Project

General

Profile

Activity

From 12/13/2016 to 01/11/2017

01/11/2017

08:07 PM Feature #18490: client: implement delegation support in userland cephfs
I've created an nfs-ganesha category to match our Samba category. John Spray
05:52 PM Feature #18490 (Resolved): client: implement delegation support in userland cephfs
To properly implement NFSv4 delegations in ganesha, we need something that operates a little like Linux's fcntl(..., ... Jeff Layton
05:49 PM Feature #11950 (Fix Under Review): Strays enqueued for purge cause MDCache to exceed size limit
https://github.com/ceph/ceph/pull/12786 John Spray
05:00 PM Feature #18489 (New): mds: Multi-MDS-aware dirfrag split/join test
Similar to the existing dirfrag tests, but do some import/exporting of the resulting fragments so that they span mult... John Spray
01:04 PM Bug #18487 (Resolved): Crash in MDCache::split_dir -- FAILED assert(dir->is_auth())
... John Spray
12:40 PM Feature #18477: O_TMPFILE support in libcephfs
Yeah, with Linux' O_TMPFILE you can definitely do I/O to the inode before it's linked, and I think it'd be good to mi... Jeff Layton
11:49 AM Feature #18477: O_TMPFILE support in libcephfs
I was assuming that when doing it ephemerally we would not be allowing any data IO operations on the inode until it w... John Spray
11:50 AM Feature #18483: Forward scrub ops are not in Op Tracker
See also http://tracker.ceph.com/issues/17852 John Spray
01:22 AM Feature #18483 (New): Forward scrub ops are not in Op Tracker
We started a forward scrub on the LRC today to look for any busted rstats since we appear to have leaked data somewhe... Greg Farnum

01/10/2017

10:38 PM Feature #18477: O_TMPFILE support in libcephfs
I'm pretty skeptical that doing it ephemerally (without initially setting it up as a journaled stray) is a feasible s... Greg Farnum
08:50 PM Feature #18477: O_TMPFILE support in libcephfs
The stray would end up getting journaled, probably never written to backing store as long as the link operation came ... John Spray
07:19 PM Feature #18477: O_TMPFILE support in libcephfs
I think it makes sense to optimize for the success case here. In most cases, the link will be successful and it'll en... Jeff Layton
07:12 PM Feature #18477: O_TMPFILE support in libcephfs
Main decision here is probably whether it should be a stray or some new mechanism.
Strays feel like overkill here ...
John Spray
05:39 PM Feature #18477 (New): O_TMPFILE support in libcephfs
nfs-ganesha could make use of the ability to create a disconnected inode (pinned only by an open file descriptor) tha... Jeff Layton
02:40 PM Feature #18475 (Resolved): qa: run xfstests in the nightlies
We have manually run xfstests against ceph-fuse and kceph before, but apparently don't do so in the nightlies. Jeff r... Greg Farnum
02:16 PM Support #16526 (Resolved): cephfs client side quotas - nfs-ganesha
Yep, I think so. John Spray
01:53 PM Support #16526: cephfs client side quotas - nfs-ganesha
In a Ganesha (V2.5-dev-6) and Ceph (latest Jewel) setup, I set `client quota = true` in the client section of the cep... Ramana Raja
09:45 AM Bug #18460 (Fix Under Review): ceph-fuse crash during snapshot tests
https://github.com/ceph/ceph/pull/12859 Zheng Yan
03:40 AM Bug #18461 (Fix Under Review): failed to reconnect caps during snapshot tests
Zheng Yan
03:40 AM Bug #18461: failed to reconnect caps during snapshot tests
https://github.com/ceph/ceph/pull/12852 Zheng Yan

01/09/2017

01:58 PM Backport #18462 (In Progress): jewel: Decode errors on backtrace will crash MDS
Nathan Cutler
11:21 AM Backport #18462 (Resolved): jewel: Decode errors on backtrace will crash MDS
https://github.com/ceph/ceph/pull/12836 Nathan Cutler
01:57 PM Backport #18463 (In Progress): kraken: Decode errors on backtrace will crash MDS
Nathan Cutler
11:21 AM Backport #18463 (Resolved): kraken: Decode errors on backtrace will crash MDS
https://github.com/ceph/ceph/pull/12835 Nathan Cutler
01:02 PM Bug #18396 (Fix Under Review): Test Failure: kcephfs test_client_recovery.TestClientRecovery
kernel_mount.py does implement force umount
https://github.com/ceph/ceph/pull/12833
Zheng Yan
08:36 AM Bug #18396: Test Failure: kcephfs test_client_recovery.TestClientRecovery
http://qa-proxy.ceph.com/teuthology/teuthology-2017-01-05_11:20:01-kcephfs-kraken-testing-basic-smithi/691532/
http:...
Zheng Yan
11:04 AM Bug #18311 (Pending Backport): Decode errors on backtrace will crash MDS
John Spray
08:31 AM Bug #18461 (Resolved): failed to reconnect caps during snapshot tests
http://qa-proxy.ceph.com/teuthology/teuthology-2017-01-07_17:15:02-fs-master---basic-smithi/698957/ Zheng Yan
07:47 AM Bug #18460 (Resolved): ceph-fuse crash during snapshot tests
http://qa-proxy.ceph.com/teuthology/teuthology-2017-01-05_11:10:02-fs-kraken---basic-smithi/691432/teuthology.log
...
Zheng Yan

01/08/2017

08:04 PM Bug #11124 (Fix Under Review): MDSMonitor: refuse to do "fs new" on metadata pools containing obj...
https://github.com/ceph/ceph/pull/12825 Michal Jarzabek

01/06/2017

03:42 PM Backport #18439 (In Progress): kraken: TestVolumeClient.test_evict_client failure creating pidfile
Nathan Cutler
03:40 PM Backport #18439 (Resolved): kraken: TestVolumeClient.test_evict_client failure creating pidfile
https://github.com/ceph/ceph/pull/12813 Nathan Cutler
03:29 PM Bug #18309 (Pending Backport): TestVolumeClient.test_evict_client failure creating pidfile
Kefu Chai
07:59 AM Bug #18306 (Fix Under Review): segfault in handle_client_caps
https://github.com/ceph/ceph/pull/12808 Zheng Yan

01/05/2017

01:50 PM Bug #18306: segfault in handle_client_caps
Zheng Yan
01:49 PM Bug #18306: segfault in handle_client_caps
http://qa-proxy.ceph.com/teuthology/zyan-2017-01-05_11:43:04-fs-wip-zyan-testing-testing-basic-mira/692034/teuthology... Zheng Yan
05:21 AM Feature #18425: mds: add the option to use tcmalloc directly
https://github.com/ceph/ceph/pull/12792
By default, MDS is still using boost::pool.
Zhi Zhang
05:19 AM Feature #18425 (Resolved): mds: add the option to use tcmalloc directly
As describable in http://tracker.ceph.com/issues/18225, MDS uses boost:pool by default and unused memory is usually m... Zhi Zhang

01/04/2017

01:57 PM Bug #16914: multimds: pathologically slow deletions in some tests
Right, but users are going to do this -- it needs to work. John Spray
10:31 AM Backport #18413 (In Progress): jewel: lookup of /.. in jewel returns -ENOENT
Nathan Cutler
10:26 AM Backport #18413 (Resolved): jewel: lookup of /.. in jewel returns -ENOENT
https://github.com/ceph/ceph/pull/12783 Nathan Cutler

01/03/2017

08:13 PM Bug #16397: nfsd selinux denials causing knfs tests to fail
Ok, sorry for the delay on this. Finally got around to opening a RHBZ:
https://bugzilla.redhat.com/show_bug.cg...
Jeff Layton
05:54 PM Bug #18408: lookup of /.. in jewel returns -ENOENT
The gory details of this problem are available here:
https://bugzilla.redhat.com/show_bug.cgi?id=1408989
Jeff Layton
05:52 PM Bug #18408 (Pending Backport): lookup of /.. in jewel returns -ENOENT
Jeff Layton
05:52 PM Bug #18408 (Resolved): lookup of /.. in jewel returns -ENOENT
This is a problem for nfs-ganesha, which needs to be able to perform a lookup of ".." in the root directory in order ... Jeff Layton
02:38 PM Bug #17563 (Resolved): extremely slow ceph_fsync calls
Kernel patches merged for v4.10. Jeff Layton
02:27 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
Sorry for the late response. At the very least, we need these commits:... Jeff Layton
09:36 AM Bug #18396 (Resolved): Test Failure: kcephfs test_client_recovery.TestClientRecovery
http://pulpito.ceph.com/teuthology-2016-12-31_11:20:02-kcephfs-kraken-testing-basic-smithi/678546/
Looks like the ...
Zheng Yan
09:09 AM Bug #18361: Test failure: test_session_reject (tasks.cephfs.test_sessionmap.TestSessionMap)
https://github.com/ceph/ceph/pull/12757 Zheng Yan
03:55 AM Bug #18157 (Resolved): ceph-fuse segfaults on daemonize
Zheng Yan
03:47 AM Bug #18179 (Fix Under Review): MDS crashes on missing metadata object
https://github.com/ceph/ceph/pull/12749 Zheng Yan
03:02 AM Bug #18047 (Resolved): assertion in MDSMap::get_up_features()
Zheng Yan
02:19 AM Bug #18362: Test failure: test_evict_client (tasks.cephfs.test_volume_client.TestVolumeClient)
http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-31_17:15:02-fs-master---basic-smithi/679504/
http://qa-proxy....
Zheng Yan

12/30/2016

06:10 AM Bug #18211 (Resolved): test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data ...
Zheng Yan
06:08 AM Bug #18363: Test failure: test_ops_throttle (tasks.cephfs.test_strays.TestStrays)
Oops, The log files no long exist. looks like someone is actively deleting the logs Zheng Yan

12/29/2016

09:58 AM Bug #18363 (Can't reproduce): Test failure: test_ops_throttle (tasks.cephfs.test_strays.TestStrays)
http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-24_17:15:02-fs-master---basic-smithi/663459/teuthology.log Zheng Yan
09:55 AM Bug #18362 (Duplicate): Test failure: test_evict_client (tasks.cephfs.test_volume_client.TestVolu...
http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-27_11:10:01-fs-kraken---basic-smithi/669343/
probably it'...
Zheng Yan
09:53 AM Bug #18361: Test failure: test_session_reject (tasks.cephfs.test_sessionmap.TestSessionMap)
http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-27_11:10:01-fs-kraken---basic-smithi/669334/ Zheng Yan
09:49 AM Bug #18361 (Fix Under Review): Test failure: test_session_reject (tasks.cephfs.test_sessionmap.Te...
https://github.com/ceph/ceph/pull/12708 Zheng Yan
09:16 AM Bug #18361 (Resolved): Test failure: test_session_reject (tasks.cephfs.test_sessionmap.TestSessio...
Zheng Yan

12/28/2016

10:19 AM Bug #16914: multimds: pathologically slow deletions in some tests
The reason is that you use "rm -rf delete_me/*" to delete files. ceph-fuse needs to do a lookup "delete_me" for each ... Zheng Yan

12/27/2016

11:33 AM Bug #11482 (Resolved): kclient: intermittent log warnings "client.XXXX isn't responding to mclien...
Nathan Cutler
11:32 AM Backport #13932 (Rejected): hammer: kclient: intermittent log warnings "client.XXXX isn't respond...
Nathan Cutler

12/24/2016

02:45 PM Bug #16914: multimds: pathologically slow deletions in some tests
I have a nice simple reproducer for this now (even with fuse default permissions = false it has the slowdown).
It'...
John Spray

12/22/2016

05:26 PM Bug #18309: TestVolumeClient.test_evict_client failure creating pidfile
Alternative approach: https://github.com/ceph/ceph/pull/12628 Nathan Cutler
02:17 PM Bug #18314 (Resolved): commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks la...
Sage Weil
01:58 PM Bug #18314: commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks large directory
http://tracker.ceph.com/issues/18334 to track a proper fix for OMAP_GETKEYS Sage Weil
10:14 AM Backport #17478 (Resolved): jewel: MDS goes damaged on blacklist (failed to read JournalPointer: ...
Loïc Dachary
10:14 AM Backport #17582 (Resolved): jewel: monitor assertion failure when deactivating mds in (invalid) f...
Loïc Dachary
10:14 AM Backport #17615 (Resolved): jewel: mds: false "failing to respond to cache pressure" warning
Loïc Dachary
10:14 AM Backport #17617 (Resolved): jewel: [cephfs] fuse client crash when adding a new osd
Loïc Dachary
10:14 AM Backport #17697 (Resolved): jewel: MDS long-time blocked ops. ceph-fuse locks up with getattr of ...
Loïc Dachary
10:14 AM Backport #17706 (Resolved): jewel: multimds: mds entering up:replay and processing down mds aborts
Loïc Dachary
10:14 AM Backport #17720 (Resolved): jewel: MDS: false "failing to respond to cache pressure" warning
Loïc Dachary
10:13 AM Backport #17841 (Resolved): jewel: mds fails to respawn if executable has changed
Loïc Dachary
10:13 AM Backport #17885 (Resolved): jewel: "[ FAILED ] LibCephFS.InterProcessLocking" in jewel v10.2.4
Loïc Dachary

12/21/2016

08:02 PM Bug #18309 (Fix Under Review): TestVolumeClient.test_evict_client failure creating pidfile
-https://github.com/ceph/ceph/pull/12606- Nathan Cutler
06:20 PM Bug #18309: TestVolumeClient.test_evict_client failure creating pidfile
The problem is that global_init_prefork is calling pidfile_write, and we started using that from the client in 83aaa5... John Spray
06:17 PM Backport #18308 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
Nathan Cutler
05:20 PM Backport #18308 (New): ceph-fuse not clearing setuid/setgid bits on chown
Nathan Cutler
04:36 PM Backport #18308: ceph-fuse not clearing setuid/setgid bits on chown
h3. original description
I had some test failures that showed up in my most recent fs suite run here:
http...
Nathan Cutler
06:17 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
*master PR*: https://github.com/ceph/ceph/pull/12331 Nathan Cutler
04:38 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
@Jeff: Which commit fixes the issue/should be backported to jewel? Nathan Cutler
05:18 PM Bug #18254 (Resolved): path restricted cephx caps not working correctly
Nathan Cutler
05:16 PM Bug #18254: path restricted cephx caps not working correctly
*master PR*: https://github.com/ceph/ceph/pull/12505 Nathan Cutler
04:52 PM Bug #18254: path restricted cephx caps not working correctly
@Jeff: We have a system/service in place for backporting bugfixes to our stable releases. Patches backported via this... Nathan Cutler
05:18 PM Backport #18307: path restricted cephx caps not working correctly
(removed attachments that are available at #18254) Nathan Cutler
05:17 PM Backport #18307 (Resolved): path restricted cephx caps not working correctly
Nathan Cutler
04:39 PM Backport #18307 (New): path restricted cephx caps not working correctly
h3. original description
Ramana noticed this first while testing my ganesha patches to allow restricting exports. ...
Nathan Cutler
02:24 PM Bug #18314 (Fix Under Review): commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" b...
https://github.com/ceph/ceph/pull/12599 Zheng Yan
08:37 AM Bug #18314: commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks large directory
... Zheng Yan
08:32 AM Bug #18314 (Resolved): commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks la...
OPTION(osd_max_omap_bytes_per_request, OPT_U64, 4<<20)
4M can only carry about 5k dentries. It's too small
Zheng Yan
11:14 AM Bug #15921 (Can't reproduce): segfault in cephfs-journal-tool (TestJournalRepair failure)
Haven't seen this failure in a long time. John Spray
11:11 AM Bug #2375 (Closed): rrdtoll data malfuntion..
Ancient, closing. John Spray
11:09 AM Bug #1206 (Closed): NFS reexport file creation lags 1-3 seconds
Closing this because it's ancient (and if NFS creates were super-slow we'd notice on the knfs suite) John Spray

12/20/2016

06:54 PM Backport #18307: path restricted cephx caps not working correctly
PR is up here:
https://github.com/ceph/ceph/pull/12592
Jeff Layton
01:00 PM Backport #18307 (Resolved): path restricted cephx caps not working correctly
https://github.com/ceph/ceph/pull/12592 Jeff Layton
06:06 PM Bug #18311 (Fix Under Review): Decode errors on backtrace will crash MDS
https://github.com/ceph/ceph/pull/12588 John Spray
03:16 PM Bug #18311 (Resolved): Decode errors on backtrace will crash MDS
Noticed by inspection:... John Spray
05:46 PM Bug #18225 (Resolved): MDS doesn't release memory after exceeding its cache size limit
John Spray
05:34 PM Bug #9935 (Fix Under Review): client: segfault on ceph_rmdir path "/"
https://github.com/ceph/ceph/pull/12550 Michal Jarzabek
01:19 PM Bug #18309 (Resolved): TestVolumeClient.test_evict_client failure creating pidfile
Consistent on master
http://pulpito.ceph.com/jspray-2016-12-19_21:05:25-fs-master-distro-basic-smithi/648157
I ...
John Spray
01:13 PM Backport #18308 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
https://github.com/ceph/ceph/pull/12591 Jeff Layton
01:01 PM Bug #18131 (Pending Backport): ceph-fuse not clearing setuid/setgid bits on chown
Jeff Layton
12:59 PM Bug #18254 (Pending Backport): path restricted cephx caps not working correctly
Jeff Layton
12:21 PM Bug #18254: path restricted cephx caps not working correctly
Patch merged. We'll also want this backported to jewel. Jeff Layton
11:16 AM Bug #18306 (Resolved): segfault in handle_client_caps
http://pulpito.ceph.com/jspray-2016-12-19_21:05:25-fs-master-distro-basic-smithi/648247... John Spray

12/16/2016

02:42 PM Backport #18283 (Closed): kraken: monitor cannot start because of "FAILED assert(info.state == MD...
Nathan Cutler
02:42 PM Backport #18282 (Resolved): jewel: monitor cannot start because of "FAILED assert(info.state == M...
https://github.com/ceph/ceph/pull/13123 Nathan Cutler

12/14/2016

10:52 PM Bug #18254: path restricted cephx caps not working correctly
The patch turns out to be pretty trivial:... Jeff Layton
09:26 PM Bug #18254: path restricted cephx caps not working correctly
Revised test program here, in patch format so it can build in tree. We should probably roll this up into a regression... Jeff Layton
08:56 PM Bug #18254: path restricted cephx caps not working correctly
Thanks Greg, I'll take a look at how all of that stuff gets set. FWIW, here's the log with the client debugging crank... Jeff Layton
08:44 PM Bug #18254: path restricted cephx caps not working correctly
Did you check the client log to see where it's failing out at?
I'd check the code flow from Client::mount() to the M...
Greg Farnum
08:28 PM Bug #18254: path restricted cephx caps not working correctly
The program logs this in the MDS logs when run. I'm definitely passing in a real path there:... Jeff Layton
08:12 PM Bug #18254: path restricted cephx caps not working correctly
Oh, and you will need to overwrite the key in the reproducer program with the one for "alice". Jeff Layton
08:05 PM Bug #18254 (Resolved): path restricted cephx caps not working correctly
Ramana noticed this first while testing my ganesha patches to allow restricting exports. It appears that attempting t... Jeff Layton
07:45 PM Bug #18119 (Closed): mds: check and get latest current logsegment to avoid trimming logsegment cr...
This does not seem to be an issue in either master nor Jewel. Greg Farnum
01:54 PM Feature #12132 (Resolved): cephfs-data-scan: Cleanup phase
https://github.com/ceph/ceph/pull/12337#pullrequestreview-12909728... John Spray
12:56 PM Bug #18166 (Pending Backport): monitor cannot start because of "FAILED assert(info.state == MDSMa...
John Spray

12/13/2016

10:47 PM Bug #18151: Incorrect report of size when quotas are enabled.
As commented in the users ML, we will be updating to 10.2.5 in early January. Will provide feedback once that is done. Goncalo Borges
07:58 PM Bug #18151: Incorrect report of size when quotas are enabled.
In fact the quota tree changes already got backported so I think this is resolved. http://tracker.ceph.com/issues/16313 Greg Farnum
06:17 AM Bug #18151 (In Progress): Incorrect report of size when quotas are enabled.
Well, this code changed a fair bit between Jewel and master, as Zheng ripped out the quota trees. However, there appe... Greg Farnum
05:59 PM Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
I'll lower the priority to Normal now.
Ok, this should be fixed in mainline kernels and coming to stable series ke...
Jeff Layton
02:24 PM Bug #18159 (Fix Under Review): "Unknown mount option mds_namespace"
https://github.com/ceph/ceph/pull/12465 John Spray
02:21 PM Bug #16691 (Resolved): sepia LRC lost directories
John Spray
02:21 PM Feature #17853 (Resolved): More deterministic timing for directory fragmentation
John Spray
01:47 PM Bug #18238 (Can't reproduce): TestDataScan failing due to log "unmatched rstat on 100"

This is almost certainly just something where we need to update the log whitelist, but I'm curious about how we got...
John Spray
10:14 AM Bug #17270: [cephfs] fuse client crash when adding a new osd
@Henrik: The fix appears to be to revert https://github.com/ceph/ceph/commit/1a48a8a2b222e41236341cb1241f0885a1b0b9d8... Nathan Cutler
09:39 AM Bug #17270: [cephfs] fuse client crash when adding a new osd
Is there are chance to get this backported to hammer too? We had same ceph-fuse crashes recently (0.94.9 ceph-fuse an... Henrik Korkuc
08:17 AM Bug #18211: test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data pool empty ...
Zheng Yan
08:17 AM Bug #18211: test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data pool empty ...
https://github.com/ceph/ceph-client/commit/6899bb08e4173b7dfc0aa232e589541da869411f Zheng Yan
 

Also available in: Atom