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
- 09:27 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
- Actually, yeh I'll look at this.
- 03:30 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
- Is this still an issue, Noah?
- 09:23 PM CephFS Bug #4861 (Rejected): Alter Java components to build against Java 1.6 (or 1.7)
- 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...
- 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...
- 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...
- 04:03 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
- Is this still a problem?
- 05:14 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
- who cares 3.5 kernel?
- 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!
- 05:13 PM CephFS Bug #7565: Failed assert in check_rstats
- it's CDir::check_rstats() bug, not rstat corruption.
- 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...- 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. - 04:50 PM CephFS Bug #926: mds: fix rename between snaprealms
- Snapshots
- 04:50 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
- #7326
- 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.
- 04:45 PM CephFS Bug #3596: ceph-fuse: crash in mds rejoin
- Snapshots
- 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.
- 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, ... - 04:42 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
- Confirmed MDS bug!
- 04:41 PM Bug #7458: osd: stray pg ref on shutdown
- 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.
- 04:38 PM CephFS Bug #1666: hadoop: time-related meta-data problems
- Also see #7564
But low priority, for this is Hadoop - 04:36 PM CephFS Bug #4212: mds: open_snap_parents isn't called all the times it needs to be
- Snapshots
- 04:36 PM CephFS Bug #4213: mds: old_parents is never cleaned up
- Snapshots
- 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
- 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...
- 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.
- 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... - 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...
- 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...
- 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...
- 03:53 PM CephFS Bug #4134: mds: request locking hang under snaptests
- snapshots = low
- 03:52 PM CephFS Bug #3719 (Can't reproduce): pjd test 145 failed in the nightly runs
- These logs are gone.
- 03:45 PM CephFS Bug #4280: mds: crash on lookupsnap
- Snapshots = low priority
- 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...
- 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...
- 03:30 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
- Need more info, samba, uclient, etc.
- 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...
- 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.
- 03:25 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- uclient = low priority, for now.
- 03:25 PM Bug #7542: ec misdirected op
- wip-7542
- 03:25 PM Bug #7539: Firefly EC pool massive memory leak during writes
- testing wip-7542
- 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... - 03:25 PM CephFS Bug #4188: mds crashes when cow-ing entries in formerly snapshotted dir
- Snapshots = low priority. *sigh*
- 03:21 PM CephFS Bug #5360: ceph-fuse: failing smbtorture tests
- Samba against ceph-fuse (not even using libcephfs) = low priority.
- 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...
- 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!
- 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.
- 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.
- 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.
- 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...
- 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?
- 01:24 PM CephFS Bug #6741: failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
- Downgrading: ceph-fuse and snapshots.
- 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.
- 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...
- 01:20 PM CephFS Bug #7206 (Need More Info): Ceph MDS Hang on hadoop workloads
- 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...
- 12:42 PM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
- ...
- 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.
- 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...
- 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... - 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 ... - 07:57 AM Bug #7248 (Fix Under Review): osd: bench set max size
- https://github.com/ceph/ceph/pull/1324
- 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...
- 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/...
02/26/2014
- 11:02 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
- 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... - 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... - 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. ...- 05:01 PM CephFS Bug #4746: client: invalidate callback can deadlock
- Demoted due to ceph-fuse and FUSE interface work.
- 05:00 PM CephFS Bug #4829: client: handling part of MClientForward incorrectly?
- Demoting due to uclient and multi-mds.
- 04:58 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- Demoting due to uclient and Need More Info.
- 04:57 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
- Demoting due to multi-mds.
- 04:57 PM CephFS Bug #5765: kclient: High CPU due to raw_spin_lock in ceph_cap_string
- Demoting due to performance, not correctness.
- 04:56 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- Demoting due to uclient.
- 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....
- 04:48 PM CephFS Bug #6608: samba teuthology dbench failure
- Demoting priority on samba.
- 04:47 PM CephFS Bug #7011: ENOTEMPTY on ceph-fuse + snaptest-? test
- Demoting priority on ceph-fuse and snapshots.
- 04:47 PM CephFS Bug #6613: samba is crashing in teuthology
- Demoting priority on samba.
- 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?
- 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...
- 04:29 PM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
- Again, Zheng got this done.
- 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...
- 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)?
- 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...
- 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...
- 03:33 PM Bug #7549: Mon deadlock
I did add a -d to the vstart.sh invocation in the test/vstart_wrapper.sh script.- 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...- 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
- 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.
- 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.
- 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.... - 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 ...
- 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...
- 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 ...
- 07:15 AM CephFS Bug #7530: mds: failed anchor assert on replay
- commit:7ba3200f1e91d803cdf84f96777641f7d18d3c01
- 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. - 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".
- 01:08 AM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
- MDS map contains CompatSet::FeatureSet
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... - 08:42 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
- 5a6cb3da201ce503b4aef1744c3dc15511d15a13
- 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]
... - 07:55 PM Bug #7406: Seg fault in find_object_context()in recent master rados run
- 07:52 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily
- 12:55 PM Bug #7535: Switching to classic scrub unnecessarily
This was primarily fixed by 7357b6ed4bbc6ef44a80640ffb7e1ddacab10b5e for tracker #7517.- 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 ...- 07:34 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
- Created and on the index page.
- 06:27 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
- 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...
- 09:09 AM CephFS Bug #7530: mds: failed anchor assert on replay
- Crashed on first try, log at debug-mds=10 attached
- 07:04 AM CephFS Bug #7530 (In Progress): mds: failed anchor assert on replay
- 03:47 PM Bug #6922 (Resolved): mon: do not allow unreasonable PG splitting
- Sam merged this.
- 01:40 PM Bug #6922: mon: do not allow unreasonable PG splitting
- PR: https://github.com/ceph/ceph/pull/1316
- 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...
- 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...
- 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...
- 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/...
- 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...
- 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:...
- 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.
- 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...
- 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...
- 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.
- 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.
- 07:02 AM CephFS Feature #3863 (In Progress): implement a tool to lookup inode numbers without holding their path
- 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... - 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... - 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...
- 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...
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...
- 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 ...
- 10:11 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
- ...
- 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 ...
- 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...
- 08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
- 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.
... - 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...
- 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 ... - 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...
- 05:10 PM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
- 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?
- 05:10 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
- 05:09 PM CephFS Feature #3999 (Resolved): update CDir encoding
- this was revved as part of zheng's omap stuff
- 04:15 PM Linux kernel client Cleanup #2847 (Resolved): libceph: osdmap definition is out of date
- 04:15 PM Linux kernel client Feature #6991 (Resolved): support CEPH_FEATURE_OSDMAP_ENC
- 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...
- 11:24 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- Seems related to #7468
- 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... - 10:20 AM rgw Bug #6936 (Resolved): radosgw-admin allows same user to be created multiple times
- Fixed for firefly, commit:53de64122b206d11aa42fd401f88f02f2908e942
- 10:20 AM rgw Bug #6951 (Resolved): rgw: bucket re-create fails when cache is disabled
- Fixed for firefly, commit:859ed33ed7f9a96f4783dfb3e130d5eb60c622dd
- 10:16 AM rgw Bug #6830 (Resolved): S3 CompleteMultipartUploadResult has empty ETag element
- Fixed, commit:2b3e3c834cd0e8b890296fa2b92ebb5de01a1bc1
- 10:15 AM rgw Bug #7064 (Resolved): S3 request to non-existent object in non-existent bucket results in 30 seco...
- Fixed, commit:3ed68eb9fac9b3d0bf9111867d609f9ea08fb202
- 09:58 AM devops Bug #7356 (In Progress): Kill all while loops that will never end....
- 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...
- 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... - 07:28 AM Bug #7504 (Rejected): Ceph does not specify python2
- 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... - 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....
- 12:58 AM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
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...
- 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... - 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
- 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...
- 07:49 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
- 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... - 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...
- 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...
- 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...
- 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 - 02:48 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
- 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...
- 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 ...
- 12:21 PM Bug #7493 (Resolved): cephtool/pool_ops failure
- commit:70d23b9a0ad9af5ca35a627a7f93c7e610e17549
- 08:23 AM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
- 07:54 AM Bug #7494 (Resolved): EC filter read op bug
- 07:54 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- 07:53 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
- 07:25 AM Bug #7491 (Resolved): rados api crashes
- 07:21 AM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
- 07:21 AM Feature #7514 (Resolved): qa: add ceph_test_objectstore to rados test suite
02/22/2014
- 05:35 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
- 05:27 PM Bug #7513: PGLog::activate_not_complete: log.complete_to decrement typo
- https://github.com/ceph/ceph/pull/1300
- 05:25 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
- 05:19 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
- merged
- 01:48 PM Bug #7511 (Fix Under Review): "set noup; set down <n>; unset noup" doesn't bring <n> back up
- 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...
02/21/2014
- 09:15 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
- ...
- 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... - 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... - 07:32 PM Bug #6685 (Resolved): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- a9677e136ee4753b86ed1151ca6ff08e4b63473d
- 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...- 02:15 PM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 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...
- 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...
- 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
- 02:39 PM Messengers Bug #5508 (Can't reproduce): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
- 02:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
- 02:37 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
- 02:37 PM Bug #6671 (Can't reproduce): FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
- 02:36 PM Bug #6636: sockaddr_storage and uuid_t are not portable to other platforms
- 02:35 PM Bug #6730 (Won't Fix): BUG: MAX_LOCKDEP_ENTRIES too low!
- 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...
- 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
- 02:33 PM Bug #6633 (Resolved): osd: pgls vs osd restart/peering race misses objects
- 02:32 PM Bug #6787: upstart is restarting daemons which we want to be dead
- 02:30 PM Bug #7120 (Need More Info): osd: EEXIST on mkcoll on dumpling
- 02:29 PM Bug #7170 (Can't reproduce): rados api test LibRadosMisc.CopyPP failed on next branch
- 02:29 PM Bug #7172 (Resolved): osd: OSD failed to start with osd_leveldb_cache_size > 0
- 02:29 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
- 02:28 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
- 02:28 PM Bug #7376 (In Progress): mon: >10s spent in remove_redundant_pg_temp
- 02:28 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
- 02:24 PM Bug #7068 (Need More Info): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.s...
- 02:21 PM Bug #7072: logrotate not sending HUP signal
- 02:20 PM Bug #7145 (Can't reproduce): PG::update_snap_map assert
- 02:19 PM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
- 02:18 PM Bug #7248: osd: bench set max size
- 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...
- 02:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
- 02:13 PM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
- 02:13 PM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
- 02:12 PM Bug #7393 (Need More Info): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0...
- 02:12 PM Bug #7458: osd: stray pg ref on shutdown
- perhaps that pg work queue PGBackend implementation can use?
- 02:11 PM rbd Bug #7385 (In Progress): Objectcacher setting max object counts too low
- 02:10 PM Bug #7398 (Need More Info): osd: ERANGE from clone
- 02:09 PM Bug #7491 (In Progress): rados api crashes
- 02:09 PM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- 09:36 AM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- wip-7506
- 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... - 02:09 PM Bug #7494: EC filter read op bug
- 02:08 PM Bug #7496 (Need More Info): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
- 02:08 PM Bug #7498 (Need More Info): stuck in recovery
- 02:08 PM Bug #7497 (Need More Info): timeout waiting to go clean
- 02:08 PM Bug #7495 (Need More Info): ENOTEMPTY on collection remove
- 01:58 PM Bug #7463: ceph-rest-api fails to start with no OSDs up
- Dan fixed in db88e7f385f4464f5f4de517845607391c314ef5
- 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...
- 11:57 AM Bug #7508: 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burnupi09.front...
- wip-7508
- 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... - 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 ... - 09:29 AM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
- 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... - 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... - 08:30 AM CephFS Bug #7485 (Fix Under Review): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
- 08:29 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)
- https://github.com/ceph/ceph/pull/1283
- 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...- 07:12 AM devops Bug #7486: python-backports needs fixing for rhel
- 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. ...
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 ...
- 09:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
- pull request is #1280 for wip branch wip-7374-wusui
- 09:22 PM rgw Bug #7374: s3_multipart_upload.pl fails
- This has been pushed in its own branch to wip-7374-wusui
- 09:28 PM rgw Bug #7375: s3_user_quota.pl fails
- Pull request is #1279 for wip branch wip-7375-wusui
- 09:21 PM rgw Bug #7375: s3_user_quota.pl fails
- this has been pushed in its own branch to wip-7375-wusui
- 05:47 PM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
- 05:05 PM Bug #7471 (Resolved): ec pools copyfrom broken
- 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 ...
- 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:
... - 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
- 02:45 PM Bug #7497: timeout waiting to go clean
- We might just increase the timeout for rados bench runs.
- 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 ...
- 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...
- 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... - 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...
- 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... - 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... - 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... - 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... - 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...
- 09:49 AM rgw Feature #7467: Make radosgw work with multiple hostnames
- 09:20 AM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
- 09:19 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
- actually, seems that the original code is post dumpling.
- 09:13 AM rgw Bug #7453 (Pending Backport): Authentication to keystone using rgw_keystone_admin_* failed
- Pushed, commit:5fb90a2f6dd5b31634efc748a977924dbdbebcb9
- 08:11 AM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
- New signed off patch
- 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... - 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... - 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"...
- 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 ... - 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...- 02:45 AM Bug #7367: fail to run mds and mount rbd (v0.76)
- yes, please
- 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 ...
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...
- 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
- 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...
- 05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- aa110af991e6d637b30d740af46f3dc2168cde01
- 03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
- wip-copyget
- 11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- 05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
- 05:20 PM rgw Bug #7375: s3_user_quota.pl fails
- This is the same issue as 7374.
- 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.
- 05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
- I have pushed a change for this.
- 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. - 04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- The last call will end with abort()...
- 01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- ...
- 10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
- 06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
- crashes on master as of today
- 02:40 PM Bug #7471: ec pools copyfrom broken
- wip-copyget
- 02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
- 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...
- 01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
- This is already done (CORS).
- 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...
- 01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
- 01:33 PM rgw Tasks #5121 (Closed): bump up librados version
- Closing this one.
- 01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
- Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7
- 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
- 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...
- 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...
- 01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
- There's a good chance that this was #7030. Closing.
- 01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
- This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd
- 01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
- Fix looks fine to me. Can you sign-off it?
- 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. ...
- 10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
- 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...
- 10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
- 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
... - 08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
- 08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
- 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... - 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.
- 06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
- crashes, investigating why
- 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
- 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).
- 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...
02/18/2014
- 11:07 PM CephFS Bug #6608: samba teuthology dbench failure
- still see the issue ?
- 10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- wip-strays
- 07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
- 1d907c60d7628429292917fbabf61d09ef8dfa6f
- 04:15 PM Bug #7469: ENXIO on ec pool write
- 04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
- testing wip-primary
- 07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
- Stopping the teuthology run and running the commands manually reveals the following:...
- 06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
- 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:...
- 12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
- 04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
- 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.
- 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-... - 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... - 03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
- Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d
- 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...
- 02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
- 09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
- 02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
- commit:609f4c56718d8279895b02b8163bbe1976c02bfb
- 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.
- 01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 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:...
- 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... - 12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
- 12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
- 12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 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:...
- 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
- 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.
- 12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
- Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e
- 11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
- 11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
- 11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
- 11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7366 (Resolved): EC: scrubbing
- 11:01 AM Feature #7366: EC: scrubbing
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 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
- 11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
- Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b
- 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.
- 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...
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...
- 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.
... - 03:44 PM Bug #7458: osd: stray pg ref on shutdown
- 03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
- ...
- 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... - 02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
- 02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
- 02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
- 02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
- 02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
- 02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
- 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...
- 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=...
- 01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- 01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
- 01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
- reopened #7385
- 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... - 01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
- when this is complete, be sure to fix ceph-qa-suite.git
- 11:08 AM Bug #7212 (Pending Backport): monitor fails to start
- 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, ...
- 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... - 07:32 AM CephFS Bug #7424: Cannot read from zero-length file
- * Strange that it worked without permission. Where had it stored the data?
- 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... - 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.
- 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...
- 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...
- 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...
02/16/2014
- 10:43 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
- 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:...
- 09:46 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
- we missed the backport of commit:b1976dd00f5b29c01791272f63a18250319f2edb
- 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... - 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...
- 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...
- 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....
- 08:27 AM Bug #7371 (Pending Backport): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ...
- 06:33 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- 01:39 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- I applied following patch...
- 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...
02/15/2014
- 10:36 PM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
- 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.
- 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
- 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
- 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
- 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...
- 06:07 PM CephFS Bug #6791 (Won't Fix): mds assert after startup - CDir::commit error (want > commited version)
- 05:00 PM Feature #7058 (Resolved): osd primary affinity
- 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 ...
- 04:23 PM Bug #7445: missing feature bit ( next )
- next is missing "osd crush rule create-erasure":https://github.com/ceph/ceph/commits/cb39b1367676215fc244664d83ffb3e2...
- 04:03 PM Bug #7445 (Rejected): missing feature bit ( next )
- On ea6dc997668df98c0a553d677cf22850b476e412 running *test/mon/osd-pool-create.sh* blocks...
- 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
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:...
- 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...
- 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...
- 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.
- 02:12 PM Feature #7442 (Resolved): mon: health warn on pg "full"
- 02:09 PM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
- 02:04 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 01:59 PM RADOS Feature #7440 (New): erasure-code: adapt scrub/repair teuthology tests for EC and add to nightly
- 01:58 PM Feature #7439 (Resolved): EC: adapt unfound teuthology tests and add to nightly for EC
- 01:58 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
- 01:57 PM Feature #7437 (Resolved): EC: add adapt unittest teuthology task and add to nightly
- 01:42 PM devops Feature #7293: packaging: enable qemu to find librbd on rhev or rhel-osp
- 01:41 PM devops Feature #7436 (Rejected): Build and test RHEL on same subversions.
- 01:39 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
- 01:38 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
- Removed requirement for SLES/OpenSuse. Therefore, completed.
- 01:33 PM devops Feature #7046 (Resolved): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
- 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.
- 01:06 PM rgw Documentation #7434 (Resolved): rgw: doc user/group quota
- 01:05 PM rgw Feature #6339: rgw: compact manifest data
- 01:05 PM rgw Feature #6338: rgw: better manifest scaling
- 11:53 AM rgw Feature #6513 (In Progress): rgw: dr: Service scripts for meta/data sync agents
- 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...
- 09:13 AM devops Bug #7427 (Resolved): sha1 does not exist on gitbuilder, install fails
- ...
- 11:13 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
- After investigating what was returning this message:...
- 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
- 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
- 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 ...
- 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/
<... - 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...
- 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/
... - 06:25 AM CephFS Bug #7424: Cannot read from zero-length file
- do you have selinux enabled
- 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... - 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...
- 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
> [...]
>... - 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:... - 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...
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...
- 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... - 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...
- 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...
- 03:38 PM Bug #7406 (Fix Under Review): Seg fault in find_object_context()in recent master rados run
- Pushed wip-7406
- 11:28 AM devops Bug #7390 (In Progress): ceph-deploy should remove ceph-release and call yum clean all
- 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...
- 10:30 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
- 3e473d4237697872498094b41fed19b414f8d3c4
- 10:06 AM Bug #7212 (Fix Under Review): monitor fails to start
- patch bb863b73c45ce5592844c2c72028ef1cfd9647f8 ; pull request: https://github.com/ceph/ceph/pull/1236
- 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
- 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...
- 02:14 AM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
- Sure, totally agree on the low priority.
- 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...
02/12/2014
- 10:45 PM Bug #7222 (Won't Fix): init-ceph failed when cluster created by "mkcephfs" and start osd firstly ...
- 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...
- 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 (... - 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:...
- 05:57 PM Bug #7408 (Resolved): filestore xattr use omap = true
- will be in next dumpling point release.
- 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.
- 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. ...
- 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...
- 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...
- 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... - 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 ...
- 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...
- 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...
- 12:55 PM Bug #7407 (New): Illogical defaults in Python bindings: conffile=None loads no config, conffile='...
- This feels weird:...
- 02:25 PM Fix #7394 (Fix Under Review): OSD: relax monitor ping requirements while connecting
- PR: https://github.com/ceph/ceph/pull/1227
- 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...
- 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...
- 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*
- 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...
- 12:05 PM devops Bug #7334 (Pending Backport): ceph-disk: cannot run partprobe on used devices with EL6
- Alfredo - please cherry pick to Dumpling
- 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... - 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... - 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...
- 10:08 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
- 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.
- 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), ...
- 09:54 AM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
- 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... - 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 ...
- 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...
- 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
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 ... - 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... - 10:36 PM Bug #7401 (Resolved): rados bench takes into account second '0' for stddev calculation
- For example:...
- 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... - 07:20 PM rgw Bug #7346 (Fix Under Review): An unfound object as part of multi-object delete should return dele...
- 04:48 PM rgw Bug #7346 (In Progress): An unfound object as part of multi-object delete should return deleted i...
- 04:49 PM rgw Bug #7271 (In Progress): container create via swift doesn't register ACL
- 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...
- 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.
- 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,...
- 01:14 PM rbd Bug #7385 (Fix Under Review): Objectcacher setting max object counts too low
- https://github.com/ceph/ceph/pull/1215
- 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...
- 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 ...
- 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 ... - 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...
- 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,
... - 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... - 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 ...
- 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.
- 09:41 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
- yay
- 09:41 AM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
- 09:18 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
- 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...- 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... - 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...
- 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...
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...
- 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
- 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... - 05:57 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
- The (compiled) osdmap attached.
- 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... - 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...
- 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... - 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.
- 04:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
- The problem could also be in the packaging
- 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...
- 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...
- 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...
- 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
- 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
- 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...
- 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:...
- 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...
- 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...- 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...
- 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...
- 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...
- 02:04 PM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
- merged into ceph's master branch af5d0fc
- 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
- 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... - 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...
- 09:51 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
- ...
- 08:58 AM Tasks #7377 (Resolved): security Certificate is out of date
- 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... - 06:45 AM Tasks #7377: security Certificate is out of date
- I think this should be resolved already, based on an email discussion.
- 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... - 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.
...
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/
- 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/
- 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... - 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...
- 03:05 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
- ...
- 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
-... - 10:38 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
- see #7329 for the first two failures.
- 10:38 AM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
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
- 09:14 PM Bug #7329: osd: LibRadosTier.FlushTryFlushRaces failures
- 04:14 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
- "resolved by":https://github.com/ceph/ceph/pull/1201
- 12:20 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
- i broken crush tries behavior when refactoring in commit:27f4d1f6bc32c2ed7b2c5080cbd58b14df622607
- 02:31 PM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
- 471c67828cf98224f89bd8efb28d377f8d745b7a
- 02:30 PM Feature #7366: EC: scrubbing
- 02:30 PM Feature #7361: EC: arrange for chunks to have some padding where we can later add checksums
- 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)
... - 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...
- 02:25 AM Subtask #5857 (Resolved): Refactor recovery to use PGBackend methods
- 02:24 AM Subtask #5856 (Resolved): Refactor Backfill to use PGBackend methods
- 01:39 AM Feature #7195: librados: complete C write object operation bindings
- "implementation":https://github.com/ceph/ceph/commit/33717b4f60ce0ba7088164182b99eaf48cf0486f
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 ... - 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? :)
- 03:45 PM CephFS Fix #7109 (Resolved): disallow removing the first data pool
- Merged into master in commit:4cca38c
- 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... - 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) - 02:16 PM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
- ...
- 01:26 PM Feature #7366 (Resolved): EC: scrubbing
- Fill in the ECBackend methods for shallow and deep scrubbing
- 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... - 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...
- 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 ... - 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...
- 09:13 AM devops Bug #7334 (In Progress): ceph-disk: cannot run partprobe on used devices with EL6
- 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...
- 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... - 04:07 AM Feature #7266: erasure code : implement locality (was pyramid)
- "primary affinity":https://github.com/ceph/ceph/pull/1176
- 12:48 AM rgw Bug #6621 (Resolved): quota: the max-size and max-objects value when zero
- 12:29 AM rgw Bug #6621 (In Progress): quota: the max-size and max-objects value when zero
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/...
- 09:32 PM Fix #6483 (Fix Under Review): osd: does not fill in OSDOp::rval member
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Feature #7194 (Fix Under Review): librados: omap in the c api
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Feature #7193 (Fix Under Review): librados: object operation bindings for reads
- https://github.com/ceph/ceph/pull/1195
- 09:31 PM Bug #7250 (Fix Under Review): osd: string xattr comparison can have undefined behavior
- https://github.com/ceph/ceph/pull/1195
- 09:30 PM Feature #7195 (Fix Under Review): librados: complete C write object operation bindings
- https://github.com/ceph/ceph/pull/1195
- 07:53 PM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
- 07:52 PM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
- nvm
- 07:18 PM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
- 42a64e19b7a06c1b3e0fd40e2d9c572103e3e426
- 03:07 PM Bug #7355 (In Progress): assert(0) in_make_pg() because EC getting enabled
- 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...
- 11:45 AM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
- 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... - 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
- 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...
- 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...
- 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...
- 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
- 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 ?
- 02:18 AM Subtask #7292: erasure code: plugin backward compatibility
- "work in progress":https://github.com/ceph/ceph/pull/1193
- 01:45 AM Subtask #7292 (In Progress): erasure code: plugin backward compatibility
- 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...
- 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... - 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...- 11:12 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
- Duplicate of #7336. Already fixed on next.
- 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/
... - 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...
- 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 ...
- 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... - 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
- 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... - 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
- 06:57 AM CephFS Feature #7352 (In Progress): mds: make classes encode/decode-able
- 06:55 AM CephFS Feature #7352 (Resolved): mds: make classes encode/decode-able
- 06:54 AM CephFS Feature #7319 (In Progress): qa: multimds, no failure
- 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
- 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...
- 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.
...
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:
... - 04:42 PM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
- 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
- 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... - 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... - 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...
- 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...
- 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... - 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
... - 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 ...
- 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...
- 11:46 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 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...- 10:20 AM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 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...
- 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...
- 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 - 09:26 AM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
- Merged into ceph-deploy's master branch with hash c036cbd
- 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
- 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.
- 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...
- 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...
- 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 ... - 01:45 AM Feature #7340 (Duplicate): rados.py does not expose object locking
- Commit d8415663b62edb812d087cba40b03b933e3e4556 exposed @rados_lock_exclusive()@, @rados_lock_shared()@, @rados_unloc...
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...
- 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...
- 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...
- 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.
- 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... - 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...
- 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... - 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...
- 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... - 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... - 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.
- 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... - 12:00 PM Bug #6685 (Fix Under Review): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present ...
- 10:48 AM rgw Bug #7336 (Fix Under Review): rgw: limit on list buckets broken
- 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.
- 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...
- 03:11 AM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
- 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-... - 07:02 AM CephFS Feature #7319: qa: multimds, no failure
- Enable the marginal suite multi-mds tests.
- 06:59 AM CephFS Feature #7316: improve mds state dumps (memory usage, completeness)
- https://wiki.ceph.com/Planning/Sideboard/mds%3A_dumpability
- 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...
- 06:50 AM CephFS Fix #7109 (Fix Under Review): disallow removing the first data pool
- https://github.com/ceph/ceph/pull/1173
- 05:50 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
- ...
- 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... - 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 ... - 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... - 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... - 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
- 03:00 AM Subtask #7146 (Resolved): implement osd crush rule create-erasure
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...
- 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... - 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... - 12:37 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- didn't mean to change these
- 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...
- 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 ... - 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...
- 05:22 PM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
- 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....
- 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...
- 05:28 PM CephFS Bug #6623 (Resolved): mds: update backtraces on existing clusters
- 05:27 PM CephFS Feature #1448 (Resolved): test hadoop on sepia
- 05:25 PM CephFS Bug #4489 (Can't reproduce): ceph fs hangs on file stat
- 05:25 PM CephFS Bug #5485 (Can't reproduce): failed cifs mount
- 05:23 PM CephFS Bug #4685 (Can't reproduce): BUG: unable to handle kernel NULL pointer dereference at
- 05:20 PM CephFS Bug #5753 (Duplicate): ceph-fuse: segfault when getting back a traceless rename op
- 05:19 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
- 05:18 PM CephFS Bug #4909 (Can't reproduce): mds: stalled/stuck directory (standby)
- 05:01 PM CephFS Feature #3863: implement a tool to lookup inode numbers without holding their path
- 05:01 PM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
- 05:00 PM CephFS Feature #1693 (Resolved): libcephfs: Support TRIM (hole punching)
- 04:59 PM CephFS Feature #3867 (Resolved): optionally do not use an anchor table
- 04:58 PM CephFS Cleanup #2177 (Resolved): mds: play nicely with omap
- 04:58 PM CephFS Feature #7326 (New): qa: fix flock tests
- 04:57 PM CephFS Feature #7325 (New): mds: tool to examine (later, manipulate) dirfrag objects
- 04:57 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
- 04:56 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
- 04:55 PM CephFS Feature #7322 (New): qa: inline data + thrashing
- 04:55 PM CephFS Feature #7321 (Duplicate): qa: multimds thrasher
- 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
- 04:54 PM CephFS Feature #7319 (Resolved): qa: multimds, no failure
- 04:54 PM CephFS Feature #7318 (Duplicate): qa: ceph-fuse + sync mode
- 04:53 PM CephFS Feature #7317 (Resolved): mds: behave with fs fills (e.g., allow deletion)
- 04:53 PM CephFS Feature #7316 (New): improve mds state dumps (memory usage, completeness)
- 04:52 PM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
- 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
- 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
- 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 ... - 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 ... - 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:
... - 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-... - 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... - 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...
- 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 ... - 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... - 11:26 AM Bug #7178 (Resolved): sample.ceph.conf needs update
- commit:e268e9562dd0831fe40702e56bfbdf8f6cb80b1a
- 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... - 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... - 07:37 AM devops Bug #7311 (Closed): GPG/packaging failures
- apt complained throughout the install process...
- 07:25 AM rbd Bug #7310 (Can't reproduce): rbd snap unprotect test failing
- ...
- 06:51 AM CephFS Bug #5411 (Resolved): teuthology: bad object dereference
- 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...
02/02/2014
- 05:19 PM Feature #7058 (Fix Under Review): osd primary affinity
- 05:18 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 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... - 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...
- 05:51 AM Subtask #7146 (Fix Under Review): implement osd crush rule create-erasure
- "work in progress":https://github.com/ceph/ceph/pull/1144
- 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
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...
- 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
- 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). - 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...
- 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 ...
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 ...
- 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...
- 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... - 02:39 PM Documentation #6547: should document magic data/journal partition types
- No, thanks, fixed
- 02:34 PM Documentation #6547: should document magic data/journal partition types
- hmm, is this meant to be in the calamari product?
- 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 ... - 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...
- 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...
- 01:58 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
- 01:57 PM Feature #7034: cachepool: agent: basic eviction
- 01:56 PM Feature #7033: cachepool: agent: trivial flushing
- 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...
- 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.
- 01:24 PM devops Feature #7047 (In Progress): rhel7: build process for rbd.ko, ceph.ko kernel modules
- 01:24 PM devops Feature #7046 (In Progress): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
- 01:22 PM devops Feature #7094 (Resolved): f20 gitbuilder
- 01:22 PM devops Fix #7095 (Resolved): fix f19 gitbuilder
- 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...
- 12:54 PM rgw Feature #6338 (In Progress): rgw: better manifest scaling
- 12:54 PM rgw Feature #6339 (In Progress): rgw: compact manifest data
- 12:32 PM Subtask #5861 (Resolved): Refactor scrub to use PGBackend methods
- dffe6019c3698ca1661c94984df9629241c3e1ef
- 12:31 PM Feature #5997 (Resolved): EC: [link] Refactor scrub to use PGBackend methods
- dffe6019c3698ca1661c94984df9629241c3e1ef
- 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 ... - 10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
- 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...
- 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...
- 10:22 AM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
- 10:12 AM Bug #7256: ceph osd crashed at ReplicatedPG::trim_object on next
- maybe dup of #6101 ?
- 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...
- 09:49 AM CephFS Fix #7109: disallow removing the first data pool
- https://github.com/ceph/ceph/pull/1173
- 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 ...
- 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... - 12:47 AM rbd Bug #7076 (Resolved): rbd: check for watchers before removing an image
01/30/2014
- 06:45 PM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
- 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... - 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
- 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
- 10:53 AM Feature #7059 (Resolved): filestore: avoid leveldb check for xattr when possible
- 10:38 AM Feature #5997: EC: [link] Refactor scrub to use PGBackend methods
- 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.
- 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 ... - 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...
- 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 ... - 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:...
- 09:16 AM Bug #7258 (Resolved): ceph-disk: many calls do not work if command is not in PATH
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...
- 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
- 09:44 PM Feature #6960 (Closed): DBObjectMap: refactor interface
- 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...
- 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... - 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...
- 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... - 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... - 02:20 PM Feature #7247: EC: distinguish is_missing from is_readable
- 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...
- 01:32 PM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
- 01:32 PM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
- 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... - 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... - 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.
- 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?
- 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...
- 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...
- 07:12 AM Feature #6173 (Resolved): Add LevelDB support to ceph cluster backend store
- 07:12 AM Bug #6950 (Resolved): refactor OSD awareness of FileStore to make the ObjectStore backend configu...
- 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
Also available in: Atom