Project

General

Profile

Activity

From 03/08/2021 to 04/06/2021

04/06/2021

07:25 PM Backport #50127 (In Progress): pacific: pybind/mgr/volumes: deadlock on async job hangs finisher ...
Patrick Donnelly
07:22 PM Backport #50025 (In Progress): pacific: client: items pinned in cache preventing unmount
Patrick Donnelly
07:18 PM Backport #50022 (In Progress): pacific: ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert...
Patrick Donnelly
06:10 PM Backport #50187 (In Progress): pacific: ceph-dokan improvements for additional mounts
Lucian Petrut
05:50 PM Backport #50187 (Resolved): pacific: ceph-dokan improvements for additional mounts
https://github.com/ceph/ceph/pull/40627 Backport Bot
05:50 PM Backport #50190 (Resolved): pacific: qa: "Assertion `cb_done' failed."
https://github.com/ceph/ceph/pull/40683 Backport Bot
05:50 PM Backport #50189 (Rejected): nautilus: qa: "Assertion `cb_done' failed."
Backport Bot
05:50 PM Backport #50188 (Rejected): octopus: qa: "Assertion `cb_done' failed."
Backport Bot
05:46 PM Bug #49662 (Pending Backport): ceph-dokan improvements for additional mounts
Patrick Donnelly
05:46 PM Backport #50186 (Resolved): pacific: qa: daemonwatchdog fails if mounts not defined
https://github.com/ceph/ceph/pull/40634 Backport Bot
05:45 PM Backport #50185 (Resolved): pacific: qa: "RADOS object not found (Failed to operate read op for o...
https://github.com/ceph/ceph/pull/40684 Backport Bot
05:45 PM Backport #50184 (Rejected): octopus: client: openned inodes counter is inconsistent
Backport Bot
05:45 PM Backport #50183 (Resolved): pacific: client: openned inodes counter is inconsistent
https://github.com/ceph/ceph/pull/40685 Backport Bot
05:45 PM Backport #50182 (Rejected): nautilus: client: openned inodes counter is inconsistent
Backport Bot
05:45 PM Bug #49500 (Pending Backport): qa: "Assertion `cb_done' failed."
Patrick Donnelly
05:45 PM Backport #50181 (Resolved): octopus: client: only check pool permissions for regular files
https://github.com/ceph/ceph/pull/40779 Backport Bot
05:45 PM Backport #50180 (Resolved): pacific: client: only check pool permissions for regular files
https://github.com/ceph/ceph/pull/40686 Backport Bot
05:45 PM Backport #50179 (Resolved): nautilus: client: only check pool permissions for regular files
https://github.com/ceph/ceph/pull/40730 Backport Bot
05:44 PM Bug #50090 (Pending Backport): client: only check pool permissions for regular files
Patrick Donnelly
05:43 PM Bug #50020 (Pending Backport): qa: "RADOS object not found (Failed to operate read op for oid cep...
Patrick Donnelly
05:41 PM Bug #50057 (Pending Backport): client: openned inodes counter is inconsistent
Patrick Donnelly
05:30 PM Bug #50178 (Rejected): qa: "TypeError: run() got an unexpected keyword argument 'shell'"
... Patrick Donnelly
03:25 PM Backport #50173 (Resolved): pacific: mgr/nfs: validation error on creating custom export
https://github.com/ceph/ceph/pull/40687 Backport Bot
03:24 PM Documentation #50161 (Pending Backport): mgr/nfs: validation error on creating custom export
Patrick Donnelly
10:24 AM Documentation #50161 (In Progress): mgr/nfs: validation error on creating custom export
Varsha Rao
10:18 AM Documentation #50161 (Resolved): mgr/nfs: validation error on creating custom export
... Varsha Rao
12:33 PM Documentation #49406: Exceeding osd nearfull ratio causes write throttle.
It's unfortunate that it caught you by surprise. Would you care to draft a patch to update the documentation? Where w... Jeff Layton
11:59 AM Bug #50112: MDS stuck at stopping when reducing max_mds
Xiubo Li wrote:
> BTW, do you have more logs for the mds.0 ? I need to check the logs to get why.
Only less than ...
玮文 胡
11:14 AM Bug #50112: MDS stuck at stopping when reducing max_mds
玮文 胡 wrote:
> Xiubo Li wrote:
> > It seems the "mdsdir_in->get_num_ref()" is not zero in mds.0
>
> Yes, do you h...
Xiubo Li
11:00 AM Bug #50112: MDS stuck at stopping when reducing max_mds
Xiubo Li wrote:
> It seems the "mdsdir_in->get_num_ref()" is not zero in mds.0
Yes, do you have any idea why? As ...
玮文 胡
10:46 AM Bug #50112: MDS stuck at stopping when reducing max_mds
It seems the "mdsdir_in->get_num_ref()" is not zero in mds.0:... Xiubo Li
09:03 AM Bug #50112: MDS stuck at stopping when reducing max_mds
玮文 胡 wrote:
> Some more progress. mds.0 seems actually sending an empty cache_expire message to mds.1, despite sayin...
Xiubo Li
09:22 AM Bug #50021 (Fix Under Review): qa: snaptest-git-ceph failure during mon thrashing
Xiubo Li
05:54 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Patrick Donnelly wrote:
> Xiubo Li wrote:
>
[...]
> > > >
> > > > What repo do you want to mirror?
> > >
...
Xiubo Li
03:21 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Xiubo Li wrote:
> Patrick Donnelly wrote:
> > David Galloway wrote:
> > > Xiubo Li wrote:
> > > > Patrick Donnell...
Patrick Donnelly
02:15 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Patrick Donnelly wrote:
> David Galloway wrote:
> > Xiubo Li wrote:
> > > Patrick Donnelly wrote:
> > > > Xiubo L...
Xiubo Li
01:50 AM Feature #50150 (Pending Backport): qa: begin grepping kernel logs for kclient warnings/failures t...
Right now, TMK, we are not confirming there are no warnings/errors/lockups in the kclient before passing a test. We d... Patrick Donnelly
01:46 AM Cleanup #50149 (Resolved): client: always register callbacks before mount()
Make Client::ll_register_callbacks() return 'int' type value instead
and return negative errno if not successful.
...
Xiubo Li

04/05/2021

05:56 PM Bug #48439: fsstress failure with mds thrashing: "mds.0.6 Evicting (and blocklisting) client sess...
Deepika Upadhyay wrote:
> @Patrick I am seeing this issue on Ubuntu 18.04; doesn't seem to be related to testing pr....
Patrick Donnelly
05:02 PM Bug #48439: fsstress failure with mds thrashing: "mds.0.6 Evicting (and blocklisting) client sess...
@Patrick I am seeing this issue on Ubuntu 18.04; doesn't seem to be related to testing pr.
Not sure if it's related ...
Deepika Upadhyay
05:12 PM Bug #50112: MDS stuck at stopping when reducing max_mds
I wonder if this is related to
https://tracker.ceph.com/issues/49922
The code would indicate it's normal for md...
Patrick Donnelly
04:48 PM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
David Galloway wrote:
> Xiubo Li wrote:
> > Patrick Donnelly wrote:
> > > Xiubo Li wrote:
> > >
> > > [...]
> >...
Patrick Donnelly
01:35 PM Bug #50035 (Triaged): cephfs-mirror: use sensible mount/shutdown timeouts
Patrick Donnelly
11:47 AM Feature #49304 (Resolved): nfs-ganesha: plumb xattr support into FSAL_CEPH
Patches are merged into the ganesha next branch and should make next release. Jeff Layton

04/04/2021

02:06 PM Bug #50112: MDS stuck at stopping when reducing max_mds
Some more progress. mds.0 seems actually sending an empty cache_expire message to mds.1, despite saying "successfully... 玮文 胡
09:09 AM Bug #50112: MDS stuck at stopping when reducing max_mds
I spent some more time investigating this. Hope this is helpful.
When I issue "dump cache" to the stopping mds.1, ...
玮文 胡

04/03/2021

04:35 PM Bug #49912: client: dir->dentries inconsistent, both newname and oldname points to same inode, m...
Xiubo Li wrote:
> I am doubting that if there has two tasks are doing the rename:
>
> For task1, if it just do _l...
Xiaoxi Chen
04:21 PM Bug #49912: client: dir->dentries inconsistent, both newname and oldname points to same inode, m...
Jeff Layton wrote:
> I think that after the mv, the directory should no longer be considered ORDERED. We probably _c...
Xiaoxi Chen
02:25 PM Backport #50128 (Resolved): nautilus: pybind/mgr/volumes: deadlock on async job hangs finisher th...
https://github.com/ceph/ceph/pull/41394 Backport Bot
02:25 PM Backport #50127 (Resolved): pacific: pybind/mgr/volumes: deadlock on async job hangs finisher thread
https://github.com/ceph/ceph/pull/40630 Backport Bot
02:25 PM Backport #50126 (Rejected): octopus: pybind/mgr/volumes: deadlock on async job hangs finisher thread
https://github.com/ceph/ceph/pull/43269 Backport Bot
02:24 PM Bug #49605 (Pending Backport): pybind/mgr/volumes: deadlock on async job hangs finisher thread
Kefu Chai

04/02/2021

05:44 PM Bug #50112 (Triaged): MDS stuck at stopping when reducing max_mds
Patrick Donnelly
01:42 PM Bug #50112: MDS stuck at stopping when reducing max_mds
I've figured out "7 mds.1.cache still have replicated objects" may be the reason that this MDS cannot complete its sh... 玮文 胡
12:13 PM Bug #50112 (Resolved): MDS stuck at stopping when reducing max_mds
We are trying to upgrade to v16 today. Cephadm is trying to reduce max_mds to 1 automatically. However, MDS.1 is stuc... 玮文 胡
07:10 AM Feature #46865 (Resolved): client: add metric for number of pinned capabilities
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:09 AM Bug #48559 (Resolved): qa: ERROR: test_damaged_dentry, KeyError: 'passed_validation'
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:09 AM Fix #48802 (Resolved): mds: define CephFS errors that replace standard errno values
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:08 AM Bug #48912 (Resolved): ls -l in cephfs-shell tries to chase symlinks when stat'ing and errors out...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:08 AM Bug #49074 (Resolved): mds: don't start purging inodes in the middle of recovery
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:08 AM Bug #49121 (Resolved): vstart: volumes/nfs interface complaints cluster does not exists
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Bug #49391 (Resolved): qa: run fs:verify with tcmalloc
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Bug #49464 (Resolved): qa: rank_freeze prevents failover on some tests
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Bug #49507 (Resolved): qa: mds removed because trimming for too long with valgrind
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Bug #49607 (Resolved): qa: slow metadata ops during scrubbing
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Feature #49619 (Resolved): cephfs-mirror: add mirror peers via bootstrapping
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:07 AM Feature #49623 (Resolved): Windows CephFS support - ceph-dokan
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:06 AM Bug #49711 (Resolved): cephfs-mirror: symbolic links do not get synchronized at times
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:06 AM Bug #49719 (Resolved): mon/MDSMonitor: standby-replay daemons should be removed when the flag is ...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:06 AM Bug #49725 (Resolved): client: crashed in cct->_conf.get_val() in Client::start_tick_thread()
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
07:06 AM Bug #49822 (Resolved): test: test_mirroring_command_idempotency (tasks.cephfs.test_admin.TestMirr...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
03:55 AM Bug #50108 (New): access to a file with the wrong permission when changing the parent directory's...
Recently, we tried to manage the permission of files and directories in ceph with ACL.
Basically, we planed to set...
cao yi

04/01/2021

06:17 PM Backport #49935 (Resolved): pacific: libcephfs: test termination "what(): Too many open files"
Patrick Donnelly
06:17 PM Backport #49932 (Resolved): pacific: MDS should return -ENODATA when asked to remove xattr that d...
Patrick Donnelly
06:17 PM Backport #49929 (Resolved): pacific: test: test_mirroring_command_idempotency (tasks.cephfs.test_...
Patrick Donnelly
06:16 PM Backport #49905 (Resolved): pacific: mgr/volumes: setuid and setgid file bits are not retained af...
Patrick Donnelly
06:16 PM Backport #49854 (Resolved): pacific: client: crashed in cct->_conf.get_val() in Client::start_tic...
Patrick Donnelly
06:16 PM Backport #49852 (Resolved): pacific: mds: race of fetching large dirfrag
Patrick Donnelly
06:16 PM Backport #49765 (Resolved): pacific: cephfs-mirror: symbolic links do not get synchronized at times
Patrick Donnelly
06:16 PM Backport #49753 (Resolved): pacific: cephfs-mirror: add mirror peers via bootstrapping
Patrick Donnelly
06:15 PM Backport #49751 (Resolved): pacific: snap-schedule doc
Patrick Donnelly
06:14 PM Backport #49713 (Resolved): pacific: mgr/nfs: Add interface to update export
Patrick Donnelly
06:14 PM Backport #49687 (Resolved): pacific: client: add metric for number of pinned capabilities
Patrick Donnelly
06:14 PM Backport #49685 (Resolved): pacific: ls -l in cephfs-shell tries to chase symlinks when stat'ing ...
Patrick Donnelly
06:14 PM Backport #49634 (Resolved): pacific: Windows CephFS support - ceph-dokan
Patrick Donnelly
06:13 PM Backport #49631 (Resolved): pacific: mds: don't start purging inodes in the middle of recovery
Patrick Donnelly
06:13 PM Backport #49630 (Resolved): pacific: qa: slow metadata ops during scrubbing
Patrick Donnelly
06:13 PM Backport #49612 (Resolved): pacific: qa: racy session evicted check
Patrick Donnelly
06:13 PM Backport #49610 (Resolved): pacific: qa: mds removed because trimming for too long with valgrind
Patrick Donnelly
06:12 PM Backport #49609 (Resolved): pacific: qa: ERROR: test_damaged_dentry, KeyError: 'passed_validation'
Patrick Donnelly
06:12 PM Backport #49608 (Resolved): pacific: mds: define CephFS errors that replace standard errno values
Patrick Donnelly
06:12 PM Backport #49569 (Resolved): pacific: qa: rank_freeze prevents failover on some tests
Patrick Donnelly
06:12 PM Backport #49563 (Resolved): pacific: qa: run fs:verify with tcmalloc
Patrick Donnelly
06:11 PM Backport #49561 (Resolved): pacific: qa: file system deletion not complete because starter fs alr...
Patrick Donnelly
06:11 PM Backport #49520 (Resolved): pacific: client: wake up the front pos waiter
Patrick Donnelly
06:11 PM Backport #49517 (Resolved): pacific: pybind/cephfs: DT_REG and DT_LNK values are wrong
Patrick Donnelly
06:11 PM Backport #49512 (Resolved): pacific: client: allow looking up snapped inodes by inode number+snap...
Patrick Donnelly
06:10 PM Backport #49474 (Resolved): pacific: nautilus: qa: "Assertion `cb_done' failed."
Patrick Donnelly
06:10 PM Backport #49470 (Resolved): pacific: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
Patrick Donnelly
06:10 PM Backport #49346 (Resolved): pacific: vstart: volumes/nfs interface complaints cluster does not ex...
Patrick Donnelly
03:45 PM Bug #49662 (Fix Under Review): ceph-dokan improvements for additional mounts
Patrick Donnelly
02:58 PM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Xiubo Li wrote:
> Patrick Donnelly wrote:
> > Xiubo Li wrote:
> >
> > [...]
> >
> > > @Patrick,
> > >
> > > ...
David Galloway
12:27 PM Bug #50083: CephFS file access issues using kernel driver: file overwritten with null bytes
More questions:
1) how large are these files (generally)?
2) at what point does the corruption start?
3) How far...
Jeff Layton
12:05 PM Bug #50083: CephFS file access issues using kernel driver: file overwritten with null bytes
Ok, so it is reproducible in your environment. The problem is that I'm unclear on what sort of I/O is being done here... Jeff Layton
08:32 AM Bug #50083: CephFS file access issues using kernel driver: file overwritten with null bytes
We do have a reliable repro currently yes. A file that we write to several times an hour shows clear corruption corre... David Piper
09:18 AM Bug #50091 (Fix Under Review): cephfs-top: exception: addwstr() returned ERR
Xiubo Li
04:24 AM Bug #50091 (Resolved): cephfs-top: exception: addwstr() returned ERR
When the terminal is not wide enough, this can be seen 100%. Xiubo Li
01:32 AM Bug #50090 (Resolved): client: only check pool permissions for regular files
There is no need to do a check_pool_perm() on anything that isn't
a regular file, as the MDS is what handles talking...
Xiubo Li

03/31/2021

08:46 PM Bug #50083: CephFS file access issues using kernel driver: file overwritten with null bytes
This is the first I've heard of this as well. You mentioned seeing this on v5.11 kernels. Have you also seen it on ea... Jeff Layton
07:05 PM Bug #50083 (Triaged): CephFS file access issues using kernel driver: file overwritten with null b...
This has never been heard of before. The most likely cause is something in your setup, e.g. a rogue process (rsync) m... Patrick Donnelly
01:57 PM Bug #50083 (Resolved): CephFS file access issues using kernel driver: file overwritten with null ...
Ceph cluster is running 14.2.9 (nautilus), a 3 node containerised cluster. 1 active MDS, 2 standby
Using ceph kernel...
David Piper
06:09 PM Feature #41073 (Rejected): cephfs-sync: tool for synchronizing cephfs snapshots to remote target
Patrick Donnelly
04:24 AM Feature #41073: cephfs-sync: tool for synchronizing cephfs snapshots to remote target
I think this can be closed. Right Milind?
(We dropped relying on rsync)
Venky Shankar
06:08 PM Feature #46432 (Resolved): cephfs-mirror: manager module interface to add/remove directory snapshots
Patrick Donnelly
04:22 AM Feature #46432 (Closed): cephfs-mirror: manager module interface to add/remove directory snapshots
Feature available in Pacific. Venky Shankar
06:08 PM Feature #44191 (Resolved): cephfs: geo-replication
Patrick Donnelly
04:22 AM Feature #44191 (Closed): cephfs: geo-replication
Feature available in Pacific. Venky Shankar
06:08 PM Feature #41074 (Resolved): pybind/mgr/volumes: mirror (scheduled) snapshots to remote target
Patrick Donnelly
04:21 AM Feature #41074 (Closed): pybind/mgr/volumes: mirror (scheduled) snapshots to remote target
Patrick Donnelly wrote:
> Close this out?
Definitely.
Venky Shankar
03:30 PM Backport #50086 (Resolved): pacific: tasks.cephfs.test_volumes.TestSubvolumeGroups: RuntimeError:...
https://github.com/ceph/ceph/pull/40688 Backport Bot
03:26 PM Bug #48411 (Pending Backport): tasks.cephfs.test_volumes.TestSubvolumeGroups: RuntimeError: rank ...
Patrick Donnelly
02:31 PM Backport #50030 (In Progress): pacific: qa: fs:cephadm mount does not wait for mds to be created
Patrick Donnelly
02:11 PM Feature #49811 (Fix Under Review): mds: collect I/O sizes from client for cephfs-top
Xiubo Li
01:06 PM Bug #49939: cephfs-mirror: be resilient to recreated snapshot during synchronization
So, I am experimenting with how MDS handles path traversals when just an inode number rather than inode number+dname ... Venky Shankar
12:48 PM Cleanup #50080 (In Progress): mgr/nfs: move nfs code out of volumes plugin
Varsha Rao
12:45 PM Cleanup #50080 (Resolved): mgr/nfs: move nfs code out of volumes plugin
Varsha Rao
09:54 AM Bug #48805 (Fix Under Review): mds: "cluster [WRN] Scrub error on inode 0x1000000039d (/client.0/...
Milind Changire

03/30/2021

10:30 PM Feature #41073: cephfs-sync: tool for synchronizing cephfs snapshots to remote target
ping Patrick Donnelly
10:30 PM Feature #46432: cephfs-mirror: manager module interface to add/remove directory snapshots
Close this out? Patrick Donnelly
10:30 PM Feature #44191: cephfs: geo-replication
Close this out? Patrick Donnelly
10:29 PM Feature #41074: pybind/mgr/volumes: mirror (scheduled) snapshots to remote target
Close this out? Patrick Donnelly
10:28 PM Backport #49930 (Resolved): pacific: mon/MDSMonitor: standby-replay daemons should be removed whe...
Patrick Donnelly
10:27 PM Bug #49720 (Fix Under Review): mon/MDSMonitor: do not pointlessly kill standbys that are incompat...
Patrick Donnelly
08:52 PM Bug #48411 (In Progress): tasks.cephfs.test_volumes.TestSubvolumeGroups: RuntimeError: rank all f...
Ramana Raja
06:58 PM Bug #50060 (Triaged): client: access(path, X_OK) on non-executable file as root always succeeds
Patrick Donnelly
06:58 PM Bug #50060 (Resolved): client: access(path, X_OK) on non-executable file as root always succeeds
See "[ceph-users] ceph-fuse false passed X_OK check".
Check works for non-root users.
Patrick Donnelly
04:00 PM Bug #50057 (Fix Under Review): client: openned inodes counter is inconsistent
Patrick Donnelly
03:12 PM Bug #50057 (Resolved): client: openned inodes counter is inconsistent
... Xiubo Li
11:08 AM Bug #49466: qa: "Command failed on gibba030 with status 1: 'set -ex\nsudo dd of=/tmp/tmp.ZEeZBasJ...
Thanks Rishabh for your analysis.
> The best fix is to add a method to teuthology.orchestra.remote.Remote. It woul...
Kyrylo Shatskyy
03:48 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Patrick Donnelly wrote:
> Xiubo Li wrote:
>
> [...]
>
> > @Patrick,
> >
> > Maybe we could save a ceph repo s...
Xiubo Li
03:20 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Xiubo Li wrote:
> Okay, I was in wrong direction yesterday.
>
> I think it was the `git clone ceph...` command's ...
Patrick Donnelly
03:16 AM Bug #50048 (Fix Under Review): mds: standby-replay only trims cache when it reaches the end of th...
Patrick Donnelly
03:03 AM Bug #50048 (Resolved): mds: standby-replay only trims cache when it reaches the end of the replay...
This could take a significant amount of time under load. Trim regularly like the active MDS. Patrick Donnelly

03/29/2021

11:55 PM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Okay, I was in wrong direction yesterday.
I think it was the `git clone ceph...` command's problem, it took too lo...
Xiubo Li
01:51 PM Bug #50021 (In Progress): qa: snaptest-git-ceph failure during mon thrashing
Xiubo Li
01:05 PM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
The exception occured just before the snap test at:... Xiubo Li
12:58 PM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Checked all the mds/osd/mon/client/kernel/misc related logs, didn't find any error during that exception around 2021-... Xiubo Li
08:19 AM Bug #50021: qa: snaptest-git-ceph failure during mon thrashing
Checked the client logs in `smithi016/log/ceph-client.0.25180.log.gz`, everything works well till now, I didn't see a... Xiubo Li
10:13 PM Fix #50045 (Fix Under Review): qa: test standby_replay in workloads
Patrick Donnelly
10:12 PM Fix #50045 (Resolved): qa: test standby_replay in workloads
To improve our test coverage of this frequently enabled feature (both in cephadm and Rook). Patrick Donnelly
01:47 PM Bug #49939 (In Progress): cephfs-mirror: be resilient to recreated snapshot during synchronization
Patrick Donnelly
01:43 PM Bug #50033 (Triaged): mgr/stats: be resilient to offline MDS rank-0
Patrick Donnelly
06:41 AM Bug #50033 (Resolved): mgr/stats: be resilient to offline MDS rank-0
mgr/stats can repeatedly report stale perf stats when MDS rank-0 becomes offline. Even after a standby daemon transit... Venky Shankar
09:15 AM Bug #50035 (Resolved): cephfs-mirror: use sensible mount/shutdown timeouts
The mirror daemon just relies on the defaults which are pretty high:... Venky Shankar
07:21 AM Bug #50020: qa: "RADOS object not found (Failed to operate read op for oid cephfs_mirror)"
test case fix: prio -> low Venky Shankar
07:21 AM Bug #50020: qa: "RADOS object not found (Failed to operate read op for oid cephfs_mirror)"
The real failure was the "failed" state not reflecting in mirror status. From the daemon logs, the mirror daemon rest... Venky Shankar
07:19 AM Bug #50020 (Fix Under Review): qa: "RADOS object not found (Failed to operate read op for oid cep...
Venky Shankar

03/28/2021

12:05 PM Backport #50030 (Resolved): pacific: qa: fs:cephadm mount does not wait for mds to be created
https://github.com/ceph/ceph/pull/40528 Backport Bot
12:04 PM Bug #49684 (Pending Backport): qa: fs:cephadm mount does not wait for mds to be created
Kefu Chai

03/27/2021

06:38 PM Bug #49301 (Resolved): mon/MonCap: `fs authorize` generates unparseable cap for file system name ...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
06:37 PM Bug #49736 (Resolved): cephfs-top: missing keys in the client_metadata
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
06:37 PM Feature #49953 (Resolved): cephfs-top : allow configurable stats refresh interval
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
06:37 PM Bug #49974 (Resolved): cephfs-top: fails with exception "OPENED_FILES"
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
06:36 PM Bug #50005 (Resolved): cephfs-top: flake8 E501 line too long error
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
07:39 AM Bug #50020: qa: "RADOS object not found (Failed to operate read op for oid cephfs_mirror)"
The index object (cephfs_mirror) is missing in the rados pool. This is created when mirroring is enabled (via mgr/mir... Venky Shankar
12:53 AM Feature #48682 (Fix Under Review): MDSMonitor: add command to print fs flags
Jos Collin
12:53 AM Fix #48683 (Fix Under Review): mds/MDSMap: print each flag value in MDSMap::dump
Jos Collin

03/26/2021

10:16 PM Backport #50027 (Resolved): octopus: client: items pinned in cache preventing unmount
https://github.com/ceph/ceph/pull/40778 Backport Bot
10:15 PM Backport #50026 (Resolved): nautilus: client: items pinned in cache preventing unmount
https://github.com/ceph/ceph/pull/40722 Backport Bot
10:15 PM Backport #50025 (Resolved): pacific: client: items pinned in cache preventing unmount
https://github.com/ceph/ceph/pull/40629 Backport Bot
10:15 PM Backport #50024 (Rejected): octopus: ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_n...
Backport Bot
10:15 PM Backport #50023 (Rejected): nautilus: ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_...
Backport Bot
10:15 PM Backport #50022 (Resolved): pacific: ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_n...
https://github.com/ceph/ceph/pull/40628 Backport Bot
10:13 PM Bug #48679 (Pending Backport): client: items pinned in cache preventing unmount
Patrick Donnelly
10:11 PM Bug #49936 (Pending Backport): ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_num <= ...
Patrick Donnelly
10:08 PM Bug #50016: qa: test_damage: "RuntimeError: 2 mutations had unexpected outcomes"
/ceph/teuthology-archive/pdonnell-2021-03-24_23:26:35-fs-wip-pdonnell-testing-20210324.190252-distro-basic-smithi/599... Patrick Donnelly
03:25 PM Bug #50016 (New): qa: test_damage: "RuntimeError: 2 mutations had unexpected outcomes"
... Patrick Donnelly
10:07 PM Bug #48771: qa: iogen: workload fails to cause balancing
/ceph/teuthology-archive/pdonnell-2021-03-24_23:26:35-fs-wip-pdonnell-testing-20210324.190252-distro-basic-smithi/599... Patrick Donnelly
10:05 PM Bug #50021 (Resolved): qa: snaptest-git-ceph failure during mon thrashing
... Patrick Donnelly
09:57 PM Bug #50020 (Resolved): qa: "RADOS object not found (Failed to operate read op for oid cephfs_mirr...
... Patrick Donnelly
09:56 PM Bug #50019 (Closed): qa: mount failure with cephadm "probably no MDS server is up?"
... Patrick Donnelly
07:29 PM Backport #49564 (Resolved): pacific: mon/MonCap: `fs authorize` generates unparseable cap for fil...
Patrick Donnelly
05:48 PM Backport #49935: pacific: libcephfs: test termination "what(): Too many open files"
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40372
merged
Yuri Weinstein
05:31 PM Backport #50011 (Resolved): pacific: cephfs-top: flake8 E501 line too long error
Patrick Donnelly
12:17 PM Backport #50011 (In Progress): pacific: cephfs-top: flake8 E501 line too long error
Venky Shankar
12:00 PM Backport #50011 (Resolved): pacific: cephfs-top: flake8 E501 line too long error
https://github.com/ceph/ceph/pull/40422 Backport Bot
05:31 PM Backport #49994 (Resolved): pacific: cephfs-top: fails with exception "OPENED_FILES"
Patrick Donnelly
12:17 PM Backport #49994 (In Progress): pacific: cephfs-top: fails with exception "OPENED_FILES"
Venky Shankar
06:25 AM Backport #49994 (Resolved): pacific: cephfs-top: fails with exception "OPENED_FILES"
https://github.com/ceph/ceph/pull/40422 Backport Bot
05:24 PM Backport #49986 (Resolved): pacific: cephfs-top : allow configurable stats refresh interval
Venky Shankar
05:24 PM Backport #49973 (Resolved): pacific: cephfs-top: missing keys in the client_metadata
Venky Shankar
03:34 PM Backport #49932: pacific: MDS should return -ENODATA when asked to remove xattr that doesn't exist
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40371
merged
Yuri Weinstein
03:33 PM Backport #49685: pacific: ls -l in cephfs-shell tries to chase symlinks when stat'ing and errors ...
Varsha Rao wrote:
> https://github.com/ceph/ceph/pull/40308
merged
Yuri Weinstein
03:33 PM Backport #49713: pacific: mgr/nfs: Add interface to update export
Varsha Rao wrote:
> https://github.com/ceph/ceph/pull/40307
merged
Yuri Weinstein
03:32 PM Backport #49852: pacific: mds: race of fetching large dirfrag
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40252
merged
Yuri Weinstein
03:32 PM Backport #49854: pacific: client: crashed in cct->_conf.get_val() in Client::start_tick_thread()
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40251
merged
Yuri Weinstein
03:31 PM Bug #49379: client: wake up the front pos waiter
https://github.com/ceph/ceph/pull/40109 merged Yuri Weinstein
03:30 PM Backport #49609: pacific: qa: ERROR: test_damaged_dentry, KeyError: 'passed_validation'
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40108
merged
Yuri Weinstein
03:25 PM Backport #50015 (Resolved): pacific: qa: "AttributeError: 'NoneType' object has no attribute 'mon...
https://github.com/ceph/ceph/pull/40645 Backport Bot
03:21 PM Bug #49511 (Pending Backport): qa: "AttributeError: 'NoneType' object has no attribute 'mon_manag...
Also seen in pacific: https://pulpito.ceph.com/yuriw-2021-03-25_21:03:23-fs-wip-yuri-testing-2021-03-25-1105-pacific-... Patrick Donnelly
12:20 PM Documentation #49921: mgr/nfs: Update about cephadm single nfs-ganesha daemon per host limitation
pacifci backport merged in #40355 Sage Weil
11:56 AM Bug #50005 (Pending Backport): cephfs-top: flake8 E501 line too long error
Venky Shankar
09:43 AM Bug #50005 (Fix Under Review): cephfs-top: flake8 E501 line too long error
Varsha Rao
09:42 AM Bug #50005 (Resolved): cephfs-top: flake8 E501 line too long error
... Varsha Rao
11:39 AM Bug #50010 (Resolved): qa/cephfs: get_key_from_keyfile() return None when key is not found in key...
Absence of key in a keyring file is an odd and exceptional situation. Therefore, @CephFSMount.get_key_from_keyfile()@... Rishabh Dave
11:03 AM Documentation #49372 (Resolved): doc: broken links multimds and kcephfs
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
11:02 AM Documentation #49763 (Resolved): doc: Document mds cap acquisition readdir throttle
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
10:52 AM Documentation #50008 (Resolved): mgr/nfs: Add troubleshooting section
Varsha Rao
08:59 AM Bug #49466: qa: "Command failed on gibba030 with status 1: 'set -ex\nsudo dd of=/tmp/tmp.ZEeZBasJ...
Cause of the bug: Write was attempted on @/tmp@ file with the @root@ user. Files in @/tmp@ can't be written by any us... Rishabh Dave
06:26 AM Bug #49466 (In Progress): qa: "Command failed on gibba030 with status 1: 'set -ex\nsudo dd of=/tm...
Rishabh Dave
08:18 AM Bug #49972 (Fix Under Review): mds: failed to decode message of type 29 v1: void CapInfoPayload::...
Xiubo Li
07:26 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Venky Shankar wrote:
> Xiubo Li wrote:
> > @Venkey, with your backport patch I can reproduce it locally.
>
> Whi...
Xiubo Li
06:20 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Venky Shankar wrote:
> Xiubo Li wrote:
> > @Venkey, with your backport patch I can reproduce it locally.
>
> Whi...
Xiubo Li
06:13 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Xiubo Li wrote:
> @Venkey, with your backport patch I can reproduce it locally.
Which backport? cephfs-mirror ser...
Venky Shankar
06:04 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
@Venkey, with your backport patch I can reproduce it locally. Xiubo Li
04:58 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Patrick Donnelly wrote:
> I think this might just be because the pacific branch was missing: https://tracker.ceph.co...
Venky Shankar
04:37 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Locally I have built the origin/pacific ceph and with the lasted origin/testing kclient, it works well:... Xiubo Li
03:06 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
... Xiubo Li
06:22 AM Bug #49974 (Pending Backport): cephfs-top: fails with exception "OPENED_FILES"
Venky Shankar

03/25/2021

08:37 PM Bug #49500 (Fix Under Review): qa: "Assertion `cb_done' failed."
Patrick Donnelly
06:05 PM Backport #49986 (In Progress): pacific: cephfs-top : allow configurable stats refresh interval
Venky Shankar
05:15 PM Backport #49986 (Resolved): pacific: cephfs-top : allow configurable stats refresh interval
https://github.com/ceph/ceph/pull/40417 Backport Bot
05:41 PM Bug #49974: cephfs-top: fails with exception "OPENED_FILES"
PR https://github.com/ceph/ceph/pull/39972 is merged in pacific. Backport should be straightforward. Venky Shankar
11:18 AM Bug #49974 (Fix Under Review): cephfs-top: fails with exception "OPENED_FILES"
Venky Shankar
11:12 AM Bug #49974 (Resolved): cephfs-top: fails with exception "OPENED_FILES"
Commit 89cc2cda4aa4 introduces additional metrics but did not add those metrics to cephfs-top.
Also, include a che...
Venky Shankar
05:34 PM Backport #49905: pacific: mgr/volumes: setuid and setgid file bits are not retained after a subvo...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40267
merged
Yuri Weinstein
05:33 PM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Patrick Donnelly wrote:
> I think this might just be because the pacific branch was missing: https://tracker.ceph.co...
Patrick Donnelly
05:33 PM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
I think this might just be because the pacific branch was missing: https://tracker.ceph.com/issues/46865 Patrick Donnelly
01:40 PM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
Patrick mentioned that this could be related to the testing kernel (as Jeff merged some of Xiubo's patches that adds ... Venky Shankar
08:52 AM Bug #49972: mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
another instance (same branch): https://pulpito.ceph.com/vshankar-2021-03-25_05:53:38-fs-wip-cephfs-mirror-pacific-ba... Venky Shankar
08:51 AM Bug #49972 (Resolved): mds: failed to decode message of type 29 v1: void CapInfoPayload::decode
This was seen in pacific backport branch: https://pulpito.ceph.com/vshankar-2021-03-25_05:53:38-fs-wip-cephfs-mirror-... Venky Shankar
05:33 PM Backport #49563: pacific: qa: run fs:verify with tcmalloc
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40091
merged
Yuri Weinstein
05:33 PM Backport #49610: pacific: qa: mds removed because trimming for too long with valgrind
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40091
merged
Yuri Weinstein
05:32 PM Backport #49634: pacific: Windows CephFS support - ceph-dokan
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40069
merged
Yuri Weinstein
05:32 PM Backport #49346: pacific: vstart: volumes/nfs interface complaints cluster does not exists
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/39974
merged
Yuri Weinstein
05:31 PM Backport #49687: pacific: client: add metric for number of pinned capabilities
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/39972
merged
Yuri Weinstein
12:16 PM Bug #49843 (Resolved): qa: fs/snaps/snaptest-upchildrealms.sh failure
Jeff Layton
10:46 AM Backport #49973 (In Progress): pacific: cephfs-top: missing keys in the client_metadata
Jos Collin
09:50 AM Backport #49973 (Resolved): pacific: cephfs-top: missing keys in the client_metadata
https://github.com/ceph/ceph/pull/40402 Backport Bot
09:46 AM Feature #49953 (Pending Backport): cephfs-top : allow configurable stats refresh interval
Venky Shankar
09:46 AM Bug #49736 (Pending Backport): cephfs-top: missing keys in the client_metadata
Venky Shankar
09:39 AM Bug #49736 (Fix Under Review): cephfs-top: missing keys in the client_metadata
Jos Collin
03:55 AM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Jeff Layton wrote:
> Are you exporting your ceph mount via knfsd?
No, I don't have anything related to NFS deploy...
玮文 胡

03/24/2021

11:24 PM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Jeff Layton wrote:
> Yeah, that repeated call makes it look like the client is repeatedly calling in to the MDS for ...
Patrick Donnelly
10:10 PM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Yeah, that repeated call makes it look like the client is repeatedly calling in to the MDS for that inode number. It'... Jeff Layton
09:53 PM Bug #49922 (Fix Under Review): MDS slow request lookupino #0x100 on rank 1 block forever on dispa...
Patrick Donnelly
09:01 PM Bug #49922 (In Progress): MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Patrick Donnelly
08:45 PM Bug #49500: qa: "Assertion `cb_done' failed."
Patrick Donnelly wrote:
> Jeff Layton wrote:
> > Maybe we could lower mds_max_caps_per_client for this test? It def...
Jeff Layton
08:33 PM Bug #49500: qa: "Assertion `cb_done' failed."
Jeff Layton wrote:
> Maybe we could lower mds_max_caps_per_client for this test? It defaults to 1M now, but we could...
Patrick Donnelly
06:52 PM Bug #49605: pybind/mgr/volumes: deadlock on async job hangs finisher thread
Venky Shankar wrote:
> Patrick Donnelly wrote:
> > So the issue is that AsyncJobs.get_job() is called with AsyncJob...
Patrick Donnelly
04:01 PM Backport #49935 (In Progress): pacific: libcephfs: test termination "what(): Too many open files"
Patrick Donnelly
03:59 PM Backport #49520 (In Progress): pacific: client: wake up the front pos waiter
Patrick Donnelly
03:58 PM Backport #49609 (In Progress): pacific: qa: ERROR: test_damaged_dentry, KeyError: 'passed_validat...
Patrick Donnelly
03:58 PM Backport #49930 (In Progress): pacific: mon/MDSMonitor: standby-replay daemons should be removed ...
Patrick Donnelly
03:58 PM Backport #49932 (In Progress): pacific: MDS should return -ENODATA when asked to remove xattr tha...
Patrick Donnelly
03:53 PM Backport #49423 (Resolved): pacific: doc: broken links multimds and kcephfs
Patrick Donnelly
03:49 PM Backport #49877 (Resolved): pacific: doc: Document mds cap acquisition readdir throttle
Patrick Donnelly
03:47 PM Backport #49414 (Resolved): pacific: mgr/nfs: Update about user config
Patrick Donnelly
03:45 PM Backport #49951 (Resolved): pacific: mgr/nfs: Update about cephadm single nfs-ganesha daemon per ...
Patrick Donnelly
10:27 AM Backport #49951 (In Progress): pacific: mgr/nfs: Update about cephadm single nfs-ganesha daemon p...
Varsha Rao
01:50 AM Backport #49951 (Resolved): pacific: mgr/nfs: Update about cephadm single nfs-ganesha daemon per ...
https://github.com/ceph/ceph/pull/40362 Backport Bot
05:43 AM Feature #49953 (Fix Under Review): cephfs-top : allow configurable stats refresh interval
Venky Shankar
05:42 AM Feature #49953 (In Progress): cephfs-top : allow configurable stats refresh interval
Venky Shankar
05:39 AM Feature #49953 (Resolved): cephfs-top : allow configurable stats refresh interval
Rachana Patel
03:11 AM Bug #49928 (Duplicate): client: items pinned in cache preventing unmount x2
Xiubo Li
03:10 AM Bug #49928: client: items pinned in cache preventing unmount x2
For the inode `0x10000001949`, since it has Fb cap and the flush cap snap was delayed, but never did it after that:
...
Xiubo Li
12:43 AM Bug #49928 (In Progress): client: items pinned in cache preventing unmount x2
Xiubo Li
01:50 AM Backport #49950 (Resolved): octopus: mgr/nfs: Update about cephadm single nfs-ganesha daemon per ...
https://github.com/ceph/ceph/pull/40777 Backport Bot
01:47 AM Bug #49936 (Fix Under Review): ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_num <= ...
Patrick Donnelly
01:46 AM Documentation #49921 (Pending Backport): mgr/nfs: Update about cephadm single nfs-ganesha daemon ...
Patrick Donnelly

03/23/2021

03:00 PM Backport #49564: pacific: mon/MonCap: `fs authorize` generates unparseable cap for file system na...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40086
merged
Yuri Weinstein
03:00 PM Backport #49569: pacific: qa: rank_freeze prevents failover on some tests
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40082
merged
Yuri Weinstein
02:56 PM Backport #49474: pacific: nautilus: qa: "Assertion `cb_done' failed."
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40093
merged
Yuri Weinstein
02:55 PM Backport #49512: pacific: client: allow looking up snapped inodes by inode number+snapid tuple
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40092
merged
Yuri Weinstein
02:55 PM Backport #49751: pacific: snap-schedule doc
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40090
merged
Yuri Weinstein
02:53 PM Backport #49561: pacific: qa: file system deletion not complete because starter fs already destroyed
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40089
merged
Yuri Weinstein
02:53 PM Backport #49470: pacific: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40087
merged
Yuri Weinstein
02:51 PM Backport #49517: pacific: pybind/cephfs: DT_REG and DT_LNK values are wrong
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40085
merged
Yuri Weinstein
02:50 PM Backport #49608: pacific: mds: define CephFS errors that replace standard errno values
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40083
merged
Yuri Weinstein
02:49 PM Backport #49612: pacific: qa: racy session evicted check
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40081
merged
Yuri Weinstein
02:48 PM Backport #49630: pacific: qa: slow metadata ops during scrubbing
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40080
merged
Yuri Weinstein
02:47 PM Backport #49631: pacific: mds: don't start purging inodes in the middle of recovery
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40079
merged
Yuri Weinstein
01:24 PM Feature #49942 (Resolved): cephfs-mirror: enable running in HA
cephfs-mirror and mgr/mirroring has the machinery to run/support HA but we do not have any test coverage for such a s... Venky Shankar
09:13 AM Bug #49912: client: dir->dentries inconsistent, both newname and oldname points to same inode, m...
I am doubting that if there has two tasks are doing the rename:
For task1, if it just do _lookup(_INPROGRESS) and ...
Xiubo Li
03:29 AM Bug #49912: client: dir->dentries inconsistent, both newname and oldname points to same inode, m...
@Xiaoxi
Is this reproduceable for you ? If so, how often ? Locally I was trying in a loop by renaming two file for...
Xiubo Li
09:03 AM Bug #49939 (Resolved): cephfs-mirror: be resilient to recreated snapshot during synchronization
The mirror daemon works with snapshots paths. It does rely on snap-id to infer deleted and renamed snapshots, but onc... Venky Shankar
07:04 AM Bug #49605: pybind/mgr/volumes: deadlock on async job hangs finisher thread
Patrick Donnelly wrote:
> So the issue is that AsyncJobs.get_job() is called with AsyncJobs.lock locked. Then gettin...
Venky Shankar
05:43 AM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Logs from mds.0. Also repeating at the same frequency.... 玮文 胡
04:21 AM Backport #49929 (In Progress): pacific: test: test_mirroring_command_idempotency (tasks.cephfs.te...
Venky Shankar
03:05 AM Backport #49929 (Resolved): pacific: test: test_mirroring_command_idempotency (tasks.cephfs.test_...
https://github.com/ceph/ceph/pull/40206 Backport Bot
03:19 AM Bug #49936 (Pending Backport): ceph-fuse: src/include/buffer.h: 1187: FAILED ceph_assert(_num <= ...
... Yanhu Cao
03:10 AM Backport #49935 (Resolved): pacific: libcephfs: test termination "what(): Too many open files"
https://github.com/ceph/ceph/pull/40372 Backport Bot
03:10 AM Backport #49934 (Resolved): octopus: libcephfs: test termination "what(): Too many open files"
https://github.com/ceph/ceph/pull/40776 Backport Bot
03:10 AM Backport #49933 (Rejected): nautilus: MDS should return -ENODATA when asked to remove xattr that ...
Backport Bot
03:10 AM Backport #49932 (Resolved): pacific: MDS should return -ENODATA when asked to remove xattr that d...
https://github.com/ceph/ceph/pull/40371 Backport Bot
03:10 AM Backport #49931 (Rejected): octopus: MDS should return -ENODATA when asked to remove xattr that d...
Backport Bot
03:06 AM Bug #49559 (Pending Backport): libcephfs: test termination "what(): Too many open files"
Patrick Donnelly
03:05 AM Bug #49621 (Resolved): qa: ERROR: test_fragmented_injection (tasks.cephfs.test_data_scan.TestData...
Patrick Donnelly
03:05 AM Backport #49930 (Resolved): pacific: mon/MDSMonitor: standby-replay daemons should be removed whe...
https://github.com/ceph/ceph/pull/40325 Backport Bot
03:05 AM Bug #49833 (Pending Backport): MDS should return -ENODATA when asked to remove xattr that doesn't...
Patrick Donnelly
03:04 AM Bug #49822 (Pending Backport): test: test_mirroring_command_idempotency (tasks.cephfs.test_admin....
Patrick Donnelly
03:03 AM Bug #49719 (Pending Backport): mon/MDSMonitor: standby-replay daemons should be removed when the ...
Patrick Donnelly
02:53 AM Bug #49928 (Duplicate): client: items pinned in cache preventing unmount x2
... Patrick Donnelly

03/22/2021

05:04 PM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
Jeff Layton wrote:
> Was there anything useful in the logs from mds 1 about the op and what state it's in?
I set ...
玮文 胡
03:31 PM Bug #49922: MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
I'm unfamiliar with the MDS code so some notes as I peruse it:
Ok, so the TrackedOp entries get put on the list wh...
Jeff Layton
12:05 PM Bug #49922 (Resolved): MDS slow request lookupino #0x100 on rank 1 block forever on dispatched
We have two MDSs deployed by cephadm.
Several hours ago, we got a health warning:...
玮文 胡
02:02 PM Bug #49912: client: dir->dentries inconsistent, both newname and oldname points to same inode, m...
I think that after the mv, the directory should no longer be considered ORDERED. We probably _can_ consider it comple... Jeff Layton
01:41 PM Bug #49912 (Triaged): client: dir->dentries inconsistent, both newname and oldname points to same...
Patrick Donnelly
01:51 PM Bug #49845 (Resolved): qa: failed umount in test_volumes
The client kernel in this test had a bad patch in it that has since been fixed. See:
https://tracker.ceph.com/...
Jeff Layton
12:44 PM Backport #49685 (In Progress): pacific: ls -l in cephfs-shell tries to chase symlinks when stat'i...
https://github.com/ceph/ceph/pull/40308 Varsha Rao
12:36 PM Backport #49713 (In Progress): pacific: mgr/nfs: Add interface to update export
https://github.com/ceph/ceph/pull/40307 Varsha Rao
12:23 PM Backport #49414 (In Progress): pacific: mgr/nfs: Update about user config
Varsha Rao
11:58 AM Documentation #49921 (In Progress): mgr/nfs: Update about cephadm single nfs-ganesha daemon per h...
Varsha Rao
11:38 AM Documentation #49921 (Resolved): mgr/nfs: Update about cephadm single nfs-ganesha daemon per host...
Varsha Rao
03:45 AM Feature #49811: mds: collect I/O sizes from client for cephfs-top
@Patric, @Jeff
Comparing the iotop/iostat:
We may also need to collect the average IO READ/WRITE speed per-seco...
Xiubo Li
03:23 AM Feature #49811 (In Progress): mds: collect I/O sizes from client for cephfs-top
Xiubo Li
02:33 AM Bug #49605: pybind/mgr/volumes: deadlock on async job hangs finisher thread
So the issue is that AsyncJobs.get_job() is called with AsyncJobs.lock locked. Then getting the next job involves ope... Patrick Donnelly
02:30 AM Feature #46866: kceph: add metric for number of pinned capabilities
Pushing the kclient patchwork. Xiubo Li

03/21/2021

05:50 PM Bug #49605 (In Progress): pybind/mgr/volumes: deadlock on async job hangs finisher thread
... Patrick Donnelly
04:51 PM Bug #49912 (Resolved): client: dir->dentries inconsistent, both newname and oldname points to sam...
we have an applications that use FS as a lock --- an empty file named .dw_gem2_cmn_sd_{INPROGRESS/COMPLETE} , applic... Xiaoxi Chen

03/20/2021

04:19 AM Backport #49903 (In Progress): nautilus: mgr/volumes: setuid and setgid file bits are not retaine...
Kotresh Hiremath Ravishankar
03:15 AM Backport #49903 (Resolved): nautilus: mgr/volumes: setuid and setgid file bits are not retained a...
https://github.com/ceph/ceph/pull/40270 Backport Bot
04:01 AM Backport #49904 (In Progress): octopus: mgr/volumes: setuid and setgid file bits are not retained...
Kotresh Hiremath Ravishankar
03:15 AM Backport #49904 (Resolved): octopus: mgr/volumes: setuid and setgid file bits are not retained af...
https://github.com/ceph/ceph/pull/40268 Backport Bot
03:29 AM Backport #49905 (In Progress): pacific: mgr/volumes: setuid and setgid file bits are not retained...
Kotresh Hiremath Ravishankar
03:15 AM Backport #49905 (Resolved): pacific: mgr/volumes: setuid and setgid file bits are not retained af...
https://github.com/ceph/ceph/pull/40267 Backport Bot
03:12 AM Bug #49882 (Pending Backport): mgr/volumes: setuid and setgid file bits are not retained after a ...
Patrick Donnelly

03/19/2021

09:46 PM Bug #49605: pybind/mgr/volumes: deadlock on async job hangs finisher thread
debugging pr https://github.com/ceph/ceph/pull/40264 Patrick Donnelly
09:20 PM Bug #49605: pybind/mgr/volumes: deadlock on async job hangs finisher thread
/ceph/teuthology-archive/pdonnell-2021-03-15_22:16:56-fs-wip-pdonnell-testing-20210315.182203-distro-basic-smithi/596... Patrick Donnelly
06:13 PM Backport #49852 (In Progress): pacific: mds: race of fetching large dirfrag
singuliere _
06:12 PM Backport #49854 (In Progress): pacific: client: crashed in cct->_conf.get_val() in Client::start_...
singuliere _
06:12 PM Backport #49877 (In Progress): pacific: doc: Document mds cap acquisition readdir throttle
singuliere _
02:46 PM Bug #49500: qa: "Assertion `cb_done' failed."
Maybe we could lower mds_max_caps_per_client for this test? It defaults to 1M now, but we could take that down to 500... Jeff Layton
02:39 PM Bug #49500: qa: "Assertion `cb_done' failed."
I'm not sure that setting is enough to explain this. AFAICT, that setting is only consulted in notify_health(), so I ... Jeff Layton
12:57 PM Backport #49753 (In Progress): pacific: cephfs-mirror: add mirror peers via bootstrapping
Venky Shankar
12:57 PM Backport #49765 (In Progress): pacific: cephfs-mirror: symbolic links do not get synchronized at ...
Venky Shankar
10:07 AM Feature #48943 (Resolved): cephfs-mirror: display cephfs mirror instances in `ceph status` command
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
10:06 AM Bug #49419 (Resolved): cephfs-mirror: dangling pointer in PeerReplayer
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:12 AM Bug #49882 (Fix Under Review): mgr/volumes: setuid and setgid file bits are not retained after a ...
Kotresh Hiremath Ravishankar

03/18/2021

03:07 PM Bug #49882 (In Progress): mgr/volumes: setuid and setgid file bits are not retained after a subvo...
Kotresh Hiremath Ravishankar
02:23 PM Bug #49882 (Resolved): mgr/volumes: setuid and setgid file bits are not retained after a subvolum...
setuid and setgid file bits are not retained after a subvolume snapshot restore
Reproducer on vstart cluster:
#...
Kotresh Hiremath Ravishankar
01:53 PM Backport #49686: pacific: cephfs-mirror: display cephfs mirror instances in `ceph status` command
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/39973
m...
Nathan Cutler
01:53 PM Backport #49432: pacific: cephfs-mirror: dangling pointer in PeerReplayer
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/39810
m...
Nathan Cutler
01:26 PM Bug #49873: ceph_lremovexattr does not return error on file in ceph pacific
Jeff Layton wrote:
> John, I fixed a similar sounding bug in the MDS yesterday:
>
> https://tracker.ceph.com/...
John Mulligan
01:01 PM Bug #49873: ceph_lremovexattr does not return error on file in ceph pacific
John, I fixed a similar sounding bug in the MDS yesterday:
https://tracker.ceph.com/issues/49833
Are you ab...
Jeff Layton
09:29 AM Bug #49736: cephfs-top: missing keys in the client_metadata
https://github.com/ceph/ceph/pull/40210 Jos Collin
04:50 AM Bug #44100: cephfs rsync kworker high load.
We have also experienced a similar issue, where kernel mount performance degraded severely while doing rsync (running... Andras Sali
02:45 AM Backport #49877 (Resolved): pacific: doc: Document mds cap acquisition readdir throttle
https://github.com/ceph/ceph/pull/40250 Backport Bot
02:41 AM Documentation #49763 (Pending Backport): doc: Document mds cap acquisition readdir throttle
Patrick Donnelly

03/17/2021

09:47 PM Feature #48791 (Need More Info): mds: support file block size
Patrick Donnelly
09:45 PM Feature #41073: cephfs-sync: tool for synchronizing cephfs snapshots to remote target
Milind what's the status of this tickeT? Patrick Donnelly
07:03 PM Bug #49873: ceph_lremovexattr does not return error on file in ceph pacific
I'll also note that I did find the following issue
https://tracker.ceph.com/issues/49833
But forgot to reference ...
John Mulligan
07:00 PM Bug #49873 (Triaged): ceph_lremovexattr does not return error on file in ceph pacific
John Mulligan wrote:
> To try and clarify:
>
> The xattr is set on the link. There should be no xattr of that nam...
Patrick Donnelly
06:52 PM Bug #49873: ceph_lremovexattr does not return error on file in ceph pacific
To try and clarify:
The xattr is set on the link. There should be no xattr of that name on the file the link point...
John Mulligan
06:46 PM Bug #49873: ceph_lremovexattr does not return error on file in ceph pacific
John Mulligan wrote:
> While running our go-ceph CI against pacific for the first time our CI failed in the xattr te...
Patrick Donnelly
06:24 PM Bug #49873 (Duplicate): ceph_lremovexattr does not return error on file in ceph pacific
While running our go-ceph CI against pacific for the first time our CI failed in the xattr tests.
It expected a call...
John Mulligan
04:02 PM Bug #49859 (Triaged): Snapshot schedules are not deleted after enabling/disabling snap module
Patrick Donnelly
10:15 AM Bug #49859 (Triaged): Snapshot schedules are not deleted after enabling/disabling snap module
Assuming the following:... Sébastien Han
03:41 PM Bug #49559: libcephfs: test termination "what(): Too many open files"
Xiubo Li wrote:
> It seems the tests will fire many event works, which will open many fds, the last issue about this...
Jeff Layton
01:48 PM Backport #49686 (Resolved): pacific: cephfs-mirror: display cephfs mirror instances in `ceph stat...
Venky Shankar
01:46 PM Backport #49432 (Resolved): pacific: cephfs-mirror: dangling pointer in PeerReplayer
Venky Shankar
10:02 AM Bug #49621: qa: ERROR: test_fragmented_injection (tasks.cephfs.test_data_scan.TestDataScan)
There is another error log ahead of the above call trace:... Xiubo Li
09:59 AM Bug #49621 (Fix Under Review): qa: ERROR: test_fragmented_injection (tasks.cephfs.test_data_scan....
Xiubo Li
04:28 AM Bug #49621 (In Progress): qa: ERROR: test_fragmented_injection (tasks.cephfs.test_data_scan.TestD...
Xiubo Li
04:28 AM Feature #49811: mds: collect I/O sizes from client for cephfs-top
Sure, will work on it. Thanks. Xiubo Li
03:30 AM Backport #49854 (Resolved): pacific: client: crashed in cct->_conf.get_val() in Client::start_tic...
https://github.com/ceph/ceph/pull/40251 Backport Bot
03:25 AM Backport #49853 (Resolved): nautilus: mds: race of fetching large dirfrag
https://github.com/ceph/ceph/pull/40720 Backport Bot
03:25 AM Backport #49852 (Resolved): pacific: mds: race of fetching large dirfrag
https://github.com/ceph/ceph/pull/40252 Backport Bot
03:25 AM Bug #49725 (Pending Backport): client: crashed in cct->_conf.get_val() in Client::start_tick_thre...
Patrick Donnelly
03:25 AM Backport #49851 (Resolved): octopus: mds: race of fetching large dirfrag
https://github.com/ceph/ceph/pull/40774 Backport Bot
03:23 AM Bug #49617 (Pending Backport): mds: race of fetching large dirfrag
Patrick Donnelly

03/16/2021

08:42 PM Bug #49843 (Fix Under Review): qa: fs/snaps/snaptest-upchildrealms.sh failure
Bad error handling in this patch:
https://lore.kernel.org/ceph-devel/20210315180717.266155-3-jlayton@kernel.or...
Jeff Layton
08:12 PM Bug #49843: qa: fs/snaps/snaptest-upchildrealms.sh failure
This may be fallout from the recent snapdir handling fixes. I'll take a look.
Jeff Layton
07:53 PM Bug #49843 (Resolved): qa: fs/snaps/snaptest-upchildrealms.sh failure
... Patrick Donnelly
08:01 PM Bug #49845 (Resolved): qa: failed umount in test_volumes
... Patrick Donnelly
07:21 PM Bug #49837 (Fix Under Review): mgr/pybind/snap_schedule: do not fail when no fs snapshots are ava...
Patrick Donnelly
05:16 PM Bug #49837 (Resolved): mgr/pybind/snap_schedule: do not fail when no fs snapshots are available
When calling the json output, we should not return any error but just an empty dict:... Sébastien Han
05:35 PM Bug #49833 (Fix Under Review): MDS should return -ENODATA when asked to remove xattr that doesn't...
Patrick Donnelly
04:36 PM Bug #49833: MDS should return -ENODATA when asked to remove xattr that doesn't exist
I'll take this one since I have a patch (and testcase). Jeff Layton
04:22 PM Bug #49833 (Triaged): MDS should return -ENODATA when asked to remove xattr that doesn't exist
Patrick Donnelly
04:16 PM Bug #49833 (Resolved): MDS should return -ENODATA when asked to remove xattr that doesn't exist
This patch adds a small gtest that shows that the handling of removexattr is wrong:... Jeff Layton
04:50 PM Bug #49834 (Won't Fix - EOL): octopus: qa: test_statfs_on_deleted_fs failure
https://pulpito.ceph.com/yuriw-2021-03-13_22:13:22-fs-wip-yuriw-octopus-15.2.10-distro-basic-smithi/5962994/
Test ...
Patrick Donnelly
04:34 PM Bug #49826: Multiple nfs-ganesha instances and strays objects in CephFS
The strays behavior makes some sense, since we don't really do anything client-side to notify the application when th... Jeff Layton
04:27 PM Bug #49826: Multiple nfs-ganesha instances and strays objects in CephFS
Aleksandr Rudenko wrote:
> Usual stray objects are purged after 10-20 secs. But not in this case. In this case stray...
Patrick Donnelly
07:15 AM Bug #49826 (New): Multiple nfs-ganesha instances and strays objects in CephFS
Hi!
We have one CephFS and two standalone ganesha instances on different hosts which export the same directory.
W...
Aleksandr Rudenko
12:15 PM Bug #49736: cephfs-top: missing keys in the client_metadata
Venky Shankar wrote:
MDSRank::dump_sessions() has this filter:
>
> [...]
>
> ... which might be the reason tha...
Jos Collin
05:34 AM Bug #49822 (Fix Under Review): test: test_mirroring_command_idempotency (tasks.cephfs.test_admin....
Venky Shankar
04:09 AM Bug #49822 (Resolved): test: test_mirroring_command_idempotency (tasks.cephfs.test_admin.TestMirr...
With https://github.com/ceph/ceph/pull/39845/commits/a04010e9490aa726d219c41139c27417dac836e2 peer_add monitor interf... Venky Shankar
02:46 AM Bug #49719 (Fix Under Review): mon/MDSMonitor: standby-replay daemons should be removed when the ...
Patrick Donnelly

03/15/2021

06:25 PM Feature #49811 (Resolved): mds: collect I/O sizes from client for cephfs-top
An average is a start but a histogram would be better for this kind of data. Patrick Donnelly
05:44 AM Backport #49520: pacific: client: wake up the front pos waiter
Patrick Donnelly wrote:
> Xiubo, please do this backport.
The backport PR: https://github.com/ceph/ceph/pull/40109
Xiubo Li
05:38 AM Backport #49609: pacific: qa: ERROR: test_damaged_dentry, KeyError: 'passed_validation'
Patrick Donnelly wrote:
> Xiubo, please do this backport.
The backport PR: https://github.com/ceph/ceph/pull/40108
Xiubo Li

03/12/2021

09:10 PM Backport #49634 (In Progress): pacific: Windows CephFS support - ceph-dokan
Patrick Donnelly
02:42 PM Backport #49634: pacific: Windows CephFS support - ceph-dokan
please link this Backport tracker issue with GitHub PR https://github.com/ceph/ceph/pull/40069
ceph-backport.sh versi...
Lucian Petrut
09:08 PM Backport #49432 (In Progress): pacific: cephfs-mirror: dangling pointer in PeerReplayer
Patrick Donnelly
08:59 PM Backport #49432 (Need More Info): pacific: cephfs-mirror: dangling pointer in PeerReplayer
Patrick Donnelly
09:06 PM Backport #49685 (Need More Info): pacific: ls -l in cephfs-shell tries to chase symlinks when sta...
Patrick Donnelly
09:05 PM Backport #49474 (In Progress): pacific: nautilus: qa: "Assertion `cb_done' failed."
Patrick Donnelly
09:03 PM Backport #49512 (In Progress): pacific: client: allow looking up snapped inodes by inode number+s...
Patrick Donnelly
09:01 PM Backport #49610 (In Progress): pacific: qa: mds removed because trimming for too long with valgrind
Patrick Donnelly
08:59 PM Backport #49765 (Need More Info): pacific: cephfs-mirror: symbolic links do not get synchronized ...
Patrick Donnelly
12:55 PM Backport #49765 (Resolved): pacific: cephfs-mirror: symbolic links do not get synchronized at times
https://github.com/ceph/ceph/pull/40206 Backport Bot
08:59 PM Backport #49753 (Need More Info): pacific: cephfs-mirror: add mirror peers via bootstrapping
Patrick Donnelly
08:59 PM Backport #49713 (Need More Info): pacific: mgr/nfs: Add interface to update export
Varsha, please do this backport. Patrick Donnelly
08:58 PM Backport #49609 (Need More Info): pacific: qa: ERROR: test_damaged_dentry, KeyError: 'passed_vali...
Xiubo, please do this backport. Patrick Donnelly
08:58 PM Backport #49751 (In Progress): pacific: snap-schedule doc
Patrick Donnelly
08:56 PM Backport #49561 (In Progress): pacific: qa: file system deletion not complete because starter fs ...
Patrick Donnelly
08:55 PM Backport #49414 (Need More Info): pacific: mgr/nfs: Update about user config
Varsha, please do this one. Patrick Donnelly
08:55 PM Backport #49470 (In Progress): pacific: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
Patrick Donnelly
08:53 PM Backport #49564 (In Progress): pacific: mon/MonCap: `fs authorize` generates unparseable cap for ...
Patrick Donnelly
08:51 PM Backport #49517 (In Progress): pacific: pybind/cephfs: DT_REG and DT_LNK values are wrong
Patrick Donnelly
08:49 PM Backport #49520 (Need More Info): pacific: client: wake up the front pos waiter
Xiubo, please do this backport. Patrick Donnelly
08:49 PM Backport #49563 (In Progress): pacific: qa: run fs:verify with tcmalloc
Patrick Donnelly
08:48 PM Backport #49608 (In Progress): pacific: mds: define CephFS errors that replace standard errno values
Patrick Donnelly
08:46 PM Backport #49569 (In Progress): pacific: qa: rank_freeze prevents failover on some tests
Patrick Donnelly
08:44 PM Backport #49612 (In Progress): pacific: qa: racy session evicted check
Patrick Donnelly
08:43 PM Backport #49630 (In Progress): pacific: qa: slow metadata ops during scrubbing
Patrick Donnelly
08:41 PM Backport #49631 (In Progress): pacific: mds: don't start purging inodes in the middle of recovery
Patrick Donnelly
04:47 PM Documentation #49763 (Fix Under Review): doc: Document mds cap acquisition readdir throttle
Patrick Donnelly
11:19 AM Documentation #49763 (In Progress): doc: Document mds cap acquisition readdir throttle
Kotresh Hiremath Ravishankar
08:13 AM Documentation #49763 (Resolved): doc: Document mds cap acquisition readdir throttle
Documentation for mds cap acquisition readdir throttle is missing which is introduced
with the PR [1]. This needs to...
Kotresh Hiremath Ravishankar
12:50 PM Bug #49711 (Pending Backport): cephfs-mirror: symbolic links do not get synchronized at times
Venky Shankar
07:27 AM Bug #49736: cephfs-top: missing keys in the client_metadata
Patrick Donnelly wrote:
> > Either cephfs-top should handle the missing metadata entries or the mgr/stats should fil...
Venky Shankar
02:20 AM Bug #49559: libcephfs: test termination "what(): Too many open files"
It seems the tests will fire many event works, which will open many fds, the last issue about this was cause by the e... Xiubo Li
12:46 AM Bug #49725: client: crashed in cct->_conf.get_val() in Client::start_tick_thread()
With the upstream code, I can reproduce it around 10 time by running 8 hours at night. Xiubo Li

03/11/2021

08:05 PM Feature #49304 (Fix Under Review): nfs-ganesha: plumb xattr support into FSAL_CEPH
I've proposed some patches for ganesha to update its xattr implementation (which was based on an earlier draft of the... Jeff Layton
08:03 PM Bug #49559: libcephfs: test termination "what(): Too many open files"
We still have the coredump from this test failure, but the x86_64 binaries have been reaped so we can't analyze it. I... Jeff Layton
06:30 PM Bug #49559: libcephfs: test termination "what(): Too many open files"
Logging the RLIMIT_NOFILE we set should be no problem.
It may be tough to get a file descriptor in the same proces...
Jeff Layton
05:36 PM Bug #49559: libcephfs: test termination "what(): Too many open files"
Jeff Layton wrote:
> Xiubo Li wrote:
> > IMO, for this we can lower down the concurent threads 128 --> 32 and can t...
Patrick Donnelly
02:49 PM Bug #49559: libcephfs: test termination "what(): Too many open files"
Xiubo Li wrote:
> IMO, for this we can lower down the concurent threads 128 --> 32 and can try it serveral times. Fr...
Jeff Layton
05:40 PM Backport #49753 (Resolved): pacific: cephfs-mirror: add mirror peers via bootstrapping
https://github.com/ceph/ceph/pull/40206 Backport Bot
05:39 PM Bug #49500: qa: "Assertion `cb_done' failed."
Jeff Layton wrote:
> Yeah, looking at the MDS logs from the above run. I don't see any occurrences of the word "reca...
Patrick Donnelly
03:17 PM Bug #49500: qa: "Assertion `cb_done' failed."
Yeah, looking at the MDS logs from the above run. I don't see any occurrences of the word "recall" in there and at le... Jeff Layton
03:01 PM Bug #49500: qa: "Assertion `cb_done' failed."
With the most recent change to make that variable atomic, I doubt we're hitting cache-coherency problems. It seems mo... Jeff Layton
05:35 PM Feature #49619 (Pending Backport): cephfs-mirror: add mirror peers via bootstrapping
Patrick Donnelly
05:32 PM Bug #49736 (Triaged): cephfs-top: missing keys in the client_metadata
> Either cephfs-top should handle the missing metadata entries or the mgr/stats should fill in defaults until it can ... Patrick Donnelly
01:04 PM Bug #49736 (Resolved): cephfs-top: missing keys in the client_metadata
There are missing keys in the mgr/stats client_metadata for some clients, which causes the exception mentioned in the... Jos Collin
05:25 PM Backport #49752 (Resolved): octopus: snap-schedule doc
https://github.com/ceph/ceph/pull/40775 Backport Bot
05:25 PM Backport #49751 (Resolved): pacific: snap-schedule doc
https://github.com/ceph/ceph/pull/40090 Backport Bot
05:23 PM Documentation #48017 (Pending Backport): snap-schedule doc
Patrick Donnelly
05:04 PM Feature #6373: kcephfs: qa: test fscache
Jeff Layton wrote:
> The yaml frags that let you test fscache are machine-specific since the clients need to be prov...
Patrick Donnelly
04:59 PM Feature #6373: kcephfs: qa: test fscache
The yaml frags that let you test fscache are machine-specific since the clients need to be provisioned with an extra ... Jeff Layton
04:51 PM Feature #6373 (In Progress): kcephfs: qa: test fscache
Jeff Layton
02:14 PM Bug #49725 (Fix Under Review): client: crashed in cct->_conf.get_val() in Client::start_tick_thre...
Xiubo Li
01:11 AM Bug #49725 (Resolved): client: crashed in cct->_conf.get_val() in Client::start_tick_thread()
The call trace:... Xiubo Li

03/10/2021

05:59 PM Bug #49720 (Resolved): mon/MDSMonitor: do not pointlessly kill standbys that are incompatible wit...
During a rolling upgrade, standbys may suicide once the CompatSet for the FSMap is updated. This needlessly complicat... Patrick Donnelly
05:42 PM Bug #49719 (Resolved): mon/MDSMonitor: standby-replay daemons should be removed when the flag is ...
Patrick Donnelly
03:05 PM Backport #49713 (Resolved): pacific: mgr/nfs: Add interface to update export
Backport Bot
03:05 PM Backport #49712 (Rejected): octopus: mgr/nfs: Add interface to update export
Backport Bot
03:01 PM Bug #49133 (Resolved): mgr/nfs: Rook does not support restart of services, handle the NotImplemen...
Backported with #45746. Patrick Donnelly
03:00 PM Feature #45746 (Pending Backport): mgr/nfs: Add interface to update export
Patrick Donnelly
02:57 PM Bug #49122: vstart: Rados url error
@singuliere none please do not delete the links between the parent ticket and the backport ticket. Just close the bac... Patrick Donnelly
06:33 AM Bug #49122 (Resolved): vstart: Rados url error
singuliere _
06:32 AM Bug #49122: vstart: Rados url error
Removing the "pacific" backport because the PR including the fix is already backported via https://tracker.ceph.com/i... singuliere _
02:27 PM Bug #49711 (Fix Under Review): cephfs-mirror: symbolic links do not get synchronized at times
Venky Shankar
02:21 PM Bug #49711 (Resolved): cephfs-mirror: symbolic links do not get synchronized at times
Due to this problematic code in src/tools/cephfs_mirror/PeerReplayer.cc:... Venky Shankar
06:52 AM Backport #49423 (In Progress): pacific: doc: broken links multimds and kcephfs
singuliere _
05:00 AM Backport #49423 (New): pacific: doc: broken links multimds and kcephfs
The file name and path are different in pacific. See https://github.com/ceph/ceph/blob/pacific/doc/dev/developer_guid... Jos Collin
06:29 AM Backport #49412 (Rejected): pacific: vstart: Rados url error
singuliere _
04:58 AM Documentation #49372: doc: broken links multimds and kcephfs
The file name and path are different in pacific. See https://github.com/ceph/ceph/blob/pacific/doc/dev/developer_guid... Jos Collin

03/09/2021

11:47 PM Backport #49423 (Rejected): pacific: doc: broken links multimds and kcephfs
singuliere _
11:45 PM Documentation #49372: doc: broken links multimds and kcephfs
The "documentation was not backported to pacific":https://github.com/ceph/ceph/pull/37949 nor is it associated with a... singuliere _
11:28 PM Backport #49412 (In Progress): pacific: vstart: Rados url error
singuliere _
11:27 PM Backport #49346 (In Progress): pacific: vstart: volumes/nfs interface complaints cluster does not...
singuliere _
11:25 PM Backport #49686 (In Progress): pacific: cephfs-mirror: display cephfs mirror instances in `ceph s...
singuliere _
09:45 PM Backport #49686 (Resolved): pacific: cephfs-mirror: display cephfs mirror instances in `ceph stat...
https://github.com/ceph/ceph/pull/39973 Backport Bot
11:23 PM Backport #49687 (In Progress): pacific: client: add metric for number of pinned capabilities
singuliere _
09:45 PM Backport #49687 (Resolved): pacific: client: add metric for number of pinned capabilities
https://github.com/ceph/ceph/pull/39972 Backport Bot
10:23 PM Bug #49672: nautilus: "Error EINVAL: invalid command" in fs-nautilus-distro-basic-smithi
https://github.com/ceph/ceph/pull/39960 merged Yuri Weinstein
09:00 PM Bug #49672 (Fix Under Review): nautilus: "Error EINVAL: invalid command" in fs-nautilus-distro-ba...
First occurrence https://sentry.ceph.com/organizations/ceph/issues/4718/events/3eb2f218e5b44406a9f1fd54ef90c5b4/?proj... Neha Ojha
07:51 PM Bug #49672: nautilus: "Error EINVAL: invalid command" in fs-nautilus-distro-basic-smithi
https://pulpito.ceph.com/teuthology-2021-03-06_04:20:17-upgrade:luminous-x-nautilus-distro-basic-smithi/ Neha Ojha
04:22 PM Bug #49672 (Resolved): nautilus: "Error EINVAL: invalid command" in fs-nautilus-distro-basic-smithi
This is for 14.2.17 release
Run: https://pulpito.ceph.com/yuriw-2021-03-08_16:51:42-fs-nautilus-distro-basic-smith...
Yuri Weinstein
09:55 PM Bug #49684 (Fix Under Review): qa: fs:cephadm mount does not wait for mds to be created
Patrick Donnelly
09:48 PM Bug #49684 (In Progress): qa: fs:cephadm mount does not wait for mds to be created
Patrick Donnelly
09:29 PM Bug #49684 (Resolved): qa: fs:cephadm mount does not wait for mds to be created
... Patrick Donnelly
09:41 PM Feature #46865 (Pending Backport): client: add metric for number of pinned capabilities
Patrick Donnelly
09:40 PM Feature #48943 (Pending Backport): cephfs-mirror: display cephfs mirror instances in `ceph status...
Patrick Donnelly
09:40 PM Backport #49685 (Resolved): pacific: ls -l in cephfs-shell tries to chase symlinks when stat'ing ...
Backport Bot
09:38 PM Bug #48912 (Pending Backport): ls -l in cephfs-shell tries to chase symlinks when stat'ing and er...
Patrick Donnelly
09:37 PM Bug #49511 (Resolved): qa: "AttributeError: 'NoneType' object has no attribute 'mon_manager'"
Patrick Donnelly
08:35 AM Feature #40401 (Resolved): mgr/volumes: allow/deny r/rw access of auth IDs to subvolume and subvo...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:34 AM Feature #44928 (Resolved): mgr/volumes: evict clients based on auth ID and subvolume mounted
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:34 AM Feature #44931 (Resolved): mgr/volumes: get the list of auth IDs that have been granted access to...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:33 AM Bug #48501 (Resolved): pybind/mgr/volumes: inherited snapshots should be filtered out of snapshot...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:32 AM Bug #48830 (Resolved): pacific: qa: :ERROR: test_idempotency
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:31 AM Bug #49192 (Resolved): qa::ERROR: test_recover_auth_metadata_during_authorize
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:31 AM Bug #49294 (Resolved): pacific: pybind/ceph_volume_client: volume authorize/deauthorize crashes w...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:31 AM Bug #49374 (Resolved): mgr/volumes: Bump up the AuthMetadataManager's version to 6
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
07:45 AM Bug #49662 (Resolved): ceph-dokan improvements for additional mounts
This PR [1] adds a few ceph-dokan improvements, mostly targeting additional fs mounts:
* a "unmap" command
* avoi...
Lucian Petrut

03/08/2021

10:20 PM Bug #45344 (Resolved): doc: Table Of Contents doesn't work
An update to the UI made by Kefu Chai in March 2021 fixes this issue. Zac Dover
09:22 PM Documentation #48017 (Fix Under Review): snap-schedule doc
Patrick Donnelly
11:55 AM Documentation #48017: snap-schedule doc
The module was only backported to octopus, so we can probably skip the doc backport to nautilus. Jan Fajerski
07:40 PM Backport #49431 (Resolved): octopus: mgr/volumes: Bump up the AuthMetadataManager's version to 6
Patrick Donnelly
12:20 PM Backport #49431 (In Progress): octopus: mgr/volumes: Bump up the AuthMetadataManager's version to 6
Kotresh Hiremath Ravishankar
07:40 PM Backport #49508 (Resolved): octopus: pybind/ceph_volume_client: volume authorize/deauthorize cras...
Patrick Donnelly
12:19 PM Backport #49508 (In Progress): octopus: pybind/ceph_volume_client: volume authorize/deauthorize c...
Kotresh Hiremath Ravishankar
07:30 PM Backport #49266 (Resolved): octopus: qa::ERROR: test_recover_auth_metadata_during_authorize
Patrick Donnelly
07:30 PM Backport #49230 (Resolved): octopus: qa: :ERROR: test_idempotency
Patrick Donnelly
07:30 PM Backport #49029 (Resolved): octopus: mgr/volumes: evict clients based on auth ID and subvolume mo...
Patrick Donnelly
07:30 PM Backport #48900 (Resolved): octopus: mgr/volumes: get the list of auth IDs that have been granted...
Patrick Donnelly
07:29 PM Backport #48858 (Resolved): octopus: pybind/mgr/volumes: inherited snapshots should be filtered o...
Patrick Donnelly
07:29 PM Backport #48196 (Resolved): octopus: mgr/volumes: allow/deny r/rw access of auth IDs to subvolume...
Patrick Donnelly
02:48 PM Bug #49621: qa: ERROR: test_fragmented_injection (tasks.cephfs.test_data_scan.TestDataScan)
This only failed in the local test, will work on it tommorrow. Xiubo Li
02:45 PM Bug #49559 (Triaged): libcephfs: test termination "what(): Too many open files"
Patrick Donnelly
02:44 PM Bug #49644: vstart_runner: run_ceph_w() doesn't work with shell=True
This PR exposes this issue and adds a workaround for it - https://github.com/ceph/ceph/pull/38443. Rishabh Dave
02:43 PM Bug #49644 (In Progress): vstart_runner: run_ceph_w() doesn't work with shell=True
Patrick Donnelly
09:05 AM Bug #49644 (New): vstart_runner: run_ceph_w() doesn't work with shell=True
Setting @shell@ to @True@ leads to a crash when @tasks.mgr.test_module_selftest.TestModuleSelftest.test_selftest_clus... Rishabh Dave
12:51 PM Bug #48805: mds: "cluster [WRN] Scrub error on inode 0x1000000039d (/client.0/tmp/blogbench-1.0/s...
I'm unable to comment on the exact teuthology run mentioned in the description.
However, with the testing so far, th...
Milind Changire
08:17 AM Backport #49429 (Resolved): pacific: mgr/volumes: Bump up the AuthMetadataManager's version to 6
Kotresh Hiremath Ravishankar
 

Also available in: Atom