g. ext4, we don't really have an inode limit other than th...
- 11:34 AM Bug #24849 (Resolved): client: statfs inode count odd
- Hi,
We noticed that df -i on our cehpfs was a bit odd:... - 12:15 PM Bug #23262: kclient: nofail option not supported
- We are running the latest util-linux of centos 7.5, util-linux-2.23.2-52.el7.x86_64.
If we mount another fs type wi... - 11:18 AM Backport #23641 (In Progress): luminous: auth|doc: fs authorize error for existing credentials co...
- 04:49 AM Backport #24829 (In Progress): mimic: qa: iogen.sh: line 7: cd: too many arguments
- 04:00 AM Backport #24842 (Resolved): luminous: qa: move mds/client config to qa from teuthology ceph.conf....
- https://github.com/ceph/ceph/pull/23877
- 04:00 AM Backport #24841 (Resolved): mimic: qa: move mds/client config to qa from teuthology ceph.conf.tem...
- https://github.com/ceph/ceph/pull/23659
- 03:59 AM Bug #24138 (Resolved): qa: support picking a random distro using new teuthology $
- 03:59 AM Backport #24706 (Resolved): mimic: qa: support picking a random distro using new teuthology $
- 03:58 AM Backport #24534 (Resolved): mimic: client: _ll_drop_pins travel inode_map may access invalid ‘nex...
- 03:57 AM Backport #24539 (Resolved): mimic: multimds pjd open test fails
- 03:57 AM Bug #24240 (Resolved): qa: 1 mutations had unexpected outcomes
- 03:56 AM Backport #24541 (Resolved): mimic: qa: 1 mutations had unexpected outcomes
- 03:56 AM Backport #24310 (Resolved): mimic: pjd: cd: too many arguments
- 03:42 AM Backport #24828 (In Progress): luminous: qa: iogen.sh: line 7: cd: too many arguments
07/09/2018
- 08:31 PM Backport #24706: mimic: qa: support picking a random distro using new teuthology $
- Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/22700
merged - 08:28 PM Backport #24534: mimic: client: _ll_drop_pins travel inode_map may access invalid ‘next’ iterator
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22791
merged - 08:28 PM Backport #24539: mimic: multimds pjd open test fails
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22819
merged - 08:27 PM Backport #24541: mimic: qa: 1 mutations had unexpected outcomes
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22841
merged - 08:26 PM Backport #24310: mimic: pjd: cd: too many arguments
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22882
merged - 08:14 PM Bug #24840 (Resolved): mds: explain delayed client_request due to subtree migration
- Presently you will see messages like:...
- 04:55 PM Cleanup #24839 (Resolved): qa: move mds/client config to qa from teuthology ceph.conf.template
- https://github.com/ceph/ceph/pull/22740
- 02:08 PM Bug #24730 (Duplicate): Client::_invalidate_kernel_dcache causes NFS lookup “deleted” dentry
- 01:37 PM Bug #24730 (Closed): Client::_invalidate_kernel_dcache causes NFS lookup “deleted” dentry
- 01:54 PM Cleanup #24820: overhead of g_conf->get_val<type>("config name") is high
- Idea for fix is to use cache variable where hot paths use get_val. Example:
https://github.com/ceph/ceph/blob/9755... - 01:50 PM Bug #24802: races with nfs-ganesha reboots and delegation handling
- The right fix here is probably to push forward with end-to-end ceph client reclaim. The main problem is that there is...
- 01:40 PM Bug #24732 (Rejected): lsattr is not usefull for ceph-fuse
- ceph-fuse/FUSE(?) doesn't support flags for the inode to support lsattr? Closing this.
- 01:21 PM Backport #24829 (Resolved): mimic: qa: iogen.sh: line 7: cd: too many arguments
- https://github.com/ceph/ceph/pull/22956
- 01:21 PM Backport #24828 (Resolved): luminous: qa: iogen.sh: line 7: cd: too many arguments
- https://github.com/ceph/ceph/pull/22955
- 10:14 AM Bug #24823 (Resolved): mds: deadlock when setting config value via admin socket
- I hit the below deadlock while working on a PR which introduced a configuration option for MDS. The problem is with h...
- 07:06 AM Bug #23958 (Fix Under Review): mds: scrub doesn't always return JSON results
- PR https://github.com/ceph/ceph/pull/22947
- 04:07 AM Bug #24680 (Pending Backport): qa: iogen.sh: line 7: cd: too many arguments
07/08/2018
- 08:15 AM Cleanup #24820: overhead of g_conf->get_val<type>("config name") is high
- !http://tracker.ceph.com/attachments/download/3540/Screen%20Shot%202018-07-08%20at%2016.13.15.png!
- 08:14 AM Cleanup #24820 (Resolved): overhead of g_conf->get_val<type>("config name") is high
07/07/2018
- 03:22 PM Bug #24819 (Resolved): "terminate called after throwing an instance of 'ceph::buffer::malformed_i...
- Run: http://pulpito.ceph.com/teuthology-2018-07-07_02:25:03-upgrade:luminous-x-master-distro-basic-smithi/
Jobs: ['2...
07/06/2018
- 10:51 PM Feature #17230: ceph_volume_client: py3 compatible
- Note: I've deleted the backport issues as this hasn't been merged to master yet.
- 06:07 PM Bug #24802 (New): races with nfs-ganesha reboots and delegation handling
- So I've come up with a thought experiment that I think could be problematic for ganesha with delegations enabled. Thi...
07/05/2018
- 07:57 PM Backport #24696 (In Progress): luminous: mds: low wrlock efficiency due to dirfrags traversal
- 07:50 PM Backport #24704 (In Progress): mimic: mds: low wrlock efficiency due to dirfrags traversal
- 07:38 PM Backport #24311 (In Progress): luminous: pjd: cd: too many arguments
- 07:37 PM Backport #24310 (In Progress): mimic: pjd: cd: too many arguments
- 01:28 PM Bug #24780 (Resolved): Some cephfs tool commands silently operate on only rank 0, even if multipl...
I think this is biting people, e.g. in thread "[ceph-users] CephFS - How to handle "loaded dup inode" errors"
We...- 11:47 AM Backport #23669 (In Progress): luminous: doc: create doc outlining steps to bring down cluster
07/04/2018
- 01:46 PM Documentation #24726 (Resolved): Documentation about CephFS snapshots in experimental features is...
- 01:44 PM Backport #24746 (Resolved): mimic: doc: Documentation about CephFS snapshots in experimental feat...
- 09:51 AM Feature #24604: Implement "cephfs-journal-tool event splice" equivalent for purge queue
- https://github.com/ceph/ceph/pull/22850
- 09:47 AM Cleanup #24745: Spurious empty files in CephFS root pool when multiple pools associated
- (see discussion on thread "[ceph-users] Spurious empty files in CephFS root pool when multiple pools associated")
... - 09:25 AM Backport #24759 (Need More Info): luminous: test gets ENOSPC from bluestore block device
- Wait until mimic backport https://github.com/ceph/ceph/pull/22835 is merged and use its minimal version of https://gi...
- 02:21 AM Backport #24541 (In Progress): mimic: qa: 1 mutations had unexpected outcomes
- https://github.com/ceph/ceph/pull/22841
07/03/2018
- 04:22 PM Backport #24758 (In Progress): mimic: test gets ENOSPC from bluestore block device
- 04:12 PM Backport #24758 (Resolved): mimic: test gets ENOSPC from bluestore block device
- https://github.com/ceph/ceph/pull/22835
- 04:12 PM Backport #24759 (Resolved): luminous: test gets ENOSPC from bluestore block device
- https://github.com/ceph/ceph/pull/24924
- 04:11 PM Bug #24238 (Pending Backport): test gets ENOSPC from bluestore block device
- 11:12 AM Backport #24718 (In Progress): luminous: client: returning garbage (?) for readdir
- 11:11 AM Backport #24719 (In Progress): mimic: client: returning garbage (?) for readdir
- 11:01 AM Backport #24539 (In Progress): mimic: multimds pjd open test fails
- https://github.com/ceph/ceph/pull/22819
- 10:58 AM Backport #24537 (In Progress): mimic: common/DecayCounter: set last_decay to current time when de...
- https://github.com/ceph/ceph/pull/22816
- 10:37 AM Backport #24705 (In Progress): mimic: cephfs: allow prohibiting user snapshots in CephFS
- 10:20 AM Backport #24716 (Resolved): mimic: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-s...
- 10:16 AM Backport #24694 (In Progress): luminous: PurgeQueue sometimes ignores Journaler errors
- 10:15 AM Backport #24703 (In Progress): mimic: PurgeQueue sometimes ignores Journaler errors
- 08:45 AM Bug #24512: Raw used space leak
- Unfortunately, I have now to use the disks for production...
Here follow the last tests with smaller pools, which ... - 03:58 AM Backport #24746 (In Progress): mimic: doc: Documentation about CephFS snapshots in experimental f...
- 03:08 AM Backport #24746 (Resolved): mimic: doc: Documentation about CephFS snapshots in experimental feat...
- https://github.com/ceph/ceph/pull/22803
07/02/2018
- 09:48 PM Cleanup #24745 (Won't Fix): Spurious empty files in CephFS root pool when multiple pools associated
- Hi there.
I have an issue with cephfs and multiple datapools inside. I have like SIX datapools inside the cephfs, ... - 09:38 PM Feature #24724 (Fix Under Review): client: put instance/addr information in status asok command
- https://github.com/ceph/ceph/pull/22801
- 07:28 PM Documentation #24642 (New): doc: visibility semantics to other clients
- Niklas Hambuechen wrote:
> I have upgraded to Mimic now and will check out if I see three minute delays again.
>
... - 04:52 PM Documentation #24726 (Pending Backport): Documentation about CephFS snapshots in experimental fea...
- https://github.com/ceph/ceph/pull/22656
- 04:51 PM Backport #24716: mimic: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- Abhishek Lekshmanan wrote:
> https://github.com/ceph/ceph/pull/22775
merged - 01:52 PM Bug #24732 (Rejected): lsattr is not usefull for ceph-fuse
- lsattr is not usefull for ceph-fuse
- 01:48 PM Bug #24730: Client::_invalidate_kernel_dcache causes NFS lookup “deleted” dentry
- dup of http://tracker.ceph.com/issues/21423
- 01:46 PM Bug #24730: Client::_invalidate_kernel_dcache causes NFS lookup “deleted” dentry
- set client_try_dentry_invalidate config of ceph-fuse to false
- 12:49 PM Bug #24730 (Duplicate): Client::_invalidate_kernel_dcache causes NFS lookup “deleted” dentry
- We exported an NFS directory via a mounted ceph-fuse directory named "testshawn", and then started a write/read task ...
- 11:41 AM Backport #24534: mimic: client: _ll_drop_pins travel inode_map may access invalid ‘next’ iterator
- 07:16 AM Backport #24534 (In Progress): mimic: client: _ll_drop_pins travel inode_map may access invalid ‘...
- https://github.com/ceph/ceph/pull/22791
- 11:40 AM Backport #24535 (In Progress): luminous: client: _ll_drop_pins travel inode_map may access invali...
- https://github.com/ceph/ceph/pull/22786
- 03:09 AM Backport #24540 (In Progress): luminous: multimds pjd open test fails
- https://github.com/ceph/ceph/pull/22783
- 02:32 AM Backport #23989 (In Progress): luminous: mds: don't report slow request for blocked filelock request
- https://github.com/ceph/ceph/pull/22782
07/01/2018
- 08:54 PM Documentation #24726 (Resolved): Documentation about CephFS snapshots in experimental features is...
- http://docs.ceph.com/docs/mimic/cephfs/experimental-features/
- 09:27 AM Feature #24725 (Fix Under Review): mds: propagate rstats from the leaf dirs up to the specified d...
- To make rsync "rstats" aware, we need to implement a way to propagate all rstats up through the subtree that is to be...
- 12:52 AM Feature #24724 (Resolved): client: put instance/addr information in status asok command
- Purpose is to make later lookups in the blacklist possible.
- 12:39 AM Documentation #24642: doc: visibility semantics to other clients
- I have upgraded to Mimic now and will check out if I see three minute delays again.
I would like to ask you to reo...
06/30/2018
- 12:36 AM Backport #24540: luminous: multimds pjd open test fails
- Zheng, please tkae this one. Has non-trivial conflicts.
- 12:34 AM Backport #24295 (In Progress): luminous: repeated eviction of idle client until some IO happens
- 12:26 AM Backport #24538 (In Progress): luminous: common/DecayCounter: set last_decay to current time when...
- 12:24 AM Backport #23989: luminous: mds: don't report slow request for blocked filelock request
- Zheng, this has non-trivial conflicts. Please backport.
06/29/2018
- 11:02 PM Bug #24721 (Resolved): mds: accept an inode number in hex for dump_inode command
- See also: https://github.com/ceph/ceph/pull/22569#issuecomment-398420009
- 10:50 PM Documentation #24642 (Closed): doc: visibility semantics to other clients
- Niklas Hambuechen wrote:
> Thanks everyone for the quick answers.
>
> Patrick Donnelly wrote:
> > It sounds like... - 03:27 PM Documentation #24642: doc: visibility semantics to other clients
- Thanks everyone for the quick answers.
Patrick Donnelly wrote:
> It sounds like you may have found a bug (possibl... - 05:29 PM Backport #24719 (Resolved): mimic: client: returning garbage (?) for readdir
- https://github.com/ceph/ceph/pull/22956
- 05:24 PM Backport #24718 (Resolved): luminous: client: returning garbage (?) for readdir
- https://github.com/ceph/ceph/pull/22955
- 05:24 PM Bug #24579 (Pending Backport): client: returning garbage (?) for readdir
- 05:03 PM Backport #24717: luminous: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- https://github.com/ceph/ceph/pull/22774
- 05:00 PM Backport #24717 (Resolved): luminous: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basi...
- https://github.com/ceph/ceph/pull/22774
- 04:59 PM Backport #24716 (Resolved): mimic: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-s...
- https://github.com/ceph/ceph/pull/22775
- 03:17 PM Documentation #24641: Document behaviour of fsync-after-close
- Great, that certainly makes things easier from the application perspective.
It would be great if we could write it... - 12:57 PM Bug #24679: qa: cfuse_workunit_kernel_untar_build fails on Ubuntu 18.04
- kernel source is too old for gcc 7
06/28/2018
- 08:11 PM Backport #24706 (In Progress): mimic: qa: support picking a random distro using new teuthology $
- 08:09 PM Backport #24706 (Resolved): mimic: qa: support picking a random distro using new teuthology $
- https://github.com/ceph/ceph/pull/22700
- 08:09 PM Backport #24705 (Resolved): mimic: cephfs: allow prohibiting user snapshots in CephFS
- https://github.com/ceph/ceph/pull/22812
- 08:09 PM Backport #24704 (Resolved): mimic: mds: low wrlock efficiency due to dirfrags traversal
- https://github.com/ceph/ceph/pull/22884
- 08:09 PM Backport #24703 (Resolved): mimic: PurgeQueue sometimes ignores Journaler errors
- https://github.com/ceph/ceph/pull/22810
- 08:04 PM Backport #24696 (Resolved): luminous: mds: low wrlock efficiency due to dirfrags traversal
- https://github.com/ceph/ceph/pull/22885
- 08:04 PM Backport #24695 (Rejected): jewel: PurgeQueue sometimes ignores Journaler errors
- 08:04 PM Backport #24694 (Resolved): luminous: PurgeQueue sometimes ignores Journaler errors
- https://github.com/ceph/ceph/pull/22811
- 05:32 AM Feature #24643 (Fix Under Review): libcephfs: add ceph_futimens support
- PR https://github.com/ceph/ceph/pull/22751
- 04:08 AM Bug #23262: kclient: nofail option not supported
- It seems mount command cannot recognize nofail option, not ceph or ceph kernel client.
What version of util-linux do...
06/27/2018
- 09:19 PM Bug #24284 (Pending Backport): cephfs: allow prohibiting user snapshots in CephFS
- 08:37 PM Feature #13231 (Duplicate): kclient: support SELinux
- 06:27 PM Bug #24680 (Fix Under Review): qa: iogen.sh: line 7: cd: too many arguments
- https://github.com/ceph/ceph/pull/22741
- 06:22 PM Bug #24680 (Resolved): qa: iogen.sh: line 7: cd: too many arguments
- ...
- 06:11 PM Bug #24679 (Resolved): qa: cfuse_workunit_kernel_untar_build fails on Ubuntu 18.04
- ...
- 09:11 AM Bug #24665: qa: TestStrays.test_hardlink_reintegration fails self.assertTrue(self.get_backtrace_p...
- the remote dentry was in mds cache when unlink happened, so reintegration started immediately. There were two unexpec...
06/26/2018
- 11:06 PM Bug #24522: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- https://github.com/ceph/ceph/pull/22725
- 09:08 PM Bug #21848 (Resolved): client: re-expand admin_socket metavariables in child process
- 08:32 PM Bug #24533 (Pending Backport): PurgeQueue sometimes ignores Journaler errors
- 08:32 PM Bug #24557: client: segmentation fault in handle_client_reply
- Problem only in mimic/master. Introduced by 4f2fa427f483a29df168053d0021ee35c1aa207d.
- 08:26 PM Backport #23833 (Resolved): luminous: MDSMonitor: crash after assigning standby-replay daemon in ...
- 07:05 PM Bug #24665 (Closed): qa: TestStrays.test_hardlink_reintegration fails self.assertTrue(self.get_ba...
- ...
- 12:37 PM Bug #24579 (Fix Under Review): client: returning garbage (?) for readdir
- https://github.com/ceph/ceph/pull/22718
06/25/2018
- 11:29 PM Bug #24138: qa: support picking a random distro using new teuthology $
- mimic backport https://github.com/ceph/ceph/pull/22700
- 10:48 PM Bug #24138 (Pending Backport): qa: support picking a random distro using new teuthology $
- 01:56 PM Documentation #24641: Document behaviour of fsync-after-close
- they are the same. In cephfs, there is no dirty data/metadata associated with file handle.
- 01:47 PM Documentation #24642: doc: visibility semantics to other clients
- you found a bug. this can be http://tracker.ceph.com/issues/23894
- 01:46 PM Documentation #24642: doc: visibility semantics to other clients
- Niklas Hambuechen wrote:
> I believe to just have run into a situation where one CephFS (fuse) mount created a file,... - 01:41 PM Bug #24644 (Fix Under Review): cephfs-journal-tool: wrong layout info used
- 02:29 AM Bug #24644: cephfs-journal-tool: wrong layout info used
- The fix is save the layout info to header during journal export,
When improt journal, first try to get layout from c... - 02:28 AM Bug #24644 (Resolved): cephfs-journal-tool: wrong layout info used
- when cephfs-journal-tool import journal, it uses default layout
to get object_size, this is wrong. Because default o...
06/24/2018
- 10:28 PM Feature #24643 (Resolved): libcephfs: add ceph_futimens support
- We have ceph_utime but that takes a path. We should provide a call for the file descriptor version too.
- 10:22 PM Documentation #24642: doc: visibility semantics to other clients
- User `SeanR` on freenode `#ceph` reports:
> nh2, I found (depening on mount options) if I don't call fsync() then ... - 01:14 AM Documentation #24642 (In Progress): doc: visibility semantics to other clients
- I believe to just have run into a situation where one CephFS (fuse) mount created a file, and another CephFS mount st...
- 01:08 AM Documentation #24641 (Resolved): Document behaviour of fsync-after-close
- The following should be documented:
Does close()/re-open()/fsync() provide the same durability and visibility-to-o...
06/22/2018
- 11:25 PM Bug #24467 (Pending Backport): mds: low wrlock efficiency due to dirfrags traversal
- 01:18 PM Bug #24004 (Fix Under Review): mds: curate priority of perf counters sent to mgr
- PR https://github.com/ceph/ceph/pull/22668
06/21/2018
- 12:53 PM Feature #24604 (Resolved): Implement "cephfs-journal-tool event splice" equivalent for purge queue
- cephfs-journal-tool recently got the ability to scan the purge queue via the --journal=purge_queue argument.
Howev...
06/20/2018
- 11:06 PM Bug #24522 (New): blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- Whoops!
- 09:58 PM Bug #24522: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- Patrick, this is a different script(blogbench.sh) not pjd.sh, so might not be a duplicate.
- 09:00 PM Bug #24522 (Duplicate): blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- Thanks Neha!
- 08:39 PM Bug #24522: blogbench.sh failed in upgrade:luminous-x-mimic-distro-basic-smithi
- Following is the problem:...
- 10:01 PM Bug #24137 (Resolved): client: segfault in trim_caps
- 10:00 PM Backport #24185 (Resolved): luminous: client: segfault in trim_caps
- 07:59 PM Backport #24185: luminous: client: segfault in trim_caps
- Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/22201
merged - 10:00 PM Backport #24331 (Resolved): luminous: mon: mds health metrics sent to cluster log indpeendently
- 07:58 PM Backport #24331: luminous: mon: mds health metrics sent to cluster log indpeendently
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/22558
merged - 07:57 PM Backport #23792: luminous: MDSMonitor: MDSMonitor::encode_pending modifies fsmap not pending_fsmap
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/21732
merged - 05:10 PM Feature #17854 (Fix Under Review): mds: only evict an unresponsive client when another client wan...
- 08:22 AM Bug #24579: client: returning garbage (?) for readdir
- ffsb issue. below patch can fix it. I don't know how to update http://download.ceph.com/qa/ffsb.tar.bz2...
- 07:57 AM Bug #24512: Raw used space leak
- some additional info:
- mounted with 'mount -t ceph'
- default config but:
--- 2 mds servers active
--- ram per O...
06/19/2018
- 07:22 PM Documentation #24580 (Resolved): doc: complete documentation for `ceph fs` administration commands
- Current skeleton: http://docs.ceph.com/docs/luminous/cephfs/administration/
- 07:22 PM Bug #24240: qa: 1 mutations had unexpected outcomes
- not indicated for backport to luminous because, as per Zheng, luminous does not have open file table.
- 06:56 PM Bug #24512: Raw used space leak
- I checked 'stored' vs. 'allocated' counters under bluestore section. 'stored' is the actual amount written to bluesto...
- 12:28 PM Bug #24512: Raw used space leak
- Here they are from 3 hosts (the link with hosts is in the df tree) !
Thanks! - 11:13 AM Bug #24512: Raw used space leak
- Would you share performance counters dump for several (3-5) OSDs, preferably from different nodes? And corresponding ...
- 08:08 AM Bug #24512: Raw used space leak
- sorry, wrong ceph version: 12.2.5-407 (luminous stable)
I'm still very interested by any answer. If I try filestor... - 06:09 PM Bug #24579: client: returning garbage (?) for readdir
- This seems to only happen on Ubuntu 18.04:...
- 06:05 PM Bug #24579: client: returning garbage (?) for readdir
- Here too:
/ceph/teuthology-archive/teuthology-2018-06-18_20:06:42-powercycle-master-distro-basic-smithi/2678660
... - 06:03 PM Bug #24579 (Resolved): client: returning garbage (?) for readdir
- ...
- 04:18 PM Bug #24441 (Closed): Ceph fs new cephfs command failed when meta pool already contains some objects
- This is not a bug -- the check was added to avoid people accidentally getting corrupt filesystems by trying to use a ...
- 03:37 AM Feature #24464: cephfs: file-level snapshots
- I think using rados snapshot to support is too expensive.
- 02:55 AM Bug #24557 (Fix Under Review): client: segmentation fault in handle_client_reply
- https://github.com/ceph/ceph/pull/22611
06/18/2018
- 09:19 PM Bug #24557 (Resolved): client: segmentation fault in handle_client_reply
- ...
- 07:21 PM Backport #23833 (In Progress): luminous: MDSMonitor: crash after assigning standby-replay daemon ...
- 05:45 PM Feature #17230: ceph_volume_client: py3 compatible
- There are high-level pushes to py3 in future (minor-)releases of Ceph/Openstack. RHCS 3.X (Luminous) will need to be ...
- 05:35 PM Feature #17230: ceph_volume_client: py3 compatible
- Question for all, and particularly for Patrick: why is a luminous backport of this needed, and is it worth the risk?
- 05:42 PM Bug #24518 (Duplicate): "pjd.sh: line 7: cd: too many arguments" in fs suite
- Yuri, you're using an old qa-suite branch. Thanks to Neha for noticing the cause.
- 05:29 PM Bug #24518: "pjd.sh: line 7: cd: too many arguments" in fs suite
- Line in question: https://github.com/ceph/ceph/blob/2d2293948066cae8d656dfe91bdb6695958a52e9/qa/workunits/suites/pjd....
Also available in: Atom