Project

General

Profile

Activity

From 11/20/2018 to 12/19/2018

12/19/2018

12:17 AM Bug #37543 (Fix Under Review): mds: purge queue recovery hangs during boot if PQ journal is damaged
Patrick Donnelly

12/18/2018

11:11 AM Backport #37700 (Resolved): luminous: fuse client can't read file due to can't acquire Fr
https://github.com/ceph/ceph/pull/25677 Nathan Cutler
11:11 AM Backport #37699 (Resolved): mimic: fuse client can't read file due to can't acquire Fr
https://github.com/ceph/ceph/pull/25676 Nathan Cutler
11:10 AM Backport #37696 (Rejected): luminous: client: fix failure in quota size limitation when using samba
Nathan Cutler
11:10 AM Backport #37695 (Resolved): mimic: client: fix failure in quota size limitation when using samba
https://github.com/ceph/ceph/pull/25678 Nathan Cutler
04:18 AM Bug #37547 (Pending Backport): client: fix failure in quota size limitation when using samba
Patrick Donnelly
04:17 AM Bug #37333 (Pending Backport): fuse client can't read file due to can't acquire Fr
Patrick Donnelly
04:10 AM Bug #37681 (Resolved): qa: power off still resulted in client sending session close
... Patrick Donnelly

12/17/2018

10:34 PM Feature #37678 (Fix Under Review): mds: log new client sessions with various metadata
Patrick Donnelly
10:27 PM Feature #37678 (Resolved): mds: log new client sessions with various metadata
Including time to create/journal the new session, any throttling on the new session message, mount point, and client ... Patrick Donnelly
04:35 PM Cleanup #37674 (Fix Under Review): mds: create separate config for heartbeat timeout
Patrick Donnelly
04:30 PM Cleanup #37674 (Resolved): mds: create separate config for heartbeat timeout
Currently the MDS uses the mds_beacon_grace for the heartbeat timeout. If we need to increase the beacon grace becaus... Patrick Donnelly
02:52 PM Bug #37670 (Fix Under Review): standby-replay MDS spews message to log every second
Patrick Donnelly
02:40 PM Bug #37670 (Resolved): standby-replay MDS spews message to log every second
I used the mgr volumes module on my rook cluster to create a new cephfs. The orchestrator started up 2 MDS':... Jeff Layton
02:37 PM Bug #37547 (Fix Under Review): client: fix failure in quota size limitation when using samba
Patrick Donnelly
04:13 AM Backport #37608: luminous: MDS admin socket command `dump cache` with a very large cache will han...
Patrick Donnelly wrote:
> Venky Shankar wrote:
> > btw, cannot see the `Pull request ID` section to update the PR i...
Venky Shankar

12/14/2018

07:32 PM Backport #24929 (In Progress): luminous: qa: test_recovery_pool tries asok on wrong node
Patrick Donnelly
07:12 PM Bug #37617: CephFS did not recover re-plugging network cable
Patrick Donnelly wrote:
> We do not have a tracker yet. Work is planned in the near future on this and we'll create ...
Niklas Hambuechen
05:26 PM Backport #37608: luminous: MDS admin socket command `dump cache` with a very large cache will han...
Venky Shankar wrote:
> btw, cannot see the `Pull request ID` section to update the PR id...
Backports still follo...
Patrick Donnelly
04:53 PM Backport #37608: luminous: MDS admin socket command `dump cache` with a very large cache will han...
btw, cannot see the `Pull request ID` section to update the PR id... Venky Shankar
10:36 AM Backport #37608 (Need More Info): luminous: MDS admin socket command `dump cache` with a very lar...
Nathan Cutler
10:21 AM Backport #37608 (In Progress): luminous: MDS admin socket command `dump cache` with a very large ...
Nathan Cutler
10:37 AM Backport #37609 (Need More Info): mimic: MDS admin socket command `dump cache` with a very large ...
Nathan Cutler
10:18 AM Backport #37609 (In Progress): mimic: MDS admin socket command `dump cache` with a very large cac...
Nathan Cutler
10:26 AM Backport #37629 (In Progress): luminous: mds: do not call Journaler::_trim twice
Nathan Cutler
10:25 AM Backport #37628 (In Progress): mimic: mds: do not call Journaler::_trim twice
Nathan Cutler
10:24 AM Backport #37627 (In Progress): luminous: mds: fix incorrect l_pq_executing_ops statistics when me...
Nathan Cutler
10:24 AM Backport #37626 (In Progress): mimic: mds: fix incorrect l_pq_executing_ops statistics when meet ...
Nathan Cutler
10:23 AM Backport #37610 (In Progress): luminous: qa: pjd test appears to require more than 3h timeout for...
Nathan Cutler
10:22 AM Backport #37611 (In Progress): mimic: qa: pjd test appears to require more than 3h timeout for so...
Nathan Cutler

12/13/2018

11:31 PM Bug #37617: CephFS did not recover re-plugging network cable
Niklas Hambuechen wrote:
> Hey Patrick,
>
> > Currently, it is necessary to restart the client when this happens....
Patrick Donnelly
11:22 PM Bug #37617: CephFS did not recover re-plugging network cable
Hey Patrick,
> Currently, it is necessary to restart the client when this happens.
Is there already a feature r...
Niklas Hambuechen
05:26 PM Bug #37617 (Rejected): CephFS did not recover re-plugging network cable
> I would expect Ceph to recover automatically from this short 11-minute network interruption.
Ceph will recover b...
Patrick Donnelly
11:29 PM Feature #9755 (Resolved): Fence late clients during reconnect timeout
This has been corrected but this issue was never closed. Patrick Donnelly
01:35 PM Bug #37644 (Fix Under Review): extend reconnect period when mds is busy
Zheng Yan
01:25 PM Bug #37644 (Resolved): extend reconnect period when mds is busy
Zheng Yan
03:59 AM Bug #21754 (Rejected): mds: src/osdc/Journaler.cc: 402: FAILED assert(!r)
Seems this no longer happens anymore. Patrick Donnelly
01:17 AM Backport #37481: luminous: mds: MDCache.cc: 11673: abort()
this one too please Patrick Donnelly
01:16 AM Backport #37480: mimic: mds: MDCache.cc: 11673: abort()
Zheng, please handle this. Patrick Donnelly
01:01 AM Bug #37639 (Fix Under Review): mds: output client IP of blacklisted/evicted clients to cluster log
Patrick Donnelly

12/12/2018

11:23 PM Bug #37639 (Resolved): mds: output client IP of blacklisted/evicted clients to cluster log
If the MDS evicts a misbehaving client, send a cluster INFO notice so the operator can take action or look for patter... Patrick Donnelly
10:34 PM Backport #37604 (In Progress): luminous: mds: PurgeQueue write error handler does not handle EBLA...
Nathan Cutler
10:33 PM Backport #37605 (In Progress): mimic: mds: PurgeQueue write error handler does not handle EBLACKL...
Nathan Cutler
09:52 PM Bug #36669 (Rejected): client: displayed as the capacity of all OSDs when there are multiple data...
See PR discussion. Patrick Donnelly
09:46 PM Backport #37637 (Rejected): luminous: client: support getfattr ceph.dir.pin extended attribute
Nathan Cutler
09:46 PM Backport #37636 (Rejected): mimic: client: support getfattr ceph.dir.pin extended attribute
Nathan Cutler
09:45 PM Backport #37635 (Resolved): luminous: race of updating wanted caps
https://github.com/ceph/ceph/pull/25762 Nathan Cutler
09:45 PM Backport #37634 (Resolved): mimic: race of updating wanted caps
https://github.com/ceph/ceph/pull/25680 Nathan Cutler
09:45 PM Backport #37633 (Resolved): luminous: mds: remove duplicated l_mdc_num_strays perfcounter set
https://github.com/ceph/ceph/pull/25682 Nathan Cutler
09:45 PM Backport #37632 (Resolved): mimic: mds: remove duplicated l_mdc_num_strays perfcounter set
https://github.com/ceph/ceph/pull/25681 Nathan Cutler
09:44 PM Backport #37631 (Resolved): luminous: client: do not move f->pos untill success write
https://github.com/ceph/ceph/pull/25684 Nathan Cutler
09:44 PM Backport #37630 (Resolved): mimic: client: do not move f->pos untill success write
https://github.com/ceph/ceph/pull/25683 Nathan Cutler
09:44 PM Backport #37629 (Resolved): luminous: mds: do not call Journaler::_trim twice
https://github.com/ceph/ceph/pull/25562 Nathan Cutler
09:44 PM Backport #37628 (Resolved): mimic: mds: do not call Journaler::_trim twice
https://github.com/ceph/ceph/pull/25561 Nathan Cutler
09:44 PM Backport #37627 (Resolved): luminous: mds: fix incorrect l_pq_executing_ops statistics when meet ...
https://github.com/ceph/ceph/pull/25560 Nathan Cutler
09:44 PM Backport #37626 (Resolved): mimic: mds: fix incorrect l_pq_executing_ops statistics when meet an ...
https://github.com/ceph/ceph/pull/25559 Nathan Cutler
09:41 PM Backport #37606 (In Progress): luminous: mds: directories pinned keep being replicated back and f...
Nathan Cutler
09:40 PM Backport #37607 (In Progress): mimic: mds: directories pinned keep being replicated back and fort...
Nathan Cutler
09:25 PM Backport #37602 (In Progress): luminous: mds: severe internal fragment when decoding xattr_map fr...
Nathan Cutler
09:24 PM Backport #37603 (In Progress): mimic: mds: severe internal fragment when decoding xattr_map from ...
Nathan Cutler
09:21 PM Backport #37481 (Need More Info): luminous: mds: MDCache.cc: 11673: abort()
Patrick, this looks to me like a non-trivial backport because of extensive changes to src/mds/MDCache.cc that were ma... Nathan Cutler
09:20 PM Backport #37480 (Need More Info): mimic: mds: MDCache.cc: 11673: abort()
Patrick, this looks to me like a non-trivial backport because of extensive changes to src/mds/MDCache.cc that were ma... Nathan Cutler
09:07 PM Backport #37423 (In Progress): luminous: qa: wrong setting for msgr failures
Nathan Cutler
09:06 PM Backport #37424 (In Progress): mimic: qa: wrong setting for msgr failures
Nathan Cutler
08:48 PM Bug #37566 (Pending Backport): mds: do not call Journaler::_trim twice
Patrick Donnelly
08:47 PM Bug #37567 (Pending Backport): mds: fix incorrect l_pq_executing_ops statistics when meet an inva...
Patrick Donnelly
08:46 PM Backport #37623 (In Progress): luminous: qa: client socket inaccessible without sudo
Nathan Cutler
08:46 PM Backport #37623 (Resolved): luminous: qa: client socket inaccessible without sudo
https://github.com/ceph/ceph/pull/25516 Nathan Cutler
08:46 PM Bug #24872 (Pending Backport): qa: client socket inaccessible without sudo
Nathan Cutler
08:45 PM Bug #37546 (Pending Backport): client: do not move f->pos untill success write
Patrick Donnelly
08:44 PM Bug #37368: mds: directories pinned keep being replicated back and forth between exporting mds an...
Not sure why I marked this Pending Backport but I've now merged the PR into master. Patrick Donnelly
08:44 PM Backport #36577 (In Progress): luminous: qa: teuthology may hang on diagnostic commands for fuse ...
Nathan Cutler
08:42 PM Bug #37464 (Pending Backport): race of updating wanted caps
Patrick Donnelly
08:41 PM Bug #37516 (Pending Backport): mds: remove duplicated l_mdc_num_strays perfcounter set
Patrick Donnelly
08:38 PM Backport #36578 (In Progress): mimic: qa: teuthology may hang on diagnostic commands for fuse mount
Nathan Cutler
08:32 PM Bug #26969: kclient: mount unexpectedly gets osdmap updates causing test to fail
Another: /ceph/teuthology-archive/pdonnell-2018-12-10_21:45:37-kcephfs-wip-pdonnell-testing-20181210.180934-distro-ba... Patrick Donnelly
12:52 AM Bug #37617: CephFS did not recover re-plugging network cable
The OSD logs around time `Dec 11 03:25:49` (the "I was blacklisted" time):... Niklas Hambuechen
12:44 AM Bug #37617 (Resolved): CephFS did not recover re-plugging network cable
Today my hardware hoster had a planned switch maintenance during which the switch one of my 3 ceph nodes was connecte... Niklas Hambuechen

12/11/2018

04:01 PM Backport #37611 (Resolved): mimic: qa: pjd test appears to require more than 3h timeout for some ...
https://github.com/ceph/ceph/pull/25557 Nathan Cutler
04:01 PM Backport #37610 (Resolved): luminous: qa: pjd test appears to require more than 3h timeout for so...
https://github.com/ceph/ceph/pull/25558 Nathan Cutler
04:00 PM Backport #37609 (Resolved): mimic: MDS admin socket command `dump cache` with a very large cache ...
https://github.com/ceph/ceph/pull/25642 Nathan Cutler
04:00 PM Backport #37608 (Resolved): luminous: MDS admin socket command `dump cache` with a very large cac...
https://github.com/ceph/ceph/pull/25567 Nathan Cutler
04:00 PM Backport #37607 (Resolved): mimic: mds: directories pinned keep being replicated back and forth b...
https://github.com/ceph/ceph/pull/25521 Nathan Cutler
04:00 PM Backport #37606 (Resolved): luminous: mds: directories pinned keep being replicated back and fort...
https://github.com/ceph/ceph/pull/25522 Nathan Cutler
04:00 PM Backport #37605 (Resolved): mimic: mds: PurgeQueue write error handler does not handle EBLACKLISTED
https://github.com/ceph/ceph/pull/25523 Nathan Cutler
04:00 PM Backport #37604 (Resolved): luminous: mds: PurgeQueue write error handler does not handle EBLACKL...
https://github.com/ceph/ceph/pull/25524 Nathan Cutler
03:59 PM Backport #37603 (Resolved): mimic: mds: severe internal fragment when decoding xattr_map from log...
https://github.com/ceph/ceph/pull/25519 Nathan Cutler
03:59 PM Backport #37602 (Resolved): luminous: mds: severe internal fragment when decoding xattr_map from ...
https://github.com/ceph/ceph/pull/25520 Nathan Cutler
12:20 PM Bug #37594 (Resolved): mds: mds state change race
In multi-mds cluster, recovering mds may receive mdsmap that changes
its state after other mds. Furthermore, the rec...
Zheng Yan
01:56 AM Bug #36189 (Fix Under Review): ceph-fuse client can't read or write due to backward cap_gen
Zheng Yan

12/10/2018

10:27 PM Backport #37426 (In Progress): mimic: ceph-volume-client: cannot set mode for cephfs volumes as r...
Patrick Donnelly
06:06 PM Bug #37546 (Fix Under Review): client: do not move f->pos untill success write
Patrick Donnelly
06:04 PM Bug #37566 (Fix Under Review): mds: do not call Journaler::_trim twice
Patrick Donnelly
06:02 PM Bug #37567 (Fix Under Review): mds: fix incorrect l_pq_executing_ops statistics when meet an inva...
Patrick Donnelly
04:43 PM Bug #37355 (Duplicate): tasks.cephfs.test_volume_client fails with "ImportError: No module named ...
#24919 needs backported. Patrick Donnelly
02:48 PM Feature #37523: NFS-Ganesha: Add support to set quota from nfs mount point
I assume you're looking to just expose the xattrs to the client via xattr support detailed in RFC8276? Jeff Layton
02:41 PM Feature #37523: NFS-Ganesha: Add support to set quota from nfs mount point
Supriti, is this something you wanted to work on? Patrick Donnelly
02:28 PM Support #37407 (Rejected): ceph-fuse setfattr fail
This type of question is more appropriate for the ceph-users mailing list. Please repost your question there. Patrick Donnelly

12/08/2018

05:09 AM Bug #37516 (Fix Under Review): mds: remove duplicated l_mdc_num_strays perfcounter set
Patrick Donnelly

12/07/2018

07:00 PM Bug #37368 (Pending Backport): mds: directories pinned keep being replicated back and forth betwe...
Patrick Donnelly
06:58 PM Bug #37399 (Pending Backport): mds: severe internal fragment when decoding xattr_map from log event
Patrick Donnelly
06:56 PM Bug #37394 (Pending Backport): mds: PurgeQueue write error handler does not handle EBLACKLISTED
Patrick Donnelly
06:55 PM Bug #36703 (Pending Backport): MDS admin socket command `dump cache` with a very large cache will...
Patrick Donnelly
06:53 PM Feature #36707 (Pending Backport): client: support getfattr ceph.dir.pin extended attribute
Patrick Donnelly
06:49 PM Bug #36594 (Pending Backport): qa: pjd test appears to require more than 3h timeout for some conf...
Patrick Donnelly
05:33 PM Bug #37544 (Duplicate): mds: reconnect of client during thrashing fails
Patrick Donnelly
11:22 AM Bug #37544: mds: reconnect of client during thrashing fails
... Zheng Yan
06:46 AM Bug #37544 (Duplicate): mds: reconnect of client during thrashing fails
... Patrick Donnelly
09:14 AM Bug #37567 (Resolved): mds: fix incorrect l_pq_executing_ops statistics when meet an invalid item...
l_pq_executing_ops should subtract the ops we added previous
in the condition we meet an invalid item in the purge q...
tang junhui
09:09 AM Bug #37566 (Resolved): mds: do not call Journaler::_trim twice
Journaler::_trim is called in the routine:
PurgeQueue::_execute_item
==>Journaler::write_head
==>Journaler::_finis...
tang junhui
08:41 AM Bug #37547 (Resolved): client: fix failure in quota size limitation when using samba
In samba, Client::_write may be called with the offset a
negative number, and use the f->pos as the real write offse...
tang junhui
08:36 AM Bug #37546 (Resolved): client: do not move f->pos untill success write
writes maybe failed in Client::_write, so do not move f->pos when write
successfully.
tang junhui
06:16 AM Bug #37543 (Resolved): mds: purge queue recovery hangs during boot if PQ journal is damaged
... Patrick Donnelly

12/06/2018

09:18 PM Bug #37540 (Fix Under Review): luminous: MDSMap session timeout cannot be modified
Patrick Donnelly
08:49 PM Bug #37540 (Resolved): luminous: MDSMap session timeout cannot be modified
This was fixed in https://github.com/ceph/ceph/pull/19440/commits/67ca6cd229a595d54ccea18b5452f2574ede9657
The fix...
Patrick Donnelly

12/05/2018

11:25 AM Backport #37425 (In Progress): luminous: ceph-volume-client: cannot set mode for cephfs volumes a...
Nathan Cutler

12/04/2018

03:21 PM Feature #37523 (New): NFS-Ganesha: Add support to set quota from nfs mount point
Currently NFS-Ganesha enforces quota set from other cephfs client. But there is no way to set it from nfs mount point... supriti singh
06:51 AM Bug #37516 (Resolved): mds: remove duplicated l_mdc_num_strays perfcounter set
The l_mdc_num_strays perfcounter had been encapsulated into StrayManager notify_stray_created() and notify_stray_remo... Zhi Zhang

12/03/2018

12:20 PM Bug #37378: truncate_seq ordering issues with object creation
Greg Farnum wrote:
> And a PR is probably the best way to develop new code rather than diagnose the issue, yeah!
...
Luis Henriques
11:37 AM Bug #37378: truncate_seq ordering issues with object creation
Greg Farnum wrote:
> Luis Henriques wrote:
> > However, I'm attaching here a quick hack that, from the tests I've d...
Luis Henriques

11/30/2018

08:52 PM Bug #37378: truncate_seq ordering issues with object creation
And a PR is probably the best way to develop new code rather than diagnose the issue, yeah! Greg Farnum
08:52 PM Bug #37378: truncate_seq ordering issues with object creation
Luis Henriques wrote:
> However, I'm attaching here a quick hack that, from the tests I've done, fixes this issue on...
Greg Farnum
07:45 AM Bug #37464 (Fix Under Review): race of updating wanted caps
Zheng Yan
07:21 AM Backport #37481 (Resolved): luminous: mds: MDCache.cc: 11673: abort()
https://github.com/ceph/ceph/pull/25990 Nathan Cutler
07:21 AM Backport #37480 (Resolved): mimic: mds: MDCache.cc: 11673: abort()
https://github.com/ceph/ceph/pull/26252 Nathan Cutler
03:14 AM Backport #36503 (In Progress): mimic: qa: infinite timeout on asok command causes job to die
https://github.com/ceph/ceph/pull/25332 Prashant D

11/29/2018

06:54 PM Bug #37378: truncate_seq ordering issues with object creation
One thing I forgot to mention in my last comment is that we would also need a new CEPH_FEATURE_<something> to make su... Luis Henriques
02:22 PM Bug #37378: truncate_seq ordering issues with object creation
Zheng Yan wrote:
> yes, it's what I mean. besides, we should do the check after getting RW caps of src/dest inode
...
Luis Henriques
01:43 AM Bug #37378: truncate_seq ordering issues with object creation
yes, it's what I mean. besides, we should do the check after getting RW caps of src/dest inode Zheng Yan
07:39 AM Bug #37464 (Resolved): race of updating wanted caps
Zheng Yan
04:08 AM Bug #37399 (Fix Under Review): mds: severe internal fragment when decoding xattr_map from log event
Patrick Donnelly
03:55 AM Bug #36035 (Pending Backport): mds: MDCache.cc: 11673: abort()
Patrick Donnelly

11/28/2018

11:01 PM Bug #37378: truncate_seq ordering issues with object creation
Zheng Yan wrote:
> For now, I think we can add a check to kernel client, make sure src inode and dest inode's trunca...
Luis Henriques
02:41 PM Bug #37378: truncate_seq ordering issues with object creation
For now, I think we can add a check to kernel client, make sure src inode and dest inode's truncate seq are the same.... Zheng Yan
02:04 PM Bug #37378: truncate_seq ordering issues with object creation
Would it be acceptable to do something like adding an extra CEPH_OSD_COPY_FROM_FLAG_IGNORE_TRUNCATE_SEQ flag? The ke... Luis Henriques
12:24 PM Bug #37378: truncate_seq ordering issues with object creation
It seems that CEPH_OSD_OP_COPY_FROM is designed for cache tier, not suite for general use. The problem happen if src ... Zheng Yan
11:40 AM Bug #37378: truncate_seq ordering issues with object creation
Greg Farnum wrote:
> Oh hrm. That does make it more interesting.
>
> ...oh my. I bet that when you do a copy-from...
Luis Henriques

11/27/2018

10:40 PM Backport #36200 (In Progress): luminous: mds: fix mds damaged due to unexpected journal length
Patrick Donnelly
10:27 PM Backport #37426 (Resolved): mimic: ceph-volume-client: cannot set mode for cephfs volumes as requ...
https://github.com/ceph/ceph/pull/25413 Nathan Cutler
10:27 PM Backport #37425 (Resolved): luminous: ceph-volume-client: cannot set mode for cephfs volumes as r...
https://github.com/ceph/ceph/pull/25407 Nathan Cutler
10:27 PM Backport #37424 (Resolved): mimic: qa: wrong setting for msgr failures
https://github.com/ceph/ceph/pull/25517 Nathan Cutler
10:27 PM Backport #37423 (Resolved): luminous: qa: wrong setting for msgr failures
https://github.com/ceph/ceph/pull/25518 Nathan Cutler
10:16 PM Bug #36676 (Pending Backport): qa: wrong setting for msgr failures
Patrick Donnelly
09:55 PM Bug #36651 (Pending Backport): ceph-volume-client: cannot set mode for cephfs volumes as required...
Patrick Donnelly
08:55 PM Documentation #36180 (Resolved): doc: Typo error on cephfs/fuse/
Nathan Cutler
08:55 PM Backport #36309 (Resolved): luminous: doc: Typo error on cephfs/fuse/
Nathan Cutler
08:32 PM Documentation #36286 (Resolved): doc: fix broken fstab url in cephfs/fuse
Nathan Cutler
08:32 PM Backport #36312 (Resolved): luminous: doc: fix broken fstab url in cephfs/fuse
Nathan Cutler
07:02 PM Bug #37378: truncate_seq ordering issues with object creation
Oh hrm. That does make it more interesting.
...oh my. I bet that when you do a copy-from op on the OSD side, the t...
Greg Farnum
03:39 PM Bug #37378: truncate_seq ordering issues with object creation
Greg Farnum wrote:
> From what you're showing here, it looks like that patch is effectively just disabling the OSD's...
Luis Henriques
03:18 PM Bug #37378: truncate_seq ordering issues with object creation
From what you're showing here, it looks like that patch is effectively just disabling the OSD's truncate_seq check in... Greg Farnum
10:18 AM Bug #37378: truncate_seq ordering issues with object creation
Patrick Donnelly wrote:
> Moving to RADOS since the problem appears to be there.
Thanks, Patrick. In the meantim...
Luis Henriques
02:31 PM Support #37407 (Rejected): ceph-fuse setfattr fail
I want to use the quota of cephfs, And I mount the ceph by ceph-fuse as describe in the doc.However, when i exec "set... Licheng Zhu
08:30 AM Bug #37399: mds: severe internal fragment when decoding xattr_map from log event
Either https://github.com/ceph/ceph/pull/25264 or https://github.com/ceph/ceph/pull/25275 can resolve this issue. Aft... Zheng Yan
08:23 AM Bug #37399 (Resolved): mds: severe internal fragment when decoding xattr_map from log event
Zheng Yan
12:19 AM Bug #37394 (Fix Under Review): mds: PurgeQueue write error handler does not handle EBLACKLISTED
Patrick Donnelly

11/26/2018

11:28 PM Bug #37378: truncate_seq ordering issues with object creation
Moving to RADOS since the problem appears to be there. Patrick Donnelly
04:52 PM Bug #37378: truncate_seq ordering issues with object creation
Anyone more knowledgable with OSD code could please confirm if the following PrimaryLogPG::do_read() patch makes sens... Luis Henriques
10:54 PM Bug #37368 (Fix Under Review): mds: directories pinned keep being replicated back and forth betwe...
Patrick Donnelly
10:10 PM Bug #37394 (Resolved): mds: PurgeQueue write error handler does not handle EBLACKLISTED
It should have similar logic to MDSRank::handle_write_error.
As a result, if the PQ sees a write error due to bein...
Patrick Donnelly
05:38 PM Bug #37333 (Fix Under Review): fuse client can't read file due to can't acquire Fr
Greg Farnum
04:25 PM Bug #37355 (In Progress): tasks.cephfs.test_volume_client fails with "ImportError: No module name...
'ceph_argparse' module for py2.7 is in 'ceph-common' package. And for py3 the module is in 'python3-ceph-argparse' pa... Ramana Raja

11/23/2018

08:16 PM Bug #36189 (Need More Info): ceph-fuse client can't read or write due to backward cap_gen
Zheng writes: "If cap is invalid during reconnect, mds should consider issued caps is empty (just CEPH_CAP_PIN)"
a...
Nathan Cutler
08:14 PM Backport #36462 (Need More Info): luminous: ceph-fuse client can't read or write due to backward ...
First attempted backport, https://github.com/ceph/ceph/pull/25089, was closed because the master PR might have an iss... Nathan Cutler
08:14 PM Backport #36463 (Need More Info): mimic: ceph-fuse client can't read or write due to backward cap...
The first backport was https://github.com/ceph/ceph/pull/25091. The original master fix might have an issue, though, ... Nathan Cutler
05:36 PM Bug #37378: truncate_seq ordering issues with object creation
I don't fully understand the following code, but I suspect the issue could be related to truncate_seq in this OSD fun... Luis Henriques
11:33 AM Bug #37378: truncate_seq ordering issues with object creation
I forgot to mention that using the 'rados' command I'm able to see that the objects in the data pool actually seem to... Luis Henriques
10:17 AM Bug #37378 (Resolved): truncate_seq ordering issues with object creation
I'm seeing a bug with copy_file_range in recent clients. Here's a simple way to reproduce it:... Luis Henriques

11/22/2018

05:16 PM Backport #36690 (Resolved): mimic: client: request next osdmap for blacklisted client
Nathan Cutler
04:40 PM Backport #36690: mimic: client: request next osdmap for blacklisted client
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/24987
merged
Yuri Weinstein
05:15 PM Backport #36218 (Resolved): mimic: Some cephfs tool commands silently operate on only rank 0, eve...
Nathan Cutler
04:39 PM Backport #36218: mimic: Some cephfs tool commands silently operate on only rank 0, even if multip...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25036
merged
Yuri Weinstein
05:15 PM Backport #36461 (Resolved): mimic: mds: rctime not set on system inode (root) at startup
Nathan Cutler
04:38 PM Backport #36461: mimic: mds: rctime not set on system inode (root) at startup
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25042
merged
Yuri Weinstein
04:53 PM Backport #36463 (Resolved): mimic: ceph-fuse client can't read or write due to backward cap_gen
Jonathan Brielmaier
04:41 PM Backport #36463: mimic: ceph-fuse client can't read or write due to backward cap_gen
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25091
merged
Yuri Weinstein
04:53 PM Backport #36457 (Resolved): mimic: client: explicitly show blacklisted state via asok status command
Jonathan Brielmaier
04:39 PM Backport #36457: mimic: client: explicitly show blacklisted state via asok status command
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/24993
merged
Yuri Weinstein
04:53 PM Backport #37093 (Resolved): mimic: mds: "src/mds/MDLog.cc: 281: FAILED ceph_assert(!capped)" duri...
Jonathan Brielmaier
04:37 PM Backport #37093: mimic: mds: "src/mds/MDLog.cc: 281: FAILED ceph_assert(!capped)" during max_mds ...
Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/25095
merged
Yuri Weinstein
09:42 AM Bug #37368 (Resolved): mds: directories pinned keep being replicated back and forth between expor...
Recently, when developing the rstat propagation function, we found that when pinning some directory to a specific ran... Xuehan Xu

11/21/2018

06:26 PM Bug #37355: tasks.cephfs.test_volume_client fails with "ImportError: No module named 'ceph_argpar...
I believe this problem also exists in Luminous? Patrick Donnelly
01:12 PM Bug #37355 (Duplicate): tasks.cephfs.test_volume_client fails with "ImportError: No module named ...
seen here: http://qa-proxy.ceph.com/teuthology/yuriw-2018-11-20_16:46:36-fs-wip-yuri3-testing-2018-11-16-1727-mimic-d... Venky Shankar
06:13 PM Backport #36694 (Resolved): mimic: mds: cache drop command requires timeout argument when it is s...
Patrick Donnelly
06:13 PM Backport #36282 (Resolved): mimic: mds: add drop_cache command
Patrick Donnelly
12:52 PM Bug #24517: "Loading libcephfs-jni: Failure!" in fs suite
seen again here: http://qa-proxy.ceph.com/teuthology/yuriw-2018-11-20_16:46:36-fs-wip-yuri3-testing-2018-11-16-1727-m... Venky Shankar

11/20/2018

04:24 AM Bug #37333 (Resolved): fuse client can't read file due to can't acquire Fr
ceph version: jewel:10.2.2
logs:
client.log...
Ivan Guan
 

Also available in: Atom