Project

General

Profile

Activity

From 07/29/2021 to 08/27/2021

08/27/2021

11:15 PM Bug #52430: mds: fast async create client mount breaks racy test
This one seems pretty reproducible: /ceph/teuthology-archive/pdonnell-2021-08-27_16:46:16-fs-wip-pdonnell-testing-202... Patrick Donnelly
03:54 PM Bug #52430 (New): mds: fast async create client mount breaks racy test
... Patrick Donnelly
06:37 PM Bug #52260: 1 MDSs are read only | pacific 16.2.5
Milind Changire wrote:
> @cephuser2345
> On any of the clusters still running Nautilus, please run the following co...
Patrick Donnelly
12:43 PM Bug #52260: 1 MDSs are read only | pacific 16.2.5
resetting priority to Urgent; probably got set to Normal due to some mouse or keyboard activity on my part Milind Changire
12:07 PM Bug #52260: 1 MDSs are read only | pacific 16.2.5
@cephuser2345
On any of the clusters still running Nautilus, please run the following command to extract the inode b...
Milind Changire
05:21 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
Neha Ojha wrote:
> Couple of updates:
>
> 1. I am not able to reproduce the issue in pacific with the same reprod...
Patrick Donnelly
03:33 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
Couple of updates:
1. I am not able to reproduce the issue in pacific with the same reproducer, https://pulpito.ce...
Neha Ojha
06:04 AM Fix #51873 (Fix Under Review): mds: update hit_dir for dir distinguishes META_POP_IRD and METE_PO...
Venky Shankar
02:40 AM Backport #52427 (Resolved): pacific: qa: "error reading sessionmap 'mds1_sessionmap'"
https://github.com/ceph/ceph/pull/45564 Backport Bot
02:36 AM Bug #51905 (Pending Backport): qa: "error reading sessionmap 'mds1_sessionmap'"
Patrick Donnelly
02:33 AM Bug #43216 (Fix Under Review): MDSMonitor: removes MDS coming out of quorum election
Patrick Donnelly
02:18 AM Backport #51544 (Resolved): pacific: mgr/volumes: use a dedicated libcephfs handle for subvolume ...
Patrick Donnelly
02:18 AM Backport #51834 (Resolved): pacific: mon/MDSMonitor: allow creating a file system with a specific...
Patrick Donnelly

08/26/2021

06:38 PM Backport #51544: pacific: mgr/volumes: use a dedicated libcephfs handle for subvolume API calls
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42914
merged
Yuri Weinstein
06:38 PM Backport #51834: pacific: mon/MDSMonitor: allow creating a file system with a specific fscid
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42900
merged
Yuri Weinstein
04:34 PM Backport #52029 (Need More Info): pacific: mgr/nfs :update pool name to '.nfs' in vstart.sh
Patrick Donnelly
04:33 PM Backport #51421 (Need More Info): pacific: mgr/nfs: Add support for RGW export
Patrick Donnelly
04:32 PM Backport #51832 (In Progress): pacific: mds: META_POP_READDIR, META_POP_FETCH, META_POP_STORE, an...
Patrick Donnelly
04:30 PM Backport #51932 (In Progress): pacific: mds: MDCache.cc:5319 FAILED ceph_assert(rejoin_ack_gather...
Patrick Donnelly
04:29 PM Backport #51977 (In Progress): pacific: client: make sure only to update dir dist from auth mds
Patrick Donnelly
04:27 PM Backport #51198 (In Progress): pacific: msg: active_connections regression
Patrick Donnelly
04:18 PM Backport #51935 (In Progress): pacific: mds: improve debugging for mksnap denial
Patrick Donnelly
04:16 PM Backport #52036 (Resolved): pacific: mon/MDSMonitor.cc: fix join fscid not applied with pending f...
Patrick Donnelly
04:15 PM Backport #51983 (Resolved): pacific: mon/MDSMonitor: do not pointlessly kill standbys that are in...
Patrick Donnelly
04:15 PM Backport #51411 (Resolved): pacific: pybind/mgr/volumes: purge queue seems to block operating on ...
Patrick Donnelly
04:15 PM Backport #51174 (Resolved): pacific: mgr/nfs: add nfs-ganesha config hierarchy
Patrick Donnelly
04:15 PM Backport #50991 (Resolved): pacific: mgr/nfs: skipping conf file or passing empty file throws tra...
Patrick Donnelly
12:42 PM Backport #52384 (In Progress): pacific: pybind/mgr/volumes: Cloner threads stuck in loop trying t...
Kotresh Hiremath Ravishankar
02:11 AM Bug #52386 (Fix Under Review): client: fix dump mds twice
Patrick Donnelly
02:04 AM Backport #51833 (In Progress): pacific: client: flush the mdlog in unsafe requests' relevant and ...
Xiubo Li
02:01 AM Backport #51937 (In Progress): pacific: qa: test_full_fsync (tasks.cephfs.test_full.TestClusterFu...
Xiubo Li
01:44 AM Tasks #47920 (Won't Fix): client: get rid of the client_lock for mdsmap
This approach makes not much sense but will make the code more complex and risky, will close it. Xiubo Li

08/25/2021

07:05 PM Backport #51411: pacific: pybind/mgr/volumes: purge queue seems to block operating on cephfs conn...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42083
merged
Yuri Weinstein
03:37 PM Bug #51866: mds daemon damaged after outage
David Piper wrote:
> Do the pgs need to be `active+clean` or are there other pg states that it would be safe to star...
Dan van der Ster
03:02 PM Bug #51866: mds daemon damaged after outage
We've delayed MDS restarts with a script that waits for `active+clean` pgs first. Script is attached; it's borrowed ... David Piper
02:06 PM Bug #52406: cephfs_metadata pool got full after upgrade from Nautilus to Pacific 16.2.5
Same as https://tracker.ceph.com/issues/52260 ? Dan van der Ster
09:15 AM Bug #52406: cephfs_metadata pool got full after upgrade from Nautilus to Pacific 16.2.5
OSDs with metadata utilization on SSD drives after recreating OSDs and filling CephFS with same data again:... Denis Polom
09:08 AM Bug #52406 (Need More Info): cephfs_metadata pool got full after upgrade from Nautilus to Pacific...
Hi
I have following setup on my Ceph cluster:
cephfs_metadata pool - using crush rule to use only SSD devices t...
Denis Polom
12:01 PM Bug #52260: 1 MDSs are read only | pacific 16.2.5
Is it the same as https://tracker.ceph.com/issues/52406 ? Dan van der Ster
09:40 AM Bug #52260: 1 MDSs are read only | pacific 16.2.5

We think there’s a major bug here with great risk.
Do you need any further logs/information? Try to replicate th...
cephuser2345 user
04:27 AM Backport #51544 (In Progress): pacific: mgr/volumes: use a dedicated libcephfs handle for subvolu...
Venky Shankar

08/24/2021

09:51 PM Backport #51983: pacific: mon/MDSMonitor: do not pointlessly kill standbys that are incompatible ...
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42578
merged
Yuri Weinstein
09:51 PM Backport #52036: pacific: mon/MDSMonitor.cc: fix join fscid not applied with pending fsmap at boot
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42578
merged
Yuri Weinstein
09:50 PM Backport #51174: pacific: mgr/nfs: add nfs-ganesha config hierarchy
Varsha Rao wrote:
> https://github.com/ceph/ceph/pull/42096
merged
Yuri Weinstein
09:50 PM Backport #50991: pacific: mgr/nfs: skipping conf file or passing empty file throws traceback
Varsha Rao wrote:
> https://github.com/ceph/ceph/pull/42096
merged
Yuri Weinstein
08:32 PM Bug #52397 (Resolved): pacific: qa: test_acls (tasks.cephfs.test_acls.TestACLs) failed
See this in Yuri's latest pacific run,
https://pulpito.ceph.com/yuriw-2021-08-23_19:33:26-fs-wip-yuri4-testing-2021-...
Ramana Raja
08:03 PM Bug #52396 (Duplicate): pacific: qa: ERROR: test_perf_counters (tasks.cephfs.test_openfiletable.O...
See this in Yuri's latest pacific run,
https://pulpito.ceph.com/yuriw-2021-08-23_19:33:26-fs-wip-yuri4-testing-2021-...
Ramana Raja
12:29 PM Bug #51281 (In Progress): qa: snaptest-snap-rm-cmp.sh: "echo 'FAIL: bad match, /tmp/a 4637e766853...
Venky Shankar
12:27 PM Bug #36273 (New): qa: add background task for some units which drops MDS cache
I worked on this a while back, but probably never pushed a PR. I'll move tracker state when I have the PR pushed. Venky Shankar
12:23 PM Bug #51589: mds: crash when journaling during replay
I'm unable to reproduce the crash. Do you have the MDS logs at the time of crash? As you mentioned you do not have th... Venky Shankar
04:30 AM Backport #51834 (In Progress): pacific: mon/MDSMonitor: allow creating a file system with a speci...
Ramana Raja
02:17 AM Bug #52386 (Resolved): client: fix dump mds twice
src/client: In asok cmd "dump_cache", fix dump mds twice yantao xue
12:05 AM Backport #52384 (Resolved): pacific: pybind/mgr/volumes: Cloner threads stuck in loop trying to c...
https://github.com/ceph/ceph/pull/42932 Backport Bot
12:04 AM Bug #51707 (Pending Backport): pybind/mgr/volumes: Cloner threads stuck in loop trying to clone t...
Patrick Donnelly
12:03 AM Bug #51805 (Resolved): pybind/mgr/volumes: The cancelled clone still goes ahead and complete the ...
backport part of #51707 Patrick Donnelly

08/23/2021

11:14 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
I reproduced this issue with additional logging using the same reproducer https://tracker.ceph.com/issues/51282#note-... Neha Ojha
08:06 PM Backport #52084: pacific: pybind/mgr/stats: KeyError
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/42702
m...
Loïc Dachary
08:03 PM Backport #51940: pacific: MDSMonitor: monitor crash after upgrade from ceph 15.2.13 to 16.2.4
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/42536
m...
Loïc Dachary
05:17 PM Bug #52382 (In Progress): mds,client: add flag to MClientSession for reject reason
Patrick Donnelly
05:17 PM Bug #52382 (Resolved): mds,client: add flag to MClientSession for reject reason
Ceph tracker for #47450. Patrick Donnelly

08/22/2021

12:20 PM Bug #52260: 1 MDSs are read only | pacific 16.2.5
Hi,
Any update on this?
cephuser2345 user

08/20/2021

08:53 PM Bug #51295 (Rejected): When fsname = k8s cephfs is specified, an error is displayed:"HEALTH_ERR 1...
That auth credential is not valid for Octopus. You should upgrade to Pacific. Patrick Donnelly
09:06 AM Bug #51975 (Resolved): pybind/mgr/stats: KeyError
Jos Collin
12:34 AM Bug #49132: mds crashed "assert_condition": "state == LOCK_XLOCK || state == LOCK_XLOCKDONE",
Andras Pataki wrote:
> max_mds is 1 - we are running a single active MDS only. The clients are all ceph-fuse.
> I'...
Xiubo Li

08/19/2021

10:10 PM Backport #51544: pacific: mgr/volumes: use a dedicated libcephfs handle for subvolume API calls
Venky, please take this one. Patrick Donnelly
07:56 PM Backport #51935 (Need More Info): pacific: mds: improve debugging for mksnap denial
Patrick Donnelly
07:56 PM Backport #51937 (Need More Info): pacific: qa: test_full_fsync (tasks.cephfs.test_full.TestCluste...
Xiubo, please take this one. Patrick Donnelly
07:51 PM Backport #51940 (Resolved): pacific: MDSMonitor: monitor crash after upgrade from ceph 15.2.13 to...
Patrick Donnelly
07:47 PM Backport #52084 (Resolved): pacific: pybind/mgr/stats: KeyError
Patrick Donnelly
06:00 PM Bug #49132: mds crashed "assert_condition": "state == LOCK_XLOCK || state == LOCK_XLOCKDONE",
max_mds is 1 - we are running a single active MDS only. The clients are all ceph-fuse.
I've tried setting the MDS l...
Andras Pataki

08/18/2021

09:07 AM Bug #51589: mds: crash when journaling during replay
Normally, MDLog does not expire the latest log segment during trimming. The exception to this is when then log segmen... Venky Shankar

08/17/2021

03:57 PM Backport #52084: pacific: pybind/mgr/stats: KeyError
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42702
merged
Yuri Weinstein
02:16 AM Documentation #49406 (Resolved): Exceeding osd nearfull ratio causes write throttle.
Patrick Donnelly

08/16/2021

10:38 PM Fix #52104 (Fix Under Review): qa: add testing for "copyfrom" mount option
Patrick Donnelly
09:53 PM Feature #51716 (Fix Under Review): Add option in `fs new` command to start rank 0 in failed state
Patrick Donnelly
09:30 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
Casey Bodley wrote:
> should the rgw suite be whitelisting these too?
I think ignorelisting these errors/warnings...
Patrick Donnelly
08:58 PM Backport #51940: pacific: MDSMonitor: monitor crash after upgrade from ceph 15.2.13 to 16.2.4
Backport Bot wrote:
> https://github.com/ceph/ceph/pull/42536
merged
Yuri Weinstein
06:18 PM Bug #52280: Mds crash and fails with assert on prepare_new_inode
Patrick Donnelly wrote:
> Were there any cluster health warnings? Some of the surround MDS logs would also be helpfu...
Yael Azulay
01:43 PM Bug #52280 (Need More Info): Mds crash and fails with assert on prepare_new_inode
Were there any cluster health warnings? Some of the surround MDS logs would also be helpful. Patrick Donnelly
08:57 AM Bug #52280 (Resolved): Mds crash and fails with assert on prepare_new_inode
Hi All
We have nautilus 14.2.7, cluster with 3 MDs.
Sometimes, during heavy loads of kubernetese pods, the MDs kee...
Yael Azulay
01:50 PM Bug #52134: botched cephadm upgrade due to mds failures
If you hit this again, increase debugging on mons to debug_mon=20 and let it chew for 30s-1m so we can hopefully see ... Patrick Donnelly
05:51 AM Bug #52274 (Fix Under Review): mgr/nfs: add more log messages
Varsha Rao
04:33 AM Bug #52274 (Resolved): mgr/nfs: add more log messages
Varsha Rao
02:43 AM Bug #49132: mds crashed "assert_condition": "state == LOCK_XLOCK || state == LOCK_XLOCKDONE",
Andras Pataki wrote:
> [...]
> On our other large cluster we don't see such crashes. One major config difference...
Xiubo Li

08/14/2021

05:55 AM Bug #52260 (Duplicate): 1 MDSs are read only | pacific 16.2.5
Hi,
We've upgraded from Ceph 14.2.20 to 16.2.5 a couple of weeks ago and suddently the MDS metadata pool OSD's fi...
cephuser2345 user

08/12/2021

02:01 PM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
should the rgw suite be whitelisting these too? Casey Bodley
01:35 PM Bug #52094: Tried out Quincy: All MDS Standby
Hmm, not sure turnaround times, but neither the mailing list, a proxmox forum post, nor this ticket has been responde... Joshua West
10:49 AM Bug #51866: mds daemon damaged after outage
Thanks Dan, that's a convincing diagnosis. We've diverted our attention to other projects but I'll look into implemen... David Piper

08/11/2021

09:15 PM Feature #51716 (In Progress): Add option in `fs new` command to start rank 0 in failed state
Ramana Raja
03:37 PM Bug #51365 (In Progress): mgr/nfs: show both ipv4 and ipv6 address in cluster info command
The latest code tries to use the HostSpec.addr field here. Only if that field is empty (or a hostname instead of an ... Sage Weil
03:36 PM Bug #52134: botched cephadm upgrade due to mds failures
... Jeff Layton
03:31 PM Bug #52134 (Can't reproduce): botched cephadm upgrade due to mds failures
I tried to upgrade my cephadm cluster from one (development) quincy-ish build to another. It got about halfway throug... Jeff Layton
01:26 PM Bug #49307 (Duplicate): nautilus: qa: "RuntimeError: expected fetching path of an pending clone t...
Kotresh Hiremath Ravishankar
01:23 PM Bug #49307: nautilus: qa: "RuntimeError: expected fetching path of an pending clone to fail"
Duplicate of this https://tracker.ceph.com/issues/48231 but not backported to nautilus. Kotresh Hiremath Ravishankar
01:25 PM Bug #52123 (Fix Under Review): mds sends cap updates with btime zeroed out
Jeff Layton
01:20 PM Bug #51589: mds: crash when journaling during replay
If I'm reading this correctly, it looks like an log entry can be submitted when there are no log segments available f... Venky Shankar
12:57 PM Bug #52062 (Fix Under Review): cephfs-mirror: terminating a mirror daemon can cause a crash at times
Venky Shankar
12:13 PM Documentation #49406 (In Progress): Exceeding osd nearfull ratio causes write throttle.
Ok, added a blurb to https://docs.ceph.com/en/latest/cephfs/troubleshooting/#kernel-mount-debugging Jeff Layton

08/10/2021

08:37 PM Feature #51787 (Resolved): mgr/nfs: deploy nfs-ganesha daemons on non-default port
Sage Weil
06:50 PM Bug #52123: mds sends cap updates with btime zeroed out
This was noticed as I was replicating the problem in #46574. With this PR in place, the btime is correctly reported i... Jeff Layton
02:57 PM Bug #52123 (Resolved): mds sends cap updates with btime zeroed out
The MDS is sending cap updates that have the btime zeroed out in some cases. Ensure that it's sending the right btime... Jeff Layton
04:38 PM Bug #50719: xattr returning from the dead (sic!)
Jeff Layton wrote:
> Ralph, ping? Were you ever able to determine whether this was fixed in later kernels?
At first...
Ralph Böhme
02:37 PM Cleanup #51614 (Resolved): mgr/nfs: remove dashboard test remnant from unit tests
Sage Weil
02:36 PM Bug #51800 (Resolved): mgr/nfs: create rgw export with vstart
Sage Weil
02:36 PM Documentation #51683 (Resolved): mgr/nfs: add note about creating exports for nfs using vstart to...
Sage Weil
02:33 PM Documentation #24642: doc: visibility semantics to other clients
I had in mind that hopefully CephFS could have user-facing documentation about file visibility semantics across multi... Niklas Hambuechen

08/09/2021

08:08 PM Backport #51819 (Resolved): pacific: cephfs-mirror: removing a mirrored directory path causes oth...
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/42458
m...
Loïc Dachary
08:05 PM Backport #51939: octopus: MDSMonitor: monitor crash after upgrade from ceph 15.2.13 to 16.2.4
This update was made using the script "backport-resolve-issue".
backport PR https://github.com/ceph/ceph/pull/42537
m...
Loïc Dachary
06:56 PM Bug #50719: xattr returning from the dead (sic!)
Ralph, ping? Were you ever able to determine whether this was fixed in later kernels? Jeff Layton
06:54 PM Bug #48439 (Resolved): fsstress failure with mds thrashing: "mds.0.6 Evicting (and blocklisting) ...
I think this was fixed upstream with commit 62575e270f661aba64778cbc5f354511cf9abb21, and that got backported to RHEL... Jeff Layton
06:47 PM Documentation #24642: doc: visibility semantics to other clients
It's not clear to me what this tracker bug is actually asking for. I get that you want some documentation about "guar... Jeff Layton
06:10 PM Bug #44976 (Resolved): MDS problem slow requests, cache pressure, damaged metadata after upgradin...
I think we ended up resolving the original issue and then the bug wandered off into the weeds and Mitchell opened a n... Jeff Layton
06:07 PM Feature #42447 (Resolved): add basic client setup page
Jeff Layton
06:06 PM Bug #47998 (Resolved): cephfs kernel client hung
Jeff Layton
06:06 PM Bug #47998: cephfs kernel client hung
Fixed in mainline in commit bca9fc14c70fc. Jeff Layton
06:02 PM Bug #48125 (Resolved): qa: test_subvolume_snapshot_clone_cancel_in_progress failure
Fixed in upstream commit 04fabb1199d1f995d6b9a1c42c046ac4bdac2d19. Jeff Layton
05:45 PM Feature #1276 (Fix Under Review): client: expose mds partition via virtual xattrs
Jeff Layton
05:45 PM Feature #6373: kcephfs: qa: test fscache
Patrick Donnelly wrote:
>
> What's special about smithi vs. gibba? We could teach kclient.yaml to setup a file syst...
Jeff Layton
05:35 PM Bug #50083 (Resolved): CephFS file access issues using kernel driver: file overwritten with null ...
This is probably the bug that was fixed by this commit:
https://git.kernel.org/pub/scm/linux/kernel/git/torval...
Jeff Layton
10:36 AM Bug #51870 (Fix Under Review): pybind/mgr/volumes: first subvolume permissions set perms on /volu...
Kotresh Hiremath Ravishankar
10:34 AM Fix #52104 (Fix Under Review): qa: add testing for "copyfrom" mount option
We currently don't have any testing coverage for the copy_file_range syscall, which requires the "copyfrom" mount opt... Luis Henriques
10:21 AM Feature #51787 (Fix Under Review): mgr/nfs: deploy nfs-ganesha daemons on non-default port
Varsha Rao

08/08/2021

03:36 PM Bug #52094: Tried out Quincy: All MDS Standby
... Joshua West

08/07/2021

10:43 AM Bug #52094 (Duplicate): Tried out Quincy: All MDS Standby
On Proxmox, and suffering with #51445 (https://tracker.ceph.com/issues/51445)
As any good "Knows enough to be danger...
Joshua West
12:23 AM Bug #48673 (In Progress): High memory usage on standby replay MDS
I've been able to reproduce this. Will try to track down the cause... Patrick Donnelly

08/06/2021

08:37 PM Bug #47787: mgr/nfs: exercise host-level HA of NFS-Ganesha by killing the process
Sebastian, do we have documentation somewhere about which situations cephadm will restart services? I think there nee... Patrick Donnelly
06:29 PM Fix #52068: qa: add testing for "ms_mode" mount option
There's a potential problem. I suspect that a lot of the qa/ infrastructure is building device strings using v1 mon a... Jeff Layton
05:51 PM Fix #52068 (Fix Under Review): qa: add testing for "ms_mode" mount option
Ilya Dryomov
04:25 PM Fix #52068: qa: add testing for "ms_mode" mount option
Moving to CephFS as the purpose of the ticket is the backport to pacific. Ilya Dryomov
12:52 PM Backport #52084 (In Progress): pacific: pybind/mgr/stats: KeyError
Jos Collin
12:25 PM Backport #52084 (Resolved): pacific: pybind/mgr/stats: KeyError
https://github.com/ceph/ceph/pull/42702 Backport Bot
12:22 PM Bug #51975 (Pending Backport): pybind/mgr/stats: KeyError
Jos Collin

08/05/2021

06:09 PM Fix #52068 (Resolved): qa: add testing for "ms_mode" mount option
We currently don't have any testing coverage for the "ms_mode" mount option. Add new workload variants for them. Jeff Layton
05:35 PM Bug #48673: High memory usage on standby replay MDS
We are seeing the same issue on pacific 16.2.5 as well. Not a big issue but very annoying. ... Howie C
11:47 AM Cleanup #51614 (Fix Under Review): mgr/nfs: remove dashboard test remnant from unit tests
Varsha Rao
05:26 AM Bug #52062 (Resolved): cephfs-mirror: terminating a mirror daemon can cause a crash at times
Seen in this teuthology run which thrashes the mirror daemon for active/active HA test: https://pulpito.ceph.com/vsha... Venky Shankar

08/04/2021

05:56 PM Bug #46902 (Rejected): mds: CInode::maybe_export_pin is broken
Patrick Donnelly
04:30 PM Backport #50188 (Rejected): octopus: qa: "Assertion `cb_done' failed."
Backporting to octopus is not worth the effort. Patrick Donnelly
11:43 AM Bug #51282: pybind/mgr/mgr_util: .mgr pool may be created too early causing spurious PG_DEGRADED ...
lot of these instances in: https://pulpito.ceph.com/ideepika-2021-08-03_21:18:59-rbd-wip-rbd-update-feature-distro-ba... Deepika Upadhyay
11:29 AM Documentation #51683 (In Progress): mgr/nfs: add note about creating exports for nfs using vstart...
Varsha Rao
11:29 AM Bug #51800 (Fix Under Review): mgr/nfs: create rgw export with vstart
Varsha Rao
03:04 AM Bug #51722: mds: slow performance on parallel rm operations for multiple kclients
The new PR will switch mds_lock to fair mutex. Xiubo Li

08/03/2021

06:22 PM Backport #52036 (In Progress): pacific: mon/MDSMonitor.cc: fix join fscid not applied with pendin...
Patrick Donnelly
06:20 PM Backport #52036 (Resolved): pacific: mon/MDSMonitor.cc: fix join fscid not applied with pending f...
https://github.com/ceph/ceph/pull/42578 Backport Bot
06:16 PM Bug #49157 (Pending Backport): mon/MDSMonitor.cc: fix join fscid not applied with pending fsmap a...
Patrick Donnelly
04:50 PM Backport #52029 (Rejected): pacific: mgr/nfs :update pool name to '.nfs' in vstart.sh
Backport Bot
04:48 PM Bug #51795 (Pending Backport): mgr/nfs:update pool name to '.nfs' in vstart.sh
Varsha Rao
01:23 PM Bug #51975 (Fix Under Review): pybind/mgr/stats: KeyError
Jos Collin
02:27 AM Bug #49132 (Triaged): mds crashed "assert_condition": "state == LOCK_XLOCK || state == LOCK_XLOC...
Patrick Donnelly
01:04 AM Bug #49132: mds crashed "assert_condition": "state == LOCK_XLOCK || state == LOCK_XLOCKDONE",
... Andras Pataki

08/02/2021

07:43 PM Bug #43960 (Triaged): MDS: incorrectly issues Fc for new opens when there is an existing writer
Patrick Donnelly
01:41 PM Bug #51923 (Duplicate): crash: Client::resolve_mds(std::__cxx11::basic_string<char, std::char_tra...
Patrick Donnelly
01:41 PM Bug #51757 (Duplicate): crash: /lib/x86_64-linux-gnu/libpthread.so.0(
Patrick Donnelly
11:44 AM Bug #51989 (Fix Under Review): cephfs-mirror: cephfs-mirror daemon status for a particular FS is ...
Venky Shankar
10:38 AM Bug #51989 (Resolved): cephfs-mirror: cephfs-mirror daemon status for a particular FS is not showing
`daemon status` doesn't require a file system name.... Venky Shankar

08/01/2021

08:58 PM Backport #51983 (In Progress): pacific: mon/MDSMonitor: do not pointlessly kill standbys that are...
Patrick Donnelly
03:50 AM Backport #51983 (Resolved): pacific: mon/MDSMonitor: do not pointlessly kill standbys that are in...
https://github.com/ceph/ceph/pull/42578 Backport Bot
03:46 AM Bug #49720 (Pending Backport): mon/MDSMonitor: do not pointlessly kill standbys that are incompat...
Patrick Donnelly

07/30/2021

09:05 PM Backport #51977 (Resolved): pacific: client: make sure only to update dir dist from auth mds
https://github.com/ceph/ceph/pull/42937 Backport Bot
09:05 PM Backport #51976 (Rejected): octopus: client: make sure only to update dir dist from auth mds
Backport Bot
09:03 PM Bug #51857 (Pending Backport): client: make sure only to update dir dist from auth mds
Patrick Donnelly
08:56 PM Bug #51975 (Resolved): pybind/mgr/stats: KeyError
... Patrick Donnelly
02:35 AM Backport #51939 (Resolved): octopus: MDSMonitor: monitor crash after upgrade from ceph 15.2.13 to...
Patrick Donnelly

07/29/2021

08:46 PM Bug #51964 (In Progress): qa: test_cephfs_mirror_restart_sync_on_blocklist failure
... Patrick Donnelly
09:23 AM Bug #51956 (Fix Under Review): mds: switch to use ceph_assert() instead of assert()
Xiubo Li
09:21 AM Bug #51956 (Resolved): mds: switch to use ceph_assert() instead of assert()
If the -DNDEBUG was specified when build the code, the assert() will do nothing.

I hit one odd issue that when...
Xiubo Li
 

Also available in: Atom