Project

General

Profile

Activity

From 11/07/2016 to 12/06/2016

12/06/2016

11:39 PM Bug #18159 (Resolved): "Unknown mount option mds_namespace"
I think this is just a spurious message coming from src/mount/mount.ceph.c because it was not updated when mds_namesp... John Spray
11:16 PM Bug #18157 (Fix Under Review): ceph-fuse segfaults on daemonize
https://github.com/ceph/ceph/pull/12347 Greg Farnum
10:20 PM Bug #18157: ceph-fuse segfaults on daemonize
Not detected in nightlies because of #18158 Greg Farnum
10:16 PM Bug #18157 (Resolved): ceph-fuse segfaults on daemonize
... Greg Farnum
06:52 PM Bug #17193: truncate can cause unflushed snapshot data lose
It looks like the patch hasn't eliminated the failure:
http://pulpito.ceph.com/jspray-2016-12-06_12:37:38-kcephfs:re...
John Spray
03:34 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
Testing a PR now that fixes the setattr codepaths. That's pretty simple to do from those codepaths since we're sendin... Jeff Layton
02:58 PM Feature #18154 (Fix Under Review): qa: enable mds thrash exports tests

Currently:...
John Spray
05:40 AM Bug #18086 (Pending Backport): cephfs: fix missing ll_get for ll_walk
Greg Farnum
04:34 AM Bug #18151: Incorrect report of size when quotas are enabled.
Due to other bug / issue, I've run ceph-fuse in debug mode with 'debug client = 20'. Right after launching ceph-fuse,... Goncalo Borges
01:21 AM Bug #18151: Incorrect report of size when quotas are enabled.
1) My environment:
- ceph/cephfs in 10.2.2.
- All infrastructure is in the same version (rados cluster, mons, m...
Goncalo Borges
01:15 AM Bug #18151 (Resolved): Incorrect report of size when quotas are enabled.
Goncalo Borges

12/05/2016

06:47 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
So the upshot here is that I don't think this is anything that has broken in ceph, per-se. FUSE changed its behavior,... Jeff Layton
06:12 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
Ahh, I think I see the problem:... Jeff Layton
04:25 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
Definitely a kernel problem. Works correctly on v4.8.0, broken on v4.8.6 kernel for sure. I haven't bisected to be su... Jeff Layton
03:45 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
Sorry, I mean this patch in my v4.8.10 kernel:... Jeff Layton
03:38 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
First evidence I see of this test failing is here:
http://pulpito.ceph.com/teuthology-2016-11-30_10:10:02-fs-j...
Jeff Layton
03:38 PM Backport #18026 (In Progress): jewel: ceph_volume_client.py : Error: Can't handle arrays of non-s...
Loïc Dachary
03:36 PM Backport #18100: jewel: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
@John https://github.com/ceph/ceph/pull/12097/files conflicts in a non trivial way, could you take a look when you ha... Loïc Dachary
03:33 PM Backport #18103 (In Progress): jewel: truncate can cause unflushed snapshot data lose
Loïc Dachary

12/02/2016

08:30 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
BTW as you might have guessed, the crash occurred for me when I added a metadata server to a fresh cluster. Then ceph... Loïc Minier
08:28 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
I'm a bit puzzled why the last insert fails:... Loïc Minier
07:24 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
I see MDSMonitor::prepare_beacon() proceed through the:... Loïc Minier
07:05 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
Valgrind:... Loïc Minier
07:00 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
w/ debugging symbols:... Loïc Minier
06:52 PM Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
Hi,
I can confirm this issue on armhf; I was initially having it with 10.1.2-0ubuntu1 from xenial on a scaleway C1...
Loïc Minier
06:33 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
The tests I'm mainly concered with are the pjd.sh tests in those. The rest seem to be transient failures of one sort ... Jeff Layton
06:29 PM Bug #18131 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
I had some test failures that showed up in my most recent fs suite run here:
http://pulpito.ceph.com/jlayton-...
Jeff Layton
04:51 PM Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
@jcsp did you run into this before ? Loïc Dachary
04:51 PM Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
Loïc Dachary
04:50 PM Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
https://jenkins.ceph.com/job/ceph-pull-requests/14992/console
exact same error
Loïc Dachary
01:18 PM Bug #18118 (Duplicate): multimds: mds stuck in up:creating
seems like dup of http://tracker.ceph.com/issues/18066. MDSRank::creating_done did not get called. Osd op with tid ==... Zheng Yan
03:05 AM Bug #18118 (Duplicate): multimds: mds stuck in up:creating
Seen here:
http://pulpito.ceph.com/pdonnell-2016-12-02_01:20:51-multimds-master-testing-basic-mira/594001/
mds ...
Patrick Donnelly
09:32 AM Bug #18119: mds: check and get latest current logsegment to avoid trimming logsegment crashing
https://github.com/ceph/ceph/pull/12277
The fix here is to check whether mdr->ls/mut->ls is expired or not in call...
Zhi Zhang
09:27 AM Bug #18119 (Closed): mds: check and get latest current logsegment to avoid trimming logsegment cr...
... Zhi Zhang

12/01/2016

11:58 PM Bug #17656: cephfs: high concurrent causing slow request
william sheng wrote:
> Greg Farnum wrote:
> > Just from the description it sounds like we're backing up while the M...
william sheng
08:12 PM Feature #17980: MDS should reject connections from OSD-blacklisted clients
Related to http://tracker.ceph.com/issues/9754? Ramana Raja
03:15 PM Bug #18066 (Resolved): objecter dropped op submitted before pool existed
https://github.com/ceph/ceph/pull/12234
Sage Weil
03:05 PM Backport #18103 (Resolved): jewel: truncate can cause unflushed snapshot data lose
https://github.com/ceph/ceph/pull/12324 Loïc Dachary
03:04 PM Bug #17982 (Resolved): fuse client failing to trim disconnected inode on unmount
Fix is merged -- commit 2d02d2c95af9aed31a8579a2245b759f57b3a193. Jeff Layton
03:03 PM Backport #18100 (Resolved): jewel: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
https://github.com/ceph/ceph/pull/13139 Loïc Dachary
03:03 PM Bug #18013 (Resolved): ceph_test_libcephfs access failures when run without ceph-fuse mount in te...
Fixed in commit 8a887edaffeed66f02f605ee78b9999ffd629a60. Jeff Layton
02:05 PM Bug #8405 (Duplicate): multimds: FAILED assert(dir->is_frozen_tree_root())
dup of http://tracker.ceph.com/issues/17606 Zheng Yan

11/30/2016

07:06 PM Bug #18066: objecter dropped op submitted before pool existed
Sage Weil
01:24 AM Bug #18086: cephfs: fix missing ll_get for ll_walk
fixed by : https://github.com/ceph/ceph/pull/12061 Hecheng Gui
01:24 AM Bug #18086 (Resolved): cephfs: fix missing ll_get for ll_walk
When exporting a cephfs with nfs-ganesha, segfault is encountered upon releasing file handles using 'systemctl stop n... Hecheng Gui

11/29/2016

08:06 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
Thanks. Potential fix is up here:
https://github.com/ceph/ceph/pull/12228
Waiting for build now so I can get a ...
Jeff Layton
02:15 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
Jeff Layton wrote:
> Thanks. To make sure i understand...
>
> Since the inode is released after the mutex is drop...
Zheng Yan
12:44 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
Thanks. To make sure i understand...
Since the inode is released after the mutex is dropped, then the refcount dec...
Jeff Layton
09:13 AM Bug #17982: fuse client failing to trim disconnected inode on unmount
This looks like inode reference leak. I found something suspicious ... Zheng Yan
08:05 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
Potential fix up here. Still needs testing, but it seems to do the right thing on my box:
https://github.com/ceph/...
Jeff Layton
06:05 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
Sounds reasonable to me Jeff. Patrick Donnelly
04:25 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
Actually, now that I look further, it turns out that access.cc looks like it has just the function we need:... Jeff Layton
03:15 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
I think the right solution is to add a new function for setting the default UserPerm for the cmount, and have those j... Jeff Layton
05:09 PM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
RPMs here: http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/wip-17837-jewel/x86_64/ John Spray
12:01 PM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Alexander: I've pushed a backport of this to jewel to a branch called wip-17837-jewel. It will build in an hour or t... John Spray
11:50 AM Bug #17837 (Pending Backport): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
John Spray
07:12 AM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
I could test the changes, do I have to compile this project?
alexander walker
02:29 PM Bug #16397: nfsd selinux denials causing knfs tests to fail
From a recent run I see this is only happening on centos NFS servers, so I'm going to pin these tests to ubuntu (but ... John Spray
01:45 PM Bug #18066 (Resolved): objecter dropped op submitted before pool existed

http://pulpito.ceph.com/teuthology-2016-11-28_17:15:02-fs-master---basic-smithi/583404/
This is manifesting as a...
John Spray
12:54 PM Bug #17193 (Pending Backport): truncate can cause unflushed snapshot data lose
John Spray
12:40 PM Feature #12552 (Rejected): qa: test cephfs over cache tier in fs suite
Cache tiers are deprecated. John Spray
08:23 AM Bug #18047 (Fix Under Review): assertion in MDSMap::get_up_features()
https://github.com/ceph/ceph/pull/12208 Zheng Yan

11/28/2016

02:29 PM Feature #11950 (In Progress): Strays enqueued for purge cause MDCache to exceed size limit
John Spray
01:25 PM Feature #18050 (New): Enable mounting a .snap directory from libcephfs/ceph-fuse

Manila is adding a "mountable snapshots" feature:
https://github.com/openstack/manila-specs/blob/master/specs/ocat...
John Spray
09:43 AM Bug #18047 (Resolved): assertion in MDSMap::get_up_features()
... Zheng Yan
07:03 AM Feature #12132 (In Progress): cephfs-data-scan: Cleanup phase
The following xattrs are added to zeroth object:
#define XATTR_CEILING "scan_ceiling"
#define XATTR_MAX_MTIME "...
Vishal Kanaujia
01:24 AM Bug #17911 (Resolved): ensure that we vet the ceph_statx flags masks in libcephfs API
Merged in https://github.com/ceph/ceph/pull/12106 Jeff Layton

11/24/2016

08:35 PM Documentation #18040: Documentation says not to run multiple MDS, but we can do that now
Merged to master -- I leave it up to you whether you want to backport (I don't usually do that for documentation) John Spray
07:31 PM Documentation #18040 (Fix Under Review): Documentation says not to run multiple MDS, but we can d...
https://github.com/ceph/ceph/pull/12184 Nathan Cutler
07:28 PM Documentation #18040 (Resolved): Documentation says not to run multiple MDS, but we can do that now
http://docs.ceph.com/docs/master/rados/deployment/ceph-deploy-mds/ has a red box that says "Do not run multiple metad... Nathan Cutler
01:25 PM Bug #18016 (Need More Info): cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
I'll keep posting on this issue whenever I find such an error. If nothing happens in a month or two we can probably f... Loïc Dachary
10:52 AM Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
Can't tell what was going on here without logs from the services (which afaik we don't gather in these situations?)
...
John Spray
08:10 AM Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
https://jenkins.ceph.com/job/ceph-pull-requests/14881/console Loïc Dachary
06:07 AM Bug #18016 (Duplicate): cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
... Loïc Dachary
10:47 AM Backport #18026 (Resolved): jewel: ceph_volume_client.py : Error: Can't handle arrays of non-strings
https://github.com/ceph/ceph/pull/12325 Nathan Cutler
08:53 AM Bug #17656: cephfs: high concurrent causing slow request
Greg Farnum wrote:
> Just from the description it sounds like we're backing up while the MDS purges deleted files fr...
william sheng

11/23/2016

09:49 PM Backport #17285 (Resolved): ceph-mon leaks in MDSMonitor when ceph-mds process is running but MDS...
Nathan Cutler
08:30 PM Bug #11258 (Resolved): cephfs-java ftruncate unit test failure
Nathan Cutler
08:30 PM Backport #13927 (Resolved): hammer: cephfs-java ftruncate unit test failure
Nathan Cutler
06:54 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
http://pulpito.ceph.com/teuthology-2016-11-21_17:15:01-fs-master---basic-smithi/567231/ John Spray
06:22 PM Bug #17982: fuse client failing to trim disconnected inode on unmount

Another instance
jspray-2016-11-23_14:06:32-fs-wip-jcsp-testing-20161122-distro-basic-smithi/572367
John Spray
06:25 PM Bug #17800 (Pending Backport): ceph_volume_client.py : Error: Can't handle arrays of non-strings
John Spray
03:05 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
This chmod may be the bit we're missing:
https://github.com/ceph/ceph-qa-suite/blob/master/tasks/cephfs/fuse_mount.p...
John Spray
02:56 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
Looks like these tests don't specify a UserPerm on the ceph function invocations, nor set up a "global" one. I imagin... Greg Farnum
02:49 PM Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
BTW, the only material difference between this test run and a normal FS suite run is that ceph-fuse is turned off. Co... Patrick Donnelly
02:46 PM Bug #18013 (Resolved): ceph_test_libcephfs access failures when run without ceph-fuse mount in te...
When ceph-fuse is turned off for the libcephfs_interface_tests task, we see access control failures:... Patrick Donnelly
02:41 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
http://pulpito.ceph.com/sage-2016-11-23_14:40:24-upgrade:hammer-x-master---basic-smithi/ Sage Weil
02:37 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
https://github.com/ceph/ceph-qa-suite/pull/1280
added debugging. the mon connection looks fine, but it isn't doin...
Sage Weil
02:18 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
It's a hammer ceph-fuse trying to mount.. my guess is a compat issue Sage Weil
08:05 AM Backport #17956 (In Progress): jewel: Clients without pool-changing caps shouldn't be allowed to ...
Loïc Dachary
08:04 AM Backport #18008 (In Progress): jewel: Cannot create deep directories when caps contain "path=/som...
Loïc Dachary
06:43 AM Backport #18008 (Resolved): jewel: Cannot create deep directories when caps contain "path=/somepath"
https://github.com/ceph/ceph/pull/12154 Loïc Dachary
07:57 AM Backport #18010 (In Progress): jewel: Cleanly reject "session evict" command when in replay
Loïc Dachary
06:43 AM Backport #18010 (Resolved): jewel: Cleanly reject "session evict" command when in replay
https://github.com/ceph/ceph/pull/12153 Loïc Dachary

11/22/2016

11:28 PM Bug #17858 (Pending Backport): Cannot create deep directories when caps contain "path=/somepath"
John Spray
06:24 PM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Greg Farnum
04:40 PM Bug #17990: newly created directory may get fragmented before it gets journaled
I guess this was getting highlighted because of the timing change in https://github.com/ceph/ceph/pull/12022 (which w... John Spray
09:49 AM Bug #17990 (Fix Under Review): newly created directory may get fragmented before it gets journaled
https://github.com/ceph/ceph/pull/12125 Zheng Yan
09:45 AM Bug #17990 (Resolved): newly created directory may get fragmented before it gets journaled
http://pulpito.ceph.com/jspray-2016-11-18_13:57:54-fs-wip-jcsp-testing-20161118-distro-basic-smithi/559675 Zheng Yan
04:38 PM Backport #17974: jewel: ceph/Client segfaults in handle_mds_map when switching mds
h3. Original description
Our manila-share daemon is segfaulting when our active mds goes away and we switch to the...
Loïc Dachary
04:38 PM Backport #17974 (In Progress): jewel: ceph/Client segfaults in handle_mds_map when switching mds
Loïc Dachary
03:51 PM Backport #17974 (Fix Under Review): jewel: ceph/Client segfaults in handle_mds_map when switching...
In jewel there is no call to erase a command from the table after it receives a reply, so if a command has ever been ... John Spray
03:39 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
One oddity in the check_caps code is that we always try to retain CEPH_CAP_PIN, even when unmounting. I'm going to te... Jeff Layton
03:07 PM Bug #17982: fuse client failing to trim disconnected inode on unmount
I'll grab this for now since I was in this codepath recently. Looking at it though, I suspect that this is unrelated ... Jeff Layton
02:11 PM Bug #16924 (Fix Under Review): Crash replaying EExport
https://github.com/ceph/ceph/pull/12133 John Spray
11:49 AM Bug #17921: CephFS snapshot removal fails with "Stale file handle" error
Ah, I didn't notice that.
Rama: modify your .yaml configuration to only list one MDS daemon, or make sure that all...
John Spray
11:37 AM Bug #17921 (Rejected): CephFS snapshot removal fails with "Stale file handle" error
you were testing snaphost on multimds setup. It's known broken. For now, please test snapshot only on single active m... Zheng Yan

11/21/2016

09:57 PM Bug #17982 (Resolved): fuse client failing to trim disconnected inode on unmount

This fuse client is failing to terminate after being unmounted. It has a disconnected inode 10000008bdc from an un...
John Spray
08:58 PM Bug #17894 (Resolved): Filesystem removals intermittently failing in qa-suite
Patrick Donnelly
06:08 PM Feature #17980 (Resolved): MDS should reject connections from OSD-blacklisted clients
Currently, MDS daemons don't have a blacklist concept: an evicted client is free to reconnect.
Rather than inventi...
John Spray
06:05 PM Feature #17979 (New): mds: disable early replies when the MDS has slow RADOS requests

This is a primitive form of flow control.
Currently, if the MDS is experiencing a backlog of RADOS operations, t...
John Spray
02:46 PM Backport #17974: jewel: ceph/Client segfaults in handle_mds_map when switching mds
(the updates to the code in Kraken were ceph-mgr related so if they fixed a bug it was completely accidental!) John Spray
02:46 PM Backport #17974: jewel: ceph/Client segfaults in handle_mds_map when switching mds
I wouldn't be surprised if it was fixed in Kraken but I'll look at the Jewel code. John Spray
11:12 AM Backport #17974 (Resolved): jewel: ceph/Client segfaults in handle_mds_map when switching mds
https://github.com/ceph/ceph/pull/12137 Dan van der Ster
12:54 PM Bug #17801 (Pending Backport): Cleanly reject "session evict" command when in replay
John Spray
12:50 PM Bug #17606: multimds: assertion failure during directory migration
possibly fix https://github.com/ceph/ceph/pull/12098 Zheng Yan
12:12 PM Bug #17837 (Fix Under Review): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
https://github.com/ceph/ceph/pull/12097 John Spray
09:36 AM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Thanks Patrick. Indeed wip-17858-jewel resolves this for us. Both mkdir -p and our original untar kernel reproducer i... Dan van der Ster

11/19/2016

05:19 PM Bug #16881 (Can't reproduce): RuntimeError: Files in flight high water is unexpectedly low (0 / 6)
This hasn't happened again afaik John Spray
05:18 PM Feature #17853 (Fix Under Review): More deterministic timing for directory fragmentation
https://github.com/ceph/ceph/pull/12022 John Spray
04:50 AM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Dan, give this a try: https://github.com/ceph/ceph/tree/wip-17858-jewel Patrick Donnelly

11/18/2016

09:14 PM Bug #17954 (Fix Under Review): standby-replay daemons can sometimes miss events
https://github.com/ceph/ceph/pull/12077 John Spray
01:55 PM Bug #17954 (Resolved): standby-replay daemons can sometimes miss events

The symptom is that a standby replay daemon gives log messages like "waiting for subtree_map. (skipping " at times...
John Spray
06:35 PM Feature #17604 (Fix Under Review): MDSMonitor: raise health warning when there are no standbys bu...
PR: https://github.com/ceph/ceph/pull/12074 Patrick Donnelly
03:52 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Sure, I just need to make some adjustments to the patch first. I'll comment here again when I've pushed the branch. Patrick Donnelly
02:41 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Err wip-17858-jewel ... you know what I meant ;) Dan van der Ster
02:15 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Thanks Patrick. I'm the user in #17893. If it's not too much trouble, could you push a wip-17893-jewel branch so we c... Dan van der Ster
02:27 AM Bug #17858 (Fix Under Review): Cannot create deep directories when caps contain "path=/somepath"
PR: https://github.com/ceph/ceph/pull/12063 Patrick Donnelly
02:53 PM Backport #17956 (Resolved): jewel: Clients without pool-changing caps shouldn't be allowed to cha...
https://github.com/ceph/ceph/pull/12155 Nathan Cutler
02:53 PM Bug #17939: non-local cephfs quota changes not visible until some IO is done
I can't immediately remember how synchronous reads on the quota xattrs are meant to be, but they should probably be d... John Spray
01:25 PM Bug #17939: non-local cephfs quota changes not visible until some IO is done
Thanks, indeed that works! I tried *touch /cephfs/foo* and *touch /cephfs2/foo*; in both cases the "wrong" quota was ... Dan van der Ster
01:10 PM Bug #17939 (Need More Info): non-local cephfs quota changes not visible until some IO is done
I don't think you need a remount (of '/cephfs' in your reproducer) for the new share quota limits to be reflected (fo... Ramana Raja
02:00 PM Bug #17798 (Pending Backport): Clients without pool-changing caps shouldn't be allowed to change ...
https://github.com/ceph/ceph/pull/11789 John Spray
02:37 AM Bug #17893: Intermittent permission denied using kernel client with mds path cap
I agree with Zheng but I can't be 100% sure this is the same issue because the pasted log doesn't have the "SessionMa... Patrick Donnelly
02:31 AM Bug #17893 (Duplicate): Intermittent permission denied using kernel client with mds path cap
Patrick Donnelly

11/17/2016

04:31 PM Bug #17937: file deletion permitted from pool Y from client mount with pool=X capabilities
John Spray wrote:
> > MDS path restrictions are not used, so perhaps pool/namespace restrictions are not supported w...
David Disseldorp
04:16 PM Bug #17937 (Won't Fix): file deletion permitted from pool Y from client mount with pool=X capabil...
> MDS path restrictions are not used, so perhaps pool/namespace restrictions are not supported without a correspondin... John Spray
02:02 PM Bug #17937 (Won't Fix): file deletion permitted from pool Y from client mount with pool=X capabil...
Not sure whether this is a bug per se, but IMO certainly falls into the strange
behaviour basket.
If I have a fil...
David Disseldorp
03:18 PM Bug #17939: non-local cephfs quota changes not visible until some IO is done
That commit seems to test client_quota_df. That works, I agree. This issue is about extending a share.
extend_shar...
Dan van der Ster
02:27 PM Bug #17939: non-local cephfs quota changes not visible until some IO is done
Hmmm. I remember testing manila's extend share API with cephfs's native driver, where the ceph_volume_client modifies... Ramana Raja
02:13 PM Bug #17939 (Resolved): non-local cephfs quota changes not visible until some IO is done
If we change the ceph.quota.max_bytes attribute on a cephfs mount, that quota is not applied until cephfs is remounte... Dan van der Ster
01:31 PM Bug #16886: multimds: kclient hang (?) in tests
fix one bug https://github.com/ceph/ceph-client/commit/2a3d8aad521306c6537c67c518ea7c4023c74f12
If you see "fail...
Zheng Yan
10:29 AM Bug #17837 (In Progress): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Thanks, can now reproduce here. ... John Spray
06:27 AM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
here is dump of mdsmap local alexander walker
08:34 AM Bug #17921: CephFS snapshot removal fails with "Stale file handle" error
please set debug_client=20 and try again Zheng Yan

11/16/2016

03:38 PM Bug #17906 (Resolved): mds: dumped ops do not include events and other information
Good point! John Spray
03:14 PM Bug #17906: mds: dumped ops do not include events and other information
John, I don't think the bug exists in jewel. The culprit commit is not merged there. Patrick Donnelly
12:03 PM Bug #17906 (Pending Backport): mds: dumped ops do not include events and other information
John Spray
02:44 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Originally I could only reproduce with the kernel client. Now I can reproduce it also with ceph-fuse. Dan van der Ster
02:34 PM Bug #17921 (Rejected): CephFS snapshot removal fails with "Stale file handle" error
Removing CephFS snapshot fails while testing it in a loop with "stale file handle" error but there will not be any sn... Ramakrishnan Periyasamy
12:03 PM Bug #17747 (Resolved): ceph-mds: remove "--journal-check" help text
John Spray
12:03 PM Bug #17797 (Resolved): rmxattr on ceph.[dir|file].layout.pool_namespace doesn't work
John Spray
12:02 PM Bug #17308 (Resolved): MDSMonitor should tolerate paxos delays without failing daemons (Was: Unex...
John Spray
11:48 AM Bug #17837 (Need More Info): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Hmm, so when I try loading up the mdsmap.bin from http://tracker.ceph.com/issues/16592#change-81117 it is decoding fi... John Spray

11/15/2016

07:47 PM Bug #17894: Filesystem removals intermittently failing in qa-suite
I'll do a run of fs:multifs to see if the bug looks resolved. Patrick Donnelly
07:46 PM Bug #17894 (Fix Under Review): Filesystem removals intermittently failing in qa-suite
Patrick Donnelly
07:45 PM Bug #17894: Filesystem removals intermittently failing in qa-suite
PR: https://github.com/ceph/ceph-qa-suite/pull/1262 Patrick Donnelly
02:24 PM Bug #17894: Filesystem removals intermittently failing in qa-suite
I think your analysis is correct John. I'll write up a fix for that. Patrick Donnelly
02:20 PM Bug #17894: Filesystem removals intermittently failing in qa-suite
I'll look at this. Patrick Donnelly
02:14 PM Bug #17894: Filesystem removals intermittently failing in qa-suite
Hmm, too similar to be a coincidence?
http://qa-proxy.ceph.com/teuthology/jspray-2016-11-15_13:27:33-fs-wip-jcsp-t...
John Spray
02:11 PM Bug #17914 (New): ObjectCacher doesn't handle snapshot+truncate properly

When truncating file, we should not drop dirty data that were created before snapshot. But it seems ObjectCacher:...
Zheng Yan
01:59 PM Bug #17193 (Fix Under Review): truncate can cause unflushed snapshot data lose
https://github.com/ceph/ceph/pull/11994 Zheng Yan
12:02 PM Bug #17911 (Resolved): ensure that we vet the ceph_statx flags masks in libcephfs API
Currently, we allow callers to set flags that are not properly defined. This could be bad if we want to add new flags... Jeff Layton
08:34 AM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
sorry for misstype, I am ON ceph-fuse Henrik Korkuc
08:34 AM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
I am not ceph-fuse Henrik Korkuc
04:20 AM Bug #17906 (Fix Under Review): mds: dumped ops do not include events and other information
PR: https://github.com/ceph/ceph/pull/11985 Patrick Donnelly
04:19 AM Bug #17906 (Resolved): mds: dumped ops do not include events and other information
... Patrick Donnelly

11/14/2016

05:25 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
John - it's reliably reproducible :(
Just re-ran again http://pulpito.front.sepia.ceph.com/yuriw-2016-11-14_16:55:4...
Yuri Weinstein
04:46 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
Yuri: probably not related unless there's something I'm missing? Zheng was pointing out that the clock in the log se... John Spray
04:43 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
related to https://github.com/ceph/ceph-qa-suite/pull/1256 ? Yuri Weinstein
02:41 PM Bug #17847 (Rejected): "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
Looks like bad clocks in the test environment John Spray
05:09 PM Bug #17837 (In Progress): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
John Spray
05:08 PM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Note to self, dumps are on http://tracker.ceph.com/issues/16592 John Spray
03:00 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
The fix for #16358 is not complete. It only handles the case that inode is newly created, but does not handle the cas... Zheng Yan
02:41 PM Bug #17858: Cannot create deep directories when caps contain "path=/somepath"
Same as http://tracker.ceph.com/issues/17893 ?
Henrik: are you on fuse or kernel client?
John Spray
02:57 PM Bug #17893: Intermittent permission denied using kernel client with mds path cap
dup of #17858 Zheng Yan
01:30 PM Bug #17893 (Duplicate): Intermittent permission denied using kernel client with mds path cap
See this mailing list thread:
http://www.spinics.net/lists/ceph-users/msg32314.html
It is reported that when usin...
John Spray
02:30 PM Bug #17894 (Resolved): Filesystem removals intermittently failing in qa-suite

http://pulpito.ceph.com/teuthology-2016-11-12_17:15:01-fs-master---basic-smithi/543466/
I suspect this is a bug ...
John Spray
02:05 PM Bug #17800: ceph_volume_client.py : Error: Can't handle arrays of non-strings
Thomas: what was the series of operations running up to this? To hit this code path it seems like the user you were ... John Spray
11:42 AM Bug #17563 (In Progress): extremely slow ceph_fsync calls
PR for the userland code has been merged, and the kernel patches are in-progress. Jeff Layton

11/13/2016

12:34 PM Backport #17885 (In Progress): jewel: "[ FAILED ] LibCephFS.InterProcessLocking" in jewel v10.2.4
Nathan Cutler
12:25 PM Backport #17885 (Resolved): jewel: "[ FAILED ] LibCephFS.InterProcessLocking" in jewel v10.2.4
https://github.com/ceph/ceph/pull/11953 Nathan Cutler
12:24 PM Bug #17832 (Pending Backport): "[ FAILED ] LibCephFS.InterProcessLocking" in jewel v10.2.4
*master PR*: https://github.com/ceph/ceph/pull/11211
This PR just disables the tests. Work on a real fix is being ...
Nathan Cutler

11/12/2016

12:23 PM Backport #13927 (In Progress): hammer: cephfs-java ftruncate unit test failure
Nathan Cutler
12:22 PM Bug #11258: cephfs-java ftruncate unit test failure
*master PR*: https://github.com/ceph/ceph/pull/4215 Nathan Cutler

11/11/2016

02:21 PM Bug #17800 (Fix Under Review): ceph_volume_client.py : Error: Can't handle arrays of non-strings
PR for fix: https://github.com/ceph/ceph/pull/11917 Ramana Raja
11:13 AM Bug #17800 (In Progress): ceph_volume_client.py : Error: Can't handle arrays of non-strings
Ramana Raja
11:24 AM Bug #17747 (Fix Under Review): ceph-mds: remove "--journal-check" help text
Oops, forgot to clean up the manpage as well. Follow-up PR: https://github.com/ceph/ceph/pull/11912 Nathan Cutler
11:19 AM Bug #17747 (Resolved): ceph-mds: remove "--journal-check" help text
Nathan Cutler
11:05 AM Feature #17853 (In Progress): More deterministic timing for directory fragmentation
John Spray
06:46 AM Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
yes, I've stopped my update and my cluster working now with two mon server.
Perhaps it is helpful, I've a test clu...
alexander walker
06:46 AM Bug #16592: Jewel: monitor asserts on "mon/MDSMonitor.cc: 2796: FAILED assert(info.state == MDSMa...
I've created the ticket #17837.
Here ist output from "ceph mds dump --format=json-pretty"...
alexander walker

11/10/2016

03:38 PM Bug #17858 (Resolved): Cannot create deep directories when caps contain "path=/somepath"
ceph-fuse client with having "path=/something" cannot create multiple dirs with mkdir (e.g. mkdir -p 1/2/3/4/5/6/7/8/... Henrik Korkuc
02:27 PM Bug #17620: Data Integrity Issue with kernel client vs fuse client
The jobs failed by incorrectly writing the object to disk. I can recreate this pretty easily by having two clients do... Aaron Bassett
02:13 PM Bug #17620 (Need More Info): Data Integrity Issue with kernel client vs fuse client
Brett Niver
01:49 PM Bug #17193 (In Progress): truncate can cause unflushed snapshot data lose
Zheng Yan
01:18 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
... Zheng Yan
01:16 PM Feature #17856 (Resolved): qa: background cephfs forward scrub teuthology task
Create a teuthology task that can be run in the background of a workunit, which simply starts a forward scrub on the ... John Spray
12:03 PM Bug #12895 (Can't reproduce): Failure in TestClusterFull.test_barrier
John Spray
12:02 PM Bug #2277: qa: flock test broken
For reference: locktest.py still exists in ceph-qa-suite, with a single use from suites/marginal/fs-misc/tasks/lockte... John Spray
11:51 AM Feature #17855 (Resolved): Don't evict a slow client if it's the only client

There is nothing gained by evicting a client session if there are no other clients who might be held up by it.
T...
John Spray
11:50 AM Feature #17854 (Resolved): mds: only evict an unresponsive client when another client wants its caps

Instead of immediately evicting a client when it has not responded within the timeout, set a flag to mark the clien...
John Spray
10:45 AM Feature #17853 (Resolved): More deterministic timing for directory fragmentation

This ticket is to track the work to replace the tick()-based consumption of the split queue with some timers, and t...
John Spray
10:26 AM Bug #17837 (Need More Info): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
Alexander: so hopefully you stopped the upgrade at that point and you still have a working cluster of two hammer mons... John Spray
03:49 AM Bug #17837 (Duplicate): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
This looks like a duplicate of 16592 but in a new code path: interestingly in a slave monitor. Patrick Donnelly

11/09/2016

11:50 PM Bug #4829: client: handling part of MClientForward incorrectly?
Targeting for Luminous to investigate and either fix or close this. John Spray
11:50 PM Bug #3267 (Closed): Multiple active MDSes stall when listing freshly created files
This ticket is old and the use case seems like something we will pick up on from the multimds suite if it's still bro... John Spray
11:48 PM Feature #3426 (Closed): ceph-fuse: build/run on os x
John Spray
11:47 PM Feature #3426: ceph-fuse: build/run on os x
I don't think it's likely we will ever "finish" this in the sense of maintaining/testing functionality on OSX, so I'm... John Spray
11:45 PM Cleanup #660 (Closed): mds: use helpers in mknod, mkdir, openc paths
John Spray
11:31 PM Bug #1511 (Closed): fsstress failure with 3 active mds
We have fresh tickets for multimds failures as they are reproduced now. John Spray
11:24 PM Feature #17852 (Resolved): mds: when starting forward scrub, return handle or stamp/version which...
Enable caller to kick off a scrub and later check completion (may just mean caller has to compare scrub stamps with a... John Spray
11:21 PM Feature #12274: mds: start forward scrubs from all subtree roots, skip non-auth metadata
Using this ticket to track the task of implementing cross-MDS forward scrub (i.e. handing off at subtree bounds) John Spray
11:12 PM Feature #11950: Strays enqueued for purge cause MDCache to exceed size limit
Targeting for Luminous and assigning to me: we will use a single Journaler() instance per MDS to track a persistent p... John Spray
11:00 PM Feature #17770: qa: test kernel client against "full" pools/filesystems
This is largely http://tracker.ceph.com/issues/17204 , but I'm leaving this ticket here as a convenient way of tracki... John Spray
05:36 PM Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
For those not familiar with the test, can you explain what versions are in play here, and what version of the client/... John Spray
04:39 PM Bug #17847 (New): "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-11-09_15:03:11-upgrade:hammer-x-jewel-distro-basic-vps/
Job: 534...
Yuri Weinstein
03:10 PM Backport #17841 (In Progress): jewel: mds fails to respawn if executable has changed
Loïc Dachary
02:47 PM Backport #17841 (Resolved): jewel: mds fails to respawn if executable has changed
https://github.com/ceph/ceph/pull/11873 Loïc Dachary
02:15 PM Backport #17582 (In Progress): jewel: monitor assertion failure when deactivating mds in (invalid...
Loïc Dachary
02:14 PM Backport #17615 (In Progress): jewel: mds: false "failing to respond to cache pressure" warning
Loïc Dachary
02:12 PM Backport #17617 (In Progress): jewel: [cephfs] fuse client crash when adding a new osd
Loïc Dachary
02:05 PM Bug #17837 (Resolved): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
I've a cluster of three nodes:... alexander walker
01:59 PM Feature #17836 (New): qa: run multi-MDS tests with cache smaller than workload
Maybe work from my wip-smallcache branch https://github.com/ceph/ceph-qa-suite/tree/wip-smallcache
The goal is to ...
John Spray
01:48 PM Bug #16926 (Rejected): multimds: kclient fails to mount
Looks like this was initially failing when running against an old kernel, and was okay on a recent kernel, so closing. John Spray
01:43 PM Feature #17835 (Fix Under Review): mds: enable killpoint tests for MDS-MDS subtree export
... John Spray
01:00 PM Backport #17697 (In Progress): jewel: MDS long-time blocked ops. ceph-fuse locks up with getattr ...
Loïc Dachary
12:58 PM Backport #17706 (In Progress): jewel: multimds: mds entering up:replay and processing down mds ab...
Loïc Dachary
12:57 PM Backport #17720 (In Progress): jewel: MDS: false "failing to respond to cache pressure" warning
Loïc Dachary
11:17 AM Feature #17834 (Resolved): MDS Balancer overrides

(Discussion from November 2016 meeting https://docs.google.com/a/redhat.com/document/d/11-O8uHWmOCqyc2_xGIukL0myjnq...
John Spray
12:55 AM Bug #17832 (Resolved): "[ FAILED ] LibCephFS.InterProcessLocking" in jewel v10.2.4
Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-11-08_16:23:29-fs-jewel-distro-basic-smithi/
Jobs: 532365, 53236...
Yuri Weinstein

11/08/2016

10:50 PM Bug #16640: libcephfs: Java bindings failing to load on CentOS
And https://github.com/ceph/ceph-qa-suite/pull/1224 Greg Farnum
09:25 PM Bug #17828 (Need More Info): libceph setxattr returns 0 without setting the attr
Using the jewel libcephfs python bindings I ran the following code snippet:... Chris Holcombe
04:40 PM Bug #17193: truncate can cause unflushed snapshot data lose
This appears to be intermittent: after ~10 runs without a failure, it's back.
http://qa-proxy.ceph.com/teuthology/...
John Spray
02:06 PM Bug #17819: MDS crashed while performing snapshot creation and deletion in a loop
016-11-08T06:04:23.498 INFO:tasks.ceph.mds.a.host.stdout:starting mds.a at :/0
2016-11-08T06:04:23.498 INFO:tasks.ce...
Ramakrishnan Periyasamy
01:22 PM Bug #17819: MDS crashed while performing snapshot creation and deletion in a loop
The log ought to display exactly what assert in check_cache failed -- can you post that too? Greg Farnum
11:17 AM Bug #17819 (Can't reproduce): MDS crashed while performing snapshot creation and deletion in a loop
--- begin dump of recent events ---
-1> 2016-11-08 11:04:27.309191 7f4a57c38700 1 -- 10.8.128.73:6812/8588 <== ...
Ramakrishnan Periyasamy
01:41 PM Bug #17522 (Resolved): ceph_readdirplus_r does not acquire caps before sending back attributes
Fixed as of commit f7028e48936cb70f623fe7ba408708a403e60270. This requires moving to libcephfs2, however. Jeff Layton
01:37 PM Feature #16419 (Resolved): add statx-like interface to libcephfs
This should now be done for the most part. New ceph_statx interfaces have been merged into kraken. This change is not... Jeff Layton
01:36 PM Feature #3314 (Resolved): client: client interfaces should take a set of group ids
Now merged as of commit c078dc0daa9c50621f7252559a97bfb191244ca1. libcephfs has been revved to version 2, which is no... Jeff Layton

11/07/2016

02:29 PM Bug #17799: cephfs-data-scan: doesn't know how to handle files with pool_namespace layouts
the backtrace objects are always in default namespace. I think data scan tool can't calculate correct size for files ... Zheng Yan
02:25 PM Bug #17801 (Fix Under Review): Cleanly reject "session evict" command when in replay
https://github.com/ceph/ceph/pull/11813 Zheng Yan
11:43 AM Bug #17193 (Resolved): truncate can cause unflushed snapshot data lose
This is no longer failing when running against the testing kernel. John Spray
 

Also available in: Atom