Project

General

Profile

Activity

From 01/29/2014 to 02/27/2014

02/27/2014

09:29 PM CephFS Cleanup #3742 (Resolved): Remove old Hadoop wrappers and configuration options
Noah Watkins
09:27 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Actually, yeh I'll look at this. Noah Watkins
03:30 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Is this still an issue, Noah? Greg Farnum
09:23 PM CephFS Bug #4861 (Rejected): Alter Java components to build against Java 1.6 (or 1.7)
Noah Watkins
09:23 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Closing. I'm not sure what the problem is here.. it looks like I am saying that the code builds for a super old versi... Noah Watkins
03:26 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Do you know the state of the Java code right now, Noah? I wonder if this got done already or is still a bug requiring... Greg Farnum
07:29 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
The race still exists, but I don't think it's big problem. Because even if ceph_get_dentry_parent_inode() returns a w... Zheng Yan
04:03 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
Is this still a problem? Greg Farnum
05:14 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
who cares 3.5 kernel? Zheng Yan
03:28 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
Sounds like this might require some protocol work and it's in the kernel client — high! Greg Farnum
05:13 PM CephFS Bug #7565: Failed assert in check_rstats
it's CDir::check_rstats() bug, not rstat corruption. Zheng Yan
04:46 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats

This is odd, because it's happening very reproducibly, is not unique to the tip of master, but apparently isn't hap...
John Spray
04:51 PM CephFS Bug #1181: mds: old_inodes crash
Snapshots
See also #4248, which may or may not have anything to do with this.
Greg Farnum
04:50 PM CephFS Bug #926: mds: fix rename between snaprealms
Snapshots Greg Farnum
04:50 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
#7326 Greg Farnum
04:48 PM CephFS Bug #2740: mds: crash in Objecter when shutting down too early
I'm pretty sure this is fixed, but let's check it out and make sure. Greg Farnum
04:45 PM CephFS Bug #3596: ceph-fuse: crash in mds rejoin
Snapshots Greg Farnum
04:44 PM CephFS Bug #2187: pjd chown/00.t failed test 97
This is either an MDS or protocol bug since we've seen it across clients. Greg Farnum
04:43 PM CephFS Bug #2863: client: does not tolerate traceless replies from mds
uclient failure-case: low priority.
I believe we've established that the kclient does not suffer from this issue, ...
Greg Farnum
04:42 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
Confirmed MDS bug! Greg Farnum
04:41 PM Bug #7458: osd: stray pg ref on shutdown
David Zafman
04:40 PM CephFS Bug #2679: POSIX file lock not released on process termination
Let's see if we can reproduce this as it's some combination of kclient, MDS, or protocol bug. Greg Farnum
04:38 PM CephFS Bug #1666: hadoop: time-related meta-data problems
Also see #7564
But low priority, for this is Hadoop
Greg Farnum
04:36 PM CephFS Bug #4212: mds: open_snap_parents isn't called all the times it needs to be
Snapshots Greg Farnum
04:36 PM CephFS Bug #4213: mds: old_parents is never cleaned up
Snapshots Greg Farnum
04:35 PM CephFS Fix #7564: synchronize MDS and client times in a way that makes pjd happy even under clock skew
See also #1666 Greg Farnum
04:28 PM CephFS Fix #7564 (Duplicate): synchronize MDS and client times in a way that makes pjd happy even under ...
See #854. We have ops happen on both the client and the MDS, and so sometimes one time wins and sometimes the other d... Greg Farnum
04:29 PM CephFS Bug #854 (Duplicate): unsynchronized clocks between kernel-client/cmds cause PJD fstest failures
I'm closing this in favor of fix ticket #7564. Greg Farnum
04:13 PM CephFS Bug #1874: Running `git gc` on a bare git repository hosted by ceph results in a bus error.
So basically two things could have gone wrong here:
1) The OSD replied with a bad tid (unlikely)
2) the client forg...
Greg Farnum
04:02 PM CephFS Bug #4370: mds: high-cpu utilization in memorymodel:_sample
Figure out if the current MemoryModel is actually useful for anything — I think it might not be. All the lovely ticke... Greg Farnum
04:01 PM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
The hangs sound like generic cap and request waitlisting issues to to me. The empty directory is tickling something i... Greg Farnum
03:57 PM CephFS Bug #4248: mds: replay does not correctly update CInode::first and ::last members
I'm going to leave this at normal even though it's a snapshotting issue — the problem's diagnosed and it's a bug in t... Greg Farnum
03:53 PM CephFS Bug #4134: mds: request locking hang under snaptests
snapshots = low Greg Farnum
03:52 PM CephFS Bug #3719 (Can't reproduce): pjd test 145 failed in the nightly runs
These logs are gone. Greg Farnum
03:45 PM CephFS Bug #4280: mds: crash on lookupsnap
Snapshots = low priority Greg Farnum
03:38 PM CephFS Bug #2445: crash when removing a non-empty directory
Let's validate behavior here — there's a good chance Zheng or somebody fixed whatever bug caused this, and we want to... Greg Farnum
03:32 PM CephFS Bug #1877: ceph.ko (3.1.6) oopses upon cephfs set_layout of a symlink to a dir
Kernel client layout crash = high. Identify if this is still a problem, and if we can trigger it using the vxattrs as... Greg Farnum
03:30 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
Need more info, samba, uclient, etc. Greg Farnum
03:29 PM Bug #7563 (Resolved): osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_up...
2014-02-27 15:13:26.966410 7f65a44d6700 20 _merge_old_entry: oe.prior_version == 0 && already missing, removing missi... Samuel Just
03:27 PM CephFS Bug #4732: uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
The blocker bug is low, so this one can't have a higher priority. Greg Farnum
03:25 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
uclient = low priority, for now. Greg Farnum
03:25 PM Bug #7542: ec misdirected op
wip-7542 Samuel Just
03:25 PM Bug #7539: Firefly EC pool massive memory leak during writes
testing wip-7542 Samuel Just
01:30 PM Bug #7539: Firefly EC pool massive memory leak during writes
ubuntu@teuthology:/a/teuthology-2014-02-26_23:00:27-rados-firefly-testing-basic-plana/106918/remote
Messing up nig...
Samuel Just
03:25 PM CephFS Bug #4188: mds crashes when cow-ing entries in formerly snapshotted dir
Snapshots = low priority. *sigh* Greg Farnum
03:21 PM CephFS Bug #5360: ceph-fuse: failing smbtorture tests
Samba against ceph-fuse (not even using libcephfs) = low priority. Greg Farnum
03:20 PM CephFS Feature #5486: kclient: make it work with selinux
I don't know anything about SELinux, nor its users. What needs to work for us to support SELinux, and how big of a st... Greg Farnum
03:19 PM CephFS Bug #5762: teuthology: Failed MPI runs lead to a hung test instead of a failure
It's a test which we can't use properly. High priority! Greg Farnum
03:18 PM CephFS Bug #6458 (Need More Info): journaler: journal too short during replay
I've bumped up #4708, so if that's the cause of this it'll be fixed when that is. If not, we need more info. Greg Farnum
03:17 PM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
#6458 could be a result of this issue, so I'm bumping up the priority. Greg Farnum
03:14 PM CephFS Bug #5950: kcephfs: cephfs set_layout -p 4 gets EINVAL
We want to use the virtual xattrs moving forward, so downgrading a bug in the cephfs tool. Greg Farnum
01:38 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I wasn't on 3.8, it was 3.11. Unfortunately I can't use the machines I was experimenting with for this purpose anymor... Peter Waller
01:19 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
Zheng, do you have a specific bug you think this is so we can close it out? Greg Farnum
01:24 PM CephFS Bug #6741: failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
Downgrading: ceph-fuse and snapshots. Greg Farnum
01:23 PM CephFS Bug #6609: teuthology rsync workunit failure
I haven't noticed this in a while, but upgrading as it was a failure across both clients. Greg Farnum
01:22 PM CephFS Bug #5864: cfuse_workunit_suites_ffsb suite on Centos hangs with *** Got Signal Interrupt ***
This is passing in the nightlies, so if there is a bug it has to do with not only ceph-fuse, but ceph-fuse specifical... Greg Farnum
01:20 PM CephFS Bug #7206 (Need More Info): Ceph MDS Hang on hadoop workloads
Greg Farnum
01:18 PM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
We merged this to master in commit:9a040bfd46d141712c32aaa0fa8fc5de93336306, but I guess we missed closing out the ti... Greg Farnum
12:42 PM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
... Greg Farnum
11:48 AM Fix #7560 (Closed): mon: add compat set feature to mark an upgraded pg format in order to disallo...
We do not currently prevent a cuttlefish monitor from running on a dumpling store after an upgrade. Joao Eduardo Luis
11:02 AM Documentation #7558 (Resolved): broken link in install/manual-deployment/
The link under "See Monitor Config Reference - Data for details." is broken. Still think we should be spidering link... Dan Mick
08:21 AM devops Bug #6726: Official packages do not appear to be available for Saucy
We are currently building on both Saucy and Trusty, just need to push packages out to ceph.com
See
http://gitbuil...
Ian Colle
06:41 AM devops Bug #6726: Official packages do not appear to be available for Saucy
Just had a suggestion to use the raring packages from Tim Bishop on the users list.
Would be nice if we could get ...
Michael Potter
07:57 AM Bug #7248 (Fix Under Review): osd: bench set max size
https://github.com/ceph/ceph/pull/1324 Joao Eduardo Luis
06:50 AM CephFS Feature #7325: mds: tool to examine (later, manipulate) dirfrag objects
Is this intended to be an online thing (modifying live MDS state), or something that operates on the RADOS objects (i... John Spray
06:35 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
There was an earlier patch that introduced an "I'm in dispatch" flag, and a more recent one (https://github.com/ceph/... John Spray

02/26/2014

11:02 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Dan Mick
06:19 PM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
So I did a lot of testing on Fedora today. This is done so closing it out.
It looks like fedora18 was now kernel...
Sandon Van Ness
10:37 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
Ok so this is done but ceph-deploy tests are still failing...
Also that being said it looks like centos/rhel are r...
Sandon Van Ness
05:51 PM Feature #7553 (Resolved): Remove classic scrub

Bobtail was the first release with chunky scrub and had maintained classic scrub code for backwards compatibility. ...
David Zafman
05:01 PM CephFS Bug #4746: client: invalidate callback can deadlock
Demoted due to ceph-fuse and FUSE interface work. Greg Farnum
05:00 PM CephFS Bug #4829: client: handling part of MClientForward incorrectly?
Demoting due to uclient and multi-mds. Greg Farnum
04:58 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
Demoting due to uclient and Need More Info. Greg Farnum
04:57 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
Demoting due to multi-mds. Greg Farnum
04:57 PM CephFS Bug #5765: kclient: High CPU due to raw_spin_lock in ceph_cap_string
Demoting due to performance, not correctness. Greg Farnum
04:56 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
Demoting due to uclient. Greg Farnum
04:55 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
I'm pretty sure we had a discussion about your patch, but I can't find the comments and I don't remember the outcome.... Greg Farnum
04:48 PM CephFS Bug #6608: samba teuthology dbench failure
Demoting priority on samba. Greg Farnum
04:47 PM CephFS Bug #7011: ENOTEMPTY on ceph-fuse + snaptest-? test
Demoting priority on ceph-fuse and snapshots. Greg Farnum
04:47 PM CephFS Bug #6613: samba is crashing in teuthology
Demoting priority on samba. Greg Farnum
04:37 PM CephFS Feature #7326: qa: fix flock tests
I don't remember which tests these are; the locktest ones that are racy, or something else? Greg Farnum
04:35 PM CephFS Feature #7352: mds: make classes encode/decode-able
We've already merged in the MDSTable and Journaler header dumping stuff; I think that's all the stuff that you were t... Greg Farnum
04:29 PM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
Again, Zheng got this done. Greg Farnum
04:26 PM CephFS Cleanup #3742: Remove old Hadoop wrappers and configuration options
This is already done, isn't it Noah? At least, the old stuff isn't where it used to be and I didn't see it with the n... Greg Farnum
04:25 PM Linux kernel client Cleanup #2085: kclient: improve mtime update in page_mkwrite
Talk to me about this; what kind of an issue is it (and does it still apply)? Greg Farnum
04:18 PM CephFS Feature #118: kclient: clean pages when throwing out dirty metadata on session teardown
I can't find the referenced ticket anywhere. Anybody know what this is supposed to be and if it still applies? (I thi... Greg Farnum
04:10 PM devops Bug #7552 (Resolved): dregs of mkcephfs still live on
There are still references to mkcephfs in the code. These should be removed and replaced with ceph-deploy if appropri... Ian Colle
03:33 PM Bug #7549: Mon deadlock

I did add a -d to the vstart.sh invocation in the test/vstart_wrapper.sh script.
David Zafman
02:57 PM Bug #7549 (Won't Fix): Mon deadlock

I was running test/vstart_wrapped_tests.sh built from 60c9aafaf0ff033dca22606ea811c792f1cda781. It looks like mult...
David Zafman
02:04 PM Bug #7538 (Fix Under Review): librados: rados ls crashes on firefly due to segfault in ObjectIter...
https://github.com/ceph/ceph/pull/1322 Josh Durgin
11:39 AM devops Tasks #7230 (In Progress): Rebuild sync-agent packages for dumpling repo
Talked to Josh and he wants to get some more fixes in which should happen later this week. Sandon Van Ness
10:34 AM devops Tasks #7230: Rebuild sync-agent packages for dumpling repo
Packages are built but I need to test to make sure its working. Sandon Van Ness
10:20 AM Subtask #7548 (Resolved): Basic docs for Erasure Coding
"work in progress":https://github.com/ceph/ceph/pull/1362
Similar to what Greg created for tiering at http://ceph....
Neil Levine
10:18 AM Feature #7547 (Resolved): Basic docs for Cache Tiering functionality
The content at http://ceph.com/docs/master/dev/cache-pool/ is fine for the Firefly release. Can you liaise with John ... Neil Levine
09:46 AM Bug #7545: rados: notify was not recieved in ceph_test_rados_watch_notify with thrashing on emperor
this was from http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-24_19:00:20-rados-emperor-testing-basic-plana/99... Josh Durgin
09:46 AM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
This looks like it might just be a bug in the test. This is all the output from ceph_test_rados_watch_notify, with a ... Josh Durgin
07:15 AM CephFS Bug #7530: mds: failed anchor assert on replay
commit:7ba3200f1e91d803cdf84f96777641f7d18d3c01 Greg Farnum
05:22 AM rgw Bug #7543: rgw: off-by-one bug in rgw_trim_whitespace()
I've sent a pull request to fix this bug at https://github.com/ceph/ceph/pull/1321
Please help to review it.
Xiangyu Lv
02:38 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
There is an off-by-one bug in rgw_trim_whitespace(). It results in trimming off all characters with input like " t". Xiangyu Lv
01:08 AM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
MDS map contains CompatSet::FeatureSet Zheng Yan

02/25/2014

11:24 PM Bug #7542 (Resolved): ec misdirected op
OSD recomputes op target based on current OSDMap. With an EC pg, we can get this result:
1) client at map 512 sends...
Samuel Just
08:42 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
5a6cb3da201ce503b4aef1744c3dc15511d15a13 Samuel Just
12:33 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
11: (OSD::PeeringWQ::_process(std::list<PG*, std::allocator<PG*> > const&, ThreadPool::TPHandle&)+0x12) [0x6a5282]
...
Samuel Just
07:55 PM Bug #7406: Seg fault in find_object_context()in recent master rados run
David Zafman
07:52 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily
David Zafman
12:55 PM Bug #7535: Switching to classic scrub unnecessarily

This was primarily fixed by 7357b6ed4bbc6ef44a80640ffb7e1ddacab10b5e for tracker #7517.
David Zafman
12:10 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily

test/vstart_wrapped_tests.sh output:
pg[0.0( empty local-les=20 n=0 ec=1 les/c 20/20 14/14/6) [0,2,1] r=-1 lpr=14 ...
David Zafman
07:34 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
Created and on the index page. Sandon Van Ness
06:27 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
Zheng Yan
09:14 AM CephFS Bug #7530: mds: failed anchor assert on replay
config used was (suites/fs/thrash/): ceph/base.yaml ceph-thrash/default.yaml clusters/mds-1active-1standby.yaml debug... John Spray
09:09 AM CephFS Bug #7530: mds: failed anchor assert on replay
Crashed on first try, log at debug-mds=10 attached John Spray
07:04 AM CephFS Bug #7530 (In Progress): mds: failed anchor assert on replay
John Spray
03:47 PM Bug #6922 (Resolved): mon: do not allow unreasonable PG splitting
Sam merged this. Greg Farnum
01:40 PM Bug #6922: mon: do not allow unreasonable PG splitting
PR: https://github.com/ceph/ceph/pull/1316 Greg Farnum
03:14 PM Feature #7540 (Resolved): Spread out deep-scrubs to avoid I/O contention
Parallel deep-scrubs have the potential to cause client I/O contention. A mechanism to spread out deep-scrubs and mak... Brian Andrus
03:02 PM Feature #7288: Deep-scrub throttle
Actually, there's a reservation system which should prevent that. The primary must reserve a slot in itself and each... Samuel Just
02:19 PM Bug #7539 (Resolved): Firefly EC pool massive memory leak during writes
EC pools appear to leak memory rather badly during writes. Looks like messages aren't being properly cleaned up. Ma... Mark Nelson
01:59 PM Bug #7538 (Resolved): librados: rados ls crashes on firefly due to segfault in ObjectIterator::op...
as seen in: http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-23_23:02:27-rbd-firefly-testing-basic-plana/99242/... Josh Durgin
11:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
hmm.. the timestamps actually match, so the shard sync failure might be the culprit. Seems like a sync agent issue (a... Yehuda Sadeh
09:36 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
I think the real issue is here, the specific agent error looks like a red herring:... Yehuda Sadeh
11:06 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
This should be fixed in ceph-qa-chef. I will run a new ceph-deploy run on vps and see how it goes. Sandon Van Ness
07:33 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
On the vm I deployed when tracking this, it only took me a 'yum upgrade leveldb' or something similar. I would think... Joao Eduardo Luis
07:19 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
All Fedora tests are still failing. We need to address this as soon as possible. I am not sure what entails upgrading... Alfredo Deza
10:48 AM Bug #7448: os/FileJournal.cc: FAILED assert(fd >= 0)
Increasing the priority on this since we cannot seem to get passing tests for ceph-deploy for months. Alfredo Deza
07:25 AM CephFS Bug #7503: mds start and oops after access to cephfs
fine, ok for the ticket #7531.This one should be closed.
Yann Dupont
07:02 AM CephFS Feature #3863 (In Progress): implement a tool to lookup inode numbers without holding their path
John Spray
05:33 AM devops Bug #7356: Kill all while loops that will never end....
This is going to take some effort because there are over 100 while loops in teuthology that look dangerous.
The in...
Alfredo Deza
05:24 AM Bug #6101: ceph-osd crash on corrupted store
We applied the fix last week the crashing node.
The osd node now runs again, but see that the missing objects gets t...
Daniel Poelzleithner
02:39 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
The patch has been accepted in libvirt upstream: http://libvirt.org/git/?p=libvirt.git;a=commitdiff;h=60f70542f97805a... Wido den Hollander
12:34 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Hi Greg,
I got a chance to test against the fix in our cluster (the leaf folder has around 1000 files), there are tw...
Guang Yang

02/24/2014

10:31 PM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
Ah, it sounds like this is happening because the MDS doesn't currently have a good versioning system to prevent too-o... Greg Farnum
10:30 PM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
This'll be a little interesting because the MDS doesn't have local storage. Evaluate if feature sets are best stored ... Greg Farnum
10:11 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
... Greg Farnum
08:32 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The kmods are built from a common source RPM because ceph.ko and rbd.ko require libceph.ko to be built and available ... Ken Dreyer
08:29 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Having them in one package is fine for now, but on reflection I do think we are going to need to have these in separa... Neil Levine
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Ken Dreyer
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The packages only run depmod, and they leave modprobe to the user or to the tooling. So it sounds like we're good.
...
Ken Dreyer
03:42 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
mount.ceph and 'rbd map' will do the modprobe for the user if it's not already loaded, so there's no need for the pac... Josh Durgin
03:25 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Does the package install the module into the kernel or does the user have to do modprobe manually?
If it installs ...
Neil Levine
03:20 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
I've unified all three kmods into a single package, available on GitHub: https://github.com/kdreyer-inktank/ceph-kmod... Ken Dreyer
05:10 PM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
Sage Weil
03:16 PM CephFS Feature #4000: Design a migration path from using the AnchorTable to using lookup-by-ino
Did this already get done with Zheng's work to remove the AnchorTable? Greg Farnum
05:10 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
Sage Weil
05:09 PM CephFS Feature #3999 (Resolved): update CDir encoding
this was revved as part of zheng's omap stuff Sage Weil
04:15 PM Linux kernel client Cleanup #2847 (Resolved): libceph: osdmap definition is out of date
Sage Weil
04:15 PM Linux kernel client Feature #6991 (Resolved): support CEPH_FEATURE_OSDMAP_ENC
Sage Weil
02:07 PM rgw Bug #7526 (Resolved): "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-di...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98508... Yuri Weinstein
11:24 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Seems related to #7468 Yuri Weinstein
11:23 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98483
Error...
Yuri Weinstein
10:20 AM rgw Bug #6936 (Resolved): radosgw-admin allows same user to be created multiple times
Fixed for firefly, commit:53de64122b206d11aa42fd401f88f02f2908e942 Yehuda Sadeh
10:20 AM rgw Bug #6951 (Resolved): rgw: bucket re-create fails when cache is disabled
Fixed for firefly, commit:859ed33ed7f9a96f4783dfb3e130d5eb60c622dd Yehuda Sadeh
10:16 AM rgw Bug #6830 (Resolved): S3 CompleteMultipartUploadResult has empty ETag element
Fixed, commit:2b3e3c834cd0e8b890296fa2b92ebb5de01a1bc1 Yehuda Sadeh
10:15 AM rgw Bug #7064 (Resolved): S3 request to non-existent object in non-existent bucket results in 30 seco...
Fixed, commit:3ed68eb9fac9b3d0bf9111867d609f9ea08fb202 Yehuda Sadeh
09:58 AM devops Bug #7356 (In Progress): Kill all while loops that will never end....
Alfredo Deza
09:46 AM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Consistent on firefly as well - http://pulpito.front.sepia.ceph.com/teuthology-2014-02-22_23:02:06-rbd-firefly-distro... Yuri Weinstein
08:29 AM Bug #7504: Ceph does not specify python2
Yeah I was talking about the shebang.
I understand that you can't do anything but this situation sucks. Instead of d...
Alexandre BIQUE
07:28 AM Bug #7504 (Rejected): Ceph does not specify python2
Alfredo Deza
07:21 AM Bug #7504: Ceph does not specify python2
When you say that ceph scripts should 'use explicitly python2' you mean altering the shebang line?
There is no con...
Alfredo Deza
01:02 AM Bug #7521 (Won't Fix): Add more events (hold object context) to OpTracker to better analyze perfo...
This ticket is to help on the effort I sent to community for this - http://www.spinics.net/lists/ceph-users/msg07866.... Guang Yang
12:58 AM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
Zheng Yan

02/23/2014

11:24 PM Bug #7423: erasure code: ./rados get retrieves a larger object
As of "today":https://github.com/ceph/ceph/commit/24c89bf01c61ecedb3bc7045332c9ed0340b37dc instead of crashing it ret... Loïc Dachary
08:24 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
Hi Greg,
Thanks for the reply.
-bash-4.1$ sudo ceph --version
ceph version 0.76-874-g40bdcb8 (40bdcb88504aea6...
Zhi Zhang
08:10 PM Bug #7520: Lock contention during scrubbing which could potentially hang the OSD for a couple of ...
Pull request - https://github.com/ceph/ceph/pull/1309 Guang Yang
07:41 PM Bug #7520 (Resolved): Lock contention during scrubbing which could potentially hang the OSD for a...
We are using Ceph as object store (via radosgw) and each time the cluster starts doing scrubbing, the performance deg... Guang Yang
07:49 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
Sage Weil
03:07 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
EC pool scrub bug -- reproducible
2014-02-23 15:03:57.195155 7ffbe7183700 10 osd.1 341 dequeue_op 0x51c2b40 finish...
Samuel Just
07:16 PM Bug #7519 (Can't reproduce): upgrade: osd crash on cuttlefish -> v0.67.1 -> emperor
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-02-22_19:40:17-upgrade:dumpling-next---basic-plana/978... Sage Weil
07:00 PM Feature #7518 (Closed): Add inline attrs support to KeyValueStore
"header" is a structure play a role like inode in FileSystem. Attrs are accessed frequently by PG layer, make attrs i... Haomai Wang
04:29 PM Bug #6671: FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Someone (I think it was Sam Just) helped me on #ceph to replace this OSD and rebuild data that was missing, so we wor... Tom Lanyon
03:46 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
ubuntu@teuthology:/a/teuthology-2014-02-21_23:02:40-rgw-firefly-testing-basic-plana/96767
with full osd logs
Sage Weil
02:48 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
Sage Weil
01:02 PM Feature #7516 (Resolved): mon: reweight-by-pg
The reweight-by-utilization function is important for maintaining a tight distribution of utilizations across lots of... Sage Weil
12:54 PM Feature #7515 (Resolved): mon: 'osd crush reweight-subtree <name> <weight>'
The 'osd crush reweight ...' command only lets you reweight a single item. In a large cluster, it may be helpful to ... Sage Weil
12:21 PM Bug #7493 (Resolved): cephtool/pool_ops failure
commit:70d23b9a0ad9af5ca35a627a7f93c7e610e17549 Sage Weil
08:23 AM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
Sage Weil
07:54 AM Bug #7494 (Resolved): EC filter read op bug
Sage Weil
07:54 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
07:53 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Sage Weil
07:25 AM Bug #7491 (Resolved): rados api crashes
Sage Weil
07:21 AM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
Sage Weil
07:21 AM Feature #7514 (Resolved): qa: add ceph_test_objectstore to rados test suite
Sage Weil

02/22/2014

05:35 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:27 PM Bug #7513: PGLog::activate_not_complete: log.complete_to decrement typo
https://github.com/ceph/ceph/pull/1300 Samuel Just
05:25 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:19 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
merged Samuel Just
01:48 PM Bug #7511 (Fix Under Review): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Sage Weil
12:29 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
OSD::project_pg_history needs to take into account up_primary/acting_primary -- testing.
2014-02-22 01:48:56.31806...
Samuel Just

02/21/2014

09:15 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
... Sage Weil
09:05 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
ha, this apears to be what is breaking the unit tests on firefly/master:
http://gitbuilder.sepia.ceph.com/gitbuilder...
Sage Weil
04:21 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Experiment:
ceph osd set noup
ceph osd down 1
<osd 1 is down>
ceph osd unset noup
Expected:
<osd 1 is back u...
Dan Mick
07:32 PM Bug #6685 (Resolved): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
a9677e136ee4753b86ed1151ca6ff08e4b63473d David Zafman
07:22 PM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")

The fix 545135f3e1c75318940caa2c82ac32a53fc4f957 went in because it was thought that a race was occurring betwe...
David Zafman
02:15 PM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
03:15 PM CephFS Bug #7503: mds start and oops after access to cephfs
Ok for explanation, and as already said, all that data was test data, so I can loose it without problems. I also full... Yann Dupont
08:45 AM CephFS Bug #7503: mds start and oops after access to cephfs
MDS is getting an ENFILE (object lost) from the OSD while trying to read the OMAP from one of its stray directory obj... John Spray
07:18 AM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
this is a follow up to http://tracker.ceph.com/issues/7367, which explain the scenario.
I now attach the mds.log
Yann Dupont
02:39 PM Messengers Bug #5508 (Can't reproduce): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
Sage Weil
02:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
Sage Weil
02:37 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
Sage Weil
02:37 PM Bug #6671 (Can't reproduce): FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Sage Weil
02:36 PM Bug #6636: sockaddr_storage and uuid_t are not portable to other platforms
Sage Weil
02:35 PM Bug #6730 (Won't Fix): BUG: MAX_LOCKDEP_ENTRIES too low!
Sage Weil
02:35 PM Bug #6333 (Closed): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
See #6278 for teh snaptrimmer portion of this. the rest is somewhere between resolved, need more info, and can't repr... Sage Weil
02:33 PM Bug #6806: mon: audit cmd_getval() calls to make sure they handle failures correctly
this patch is still sitting in wip-6796-b Sage Weil
02:33 PM Bug #6633 (Resolved): osd: pgls vs osd restart/peering race misses objects
Samuel Just
02:32 PM Bug #6787: upstart is restarting daemons which we want to be dead
Sage Weil
02:30 PM Bug #7120 (Need More Info): osd: EEXIST on mkcoll on dumpling
Sage Weil
02:29 PM Bug #7170 (Can't reproduce): rados api test LibRadosMisc.CopyPP failed on next branch
Sage Weil
02:29 PM Bug #7172 (Resolved): osd: OSD failed to start with osd_leveldb_cache_size > 0
Samuel Just
02:29 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
Sage Weil
02:28 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
Samuel Just
02:28 PM Bug #7376 (In Progress): mon: >10s spent in remove_redundant_pg_temp
Sage Weil
02:28 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
Sage Weil
02:24 PM Bug #7068 (Need More Info): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.s...
Sage Weil
02:21 PM Bug #7072: logrotate not sending HUP signal
Sage Weil
02:20 PM Bug #7145 (Can't reproduce): PG::update_snap_map assert
Sage Weil
02:19 PM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
Sage Weil
02:18 PM Bug #7248: osd: bench set max size
Sage Weil
02:17 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
It looks like you've got an older ceph tool installed locally. Can you validate that the versions match? (i.e., on th... Greg Farnum
02:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
Sage Weil
02:13 PM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
Sage Weil
02:13 PM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
Sage Weil
02:12 PM Bug #7393 (Need More Info): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0...
Sage Weil
02:12 PM Bug #7458: osd: stray pg ref on shutdown
perhaps that pg work queue PGBackend implementation can use? Samuel Just
02:11 PM rbd Bug #7385 (In Progress): Objectcacher setting max object counts too low
Sage Weil
02:10 PM Bug #7398 (Need More Info): osd: ERANGE from clone
Sage Weil
02:09 PM Bug #7491 (In Progress): rados api crashes
Sage Weil
02:09 PM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
09:36 AM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
wip-7506 Samuel Just
09:35 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
simple fix, ECTransaction needs to require hash_infos for deletions and stashes.
-6> 2014-02-20 22:47:44.48251...
Samuel Just
02:09 PM Bug #7494: EC filter read op bug
Sage Weil
02:08 PM Bug #7496 (Need More Info): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
Sage Weil
02:08 PM Bug #7498 (Need More Info): stuck in recovery
Sage Weil
02:08 PM Bug #7497 (Need More Info): timeout waiting to go clean
Sage Weil
02:08 PM Bug #7495 (Need More Info): ENOTEMPTY on collection remove
Sage Weil
01:58 PM Bug #7463: ceph-rest-api fails to start with no OSDs up
Dan fixed in db88e7f385f4464f5f4de517845607391c314ef5 Brian Andrus
01:08 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
This is pretty consistent in the rbd runs - 0 vs 1 dirty objects in each of these failures: http://pulpito.front.sepi... Josh Durgin
11:57 AM Bug #7508: 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burnupi09.front...
wip-7508 Samuel Just
11:57 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Objecter doesn't take primary position into account.
2014-02-20T21:16:09.130 INFO:teuthology.task.rados.rados.0.ou...
Samuel Just
10:23 AM rbd Feature #7507 (New): krbd: Make device symlinks cluster aware
Currently when a device is mapped a udev script creates a symlink at /dev/rbd/<pool>/<imagename>
Would be nice if ...
Tyler Brekke
09:29 AM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
Ian Colle
07:22 AM Bug #7367: fail to run mds and mount rbd (v0.76)
OK, so see #7503, http://tracker.ceph.com/issues/7503.
Also see #7368, http://tracker.ceph.com/issues/7368 which...
Yann Dupont
09:02 AM Bug #7504 (Rejected): Ceph does not specify python2
Hi,
Ceph fails on archlinux because it uses python and not python2.
On Archlinux, python = python3 and to use pyt...
Alexandre BIQUE
08:30 AM CephFS Bug #7485 (Fix Under Review): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
John Spray
08:29 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)
https://github.com/ceph/ceph/pull/1283 John Spray
08:14 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)

MDS -1 gid 1 starts in BOOTING, sends a beacon
MON prepare_beacon records its existence and puts it into state STA...
John Spray
07:12 AM devops Bug #7486: python-backports needs fixing for rhel

Sheldon Mustard
12:48 AM rgw Bug #7502 (Rejected): S3 API - deleting object always returns 204 regardless of object is existin...
When using S3 API, deleting object always returns 204 regardless of object is existing or not. This is reproducible. ... Zhi Zhang

02/20/2014

10:42 PM Support #7501 (Closed): Firefly - monitor hangs when ceating EC pool with latest code in master/f...
We are so eager to test out the Firefly erasure coding features even before the RPM packages being released. Here we ... Zhi Zhang
09:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
pull request is #1280 for wip branch wip-7374-wusui Anonymous
09:22 PM rgw Bug #7374: s3_multipart_upload.pl fails
This has been pushed in its own branch to wip-7374-wusui Anonymous
09:28 PM rgw Bug #7375: s3_user_quota.pl fails
Pull request is #1279 for wip branch wip-7375-wusui Anonymous
09:21 PM rgw Bug #7375: s3_user_quota.pl fails
this has been pushed in its own branch to wip-7375-wusui
Anonymous
05:47 PM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
Dan Mick
05:05 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
04:27 PM rgw Bug #7499 (Resolved): rgw: bucket unlink / link isn't working
bucket link doesn't work, as we're not able to specify the bucket instance to be linked. We need to think whether we ... Yehuda Sadeh
02:48 PM Bug #7498 (Resolved): stuck in recovery
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91241
- exec:
client.0:
...
Samuel Just
02:46 PM Bug #7497: timeout waiting to go clean
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91236 Samuel Just
02:45 PM Bug #7497: timeout waiting to go clean
We might just increase the timeout for rados bench runs. Samuel Just
02:44 PM Bug #7497 (Can't reproduce): timeout waiting to go clean
2014-02-20T07:02:16.913 INFO:teuthology.task.radosbench.radosbench.0.err:[10.214.132.16]: 2014-02-20 07:02:16.911765 ... Samuel Just
02:40 PM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
-6> 2014-02-20 02:51:46.869695 7f9b5302e700 5 osd.0 pg_epoch: 152 pg[4.3( v 152'3174 (15'171,152'3174] local-les... Samuel Just
02:39 PM Bug #7495 (Resolved): ENOTEMPTY on collection remove
"can_rollback_to": 12}}]}
2014-02-20 06:28:11.741673 7fcba3c5c700 -1 os/FileStore.cc: In function 'uns...
Samuel Just
02:33 PM Bug #7494 (Resolved): EC filter read op bug
-4> 2014-02-20 00:12:48.296974 7f1623101700 5 -- op tracker -- , seq: 39278, time: 2014-02-20 00:12:48.295450, e... Samuel Just
02:24 PM Bug #7493 (Resolved): cephtool/pool_ops failure
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90946
{description: 'rados/si...
Samuel Just
02:18 PM Bug #7491 (Resolved): rados api crashes
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90865
2014-02-19T23:44:36.621...
Samuel Just
02:18 PM Bug #7490 (Closed): [docs] adding monitor section doesn't specify the need for the admin keyring
The documentation to add monitors manually does not note that the admin keyring file needs to be present
when adding...
Alfredo Deza
01:42 PM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
While attempting to add a monitor that already was in the cluster with a specific IP, instead of
reporting the actu...
Alfredo Deza
10:52 AM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
this came down to a crush flaw. there is a new tunable to address it in firefly, although it will remain off for the... Sage Weil
09:49 AM rgw Feature #7467: Make radosgw work with multiple hostnames
Yehuda Sadeh
09:20 AM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
Yehuda Sadeh
09:19 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
actually, seems that the original code is post dumpling. Yehuda Sadeh
09:13 AM rgw Bug #7453 (Pending Backport): Authentication to keystone using rgw_keystone_admin_* failed
Pushed, commit:5fb90a2f6dd5b31634efc748a977924dbdbebcb9 Yehuda Sadeh
08:11 AM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
New signed off patch Mouad Ben
08:48 AM rados-java Bug #7488: "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Yuri Weinstein wrote:
> Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing...
Yuri Weinstein
08:46 AM rados-java Bug #7488 (Rejected): "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing-basic-plana/88201
err...
Yuri Weinstein
07:20 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
See the thread "[ceph-users] ceph-mon segmentation fault"... Greg Farnum
06:48 AM devops Bug #7486 (Rejected): python-backports needs fixing for rhel
Getting warnings
/usr/lib/python2.6/site-packages/babel/__init__.py:33: UserWarning: Module backports was already ...
Sheldon Mustard
06:23 AM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)

Pretty easy to reproduce: start MDS for first time on fresh cluster (I'm using vstart here), ctrl-c it promptly, tr...
John Spray
02:45 AM Bug #7367: fail to run mds and mount rbd (v0.76)
yes, please Zheng Yan
02:33 AM Bug #7367: fail to run mds and mount rbd (v0.76)
I think this bug can be closed as we're probably not in a supported scenario.
I've been able to backup all my RBD ...
Yann Dupont

02/19/2014

10:14 PM CephFS Bug #6608: samba teuthology dbench failure
We're still occasional samba test failures, but I haven't diagnosed them carefully enough to know if they're this fai... Greg Farnum
07:23 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
are you using 3.8 kernel? if you are, please try 3.12 or 3.13 Zheng Yan
01:07 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I'm on Ubuntu 13.10 and I've installed the packages distributed with it (ceph-deploy 1.2.3-0ubuntu1 and `ceph` 0.67.4... Peter Waller
05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
aa110af991e6d637b30d740af46f3dc2168cde01 Samuel Just
03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
wip-copyget Samuel Just
11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
Samuel Just
05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
Anonymous
05:20 PM rgw Bug #7375: s3_user_quota.pl fails
This is the same issue as 7374. Anonymous
02:16 PM rgw Bug #7375: s3_user_quota.pl fails
This appears to be a problem in the 7375 pl script. I am taking it. Anonymous
05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
I have pushed a change for this. Anonymous
02:15 PM rgw Bug #7374: s3_multipart_upload.pl fails
This appears to be two problems in the s3_multipart_upload.pl script.
I am taking this.
Anonymous
04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
The last call will end with abort()... Loïc Dachary
01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
... Loïc Dachary
10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
Loïc Dachary
06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
crashes on master as of today Loïc Dachary
02:40 PM Bug #7471: ec pools copyfrom broken
wip-copyget Samuel Just
02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Samuel Just
11:41 AM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Mon uses acting[0] to send create messages. More importantly, pg_stat_t does not include acting_primary or up_primar... Samuel Just
01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
This is already done (CORS). Yehuda Sadeh
01:34 PM Feature #7484 (New): better wording when authentication fails
After having a mismatch for the client.admin.keyring in a new host that I needed to get a monitor running I was getti... Alfredo Deza
01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
Yehuda Sadeh
01:33 PM rgw Tasks #5121 (Closed): bump up librados version
Closing this one. Yehuda Sadeh
01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7 Yehuda Sadeh
01:30 PM rgw Bug #6710 (Resolved): radosgw init script does not exit 1 and tell the user if the hostname does ...
This was fixed, commit:0c610918c4ebd6fc1376027cfe6425cfdcfa0245 Yehuda Sadeh
01:29 PM devops Bug #7483 (Rejected): ceph-deploy should fetch keyrings always
If keyring files exist in the cwd and they are dated/wrong ceph-deploy will say it has them and will not attempt to r... Alfredo Deza
01:28 PM rgw Feature #5136 (Closed): rgw: revise user stats
Yeah, I have no idea what this issue is about. Now, considering that user stats have actually been revised for the us... Yehuda Sadeh
01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
There's a good chance that this was #7030. Closing. Yehuda Sadeh
01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd Yehuda Sadeh
01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
Fix looks fine to me. Can you sign-off it? Yehuda Sadeh
10:29 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
subusers are only relevant for the swift case, and the regular access-key/secret combination does not apply to them. ... Yehuda Sadeh
10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
Yehuda Sadeh
10:19 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
So these packages were on the DVD (iso downloaded from https://rhn.redhat.com/rhn/software/channel/downloads/Download... Sandon Van Ness
10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
Yehuda Sadeh
09:35 AM rados-java Bug #7479 (Won't Fix): Test failed in rados-dumpling-testing-basic-plana
Logs are in - qa-proxy.ceph.com/teuthology/teuthology-2014-02-18_19:00:09-rados-dumpling-testing-basic-plana/89421
...
Yuri Weinstein
08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
Yehuda Sadeh
08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
Yehuda Sadeh
08:06 AM Bug #7451: updatedb will index /var/lib/ceph
This should also be reported to mlocate upstream (at Fedora) and to Red Hat for RHEL 7.
Here's the upstream update...
Ken Dreyer
07:53 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
This was an issue with the osd, fixed by commit:2795339d3632df975486d51e69762f9f567fb43d. Yehuda Sadeh
06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
crashes, investigating why Loïc Dachary
05:09 AM Bug #7445 (Rejected): missing feature bit ( next )
LD_LIBRARY_PATH was set to /usr/local/bin which contained an old version of the ceph libraries, causing the problem Loïc Dachary
04:24 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
Just a note, bug itself is very unlikely to reproduce in a short times (one crash per 1k VM instances per month or so). Andrey Korolyov
01:35 AM devops Feature #7475 (Rejected): ceph-disk: prepare should be idempotent
If the target device / directory is already prepared exactly as required, ceph-disk prepare should return true with a... Loïc Dachary

02/18/2014

11:07 PM CephFS Bug #6608: samba teuthology dbench failure
still see the issue ? Zheng Yan
10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
wip-strays Samuel Just
07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
1d907c60d7628429292917fbabf61d09ef8dfa6f Samuel Just
04:15 PM Bug #7469: ENXIO on ec pool write
Samuel Just
04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
testing wip-primary Samuel Just
07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
Stopping the teuthology run and running the commands manually reveals the following:... Anonymous
06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
Yehuda Sadeh
05:09 PM rbd Bug #6480 (Need More Info): librbd crashed qemu-system-x86_64
...and now there's a new similar instance, this time on rhel:... Josh Durgin
12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
Ian Colle
04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
03:46 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Moving to the ceph project since any scrub errors are general rados problems. Josh Durgin
03:33 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Yuri Weinstein wrote:
Logs - qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-master-testing-basic-...
Yuri Weinstein
03:30 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
There are several of those.
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-maste...
Yuri Weinstein
03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d Yehuda Sadeh
03:10 PM rgw Feature #7467 (Resolved): Make radosgw work with multiple hostnames
A ceph user has a situation in which they would like to switch to a new hostname for accessing the gateways. At the t... Brian Andrus
02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
Yehuda Sadeh
09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
Yehuda Sadeh
02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
commit:609f4c56718d8279895b02b8163bbe1976c02bfb Josh Durgin
02:21 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
The recently added timeouts for librados should result in a specific exception type in the python bindings. Josh Durgin
01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:07 PM Bug #7463 (Fix Under Review): ceph-rest-api fails to start with no OSDs up
No reason not to start. This appears to fix it:... Dan Mick
11:26 AM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
ceph-rest-api fails to start id it can find no up OSDs:
osdid = find_up_osd(app)
File "/usr/lib/python2.6/sit...
Brian Andrus
12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
Ian Colle
12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
Ian Colle
12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
Ian Colle
12:45 PM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
This was observed on a 3.11 ubuntu kernel:... Josh Durgin
12:40 PM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
backported in commit:4e47a003bb3adcee690067d4037c248a93023c20 a while ago Josh Durgin
12:37 PM Feature #7464 (Rejected): Backport appropriate pieces of #7394, #7395
We put some fixes for OSDs overwhelming the monitor into master; now they need to get backported to Dumpling. Greg Farnum
12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e Greg Farnum
11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
Samuel Just
11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
Samuel Just
11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
Samuel Just
11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7366 (Resolved): EC: scrubbing
Samuel Just
11:01 AM Feature #7366: EC: scrubbing
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
Not desirable for final design Samuel Just
11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b Yehuda Sadeh
09:29 AM rgw Bug #7346 (Pending Backport): An unfound object as part of multi-object delete should return dele...
A fix was pushed, commit:8ca3d95bf633ea9616852cec74f02285a03071d5. Yehuda Sadeh
08:54 AM Bug #7451: updatedb will index /var/lib/ceph
Sage Weil wrote:
> I'm not sure the init script is the place to do it.. maybe the package postinst?
postinst is n...
Dietmar Maurer

02/17/2014

11:56 PM RADOS Bug #7460 (New): librados: no test for c api's global ops flags
This could be tested by creating a binary just for testing that enables logging, sets some global op flags, and grepp... Josh Durgin
04:28 PM Feature #7459 (Closed): ceph-rest-api: sysvinit and upstart scripts
enumerate daemon by directory in /var/lib/ceph/rest, using the same structure as the osd, mon, and other daemons.
...
Sage Weil
03:44 PM Bug #7458: osd: stray pg ref on shutdown
Sage Weil
03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
... Sage Weil
03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
http://pulpito.ceph.com/teuthology-2014-02-14_23:00:16-rados-master-testing-basic-plana/84322
http://pulpito.ceph.co...
Sage Weil
02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
Sage Weil
02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
Sage Weil
02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
Sage Weil
02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
Sage Weil
02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
Sage Weil
01:39 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
Simplest thing seems to be to unconditionally send temp object ops to the backfill targets. Then the final completio... Sage Weil
01:37 PM CephFS Bug #7422 (In Progress): client/barrier.h uses boost's interval set library, which is not availab...
The barrier code has been disabled to fix the build. Matt said he will follow up. http://marc.info/?l=ceph-devel&m=... Sage Weil
01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
Sage Weil
01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
Sage Weil
01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
reopened #7385 Sage Weil
01:33 PM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
This now leaks memory.. presumably stray Object's the cache that never get cleaned up.
Let's just increase the obj...
Sage Weil
01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
Sage Weil
01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
when this is complete, be sure to fix ceph-qa-suite.git Sage Weil
11:08 AM Bug #7212 (Pending Backport): monitor fails to start
Sage Weil
10:34 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
The problem is in rgw_user.h:void set_subuser(..) sets 'gen_access = true;'. I can't understand why it's doing that, ... Robin Johnson
08:44 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
Pavel Veretennikov wrote:
> * Strange that it worked without permission. Where had it stored the data?
It was onl...
Sage Weil
07:32 AM CephFS Bug #7424: Cannot read from zero-length file
* Strange that it worked without permission. Where had it stored the data? Pavel Veretennikov
07:31 AM CephFS Bug #7424: Cannot read from zero-length file
Yes, the problem resolved after I gave client access to default data pool
rwx pool=data
Strange that it work...
Pavel Veretennikov
06:52 AM CephFS Bug #7424: Cannot read from zero-length file
does client have permission permission to access the data pool? try using admin's keyring to mount the fs. Zheng Yan
01:19 AM CephFS Bug #7424: Cannot read from zero-length file
Ubuntu doesn't use SELinux as I know. /selinux lib is empty, only one related selinux package is present - libselinux... Pavel Veretennikov
05:43 AM devops Feature #7454 (Resolved): ceph-disk: support osd removal / ceph-disk remove
There should be a *ceph-disk remove* to cleanup an OSD and the associated device / directory. This is not something a... Loïc Dachary
05:35 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
If you supply rgw_keystone_admin_user and rgw_keystone_admin_password ... instead of supplying "rgw_keystone_admin_to... Mouad Ben

02/16/2014

10:43 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
Zheng Yan
09:57 PM CephFS Bug #7372: kcephfs: pjd tests fail
well, as far as i can tell, the pjd tests also fail on ext4 in the same way they do on ceph:... Sage Weil
09:46 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
we missed the backport of commit:b1976dd00f5b29c01791272f63a18250319f2edb Sage Weil
09:09 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
it seems to have been failing for a while, too:
http://pulpito.ceph.com/compare/?branch=dumpling&suite=rgw&count=1...
Sage Weil
08:56 PM Bug #7451 (Resolved): updatedb will index /var/lib/ceph
See http://git.openvz.org/?p=vzctl;a=commitdiff;h=47334979b9b5340f84d84639b2d77a8a1f0bb7cf for one example of a packa... Sage Weil
08:22 PM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
And this bug exists at least as far back as 0.72. I need a fix/workaround asap, to migrate users+subusers between two... Robin Johnson
08:20 PM rgw Bug #7450 (Resolved): "radosgw-admin key create" ignores specified access key when subuser specified
If I create to create an explicit accesskey/secret key combo, and specify a subuser, then the access key is not used.... Robin Johnson
08:27 AM Bug #7371 (Pending Backport): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ...
Sage Weil
06:33 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
Zheng Yan
01:39 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
I applied following patch... Zheng Yan
04:38 AM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
Triggered while running the ceph-deploy suite on next, on debian (http://pulpito.ceph.com/sage-2014-02-15_17:05:48-ce... Joao Eduardo Luis

02/15/2014

10:36 PM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
Sage Weil
10:19 PM Bug #7188 (Pending Backport): Admin socket files are lost on log rotation calling initctl reload ...
merged into next. want to wait a bit before backporting. Sage Weil
03:13 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
"dumpling backport":https://github.com/ceph/ceph/pull/1248 Loïc Dachary
03:11 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
"emperor backport":https://github.com/ceph/ceph/pull/1247 Loïc Dachary
02:55 AM Bug #7188 (Fix Under Review): Admin socket files are lost on log rotation calling initctl reload ...
"work in progress":https://github.com/ceph/ceph/pull/1246 Loïc Dachary
06:48 PM Bug #7447 (Resolved): osd: copy_from temp objects interact awkwardly with backfill
We decide whether to send the operation based on the object named in the repop, but the temp objects do not get backf... Samuel Just
06:07 PM CephFS Bug #6791 (Won't Fix): mds assert after startup - CDir::commit error (want > commited version)
Zheng Yan
05:00 PM Feature #7058 (Resolved): osd primary affinity
Sage Weil
04:27 PM Bug #7445 (Need More Info): missing feature bit ( next )
Is it worth investigating the current failure of next on make check ? It will probably go away when master is merged ... Loïc Dachary
04:23 PM Bug #7445: missing feature bit ( next )
next is missing "osd crush rule create-erasure":https://github.com/ceph/ceph/commits/cb39b1367676215fc244664d83ffb3e2... Loïc Dachary
04:03 PM Bug #7445 (Rejected): missing feature bit ( next )
On ea6dc997668df98c0a553d677cf22850b476e412 running *test/mon/osd-pool-create.sh* blocks... Loïc Dachary
04:01 PM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
"revert due to accidental merge of a DNM":https://github.com/ceph/ceph/pull/1249 Loïc Dachary

02/14/2014

03:45 PM Bug #7188 (In Progress): Admin socket files are lost on log rotation calling initctl reload (ubun...
Steps to reproduce:... Loïc Dachary
03:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
From a fresh install of "ubuntu 13.04":http://mirrors.ircam.fr/pub/ubuntu/releases/raring/ubuntu-13.04-server-amd64.i... Loïc Dachary
02:37 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
ceph-osd "installs a sighup handler":https://github.com/ceph/ceph/blob/emperor/src/ceph_osd.cc#L477 which "reopens lo... Loïc Dachary
12:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
Not sure if I can fix it but I'll give it a shot. Loïc Dachary
02:12 PM Feature #7442 (Resolved): mon: health warn on pg "full"
Sage Weil
02:09 PM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
Sage Weil
02:04 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
01:59 PM RADOS Feature #7440 (New): erasure-code: adapt scrub/repair teuthology tests for EC and add to nightly
Samuel Just
01:58 PM Feature #7439 (Resolved): EC: adapt unfound teuthology tests and add to nightly for EC
Samuel Just
01:58 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
Samuel Just
01:57 PM Feature #7437 (Resolved): EC: add adapt unittest teuthology task and add to nightly
Samuel Just
01:42 PM devops Feature #7293: packaging: enable qemu to find librbd on rhev or rhel-osp
Neil Levine
01:41 PM devops Feature #7436 (Rejected): Build and test RHEL on same subversions.
Ian Colle
01:39 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
Ian Colle
01:38 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
Removed requirement for SLES/OpenSuse. Therefore, completed. Ian Colle
01:33 PM devops Feature #7046 (Resolved): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
Ian Colle
01:31 PM rgw Documentation #7434: rgw: doc user/group quota
John: can you please provide feedback to Yehuda on where he should put the new docs about the user quotas. Neil Levine
01:06 PM rgw Documentation #7434 (Resolved): rgw: doc user/group quota
Sage Weil
01:05 PM rgw Feature #6339: rgw: compact manifest data
Ian Colle
01:05 PM rgw Feature #6338: rgw: better manifest scaling
Ian Colle
11:53 AM rgw Feature #6513 (In Progress): rgw: dr: Service scripts for meta/data sync agents
Josh Durgin
11:23 AM devops Bug #7427: sha1 does not exist on gitbuilder, install fails
This happened because the build failed on the rpm gitbuilder. It actually looks like many of the last few master buil... Sandon Van Ness
09:13 AM devops Bug #7427 (Resolved): sha1 does not exist on gitbuilder, install fails
... Alfredo Deza
11:13 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
After investigating what was returning this message:... Alfredo Deza
11:05 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
Merged into ceph-deploy master branch 348bf8c Alfredo Deza
07:53 AM devops Bug #7390 (Fix Under Review): ceph-deploy should remove ceph-release and call yum clean all
Pull request opened https://github.com/ceph/ceph-deploy/pull/163 Alfredo Deza
09:26 AM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
When deploying monitors on fedora 19 VMs, the monitors fail to mkfs due to some segfault. This happens regardless of ... Joao Eduardo Luis
09:04 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:23:01-rgw-dumpling-master-basic-plana/81039/
<...
Yuri Weinstein
08:20 AM Bug #7406: Seg fault in find_object_context()in recent master rados run
I don't think snaps should ever be empty.. if it is, there is a bug somewhere that is causing it. On the one hand no... Sage Weil
08:10 AM rados-java Bug #7425 (Rejected): Error in run_seed_to_range.sh for rados-dumpling-master-basic-plana
Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:24:10-rados-dumpling-master-basic-plana/81235/
...
Yuri Weinstein
06:25 AM CephFS Bug #7424: Cannot read from zero-length file
do you have selinux enabled Zheng Yan
02:16 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
Ubuntu 12.04 LTS 3.8.0-35-generic x64
Ceph 0.72.2-1precise from http://ceph.com/debian-emperor/
cluster b8...
Pavel Veretennikov
02:04 AM Bug #7423: erasure code: ./rados get retrieves a larger object
On "ecbackend-8":https://github.com/ceph/ceph/tree/wip-ecbackend-8 it fails in the same way ( the crash does not happ... Loïc Dachary
01:29 AM Bug #7423: erasure code: ./rados get retrieves a larger object
Loic Dachary wrote:
> While playing with "ECBackend pull request":https://github.com/ceph/ceph/pull/1228
> [...]
>...
Loïc Dachary
01:28 AM Bug #7423 (Resolved): erasure code: ./rados get retrieves a larger object
"work in progress":https://github.com/ceph/ceph/pull/1327
Steps to reproduce:...
Loïc Dachary
12:45 AM CephFS Bug #7422 (Resolved): client/barrier.h uses boost's interval set library, which is not available ...
http://gitbuilder.sepia.ceph.com/gitbuilder-centos6-amd64/log.cgi?log=9cbbc883e225b08b3e31cd2cf6e766688795886b
Thi...
Josh Durgin

02/13/2014

10:27 PM Bug #7420: posix_fallocate failed under CentOS 6.5 when DIO enabled
posix_allocate in FileJournal::_open_file will call pread to pre-allocate space which will return 22 because unalgine... Haomai Wang
10:19 PM Bug #7420 (Won't Fix): posix_fallocate failed under CentOS 6.5 when DIO enabled
under CentOS 6.5, when enable DIO and initialize OSD directory will cause failed:
2014-02-14 05:46:15.591387 7ffff...
Haomai Wang
07:41 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
Recent change is causing 2GB VM KVM processes to consume up to 5GB of memory during heavy write workload. Sage think... Mark Nelson
04:43 PM devops Bug #7417 (Resolved): libleveldb1 missing in debian-testing
The libleveldb1 package is listed as a dependency for precise/testing (http://ceph.com/debian-testing/dists/precise/m... Noah Watkins
03:38 PM Bug #7406 (Fix Under Review): Seg fault in find_object_context()in recent master rados run
Pushed wip-7406 David Zafman
11:28 AM devops Bug #7390 (In Progress): ceph-deploy should remove ceph-release and call yum clean all
Alfredo Deza
10:38 AM rados-java Bug #7413 (Rejected): LibRadosTier.FlushTryFlushRaces failed on rados:basic-wip-agent-testing-bas...
Logs are in sage-2014-02-12_13:47:37-rados:basic-wip-agent-testing-basic-plana/79327... Yuri Weinstein
10:30 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
3e473d4237697872498094b41fed19b414f8d3c4 David Zafman
10:06 AM Bug #7212 (Fix Under Review): monitor fails to start
patch bb863b73c45ce5592844c2c72028ef1cfd9647f8 ; pull request: https://github.com/ceph/ceph/pull/1236 Joao Eduardo Luis
07:49 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
Merged into ceph dumpling branch with hash 1c42a6e Alfredo Deza
06:48 AM devops Bug #7334: ceph-disk: cannot run partprobe on used devices with EL6
Created branch dumpling-7334 and got all dumpling ceph-deploy suite tests to pass http://pulpito.ceph.com/ubuntu-2014... Alfredo Deza
02:14 AM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
Sure, totally agree on the low priority. Florian Haas
12:52 AM Bug #7409 (Can't reproduce): "make check" doesn't work without --with-radosgw
It may looks like improper that we can't run "make check" by default configure which lack of "--with-radosgw".
tes...
Haomai Wang

02/12/2014

10:45 PM Bug #7222 (Won't Fix): init-ceph failed when cluster created by "mkcephfs" and start osd firstly ...
Haomai Wang
10:42 PM Bug #7222: init-ceph failed when cluster created by "mkcephfs" and start osd firstly and
mkcephfs won't add osd id to osdmap. So if cluster created by mkcephfs, it need to add "osd crush update on start = 0... Haomai Wang
06:46 PM rgw Bug #7374: s3_multipart_upload.pl fails
Also, use Amazon::S3 results in the same error message on a hello world perl script.
I got S3 installed via cpan (...
Anonymous
06:41 PM rgw Bug #7374: s3_multipart_upload.pl fails
Okay. I think that the Yaml file is okay. There appear to be make issues. The most noticable one is:... Anonymous
05:57 PM Bug #7408 (Resolved): filestore xattr use omap = true
will be in next dumpling point release. Sage Weil
05:52 PM Bug #7408: filestore xattr use omap = true
My code has been backported to Dumpling. So the filestore_xattr_use_omap will be gone from the next Dumpling release. David Zafman
04:08 PM Bug #7408: filestore xattr use omap = true
Let's see how we (Sage) decide to resolve #7404. I've created a pull request to backport my 6143 change completely. ... David Zafman
02:22 PM Bug #7408: filestore xattr use omap = true
As I understood Sage what's being done in Dumpling is to flip the default; if so then users still need a warning neve... Florian Haas
02:20 PM Bug #7408: filestore xattr use omap = true
We've generated a couple different tickets about this now that I think are crossing wires, but we're about to backpor... Greg Farnum
02:14 PM Bug #7408: filestore xattr use omap = true
David Zafman wrote:
> The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new...
Florian Haas
02:09 PM Bug #7408: filestore xattr use omap = true
The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new behavior is just like ... David Zafman
01:54 PM Bug #7408 (Resolved): filestore xattr use omap = true
At the core standup yesterday we talked about a really nasty bug where data loss can occur if filestore xattr use oma... Mark Nelson
04:42 PM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
The original rationale was to keep the existing behavior (not reading a conf file) and use None as a default value to... Josh Durgin
12:55 PM Bug #7407 (New): Illogical defaults in Python bindings: conffile=None loads no config, conffile='...
This feels weird:... Florian Haas
02:25 PM Fix #7394 (Fix Under Review): OSD: relax monitor ping requirements while connecting
PR: https://github.com/ceph/ceph/pull/1227 Greg Farnum
01:47 PM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
I believe this is fixed now. It appears it installed ok if you just did a yum install mod_ssl but once httpd and http... Sandon Van Ness
12:07 PM devops Bug #7283 (In Progress): centos 6 - gitbuilder mod_ssl broken dependency
I completley missed this issue bieng assigned to me. It looks like a simple issue with the dependency string containi... Sandon Van Ness
12:10 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
I haven't looked at any of the code involved for real, but that sounds like a good plan to me. *thumbs up* Greg Farnum
11:22 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
What's happening is that suicide() is getting called from another thread while the dispatch thread is inside _dispatc... John Spray
12:05 PM devops Bug #7334 (Pending Backport): ceph-disk: cannot run partprobe on used devices with EL6
Alfredo - please cherry pick to Dumpling Ian Colle
11:37 AM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
On commit 7fe10f1271dd94d4c5014a35c6362a7772dc4508
/a/teuthology-2014-02-09_23:00:13-rados-master-testing-basic-pl...
David Zafman
11:06 AM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Yeah -- I don't really want to open that can of worms either, and we'll add some extra hygiene here in Calamari.
B...
John Spray
10:30 AM Feature #7404: backport default filestore_use_omap and superblock checking to dumpling
The original change in master removed the filestore_xattr_use_omap variable. I checked current master branch and thi... David Zafman
10:08 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
Samuel Just
10:26 AM Bug #7345 (Need More Info): LibRadosTier.Evict failed in rados suite
Deferring this since there are a bunch of other outstanding changes to this code. Greg Farnum
10:17 AM Bug #7345 (In Progress): LibRadosTier.Evict failed in rados suite
This hasn't failed in the nightlies since then (although there are other related failures which Sage is looking at), ... Greg Farnum
09:54 AM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
Sage Weil
09:52 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
> > * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
>
> We haven't conf...
Florian Haas
09:47 AM RADOS Cleanup #7402 (New): OSD: audit osdmap_subscribe calls to remove forced subscription attempts
There are a number of places where the OSD subscribes to a map and forces the MonClient to renew its subscription. I ... Greg Farnum
09:43 AM Bug #5804 (In Progress): mon: binds to 0.0.0.0:6800something port
The 0.0.0.0 portion of the address is normal. Unless a monitor has a prebuilt monmap supplied at time of creation, al... Joao Eduardo Luis
09:40 AM Fix #7395 (Fix Under Review): OSD: update osdmap subscription proactively instead of when we want...
PR at https://github.com/ceph/ceph/pull/1223 Greg Farnum

02/11/2014

11:44 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Josh Durgin wrote:
> Hi Wido,
>
> Attached is a patch to use the timeouts with a libvirt storage pool. I noticed ...
Wido den Hollander
06:27 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Hi Wido,
Attached is a patch to use the timeouts with a libvirt storage pool. I noticed that libvirt will actually...
Josh Durgin
10:36 PM Bug #7401 (Resolved): rados bench takes into account second '0' for stddev calculation
For example:... Ivo Jimenez
08:39 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
To do additional debugging on this problem, I printed out my monmap with:
ceph mon getmap -o zzzz
got latest monm...
Eric Eastman
07:20 PM rgw Bug #7346 (Fix Under Review): An unfound object as part of multi-object delete should return dele...
Yehuda Sadeh
04:48 PM rgw Bug #7346 (In Progress): An unfound object as part of multi-object delete should return deleted i...
Yehuda Sadeh
04:49 PM rgw Bug #7271 (In Progress): container create via swift doesn't register ACL
Yehuda Sadeh
04:41 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
IMO this is a big can of worms having to do with Ceph itself; I'm willing to bet that *none* of the internal routines... Dan Mick
02:45 PM Fix #7395: OSD: update osdmap subscription proactively instead of when we want a new map
Waiting for the gitbuilders to build the branch so I can run it through thrashing. Greg Farnum
10:12 AM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
In most circumstances, the OSD does a one-time subscription for the "next map" from what it has. But in a few places,... Greg Farnum
01:14 PM rbd Bug #7385 (Fix Under Review): Objectcacher setting max object counts too low
https://github.com/ceph/ceph/pull/1215 Josh Durgin
06:07 AM rbd Bug #7385: Objectcacher setting max object counts too low
Does it make sense to be exposing this to librbd/client.cc at all vs just directly setting it via a config option? (o... Mark Nelson
12:48 PM Bug #6101: ceph-osd crash on corrupted store
(18:02:26) sage: poelzi: looks reasonable. can you make it log to the cluster log about the error, though? IIRC it ... Daniel Poelzleithner
01:31 AM Bug #6101: ceph-osd crash on corrupted store
Daniel Poelzleithner wrote:
> We deleted the rados block that was in the stack trace, but deleting it did not solve ...
Florian Haas
12:27 PM Bug #7398 (Resolved): osd: ERANGE from clone
ubuntu@teuthology:/a/teuthology-2014-02-10_23:01:27-rbd-master-testing-basic-plana/76311... Sage Weil
11:33 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
Florian Haas wrote:
> * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
...
Sage Weil
07:25 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
This issue has caused data corruption in at least one user (Inktank PS is well aware of this).
Since
* https://g...
Florian Haas
09:59 AM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
Right now, the OSD will time out a monitor after 30 seconds if it fails to ack a PGStats message. But sometimes, the ... Greg Farnum
09:53 AM Bug #7393 (Duplicate): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whit...
from new scrub before test teardown. Sage Weil
09:41 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
yay Sage Weil
09:41 AM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
Sage Weil
09:18 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
Loïc Dachary
12:18 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon

Line numbers are relative to b9a127e
src/client/Client.cc:113 is not safe
src/osdc/Objecter.cc:2509 i...
Loïc Dachary
06:36 AM devops Bug #7391 (Resolved): ceph-deploy should pass the verbose flag to ceph-disk
Any and all output from ceph-disk is useful, no need to be quiet about it because it makes it extremely hard
to debu...
Alfredo Deza
05:53 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
When uninstalling ceph (or when purging) not removing ceph-release and not calling yum clean all leaves yum in a terr... Alfredo Deza
01:55 AM Bug #7093: osd: peering can send messages prior to auth
I would like to add the following comment because I have learned that this is related to an issue we have seen in the... Florian Haas

02/10/2014

11:59 PM Cleanup #7388 (Closed): ceph osd find has no format argument
Although it appears to "handle a format argument":https://github.com/ceph/ceph/blob/v0.76/src/mon/OSDMonitor.cc#L2231... Loïc Dachary
08:53 PM devops Feature #6020: radosgw-apache opinionated package
For reference, Gary's WIP branch is here: https://github.com/ceph/ceph/tree/wip-6020 Ken Dreyer
08:06 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
> mon_lease_ack_timeout = 10
> mon_accept_timeout = 10
Thanks Sage! After changing the above configuration to 30, t...
Guang Yang
05:57 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
The (compiled) osdmap attached. Guang Yang
09:40 AM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
can you attach a copy of your osdmap so we can see what the time might be spent on?
in the meantime, you can incre...
Sage Weil
01:24 AM Bug #7376 (Resolved): mon: >10s spent in remove_redundant_pg_temp
We have a cluster which has 3 monitors, most recently, due to server restart (for both OSDs and Monitors), the cluste... Guang Yang
06:44 PM Bug #6101: ceph-osd crash on corrupted store
The patch removes the assert in case the trim event is done an a non existing context.
I think this is save and shou...
Daniel Poelzleithner
05:49 PM rgw Bug #7374: s3_multipart_upload.pl fails
I believe that this is a yaml file problem (Same issue as 7375). I am investigating. Anonymous
04:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
The problem could also be in the packaging Anonymous
04:27 PM rgw Bug #7374: s3_multipart_upload.pl fails
I've been looking at this. There may be a problem with the script in that a directory is not there that the script e... Anonymous
05:48 PM rgw Bug #7375: s3_user_quota.pl fails
I believe that the yaml files are not right here. This is probably a ceph-qa-suite problem. I am still investigatin... Anonymous
05:11 PM Feature #6507 (Resolved): librados shouldn't block indefinitely when cluster doesn't respond
merged in commit:32aa9fdf666063e4c5539b5e850f04af37e30b2e to master, backported to dumpling around commit:30dafacd0b5... Josh Durgin
03:52 PM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
"dumpling backport":https://github.com/ceph/ceph/pull/1210
"emperor backport":https://github.com/ceph/ceph/pull/1208
Loïc Dachary
03:12 PM Bug #7378 (Fix Under Review): ceph --format plain --admin-socket mon.asok crashes the mon
"work in progress":https://github.com/ceph/ceph/pull/1207
Loïc Dachary
09:55 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
For what it's worth, it's not a blocker for me. The "plain" format is documented to not being supported and it only h... Loïc Dachary
07:25 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
Steps to reproduce, from the src dir on todays master:... Loïc Dachary
03:46 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Urgh, redmine apparently can't cope with unicode either! Here's what the snipped should look like http://pastebin.co... John Spray
03:45 PM Bug #7387 (Resolved): Malformed JSON command output when non-ASCII strings are present

Ceph accepts non-ascii input when setting e.g. the name of a pool. Subsequently, when using human-formatted CLI ou...
John Spray
03:29 PM rbd Bug #7385: Objectcacher setting max object counts too low
This is set by librbd or ceph-fuse's Client.cc after creating the objectcacher. There's already a config option for C... Josh Durgin
03:19 PM rbd Bug #7385 (Resolved): Objectcacher setting max object counts too low
It appears that the objectcacher is setting max object counts based on the max dirty data size and object size. With... Mark Nelson
03:24 PM RADOS Documentation #7386 (Won't Fix): librados: document rados_osd_op_timeout and rados_mon_op_timeout...
These were added in https://github.com/ceph/ceph/pull/1192. They shouldn't be used generally, but are useful for libr... Josh Durgin
02:04 PM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
merged into ceph's master branch af5d0fc Alfredo Deza
12:36 PM devops Bug #7334 (Fix Under Review): ceph-disk: cannot run partprobe on used devices with EL6
pull request opened https://github.com/ceph/ceph/pull/1205 Alfredo Deza
01:42 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
I change the ceph-disk a little bit:
In mount_active, mount the disk using default mount options, then activate it t...
Kai Zhang
11:35 AM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
After the disk are prepared, udev notices the disk label and this rule calls ceph-disk-activate: https://github.com/c... Josh Durgin
09:51 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
... Alfredo Deza
08:58 AM Tasks #7377 (Resolved): security Certificate is out of date
Greg Farnum
07:49 AM Tasks #7377: security Certificate is out of date
Greg Farnum wrote:
> I think this should be resolved already, based on an email discussion.
Yes, thats correct. T...
gr kooi
06:45 AM Tasks #7377: security Certificate is out of date
I think this should be resolved already, based on an email discussion. Greg Farnum
01:39 AM Tasks #7377 (Resolved): security Certificate is out of date
The certificate of https://ceph.com/git/?p=ceph.git;a=blob_plain;f=keys/release.asc is ended yesterday (8-2-2014).
A...
gr kooi
05:32 AM Bug #7367: fail to run mds and mount rbd (v0.76)
Quick follow Up ;
with 0.76 OSD, MON, MDS: Creating new volume , formatting, mounting leads to normal comportment.
...
Yann Dupont

02/09/2014

09:01 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/ Sage Weil
09:01 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/ Sage Weil
08:57 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
My guess is that this is due to the new ACL code.
http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-08_23:05...
Sage Weil
03:59 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
Hi, I was trying to fix this today. But in my cluster, disk was activated automatically right after ceph-disk-prepare... Kai Zhang
03:05 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
... Sage Weil
03:02 PM Bug #7371 (Resolved): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
ubuntu@teuthology:/a/teuthology-2014-02-08_23:05:12-kcephfs-next-testing-basic-plana/73644
tasks:
- chef: null
-...
Sage Weil
10:38 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
see #7329 for the first two failures. Sage Weil
10:38 AM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
Sage Weil

02/08/2014

09:15 PM Bug #6003: journal Unable to read past sequence 406 ...
ubuntu@teuthology:/a/sage-2014-02-08_15:50:23-rados:thrash-wip-agent-testing-basic-plana/72854 Sage Weil
09:14 PM Bug #7329: osd: LibRadosTier.FlushTryFlushRaces failures
Sage Weil
04:14 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
"resolved by":https://github.com/ceph/ceph/pull/1201 Loïc Dachary
12:20 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
i broken crush tries behavior when refactoring in commit:27f4d1f6bc32c2ed7b2c5080cbd58b14df622607 Sage Weil
02:31 PM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
471c67828cf98224f89bd8efb28d377f8d745b7a Samuel Just
02:30 PM Feature #7366: EC: scrubbing
Samuel Just
02:30 PM Feature #7361: EC: arrange for chunks to have some padding where we can later add checksums
Samuel Just
01:56 PM devops Feature #5214: Kernel gitbuilders for rpm distros
Forgot to update this as it was getting pretty late last night. I got gitbuilders up for:
rhel7beta
rhel6 (6.5)
...
Sandon Van Ness
04:08 AM CephFS Feature #7352: mds: make classes encode/decode-able
It's maybe a bit less broad than it sounds (in my mind at least) -- I'm concentrating on the in-rados representations... John Spray
02:25 AM Subtask #5857 (Resolved): Refactor recovery to use PGBackend methods
Loïc Dachary
02:24 AM Subtask #5856 (Resolved): Refactor Backfill to use PGBackend methods
Loïc Dachary
01:39 AM Feature #7195: librados: complete C write object operation bindings
"implementation":https://github.com/ceph/ceph/commit/33717b4f60ce0ba7088164182b99eaf48cf0486f Loïc Dachary

02/07/2014

03:56 PM Bug #7368 (Can't reproduce): ceph osd repair * blocks after some minutes and prevent other ceph p...
Hello,
this is a follow up of http://tracker.ceph.com/issues/7367
An unfortunate update To 0.75 endend with lots ...
Yann Dupont
03:46 PM CephFS Feature #7352: mds: make classes encode/decode-able
This is...remarkably broad. Do we have an order of priorities or anything? :) Greg Farnum
03:45 PM CephFS Fix #7109 (Resolved): disallow removing the first data pool
Merged into master in commit:4cca38c Greg Farnum
03:39 PM Bug #7367: fail to run mds and mount rbd (v0.76)
Hello, all & thanks to loic for taking the time to make a bugreport.
The problem occured on one of my cluster, th...
Yann Dupont
02:19 PM Bug #7367: fail to run mds and mount rbd (v0.76)
Is this a CephFS or an RBD bug report?
(Perhaps it should be two different ones. :p)
Greg Farnum
02:16 PM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
... Loïc Dachary
01:26 PM Feature #7366 (Resolved): EC: scrubbing
Fill in the ECBackend methods for shallow and deep scrubbing Samuel Just
09:59 AM Bug #6101: ceph-osd crash on corrupted store
We deleted the rados block that was in the stack trace, but deleting it did not solve the problem.
The node still cr...
Daniel Poelzleithner
09:31 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Is it actually that much work to enable? We'll want it in the future and it'll be easier if it's set up using the cor... Greg Farnum
09:24 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Greg Farnum wrote:
> Unless you've already done so, the agent will also need to be recast the same way. We might as ...
Sage Weil
09:15 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Unless you've already done so, the agent will also need to be recast the same way. We might as well make this work pr... Greg Farnum
09:13 AM devops Bug #7334 (In Progress): ceph-disk: cannot run partprobe on used devices with EL6
Alfredo Deza
04:57 AM Subtask #7363 (Rejected): erasure code: reduce the chunk size to a minimum
make sure the jerasure cauchy technique does not oversize chunks, see "related mail thread":http://www.spinics.net/li... Loïc Dachary
04:23 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
"pulpito report":http://pulpito.ceph.com/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69541/
"cor...
Loïc Dachary
04:07 AM Feature #7266: erasure code : implement locality (was pyramid)
"primary affinity":https://github.com/ceph/ceph/pull/1176 Loïc Dachary
12:48 AM rgw Bug #6621 (Resolved): quota: the max-size and max-objects value when zero
Tamilarasi muthamizhan
12:29 AM rgw Bug #6621 (In Progress): quota: the max-size and max-objects value when zero

Tamilarasi muthamizhan

02/06/2014

09:32 PM Fix #6483: osd: does not fill in OSDOp::rval member
Running this through the rados suite. It's in wip-librados-op-rvals, which is on top of https://github.com/ceph/ceph/... Josh Durgin
09:32 PM Fix #6483 (Fix Under Review): osd: does not fill in OSDOp::rval member
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Feature #7194 (Fix Under Review): librados: omap in the c api
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Feature #7193 (Fix Under Review): librados: object operation bindings for reads
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Bug #7250 (Fix Under Review): osd: string xattr comparison can have undefined behavior
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:30 PM Feature #7195 (Fix Under Review): librados: complete C write object operation bindings
https://github.com/ceph/ceph/pull/1195 Josh Durgin
07:53 PM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
Samuel Just
07:52 PM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
nvm Samuel Just
07:18 PM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
42a64e19b7a06c1b3e0fd40e2d9c572103e3e426 David Zafman
03:07 PM Bug #7355 (In Progress): assert(0) in_make_pg() because EC getting enabled
David Zafman
11:49 AM Bug #7355: assert(0) in_make_pg() because EC getting enabled
2014-02-06T01:24:45.644 INFO:teuthology.task.workunit.client.0.err:[10.214.133.32]: + ceph osd pool delete fuggg fugg... David Zafman
11:45 AM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
David Zafman
07:18 PM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
"Work in progress":https://github.com/ceph/ceph/pull/1267
Once OSDs can handle Erasure Coding we should add back t...
David Zafman
04:10 PM rados-java Bug #7359: [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-plana suite
Same issue was reported in ceph project - BUG #7354 Yuri Weinstein
03:52 PM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69709... Yuri Weinstein
01:38 PM Subtask #7358 (Rejected): erasure code : plugin upgrade documentation
when a plugin is upgraded and its behavior changes, it must be renamed. That is until there is a more sophisticated p... Loïc Dachary
01:36 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
For Firefly it is enough to document. If a new backward compatible plugin is introduced in Giant, it will need to hav... Loïc Dachary
09:36 AM Subtask #7292: erasure code: plugin backward compatibility
Or maybe a increasing version and mandatory backward compatibility is all we need and compatset is overkill Loïc Dachary
05:50 AM Subtask #7292 (Need More Info): erasure code: plugin backward compatibility
Is there a better way to prepare an upgrade path without over engineering it ? Loïc Dachary
02:18 AM Subtask #7292: erasure code: plugin backward compatibility
"work in progress":https://github.com/ceph/ceph/pull/1193 Loïc Dachary
01:45 AM Subtask #7292 (In Progress): erasure code: plugin backward compatibility
Loïc Dachary
12:45 PM devops Bug #7356 (Rejected): Kill all while loops that will never end....
Ok maybe with the one exception of one of mine that is for VPS creation... If the host machine is down then it will j... Sandon Van Ness
11:49 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
Hi,
I am seeing the same issue on my clusters with 3 monitors. I am running:
ceph --version
ceph version 0.7...
Eric Eastman
11:45 AM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure

During master run and a also my branch which has a backfill fix we have seen the following test case failures:
L...
David Zafman
11:12 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
Duplicate of #7336. Already fixed on next. Yehuda Sadeh
10:34 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:02:36-rgw-master-testing-basic-plana/69941/
...
Yuri Weinstein
10:31 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
Thanks Sage -- I can confirm that the issue does not appear when echo'ing directly into the file. So evidently it was... Florian Haas
09:40 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
the problem is that vi is renaming the file and we cache recently opened files. use echo asdf >> file or similar to ... Sage Weil
04:18 AM Bug #7350 (Won't Fix): osd: scrub does not detect recently touched and then renamed backend files
This is on Dumpling (0.67.5-1precise).
Steps to reproduce:
> Create a single-byte RADOS object and read it back...
Florian Haas
09:57 AM Feature #6507 (Fix Under Review): librados shouldn't block indefinitely when cluster doesn't resp...
https://github.com/ceph/ceph/pull/1192 Josh Durgin
07:48 AM Documentation #6465: admin/build-doc should have some kind of build check for broken links
No updates here, assigning back to John since this looks like a problem with the build.
The one change added to th...
Alfredo Deza
07:00 AM CephFS Feature #7352: mds: make classes encode/decode-able
working on this at https://github.com/ceph/ceph/tree/wip-mds-dencoder John Spray
06:57 AM CephFS Feature #7352 (In Progress): mds: make classes encode/decode-able
Sage Weil
06:55 AM CephFS Feature #7352 (Resolved): mds: make classes encode/decode-able
Sage Weil
06:54 AM CephFS Feature #7319 (In Progress): qa: multimds, no failure
Sage Weil
01:41 AM Feature #7238 (In Progress): erasure code : implement LRC plugin
refactoring to not introduce new API functions as it turns out to be more complicated Loïc Dachary
01:38 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
Alignment is calculated using "LARGEST_VECTOR_WORDSIZE":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39b... Loïc Dachary
01:06 AM Subtask #7158 (Resolved): EC: flesh out how the ceph tool should be used to manage ec pools and c...
http://tracker.ceph.com/issues/7146 was created and implemented. There does not seem to be a need for more tools.
...
Loïc Dachary

02/05/2014

04:59 PM Feature #7347 (New): Per CRUSH type mon_osd_down_out_interval
Ability to have different mon_osd_down_out_interval values for different CRUSH types.
For example, you could set:
...
Alexandre Marangone
04:42 PM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
Loïc Dachary
12:09 PM Subtask #7339 (Fix Under Review): erasure code: add stripe width to pg_pool_t
"work in progress":https://github.com/ceph/ceph/pull/1188 Loïc Dachary
01:39 AM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
* add *erasure_code_stripe_width* to config_opts.h
* on *osd pool create*, set the pg_pool_t::stripe_width to be get...
Loïc Dachary
04:35 PM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
Upon trying to issue a multiple delete operation on a bucket that contains an unfound object, we return:
@<?xml ve...
Brian Andrus
03:44 PM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
This func does two things: either returns in in-memory structure, or generates the right archived hitset that spans t... Sage Weil
03:20 PM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
No pattern has emerged, except that it happened twice in rapid succession after a long period of not happening (weeks... Nathaniel Filardo
08:28 AM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
Hi Nathaniel,
What kind of workload are you running? Have you noticed any pattern
wrt when it occurs, what might...
Ilya Dryomov
03:15 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
Logs are in - http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68114
...
Yuri Weinstein
11:51 AM Feature #7344: osd: add additional heartbeat on cluster interface
If we have to do heartbeating over the exact same connection we send our other traffic on, is there any advantage to ... Greg Farnum
11:24 AM Feature #7344 (Resolved): osd: add additional heartbeat on cluster interface
A user had a switch configuration problem (no jumbo frames) that prevented progress on the cluster interface but allo... Sage Weil
11:46 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
11:18 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")

As unsigned values CEPH_SNAPDIR (snapdir) > CEPH_NOSNAP (head). The code wants to collapse both into a single last...
David Zafman
10:20 AM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
11:20 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68416/te... Yuri Weinstein
09:30 AM devops Bug #6595 (Resolved): Hardcoded install path in ceph-disk
All subprocess calls in ceph-disk will use a PATH helper to find the correct executables regardless if $PATH is set o... Alfredo Deza
09:28 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
Pull request https://github.com/ceph/ceph-deploy/pull/160
Merged into master with hash b50345e
Alfredo Deza
09:26 AM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
Merged into ceph-deploy's master branch with hash c036cbd Alfredo Deza
08:37 AM devops Bug #7276 (Fix Under Review): ceph-deploy: -n arg is ignored
pull request opened https://github.com/ceph/ceph-deploy/pull/162 Alfredo Deza
07:18 AM devops Bug #7276 (In Progress): ceph-deploy: -n arg is ignored
Ah good catch. That does absolutely nothing. Will have to remove that. Alfredo Deza
07:27 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
> Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about wh... Florian Haas
07:18 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about whic... Greg Farnum
01:03 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Dan Mick wrote:
> Another way to state this: rbd images are defined such that if an object doesn't exist within the ...
Florian Haas
01:45 AM Feature #7340 (Duplicate): rados.py does not expose object locking
Commit d8415663b62edb812d087cba40b03b933e3e4556 exposed @rados_lock_exclusive()@, @rados_lock_shared()@, @rados_unloc... Florian Haas

02/04/2014

06:10 PM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Another way to state this: rbd images are defined such that if an object doesn't exist within the defined size of the... Dan Mick
11:20 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
There's a big difference between what happens if the objects get zapped versus rendered unreadable — if unreadable, t... Greg Farnum
10:54 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
OK. Now the recent rgw/xattr bug has shown that it is possible for a Ceph application to mess up objects so badly tha... Florian Haas
10:29 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Just the first; as you say, it's how we do TRIM and that implementation is very common behavior among storage systems. Greg Farnum
10:25 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
> Nonexistent objects are *defined* as zeros in RBD.
Erm, OK. I take it that this is also how TRIM/DISCARD is imp...
Florian Haas
10:14 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Nonexistent objects are *defined* as zeros in RBD. We'd have to distinguish between deliberately nonexistent and lost... Greg Farnum
10:10 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Greg Farnum wrote:
> At present this is expected behavior. In order to raise an error we would need to know that the...
Florian Haas
09:42 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
At present this is expected behavior. In order to raise an error we would need to know that the object was supposed t... Greg Farnum
09:32 AM Bug #7335 (Won't Fix): librbd does not raise "Object Not Found", instead returning NUL bytes
Test case attached. @test_remove_object@ fails. Prose description:
* Create RBD image
* Remove RADOS object belon...
Florian Haas
12:27 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
12:08 <@sage> alram joao wido: on issue 5804 i'm guessing ssh access and debugging is the trick,
altho...
Alexandre Marangone
12:13 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
really think that log message would go a long way toward helping. Dan Mick
11:58 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
I'm able to reproduce this fairly consistently on the Ceph VM Wido is mentioning.
Any information/debug settings t...
Alexandre Marangone
12:00 PM Bug #6685 (Fix Under Review): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present ...
David Zafman
10:48 AM rgw Bug #7336 (Fix Under Review): rgw: limit on list buckets broken
Yehuda Sadeh
10:22 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
The limit param that is used in swift when listing buckets does not work correctly on latest master. Yehuda Sadeh
10:28 AM Subtask #7277: EC: on erasure pool creation, size needs to be fixed to K+M, size must not subsequ...
resolved with https://github.com/dachary/ceph/commit/c8c4cc6e81816069886af6bff968712993554759 and later amended by ht... Loïc Dachary
03:11 AM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
Loïc Dachary
08:46 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
commit:42900ff9da9f5adcac239a84ebf4d2e407c29699
https://bugzilla.redhat.com/show_bug.cgi?id=614357.
After ceph-...
Alexandre Marangone
07:02 AM CephFS Feature #7319: qa: multimds, no failure
Enable the marginal suite multi-mds tests. Greg Farnum
06:59 AM CephFS Feature #7316: improve mds state dumps (memory usage, completeness)
https://wiki.ceph.com/Planning/Sideboard/mds%3A_dumpability Greg Farnum
06:52 AM CephFS Feature #7333 (In Progress): client: evaluate multiple O_APPEND writers
This needs done for kclient and libcephfs. Extending the size of the file is potentially racy with updates to inode's... Sage Weil
06:50 AM CephFS Fix #7109 (Fix Under Review): disallow removing the first data pool
https://github.com/ceph/ceph/pull/1173 Greg Farnum
05:50 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
... Alfredo Deza
05:22 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Wido den Hollander wrote:
> > Florian Haas wrote:
> > > Just for clarification: when you say...
Wido den Hollander
05:02 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Wido den Hollander wrote:
> Florian Haas wrote:
> > Just for clarification: when you say "it" blocked forever, are ...
Florian Haas
02:34 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Wido den Hollander wrote:
> > > * Did you only test with an RBD storage *pool*, or do you als...
Wido den Hollander
04:26 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Josh Durgin wrote:
> Wido den Hollander wrote:
> > Josh Durgin wrote:
> > > It makes sense to add as an option for...
Wido den Hollander
03:22 AM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
"pull request":https://github.com/ceph/ceph/pull/1180
Loïc Dachary
03:00 AM Subtask #7146 (Resolved): implement osd crush rule create-erasure
Loïc Dachary

02/03/2014

09:14 PM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
sage-2014-02-03_16:41:22-rados:basic-wip-agent-testing-basic-plana/64994... Sage Weil
08:03 PM Feature #6507 (In Progress): librados shouldn't block indefinitely when cluster doesn't respond
Wido den Hollander wrote:
> Josh Durgin wrote:
> > It makes sense to add as an option for librados users like the l...
Josh Durgin
12:45 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Josh Durgin wrote:
> It makes sense to add as an option for librados users like the libvirt storage pool. The defaul...
Wido den Hollander
12:37 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
didn't mean to change these Josh Durgin
12:21 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
It makes sense to add as an option for librados users like the libvirt storage pool. The default is blocking for thin... Josh Durgin
02:41 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Dan Mick wrote:
> 1) I solved this in the python bindings with a separate timer thread, which is always possible in ...
Wido den Hollander
06:26 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
I just wanted to inform you that since 0.7, I don't have to patch and recompile ceph-mds to get it to start every upd... Jérôme Poulin
05:22 PM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
Sage Weil
06:07 PM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
Running ceph osd reweight-by-utilization resulted in stuck pgs.... Tyler Brekke
05:30 PM rbd Bug #7327 (Resolved): Assertion failure in rbd_object_request_destroy()
Running Debian kernel 3.12.6 (debian package linux-image-3.12-1-amd64_3.12.6-2_amd64) inside a Xen DomU, we occasiona... Nathaniel Filardo
05:28 PM CephFS Bug #6623 (Resolved): mds: update backtraces on existing clusters
Sage Weil
05:27 PM CephFS Feature #1448 (Resolved): test hadoop on sepia
Sage Weil
05:25 PM CephFS Bug #4489 (Can't reproduce): ceph fs hangs on file stat
Sage Weil
05:25 PM CephFS Bug #5485 (Can't reproduce): failed cifs mount
Sage Weil
05:23 PM CephFS Bug #4685 (Can't reproduce): BUG: unable to handle kernel NULL pointer dereference at
Sage Weil
05:20 PM CephFS Bug #5753 (Duplicate): ceph-fuse: segfault when getting back a traceless rename op
Sage Weil
05:19 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
Sage Weil
05:18 PM CephFS Bug #4909 (Can't reproduce): mds: stalled/stuck directory (standby)
Sage Weil
05:01 PM CephFS Feature #3863: implement a tool to lookup inode numbers without holding their path
Sage Weil
05:01 PM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
Sage Weil
05:00 PM CephFS Feature #1693 (Resolved): libcephfs: Support TRIM (hole punching)
Sage Weil
04:59 PM CephFS Feature #3867 (Resolved): optionally do not use an anchor table
Sage Weil
04:58 PM CephFS Cleanup #2177 (Resolved): mds: play nicely with omap
Sage Weil
04:58 PM CephFS Feature #7326 (New): qa: fix flock tests
Sage Weil
04:57 PM CephFS Feature #7325 (New): mds: tool to examine (later, manipulate) dirfrag objects
Sage Weil
04:57 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
Sage Weil
04:56 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
Sage Weil
04:55 PM CephFS Feature #7322 (New): qa: inline data + thrashing
Sage Weil
04:55 PM CephFS Feature #7321 (Duplicate): qa: multimds thrasher
Sage Weil
04:54 PM CephFS Feature #7320 (Fix Under Review): qa: thrash directory fragmentation
Define killpoints for directory fragmentation. Create tests as in https://github.com/ceph/ceph/pull/28004 Sage Weil
04:54 PM CephFS Feature #7319 (Resolved): qa: multimds, no failure
Sage Weil
04:54 PM CephFS Feature #7318 (Duplicate): qa: ceph-fuse + sync mode
Sage Weil
04:53 PM CephFS Feature #7317 (Resolved): mds: behave with fs fills (e.g., allow deletion)
Sage Weil
04:53 PM CephFS Feature #7316 (New): improve mds state dumps (memory usage, completeness)
Sage Weil
04:52 PM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
Sage Weil
04:40 PM Cleanup #7314 (In Progress): remove dead code from OSDMonitor::should_propose
"located here":https://github.com/ceph/ceph/blob/v0.75/src/mon/OSDMonitor.cc#L763 Loïc Dachary
02:47 PM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
before asking the erasure-code plugin to create the rule, check if CEPH_FEATURE_CRUSH_V2 is supported by all daemons Loïc Dachary
12:59 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Wido den Hollander wrote:
> > * Did you only test with an RBD storage *pool*, or do you also have *domains* running ...
Florian Haas
12:46 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT ...
Wido den Hollander
10:55 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT bug.
Two questions:
...
Florian Haas
06:00 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
So I've played around with this today and I can't fully reproduce it.
I have a machine running with libvirt 1.1.1-...
Wido den Hollander
01:48 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Right, but why should the qemu process stall if all the MONs are available, and only a few RBD...
Wido den Hollander
01:42 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Right, but why should the qemu process stall if all the MONs are available, and only a few RBDs are shot? (if they ar... Florian Haas
12:56 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
I'm going to try to figure this out, I'm setting up a test env right now.
I think it's libvirt which can't handle ...
Wido den Hollander
12:32 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
With Wido having confirmed that the issue exists, I'm bumping the severity to critical.
Wido, if you could offer y...
Florian Haas
11:26 AM Bug #7178 (Resolved): sample.ceph.conf needs update
commit:e268e9562dd0831fe40702e56bfbdf8f6cb80b1a Josh Durgin
09:45 AM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Work-in-progress kmod packaging here: https://github.com/kdreyer-inktank/ceph-kmod-rpm
Originally I'd planned to b...
Ken Dreyer
08:32 AM devops Bug #7312 (Resolved): ERROR: Running exception handlers
Failed in:
teuthology-2014-01-31_19:35:02-upgrade:small-next-testing-basic-vps/61907
logs in http://qa-proxy.ceph...
Yuri Weinstein
07:37 AM devops Bug #7311 (Closed): GPG/packaging failures
apt complained throughout the install process... Alfredo Deza
07:25 AM rbd Bug #7310 (Can't reproduce): rbd snap unprotect test failing
... Alfredo Deza
06:51 AM CephFS Bug #5411 (Resolved): teuthology: bad object dereference
Sage Weil
05:21 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Greg Farnum wrote:
> Which op threads and filestore threads are you talking about? The splitting happens whenever th...
Guang Yang

02/02/2014

05:19 PM Feature #7058 (Fix Under Review): osd primary affinity
Sage Weil
05:18 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
07:53 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Hey Wido,
thanks for responding to this, and doubly for doing so on a weekend. Much appreciated.
> I'm aware of...
Florian Haas
06:30 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
The "get_chunk_size() method":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39bfd1146a25f465/src/osd/Eras... Loïc Dachary
05:51 AM Subtask #7146 (Fix Under Review): implement osd crush rule create-erasure
"work in progress":https://github.com/ceph/ceph/pull/1144 Loïc Dachary
05:42 AM Subtask #7277 (In Progress): EC: on erasure pool creation, size needs to be fixed to K+M, size mu...
"setting the size of the pool":https://github.com/ceph/ceph/pull/1144#issuecomment-33899812 Loïc Dachary

02/01/2014

10:57 PM Feature #7288: Deep-scrub throttle
Yes but if you have one scrub per OSD and you have a replication of 3. It could be easily happen that one OSD has 3 o... Stefan Priebe
09:01 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
ubuntu@teuthology:/a/teuthology-2014-01-31_23:00:01-rados-master-testing-basic-plana/62166 Sage Weil
02:22 PM Bug #7178: sample.ceph.conf needs update
Fully merged by Josh Durgin -- thanks.
This bug can be closed now (I have no rights to do that).
Dmitry Smirnov
11:40 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
I'm aware of this. It's not only with RBD though, the same happens with libvirt when you use NFS and a export is dead... Wido den Hollander
12:33 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
I'm sorry to say, all my data is considered lost right now. I like Ceph architecture very much but cannot use due to ... Grigory Gorelov

01/31/2014

07:08 PM Feature #7288: Deep-scrub throttle
As it is we have config value osd_max_scrubs which defaults to 1. This should cause each OSD to only scrub a single ... David Zafman
12:13 PM Feature #7288 (Resolved): Deep-scrub throttle
Currently, it appears many PGs are allowed to enter a deep-scrubbing state. Due to the more intensive nature of a dee... Brian Andrus
03:09 PM Bug #7093 (Pending Backport): osd: peering can send messages prior to auth
Backported this to dumpling in commit:183deb899bc6b1b7b2a1ec639425e45786e56b01
Do we also want to backport it to e...
Greg Farnum
02:39 PM Documentation #6547: should document magic data/journal partition types
No, thanks, fixed Dan Mick
02:34 PM Documentation #6547: should document magic data/journal partition types
hmm, is this meant to be in the calamari product? John Spray
02:13 PM devops Feature #7293 (Resolved): packaging: enable qemu to find librbd on rhev or rhel-osp
qemu-kvm-rhev will dynamically load librbd if /usr/lib64/qemu/librbd.so.1 exists.
The librbd package needs to add ...
Josh Durgin
02:02 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
The goal is to allow Giant to install upgraded backward compatible erasure-code plugins so that pools created with Fi... Loïc Dachary
02:01 PM Feature #7291 (New): EC: add mechanism for mon to detect and whitelist EC plugins which are globa...
Otherwise, we might end up with a situation where the mon believes an EC plugin is usable and creates such a pool, bu... Samuel Just
01:58 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Ian Colle
01:57 PM Feature #7034: cachepool: agent: basic eviction
Ian Colle
01:56 PM Feature #7033: cachepool: agent: trivial flushing
Ian Colle
01:53 PM Fix #7215 (Resolved): mon: prevent old monitors which do not support new encodings from joining t...
This is merged (and so are some fixes around it), just didn't get the automated tests debugged but they can go elsewh... Greg Farnum
01:27 PM devops Feature #6882 (Resolved): downburst: list available distro/versions
This is done in branch wip-list-distros which was merged a while ago. Sandon Van Ness
01:24 PM devops Feature #7047 (In Progress): rhel7: build process for rbd.ko, ceph.ko kernel modules
Ian Colle
01:24 PM devops Feature #7046 (In Progress): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
Ian Colle
01:22 PM devops Feature #7094 (Resolved): f20 gitbuilder
Ian Colle
01:22 PM devops Fix #7095 (Resolved): fix f19 gitbuilder
Ian Colle
01:08 PM rgw Feature #6338: rgw: better manifest scaling
Currently a gateway object includes in the manifest a list of all the rados objects that it uses. Every time we acces... Yehuda Sadeh
12:54 PM rgw Feature #6338 (In Progress): rgw: better manifest scaling
Ian Colle
12:54 PM rgw Feature #6339 (In Progress): rgw: compact manifest data
Ian Colle
12:32 PM Subtask #5861 (Resolved): Refactor scrub to use PGBackend methods
dffe6019c3698ca1661c94984df9629241c3e1ef David Zafman
12:31 PM Feature #5997 (Resolved): EC: [link] Refactor scrub to use PGBackend methods
dffe6019c3698ca1661c94984df9629241c3e1ef David Zafman
10:37 AM Feature #7287 (New): Make units of measurement constant and definable in ceph commands
From the customer:
It would be great if it were possible to lock the units for ceph reporting
ceph -w /ceph -s ...
Brian Andrus
10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
Samuel Just
10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
While ReplicatedBackend always calls log_operation from within the call to log_operation, this won't be true of ECBac... Samuel Just
10:28 AM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
This is necessary because though with ReplicatedBackend, log_operation will be called from within the submit_transact... Samuel Just
10:22 AM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
Samuel Just
10:12 AM Bug #7256: ceph osd crashed at ReplicatedPG::trim_object on next
maybe dup of #6101 ? Daniel Poelzleithner
09:59 AM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
From the doc, I'm using http://gitbuilder.ceph.com/apache2-rpm-centos6-x86_64-basic/ref/master to install httpd on th... Alexandre Marangone
09:49 AM CephFS Fix #7109: disallow removing the first data pool
https://github.com/ceph/ceph/pull/1173 John Spray
09:47 AM rbd Bug #7282 (Resolved): Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connect...
This isn't fully confirmed yet, because we haven't found a reliable way to reproduce. In short, it seems that if you ... Florian Haas
07:49 AM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
> "2014-01-31 05:32:26.722560 osd.5 10.214.131.11:6810/5928 5 : [ERR] 3.12 3
> tried to pull 1518ccf2/plana1...
Sage Weil
12:47 AM rbd Bug #7076 (Resolved): rbd: check for watchers before removing an image
Ilya Dryomov

01/30/2014

06:45 PM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
Samuel Just
04:13 PM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
Originally noticed this after running ceph-deploy -n --overwrite-conf config push host1 host2 host3
I also tried ins...
Alexandre Marangone
11:06 AM devops Bug #7263 (Resolved): ceph-deploy should not use color formatting in non-tty sessions
Merged into ceph-deploy's master branch 2fcf4bc Alfredo Deza
08:17 AM devops Bug #7263 (Fix Under Review): ceph-deploy should not use color formatting in non-tty sessions
Pull request opened https://github.com/ceph/ceph-deploy/pull/157 Alfredo Deza
10:53 AM Feature #7059 (Resolved): filestore: avoid leveldb check for xattr when possible
Sage Weil
10:38 AM Feature #5997: EC: [link] Refactor scrub to use PGBackend methods
David Zafman
10:33 AM rgw Bug #7099: Strange Comportments with media files
I'm not saying that it's not. I'm trying to figure out what the gateway does that makes the client behave like that. Yehuda Sadeh
10:31 AM rgw Bug #7099: Strange Comportments with media files
Yehuda,
It's a general problem on all range request. I have reproduced it on multiple installations ...
It's ...
Julien Calvet
10:16 AM rbd Feature #7272 (Duplicate): rbd: import performance
Currently the rbd import appears to be single threaded which means the import process is being written to a single di... Tyler Brekke
09:55 AM rgw Bug #7271 (Resolved): container create via swift doesn't register ACL
Hi,
when creating a container thanks the Swift API (PUT /{version}/{account}/{container}), X-Container-Read seems ...
Olivier Bonvalet
09:31 AM RADOS Feature #7270 (New): /usr/bin/ceph: notify user when privs are insufficient
It should be pretty straightforward to significantly enhance this user experience:... Zack Cerza
09:16 AM Bug #7258 (Resolved): ceph-disk: many calls do not work if command is not in PATH
Sage Weil

01/29/2014

11:50 PM RADOS Feature #7267 (New): erasure code: take advantage of locality for recovery
Only select the chunks with the "closest ancestor":https://github.com/ceph/ceph/blob/v0.75/src/crush/CrushWrapper.h#L... Loïc Dachary
11:44 PM Feature #7266 (Resolved): erasure code : implement locality (was pyramid)
"June 2014 Giant / Hammer summit":http://pad.ceph.com/p/GH-locally-repairable-code Loïc Dachary
09:44 PM Feature #6960 (Closed): DBObjectMap: refactor interface
Haomai Wang
05:45 PM Bug #6101: ceph-osd crash on corrupted store
The initial problem was thought to be related to snapshots, therefore they cleaned all snapshots on the cluster but t... Daniel Poelzleithner
05:15 PM Bug #6101: ceph-osd crash on corrupted store
find_object_context() in trim_object returned -ENOENT.
But I couldn't track down why, optimized builds were drivin...
Daniel Poelzleithner
03:50 PM Bug #6101: ceph-osd crash on corrupted store
The nodes use xfs, so I don't think that the original assumption that filesystem corruption may be the cause is the o... Daniel Poelzleithner
03:40 PM Bug #6101: ceph-osd crash on corrupted store
Today I had contact with a cluster that suffers the same problem.
ceph version 0.67.5 (a60ac9194718083a4b6a225fc17...
Daniel Poelzleithner
03:53 PM Documentation #7265 (Closed): OpenStack <=> RBD docs should specify that config stanzas should be...
At:
http://ceph.com/docs/master/rbd/rbd-openstack/
Under "Configure OpenStack to use Ceph", it should be mentione...
Zack Cerza
02:20 PM Feature #7247: EC: distinguish is_missing from is_readable
Samuel Just
01:58 PM Bug #7264 (Resolved): rados.py: exception catching when librados load fails hides error
A developer had built a library set that had an unresolved-symbol problem; rados.py, and thus the ceph cli, failed wi... Dan Mick
01:32 PM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
Samuel Just
01:32 PM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
Samuel Just
12:54 PM devops Bug #7263 (Resolved): ceph-deploy should not use color formatting in non-tty sessions
Hopefully this would mean that teuthology logs would not be filled with ANSI escape codes trying to represent
colors...
Alfredo Deza
12:33 PM Bug #7262 (Resolved): ceph-disk-activate: custom mount options aren't handled correctly for non-d...
Mount options are initially read from the hardcoded ceph.conf:
https://github.com/ceph/ceph/blob/d7b0c7faafd37e4ae...
Josh Durgin
10:43 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
No, clean server right now means there is nothing except gentoo stage3 installation. Grigory Gorelov
07:55 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
are you reusing a previous store, from a previously problematic cluster? Joao Eduardo Luis
09:20 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Which op threads and filestore threads are you talking about? The splitting happens whenever the filestore actually d... Greg Farnum
07:44 AM Bug #7259: ceph mon crash in master branch
Tamil, I suspect this is related to #7215, which should have been fixed by https://github.com/ceph/ceph/pull/1148 (wh... Joao Eduardo Luis
07:12 AM Feature #6173 (Resolved): Add LevelDB support to ceph cluster backend store
Haomai Wang
07:12 AM Bug #6950 (Resolved): refactor OSD awareness of FileStore to make the ObjectStore backend configu...
Haomai Wang
06:15 AM rbd Bug #7076 (Fix Under Review): rbd: check for watchers before removing an image
wip-rbd-rm-watchers; https://github.com/ceph/ceph/pull/1159 Ilya Dryomov
 

Also available in: Atom