Project

General

Profile

Activity

From 05/07/2021 to 06/05/2021

06/05/2021

02:10 AM Bug #51077 (Triaged): MDSMonitor: crash when attempting to mount cephfs
Patrick Donnelly

06/04/2021

08:09 AM Bug #51092 (Resolved): mds: Timed out waiting for MDS daemons to become healthy
From https://pulpito.ceph.com/xiubli-2021-06-03_11:25:58-fs:functional:-wip-lxb-20210603-45434-pg-num-distro-basic-sm... Xiubo Li
07:11 AM Backport #51084 (In Progress): pacific: mgr/volumes: hang when removing subvolume when pools are ...
Kotresh Hiremath Ravishankar
02:37 AM Bug #51062: mds,client: suppport getvxattr RPC
Jeff Layton wrote:
> kclient, but I don't think it matters. This is a server-side xattr, so it comes down to allowin...
Patrick Donnelly
02:15 AM Backport #51085 (In Progress): pacific: mds: scrub error on inode 0x1
Patrick Donnelly

06/03/2021

11:56 PM Bug #51062: mds,client: suppport getvxattr RPC
kclient, but I don't think it matters. This is a server-side xattr, so it comes down to allowing it to be queried via... Jeff Layton
11:04 PM Bug #51062: mds,client: suppport getvxattr RPC
Jeff Layton wrote:
> Playing with ephemeral pinning today, and found that I can't query ceph.dir.pin.random:
>
> ...
Patrick Donnelly
11:03 PM Backport #50539 (Rejected): octopus: mgr/pybind/snap_schedule: do not fail when no fs snapshots a...
https://tracker.ceph.com/issues/49837#note-8 Patrick Donnelly
11:03 PM Bug #49837: mgr/pybind/snap_schedule: do not fail when no fs snapshots are available
Cory Snyder wrote:
> @Patrick Donnelly - it seems that the snap_schedule module was added in Pacific, so I don't bel...
Patrick Donnelly
11:00 PM Backport #47020 (Resolved): nautilus: client: shutdown race fails with status 141
Patrick Donnelly
03:13 PM Backport #47020: nautilus: client: shutdown race fails with status 141
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/41593
merged
Yuri Weinstein
08:40 PM Backport #51087 (Need More Info): pacific: mds: segfault printing unknown metric
Patrick Donnelly
08:40 PM Backport #51087 (Resolved): pacific: mds: segfault printing unknown metric
https://github.com/ceph/ceph/pull/41596 Backport Bot
08:37 PM Bug #51067 (Pending Backport): mds: segfault printing unknown metric
Patrick Donnelly
02:08 PM Bug #51067 (Fix Under Review): mds: segfault printing unknown metric
Patrick Donnelly
08:35 PM Backport #51086 (Resolved): pacific: qa: fs:mirror: reduced data availability
https://github.com/ceph/ceph/pull/41947 Backport Bot
08:35 PM Backport #51085 (Resolved): pacific: mds: scrub error on inode 0x1
https://github.com/ceph/ceph/pull/41685 Backport Bot
08:34 PM Bug #50976 (Pending Backport): mds: scrub error on inode 0x1
Patrick Donnelly
08:32 PM Bug #50867 (Pending Backport): qa: fs:mirror: reduced data availability
Patrick Donnelly
08:25 PM Backport #51084 (Resolved): pacific: mgr/volumes: hang when removing subvolume when pools are full
https://github.com/ceph/ceph/pull/41691 Backport Bot
08:22 PM Bug #50532 (Pending Backport): mgr/volumes: hang when removing subvolume when pools are full
Patrick Donnelly
08:20 PM Bug #43216: MDSMonitor: removes MDS coming out of quorum election
/ceph/teuthology-archive/pdonnell-2021-06-03_03:40:33-fs-wip-pdonnell-testing-20210603.020013-distro-basic-smithi/614... Patrick Donnelly
12:40 PM Bug #51077 (Resolved): MDSMonitor: crash when attempting to mount cephfs
I'm using ceph v16.2.4 deployed with cephadm/docker.
When I try mounting the cephfs from a client, all 3 monitor con...
Stanislav Datskevych
11:14 AM Bug #51055 (Duplicate): mds crash in pacific backport
Jeff Layton
12:47 AM Bug #51055: mds crash in pacific backport
Jeff,
This should be fixed by Patrick in https://tracker.ceph.com/issues/51067.
Xiubo Li
05:35 AM Bug #51023 (Fix Under Review): mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
Xiubo Li
01:44 AM Bug #51023: mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
Patrick Donnelly wrote:
> Xiubo Li wrote:
> > Patrick Donnelly wrote:
> > > Xiubo Li wrote:
> > > > It was one us...
Xiubo Li
01:32 AM Bug #51023: mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
Xiubo Li wrote:
> Patrick Donnelly wrote:
> > Xiubo Li wrote:
> > > It was one use-after-free bug, maybe we should...
Patrick Donnelly
01:16 AM Bug #51023: mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
Patrick Donnelly wrote:
> Xiubo Li wrote:
> > It was one use-after-free bug, maybe we should lru_pin the stray dent...
Xiubo Li
01:34 AM Backport #49514 (Resolved): nautilus: client: allow looking up snapped inodes by inode number+sna...
Patrick Donnelly
01:34 AM Backport #50128 (Resolved): nautilus: pybind/mgr/volumes: deadlock on async job hangs finisher th...
Patrick Donnelly
01:34 AM Backport #50290 (Resolved): nautilus: MDS stuck at stopping when reducing max_mds
Patrick Donnelly
01:34 AM Backport #50625 (Resolved): nautilus: qa: "ls: cannot access 'lost+found': No such file or direct...
Patrick Donnelly
01:33 AM Backport #50628 (Resolved): nautilus: client: access(path, X_OK) on non-executable file as root a...
Patrick Donnelly
01:33 AM Backport #50634 (Resolved): nautilus: mds: failure replaying journal (EMetaBlob)
Patrick Donnelly
01:33 AM Backport #50897 (Resolved): nautilus: mds: monclient: wait_auth_rotating timed out after 30
Patrick Donnelly

06/02/2021

07:02 PM Bug #51023: mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
Xiubo Li wrote:
> It was one use-after-free bug, maybe we should lru_pin the stray dentries.
That's what ultimate...
Patrick Donnelly
11:56 AM Bug #51023: mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)
It was one use-after-free bug, maybe we should lru_pin the stray dentries. Xiubo Li
05:19 AM Bug #51023 (In Progress): mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)

The root cause is that the "~mds0/stray0" dentry has been trimmed before the "C_MDC_CreateSystemFile" finisher call...
Xiubo Li
06:20 PM Bug #45997 (Resolved): nautilus: ceph_volume_client.py: UnicodeEncodeError exception while removi...
Patrick Donnelly
04:16 PM Backport #51070 (In Progress): pacific: qa: test_ephemeral_pin_distribution failure
Patrick Donnelly
03:30 PM Backport #51070 (Resolved): pacific: qa: test_ephemeral_pin_distribution failure
https://github.com/ceph/ceph/pull/41659 Backport Bot
03:25 PM Bug #51060 (Pending Backport): qa: test_ephemeral_pin_distribution failure
Patrick Donnelly
03:23 PM Bug #51069 (Triaged): mds: mkdir on ephemerally pinned directory sometimes blocked on journal flush
Patrick Donnelly
03:23 PM Bug #51069 (Resolved): mds: mkdir on ephemerally pinned directory sometimes blocked on journal flush
... Patrick Donnelly
03:13 PM Backport #50873: pacific: mon,doc: deprecate min_compat_client
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/41468
merged
Yuri Weinstein
02:28 PM Bug #51067 (Resolved): mds: segfault printing unknown metric
Regression caused by b1b44d775df3160d937c068d5e1079e24199ed6b.
Instead of an assertion we get a happy seg fault =)...
Patrick Donnelly
12:44 PM Bug #51055: mds crash in pacific backport
Jeff Layton wrote:
> If you can reproduce the crash and get a coredump, and ensure that the packages stay around, we...
Xiubo Li
12:33 PM Bug #51055: mds crash in pacific backport
If you can reproduce the crash and get a coredump, and ensure that the packages stay around, we should (supposedly) b... Jeff Layton
12:14 PM Bug #51055: mds crash in pacific backport
I was also hitting the same issue in upstream :
https://pulpito.ceph.com/xiubli-2021-05-28_03:27:40-fs:functional:-w...
Xiubo Li
09:55 AM Bug #51055: mds crash in pacific backport
Xiubo Li wrote:
> It might be crashed here first:
>
> [...]
>
> Then the watchdog bark and kill the mds daemon...
Jeff Layton
01:12 AM Bug #51055: mds crash in pacific backport
Jeff Layton wrote:
> A lot of MDS failures, possibly involving the stats code. One of the tests' teuthology log is h...
Xiubo Li
12:01 PM Bug #51062 (Resolved): mds,client: suppport getvxattr RPC
Playing with ephemeral pinning today, and found that I can't query ceph.dir.pin.random:... Jeff Layton
05:24 AM Backport #50392 (Resolved): pacific: cephfs-top: exception: addwstr() returned ERR
Patrick Donnelly
04:59 AM Backport #50843 (Resolved): pacific: mgr/nfs: cli is broken as cluster id and binding arguments a...
Patrick Donnelly
04:59 AM Backport #50597 (Resolved): pacific: mgr/nfs: Add troubleshooting section
Patrick Donnelly
04:59 AM Backport #50488 (Resolved): pacific: mgr/nfs: move nfs code out of volumes plugin
Patrick Donnelly
04:49 AM Backport #50186 (Resolved): pacific: qa: daemonwatchdog fails if mounts not defined
Patrick Donnelly

06/01/2021

09:17 PM Bug #50976: mds: scrub error on inode 0x1
Milind, please paste the run this failure comes from. Patrick Donnelly
08:57 PM Bug #51060 (Resolved): qa: test_ephemeral_pin_distribution failure
... Patrick Donnelly
07:18 PM Bug #51055: mds crash in pacific backport
Some of the cores seem to be missing. For instance, there is this in the teuthology.log:
2021-05-31T16:36:41.2...
Jeff Layton
06:35 PM Bug #51055 (Duplicate): mds crash in pacific backport
A lot of MDS failures, possibly involving the stats code. One of the tests' teuthology log is here:

http://qa...
Jeff Layton
12:19 PM Backport #50874 (In Progress): octopus: mds: MDSLog::journaler pointer maybe crash with use-after...
Cory Snyder
12:17 PM Backport #50635 (In Progress): octopus: session dump includes completed_requests twice, once as a...
Cory Snyder
12:14 PM Bug #49837: mgr/pybind/snap_schedule: do not fail when no fs snapshots are available
@Patrick Donnelly - it seems that the snap_schedule module was added in Pacific, so I don't believe that this fix nee... Cory Snyder
06:03 AM Feature #48619 (Fix Under Review): client: track (and forward to MDS) average read/write/metadata...
Venky Shankar

05/31/2021

05:05 PM Backport #50897: nautilus: mds: monclient: wait_auth_rotating timed out after 30
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/41448
merged
Yuri Weinstein
05:05 PM Backport #50128: nautilus: pybind/mgr/volumes: deadlock on async job hangs finisher thread
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/41394
merged
Yuri Weinstein
05:03 PM Backport #50625: nautilus: qa: "ls: cannot access 'lost+found': No such file or directory"
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40769
merged
Yuri Weinstein
05:03 PM Backport #50290: nautilus: MDS stuck at stopping when reducing max_mds
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40769
merged
Yuri Weinstein
05:03 PM Backport #49514: nautilus: client: allow looking up snapped inodes by inode number+snapid tuple
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40769
merged
Yuri Weinstein
08:47 AM Bug #50954: mgr/pybind/snap_schedule: commands only support positional arguments?
Can you use proper positional arguments here? ... Sebastian Wagner
08:41 AM Backport #50872 (In Progress): pacific: qa: testing kernel patch for client metrics causes mds abort
Xiubo Li
08:08 AM Backport #47020 (In Progress): nautilus: client: shutdown race fails with status 141
Nathan Cutler
06:27 AM Bug #50530 (In Progress): pacific: client: abort after MDS blocklist
Venky Shankar
02:16 AM Bug #51023 (Resolved): mds: tcmalloc::allocate_full_cpp_throw_oom(unsigned long)+0xf3)

From https://pulpito.ceph.com/yuriw-2021-05-27_19:31:33-kcephfs-wip-yuri3-testing-2021-05-27-0818-nautilus-distro-...
Xiubo Li
01:30 AM Backport #49519 (Resolved): nautilus: client: wake up the front pos waiter
Thanks. Xiubo Li

05/29/2021

03:17 PM Backport #50628: nautilus: client: access(path, X_OK) on non-executable file as root always succeeds
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/41297
merged
Yuri Weinstein
03:16 PM Backport #49519: nautilus: client: wake up the front pos waiter
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40865
merged
Yuri Weinstein
03:16 PM Backport #50634: nautilus: mds: failure replaying journal (EMetaBlob)
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/41144
merged
Yuri Weinstein

05/28/2021

04:40 AM Backport #50993 (In Progress): pacific: cephfs-mirror: incrementally transfer snapshots whenever ...
Venky Shankar

05/27/2021

01:18 PM Bug #50984 (Fix Under Review): qa: test_full multiple the mon_osd_full_ratio twice
Xiubo Li
03:20 AM Bug #50984 (Resolved): qa: test_full multiple the mon_osd_full_ratio twice
The cluster has already multiple the full ratio before returning the "max_avail". Xiubo Li
08:35 AM Backport #50994 (Resolved): pacific: cephfs-mirror: be resilient to recreated snapshot during syn...
https://github.com/ceph/ceph/pull/41947 Backport Bot
08:35 AM Backport #50993 (Resolved): pacific: cephfs-mirror: incrementally transfer snapshots whenever pos...
https://github.com/ceph/ceph/pull/41475 Backport Bot
08:33 AM Bug #50561 (Pending Backport): cephfs-mirror: incrementally transfer snapshots whenever possible
Venky Shankar
08:32 AM Bug #49939 (Pending Backport): cephfs-mirror: be resilient to recreated snapshot during synchroni...
Venky Shankar
07:25 AM Backport #50991 (Resolved): pacific: mgr/nfs: skipping conf file or passing empty file throws tra...
https://github.com/ceph/ceph/pull/42096 Backport Bot
07:24 AM Bug #50858 (Pending Backport): mgr/nfs: skipping conf file or passing empty file throws traceback
Kefu Chai
01:42 AM Bug #50976 (Fix Under Review): mds: scrub error on inode 0x1
Milind Changire

05/26/2021

01:58 PM Bug #45997: nautilus: ceph_volume_client.py: UnicodeEncodeError exception while removing volume w...
https://github.com/ceph/ceph/pull/36679 merged Yuri Weinstein
09:28 AM Bug #50976: mds: scrub error on inode 0x1
In this case, the backtrace check for inode 0x1 has failed.
Root Inode backtrace needs to be saved as soon as the in...
Milind Changire
09:25 AM Bug #50976 (Resolved): mds: scrub error on inode 0x1
... Milind Changire

05/24/2021

09:47 PM Bug #48753 (Resolved): mds: spurious wakeups in cache upkeep
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
09:47 PM Bug #48877 (Resolved): qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
09:46 PM Bug #49309 (Resolved): nautilus: qa: "Assertion `cb_done' failed."
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
09:45 PM Bug #50048 (Resolved): mds: standby-replay only trims cache when it reaches the end of the replay...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
09:31 PM Backport #49472 (Resolved): octopus: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40767
m...
Loïc Dachary
09:31 PM Backport #50633 (Resolved): octopus: mds: failure replaying journal (EMetaBlob)
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40743
m...
Loïc Dachary
09:31 PM Backport #50256 (Resolved): octopus: mds: standby-replay only trims cache when it reaches the end...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40743
m...
Loïc Dachary
09:31 PM Backport #48813 (Resolved): octopus: mds: spurious wakeups in cache upkeep
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40743
m...
Loïc Dachary
09:31 PM Backport #49475 (Resolved): octopus: nautilus: qa: "Assertion `cb_done' failed."
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40708
m...
Loïc Dachary
09:21 PM Bug #50258 (Resolved): pacific: qa: "run() got an unexpected keyword argument 'stdin_data'"
Loïc Dachary
09:18 PM Backport #50632 (Resolved): pacific: mds: failure replaying journal (EMetaBlob)
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40855
m...
Loïc Dachary
09:18 PM Backport #50254 (Resolved): pacific: mds: standby-replay only trims cache when it reaches the end...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40855
m...
Loïc Dachary
09:18 PM Backport #50183 (Resolved): pacific: client: openned inodes counter is inconsistent
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40685
m...
Loïc Dachary
01:08 PM Bug #50954 (Resolved): mgr/pybind/snap_schedule: commands only support positional arguments?
It looks like the module does not support passing optional ceph arguments.
See:...
Sébastien Han
05:01 AM Bug #50946 (Duplicate): mgr/stats: exception ValueError in perf stats
'ceph fs perf stats' command excepts for giving strings mistakenly in the rank list.... Jos Collin

05/22/2021

02:34 PM Bug #49845: qa: failed umount in test_volumes
Also seen in the run http://pulpito.front.sepia.ceph.com/khiremat-2021-05-21_16:22:47-fs:volumes-wip-khiremat-41403-d... Kotresh Hiremath Ravishankar
10:44 AM Bug #50719: xattr returning from the dead (sic!)
Jeff Layton wrote:
> Ok. RHEL7's kcephfs client is quite old. It's possible that this is something fixed in a more r...
Ralph Böhme

05/21/2021

09:51 PM Backport #50872 (Need More Info): pacific: qa: testing kernel patch for client metrics causes mds...
Xiubo please take this one too. Patrick Donnelly
08:06 PM Bug #50870 (Closed): qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
This issue was caused by a bug in the aforementioned PR. No need to work on this Xiubo. Patrick Donnelly
08:26 AM Bug #50870: qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
Patrick Donnelly wrote:
> Xiubo, please take a look at this one. It might be something to do with the caps but that'...
Xiubo Li
06:05 PM Backport #50284 (Rejected): nautilus: MDS slow request lookupino #0x100 on rank 1 block forever o...
Will drop this as nautilus is EOL and how the original bug was induced is not known. Patrick Donnelly
06:04 PM Backport #47020 (Need More Info): nautilus: client: shutdown race fails with status 141
Xiubo, please do this backport. Patrick Donnelly
04:18 PM Feature #48404 (Fix Under Review): client: add a ceph.caps vxattr
Kotresh Hiremath Ravishankar
10:35 AM Backport #50876 (In Progress): pacific: cephfs-mirror: allow mirror daemon to connect to local/pr...
Venky Shankar
10:34 AM Backport #50917 (In Progress): pacific: Mirroring path "remove" don't not seem to work
Venky Shankar
10:34 AM Backport #50537 (In Progress): pacific: "ceph fs snapshot mirror daemon status" should not use js...
Venky Shankar
03:10 AM Backport #50537: pacific: "ceph fs snapshot mirror daemon status" should not use json keys as value
Please take this one Venky. Patrick Donnelly
10:33 AM Backport #50877 (In Progress): pacific: qa: test_mirroring_init_failure_with_recovery failure
Venky Shankar
10:32 AM Backport #50871 (In Progress): pacific: cephfs-mirror: use sensible mount/shutdown timeouts
Venky Shankar
10:29 AM Backport #50629 (In Progress): pacific: cephfs-mirror: ignore snapshots on parent directories whe...
Venky Shankar
06:59 AM Backport #50629: pacific: cephfs-mirror: ignore snapshots on parent directories when synchronizin...
Patrick Donnelly wrote:
> Venky please take this one.
ack
Venky Shankar
03:05 AM Backport #50629: pacific: cephfs-mirror: ignore snapshots on parent directories when synchronizin...
Venky please take this one. Patrick Donnelly
08:23 AM Bug #50824 (In Progress): qa: snaptest-git-ceph bus error
Xiubo Li
08:21 AM Bug #50824: qa: snaptest-git-ceph bus error
The distro is rhel 8. Xiubo Li
08:18 AM Bug #50824: qa: snaptest-git-ceph bus error
For this one, I think it should be a bug of `git` tool:... Xiubo Li
08:22 AM Bug #50825: qa: snaptest-git-ceph hang during mon thrashing v2
I am afraid this is also caused by `git` tool's bug, but there has not remote/ directory for this test. Xiubo Li
05:19 AM Bug #50825: qa: snaptest-git-ceph hang during mon thrashing v2
... Xiubo Li
03:08 AM Backport #50541 (In Progress): pacific: libcephfs: support file descriptor based *at() APIs
Patrick Donnelly
03:03 AM Backport #50538 (In Progress): pacific: mgr/pybind/snap_schedule: do not fail when no fs snapshot...
Patrick Donnelly
02:53 AM Backport #50873 (In Progress): pacific: mon,doc: deprecate min_compat_client
Patrick Donnelly

05/20/2021

07:45 PM Backport #50917 (Resolved): pacific: Mirroring path "remove" don't not seem to work
https://github.com/ceph/ceph/pull/41475 Backport Bot
07:45 PM Backport #50914 (Resolved): octopus: MDS heartbeat timed out between during executing MDCache::st...
https://github.com/ceph/ceph/pull/45157 Backport Bot
07:45 PM Backport #50913 (Resolved): pacific: MDS heartbeat timed out between during executing MDCache::st...
https://github.com/ceph/ceph/pull/42061 Backport Bot
07:43 PM Bug #50834 (Pending Backport): MDS heartbeat timed out between during executing MDCache::start_fi...
Patrick Donnelly
07:43 PM Bug #50523 (Pending Backport): Mirroring path "remove" don't not seem to work
Patrick Donnelly
07:36 PM Bug #49845: qa: failed umount in test_volumes
Back: /ceph/teuthology-archive/pdonnell-2021-05-20_14:09:54-fs-wip-pdonnell-testing-20210518.214114-distro-basic-smit... Patrick Donnelly
04:49 PM Bug #47979 (Can't reproduce): qa: test_ephemeral_pin_distribution failure

Haven't seen this again.
Patrick Donnelly
04:43 PM Feature #48577 (In Progress): pybind/mgr/volumes: support snapshots on subvolumegroups
Patrick Donnelly
02:14 PM Bug #50825 (In Progress): qa: snaptest-git-ceph hang during mon thrashing v2
Xiubo Li
01:40 PM Bug #50867 (Fix Under Review): qa: fs:mirror: reduced data availability
Venky Shankar
01:26 PM Bug #50867 (In Progress): qa: fs:mirror: reduced data availability
Venky Shankar
12:35 PM Documentation #50904 (In Progress): mgr/nfs: add nfs-ganesha config hierarchy
Varsha Rao
12:29 PM Documentation #50904 (Resolved): mgr/nfs: add nfs-ganesha config hierarchy
Varsha Rao
07:44 AM Backport #50899 (In Progress): pacific: mds: monclient: wait_auth_rotating timed out after 30
Ilya Dryomov
06:25 AM Backport #50899 (Resolved): pacific: mds: monclient: wait_auth_rotating timed out after 30
https://github.com/ceph/ceph/pull/41450 Backport Bot
07:44 AM Backport #50898 (In Progress): octopus: mds: monclient: wait_auth_rotating timed out after 30
Ilya Dryomov
06:25 AM Backport #50898 (Resolved): octopus: mds: monclient: wait_auth_rotating timed out after 30
https://github.com/ceph/ceph/pull/41449 Backport Bot
07:44 AM Backport #50897 (In Progress): nautilus: mds: monclient: wait_auth_rotating timed out after 30
Ilya Dryomov
06:25 AM Backport #50897 (Resolved): nautilus: mds: monclient: wait_auth_rotating timed out after 30
https://github.com/ceph/ceph/pull/41448 Backport Bot
06:24 AM Bug #50390 (Pending Backport): mds: monclient: wait_auth_rotating timed out after 30
Kefu Chai
01:27 AM Bug #50840 (Fix Under Review): mds: CephFS kclient gets stuck when getattr() on a certain file
Xiubo Li
01:13 AM Bug #50840: mds: CephFS kclient gets stuck when getattr() on a certain file
From the logs, we can see that the inode 0x100000003ed was trying to recover the size at least 2 minutes ago, the log... Xiubo Li

05/19/2021

08:14 PM Bug #50852 (Fix Under Review): mds: remove fs_name stored in MDSRank
Ramana Raja
07:54 PM Bug #50622 (Fix Under Review): msg: active_connections regression
Sage Weil
07:27 PM Backport #50632: pacific: mds: failure replaying journal (EMetaBlob)
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40855
merged
Yuri Weinstein
07:27 PM Backport #50254: pacific: mds: standby-replay only trims cache when it reaches the end of the rep...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40855
merged
Yuri Weinstein
07:27 PM Backport #50183: pacific: client: openned inodes counter is inconsistent
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40685
merged
Yuri Weinstein
01:44 PM Bug #50532 (Fix Under Review): mgr/volumes: hang when removing subvolume when pools are full
Kotresh Hiremath Ravishankar
01:43 PM Bug #49308 (Duplicate): nautilus: qa: "AssertionError: expected removing source snapshot of a clo...
Duplicate of https://tracker.ceph.com/issues/48231 Kotresh Hiremath Ravishankar
01:42 PM Bug #49469 (Duplicate): qa: "AssertionError: expected removing source snapshot of a clone to fail"
Duplicate of https://tracker.ceph.com/issues/48231 Kotresh Hiremath Ravishankar
01:41 PM Bug #48231 (Fix Under Review): qa: test_subvolume_clone_in_progress_snapshot_rm is racy
Kotresh Hiremath Ravishankar
01:41 PM Bug #48231 (In Progress): qa: test_subvolume_clone_in_progress_snapshot_rm is racy
Kotresh Hiremath Ravishankar
03:34 AM Backport #50128 (In Progress): nautilus: pybind/mgr/volumes: deadlock on async job hangs finisher...
Patrick Donnelly
12:47 AM Documentation #50865 (Resolved): doc: move mds state diagram .dot into rst
Kefu Chai

05/18/2021

09:31 PM Bug #50870 (Need More Info): qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
Nevermind Xiubo. Patrick Donnelly
08:34 PM Bug #50870: qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
Probably caused by: https://github.com/ceph/ceph/pull/39910#pullrequestreview-662546315 Patrick Donnelly
08:16 PM Bug #50870 (Triaged): qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
Xiubo, please take a look at this one. It might be something to do with the caps but that'd be weird. Patrick Donnelly
08:16 PM Bug #50870 (Closed): qa: test_full: "rm: cannot remove 'large_file_a': Permission denied"
... Patrick Donnelly
08:45 PM Backport #50877 (Resolved): pacific: qa: test_mirroring_init_failure_with_recovery failure
https://github.com/ceph/ceph/pull/41475 Backport Bot
08:45 PM Backport #50876 (Resolved): pacific: cephfs-mirror: allow mirror daemon to connect to local/prima...
https://github.com/ceph/ceph/pull/41475 Backport Bot
08:45 PM Backport #50875 (Resolved): pacific: mds: MDSLog::journaler pointer maybe crash with use-after-free
https://github.com/ceph/ceph/pull/42060 Backport Bot
08:45 PM Backport #50874 (Resolved): octopus: mds: MDSLog::journaler pointer maybe crash with use-after-free
https://github.com/ceph/ceph/pull/41626 Backport Bot
08:45 PM Backport #50873 (Resolved): pacific: mon,doc: deprecate min_compat_client
https://github.com/ceph/ceph/pull/41468 Backport Bot
08:45 PM Backport #50872 (Resolved): pacific: qa: testing kernel patch for client metrics causes mds abort
https://github.com/ceph/ceph/pull/41596 Backport Bot
08:43 PM Bug #50822 (Pending Backport): qa: testing kernel patch for client metrics causes mds abort
Patrick Donnelly
08:43 PM Bug #50819 (Pending Backport): mon,doc: deprecate min_compat_client
Patrick Donnelly
08:42 PM Bug #50807 (Pending Backport): mds: MDSLog::journaler pointer maybe crash with use-after-free
Patrick Donnelly
08:41 PM Bug #50224 (Pending Backport): qa: test_mirroring_init_failure_with_recovery failure
Patrick Donnelly
08:41 PM Feature #50581 (Pending Backport): cephfs-mirror: allow mirror daemon to connect to local/primary...
Patrick Donnelly
08:40 PM Backport #50871 (Resolved): pacific: cephfs-mirror: use sensible mount/shutdown timeouts
https://github.com/ceph/ceph/pull/41475 Backport Bot
08:39 PM Bug #50035 (Pending Backport): cephfs-mirror: use sensible mount/shutdown timeouts
Patrick Donnelly
08:20 PM Bug #42516 (Resolved): mds: some mutations have initiated (TrackedOp) set to 0
Patrick Donnelly
07:59 PM Bug #50868 (New): qa: "kern.log.gz already exists; not overwritten"
... Patrick Donnelly
07:50 PM Bug #50867 (Resolved): qa: fs:mirror: reduced data availability
... Patrick Donnelly
06:14 PM Documentation #50865 (Fix Under Review): doc: move mds state diagram .dot into rst
Patrick Donnelly
04:00 PM Documentation #50865 (Resolved): doc: move mds state diagram .dot into rst
Apparently you can embed the .dot diagram, like in:
https://github.com/ceph/ceph/pull/41382/files
Patrick Donnelly
04:49 PM Backport #50488 (In Progress): pacific: mgr/nfs: move nfs code out of volumes plugin
Varsha Rao
04:48 PM Backport #50843 (In Progress): pacific: mgr/nfs: cli is broken as cluster id and binding argument...
https://github.com/ceph/ceph/pull/41389 Varsha Rao
04:48 PM Backport #50597 (In Progress): pacific: mgr/nfs: Add troubleshooting section
https://github.com/ceph/ceph/pull/41389 Varsha Rao
04:42 PM Bug #50858 (Fix Under Review): mgr/nfs: skipping conf file or passing empty file throws traceback
Varsha Rao
09:31 AM Bug #50858 (Resolved): mgr/nfs: skipping conf file or passing empty file throws traceback
It should print helpful error message instead of throwing traceback... Varsha Rao
01:00 PM Bug #50811: pacific: qa: paramiko.buffered_pipe.PipeTimeout
... Milind Changire
06:35 AM Bug #50854 (New): qa: ERROR: test_lifecycle (tasks.cephfs.test_volume_client.TestVolumeClient)
The test failed in pacific teuthology run as below.
2021-05-07T12:18:32.264 INFO:tasks.cephfs_test_runner:========...
Kotresh Hiremath Ravishankar
04:20 AM Bug #50852 (Resolved): mds: remove fs_name stored in MDSRank
MDSRank doesn't need to store the fs_name fetched from the MMDSMap message's map_fs_name. fs_name can be obtained by ... Ramana Raja
02:53 AM Cleanup #50149 (Resolved): client: always register callbacks before mount()
Patrick Donnelly
02:50 AM Bug #48365 (Resolved): qa: ffsb build failure on CentOS 8.2
Patrick Donnelly
02:45 AM Backport #50849 (Rejected): octopus: mds: "cluster [ERR] Error recovering journal 0x203: (2) No...
Backport Bot
02:45 AM Backport #50848 (Resolved): pacific: mds: "cluster [ERR] Error recovering journal 0x203: (2) No...
https://github.com/ceph/ceph/pull/42059 Backport Bot
02:42 AM Bug #50389 (Pending Backport): mds: "cluster [ERR] Error recovering journal 0x203: (2) No such ...
Patrick Donnelly
02:40 AM Backport #50847 (Resolved): octopus: mds: journal recovery thread is possibly asserting with mds_...
https://github.com/ceph/ceph/pull/45156 Backport Bot
02:40 AM Backport #50846 (Resolved): pacific: mds: journal recovery thread is possibly asserting with mds_...
https://github.com/ceph/ceph/pull/42058 Backport Bot
02:39 AM Bug #50744 (Pending Backport): mds: journal recovery thread is possibly asserting with mds_lock n...
Patrick Donnelly
01:52 AM Feature #1276: client: expose mds partition via virtual xattrs
Jeff Layton wrote:
> This ticket is quite old and it's not very clear what it's asking for. Sage or Patrick, can you...
Patrick Donnelly
01:51 AM Bug #50826: kceph: stock RHEL kernel hangs on snaptests with mon|osd thrashers
Jeff Layton wrote:
> The bad patch involved in #50281 was never merged into RHEL, so I doubt this is related.
>
>...
Patrick Donnelly

05/17/2021

11:50 PM Bug #42516 (Fix Under Review): mds: some mutations have initiated (TrackedOp) set to 0
Ramana Raja
09:13 PM Bug #47276 (Fix Under Review): MDSMonitor: add command to rename file systems
Ramana Raja
04:14 PM Bug #50834 (Fix Under Review): MDS heartbeat timed out between during executing MDCache::start_fi...
Patrick Donnelly
05:10 AM Bug #50834 (Resolved): MDS heartbeat timed out between during executing MDCache::start_files_to_r...
This issue happens with v14.2.19 (also v14.2.16). We have also discussed it in the mailing list https://lists.ceph.io... Yongseok Oh
03:40 PM Backport #50843 (Resolved): pacific: mgr/nfs: cli is broken as cluster id and binding arguments a...
https://github.com/ceph/ceph/pull/41389 Backport Bot
03:39 PM Bug #50783 (Pending Backport): mgr/nfs: cli is broken as cluster id and binding arguments are opt...
Patrick Donnelly
03:36 PM Bug #50823: qa: RuntimeError: timeout waiting for cluster to stabilize
The MDSThrasher timed out for some reason setting thrasher exception which caused the daemonwatchdog to bark. Jos Collin
01:53 PM Bug #50840 (Resolved): mds: CephFS kclient gets stuck when getattr() on a certain file

Copied from the mail list:...
Xiubo Li
01:48 PM Bug #50696 (Won't Fix): nautilus: qa: multimds/thrash tasks/cfuse_workunit_suites_fsstress failure
Patrick Donnelly
12:50 PM Feature #1276: client: expose mds partition via virtual xattrs
This ticket is quite old and it's not very clear what it's asking for. Sage or Patrick, can you elaborate? Jeff Layton
11:36 AM Bug #50826: kceph: stock RHEL kernel hangs on snaptests with mon|osd thrashers
The bad patch involved in #50281 was never merged into RHEL, so I doubt this is related.
The hung task warning in ...
Jeff Layton
06:08 AM Bug #48812 (In Progress): qa: test_scrub_pause_and_resume_with_abort failure
Venky Shankar
06:08 AM Bug #48812: qa: test_scrub_pause_and_resume_with_abort failure
Patrick Donnelly wrote:
> /ceph/teuthology-archive/pdonnell-2021-05-14_21:45:42-fs-master-distro-basic-smithi/611574...
Venky Shankar
03:33 AM Bug #50822 (Fix Under Review): qa: testing kernel patch for client metrics causes mds abort
Since we have tolerate unknown metric types in MDS, so we should fix this in MDS code, do not assert when receiving u... Xiubo Li

05/15/2021

04:15 PM Backport #49472: octopus: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40767
merged
Yuri Weinstein
04:07 PM Backport #50633: octopus: mds: failure replaying journal (EMetaBlob)
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40743
merged
Yuri Weinstein
04:07 PM Backport #50256: octopus: mds: standby-replay only trims cache when it reaches the end of the rep...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40743
merged
Yuri Weinstein
04:07 PM Backport #48813: octopus: mds: spurious wakeups in cache upkeep
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40743
merged
Yuri Weinstein
04:06 PM Backport #49475: octopus: nautilus: qa: "Assertion `cb_done' failed."
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40708
merged
Yuri Weinstein
03:44 AM Bug #50826: kceph: stock RHEL kernel hangs on snaptests with mon|osd thrashers
Might be related to #50281 but that was with the testing kernel. Patrick Donnelly
03:44 AM Bug #50826 (Closed): kceph: stock RHEL kernel hangs on snaptests with mon|osd thrashers
/ceph/teuthology-archive/pdonnell-2021-05-14_21:45:42-fs-master-distro-basic-smithi/6115757/teuthology.log
and
...
Patrick Donnelly
03:30 AM Bug #50825 (Need More Info): qa: snaptest-git-ceph hang during mon thrashing v2
... Patrick Donnelly
03:22 AM Bug #50824 (Won't Fix): qa: snaptest-git-ceph bus error
... Patrick Donnelly
03:19 AM Bug #50823 (New): qa: RuntimeError: timeout waiting for cluster to stabilize
... Patrick Donnelly
03:13 AM Bug #50822 (Resolved): qa: testing kernel patch for client metrics causes mds abort
... Patrick Donnelly
03:11 AM Bug #50821: qa: untar_snap_rm failure during mds thrashing
I don't think this is related to #50281 but may be. Patrick Donnelly
03:11 AM Bug #50821 (New): qa: untar_snap_rm failure during mds thrashing
... Patrick Donnelly
03:03 AM Bug #48812 (New): qa: test_scrub_pause_and_resume_with_abort failure
/ceph/teuthology-archive/pdonnell-2021-05-14_21:45:42-fs-master-distro-basic-smithi/6115747/teuthology.log
and
...
Patrick Donnelly

05/14/2021

07:23 PM Bug #50819 (Fix Under Review): mon,doc: deprecate min_compat_client
Patrick Donnelly
07:21 PM Bug #50819 (Resolved): mon,doc: deprecate min_compat_client
We effectively did this already in Pacific but didn't update the docs or add a warning to the min_compat_client fs se... Patrick Donnelly
04:44 PM Bug #41034 (Resolved): cephfs-journal-tool: NetHandler create_socket couldn't create socket
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:43 PM Bug #45100 (Resolved): qa: Test failure: test_damaged_dentry (tasks.cephfs.test_damage.TestDamage)
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:42 PM Bug #45835 (Resolved): mds: OpenFileTable::prefetch_inodes during rejoin can cause out-of-memory
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:42 PM Documentation #48017 (Resolved): snap-schedule doc
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:42 PM Bug #48403 (Resolved): mds: fix recall defaults based on feedback from production clusters
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:41 PM Bug #48679 (Resolved): client: items pinned in cache preventing unmount
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:41 PM Bug #48765 (Resolved): have mount helper pick appropriate mon sockets for ms_mode value
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:41 PM Documentation #48914 (Resolved): mgr/nfs: Update about user config
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:41 PM Bug #49318 (Resolved): qa: racy session evicted check
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:40 PM Bug #49459 (Resolved): pybind/cephfs: DT_REG and DT_LNK values are wrong
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:40 PM Bug #49510 (Resolved): qa: file system deletion not complete because starter fs already destroyed
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:40 PM Bug #49559 (Resolved): libcephfs: test termination "what(): Too many open files"
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:40 PM Bug #49617 (Resolved): mds: race of fetching large dirfrag
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:40 PM Bug #49882 (Resolved): mgr/volumes: setuid and setgid file bits are not retained after a subvolum...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:39 PM Documentation #49921 (Resolved): mgr/nfs: Update about cephadm single nfs-ganesha daemon per host...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:39 PM Bug #50090 (Resolved): client: only check pool permissions for regular files
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
04:39 PM Bug #50215 (Resolved): qa: "log [ERR] : error reading sessionmap 'mds2_sessionmap'"
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
03:40 PM Backport #50286 (Resolved): octopus: qa: "log [ERR] : error reading sessionmap 'mds2_sessionmap'"
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40783
m...
Loïc Dachary
03:39 PM Backport #50181 (Resolved): octopus: client: only check pool permissions for regular files
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40779
m...
Loïc Dachary
03:39 PM Backport #50027 (Resolved): octopus: client: items pinned in cache preventing unmount
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40778
m...
Loïc Dachary
03:39 PM Backport #49950 (Resolved): octopus: mgr/nfs: Update about cephadm single nfs-ganesha daemon per ...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40777
m...
Loïc Dachary
03:39 PM Backport #49934 (Resolved): octopus: libcephfs: test termination "what(): Too many open files"
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40776
m...
Loïc Dachary
03:39 PM Backport #49752 (Resolved): octopus: snap-schedule doc
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40775
m...
Loïc Dachary
03:39 PM Cleanup #50816 (Fix Under Review): mgr/nfs: add nfs to mypy
Annotate all the functions in this source file and add an section in src/mypy.ini to ensure that this file is annotat... Varsha Rao
03:39 PM Backport #49851 (Resolved): octopus: mds: race of fetching large dirfrag
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40774
m...
Loïc Dachary
03:39 PM Backport #49611 (Resolved): octopus: qa: racy session evicted check
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40773
m...
Loïc Dachary
03:38 PM Backport #49560 (Resolved): octopus: qa: file system deletion not complete because starter fs alr...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40772
m...
Loïc Dachary
03:38 PM Backport #49518 (Resolved): octopus: client: wake up the front pos waiter
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40771
m...
Loïc Dachary
03:38 PM Backport #49515 (Resolved): octopus: pybind/cephfs: DT_REG and DT_LNK values are wrong
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40770
m...
Loïc Dachary
03:38 PM Backport #49347 (Resolved): octopus: qa: Test failure: test_damaged_dentry (tasks.cephfs.test_dam...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40765
m...
Loïc Dachary
03:38 PM Backport #48878 (Resolved): octopus: mds: fix recall defaults based on feedback from production c...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40764
m...
Loïc Dachary
03:38 PM Backport #48836 (Resolved): octopus: have mount helper pick appropriate mon sockets for ms_mode v...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40763
m...
Loïc Dachary
03:38 PM Backport #45853 (Resolved): octopus: cephfs-journal-tool: NetHandler create_socket couldn't creat...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40762
m...
Loïc Dachary
03:37 PM Backport #49904 (Resolved): octopus: mgr/volumes: setuid and setgid file bits are not retained af...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40268
m...
Loïc Dachary
01:07 PM Bug #50801 (Duplicate): cephfs-top should show average instead of cumulative latency
Duplicate of #48619 Venky Shankar
11:05 AM Bug #50016: qa: test_damage: "RuntimeError: 2 mutations had unexpected outcomes"
recurrence seen in Pacific QA:
# https://pulpito.ceph.com/yuriw-2021-05-06_19:28:46-fs-wip-yuri8-testing-2021-05-06-...
Milind Changire
10:58 AM Bug #45434: qa: test_full_fsync (tasks.cephfs.test_full.TestClusterFull) failed
recurrence seen in Pacific QA:
# https://pulpito.ceph.com/yuriw-2021-05-06_19:28:46-fs-wip-yuri8-testing-2021-05-06-...
Milind Changire
09:19 AM Feature #47277 (Fix Under Review): implement new mount "device" syntax for kcephfs
Venky Shankar
08:23 AM Bug #50808 (Fix Under Review): qa: test_data_scan.TestDataScan.test_pg_files AssertionError: Item...
Xiubo Li
05:10 AM Bug #50808 (Resolved): qa: test_data_scan.TestDataScan.test_pg_files AssertionError: Items in the...
Run the qa test locally:... Xiubo Li
07:24 AM Bug #50811 (New): pacific: qa: paramiko.buffered_pipe.PipeTimeout
"Teuthology run":https://pulpito.ceph.com/yuriw-2021-05-06_19:28:46-fs-wip-yuri8-testing-2021-05-06-0832-pacific-dist... Milind Changire
07:11 AM Bug #50279: qa: "Replacing daemon mds.b as rank 0 with standby daemon mds.c"
A fresh "run for the Pacific branch":https://pulpito.ceph.com/yuriw-2021-05-06_19:28:46-fs-wip-yuri8-testing-2021-05-... Milind Changire
02:47 AM Bug #50807 (Fix Under Review): mds: MDSLog::journaler pointer maybe crash with use-after-free
Xiubo Li
02:24 AM Bug #50807 (Resolved): mds: MDSLog::journaler pointer maybe crash with use-after-free
When the _recovery_thread is trying to reformat the journal, it will delete the old journal pointer and assign with a... Xiubo Li

05/13/2021

01:48 PM Bug #50801 (Duplicate): cephfs-top should show average instead of cumulative latency
I was playing with cephfs-top today and noticed that the read/write latency fields are in seconds, but the numbers we... Jeff Layton

05/12/2021

05:46 PM Bug #50783 (Fix Under Review): mgr/nfs: cli is broken as cluster id and binding arguments are opt...
Varsha Rao
04:54 PM Bug #50783 (Resolved): mgr/nfs: cli is broken as cluster id and binding arguments are optional
In the following commands clusterid requirement is made optional which breaks cli.... Varsha Rao
03:18 PM Backport #50286: octopus: qa: "log [ERR] : error reading sessionmap 'mds2_sessionmap'"
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40783
merged
Yuri Weinstein
03:18 PM Backport #50181: octopus: client: only check pool permissions for regular files
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40779
merged
Yuri Weinstein
03:18 PM Backport #50027: octopus: client: items pinned in cache preventing unmount
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40778
merged
Yuri Weinstein
03:17 PM Backport #49950: octopus: mgr/nfs: Update about cephadm single nfs-ganesha daemon per host limita...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40777
merged
Yuri Weinstein
03:17 PM Backport #49934: octopus: libcephfs: test termination "what(): Too many open files"
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40776
merged
Yuri Weinstein
03:16 PM Backport #49752: octopus: snap-schedule doc
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40775
merged
Yuri Weinstein
03:16 PM Backport #49851: octopus: mds: race of fetching large dirfrag
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40774
merged
Yuri Weinstein
03:15 PM Backport #49611: octopus: qa: racy session evicted check
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40773
merged
Yuri Weinstein
03:15 PM Backport #49560: octopus: qa: file system deletion not complete because starter fs already destroyed
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40772
merged
Yuri Weinstein
03:14 PM Backport #49518: octopus: client: wake up the front pos waiter
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40771
merged
Yuri Weinstein
03:13 PM Backport #49515: octopus: pybind/cephfs: DT_REG and DT_LNK values are wrong
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40770
merged
Yuri Weinstein
03:13 PM Backport #49347: octopus: qa: Test failure: test_damaged_dentry (tasks.cephfs.test_damage.TestDam...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40765
merged
Yuri Weinstein
03:12 PM Backport #48878: octopus: mds: fix recall defaults based on feedback from production clusters
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40764
merged
Yuri Weinstein
03:12 PM Backport #48836: octopus: have mount helper pick appropriate mon sockets for ms_mode value
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40763
merged
Yuri Weinstein
03:11 PM Backport #45853: octopus: cephfs-journal-tool: NetHandler create_socket couldn't create socket
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/40762
merged
Yuri Weinstein
03:11 PM Backport #49904: octopus: mgr/volumes: setuid and setgid file bits are not retained after a subvo...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40268
merged
Yuri Weinstein
02:26 PM Bug #50390: mds: monclient: wait_auth_rotating timed out after 30
error message:
2021-05-04T05:51:54.719+0800 7f105b2737c0 -1 mds.c unable to obtain rotating service keys; retrying...
wenge song
08:00 AM Bug #50390: mds: monclient: wait_auth_rotating timed out after 30
It seem to that paxos not active cause mon leader not push to other mon
2021-05-12T15:07:43.654+0800 7f5f761f9700 ...
wenge song
02:47 AM Bug #50390: mds: monclient: wait_auth_rotating timed out after 30
pull request id 40880 fixed this? I just see the parameters "rotating keys bootstrap timeout: 15" added. It doesn't s... wenge song
10:50 AM Bug #50719: xattr returning from the dead (sic!)
Ralph Böhme wrote:
> > What kernel version are you running this on?
>
> # uname -r
> 3.10.0-1062.18.1.el7.x86_...
Jeff Layton
07:22 AM Bug #50719: xattr returning from the dead (sic!)
Hi Jeff,
thanks for looking into this!
Jeff Layton wrote:
> What kernel version are you running this on?
# ...
Ralph Böhme
09:23 AM Backport #50628 (In Progress): nautilus: client: access(path, X_OK) on non-executable file as roo...
Kotresh Hiremath Ravishankar
09:14 AM Backport #50626 (In Progress): octopus: client: access(path, X_OK) on non-executable file as root...
Kotresh Hiremath Ravishankar
09:12 AM Backport #50627 (In Progress): pacific: client: access(path, X_OK) on non-executable file as root...
Kotresh Hiremath Ravishankar
09:06 AM Backport #50625 (In Progress): nautilus: qa: "ls: cannot access 'lost+found': No such file or dir...
Nathan Cutler
08:59 AM Backport #50623 (In Progress): octopus: qa: "ls: cannot access 'lost+found': No such file or dire...
Nathan Cutler
04:38 AM Backport #50186 (In Progress): pacific: qa: daemonwatchdog fails if mounts not defined
Jos Collin
02:38 AM Bug #42516: mds: some mutations have initiated (TrackedOp) set to 0
Ramana Raja wrote:
> I checked Migrator.cc for creation of MutationImpl object and setting of its TrackedOp initiate...
Patrick Donnelly

05/11/2021

07:56 PM Backport #47609 (Rejected): nautilus: mds: OpenFileTable::prefetch_inodes during rejoin can cause...
Patrick Donnelly
07:51 PM Backport #49413 (Resolved): octopus: mgr/nfs: Update about user config
Patrick Donnelly
05:50 PM Bug #50755 (Duplicate): mds restart but unable to obtain rotating service keys
Patrick Donnelly
08:31 AM Bug #50755 (Duplicate): mds restart but unable to obtain rotating service keys
version-15.2.0
error message:
2021-05-04T05:51:54.719+0800 7f105b2737c0 -1 mds.c unable to obtain rotating ser...
wenge song
09:00 AM Bug #45349 (Resolved): mds: send scrub status to ceph-mgr only when scrub is running (or paused, ...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Loïc Dachary
08:55 AM Backport #49471 (Resolved): nautilus: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/40713
m...
Loïc Dachary
08:53 AM Backport #46480 (Resolved): nautilus: mds: send scrub status to ceph-mgr only when scrub is runni...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36183
m...
Loïc Dachary
08:14 AM Bug #50390: mds: monclient: wait_auth_rotating timed out after 30
I had the same problem, repeat to restart mds.
wenge song
08:06 AM Bug #50390: mds: monclient: wait_auth_rotating timed out after 30
I have same question, target version ceph-v15.2.0
2021-05-04T05:49:24.717+0800 7f105b2737c0 0 monclient: wait_auth_...
zizhou sun
05:25 AM Bug #50744 (Fix Under Review): mds: journal recovery thread is possibly asserting with mds_lock n...
Xiubo Li
03:40 AM Bug #50744 (Resolved): mds: journal recovery thread is possibly asserting with mds_lock not locked
in MDLog::_recovery_thread it is running without holding the mds_lock, but it will call mds->damanaged(), which will ... Xiubo Li

05/10/2021

05:02 PM Bug #50719: xattr returning from the dead (sic!)
What kernel version are you running this on? Is this something easily reproducible, or does it take a while?
There...
Jeff Layton
01:40 PM Bug #50719 (Triaged): xattr returning from the dead (sic!)
Patrick Donnelly
05:31 AM Bug #50719 (Need More Info): xattr returning from the dead (sic!)
Hi Ceph folks,
slow from the Samba team here. :)
I'm investigating a problem at a customer site where xattr dat...
Ralph Böhme
04:46 PM Support #49116: written io continuous high occupancy
Suggest turning up debugging to see what the MDS is doing. Patrick Donnelly
02:45 PM Backport #49471: nautilus: qa: ffsb workload: PG_AVAILABILITY|PG_DEGRADED warnings
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/40713
merged
Yuri Weinstein
02:30 PM Bug #50389: mds: "cluster [ERR] Error recovering journal 0x203: (2) No such file or directory" ...
More detail:... Xiubo Li
09:35 AM Bug #50389 (Fix Under Review): mds: "cluster [ERR] Error recovering journal 0x203: (2) No such ...
There is one rare case that when mds daemon received a new mdsmap
and during decoding it, the metadata_pool will be ...
Xiubo Li
01:48 PM Bug #50622 (Triaged): msg: active_connections regression
Patrick Donnelly
01:45 PM Bug #50695 (Need More Info): nautilus: qa: Test failure: test_kill_mdstable (tasks.cephfs.test_sn...
Patrick Donnelly
01:43 PM Bug #50696: nautilus: qa: multimds/thrash tasks/cfuse_workunit_suites_fsstress failure
This was probably fixed recently for Octopus/Pacific. This one doesn't look to be worth investigating further as Naut... Patrick Donnelly

05/09/2021

05:55 AM Bug #46380 (Closed): libcephfs admin socket occurs segment fault
Greg Farnum

05/08/2021

07:53 PM Backport #46480: nautilus: mds: send scrub status to ceph-mgr only when scrub is running (or paus...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36183
merged
Yuri Weinstein
02:01 PM Bug #50389: mds: "cluster [ERR] Error recovering journal 0x203: (2) No such file or directory" ...
Checked all the possible logs in osd/mon/mds and the related code, and have compared the normal logs, the sequence ar... Xiubo Li

05/07/2021

10:09 PM Bug #50696 (Won't Fix): nautilus: qa: multimds/thrash tasks/cfuse_workunit_suites_fsstress failure
See, https://pulpito.ceph.com/yuriw-2021-05-04_15:32:03-multimds-wip-yuri3-testing-2021-04-29-1036-nautilus-distro-ba... Ramana Raja
09:27 PM Bug #50695 (Need More Info): nautilus: qa: Test failure: test_kill_mdstable (tasks.cephfs.test_sn...
See this here,
https://pulpito.ceph.com/yuriw-2021-05-04_15:32:03-multimds-wip-yuri3-testing-2021-04-29-1036-nautilu...
Ramana Raja
07:36 PM Bug #50546: nautilus: qa: 'The following counters failed to be set on mds daemons: {''mds.importe...
See again here, https://pulpito.ceph.com/yuriw-2021-05-04_15:32:03-multimds-wip-yuri3-testing-2021-04-29-1036-nautilu... Ramana Raja
04:01 AM Bug #50389: mds: "cluster [ERR] Error recovering journal 0x203: (2) No such file or directory" ...

The cephfs_metadata pool was created since osdmap v22:...
Xiubo Li
02:05 AM Bug #50389: mds: "cluster [ERR] Error recovering journal 0x203: (2) No such file or directory" ...
Checked the mds log:... Xiubo Li
02:19 AM Bug #47041 (Resolved): MDS recall configuration options not documented yet
https://docs.ceph.com/en/latest/cephfs/cache-configuration/#mds-recall Patrick Donnelly
 

Also available in: Atom