Project

General

Profile

Activity

From 03/24/2016 to 04/22/2016

04/22/2016

09:22 AM Bug #15378 (Rejected): ceph_volume_client: hasty removal of OSD caps during deauthorization
Ramana Raja
09:06 AM Bug #15378: ceph_volume_client: hasty removal of OSD caps during deauthorization
This issue would no longer be a concern once each volume (CephFS directory) gets its own RADOS namespace http://track... Ramana Raja

04/20/2016

02:00 AM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
here is my test result.... Zheng Yan

04/19/2016

02:43 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
I was able to make this happen with kernel mode as well. Does that tunable noted in #6 need to be implemented for fu... Barry Marson
07:24 AM Bug #15502 (Need More Info): files read or written with cephfs (fuse or kernel) on client drop al...
Zheng Yan
07:30 AM Bug #15045: CephFSVolumeClient.evict should be limited by path, not just auth ID
tested by https://github.com/ceph/ceph-qa-suite/pull/968 Ramana Raja

04/18/2016

12:52 PM Feature #13999: client: richacl support
code is done; waiting for richacl get merged into upstream Zheng Yan
12:49 PM Feature #13998 (Resolved): posix acl support
https://github.com/ceph/ceph/pull/5658 Zheng Yan
12:45 PM Feature #11950 (Fix Under Review): Strays enqueued for purge cause MDCache to exceed size limit
https://github.com/ceph/ceph/pull/8582 Zheng Yan
11:30 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
wip-zyan-testing branch includes that fix. http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/wip-zyan-test... Zheng Yan
08:22 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Are there rpms builded for this pr? I looked at http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ but I did n... Kenneth Waegeman
07:37 AM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
I can't reproduce this on 3.10.0-327.el7 kernel mount. To make ceph-fuse keeps the kernel pagecache, you need to set ... Zheng Yan

04/15/2016

09:32 PM Bug #15169 (Rejected): have trouble in mount.ceph in precise
This is an old ticket so you've probably already worked this out, but this was failing because your kernel was too old. John Spray
09:31 PM Bug #15168 (Duplicate): have trouble in mount.ceph
http://tracker.ceph.com/issues/15169#change-69275 John Spray
02:30 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
Kernel is 3.10.0-327.el7.x86_64 ie the GA kernel for RHEL7.2 Barry Marson
01:59 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
This was on both ceph-fuse and a recent-ish rhel (7.2? 7.3-prerelease?) kernel. Unless there's some extra thing in th... Greg Farnum
01:33 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...

This should be fixed in upstream, Barry, which version of RHEL kernel do you use?
Zheng Yan
12:29 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
Similar to http://tracker.ceph.com/issues/13640#change-66216 John Spray
12:43 PM Feature #15507: MDS: support "watching" an inode/dentry
Not a million miles away from http://tracker.ceph.com/projects/ceph/wiki/Live_Performance_Probes John Spray
07:12 AM Backport #15512 (Resolved): hammer: Double decreased the count to trim caps which will cause fail...
https://github.com/ceph/ceph/pull/8804 Nathan Cutler
03:19 AM Bug #15508: client: simultaneous readdirs are very racy
Hmm, I think the end result would be pretty much the same, although just having an array might be simpler. A pointer ... Greg Farnum
03:12 AM Bug #15508: client: simultaneous readdirs are very racy
Another option is assign dentry a cache index and use array to track the dentry list. If the shared_gen hasn't change... Zheng Yan

04/14/2016

11:06 PM Bug #13271: Missing dentry in cache when doing readdirs under cache pressure (?????s in ls-l)
This may get handled alongside http://tracker.ceph.com/issues/15508. Greg Farnum
11:06 PM Bug #15508: client: simultaneous readdirs are very racy
Some obvious solutions are disqualified, both because we can't really track what directory listing's are in progress ... Greg Farnum
11:01 PM Bug #15508 (Resolved): client: simultaneous readdirs are very racy
Imagine we have a ceph-fuse user doing readdirs a and b on a very large directory (which requires multiple MDS round-... Greg Farnum
10:49 PM Bug #11792: mds: recursive statistics are either inaccurate or too "chunky"
This is going to pop up for users. Let's be proactive about checking and fixing it if possible. Greg Farnum
10:45 PM Bug #13906 (Closed): pjd failure on hammer
I think maybe this got backported after all? If not, it hasn't come up again, so closing it. Greg Farnum
10:44 PM Bug #13107 (Resolved): ceph-fuse: handle multiple mounts on the same host (don't set nonce with o...
This got fixed when #13032 did! Greg Farnum
10:41 PM Bug #14319 (Pending Backport): Double decreased the count to trim caps which will cause failing t...
Whoops, this got merged in way back then in January!
Looks like no backport got scheduled or anything; we'll see i...
Greg Farnum
10:28 PM Bug #14716 (Won't Fix): "Thread.cc: 143: FAILED assert(status == 0)" in fs-hammer---basic-smithi
This was a result of the OSD full handling changes, which got partly backported. I think the resolution we ended up a... Greg Farnum
10:25 PM Bug #14759 (Closed): ovh: failed snaptest-git-ceph.sh test
It hasn't popped up again. Greg Farnum
10:24 PM Bug #14685: dbench hang on native cifs mount
Apparently still happening? http://qa-proxy.ceph.com/teuthology/teuthology-2016-04-02_23:14:02-samba-master---basic-s... Greg Farnum
10:19 PM Bug #15235 (Closed): MDS : erroneous error message about reading config file
There's a conversation on that PR. Greg Farnum
10:03 PM Feature #15507 (New): MDS: support "watching" an inode/dentry
It would be great if we could monitor all client access to a specific file. Obviously we can't check for each access ... Greg Farnum
09:58 PM Bug #15270 (Resolved): "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
Yuri Weinstein
09:58 PM Bug #15270: "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
changed @smoke@ suite to use kernel @testing@ Yuri Weinstein
09:48 PM Bug #15270: "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
I think anything running kernel tests needs to run with our testing kernel, not the distro kernel that happens to be ... Greg Farnum
09:51 PM Bug #15045 (Fix Under Review): CephFSVolumeClient.evict should be limited by path, not just auth ID
https://github.com/ceph/ceph/pull/8602 Greg Farnum
09:47 PM Feature #15506 (Resolved): qa: run at least one upgrade test in the FS suite
We've broken upgrading at least twice during the Jewel freeze/RC period. They would all have been detected if the PRs... Greg Farnum
09:36 PM Bug #15399 (In Progress): MDS incarnation get lost after remove filesystem
For Jewel: https://github.com/ceph/ceph/pull/8484
But a more comprehensive one (that works with pools shared betwe...
Greg Farnum
09:28 PM Bug #11314: qa: MDS crashed and the runs hung without ever timing out
We clearly aren't treating this as very important, and I think we've had more trouble with OSDs doing this than MDSes... Greg Farnum
09:27 PM Feature #14642: Validate layouts everywhere we load them
Okay, let's put this in as a feature. Greg Farnum
09:26 PM Bug #15502: files read or written with cephfs (fuse or kernel) on client drop all their page cach...
Zheng, can you look at this? Hopefully we just have a bad cap transition on the server or something. Greg Farnum
05:36 PM Bug #15502 (Resolved): files read or written with cephfs (fuse or kernel) on client drop all thei...
Testing cephfs file system I/O with early jewel bits (ceph-10.0.4-1.el7cp.x86_64) on:
RHEL72 client mounting a cep...
Barry Marson
09:23 PM Bug #9994 (Resolved): ceph-qa-suite: nfs mount timeouts
Well, this hasn't been updated in a while, and the tests I really remember failing were all on OVH, which was resolve... Greg Farnum
09:22 PM Bug #14807: MDS crashes repeatedly after upgrade to Infernalis from Hammer
Haven't seen this elsewhere, and no logs. Greg Farnum
09:20 PM Bug #15050: deleting striped file in cephfs doesn't free up file's space
Just waiting on backports, FS team doesn't need to worry about those. Greg Farnum
09:19 PM Bug #15402 (Resolved): Failure in TestMultiFilesystems.test_standby_for_fscid
Greg Farnum
09:18 PM Bug #14608: snaptests.yaml failure: [WRN] open_snap_parents has:" in cluster log
Still waiting to reproduce with logs. :( Greg Farnum
09:18 PM Bug #15303 (Resolved): Client holds incorrect complete flag on dir after losing caps
Greg Farnum
09:28 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
I send a RP that make MDS not pin strays in memory
could you take a try:
https://github.com/ukernel/ceph/tree/inf...
Zheng Yan

04/13/2016

03:37 PM Bug #15485 (Duplicate): drop /usr/bin/cephfs
Greg tells me that /usr/bin/cephfs is deprecated. We should rip it out post-Jewel.
Ken Dreyer

04/12/2016

03:43 AM Bug #15467: After "mount -l", ceph-fuse does not work
- mount -l
+ unmount -l
Shinobu Kinjo
03:39 AM Bug #15467 (Won't Fix): After "mount -l", ceph-fuse does not work
Since MDS stopped working because of running out ram, I did "mount -l" to unmount cephfs but did not restart the clie... Shinobu Kinjo
01:54 AM Bug #15465: MDSAuthCap parse fails on paths with hyphens
https://github.com/ceph/ceph/pull/8546 John Spray
01:51 AM Bug #15465 (Resolved): MDSAuthCap parse fails on paths with hyphens
John Spray

04/11/2016

09:34 PM Feature #11950: Strays enqueued for purge cause MDCache to exceed size limit
Possibly. I'm concerned about exposing slow deletes to users via Manila, but it may be the best we can do in the shor... Greg Farnum
06:39 PM Feature #11950: Strays enqueued for purge cause MDCache to exceed size limit
Yep, this should be a fairly high priority to do something about.
The "real" solution (a scalable way of persistin...
John Spray
05:26 PM Feature #11950: Strays enqueued for purge cause MDCache to exceed size limit
This came up in #15379. I think we're going to start seeing it more often with the Manila use case... Greg Farnum
02:45 PM Bug #15402 (Fix Under Review): Failure in TestMultiFilesystems.test_standby_for_fscid
https://github.com/ceph/ceph/pull/8536 Zheng Yan
12:39 PM Bug #15402: Failure in TestMultiFilesystems.test_standby_for_fscid
Did you assign this because you had an idea about it? Otherwise I'm also happy to work on it John Spray
11:01 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
When doing a number of deletes greater than the MDS cache size, you need to make sure that the MDS is purging faster ... John Spray
08:37 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
I did this on friday, I wait to let the mds delete until the evening. I did restart it friday evening, and saturday ... Kenneth Waegeman
08:27 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Can you start the MDS without resuming rm? If mds can start, please wait a few hours, to make MDS delete enough stra... Zheng Yan
07:18 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Still not able to resume the rm normally.. Even with the added RAM (now 64+32 GB), this is not enough for the MDS.
...
Kenneth Waegeman
08:42 AM Bug #15449 (Can't reproduce): [ceph-mds] mds service can not start after shutdown in 10.1.0
Hi cephers,
I was testing CephFS's HA. So I shutdown the active mds server.
Then the one of standby mds turn to b...
Desmond Shih
07:49 AM Support #15268: CephFS mount blocks VM
Sorry for the delay. This seems like duplicate of http://tracker.ceph.com/issues/15302 Zheng Yan

04/08/2016

01:07 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Adding a swapfile of 32GB did make it work.. for now.
Thanks!!
Our mds daemon is running, but now using 73G of ...
Kenneth Waegeman

04/07/2016

06:03 PM Bug #15402: Failure in TestMultiFilesystems.test_standby_for_fscid
/a/sage-2016-04-07_08:34:50-fs-wip-sage-testing---basic-smithi/114003 Sage Weil
04:02 PM Feature #15417 (Resolved): Make path prefix ("/volumes") in CephFSVolumeClient configurable
This would be a convenient way to enable e.g. multiple Manila driver instances ("backends") to use different data poo... John Spray
03:04 PM Feature #15400 (Fix Under Review): CephFSVolumeClient should isolate volumes by RADOS namespace
https://github.com/ceph/ceph/pull/8474/files John Spray
10:33 AM Bug #15304 (Resolved): qa: samba tests need to run on testing kernel
John Spray
08:21 AM Bug #15304 (Fix Under Review): qa: samba tests need to run on testing kernel
https://github.com/ceph/ceph-qa-suite/pull/938 Zheng Yan
08:46 AM Bug #15309 (Resolved): Error: Creation of multiple filesystems is disabled. To enable this exper...
Zheng Yan
07:02 AM Bug #15399: MDS incarnation get lost after remove filesystem
I think using the MDSMap epoch as the incarnation is good idea Zheng Yan
01:17 AM Bug #15387 (Resolved): legacy pool 0 might actually mean pool 0.
Zheng Yan

04/06/2016

04:53 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Ah, so this is basically http://tracker.ceph.com/issues/11950
The MDS doesn't limit how many stray files (waiting ...
John Spray
03:35 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
... Kenneth Waegeman
09:22 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
you can enable coredump by following commands
#ulimit -c unlimited
#ceph-mds -f -i a -c /etc/ceph/ceph.conf
A...
Zheng Yan
07:33 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Thanks, I uploaded the file:
ceph-post-file: 99c6e33a-7e54-472f-847b-68400954bbe4
I don't see any coredumps.
Kenneth Waegeman
02:59 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
are there coredump files? If there are, run gdb ceph-mds core.xxx. It will give us exact location of crash. Zheng Yan
02:54 PM Feature #15406 (Resolved): Add versioning to CephFSVolumeClient interface

As we add features and change things in CephFSVolumeClient, we will need to add a mechanism for users of the module...
John Spray
02:51 PM Bug #15399: MDS incarnation get lost after remove filesystem
We only do objecter->set_client_incarnation(incarnation); in MDSRank::init (after we've been assigned an active role)... John Spray
02:12 PM Bug #15399: MDS incarnation get lost after remove filesystem
So we could probably reset our network connections with an incarnation based on the last MDSMap where our role change... Greg Farnum
02:09 PM Bug #15399: MDS incarnation get lost after remove filesystem
If:
* MDSes A and B come up during the same epoch
* A becomes active and B becomes standby
* A fails
* B starts r...
Greg Farnum
10:56 AM Bug #15399: MDS incarnation get lost after remove filesystem
Here's a reproducer for the incarnation issue:
https://github.com/ceph/ceph-qa-suite/tree/wip-15399
I note that w...
John Spray
09:12 AM Bug #15399 (Resolved): MDS incarnation get lost after remove filesystem
If we remove a filesystem, then create new filesystem with old data/metadata pools. OSD may drop requests from MDS of... Zheng Yan
01:15 PM Bug #15402 (Resolved): Failure in TestMultiFilesystems.test_standby_for_fscid
... John Spray
09:24 AM Feature #15400 (Resolved): CephFSVolumeClient should isolate volumes by RADOS namespace

i.e. use the new RADOS namespace layouts for the volume's dir, and then limit the client caps to that namespace.
John Spray
09:23 AM Cleanup #12191 (In Progress): Remove ceph-mds --journal-check aka ONESHOT_REPLAY
John Spray
08:40 AM Bug #15387 (Fix Under Review): legacy pool 0 might actually mean pool 0.
https://github.com/ceph/ceph/pull/8466 Zheng Yan

04/05/2016

09:15 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
We were having some temporary infrastructure issues, can you try again? :) Greg Farnum
02:41 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Hmm, I tried this, but I can't upload it : (I added verbose output)
sftp> mkdir post/780bd87b-b262-46a3-90a9-98f68...
Kenneth Waegeman
01:58 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
It's probably best to include the whole file and upload with ceph-post-file. :) Greg Farnum
01:26 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
with debug 20 Kenneth Waegeman
12:56 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Always get Request Entity Too Large, even for one MB.. is there other way to include this ?
It works with the last ...
Kenneth Waegeman
12:53 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Did not succeed. Tried with last 100000 lines Kenneth Waegeman
12:51 PM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
I ran it with debug 10, total file after crash was 10G. I kept the last 1 million lines, I hope i'm able to add it
Kenneth Waegeman
11:41 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Hmm, you're getting heartbeatmap warnings which indicate that something in the MDS is blocking for much longer than i... John Spray
11:20 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Added the whole log file of the original crash Kenneth Waegeman
11:11 AM Bug #15379: ceph mds continiously crashes and going into laggy state (stray purging problems)
Further up the log (before the minus-prefixed line numbers) there should be info from the actual failed assertion John Spray
08:12 AM Bug #15379 (Closed): ceph mds continiously crashes and going into laggy state (stray purging prob...
We are removing a very large directory from cephFS on infernalis 9.2.1, and after a while, an MDS was in laggy state ... Kenneth Waegeman
08:15 PM Feature #15393: ceph-fuse: Request for logrotate for client side log files
This is a little weird since ceph-fuse doesn't have a service controlling it, which I think is how we normally plug t... Greg Farnum
06:35 PM Feature #15393 (Resolved): ceph-fuse: Request for logrotate for client side log files
While running cephfs with fuse, I needed to enable debug mode on the client. I quickly discovered its quite easy to ... Barry Marson
05:53 PM Bug #15266 (Fix Under Review): ceph_volume_client purge failing on non-ascii filenames
https://github.com/ceph/ceph/pull/8452
https://github.com/ceph/ceph-qa-suite/pull/934
John Spray
03:35 PM Bug #15387 (Resolved): legacy pool 0 might actually mean pool 0.
https://github.com/ceph/ceph/blob/master/src/common/fs_types.cc#L63
This is the case for old clusters, where teh p...
Sage Weil
07:21 AM Bug #15378 (Rejected): ceph_volume_client: hasty removal of OSD caps during deauthorization
When deauthorizing access of a Ceph user to a volume (a CephFS directory),
the volume client removes OSD caps that a...
Ramana Raja
02:05 AM Bug #13980 (Resolved): all nfs v3 mounts fail in ovh lab
Zheng Yan

04/04/2016

10:08 PM Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
Hi Greg,
i can confirm, that restarting the mds will solve the issue. Thank you very much for that advice !
If...
Oliver Dzombc
05:18 PM Bug #14818 (Resolved): Cython librados broke libcephfs/ceph_volume_client
This got fixed when cephfs.py was converted to cython John Spray

04/01/2016

09:02 PM Bug #15270: "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
Run: http://pulpito.ceph.com/teuthology-2016-04-01_08:43:11-smoke-master-distro-basic-mira/
Jobs: ['101644', '101645']
Yuri Weinstein
08:08 PM Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
That's probably a result of using older kernel clients in your case, Oliver. There's no max file size/count which wil... Greg Farnum
05:14 PM Bug #10944: Deadlock, MDS logs "slow request", getattr pAsLsXsFs failed to rdlock
Hi,
same here:
with clients:
3.10.0-327.10.1.el7.x86_64 = centos 7
3.19.0-25-generic #26~14.04.1-Ubuntu SM...
Oliver Dzombc

03/31/2016

02:53 PM Bug #15045 (In Progress): CephFSVolumeClient.evict should be limited by path, not just auth ID
Nathan Cutler
02:27 PM Bug #13876 (Resolved): qa: openstack MPI connection failures
The firewall on the OVH lab was configured manually. The code that is quoted is only used when dynamically provisioni... Loïc Dachary
02:18 PM Bug #13980 (Fix Under Review): all nfs v3 mounts fail in ovh lab
https://github.com/ceph/teuthology/pull/834 Loïc Dachary
10:29 AM Bug #15309 (Fix Under Review): Error: Creation of multiple filesystems is disabled. To enable th...
https://github.com/ceph/ceph/pull/8393 John Spray
05:16 AM Bug #15309: Error: Creation of multiple filesystems is disabled. To enable this experimental fea...
first bit passes, but now it fails a bit further on:
2016-03-30T15:06:45.122 INFO:tasks.workunit.client.0.smithi04...
Sage Weil

03/30/2016

11:54 PM Feature #15264: libcephfs: enable non-"ll" users to set their uid/gid
Hmm, is setting config options really the interface we want for it? It's easy enough for the moment but I'm not sure ... Greg Farnum
12:11 PM Feature #15264 (Rejected): libcephfs: enable non-"ll" users to set their uid/gid
Oh, never mind, I was looking in the libcephfs API (where you can't set it), but not in the config opts (where you ca... John Spray
06:18 PM Bug #15309: Error: Creation of multiple filesystems is disabled. To enable this experimental fea...
Greg Farnum
10:45 AM Bug #15309 (Fix Under Review): Error: Creation of multiple filesystems is disabled. To enable th...
https://github.com/ceph/ceph/pull/8372 John Spray
01:31 PM Bug #15266 (In Progress): ceph_volume_client purge failing on non-ascii filenames
John Spray
01:10 PM Bug #15045: CephFSVolumeClient.evict should be limited by path, not just auth ID
I am working on this issue. Ramana Raja

03/29/2016

05:35 PM Bug #15309: Error: Creation of multiple filesystems is disabled. To enable this experimental fea...
Could be failing because default pool names changed, so this looks like a "create second" rather than "it already exi... John Spray
05:17 PM Bug #15309 (Resolved): Error: Creation of multiple filesystems is disabled. To enable this exper...
2016-03-28T14:22:24.439 INFO:tasks.rest_api.client.rest0.smithi037.stderr:127.0.0.1 - - [28/Mar/2016 21:22:24] "PUT /... Samuel Just
01:59 PM Bug #15303 (Fix Under Review): Client holds incorrect complete flag on dir after losing caps
https://github.com/ceph/ceph/pull/8353 Zheng Yan
01:33 PM Bug #15303 (In Progress): Client holds incorrect complete flag on dir after losing caps
Client::handle_cap_grant() pass wrong parameter to Client::check_cap_issue() Zheng Yan
01:29 PM Bug #15303: Client holds incorrect complete flag on dir after losing caps
Reproducer is https://github.com/ceph/ceph-qa-suite/pull/917 John Spray
11:07 AM Bug #15303 (Resolved): Client holds incorrect complete flag on dir after losing caps

We saw this from testing Manila. The symptom is that the Manila driver gets ENOTEMPTY when trying to remove a shar...
John Spray
01:50 PM Bug #15304 (Resolved): qa: samba tests need to run on testing kernel
I think some of our "random" samba failures are not so random. It looks like we no longer pass on any of our kclient ... Greg Farnum
12:51 PM Bug #15270: "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
the test use 3.13 kernel, maybe the failure was caused by unsupported feature. Zheng Yan
08:33 AM Support #15268: CephFS mount blocks VM
Zheng Yan wrote:
> grab_super+0x2e is down_write(&s->s_umount). the backtrace show there is already a mounted cephfs...
Joao Castro
02:43 AM Support #15268: CephFS mount blocks VM
grab_super+0x2e is down_write(&s->s_umount). the backtrace show there is already a mounted cephfs, you tried mounting... Zheng Yan

03/28/2016

08:48 PM Bug #14805 (Resolved): Hadoop tests failing with EPERM
Greg Farnum
01:54 PM Support #15268: CephFS mount blocks VM
Joao Castro wrote:
> Trying to mount it on a EC2 machine
>
> Mar 27 10:37:25 ip-172-31-5-103 kernel: [ 1320.75613...
Joao Castro

03/27/2016

10:41 AM Support #15268: CephFS mount blocks VM
Trying to mount it on a EC2 machine
Mar 27 10:37:25 ip-172-31-5-103 kernel: [ 1320.756137] INFO: task mount.ceph:1...
Joao Castro

03/25/2016

08:20 AM Backport #15281 (Rejected): infernalis: standy-replay MDS does not cleanup finished replay threads
Nathan Cutler
01:02 AM Feature #15065 (Resolved): multifs: add standby_for_fscid setting on MDS and pass in MMDSBeacon
Greg Farnum
12:57 AM Feature #15063 (Resolved): multifs: option to disable sanity() calls
Greg Farnum
12:57 AM Feature #15063: multifs: option to disable sanity() calls
commit:b296629f1ace2b2c394e9303b17e952fabb06696, merged in f474c23d7c619fe014bd4cf42cab12802f1e4e2c Greg Farnum
12:57 AM Fix #15062 (Resolved): multifs cleanup: pass feature bits into MDSMap from Filesystem::encode
commit:68398258e152803cf9166a5bc3c0b1e153062d1e, merged in f474c23d7c619fe014bd4cf42cab12802f1e4e2c Greg Farnum
12:45 AM Bug #15167 (Resolved): CID 1355575: null CDir* can get pushed on ScrubStack?
Greg Farnum
12:44 AM Bug #15210 (Rejected): qa: snaptests-0.sh: file exists error after deleting+reusing name
I thought each of these was running in their own subdirectory, but if that's not the case then this is expected behav... Greg Farnum

03/24/2016

11:44 PM Support #15268: CephFS mount blocks VM
Hmm, if it were newer features in userspace than in the kernel you should be getting errors. Zheng, any idea? Greg Farnum
11:42 PM Support #15268: CephFS mount blocks VM
Joao Castro wrote:
> Greg Farnum wrote:
> > You'll need to provide a little more context. You're just trying to mou...
Joao Castro
11:41 PM Support #15268: CephFS mount blocks VM
Greg Farnum wrote:
> You'll need to provide a little more context. You're just trying to mount CephFS inside of a VM...
Joao Castro
10:33 PM Support #15268: CephFS mount blocks VM
You'll need to provide a little more context. You're just trying to mount CephFS inside of a VM, and the mount is han... Greg Farnum
03:47 PM Support #15268 (Resolved): CephFS mount blocks VM
cat /proc/modules | grep -i ceph
ceph 315392 0 - Live 0xffffffffc0460000
libceph 241664 1 ceph, Live 0xffffffffc041...
Joao Castro
10:59 PM Bug #15235: MDS : erroneous error message about reading config file
Ok I didn't know it could be related. No problem in this case :) Florent B
10:52 PM Bug #15235 (Fix Under Review): MDS : erroneous error message about reading config file
Greg Farnum
10:51 PM Bug #15235: MDS : erroneous error message about reading config file
Oh. I gather you're running into #14144, given https://github.com/ceph/ceph/pull/7060#issuecomment-200745759. The "un... Greg Farnum
10:36 PM Bug #15235: MDS : erroneous error message about reading config file
Yes I know, but is ends like this... :( Florent B
10:26 PM Bug #15235: MDS : erroneous error message about reading config file
That paste doesn't contain an error of any kind in it. :) It seems to end with the respawn command getting invoked, b... Greg Farnum
09:06 AM Bug #15235: MDS : erroneous error message about reading config file
It should respawn itself, but fails on reading configuration file. But as you can see in strace, it does not *try* to... Florent B
12:17 AM Bug #15235: MDS : erroneous error message about reading config file
If you're failing an MDS from the monitor it's respawning itself, so maybe something weird happened there. Or maybe i... Greg Farnum
10:27 PM Bug #14805: Hadoop tests failing with EPERM
d'oh, right. Okay, I get the problem now. I've run this through a couple of times in my latest integration branch, bt... Greg Farnum
12:09 PM Bug #14805: Hadoop tests failing with EPERM
Greg Farnum wrote:
> Wait, can you expand on that John? I wasn't really looking at the python tests, although I know...
John Spray
01:04 AM Bug #14805: Hadoop tests failing with EPERM
Wait, can you expand on that John? I wasn't really looking at the python tests, although I know it involved root owne... Greg Farnum
10:20 PM Bug #14144 (Pending Backport): standy-replay MDS does not cleanup finished replay threads
Greg Farnum
04:47 PM Bug #15270 (Resolved): "mount error 5 = Input/output error" in smoke-master-distro-basic-openstack
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2016-03-24_05:00:02-smoke-master-distro-basic-openstack/
Jobs...
Yuri Weinstein
03:04 PM Bug #15266 (Resolved): ceph_volume_client purge failing on non-ascii filenames
... John Spray
01:59 PM Feature #15264 (Rejected): libcephfs: enable non-"ll" users to set their uid/gid
Currently libcephfs mostly doesn't pass through a uid/gid to Client, and Client defaults to reading the uid/gid of th... John Spray
12:18 AM Bug #15008 (Resolved): fuse expects root inode number to be FUSE_ROOT_ID
Greg Farnum
 

Also available in: Atom