Project

General

Profile

Activity

From 07/28/2020 to 08/26/2020

08/26/2020

11:35 PM Backport #47096 (Resolved): nautilus: mds: provide altrenatives to increase the total cephfs subv...
Patrick Donnelly
02:38 AM Backport #47096 (In Progress): nautilus: mds: provide altrenatives to increase the total cephfs s...
Patrick Donnelly
09:23 PM Cleanup #47160: qa/tasks/cephfs: Break up test_volumes.py
To be clear: this is as simple as breaking the volumes tests into separate classes in teh same file. Then the yaml fr... Patrick Donnelly
07:16 PM Cleanup #47160 (Resolved): qa/tasks/cephfs: Break up test_volumes.py
The test_volumes has become unwieldy with growing number of non-trivial tests to test growing set of features in mgr/... Ramana Raja
07:49 PM Feature #47162 (Resolved): mds: handle encrypted filenames in the MDS for fscrypt
Once you turn a filename into encrypted text then it can have non-legal and non-printable embedded characters. To mak... Jeff Layton
07:25 PM Feature #47161 (Rejected): mds: add dedicated field to inode for fscrypt context
fscrypt requires that each encrypted inode contain an encryption context:
https://www.kernel.org/doc/html/late...
Jeff Layton
06:44 PM Backport #47157 (In Progress): nautilus: mgr/volumes: Mark subvolumes with ceph.dir.subvolume vxa...
Shyamsundar Ranganathan
05:48 PM Backport #47157 (Resolved): nautilus: mgr/volumes: Mark subvolumes with ceph.dir.subvolume vxattr...
https://github.com/ceph/ceph/pull/36833 Patrick Donnelly
05:48 PM Backport #47158 (Resolved): octopus: mgr/volumes: Mark subvolumes with ceph.dir.subvolume vxattr,...
https://github.com/ceph/ceph/pull/38612 Patrick Donnelly
05:47 PM Bug #47154 (Pending Backport): mgr/volumes: Mark subvolumes with ceph.dir.subvolume vxattr, to im...
Patrick Donnelly
05:30 PM Bug #47154 (Resolved): mgr/volumes: Mark subvolumes with ceph.dir.subvolume vxattr, to improve sn...
Fix for tracker https://tracker.ceph.com/issues/46074 introduces the vxattr ceph.dir.subvolume that can be use to mar... Shyamsundar Ranganathan
03:31 PM Backport #47152 (In Progress): nautilus: pybind/mgr/volumes: add debugging for global lock
Patrick Donnelly
03:28 PM Backport #47152 (Resolved): nautilus: pybind/mgr/volumes: add debugging for global lock
https://github.com/ceph/ceph/pull/36828 Patrick Donnelly
03:28 PM Backport #47151 (Resolved): octopus: pybind/mgr/volumes: add debugging for global lock
https://github.com/ceph/ceph/pull/37366 Patrick Donnelly
03:28 PM Fix #47149 (Pending Backport): pybind/mgr/volumes: add debugging for global lock
Patrick Donnelly
02:10 PM Fix #47149 (Resolved): pybind/mgr/volumes: add debugging for global lock
To help diagnose deadlocks we believe to be happening. Patrick Donnelly
12:02 PM Bug #47140 (Duplicate): mgr/volumes: unresponsive Client::abort_conn() when cleaning stale libcep...
ACK. Thx Venky Shankar
11:51 AM Bug #47140: mgr/volumes: unresponsive Client::abort_conn() when cleaning stale libcephfs handle
@Venky looks like a duplicate of https://tracker.ceph.com/issues/46882
From the logs further down,
Job ID: 537667...
Shyamsundar Ranganathan
07:25 AM Bug #47140: mgr/volumes: unresponsive Client::abort_conn() when cleaning stale libcephfs handle
https://pulpito.ceph.com/vshankar-2020-08-26_05:34:12-fs-wip-pdonnell-testing-20200826.032941-distro-basic-smithi/537... Venky Shankar
07:20 AM Bug #47140 (Duplicate): mgr/volumes: unresponsive Client::abort_conn() when cleaning stale libcep...
Libcephfs connection pool in mgr (mgr_util) identifies stale filesystem handles and cleans them up by calling abort_c... Venky Shankar
09:32 AM Feature #47148 (In Progress): mds: get rid of the mds_lock when storing the inode backtrace to me...
Xiubo Li
09:32 AM Feature #47148 (Resolved): mds: get rid of the mds_lock when storing the inode backtrace to meta ...
The objector->mutate() may take a long time to finish. We can get rid of the mds_lock when doing this. Xiubo Li
09:30 AM Backport #47081 (In Progress): nautilus: mds: decoding of enum types on big-endian systems broken
Nathan Cutler
09:26 AM Backport #47080 (In Progress): octopus: mds: decoding of enum types on big-endian systems broken
Nathan Cutler
09:20 AM Feature #20 (Resolved): client: recover from a killed session (w/ blacklist)
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
09:17 AM Bug #44276 (Resolved): pybind/mgr/volumes: cleanup stale connection hang
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
09:16 AM Feature #45371 (Resolved): mgr/volumes: `protect` and `clone` operation in a single transaction
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
09:14 AM Backport #47147 (Resolved): octopus: pybind/mgr/nfs: Test mounting of exports created with nfs ex...
https://github.com/ceph/ceph/pull/37365 Nathan Cutler
09:05 AM Backport #46957 (Resolved): octopus: pybind/mgr/nfs: add interface for adding user defined config...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36635
m...
Nathan Cutler
09:05 AM Backport #46795 (Resolved): octopus: mds: Subvolume snapshot directory does not save attribute "c...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36403
m...
Nathan Cutler
09:05 AM Backport #46591 (Resolved): octopus: ceph-fuse: ceph-fuse process is terminated by the logratote ...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36195
m...
Nathan Cutler
09:04 AM Backport #46528 (Resolved): octopus: mgr/volumes: `protect` and `clone` operation in a single tra...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36126
m...
Nathan Cutler
09:04 AM Backport #46402 (Resolved): octopus: client: recover from a killed session (w/ blacklist)
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/35962
m...
Nathan Cutler
09:04 AM Backport #46389 (Resolved): octopus: pybind/mgr/volumes: cleanup stale connection hang
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/35962
m...
Nathan Cutler
12:42 AM Backport #47059 (In Progress): octopus: mgr/volumes: Clone operation uses source subvolume root d...
Shyamsundar Ranganathan
12:35 AM Backport #46820 (In Progress): octopus: pybind/mgr/volumes: Add the ability to keep snapshots of ...
Shyamsundar Ranganathan

08/25/2020

10:10 PM Backport #46957: octopus: pybind/mgr/nfs: add interface for adding user defined configuration
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36635
merged
Yuri Weinstein
10:09 PM Backport #46795: octopus: mds: Subvolume snapshot directory does not save attribute "ceph.quota.m...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36403
merged
Yuri Weinstein
10:08 PM Backport #46591: octopus: ceph-fuse: ceph-fuse process is terminated by the logratote task and wh...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36195
merged
Yuri Weinstein
10:08 PM Backport #46528: octopus: mgr/volumes: `protect` and `clone` operation in a single transaction
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36126
merged
Yuri Weinstein
10:07 PM Backport #46402: octopus: client: recover from a killed session (w/ blacklist)
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/35962
merged
Yuri Weinstein
10:07 PM Backport #46389: octopus: pybind/mgr/volumes: cleanup stale connection hang
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/35962
merged
Yuri Weinstein
04:37 AM Bug #47125 (Fix Under Review): mds: fix possible crash when the MDS is stopping
Xiubo Li
04:32 AM Bug #47125 (In Progress): mds: fix possible crash when the MDS is stopping
Before I have hit one crash without any useful logs months ago, just be possible caused by this. Xiubo Li
04:30 AM Bug #47125 (Resolved): mds: fix possible crash when the MDS is stopping
While the MDS daemon is stopping and if it call journaler->flush(), it may be crash dues to the onsafe parameter in J... Xiubo Li

08/24/2020

08:20 PM Feature #46989 (Pending Backport): pybind/mgr/nfs: Test mounting of exports created with nfs expo...
Patrick Donnelly
07:37 PM Bug #47051 (Duplicate): fs/upgrade/volume_client: Command failed with status 124: 'sudo adjust-ul...
Patrick Donnelly
07:34 PM Bug #47051: fs/upgrade/volume_client: Command failed with status 124: 'sudo adjust-ulimits ceph-c...
Older log with this occurrence: https://pulpito.ceph.com/pdonnell-2020-08-08_02:16:26-fs-wip-pdonnell-testing-2020080... Patrick Donnelly
07:25 PM Bug #47051: fs/upgrade/volume_client: Command failed with status 124: 'sudo adjust-ulimits ceph-c...
I thought this might be fixed by https://github.com/ceph/ceph/pull/36499 after earlier discussions with Neha but it s... Patrick Donnelly
06:36 PM Bug #47015: mds: decoding of enum types on big-endian systems broken
Ulrich Weigand wrote:
> Thanks for creating the backport requests!
>
> Would it make sense to also include this c...
Patrick Donnelly
11:20 AM Bug #47015: mds: decoding of enum types on big-endian systems broken
Thanks for creating the backport requests!
Would it make sense to also include this commit for backporting:
https...
Ulrich Weigand
06:36 PM Backport #47081: nautilus: mds: decoding of enum types on big-endian systems broken
Note to backporters: please include https://github.com/ceph/ceph/pull/35920 Patrick Donnelly
06:36 PM Backport #47080: octopus: mds: decoding of enum types on big-endian systems broken
Note to backporters: please include https://github.com/ceph/ceph/pull/35920 Patrick Donnelly
01:51 PM Feature #47034: mds: readdir for snapshot diff
cephfs-mirror could use this to read the changes to entire subtrees (not just a single directory) given a snapshot. Patrick Donnelly
01:50 PM Bug #47009 (Resolved): TestNFS.test_cluster_set_reset_user_config: command failed with status 32:...
backport PR: https://github.com/ceph/ceph/pull/36748 Sebastian Wagner
10:41 AM Bug #47009 (Pending Backport): TestNFS.test_cluster_set_reset_user_config: command failed with st...
Varsha Rao
01:48 PM Feature #47102: mds: add perf counter for cap messages
separate perf counter for revokes and release Patrick Donnelly
01:30 AM Feature #47102 (Resolved): mds: add perf counter for cap messages
Zheng Yan
01:47 PM Feature #45747 (Resolved): pybind/mgr/nfs: add interface for adding user defined configuration
backport pr: https://github.com/ceph/ceph/pull/36748
Note that this is an exception. I don't plan to include volum...
Sebastian Wagner
01:47 PM Bug #47006 (Triaged): mon: required client features adding/removing
Patrick Donnelly

08/22/2020

07:45 PM Backport #47096 (Resolved): nautilus: mds: provide altrenatives to increase the total cephfs subv...
https://github.com/ceph/ceph/pull/36804 Nathan Cutler
07:45 PM Backport #47095 (Resolved): octopus: mds: provide altrenatives to increase the total cephfs subvo...
https://github.com/ceph/ceph/pull/38553 Nathan Cutler
07:43 PM Backport #47090 (Resolved): nautilus: After restarting an mds, its standy-replay mds remained in ...
https://github.com/ceph/ceph/pull/37179 Nathan Cutler
07:43 PM Backport #47089 (Resolved): octopus: After restarting an mds, its standy-replay mds remained in t...
https://github.com/ceph/ceph/pull/37363 Nathan Cutler
07:43 PM Backport #47088 (Resolved): nautilus: mds: recover files after normal session close
https://github.com/ceph/ceph/pull/37178 Nathan Cutler
07:43 PM Backport #47087 (Resolved): octopus: mds: recover files after normal session close
https://github.com/ceph/ceph/pull/37334 Nathan Cutler
07:43 PM Backport #47086 (Rejected): nautilus: common: validate type CephBool cause 'invalid command json'
Nathan Cutler
07:43 PM Backport #47085 (Resolved): octopus: common: validate type CephBool cause 'invalid command json'
https://github.com/ceph/ceph/pull/37362 Nathan Cutler
07:43 PM Backport #47084 (Rejected): nautilus: mds: 'forward loop' when forward_all_requests_to_auth is set
Nathan Cutler
07:43 PM Backport #47083 (Resolved): octopus: mds: 'forward loop' when forward_all_requests_to_auth is set
https://github.com/ceph/ceph/pull/37360 Nathan Cutler
07:42 PM Backport #47081 (Resolved): nautilus: mds: decoding of enum types on big-endian systems broken
https://github.com/ceph/ceph/pull/36814 Nathan Cutler
07:42 PM Backport #47080 (Resolved): octopus: mds: decoding of enum types on big-endian systems broken
https://github.com/ceph/ceph/pull/36813 Nathan Cutler
01:43 AM Bug #46988 (Pending Backport): mds: 'forward loop' when forward_all_requests_to_auth is set
Patrick Donnelly
01:42 AM Bug #46984 (Pending Backport): mds: recover files after normal session close
Patrick Donnelly
01:41 AM Bug #46976 (Pending Backport): After restarting an mds, its standy-replay mds remained in the "re...
Patrick Donnelly
01:39 AM Bug #46985 (Pending Backport): common: validate type CephBool cause 'invalid command json'
Patrick Donnelly
01:36 AM Bug #47015 (Pending Backport): mds: decoding of enum types on big-endian systems broken
Patrick Donnelly
12:01 AM Bug #47075: qa: FAIL: test_config_session_timeout
Another test that failed because of too long a sleep:
/ceph/teuthology-archive/pdonnell-2020-08-19_23:50:59-multim...
Patrick Donnelly

08/21/2020

11:44 PM Bug #47075 (New): qa: FAIL: test_config_session_timeout
... Patrick Donnelly
11:13 PM Feature #46074 (Pending Backport): mds: provide altrenatives to increase the total cephfs subvolu...
Wiring up mgr/volumes will happen in another ticket. Patrick Donnelly
11:10 PM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
Another: /ceph/teuthology-archive/pdonnell-2020-08-21_07:42:41-fs-wip-pdonnell-testing-20200821.043335-distro-basic-s... Patrick Donnelly
01:10 AM Tasks #47047 (Fix Under Review): client: release the client_lock before copying data in all the r...
Xiubo Li
01:09 AM Bug #47039 (Fix Under Review): client: mutex lock FAILED ceph_assert(nlock > 0)
It should be caused by my local code. I added more check code for using the client_lock directly. Xiubo Li

08/20/2020

11:15 PM Backport #47059: octopus: mgr/volumes: Clone operation uses source subvolume root directory mode ...
Awaiting backport for https://tracker.ceph.com/issues/46820, which conflicts with merge of backport https://github.co... Shyamsundar Ranganathan
08:09 PM Backport #47059 (Resolved): octopus: mgr/volumes: Clone operation uses source subvolume root dire...
https://github.com/ceph/ceph/pull/36803 Nathan Cutler
11:12 PM Backport #46820: octopus: pybind/mgr/volumes: Add the ability to keep snapshots of subvolumes ind...
Awaiting merge of backport https://github.com/ceph/ceph/pull/36126 as it conflicts with commits for this patch. Shyamsundar Ranganathan
11:07 PM Backport #47058 (In Progress): nautilus: mgr/volumes: Clone operation uses source subvolume root ...
Shyamsundar Ranganathan
08:09 PM Backport #47058 (Resolved): nautilus: mgr/volumes: Clone operation uses source subvolume root dir...
-https://github.com/ceph/ceph/pull/36744-
https://github.com/ceph/ceph/pull/36833
Nathan Cutler
08:54 PM Bug #41069 (Need More Info): nautilus: test_subvolume_group_create_with_desired_mode fails with "...
Let's leave this as NI and see what the new debugging for mgr/volumes shows if it comes up again. Patrick Donnelly
09:38 AM Bug #41069: nautilus: test_subvolume_group_create_with_desired_mode fails with "AssertionError: '...
Tried 1k iterations on nautilus 14.2.11 but could not reproduce. Kotresh Hiremath Ravishankar
05:32 PM Bug #47009 (Fix Under Review): TestNFS.test_cluster_set_reset_user_config: command failed with st...
Varsha Rao
12:23 PM Bug #47009 (In Progress): TestNFS.test_cluster_set_reset_user_config: command failed with status ...
Varsha Rao
12:22 PM Bug #47009: TestNFS.test_cluster_set_reset_user_config: command failed with status 32: 'sudo moun...
ganesha log... Varsha Rao
07:43 AM Bug #47009: TestNFS.test_cluster_set_reset_user_config: command failed with status 32: 'sudo moun...
/a/kchai-2020-08-19_06:47:30-rados-wip-kefu-testing-2020-08-19-1141-distro-basic-smithi/5359038/ Kefu Chai
07:22 AM Bug #47009: TestNFS.test_cluster_set_reset_user_config: command failed with status 32: 'sudo moun...
https://pulpito.ceph.com/swagner-2020-08-19_07:38:40-rados:cephadm-wip-swagner-testing-2020-08-18-1624-distro-basic-s... Sebastian Wagner
02:41 PM Bug #47054 (New): mgr/volumes: Handle potential errors in readdir cephfs python binding
Current implementation of the python binding in cephfs.pyx does not process errno in case of a nullptr return from re... Shyamsundar Ranganathan
01:25 PM Bug #47033 (Duplicate): client: inode ref leak
Zheng Yan
06:11 AM Bug #47033 (New): client: inode ref leak
It fails immediately with following trace.
/home/zhyan/Ceph/ceph/src/client/Client.cc: In function 'void Client::d...
Zheng Yan
11:23 AM Bug #46163 (Pending Backport): mgr/volumes: Clone operation uses source subvolume root directory ...
Ramana Raja
10:35 AM Backport #46821 (Resolved): nautilus: pybind/mgr/volumes: Add the ability to keep snapshots of su...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36448
m...
Nathan Cutler
09:49 AM Bug #47051 (Duplicate): fs/upgrade/volume_client: Command failed with status 124: 'sudo adjust-ul...
Hit the following error in fs/upgrade/volume_client test,... Ramana Raja
09:09 AM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
Shyam spotted this issue in a recent mgr/volumes testing,
https://github.com/ceph/ceph/pull/35756#issuecomment-67667...
Ramana Raja
05:32 AM Feature #46059 (Fix Under Review): vstart_runner.py: optionally rotate logs between tests
Rishabh Dave
05:32 AM Feature #46059: vstart_runner.py: optionally rotate logs between tests
Raised https://github.com/ceph/ceph/pull/36732 since https://github.com/ceph/ceph/pull/35824 was reversed. Rishabh Dave
02:13 AM Feature #46059 (In Progress): vstart_runner.py: optionally rotate logs between tests
Reverted by https://github.com/ceph/ceph/pull/36711 to fix api tests. Rishabh, please open a new PR. Patrick Donnelly
02:51 AM Tasks #47047 (Resolved): client: release the client_lock before copying data in all the reads
The memory copy could take a long time, we can just unlock the client_lock before doing the copy. Xiubo Li
01:50 AM Bug #47039 (In Progress): client: mutex lock FAILED ceph_assert(nlock > 0)
Checked the whole libcephfs code, didn't find any suspicious code about it. And I have one enhancement about the clie... Xiubo Li

08/19/2020

11:39 PM Bug #47039: client: mutex lock FAILED ceph_assert(nlock > 0)
IMO, it is not safe to use the client_lock.lock/.unlock diretctly without any check before it, if we use them we'd be... Xiubo Li
11:33 PM Bug #47039: client: mutex lock FAILED ceph_assert(nlock > 0)
Patrick Donnelly wrote:
> Xiubo Li wrote:
> > Introduced by https://github.com/ceph/ceph/pull/35410 ?
>
> I don'...
Xiubo Li
06:01 PM Bug #47039: client: mutex lock FAILED ceph_assert(nlock > 0)
Xiubo Li wrote:
> Introduced by https://github.com/ceph/ceph/pull/35410 ?
I don't think so. The commit looks to b...
Patrick Donnelly
01:08 PM Bug #47039: client: mutex lock FAILED ceph_assert(nlock > 0)
Introduced by https://github.com/ceph/ceph/pull/35410 ? Xiubo Li
01:08 PM Bug #47039 (Resolved): client: mutex lock FAILED ceph_assert(nlock > 0)
... Xiubo Li
11:30 PM Bug #47033: client: inode ref leak
Xiubo Li wrote:
> With [1] and [2] I have run the test for very long time and didn't see any errors.
>
> [1] htt...
Xiubo Li
11:28 PM Bug #47033 (Duplicate): client: inode ref leak
Xiubo Li
02:33 PM Bug #47033: client: inode ref leak
With [1] and [2] I have run the test for very long time and didn't see any errors.
[1] https://github.com/ceph/ce...
Xiubo Li
08:48 AM Bug #47033: client: inode ref leak
good commit is c8b5f84f49ef74609ba3ea69dea0764ef925ae85 Zheng Yan
08:07 AM Bug #47033: client: inode ref leak
Zheng Yan wrote:
> It can be easily reproduced by following program.
>
> [...]
>
> pre-create testdir at root...
Xiubo Li
07:56 AM Bug #47033 (In Progress): client: inode ref leak
I will take a look of this. Thanks :-) Xiubo Li
07:29 AM Bug #47033 (Duplicate): client: inode ref leak
It can be easily reproduced by following program. ... Zheng Yan
07:57 PM Bug #46496 (Resolved): pybind/mgr/volumes: subvolume operations throw exception if volume doesn't...
Nathan Cutler
05:59 PM Backport #46793 (Rejected): nautilus: pybind/mgr/volumes: subvolume operations throw exception if...
https://tracker.ceph.com/issues/46792#note-4 Patrick Donnelly
10:28 AM Backport #46793: nautilus: pybind/mgr/volumes: subvolume operations throw exception if volume doe...
Please check https://tracker.ceph.com/issues/46792#note-3 Kotresh Hiremath Ravishankar
05:59 PM Backport #46792 (Rejected): octopus: pybind/mgr/volumes: subvolume operations throw exception if ...
Kotresh Hiremath Ravishankar wrote:
> The issue got introduced by the commit https://github.com/ceph/ceph/pull/32319...
Patrick Donnelly
10:27 AM Backport #46792: octopus: pybind/mgr/volumes: subvolume operations throw exception if volume does...
The issue got introduced by the commit https://github.com/ceph/ceph/pull/32319/commits/a44de38b61d598fb0512ea48da0de4... Kotresh Hiremath Ravishankar
05:56 PM Bug #47006: mon: required client features adding/removing
Jos Collin wrote:
> Patrick Donnelly wrote:
> > Can you elaborate on what the problem is? Give an example.
>
> [...
Patrick Donnelly
05:05 AM Bug #47006 (New): mon: required client features adding/removing
Patrick Donnelly wrote:
> Can you elaborate on what the problem is? Give an example....
Jos Collin
01:59 PM Bug #47041 (Resolved): MDS recall configuration options not documented yet
<T1w> Hi, some of the "new" MDS recall configuration options mentioned on https://ceph.io/community/nautilus-cephfs/ ... Zac Dover
10:09 AM Backport #46948 (In Progress): nautilus: qa: Fs cleanup fails with a traceback
Kotresh Hiremath Ravishankar
10:05 AM Backport #46947 (In Progress): octopus: qa: Fs cleanup fails with a traceback
Kotresh Hiremath Ravishankar
07:46 AM Feature #47034 (New): mds: readdir for snapshot diff
make readdir return changed/removed dentries since given snapshot Zheng Yan

08/18/2020

08:16 PM Backport #47014 (In Progress): octopus: librados|libcephfs: use latest MonMap when creating from ...
Shyamsundar Ranganathan
04:03 PM Backport #47014 (Resolved): octopus: librados|libcephfs: use latest MonMap when creating from Cep...
https://github.com/ceph/ceph/pull/36705 Patrick Donnelly
08:13 PM Backport #47013 (In Progress): nautilus: librados|libcephfs: use latest MonMap when creating from...
Shyamsundar Ranganathan
04:02 PM Backport #47013 (Resolved): nautilus: librados|libcephfs: use latest MonMap when creating from Ce...
https://github.com/ceph/ceph/pull/36704 Patrick Donnelly
04:57 PM Bug #47015 (Fix Under Review): mds: decoding of enum types on big-endian systems broken
Patrick Donnelly
04:26 PM Bug #47015 (Resolved): mds: decoding of enum types on big-endian systems broken
When a struct member that has enum type needs to be encoded or
decoded, we need to use an explicit integer type, sin...
Ulrich Weigand
04:53 PM Bug #47012 (Need More Info): mds: MDCache.cc: 6418: FAILED ceph_assert(r == 0 || r == -2)
Patrick Donnelly
04:52 PM Bug #47012: mds: MDCache.cc: 6418: FAILED ceph_assert(r == 0 || r == -2)
the mds.0 debug_ms log level = 1, and log is in the attachment
Hughen X
03:21 PM Bug #47012: mds: MDCache.cc: 6418: FAILED ceph_assert(r == 0 || r == -2)
please try reproduce it again with debug_ms = 1 Zheng Yan
03:09 PM Bug #47012 (Need More Info): mds: MDCache.cc: 6418: FAILED ceph_assert(r == 0 || r == -2)
My mds.0 service (standby, active mds: 4) cyclical crash, each time the stack information is as follows:
ceph versio...
Hughen X
04:52 PM Bug #47006 (Need More Info): mon: required client features adding/removing
Can you elaborate on what the problem is? Give an example. Patrick Donnelly
12:07 PM Bug #47006 (Resolved): mon: required client features adding/removing
... Jos Collin
04:38 PM Backport #47021 (Resolved): octopus: client: shutdown race fails with status 141
https://github.com/ceph/ceph/pull/37358 Nathan Cutler
04:37 PM Backport #47020 (Resolved): nautilus: client: shutdown race fails with status 141
https://github.com/ceph/ceph/pull/41593 Nathan Cutler
04:35 PM Backport #47018 (Resolved): octopus: mds: kcephfs parse dirfrag's ndist is always 0
https://github.com/ceph/ceph/pull/37357 Nathan Cutler
04:34 PM Backport #47017 (Resolved): nautilus: mds: kcephfs parse dirfrag's ndist is always 0
https://github.com/ceph/ceph/pull/37177 Nathan Cutler
04:34 PM Backport #47016 (Resolved): octopus: mds: fix the decode version
https://github.com/ceph/ceph/pull/37356 Nathan Cutler
04:28 PM Feature #46059 (Resolved): vstart_runner.py: optionally rotate logs between tests
Patrick Donnelly
04:12 PM Bug #47011 (Fix Under Review): client: Client::open() pass wrong cap mask to path_walk
Patrick Donnelly
02:23 PM Bug #47011 (Resolved): client: Client::open() pass wrong cap mask to path_walk
Zheng Yan
04:01 PM Fix #46645 (Pending Backport): librados|libcephfs: use latest MonMap when creating from CephContext
Patrick Donnelly
12:50 PM Bug #47009 (Resolved): TestNFS.test_cluster_set_reset_user_config: command failed with status 32:...
... Sebastian Wagner
11:55 AM Feature #47005 (Fix Under Review): kceph: add metric for number of pinned capabilities and number...
Patchwork link: https://patchwork.kernel.org/patch/11720599/ Xiubo Li
11:19 AM Feature #47005 (Resolved): kceph: add metric for number of pinned capabilities and number of dirs...
Xiubo Li
11:19 AM Feature #46866 (In Progress): kceph: add metric for number of pinned capabilities
Xiubo Li
11:17 AM Feature #46866: kceph: add metric for number of pinned capabilities
The number of the pinned capbilities will always equal to the total number of the s_caps in kclient. Xiubo Li
03:40 AM Bug #43039 (Pending Backport): client: shutdown race fails with status 141
Patrick Donnelly
03:39 AM Bug #46868 (Resolved): client: switch to use ceph_mutex_is_locked_by_me always
Patrick Donnelly
03:35 AM Bug #46891 (Pending Backport): mds: kcephfs parse dirfrag's ndist is always 0
Patrick Donnelly
03:35 AM Bug #46926 (Pending Backport): mds: fix the decode version
Patrick Donnelly

08/17/2020

03:48 PM Bug #46985: common: validate type CephBool cause 'invalid command json'
Just this commit needs backported:
common: fix validate type CephBool cause 'invalid command json'
Fixes: http...
Patrick Donnelly
08:52 AM Bug #46985 (Fix Under Review): common: validate type CephBool cause 'invalid command json'
Nathan Cutler
02:07 AM Bug #46985 (Resolved): common: validate type CephBool cause 'invalid command json'
... Yanhu Cao
02:33 PM Bug #46883: kclient: ghost kernel mount
Patrick Donnelly wrote:
> So there are two issues here:
>
> * umount should not use -l so we aren't papering over...
Jeff Layton
01:45 PM Bug #46883: kclient: ghost kernel mount
So there are two issues here:
* umount should not use -l so we aren't papering over bugs. Use -f to umount. If -f ...
Patrick Donnelly
01:42 PM Bug #46887 (Need More Info): kceph: testing branch: hang in workunit by 1/2 clients during tree e...
Would be good to adjust the qa code to fetch the stack if the process hangs. Get /sys/debug/fs/ceph files as well. Patrick Donnelly
10:41 AM Feature #46989 (Fix Under Review): pybind/mgr/nfs: Test mounting of exports created with nfs expo...
Varsha Rao
10:37 AM Feature #46989 (Resolved): pybind/mgr/nfs: Test mounting of exports created with nfs export command
Varsha Rao
09:51 AM Bug #41069: nautilus: test_subvolume_group_create_with_desired_mode fails with "AssertionError: '...
The code looks ok both on master and nautilus branch. I ran 1000 iterations on master but didn't see the failure. I w... Kotresh Hiremath Ravishankar
08:44 AM Bug #46988 (Fix Under Review): mds: 'forward loop' when forward_all_requests_to_auth is set
Zheng Yan
08:38 AM Bug #46988 (Resolved): mds: 'forward loop' when forward_all_requests_to_auth is set
Zheng Yan
05:12 AM Bug #46868 (Fix Under Review): client: switch to use ceph_mutex_is_locked_by_me always
Xiubo Li
05:11 AM Tasks #46890 (Fix Under Review): client: add request lock support
Xiubo Li

08/16/2020

04:43 AM Bug #46976 (Fix Under Review): After restarting an mds, its standy-replay mds remained in the "re...
Zheng Yan
04:42 AM Bug #46984 (Fix Under Review): mds: recover files after normal session close
Zheng Yan
04:30 AM Bug #46984 (Resolved): mds: recover files after normal session close
client does not flush its cap release before sending session close request. Zheng Yan
03:59 AM Bug #42365 (Fix Under Review): client: FAILED assert(dir->readdir_cache[dirp->cache_index] == dn)
Zheng Yan

08/14/2020

06:45 PM Bug #44294: mds: "elist.h: 91: FAILED ceph_assert(_head.empty())"
This issue and #44295 were both fixed by the same PR, https://github.com/ceph/ceph/pull/33538, which was backported t... Nathan Cutler
02:00 PM Bug #46976: After restarting an mds, its standy-replay mds remained in the "resolve" state
MDSRank::calc_recovery_set() should be called by MDSRank::resolve_start Zheng Yan
09:24 AM Bug #46976 (Resolved): After restarting an mds, its standy-replay mds remained in the "resolve" s...
In multimds and standy-replay enabled Ceph cluster,after reduce a filesystem mds num and restart an active mds, its ... wei qiaomiao
12:51 PM Backport #46957 (In Progress): octopus: pybind/mgr/nfs: add interface for adding user defined con...
Nathan Cutler

08/13/2020

11:31 PM Backport #46860 (Resolved): nautilus: mds: do not raise "client failing to respond to cap release...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36513
m...
Nathan Cutler
11:31 PM Backport #46858 (Resolved): nautilus: qa: add debugging for volumes plugin use of libcephfs
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36512
m...
Nathan Cutler
11:30 PM Backport #46856 (Resolved): nautilus: client: static dirent for readdir is not thread-safe
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36511
m...
Nathan Cutler
08:53 PM Bug #41228 (Resolved): mon: deleting a CephFS and its pools causes MONs to crash
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
05:39 PM Bug #41228: mon: deleting a CephFS and its pools causes MONs to crash
also /ceph/teuthology-archive/yuriw-2020-08-05_20:28:22-fs-wip-yuri2-testing-2020-08-05-1459-octopus-distro-basic-smi... Patrick Donnelly
05:37 PM Bug #41228 (New): mon: deleting a CephFS and its pools causes MONs to crash
This is back but in Octopus. The fix for #40011 doesn't fix this, apparently.... Patrick Donnelly
08:51 PM Bug #43517 (Resolved): qa: random subvolumegroup collision
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:49 PM Backport #46960 (Resolved): nautilus: cephfs-journal-tool: incorrect read_offset after finding mi...
https://github.com/ceph/ceph/pull/37479 Nathan Cutler
08:49 PM Backport #46959 (Resolved): octopus: cephfs-journal-tool: incorrect read_offset after finding mis...
https://github.com/ceph/ceph/pull/37854 Nathan Cutler
08:49 PM Bug #45662 (Resolved): pybind/mgr/volumes: volume deletion should check mon_allow_pool_delete
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:49 PM Backport #46957 (Resolved): octopus: pybind/mgr/nfs: add interface for adding user defined config...
https://github.com/ceph/ceph/pull/36635 Nathan Cutler
08:48 PM Bug #45910 (Resolved): pybind/mgr/volumes: volume deletion not always removes the associated osd ...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:48 PM Bug #46277 (Resolved): pybind/mgr/volumes: get_pool_names may indicate volume does not exist if m...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:47 PM Bug #46565 (Resolved): mgr/nfs: Ensure pseudoroot path is absolute and is not just /
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
08:46 PM Backport #46948 (Resolved): nautilus: qa: Fs cleanup fails with a traceback
https://github.com/ceph/ceph/pull/36714 Nathan Cutler
08:46 PM Backport #46947 (Resolved): octopus: qa: Fs cleanup fails with a traceback
https://github.com/ceph/ceph/pull/36713 Nathan Cutler
08:46 PM Backport #46943 (Resolved): nautilus: mds: segv in MDCache::wait_for_uncommitted_fragments
https://github.com/ceph/ceph/pull/36968 Nathan Cutler
08:46 PM Backport #46942 (Resolved): octopus: mds: segv in MDCache::wait_for_uncommitted_fragments
https://github.com/ceph/ceph/pull/37355 Nathan Cutler
08:45 PM Backport #46941 (Resolved): nautilus: mds: memory leak during cache drop
https://github.com/ceph/ceph/pull/36967 Nathan Cutler
08:45 PM Backport #46940 (Resolved): octopus: mds: memory leak during cache drop
https://github.com/ceph/ceph/pull/37354 Nathan Cutler
08:44 PM Backport #46234 (Resolved): octopus: pybind/mgr/volumes: volume deletion not always removes the a...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36327
m...
Nathan Cutler
06:38 PM Backport #46234: octopus: pybind/mgr/volumes: volume deletion not always removes the associated o...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36327
merged
Yuri Weinstein
08:43 PM Backport #46477 (Resolved): octopus: pybind/mgr/volumes: volume deletion should check mon_allow_p...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36327
m...
Nathan Cutler
06:38 PM Backport #46477: octopus: pybind/mgr/volumes: volume deletion should check mon_allow_pool_delete
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36327
merged
Yuri Weinstein
08:43 PM Backport #46465 (Resolved): octopus: pybind/mgr/volumes: get_pool_names may indicate volume does ...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36327
m...
Nathan Cutler
06:38 PM Backport #46465: octopus: pybind/mgr/volumes: get_pool_names may indicate volume does not exist i...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36327
merged
Yuri Weinstein
08:43 PM Backport #46642 (Resolved): octopus: qa: random subvolumegroup collision
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36327
m...
Nathan Cutler
06:38 PM Backport #46642: octopus: qa: random subvolumegroup collision
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36327
merged
Yuri Weinstein
08:43 PM Backport #46712 (Resolved): octopus: mgr/nfs: Ensure pseudoroot path is absolute and is not just /
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36299
m...
Nathan Cutler
06:38 PM Backport #46712: octopus: mgr/nfs: Ensure pseudoroot path is absolute and is not just /
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36299
merged
Yuri Weinstein
08:43 PM Bug #46572 (Resolved): mgr/nfs: help for "nfs export create" and "nfs export delete" says "<attac...
Nathan Cutler
08:43 PM Backport #46632 (Resolved): octopus: mgr/nfs: help for "nfs export create" and "nfs export delete...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36220
m...
Nathan Cutler
06:37 PM Backport #46632: octopus: mgr/nfs: help for "nfs export create" and "nfs export delete" says "<at...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/36220
merged
Yuri Weinstein
03:36 PM Bug #46926 (Fix Under Review): mds: fix the decode version
Jos Collin
03:24 PM Bug #46926 (Resolved): mds: fix the decode version
https://github.com/ceph/ceph/commit/3fac3b1236c4918e9640e38fe7f5f59efc0a23b9
the decode changes are reverted, but ...
Jos Collin

08/12/2020

06:10 PM Bug #46906 (Fix Under Review): mds: fix file recovery crash after replaying delayed requests
Patrick Donnelly
04:37 AM Bug #46906 (Resolved): mds: fix file recovery crash after replaying delayed requests
When client replay stage or active stage just started, MDS replayed delayed requests firstly, then tried to recover f... Zhi Zhang
09:01 AM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
In case:... Xiubo Li
08:56 AM Bug #46882 (Fix Under Review): client: mount abort hangs: [volumes INFO mgr_util] aborting connec...
Xiubo Li
03:45 AM Bug #46905 (Fix Under Review): client: cluster [WRN] evicting unresponsive client smithi122:0 (34...
Let's just defer cancelling the event timer. Xiubo Li
03:12 AM Bug #46905 (In Progress): client: cluster [WRN] evicting unresponsive client smithi122:0 (34373),...
Xiubo Li
03:11 AM Bug #46905 (Resolved): client: cluster [WRN] evicting unresponsive client smithi122:0 (34373), af...

From https://pulpito.ceph.com/pdonnell-2020-08-08_02\:21\:01-multimds-wip-pdonnell-testing-20200808.001303-distro-b...
Xiubo Li

08/11/2020

10:56 PM Feature #45747 (Pending Backport): pybind/mgr/nfs: add interface for adding user defined configur...
Patrick Donnelly
08:17 PM Fix #46645 (Fix Under Review): librados|libcephfs: use latest MonMap when creating from CephContext
Shyamsundar Ranganathan
01:45 PM Bug #46902: mds: CInode::maybe_export_pin is broken
Zheng Yan wrote:
> void CInode::maybe_export_pin(bool update)
> {
> if (!g_conf()->mds_bal_export_pin)
> re...
Patrick Donnelly
01:39 PM Bug #46902 (Rejected): mds: CInode::maybe_export_pin is broken
void CInode::maybe_export_pin(bool update)
{
if (!g_conf()->mds_bal_export_pin)
return;
if (!is_dir() || ...
Zheng Yan
08:06 AM Bug #46893 (New): client: check the quota limit for the full path in the rename operation
In the rename operation, the first top directory with quota set on the path where the target directory is located is ... wei qiaomiao
06:03 AM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
The above was from /a/pdonnell-2020-08-08_02\:21\:01-multimds-wip-pdonnell-testing-20200808.001303-distro-basic-smith... Xiubo Li
02:35 AM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
Additional info:
From the logs we can see that the inode ref was increased by:...
Xiubo Li
02:15 AM Bug #46882: client: mount abort hangs: [volumes INFO mgr_util] aborting connection from cephfs 'c...
Checked it, it seems the write ops didn't finished and kept going while the _umount() just stopped the tick(), then t... Xiubo Li
02:10 AM Bug #46882 (In Progress): client: mount abort hangs: [volumes INFO mgr_util] aborting connection ...
Xiubo Li
04:24 AM Feature #46892 (Fix Under Review): pybind/mgr/volumes: Make number of cloner threads configurable
Kotresh Hiremath Ravishankar
04:23 AM Feature #46892 (Resolved): pybind/mgr/volumes: Make number of cloner threads configurable
The number of cloner threads is set to 4 and can't be configured.
This is bottle neck if the system resource is capa...
Kotresh Hiremath Ravishankar
02:35 AM Bug #46891 (Fix Under Review): mds: kcephfs parse dirfrag's ndist is always 0
Patrick Donnelly
02:12 AM Bug #46891 (Resolved): mds: kcephfs parse dirfrag's ndist is always 0
... Yanhu Cao
02:06 AM Tasks #46890 (Closed): client: add request lock support
For each request it will be protected by its own lock. And the lock order with client_lock will be:... Xiubo Li

08/10/2020

08:41 PM Tasks #46649 (Resolved): client: make the 'mounted', 'unmounting' and 'initialized' members a sin...
Patrick Donnelly
08:38 PM Bug #46887 (Can't reproduce): kceph: testing branch: hang in workunit by 1/2 clients during tree ...
... Patrick Donnelly
08:12 PM Bug #46883: kclient: ghost kernel mount
I think the problem here is that teuthology is using umount -l. That just detaches the mount from the tree, but defer... Jeff Layton
07:36 PM Bug #46883 (Resolved): kclient: ghost kernel mount
Relevant snippets of teuthology log:... Patrick Donnelly
07:53 PM Fix #46885 (New): pybind/mgr/mds_autoscaler: add test for MDS scaling with cephadm
There needs to be teuthology tests that validate its behavior. Patrick Donnelly
07:52 PM Documentation #46884 (Resolved): pybind/mgr/mds_autoscaler: add documentation
Explain how to enable/disable the module. What it does. Patrick Donnelly
07:47 PM Feature #40929 (Resolved): pybind/mgr/mds_autoscaler: create mgr plugin to deploy and configure M...
Patrick Donnelly
06:09 PM Bug #46882 (Resolved): client: mount abort hangs: [volumes INFO mgr_util] aborting connection fro...
... Patrick Donnelly
02:11 PM Fix #46645 (In Progress): librados|libcephfs: use latest MonMap when creating from CephContext
Shyamsundar Ranganathan
05:40 AM Bug #46831 (Resolved): nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
Zheng Yan

08/08/2020

01:34 AM Feature #46865 (In Progress): client: add metric for number of pinned capabilities
Xiubo Li

08/07/2020

11:45 PM Bug #46868 (Resolved): client: switch to use ceph_mutex_is_locked_by_me always
There is one case if the client_lock is hold by another thread, the check here will also be passed. Xiubo Li
11:25 PM Backport #46860: nautilus: mds: do not raise "client failing to respond to cap release" when clie...
Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/36513
merged
Yuri Weinstein
05:20 AM Backport #46860 (In Progress): nautilus: mds: do not raise "client failing to respond to cap rele...
Patrick Donnelly
05:14 AM Backport #46860 (Resolved): nautilus: mds: do not raise "client failing to respond to cap release...
https://github.com/ceph/ceph/pull/36513 Patrick Donnelly
11:23 PM Backport #46858: nautilus: qa: add debugging for volumes plugin use of libcephfs
Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/36512
merged
Yuri Weinstein
05:07 AM Backport #46858 (In Progress): nautilus: qa: add debugging for volumes plugin use of libcephfs
Patrick Donnelly
05:03 AM Backport #46858 (Resolved): nautilus: qa: add debugging for volumes plugin use of libcephfs
https://github.com/ceph/ceph/pull/36512 Patrick Donnelly
11:22 PM Backport #46856: nautilus: client: static dirent for readdir is not thread-safe
Patrick Donnelly wrote:
> https://github.com/ceph/ceph/pull/36511
merged
Yuri Weinstein
04:55 AM Backport #46856 (In Progress): nautilus: client: static dirent for readdir is not thread-safe
Patrick Donnelly
04:53 AM Backport #46856 (Resolved): nautilus: client: static dirent for readdir is not thread-safe
https://github.com/ceph/ceph/pull/36511 Patrick Donnelly
11:20 PM Bug #46831: nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
Zheng Yan wrote:
> https://github.com/ceph/ceph/pull/36462
merged
Yuri Weinstein
11:12 PM Bug #46434: osdc: FAILED ceph_assert(bh->waitfor_read.empty())
https://pulpito.ceph.com/yuriw-2020-08-07_15:05:02-multimds-wip-yuri4-testing-2020-08-07-1350-nautilus-distro-basic-s... Patrick Donnelly
06:08 PM Feature #46866 (Resolved): kceph: add metric for number of pinned capabilities
Specifically, we want to know how many files are open on the client. Patrick Donnelly
06:08 PM Feature #46865 (Resolved): client: add metric for number of pinned capabilities
Specifically, we want to know how many files are open on the client. Patrick Donnelly
08:46 AM Bug #43039 (Fix Under Review): client: shutdown race fails with status 141
Xiubo Li
06:39 AM Bug #43039: client: shutdown race fails with status 141
The root cause should be the test process reached the open files limit, and the fd returned is -1, or something, when... Xiubo Li
05:33 AM Bug #43039: client: shutdown race fails with status 141
Hi Jeff, Patrick
From my test locally, this issue is very similar to https://tracker.ceph.com/issues/45829, which ...
Xiubo Li
07:13 AM Bug #45333: LARGE_OMAP_OBJECTS in pool metadata
Lately I am getting more of these warnings. If needed I can raise the warning threshold, but it seems it is not exact... Kenneth Waegeman
05:14 AM Backport #46859 (Resolved): octopus: mds: do not raise "client failing to respond to cap release"...
https://github.com/ceph/ceph/pull/37353 Patrick Donnelly
05:14 AM Bug #46830 (Pending Backport): mds: do not raise "client failing to respond to cap release" when ...
Patrick Donnelly
05:03 AM Backport #46857 (Resolved): octopus: qa: add debugging for volumes plugin use of libcephfs
https://github.com/ceph/ceph/pull/37352 Patrick Donnelly
05:02 AM Fix #46851 (Pending Backport): qa: add debugging for volumes plugin use of libcephfs
Patrick Donnelly
04:52 AM Backport #46855 (Resolved): octopus: client: static dirent for readdir is not thread-safe
https://github.com/ceph/ceph/pull/37351 Patrick Donnelly
04:52 AM Bug #46832 (Pending Backport): client: static dirent for readdir is not thread-safe
Patrick Donnelly
02:55 AM Bug #46853: ceph_test_libcephfs: LibCephFS.TestUtime gets core dumped randomly
Sometimes I am also getting:... Xiubo Li
02:52 AM Bug #46853: ceph_test_libcephfs: LibCephFS.TestUtime gets core dumped randomly
Patrick Donnelly wrote:
> It's interesitn gyou were able to reproduce that locally. This one has been plaguing us fo...
Xiubo Li
01:57 AM Bug #46853: ceph_test_libcephfs: LibCephFS.TestUtime gets core dumped randomly
It's interesitn gyou were able to reproduce that locally. This one has been plaguing us for a while Xiubo. I've seen ... Patrick Donnelly
01:51 AM Bug #46853 (Duplicate): ceph_test_libcephfs: LibCephFS.TestUtime gets core dumped randomly
Patrick Donnelly
01:21 AM Bug #46853 (Duplicate): ceph_test_libcephfs: LibCephFS.TestUtime gets core dumped randomly
With the upstream, when running the ./bin/ceph_test_libcephfs test, I randomly gettting:... Xiubo Li

08/06/2020

09:11 PM Fix #46851 (Fix Under Review): qa: add debugging for volumes plugin use of libcephfs
Patrick Donnelly
09:08 PM Fix #46851 (Resolved): qa: add debugging for volumes plugin use of libcephfs
To aid debugging #46832. Patrick Donnelly
09:06 PM Bug #46832 (Fix Under Review): client: static dirent for readdir is not thread-safe
Patrick Donnelly
08:54 PM Bug #46832 (In Progress): client: static dirent for readdir is not thread-safe
Another instance with debugging: https://pulpito.ceph.com/pdonnell-2020-08-06_15:29:50-fs-wip-pdonnell-testing-202008... Patrick Donnelly
06:42 PM Bug #46844 (Won't Fix): ceph-fuse: writing data can exceed quota when mount with ceph-fuse
See: https://docs.ceph.com/docs/master/cephfs/quota/#limitations Patrick Donnelly
07:51 AM Bug #46844 (Won't Fix): ceph-fuse: writing data can exceed quota when mount with ceph-fuse
setfattr -n ceph.quota.max_bytes -v 1073741824 /opt/cephfs/test1/
use ceph-fuse mount the dir /cephfs/test1/ to /m...
Yao Ning
06:17 PM Bug #46830 (Fix Under Review): mds: do not raise "client failing to respond to cap release" when ...
Patrick Donnelly
04:06 PM Bug #46830 (In Progress): mds: do not raise "client failing to respond to cap release" when clien...
Patrick Donnelly
06:03 PM Bug #46823: nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message mds0 len 67
So I tried reproducing this locally and couldn't get the error to pop. I suspect that the MDS I have is not sending a... Jeff Layton
01:51 PM Bug #44318 (Duplicate): nautilus: mgr/volumes: exception when logging message (in logging::log())
https://tracker.ceph.com/issues/46832
So, like this was seen a while back in nautilus. Seems to happen once in a w...
Venky Shankar

08/05/2020

06:23 PM Feature #42451 (Fix Under Review): mds: add root_squash
Patrick Donnelly
06:04 PM Bug #46832: client: static dirent for readdir is not thread-safe
Debugging branch: https://github.com/ceph/ceph/pull/36483 Patrick Donnelly
08:36 AM Bug #46832: client: static dirent for readdir is not thread-safe
So, this is probably a unicode+py2 thingy. One way to fix this is to log raw strings by prefixing the log message wit... Venky Shankar
04:38 AM Bug #46832: client: static dirent for readdir is not thread-safe
Real backtrace:... Venky Shankar
02:33 PM Bug #46675 (Duplicate): nautilus: fs/upgrade test: Crash: 'wait_until_healthy' reached maximum tr...
Sorry I missed this tracker ticket when searching. I'll mark this as duplicate since the other already has the fix li... Patrick Donnelly
02:27 PM Bug #46831: nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
Bug is only in nautilus. Patrick Donnelly
11:56 AM Bug #46831: nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
This issue was already reported at https://tracker.ceph.com/issues/46675 Ramana Raja
06:51 AM Bug #46831 (Fix Under Review): nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
https://github.com/ceph/ceph/pull/36462 Zheng Yan
01:36 PM Feature #46074 (Fix Under Review): mds: provide altrenatives to increase the total cephfs subvolu...
Zheng Yan
01:00 PM Bug #46163 (Fix Under Review): mgr/volumes: Clone operation uses source subvolume root directory ...
Shyamsundar Ranganathan

08/04/2020

10:19 PM Bug #46831 (New): nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
Looks like this occurs shortly after the upgrade from Luminous:... Patrick Donnelly
08:01 PM Bug #46831 (Resolved): nautilus: mds: SIGSEGV in MDCache::finish_uncommitted_slave
... Patrick Donnelly
10:07 PM Bug #46832 (Resolved): client: static dirent for readdir is not thread-safe
... Patrick Donnelly
07:54 PM Backport #46635 (Resolved): nautilus: mds: null pointer dereference in MDCache::finish_rollback
Patrick Donnelly
05:38 PM Bug #46830 (Resolved): mds: do not raise "client failing to respond to cap release" when client w...
If a client has more than mds_min_caps_per_client caps pinned due to open files and the MDS is trying to recall caps ... Patrick Donnelly
04:38 PM Bug #46823 (In Progress): nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message ...
Patch posted upstream and marked for stable:
https://marc.info/?l=ceph-devel&m=159655872206314&w=2
Jeff Layton
02:59 PM Bug #46823: nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message mds0 len 67
I missed some of the fields. op and seq come from struct ceph_mds_session_head:... Jeff Layton
11:24 AM Bug #46823: nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message mds0 len 67
To be clear:... Jeff Layton
11:18 AM Bug #46823: nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message mds0 len 67
handle_session only really deals with the "front" part of the message, so the corruption is likely there.... Jeff Layton
02:10 AM Bug #46823 (Resolved): nautilus: kceph w/ testing branch: mdsc_handle_session corrupt message mds...
... Patrick Donnelly
12:30 PM Backport #46821 (In Progress): nautilus: pybind/mgr/volumes: Add the ability to keep snapshots of...
Shyamsundar Ranganathan
10:41 AM Bug #46426 (New): mds: 8MMDSPing is not an MMDSOp type
Jos Collin

08/03/2020

06:34 PM Backport #46635 (In Progress): nautilus: mds: null pointer dereference in MDCache::finish_rollback
Patrick Donnelly
06:21 PM Backport #46821 (Resolved): nautilus: pybind/mgr/volumes: Add the ability to keep snapshots of su...
https://github.com/ceph/ceph/pull/36448 Patrick Donnelly
06:21 PM Backport #46820 (Resolved): octopus: pybind/mgr/volumes: Add the ability to keep snapshots of sub...
https://github.com/ceph/ceph/pull/36803 Patrick Donnelly
05:13 PM Feature #42451 (In Progress): mds: add root_squash
Ramana Raja
02:35 PM Bug #46817 (Duplicate): ceph fs status prints stack trace
Duplicate of https://tracker.ceph.com/issues/45633 Jan Fajerski
01:32 PM Bug #46817 (Duplicate): ceph fs status prints stack trace
We had a cluster in an intermediate failed state (mixed versions nautilus and octopus with multiple active MDS). ceph... Jan Fajerski
01:42 PM Feature #46746 (In Progress): mgr/nfs: Add interface to accept yaml file for creating clusters
Patrick Donnelly
01:42 PM Bug #46747 (In Progress): mds: make rstats in CInode::old_inodes stable
Patrick Donnelly
01:41 PM Bug #46809 (In Progress): mds: purge orphan objects created by lost async file creation
Patrick Donnelly
01:02 AM Bug #46809 (In Progress): mds: purge orphan objects created by lost async file creation
Zheng Yan

08/01/2020

11:22 AM Backport #46796 (In Progress): nautilus: mds: Subvolume snapshot directory does not save attribut...
Shyamsundar Ranganathan
11:20 AM Backport #46795 (In Progress): octopus: mds: Subvolume snapshot directory does not save attribute...
Shyamsundar Ranganathan

07/31/2020

09:19 PM Tasks #46768 (Resolved): client: clean up the unnecessary client_lock for _conf->client_trace
Patrick Donnelly
09:19 PM Bug #46766 (Pending Backport): mds: memory leak during cache drop
Patrick Donnelly
09:18 PM Bug #46765 (Pending Backport): mds: segv in MDCache::wait_for_uncommitted_fragments
Patrick Donnelly
09:17 PM Tasks #46682 (Resolved): client: add timer_lock support
Patrick Donnelly
09:15 PM Bug #46597 (Pending Backport): qa: Fs cleanup fails with a traceback
Patrick Donnelly
09:14 PM Bug #46282 (Resolved): qa: multiclient connection interruptions by stopping one client
Patrick Donnelly
09:14 PM Bug #45806 (Resolved): qa/task/vstart_runner.py: setting the network namespace "ceph-ns--tmp-tmpq...
Patrick Donnelly
09:13 PM Bug #45817 (Resolved): qa: Command failed with status 2: ['sudo', 'bash', '-c', 'ip addr add 192....
Patrick Donnelly
09:11 PM Feature #45729 (Pending Backport): pybind/mgr/volumes: Add the ability to keep snapshots of subvo...
Patrick Donnelly
09:10 PM Bug #45575 (Pending Backport): cephfs-journal-tool: incorrect read_offset after finding missing o...
Patrick Donnelly
09:09 PM Feature #26996 (Resolved): cephfs: get capability cache hits by clients to provide introspection ...
Patrick Donnelly
05:23 PM Cleanup #46802 (In Progress): mds: do not use asserts for RADOS failures
https://github.com/ceph/ceph/blob/ec472b7b56eb5ed6ec52aa0bc4c2d18578f1e88c/src/mds/Server.cc#L371
and many others....
Patrick Donnelly
10:32 AM Backport #46796 (Resolved): nautilus: mds: Subvolume snapshot directory does not save attribute "...
https://github.com/ceph/ceph/pull/36404 Nathan Cutler
10:32 AM Backport #46795 (Resolved): octopus: mds: Subvolume snapshot directory does not save attribute "c...
https://github.com/ceph/ceph/pull/36403 Nathan Cutler
10:32 AM Backport #46793 (Rejected): nautilus: pybind/mgr/volumes: subvolume operations throw exception if...
Nathan Cutler
10:31 AM Backport #46792 (Rejected): octopus: pybind/mgr/volumes: subvolume operations throw exception if ...
Nathan Cutler
10:31 AM Backport #46790 (Rejected): nautilus: mds slave request 'no_available_op_found'
Nathan Cutler
10:31 AM Backport #46789 (Rejected): octopus: mds slave request 'no_available_op_found'
Nathan Cutler
10:31 AM Backport #46787 (Resolved): nautilus: client: in _open() the open ref maybe decreased twice, but ...
https://github.com/ceph/ceph/pull/36966 Nathan Cutler
10:31 AM Backport #46786 (Resolved): octopus: client: in _open() the open ref maybe decreased twice, but o...
https://github.com/ceph/ceph/pull/37249 Nathan Cutler
10:30 AM Backport #46784 (Resolved): nautilus: mds/CInode: Optimize only pinned by subtrees check
https://github.com/ceph/ceph/pull/36965 Nathan Cutler
10:30 AM Backport #46783 (Resolved): octopus: mds/CInode: Optimize only pinned by subtrees check
https://github.com/ceph/ceph/pull/37248 Nathan Cutler
06:41 AM Backport #46641 (Resolved): nautilus: qa: random subvolumegroup collision
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36314
m...
Nathan Cutler

07/30/2020

06:52 PM Bug #44294 (Resolved): mds: "elist.h: 91: FAILED ceph_assert(_head.empty())"
Patrick Donnelly
05:43 PM Bug #44294 (Pending Backport): mds: "elist.h: 91: FAILED ceph_assert(_head.empty())"
This should have been flagged for backport. Patrick Donnelly
05:51 PM Backport #46778 (Duplicate): nautilus: mds: "elist.h: 91: FAILED ceph_assert(_head.empty())"
Patrick Donnelly
05:44 PM Backport #46778 (Duplicate): nautilus: mds: "elist.h: 91: FAILED ceph_assert(_head.empty())"
Patrick Donnelly
09:21 AM Bug #46769 (Fix Under Review): qa: Refactor cephfs creation/removal code.
Kotresh Hiremath Ravishankar
08:14 AM Bug #46769 (In Progress): qa: Refactor cephfs creation/removal code.
Kotresh Hiremath Ravishankar
08:14 AM Bug #46769 (Fix Under Review): qa: Refactor cephfs creation/removal code.
The 'CephFSTestCase' class creates the filesystem based on
'REQUIRE_FILESYSTEM' flag in 'setUp' but the correspondin...
Kotresh Hiremath Ravishankar
08:15 AM Tasks #46768 (Fix Under Review): client: clean up the unnecessary client_lock for _conf->client_t...
Xiubo Li
08:09 AM Tasks #46768 (Resolved): client: clean up the unnecessary client_lock for _conf->client_trace
There is no need to make the "cct->_conf->client_trace" under the
client_lock, it is for the "ceph-syn" and it almos...
Xiubo Li
03:13 AM Fix #46727 (Pending Backport): mds/CInode: Optimize only pinned by subtrees check
Patrick Donnelly
03:06 AM Bug #46278 (Pending Backport): mds: Subvolume snapshot directory does not save attribute "ceph.qu...
Patrick Donnelly
03:05 AM Bug #45575 (Fix Under Review): cephfs-journal-tool: incorrect read_offset after finding missing o...
Patrick Donnelly
03:04 AM Bug #46733 (Closed): Erro:EEXIST returned while unprotecting a snap which is not protected
This issue no longer occurs as the protect/unprotect is deprecated with https://tracker.ceph.com/issues/45371
The pr...
Kotresh Hiremath Ravishankar
03:00 AM Bug #46420 (Resolved): cephfs-shell: Return proper error code instead of 1
Patrick Donnelly
02:59 AM Bug #46496 (Pending Backport): pybind/mgr/volumes: subvolume operations throw exception if volume...
Patrick Donnelly
02:57 AM Bug #46583 (Pending Backport): mds slave request 'no_available_op_found'
Patrick Donnelly
02:55 AM Bug #46664 (Pending Backport): client: in _open() the open ref maybe decreased twice, but only in...
Patrick Donnelly
02:46 AM Bug #46766 (Fix Under Review): mds: memory leak during cache drop
Patrick Donnelly
02:44 AM Bug #46766 (Resolved): mds: memory leak during cache drop
The MDSGatherBuilder used to recall state is not freed. Patrick Donnelly
02:39 AM Bug #46765 (Fix Under Review): mds: segv in MDCache::wait_for_uncommitted_fragments
Patrick Donnelly
02:34 AM Bug #46765 (Resolved): mds: segv in MDCache::wait_for_uncommitted_fragments
... Patrick Donnelly
02:05 AM Bug #46607 (Closed): nautilus: pybind/mgr/volumes: TypeError: bad operand type for unary -: 'str'
I believe this is fixed with https://tracker.ceph.com/issues/46464. Therefore I am closing this, please re-open this ... Kotresh Hiremath Ravishankar

07/29/2020

06:27 PM Bug #46675: nautilus: fs/upgrade test: Crash: 'wait_until_healthy' reached maximum tries (150) af...
This failure wasn't seen in v14.2.10 release testing,
https://tracker.ceph.com/issues/46039#note-2
https://pulpito....
Ramana Raja
06:10 PM Feature #46074: mds: provide altrenatives to increase the total cephfs subvolume snapshot counts ...
Zheng Yan wrote:
> I only see per-dir limit in the mds code. where is the 400 snapshot per-file-system limit from?
...
Patrick Donnelly
02:02 PM Feature #46074: mds: provide altrenatives to increase the total cephfs subvolume snapshot counts ...
I only see per-dir limit in the mds code. where is the 400 snapshot per-file-system limit from? Zheng Yan
02:48 PM Fix #46645: librados|libcephfs: use latest MonMap when creating from CephContext
Capturing a mail conversation on direction of fix:
> Shyamsundar
Patrick
> MonClient::handle_monmap handles th...
Shyamsundar Ranganathan
01:59 PM Feature #45747 (Fix Under Review): pybind/mgr/nfs: add interface for adding user defined configur...
Varsha Rao
10:07 AM Bug #41069 (New): nautilus: test_subvolume_group_create_with_desired_mode fails with "AssertionEr...
I see this in a recent nautilus run during 14.2.11 pre-release testing,
http://pulpito.front.sepia.ceph.com/rraja-20...
Ramana Raja
09:28 AM Bug #46747 (In Progress): mds: make rstats in CInode::old_inodes stable
when modifying dir, MDCache::project_rstat_frag_to_inode may wrongly update rstats in old_inodes of the dir. Zheng Yan
08:07 AM Feature #46746 (New): mgr/nfs: Add interface to accept yaml file for creating clusters
nfs cluster create -i <yaml_file>
This will deploy nfs ganesha clusters according to the cluster specification in ya...
Varsha Rao
04:32 AM Bug #43943 (Resolved): qa: "[WRN] evicting unresponsive client smithi131:z (6314), after 304.461 ...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:31 AM Bug #45530 (Resolved): qa/tasks/cephfs/test_snapshots.py: Command failed with status 1: ['cd', '|...
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:30 AM Bug #46025 (Resolved): client: release the client_lock before copying data in read
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:30 AM Bug #46042 (Resolved): mds: EMetablob replay too long will cause mds restart
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:30 AM Fix #46070 (Resolved): client: fix snap directory atime
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:30 AM Bug #46084 (Resolved): client: supplying ceph_fsetxattr with no value unsets xattr
While running with --resolve-parent, the script "backport-create-issue" noticed that all backports of this issue are ... Nathan Cutler
04:18 AM Backport #46466 (Resolved): nautilus: pybind/mgr/volumes: get_pool_names may indicate volume does...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36167
m...
Nathan Cutler
04:18 AM Backport #46478 (Resolved): nautilus: pybind/mgr/volumes: volume deletion should check mon_allow_...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36167
m...
Nathan Cutler
04:18 AM Backport #46235 (Resolved): nautilus: pybind/mgr/volumes: volume deletion not always removes the ...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36167
m...
Nathan Cutler
04:17 AM Backport #46470 (Resolved): nautilus: client: release the client_lock before copying data in read
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36294
m...
Nathan Cutler
04:17 AM Backport #46388 (Resolved): nautilus: pybind/mgr/volumes: cleanup stale connection hang
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36215
m...
Nathan Cutler
04:17 AM Backport #46464 (Resolved): nautilus: mgr/volumes: fs subvolume clones stuck in progress when lib...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36180
m...
Nathan Cutler
04:16 AM Backport #46523 (Resolved): nautilus: mds: fix hang issue when accessing a file under a lost pare...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36179
m...
Nathan Cutler
04:16 AM Backport #46521 (Resolved): nautilus: mds: deleting a large number of files in a directory causes...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36178
m...
Nathan Cutler
04:16 AM Backport #46517 (Resolved): nautilus: client: directory inode can not call release_callback
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36177
m...
Nathan Cutler
04:16 AM Backport #46474 (Resolved): nautilus: mds: make threshold for MDS_TRIM warning configurable
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36175
m...
Nathan Cutler
04:15 AM Backport #46409 (Resolved): nautilus: client: supplying ceph_fsetxattr with no value unsets xattr
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36173
m...
Nathan Cutler
04:15 AM Backport #46310 (Resolved): nautilus: qa/tasks/cephfs/test_snapshots.py: Command failed with stat...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36172
m...
Nathan Cutler
04:14 AM Backport #46200 (Resolved): nautilus: qa: "[WRN] evicting unresponsive client smithi131:z (6314),...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36171
m...
Nathan Cutler
04:14 AM Backport #46189 (Resolved): nautilus: mds: EMetablob replay too long will cause mds restart
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36170
m...
Nathan Cutler
12:31 AM Tasks #46688: client: add inode lock support
For the Inode::inode_lock it is responsible to protect :
1, all the members in the Inode class
2, if the Inode'...
Xiubo Li

07/28/2020

08:26 PM Backport #46187 (Resolved): nautilus: client: fix snap directory atime
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/36169
m...
Nathan Cutler
06:10 PM Bug #46733 (Triaged): Erro:EEXIST returned while unprotecting a snap which is not protected
Patrick Donnelly
10:25 AM Bug #46733 (Closed): Erro:EEXIST returned while unprotecting a snap which is not protected
Double unprotect or unprotect on a snap which is not protected give EEXIST error code.
[root@node /]# ceph fs subvo...
Humble Chirammal
03:52 PM Bug #41581 (In Progress): pybind/mgr: Fix subvolume options
Jos Collin
01:04 PM Bug #41581: pybind/mgr: Fix subvolume options
* In Progress Ajitesh Panda
02:32 PM Backport #46234 (In Progress): octopus: pybind/mgr/volumes: volume deletion not always removes th...
Kotresh Hiremath Ravishankar
02:32 PM Backport #46477 (In Progress): octopus: pybind/mgr/volumes: volume deletion should check mon_allo...
Kotresh Hiremath Ravishankar
02:32 PM Backport #46465 (In Progress): octopus: pybind/mgr/volumes: get_pool_names may indicate volume do...
Kotresh Hiremath Ravishankar
02:31 PM Backport #46642 (In Progress): octopus: qa: random subvolumegroup collision
Kotresh Hiremath Ravishankar
08:22 AM Backport #46641 (In Progress): nautilus: qa: random subvolumegroup collision
Kotresh Hiremath Ravishankar
 

Also available in: Atom