Activity
From 09/19/2013 to 10/18/2013
10/18/2013
- 11:22 PM Bug #6597 (Resolved): rados cls dlopen errors
- ...
- 11:07 PM Bug #6582 (Resolved): osd: copy_from vs read ordering broken
- 10:13 PM Bug #6582: osd: copy_from vs read ordering broken
- wip-6582 seems to be looping successfully without hitting this issue any more.
- 04:39 PM Bug #6582 (Fix Under Review): osd: copy_from vs read ordering broken
- Pushed wip-6582 which should correct this. It passes my basic local copy-from test but I'm waiting for it to build so...
- 03:12 PM Bug #6582: osd: copy_from vs read ordering broken
- And that's all on me; I ripped out Sage's mechanism for it when removing some other extraneous code. :(
- 02:51 PM Bug #6582: osd: copy_from vs read ordering broken
- Let's clear up the timeline a bit here. Before any of this, object plana885194-10 actually already exists. Then, on o...
- 06:06 PM Bug #6593 (Duplicate): osd: copy-from object blocking clashes with recovery
- sounds like a dup of #6585
- 01:48 PM Bug #6593 (Duplicate): osd: copy-from object blocking clashes with recovery
- ...
- 05:05 PM rgw Bug #6571 (Resolved): apache2 errors in nightly
- 04:50 PM Bug #6451 (Resolved): btrfs async transactions deadlock on 3.12-rcwhatever
- 09:19 AM Bug #6451: btrfs async transactions deadlock on 3.12-rcwhatever
- 04:35 PM Bug #6585: osd: backfill vs copy-from delay badness (was osd: ENOENT on clone)
- Once we are ready to actually move the object into place we need to consider the possibility that backfill is now blo...
- 03:08 PM Feature #6594 (Resolved): allow to have more than one PG implementation
- Hi, I'm marking this ticket as resolved since you've completed the proof of concept you were after.
- 02:07 PM Feature #6594 (Resolved): allow to have more than one PG implementation
- In order to fulfill feature #4928 [ http://tracker.ceph.com/issues/4929 ] ceph needs to allow to have more than one P...
- 03:05 PM Feature #6414 (In Progress): filestore: make read() use a bufferlist method
- 03:05 PM Feature #6415 (In Progress): buffer: instrument c_ptr() calls
- 03:05 PM devops Bug #6595 (Resolved): Hardcoded install path in ceph-disk
- I noticed that ceph-disk assumes that ceph was installed to /usr/bin . I believe it would be better to take a more fl...
- 12:24 PM devops Bug #6592: 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/by-partuuid
- The full chat log about research on this problem:...
- 12:23 PM devops Bug #6592 (Can't reproduce): 3.8 kernel + /dev/cciss/c0d1 + precise : fail to show in /dev/disk/b...
- After *ceph-deploy create osd* the osd fails to start because the journal can't be found...
- 12:17 PM devops Bug #6588: use WARNING level when keyring does not exist
- FWIW, this kind of warning happen when ceph-deploy is used with cephx disabled. It does not prevent the deployment of...
- 07:39 AM devops Bug #6588 (Resolved): use WARNING level when keyring does not exist
- ceph-deploy currently uses INFO to log output about keyring files that do not exist and need to be created.
This c... - 11:42 AM devops Bug #6591 (Resolved): init script does not pass alternate configuration file to osd crush create-...
- This leads to OSDs starting without being added to the CRUSH map. I ran into this bootstrapping a cluster with a nam...
- 11:40 AM rbd Documentation #5009 (Resolved): doc: explain how to get qemu packages for each distro
- Undergoing IA, but is presently included. It is only needed for RPM, as Ceph builds them and the priority must be ove...
- 11:39 AM Documentation #6464 (Resolved): dangling links to install-chef.rst
- See http://ceph.com/docs/master/rados/operations/add-or-rm-osds/
- 11:34 AM devops Bug #6590 (Resolved): Ceph Package Dependencies not Included in Ceph Extras
- When a user wants to install Ceph manually, they can download the Ceph packages and install them. However, the instal...
- 11:20 AM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- This bug resurfaced in QA, in a v0.61.7 cluster. After looking into the store of the affected monitor and some logs,...
- 10:36 AM Subtask #6391: stuck incomplete
- Here goes nuttin', from what Sam says... ;)
- 10:04 AM devops Bug #6589 (Duplicate): Get ceph-deploy docs to be Sphinx built
- We just have a poor README.rst that is too disorganized. Have a properly built Sphinx doc built, with tox calls so we...
- 09:38 AM rbd Bug #6576: librbd: test_librbd_fsx segfaults on start up on 32-bit arm
- This should be worked as part of the ARM support effort
- 09:36 AM Bug #6575: messenger: failed assert(pipes.count(p)) in reaper
- 08:11 AM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Azrael (who works with saaby) looked through logs... 1.3 million slow request warnings during their recovery. On my c...
- 05:54 AM devops Bug #6587 (Resolved): ceph-deploy does not use cluster arg for mon error checking
- In the new functionality for error checking in v1.2.7 the cluster argument
was not used and it produces errors as th... - 02:40 AM Subtask #6586 (Resolved): ErasureCodeJerasure::decode does not use want_to_read
- "ErasureCodeJerasure::decode":https://github.com/ceph/ceph/blob/812234cb09d5c4a868204fdf79fc06a4e376611e/src/osd/Eras...
10/17/2013
- 09:17 PM Bug #6585: osd: backfill vs copy-from delay badness (was osd: ENOENT on clone)
- 05:59 PM Bug #6585: osd: backfill vs copy-from delay badness (was osd: ENOENT on clone)
- around 16:27:52.761566 in osd.5 log there isa modify that happens right in the middle of the same object being backf...
- 05:46 PM Bug #6585: osd: backfill vs copy-from delay badness (was osd: ENOENT on clone)
- dump of the jouranl is in the dir now. i see a transaction taht deletes the object and starts writing to a temp obje...
- 05:19 PM Bug #6585 (Resolved): osd: backfill vs copy-from delay badness (was osd: ENOENT on clone)
- with logs!...
- 09:11 PM rgw Bug #6475 (Resolved): rgw: Log directory should not be created by the init script
- awesome, merged it in. thanks!
- 09:02 PM rgw Bug #6475: rgw: Log directory should not be created by the init script
- Debian looks good.
- 08:28 PM rgw Bug #6475: rgw: Log directory should not be created by the init script
- I've confirmed that the rpm fix is correct with one change:
diff --git a/ceph.spec.in b/ceph.spec.in
index d6cc63... - 05:49 PM Fix #6242 (Fix Under Review): ceph CLI should honor `--help` and not return log lines back
- https://github.com/ceph/ceph/pull/739
This turned out to not be a huge deal, although I did not try and suppress the... - 04:25 PM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- Need to figure out how the ceph tool works these days to fix this up, but I'm diving in.
- 05:28 PM Documentation #6127 (Resolved): CEPH_ARGS example for RHEL
- commit:533626c7e0b3e0bed55f6db92f52f64b29e532aa
- 04:31 PM Documentation #6127: CEPH_ARGS example for RHEL
- resolved by https://github.com/ceph/ceph/pull/737
- 04:51 PM Bug #6583 (Resolved): crc caching makes CopyPP test hang
- 04:10 PM Bug #6583 (Resolved): crc caching makes CopyPP test hang
- reproducible with vstart on master and ceph_test_rados_api_misc
- 03:21 PM Bug #6574: osd/ReplicatedPG.cc: 7851: FAILED assert(0)
- ~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-6574" -n 2 --owner samuelj@slider testrun...
- 03:03 PM Bug #6581 (Duplicate): osd: ceph_test_rados version mismatch from copy_from during thrashing
- #6582
- 02:22 PM Bug #6581 (Duplicate): osd: ceph_test_rados version mismatch from copy_from during thrashing
- ...
- 02:42 PM Bug #6582 (Resolved): osd: copy_from vs read ordering broken
- note uv 419 vs uv 499 on replies...
- 02:00 PM devops Feature #3347 (Fix Under Review): ceph-deploy: allow setting ssh user
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/109
- 01:59 PM devops Bug #6579 (Resolved): provide more verbose logging when mds fails
- Merged into master branch of ceph-deploy: 30f0491
- 06:42 AM devops Bug #6579 (Fix Under Review): provide more verbose logging when mds fails
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/108
- 05:34 AM devops Bug #6579 (Resolved): provide more verbose logging when mds fails
- For some reason the failure to create mds in ceph-deploy is not getting output to stderr, so it needs
log back stdou... - 12:04 PM Bug #6456 (Resolved): scripts still installing into /usr/usr/sbin
- Alan Somers wrote:
> Works for me on Ubuntu 12.04 and FreeBSD 9.1. But I'm curious, why do you no longer install mo... - 11:51 AM Bug #6456: scripts still installing into /usr/usr/sbin
- Works for me on Ubuntu 12.04 and FreeBSD 9.1. But I'm curious, why do you no longer install mount.ceph to /sbin?
- 11:29 AM devops Bug #6551 (Resolved): ceph-deploy copy config and key to cluster failure
- merged into ceph-deploy master branch: 0df07ba
- 06:50 AM devops Bug #6551 (Fix Under Review): ceph-deploy copy config and key to cluster failure
- Should be fixed with this pull request: https://github.com/ceph/ceph-deploy/pull/107
- 11:26 AM devops Bug #6580 (Resolved): make configuration write more robust
- Merged into ceph-deploy master branch: 0df07ba
- 06:37 AM devops Bug #6580 (Fix Under Review): make configuration write more robust
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/107
- 05:46 AM devops Bug #6580 (Resolved): make configuration write more robust
- ceph-deploy doesn't check much except to avoid overwriting remote ceph configs.
If for some reason the path to wri... - 11:24 AM devops Bug #6578 (Resolved): ceph-deploy fails to detect RedHat as a supported platform
- Merged into ceph-deploy master branch with hash: 19249f2
- 06:11 AM devops Bug #6578 (Fix Under Review): ceph-deploy fails to detect RedHat as a supported platform
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/106
- 05:28 AM devops Bug #6578 (Resolved): ceph-deploy fails to detect RedHat as a supported platform
- When using platform detection via Python, the OS distro name can come back as 'red hat enterprise linux server' but c...
- 10:24 AM rgw Bug #6571: apache2 errors in nightly
- 10:14 AM Bug #6565 (Resolved): stuck in recovery_wait
- 15ec5332ba4154930a0447e2bcf1acec02691e97
- 08:58 AM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- I believe saaby just saw the same thing on his cluster. Details here:
http://irclogs.ceph.widodh.nl/index.php?date... - 08:50 AM rgw Feature #3454: Support temp URLs for Swift API
- Bump .. would really love to see this feature in there.
We are deploying Cloud Foundry v2 into Openstack, and want t...
10/16/2013
- 05:48 PM CephFS Bug #6450: Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- Jens-Christian Fischer wrote:
> we have now upgraded the complete cluster to Dumpling (0.67.3) (also due to other pr... - 05:41 PM Subtask #6391: stuck incomplete
- 10:31 AM Subtask #6391: stuck incomplete
- ubuntu@teuthology:/a/teuthology-2013-10-15_18:01:09-rados-next-testing-basic-plana/53636
- 04:38 PM rbd Bug #6577: arm testing: rbd test segfaults at FAILED assert((bool)_front == (bool)_size)
- the logs are copied to ubuntu@mira055.front.sepia.ceph.com:/home/ubuntu/bug_6577
- 04:27 PM rbd Bug #6577 (Can't reproduce): arm testing: rbd test segfaults at FAILED assert((bool)_front == (bo...
- rbd test - test_librbd.sh fails on the arm setup
ceph version: dumpling [0.67.4]... - 04:38 PM Feature #6419 (In Progress): buffer: make write_fd use splice where possible
- 04:38 PM Feature #6417 (In Progress): buffer: make read use raw_pipe() where possible
- 04:25 PM CephFS Bug #6279 (Resolved): creating a new fs on pools from an old fs can lead to lost MDS Tables
- Oh, this is already backported, commit:bd073eeac28d8cba969e5746c5e6adcb95820fdf
- 04:23 PM CephFS Bug #4405 (Resolved): MDCache::populate_mydir can loop forever
- Cherry-picked to dumpling branch in commit:299ddd31b29e332dc5e76bc4f871e4769698665d
- 04:11 PM rbd Bug #5220: test_ls_snaps segfaults on the arm test setup
- config file used:...
- 03:47 PM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
- Like Sage said, blacklisting. :)
It's been a while but I think the scenario I envisioned here is one in which the or... - 02:58 PM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
- https://github.com/ceph/ceph/pull/733
- 09:55 AM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
- Possibly related to #6548.
- 03:08 PM Bug #6451: btrfs async transactions deadlock on 3.12-rcwhatever
- ubuntu@teuthology:/a/sage-2013-10-16_13:46:50-rados:thrash-next-master-basic-plana/55002
- 02:49 PM Bug #6451: btrfs async transactions deadlock on 3.12-rcwhatever
- hung tasks dump attached
- 02:30 PM rbd Bug #6139 (Closed): kernel panic in vms during disk benchmarking
- Andrei Mikhailovsky wrote:
> Sage, I am using virtio to start my vms. by default cloudstack starts vms with virtio, ... - 02:20 PM rbd Bug #6576 (Resolved): librbd: test_librbd_fsx segfaults on start up on 32-bit arm
- This occured in several runs with various configurations on the same hardware.
From http://qa-proxy.ceph.com/teuth... - 02:16 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
- This occurred with the following teuthology config on 32-bit arm:...
- 01:38 PM devops Feature #3347 (In Progress): ceph-deploy: allow setting ssh user
- 01:11 PM Bug #6574 (Resolved): osd/ReplicatedPG.cc: 7851: FAILED assert(0)
- -1> 2013-10-15 20:34:57.857980 7f8cf5a76700 5 --OSD::tracker-- reqid: unknown.0.0:0, seq: 20315, time: 2013-10-1...
- 12:54 PM Feature #6409 (Resolved): buffer: cache crc values
- 12:54 PM Feature #6408 (Resolved): crc: unit test demonstrating crc for concatenation of string
- 10:50 AM devops Bug #6482: ceph-deploy install on Centos: can't find wget?
- Alfredo Deza wrote:
> I want to rule out that this is not a problem of `wget` not being installed (would be odd) or ... - 10:41 AM rbd Bug #5425: krbd: xfstest 89 hang, 'read_partial_message skipping long message'
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-10-15_23:02:48-krbd-next-testing-basic-plana/54525
- 10:33 AM rgw Bug #6571 (Resolved): apache2 errors in nightly
- this looks suspicious:...
- 10:14 AM Bug #5818 (Resolved): leveldb 1.12: hang on shutdown (mon)
- 10:14 AM Bug #5754 (Resolved): mon: occasional osd full map not trimmed
- 10:14 AM Bug #5700: very high memory usage after update
- I created #6570 for that, Corin. There are tradeoffs involved and some of them are probably worth making, but it's no...
- 10:13 AM RADOS Fix #6570 (New): osd: do not keep full pg log entries in memory
- Right now, we keep the full pg log in memory. Each of these entries contains the name of the object involved, which m...
- 09:54 AM CephFS Bug #6458: journaler: journal too short during replay
- Hmmm, definitely possible. That ticket isn't exactly a certain diagnosis either, though. :(
- 07:13 AM CephFS Bug #6458: journaler: journal too short during replay
- maybe this is the same as #4708. Two MDS (one mds is supposed to be dead, but it's not ) modified the log at the same...
- 09:49 AM Bug #6565: stuck in recovery_wait
- For Recovery and Backfill reservations, we don't check whether the target pg is currently splitting. Working on patc...
- 09:45 AM devops Bug #6569 (Resolved): ceph-deploy errors with local connections and sudo python
- Opened PR https://github.com/ceph/ceph-deploy/pull/105
Merged into master with hash: 082992a
But that is just t... - 07:31 AM devops Bug #6569 (Resolved): ceph-deploy errors with local connections and sudo python
- For ceph-deploy to have super user permissions and do local executions it creates the gateway with `python=sudo pytho...
- 05:22 AM Feature #6568 (New): ceph-rest-api authentication
- Hi All,
When using the radosgw admin API, I have to provide an AWS authorization header to requests and also ensur... - 01:19 AM rgw Bug #6152: New S3 auth code fails when using response-* query string params to override response ...
- That commit has nothing to do with this issue ... this commit is from Februrary and related to duplicate content type...
- 12:10 AM Bug #6484: osd pool default flag hashpspool not honored
- Ok, after moving the directive to the [mon] section is seems to work. At least the new pool now has the addition "fla...
- 12:09 AM Feature #6567 (Rejected): emit warning on unknown/ invalid configuration directives
- Afaik, ceph does not complain at all when invalid/ unknown configuration directives are in the config file. I'd like ...
10/15/2013
- 11:51 PM Bug #5700: very high memory usage after update
- Allow me this last question: why has all this log information be kept in memory all the time?
- 01:53 PM Bug #5700 (Resolved): very high memory usage after update
- after reviewing this again, there are 2 things:
1- the default # of pg log entires increased from bobtail to cuttl... - 07:16 PM rbd Bug #6495: Cpu load on cluster node is very high every has the write request to cluster
- Is there configuration to QoS for each client to help limit the i/o requests send to ceph cluster from rbd ?
- 07:11 PM rbd Bug #6495: Cpu load on cluster node is very high every has the write request to cluster
- yes,there was a problem with the high cpu load. It made all system slower or couldn't receive any request from client...
- 01:29 PM rbd Bug #6495 (Need More Info): Cpu load on cluster node is very high every has the write request to ...
- it is normal for writes to generate more load than reads (they are replicated after all). is there anything that ind...
- 06:07 PM rgw Documentation #6566: Improved documentation of common RADOS GW procedures
- I should have added that the text above is actually not from myself, but this is feedback from a production user.
- 06:03 PM rgw Documentation #6566 (New): Improved documentation of common RADOS GW procedures
- I have executed the Rados GW procedures as documented. I have successfully connected to the S3 interface, so I know t...
- 05:12 PM rgw Bug #5716 (Resolved): radosgw-admin: does not validate pool name when creating region
- Fixed, commit:c7acc2aee2f4aef19386ede46b4562b6552a3955
- 04:55 PM Bug #6565: stuck in recovery_wait
- 2013-10-15 15:14:21.293917 7f2dbbe7f700 5 osd.1 pg_epoch: 753 pg[1.30( v 6'4 (0'0,6'4] local-les=753 n=4 ec=1 les/c ...
- 04:41 PM Bug #6565 (Resolved): stuck in recovery_wait
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-10-15_11:06:15-rados-next-testing-basic-plana/53130
- 04:00 PM Bug #6528 (Resolved): btrfs osd gets kicked out while removing large pg
- 01:33 PM Bug #6528 (Fix Under Review): btrfs osd gets kicked out while removing large pg
- 01:07 PM Bug #6528 (In Progress): btrfs osd gets kicked out while removing large pg
- 01:07 PM Bug #6528: btrfs osd gets kicked out while removing large pg
- Ah, we don't ping the tphandle during that process, creating patch!
- 03:46 PM Feature #6189: cachepool: osd: promote on read
- Added a few more tests, and more carefully segregated those that exist, to caching_redirects.sh.
- 03:44 PM rbd Bug #6139: kernel panic in vms during disk benchmarking
- Sage, I am using virtio to start my vms. by default cloudstack starts vms with virtio, however, the cache settings ar...
- 02:49 PM rbd Bug #6139 (Need More Info): kernel panic in vms during disk benchmarking
- please try virtio. this looks like a combination of a bad ata driver and rados being slow...
- 03:40 PM Bug #6550 (Resolved): mon/DataHealthService.cc: 131: FAILED assert(store_size > 0)
- 08:26 AM Bug #6550 (Resolved): mon/DataHealthService.cc: 131: FAILED assert(store_size > 0)
- ...
- 03:35 PM rgw Bug #6449: Initiating multipart upload fails with no Content-Length header being set
- Hmm, looking at it now, we don't test for content length existence as the request itself doesn't have any input data....
- 03:21 PM Bug #6456 (Fix Under Review): scripts still installing into /usr/usr/sbin
- can you look at https://github.com/ceph/ceph/pull/725 ?
- 03:04 PM rgw Bug #6553 (Resolved): rgw: authenticated users group permissions not working
- 12:28 PM rgw Bug #6553 (Fix Under Review): rgw: authenticated users group permissions not working
- 09:38 AM rgw Bug #6553 (Resolved): rgw: authenticated users group permissions not working
- 03:03 PM rgw Bug #6334 (Resolved): RGW admin socket doesn't appear to exist by default
- 02:35 PM rgw Bug #6334 (Fix Under Review): RGW admin socket doesn't appear to exist by default
- 03:02 PM rbd Bug #5812 (Closed): qemu-kvm guest hangs on disk write with rbd storage
- Closing due to inactivity - please reopen if it's still an issue.
- 02:58 PM rbd Bug #6265 (Resolved): krbd: blockdev --setr{o,w} claims success but has no effect
- commit 1a56f326b7d4cfdeb82d0071688732f269994884
Author: Guangliang Zhao <guangliang@unitedstack.com>
Date: Tue Se... - 02:57 PM rbd Bug #6386 (Can't reproduce): ceph-osd processes are having hang tasks
- 02:56 PM rbd Bug #4959 (Closed): xfstest 17 failure
- 02:56 PM rbd Bug #4563 (Closed): rbd xfstests: test 167 failing
- 02:56 PM rbd Bug #3685 (Closed): xfs test 186 fails in the nightlies
- 02:56 PM rbd Bug #4242 (Closed): krbd: xfstest 259 failure (FS size near 4TB)
- 02:45 PM rbd Bug #4242 (New): krbd: xfstest 259 failure (FS size near 4TB)
- 02:56 PM rbd Bug #3449 (Closed): fix xfstest 45 on precise
- 02:56 PM rbd Bug #2608 (Closed): rbd: hung xfstest 270
- 02:56 PM rbd Bug #2410 (Closed): hung xfstest #68
- 02:56 PM rbd Bug #2522 (Closed): xfstest #219
- 02:53 PM rbd Bug #5032 (Closed): xfstest 269 failure
- 02:52 PM rbd Bug #5425: krbd: xfstest 89 hang, 'read_partial_message skipping long message'
- Date: Mon, 14 Oct 2013 18:21:48 -0700
From: Josh Durgin <josh.durgin@inktank.com>
To: Sage Weil <sage@inktank.com>,... - 02:43 PM rbd Bug #3978 (Resolved): krbd qa: concurrent.sh test leaves something read-only
- 02:42 PM rbd Bug #4661 (Can't reproduce): xfstest 139 hung
- 02:38 PM rbd Bug #4661 (New): xfstest 139 hung
- 02:42 PM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Hey, any update on this one?
- 02:41 PM rbd Bug #6267 (Resolved): krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- 02:40 PM rgw Bug #5245 (Can't reproduce): Frequent 500s from radosgw
- 02:36 PM rgw Bug #6134 (Resolved): RGW returns an error on set_worker_bound if a zone's log_pool doesn't alrea...
- 02:36 PM rgw Bug #6134: RGW returns an error on set_worker_bound if a zone's log_pool doesn't already exist
- Fixed, commit:4216eac0f59af60f60d4ce909b9ace87a7b64ccc
- 02:27 PM rgw Bug #6475 (Fix Under Review): rgw: Log directory should not be created by the init script
- https://github.com/ceph/ceph/pull/722
- 02:27 PM rgw Bug #6208 (Can't reproduce): rgw: md5 checksum failed on readwrite during upgrade-next tests
- 02:18 PM Bug #3996 (Resolved): mon: 'ceph mon add' results in dubious return message
- 02:17 PM Bug #4036 (Resolved): init-ceph: assumes write access to /var/run/ceph
- 02:14 PM Bug #5869 (Resolved): osd/OSD.h: 447: FAILED assert(ret) in get_map
- 02:10 PM Bug #5869: osd/OSD.h: 447: FAILED assert(ret) in get_map
- c8a4411db11b085ea0678bcf3f51aa411bd3e106
- 02:06 PM Bug #4185 (Won't Fix): Python multiprocessing exhibiting odd behaviour with librados
- Multiprocessing forks, and that's a problem.
- 02:03 PM Bug #5175 (Resolved): leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- 01:57 PM Bug #5823 (Need More Info): cpu load on cluster node is very high, client can't get data on pg f...
- This is only happening on a particular node? Is this still a problem?
- 01:55 PM devops Bug #6485 (Resolved): purgedata should not remove /etc/ceph dir
- It now will only remove the contents of /etc/ceph/
Merged into ceph-deploy master branch with hash: 946fc54 - 01:54 PM rgw Bug #6505 (Resolved): ceph-deploy osd activate may sit undefinatly (centos)
- Fixed by setting a global timeout of 300 seconds for all remote connections.
Merged into ceph-deploy master br... - 01:52 PM devops Bug #6491 (Closed): During mon create: <type 'exceptions.TypeError'>: 'NoneType' object is not ca...
Merged into ceph-deploy master branch with hash: 946fc54- 06:03 AM devops Bug #6491 (Fix Under Review): During mon create: <type 'exceptions.TypeError'>: 'NoneType' object...
- To be fixed by pull request: https://github.com/ceph/ceph-deploy/pull/104
- 01:51 PM devops Bug #5944 (Closed): ceph-deploy osd needs to be moved to use the new remote helpers
Merged into ceph-deploy master branch with hash: 946fc54- 06:04 AM devops Bug #5944 (Fix Under Review): ceph-deploy osd needs to be moved to use the new remote helpers
- 06:03 AM devops Bug #5944: ceph-deploy osd needs to be moved to use the new remote helpers
- Would be fixed by PR 104: https://github.com/ceph/ceph-deploy/pull/104
- 01:50 PM Bug #6112 (Resolved): rgw test failed in the nightly during upgrade from dumpling to next
- the tests pass in the nightlies now.
- 01:49 PM devops Bug #6487 (Closed): remove pushy from ceph-deploy
- PR was opened: https://github.com/ceph/ceph-deploy/pull/104
And it was merged with hash: 946fc54 - 01:47 PM Bug #6390 (Need More Info): ENOTEMPTY on TEMP coll on replay
- 01:47 PM Bug #6441: msgr: leak of tls from delay thread
- i believe it is the msgr delay injection that triggers this. see the config from the referenced run.
- 01:45 PM Bug #6122 (Resolved): osd: rados cmd.cc test does not tolerate thrashing
- 01:39 PM Bug #5951 (Need More Info): osd: next: EEXIST on mkcoll
- 01:39 PM Bug #6207 (Need More Info): Found incorrect object contents
- 12:53 PM Bug #6207: Found incorrect object contents
- Oportunistic checksums are enabled by default for xfs and btrfs in the nightlies at the moment. Nothing so far?
- 01:39 PM Subtask #6391 (Need More Info): stuck incomplete
- 12:51 PM Subtask #6391: stuck incomplete
- [note for bug scrub] Will need to reproduce in order to make progress. May not be urgent.
- 01:37 PM Bug #6381 (Resolved): need apache-fastcgi packages built for fedora and debian
- 01:32 PM Bug #6118 (Can't reproduce): failed to recover before timeout expired on radosbench, rados api tests
- 01:00 PM Bug #6118: failed to recover before timeout expired on radosbench, rados api tests
- Much of the code has been replaced as part of 5992, might be worth closing for now.
- 01:26 PM Bug #6504 (Resolved): PATCH: Fix double-free of fiemap
- moved one of the free(fiemap) calls in a block and then merged to master. thanks!
- 01:06 PM Bug #6510 (Resolved): PATCH: Fix segfault when ceph_dencoder is called with test number 0 on a cl...
- applied, thanks!
- 12:59 PM Bug #6400 (Duplicate): osd crashed in dumpling due to unexpected error (EEXIST?)
- No logs, probably dup of 5951.
- 12:57 PM Bug #6447 (Resolved): osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log....
- 0c2769d3321bff6e85ec57c85a08ee0b8e751bcb
- 12:49 PM Bug #6484 (Resolved): osd pool default flag hashpspool not honored
- it is now possible to add the flag to an existing pool in master. this will be in emperor.
the option works too, ... - 12:33 PM rgw Bug #6554 (Resolved): rgw: default log is too verbose
- 12:28 PM rgw Bug #6554 (Fix Under Review): rgw: default log is too verbose
- 10:23 AM rgw Bug #6554 (Resolved): rgw: default log is too verbose
- 12:15 PM Bug #6521 (Resolved): ceph health hung after upgrading the cluster from bobtail to dumpling to next
- 09:07 AM devops Bug #6551: ceph-deploy copy config and key to cluster failure
- As a work-around I created the /etc/ceph directory, and then ran the command again, and it passed:-
ceph@pp-ceph-a... - 08:48 AM devops Bug #6551 (Resolved): ceph-deploy copy config and key to cluster failure
- Hi,
Following the following 2 wiki pages:
http://ceph.com/docs/master/start/quick-start-preflight/
http://ce... - 07:07 AM CephFS Bug #3738: kclient fsx truncate/write multi-client race
- by commit 755581977c2bc9eb81c9d9d955024cbedded2161
- 07:01 AM CephFS Bug #1117: mds: rename rollback broken on slaves during replay
- by commit 844cd46c77274ee7726ded8bf0d83e7f586da00e
- 05:30 AM devops Bug #6482 (Need More Info): ceph-deploy install on Centos: can't find wget?
- Karan could you please confirm that `wget` is actually installed/available in that host?
I want to rule out that ...
10/14/2013
- 08:24 PM CephFS Bug #5025: samba smbtorture lock test fails on kclient
- in commit:f5685013a4ff4f569413945f380dd48b6cdbfaad
- 07:01 PM CephFS Bug #5025 (Resolved): samba smbtorture lock test fails on kclient
- 05:14 PM RADOS Feature #6549 (New): FileStore: notice that the ObjectContext disagrees with the on-disk object w...
- We don't check in the OSD that the data we get back when doing a filesystem read of an object matches any reasonable ...
- 05:06 PM Feature #6147 (Resolved): mon: calculate, expose per-pool pg stat deltas
- 05:01 PM Bug #6526 (Resolved): dumpling rpm repos contain 0.69 rpms
- I've deleted the v0.69 packages from the dumpling repo, and verified that v0.67.4 is installed by default.
Not ent... - 03:34 PM devops Feature #6020 (In Progress): radosgw-apache opinionated package
- Initial version of package has been created. Still need to sort out installation of config files.
- 02:19 PM rbd Bug #6548 (Resolved): tgt: Kernel panic putting zpool on iSCSI LUN using bs_rbd
- From http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/17321:...
- 01:56 PM Documentation #6547: should document magic data/journal partition types
- OSD data: 4fbd7e29-9d25-41b8-afd0-062c0ceff05d
OSD journal: 45b0969e-9b03-4f30-b4c6-b4b80ceff106 - 01:50 PM Documentation #6547 (Closed): should document magic data/journal partition types
- We should write down the requirements for the Ceph startup scripts to automatically mount and start OSDs:
1) gpt lab... - 01:28 PM Bug #6492 (Resolved): SignalHandler::entry spins the cpu and never sleeps
- Good enough.
- 01:24 PM Bug #6492: SignalHandler::entry spins the cpu and never sleeps
- Recent Ceph checkouts don't even compile on FreeBSD. Only the wip-port branch can compile. So I don't think there's...
- 11:15 AM Bug #6492 (Pending Backport): SignalHandler::entry spins the cpu and never sleeps
- Thanks Alan, that looks good to me and going over the issue again I'm not sure why it works on Linux to begin with! G...
- 12:34 PM rgw Bug #6462 (Resolved): Cannot update object HTTP headers using swift API
- Done, commit:f2645e1c6d7383a0ace3b239f4304e353249c4bb. Cherry-picked into dumpling.
- 10:24 AM RADOS Feature #6506: Show running ceph version in "ceph osd tree"
- If the monitors don't already have the information can you think of a reason why it wouldn't be a good idea for 'ceph...
- 09:41 AM CephFS Bug #6396 (Resolved): mds: recovery hits assert(!segment.empty()) when reissuing caps
- Backported to dumpling as commit:cd1c3c9e00e90b19e83c1f11a48e516a7de93665
- 09:40 AM Feature #6189 (Fix Under Review): cachepool: osd: promote on read
- Whoops, should have updated this status last week. Needs review and test code.
- 09:27 AM CephFS Bug #1117: mds: rename rollback broken on slaves during replay
- Which patch[es]?
- 07:29 AM CephFS Bug #1117 (Resolved): mds: rename rollback broken on slaves during replay
- 09:25 AM CephFS Bug #3738: kclient fsx truncate/write multi-client race
- Is this a side effect of 3c3b2ceb03e7294704f5bf3e1e420012a0166585, or some other patch? Please reference them when cl...
- 07:24 AM CephFS Bug #3738 (Resolved): kclient fsx truncate/write multi-client race
- now mds revokes Fw before doing truncate
- 07:40 AM CephFS Bug #2385 (Can't reproduce): max mds = 2, mds hang and crash
- 07:34 AM CephFS Bug #5036 (Resolved): `ls` hangs on random folder
- 07:34 AM CephFS Bug #2019 (Resolved): mds: CInode::filelock stuck in sync->mix
- 07:31 AM CephFS Bug #3088 (Resolved): NULL pointer dereference at ceph_d_prune
- 07:28 AM CephFS Bug #429 (Resolved): mds: fix rstat propogation into past parents
- haven't seen any rstat error for months
- 07:25 AM CephFS Bug #3681 (Resolved): kclient fsx fails nightly
10/13/2013
- 10:23 AM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/teuthology-2013-10-10_22:04:00-rados-master-testing-basic-plana/44493/remote
10/12/2013
- 02:38 PM Bug #6504: PATCH: Fix double-free of fiemap
- This patch works for me to solve the same problem on OSX.
- 01:00 PM Bug #6492: SignalHandler::entry spins the cpu and never sleeps
- I found that the daemons on OSX were spinning not because they were not blocking in poll, but because the unnamed sem...
10/11/2013
- 09:26 PM Bug #6528 (Resolved): btrfs osd gets kicked out while removing large pg
- btrfs isn't exactly blazingly fast for file removal; so much is well known to me. However, there are two issues at h...
- 09:15 PM Fix #6527 (New): backfill_toofull => try backfilling another replica
- With a replication factor of 4, after changing the crushmap so that nearly all data got moved about, I noticed that w...
- 08:38 PM Bug #6526 (Resolved): dumpling rpm repos contain 0.69 rpms
- The rpm repos (f18 just re-checked, f19 checked a few days ago) contain 0.69 rpms, which end up superseding the 0.67....
- 06:24 PM rgw Bug #6462: Cannot update object HTTP headers using swift API
- Fix looks good. I'm not sure if it should be backported or not.
- 05:59 PM rgw Documentation #6525 (Closed): radosgw: update radosgw-admin man page
- There have been several options and commands added (and several more are about to be merged for quotas) that weren't ...
- 03:46 PM rgw Bug #6444 (Resolved): rgw: leak in librados::Rados::pool_async_create_completion
- 02:56 PM Bug #6521: ceph health hung after upgrading the cluster from bobtail to dumpling to next
- ...
- 02:54 PM Bug #6521 (Resolved): ceph health hung after upgrading the cluster from bobtail to dumpling to next
- ceph health hung after upgrading the cluster from bobtail to dumpling to next
ubuntu@teuthology:/a/teuthology-201... - 02:15 PM Feature #6520 (Resolved): common: bloom_filter improvements, cleanups
- * "unintended use of the wrong bloom_filter prototype":https://github.com/ceph/ceph/pull/697
* "improvements, cleanu... - 02:09 PM Documentation #6493 (Resolved): rados/operations/add-or-rm-mons.rst relative links are one parent...
- http://ceph.com/docs/master/rados/operations/add-or-rm-mons/
- 02:03 PM Fix #6059 (Fix Under Review): osd: block reads while repgather is writing across replicas
- 02:03 PM Feature #5991 (In Progress): EC: [link] Backfill peers should not be included in the acting set
- 01:59 PM Feature #6435: EC: [link] review and test PGBackend
- Not much progress this sprint.
- 01:25 PM rbd Feature #6432: Change TGT Plugin to allow setting client name for authentication
- One can set clientname now with CEPH_ARGS, but with bsopts it will become easier (done at tgtadm
time) and per-targe... - 01:22 PM rbd Feature #6432 (In Progress): Change TGT Plugin to allow setting client name for authentication
- 01:13 PM rgw Feature #6513 (Resolved): rgw: dr: Service scripts for meta/data sync agents
- For Ubuntu and Rhel/CentOS
- 01:03 PM rgw Feature #4466 (Fix Under Review): Quotas per bucket - synchronous
- 11:38 AM devops Feature #6018 (Resolved): Build ceph via jenkins
- 09:10 AM CephFS Feature #6511 (Rejected): MDS: add special purging options for testing
- We do a lot of stuff async with our journal, stray inodes, etc, that we need a good way to test. Let this ticket serv...
- 08:48 AM Bug #6510 (Fix Under Review): PATCH: Fix segfault when ceph_dencoder is called with test number 0...
- 07:58 AM Bug #6510 (Resolved): PATCH: Fix segfault when ceph_dencoder is called with test number 0 on a cl...
- select_generated() should properly validate its input. If m_list.size() == 0, then calling select_generated(0) will ...
- 07:33 AM CephFS Bug #4405 (Pending Backport): MDCache::populate_mydir can loop forever
10/10/2013
- 11:18 PM RADOS Feature #6506: Show running ceph version in "ceph osd tree"
- I don't know that the monitors *do* have that information. The OSDs do, via the
compiled-in magic version string, ... - 01:05 PM RADOS Feature #6506: Show running ceph version in "ceph osd tree"
- The version that each OSD is running
- 12:55 PM RADOS Feature #6506: Show running ceph version in "ceph osd tree"
- Are you looking for the software version each OSD is running, or the version of the monitor you're connected to?
- 11:53 AM RADOS Feature #6506 (New): Show running ceph version in "ceph osd tree"
- It would be incredibly handy to be able to see the running ceph version in the output of "ceph osd tree". I spoke wit...
- 11:03 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
- 1) I solved this in the python bindings with a separate timer thread, which is always possible in C/C++ as well, alth...
- 01:41 PM Feature #6507 (Resolved): librados shouldn't block indefinitely when cluster doesn't respond
- Currently calls like rados_connect(), rados_ioctx_create(), rados_read() block for ever if the Ceph cluster isn't res...
- 10:42 PM CephFS Bug #6396 (Pending Backport): mds: recovery hits assert(!segment.empty()) when reissuing caps
- This seems to be showing up in our nightlies a fair bit still; it should be backported.
- 04:23 PM RADOS Feature #6509 (New): OSD: be more efficient about read/write ordering
- With Sam's soon-to-be-merged patch adding a RWTracker, we are ordering operations more strictly than is necessary. In...
- 03:18 PM devops Bug #6508 (Rejected): ceph-deploy: config push and admin commands broken
- ...
- 03:00 PM devops Bug #6508: ceph-deploy: config push and admin commands broken
- ...
- 02:58 PM devops Bug #6508 (Rejected): ceph-deploy: config push and admin commands broken
- test set up: mira025, mira038
dev dumpling version of ceph [] installed and running on mira025 and mira038.
try... - 02:19 PM rgw Bug #6505: ceph-deploy osd activate may sit undefinatly (centos)
- http://paste.openstack.org/show/48238/
- 10:32 AM rgw Bug #6505 (Resolved): ceph-deploy osd activate may sit undefinatly (centos)
- ceph-deploy osd activate may sit undefinatly
http://paste.openstack.org/show/48186/
http://paste.openstack.org/s... - 01:18 PM CephFS Bug #4405 (Fix Under Review): MDCache::populate_mydir can loop forever
- He's got a patch in wip-4405 that he thinks would solve the loading problem; I think he might be right. The other iss...
- 12:55 PM Subtask #6027 (In Progress): ensure that erasure coded pools don't work until the osds can handle it
- 12:51 PM Subtask #5855 (In Progress): Backfill peers should not be included in the acting set
- 11:05 AM CephFS Bug #6460: ceph-fuse: xlist crash in ~Inode on osd_op_reply
- In general I'm not usually too worried about FS backports since anybody using the FS should be keeping up to date wit...
- 04:27 AM CephFS Bug #6460 (Resolved): ceph-fuse: xlist crash in ~Inode on osd_op_reply
- 10:24 AM Bug #6504 (Fix Under Review): PATCH: Fix double-free of fiemap
- 09:05 AM Bug #6504 (Resolved): PATCH: Fix double-free of fiemap
- If GenericFileStoreBackend::do_fiemap returns anything other than 0, then fiemap will not be allocated. However, Gen...
- 09:58 AM Feature #6002 (Resolved): EC: [link] erasure coding library plugin API documentation, including a...
- This is done!
- 09:52 AM Feature #5996: EC: [link] PG::calc_acting and friends should always choose the shortest of the av...
- 09:50 AM Feature #5996 (Rejected): EC: [link] PG::calc_acting and friends should always choose the shortes...
- This may actually be unnecessary, I think we can choose to always reject extra history.
- 07:29 AM rbd Bug #6494: High memory consumption of qemu/librbd with enabled cache
- With "rbd_cache_block_writes_upfront=1" it's harder to catch with massif, but I still see memory usage spikes using a...
- 05:00 AM devops Bug #6503 (Rejected): ceph-deploy: nosetests fail
- ...
10/09/2013
- 08:16 PM CephFS Bug #6460 (Pending Backport): ceph-fuse: xlist crash in ~Inode on osd_op_reply
- Probably already fixed by https://github.com/ceph/ceph/pull/590. Do we need to backport MDS fixes to old version?
- 02:58 PM RADOS Fix #6496 (Closed): mon: PGMap::dump should use TextTable
- Column alignment is off; TextTable would just solve this:...
- 02:48 PM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- It does matter, but there's probably middle ground with some small fixed help. I'll work on
something like that. - 06:00 AM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- @dmick it doesn't matter that a user cannot do anything with a monitor.
The best thing a CLI application can do is... - 02:42 PM Fix #6059 (In Progress): osd: block reads while repgather is writing across replicas
- 02:02 PM CephFS Bug #4832: mds: failed auth_unpin assert
- I've backported these two patches to the cuttlefish branch as well.
(Plus a cuttlefish-4832 branch on top of v0.61.8... - 01:07 PM rbd Bug #6386: ceph-osd processes are having hang tasks
- Sage, sorry, I think i've mixed the bug numbers. I've meant to post it to another bug where i've uploaded a bunch of ...
- 12:56 PM rbd Bug #6386: ceph-osd processes are having hang tasks
- Sage,
I had this happened again, while I was at the Ceph Day ((. Anyway, the behaviour seemed pretty similar. A bu... - 12:54 PM Bug #6492: SignalHandler::entry spins the cpu and never sleeps
- In signal_handler.cc at line 213, poll(2) returns immediately with POLLOUT set in revents for each of the struct poll...
- 12:41 PM Bug #6492: SignalHandler::entry spins the cpu and never sleeps
- This is outside my area of expertise, but I'm looking at http://linux.die.net/man/3/poll and not seeing why POLLOUT s...
- 12:34 PM Bug #6492: SignalHandler::entry spins the cpu and never sleeps
- I believe this is also a bug I'm seeing on OSX.
- 11:35 AM Feature #6416 (In Progress): buffer: create raw_pipe class; convert to buffer if inspected
- 10:14 AM devops Bug #6489: ceph-deploy: get_nonlocal_ip() should filter ipv6 addrs
- To further elaborate, when I recompiled python so that IPv6 support was properly enabled, the problems that I was hav...
- 09:49 AM devops Bug #6489: ceph-deploy: get_nonlocal_ip() should filter ipv6 addrs
- I'm the user that orignally reported this issue, and after talking with the Gentoo crowd about the issue, we've disco...
- 09:33 AM rbd Bug #6494: High memory consumption of qemu/librbd with enabled cache
- Excellent report! The massif output is really useful. It shows that there are a large number of buffers getting backe...
- 03:00 AM rbd Bug #6494: High memory consumption of qemu/librbd with enabled cache
- It seems that I found a way to run qemu-kvm under valgrind/massif and trigger this issue. It looks like all this happ...
- 02:44 AM rbd Bug #6494 (Resolved): High memory consumption of qemu/librbd with enabled cache
- I observe very high memory consumption on client with write-intensive load with qemu 1.6.0 + librbd 0.67.3.
For be... - 08:52 AM rbd Bug #5890 (Closed): can't remove rbd image from pool
- 02:38 AM rbd Bug #5890: can't remove rbd image from pool
- fixed.
- 08:29 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- 08:28 AM devops Bug #6487 (In Progress): remove pushy from ceph-deploy
- 03:04 AM rbd Bug #6495 (Closed): Cpu load on cluster node is very high every has the write request to cluster
- ceph version 0.61.8
Kernel Ubuntu 12.10 (GNU/Linux 3.5.0-41-generic )
CPU: 24 processors, Ram 64GB
Env: 3 ...
10/08/2013
- 09:55 PM Feature #6466: stgt: unlimit number of images supported
- Patches submitted to upstream
- 09:51 PM Feature #6466 (In Progress): stgt: unlimit number of images supported
- 08:21 PM Documentation #6493: rados/operations/add-or-rm-mons.rst relative links are one parent shy of cor...
- These would also be found automatically if we spidered the docs
- 08:10 PM Documentation #6493 (Resolved): rados/operations/add-or-rm-mons.rst relative links are one parent...
- rados/operations/add-or-rm-mons.rst has relative links to ../../install, but they need to be ../../../install to
wor... - 07:00 PM rgw Feature #5073: rgw: create tenant namespace
- That's still true.
- 02:27 PM rgw Feature #5073: rgw: create tenant namespace
- Is it still not possible to have per user namespaces?
- 03:24 PM Bug #6492 (Resolved): SignalHandler::entry spins the cpu and never sleeps
- SignalHandler::entry shouldn't poll for POLLOUT, because it never actually writes to the pipes in question. Polling ...
- 02:56 PM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- Once we have our ping messages, etc, then there will be things you can do without connecting to the monitors, though,...
- 02:52 PM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- If you can't connect to the monitor, the help is going to do you no good; you can't issue any of those commands. It ...
- 02:46 PM devops Bug #6491 (Closed): During mon create: <type 'exceptions.TypeError'>: 'NoneType' object is not ca...
- ...
- 01:10 PM rbd Bug #5426: librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::complete()
- http://qa-proxy.ceph.com/teuthology/teuthology-2013-10-07_19:01:03-rbd-dumpling-testing-basic-plana/39473/
- 12:51 PM devops Bug #6489: ceph-deploy: get_nonlocal_ip() should filter ipv6 addrs
- However, if I add "::1 <hostname>" to my /etc/hosts, and issue getaddrinfo, I get
back v6 entries that look like:
... - 12:32 PM devops Bug #6489 (Can't reproduce): ceph-deploy: get_nonlocal_ip() should filter ipv6 addrs
- get_nonlocal_ip isn't prepared to see ipv6 addresses back from getaddrinfo(); although
I haven't reproduced it perso... - 09:23 AM devops Bug #6487 (Closed): remove pushy from ceph-deploy
- The current state of ceph-deploy for remote connections is terrible to work with. While attempting to work on #6486 t...
- 05:31 AM devops Bug #6485 (Resolved): purgedata should not remove /etc/ceph dir
- It currently removes the whole directory, and it should actually just remove the contents because otherwise nothing w...
- 01:42 AM Bug #6484 (Resolved): osd pool default flag hashpspool not honored
- When creating new pools the hashpspool is not honored. And as there's no way to change it aafter pool creation, there...
10/07/2013
- 02:22 PM Fix #6483 (Resolved): osd: does not fill in OSDOp::rval member
- We provide an interface via the Objecter (and librados) for getting the return code of specific ops within a compound...
- 12:17 PM devops Bug #6482 (Resolved): ceph-deploy install on Centos: can't find wget?
- [ceph@ceph-client ~]$ ceph-deploy install ceph-node1
[ceph_deploy.install][DEBUG ] Installing stable version dumplin... - 09:50 AM rbd Bug #6480 (Resolved): librbd crashed qemu-system-x86_64
- Running Ceph 0.67.3 and qemu 1.5.2
*** Error in `qemu-system-x86_64': invalid fastbin entry (free): 0x00007fab795c... - 06:24 AM Bug #6380: Monitor tries to bind on IPv6 address while not available yet after boot
- So I did a small test:...
- 05:51 AM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- Both suggestions from Josh and Sage are entirely acceptable here. I wouldn't mind if some section of the help tells m...
10/05/2013
- 12:25 AM Subtask #6478 (Rejected): ErasureCode : XOR plugin
- "work in progress":https://github.com/ceph/ceph/pull/1164
10/04/2013
- 03:01 PM Feature #6143 (Resolved): OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xa...
- 5258c9c4e5bd61e6b1a1fdbdb781b9dee702fda3
- 01:52 PM Bug #6422: write_superblock() and write_version_stamp() not safe
- 8835ef8f9833b250e8d09716f683893073db5306
- 01:51 PM Bug #6422 (Resolved): write_superblock() and write_version_stamp() not safe
- 01:03 PM rgw Bug #6462 (Fix Under Review): Cannot update object HTTP headers using swift API
- 11:01 AM rgw Bug #6462: Cannot update object HTTP headers using swift API
- This seems to mostly work. The only thing that is not working is the (special case) content-disposition header, which...
- 01:02 PM rgw Bug #6444 (Fix Under Review): rgw: leak in librados::Rados::pool_async_create_completion
- Reopening, bug wasn't fixed completely. Pushed a second fix to wip-6444.
- 10:32 AM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- What about having --help try the monitor, but print hardcoded help if it can't connect? It could include a warning no...
- 08:29 AM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- hmm, we could make ceph --help/-h do the basic stuff, and ceph --help-all (or similar) do the mon query to get the co...
- 06:55 AM Fix #6242: ceph CLI should honor `--help` and not return log lines back
- I have to disagree here. Regardless of the reasons for needing to connect to a monitor (what is the reason to need th...
- 10:08 AM rgw Bug #6360 (Resolved): rgw: keystone token cache not working
- 09:47 AM rgw Bug #6360: rgw: keystone token cache not working
- pushed to dumpling, commit:5cd66d3b4bca92b402c95ab256fbc3f0329c446f
- 09:49 AM Bug #6254 (Resolved): ceph_test_rados: rollback then delete gets ENOENT
- 09:49 AM Bug #6474 (Resolved): osd: segfault in _rollback_to
- 09:38 AM rgw Bug #6475: rgw: Log directory should not be created by the init script
- yeah.. and i think the logs by default go into /var/log/ceph anyway. it's a bit wonky though because of ceph vs rado...
- 02:59 AM rgw Bug #6475 (Resolved): rgw: Log directory should not be created by the init script
- The init script currently created /var/log/radosgw, which isn't the way it's supposed to be:
# directory to write ... - 09:35 AM Bug #6476: lost around 30 OSDs (of 75) at once
- Jens, any osd logs you can attach to 6429 would be helpful. thanks!
- 09:34 AM Bug #6476 (Duplicate): lost around 30 OSDs (of 75) at once
- 06:51 AM Bug #6476 (Duplicate): lost around 30 OSDs (of 75) at once
- Our dumpling cluster (0.67.3) with 64 SATA and 10 SSD OSDs on 10 servers suddenly experienced a crash of the majority...
- 08:41 AM CephFS Bug #5290 (Can't reproduce): mds: crash whilst trying to reconnect
- 07:24 AM CephFS Bug #5290: mds: crash whilst trying to reconnect
- I certainly haven't been hit by this again, so if you consider it resolved...
10/03/2013
- 09:59 PM rbd Bug #5220: test_ls_snaps segfaults on the arm test setup
- 09:58 PM Bug #6254 (Fix Under Review): ceph_test_rados: rollback then delete gets ENOENT
- Sage Weil wrote:
> BUT the osd behavior here is also confusing: if you say "rollback to snap X" and snap X does not ... - 09:47 PM Bug #6254: ceph_test_rados: rollback then delete gets ENOENT
- https://github.com/ceph/ceph/pull/689 for the model fix
- 09:39 PM Bug #6254: ceph_test_rados: rollback then delete gets ENOENT
- aha:...
- 09:08 PM Bug #6254: ceph_test_rados: rollback then delete gets ENOENT
- ubuntu@teuthology:/a/teuthology-2013-10-02_23:00:03-rados-master-testing-basic-plana/31098
- 09:29 PM Bug #6474 (Fix Under Review): osd: segfault in _rollback_to
- https://github.com/ceph/ceph/pull/688
- 09:05 PM Bug #6474 (Resolved): osd: segfault in _rollback_to
- ...
- 07:50 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I just updated to 0.67.3 and I want to confirm that I still have to recompile to get around the abort.
0> 201... - 06:27 PM Bug #5896 (Resolved): mon: MonmapMonitor: 'ceph mon add' always returns 'mon already exists'
- 06:11 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
- ubuntu@teuthology:/a/sage-2013-10-03_17:25:57-marginal:multimds-master-testing-basic-/32499
- 06:11 PM CephFS Bug #6473 (Can't reproduce): multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
- ...
- 05:01 PM rgw Bug #6462: Cannot update object HTTP headers using swift API
- Of course I meant "I swear this used to work in argonaut and works in Swift but *not* in ceph .69."
- 01:34 PM CephFS Bug #5025: samba smbtorture lock test fails on kclient
- http://qa-proxy.ceph.com/teuthology/teuthology-2013-10-02_23:01:08-fs-master-testing-basic-plana/31442/
- 01:33 PM CephFS Bug #5025: samba smbtorture lock test fails on kclient
- oops, still fails on kclient.
- 01:33 PM CephFS Bug #2825 (Resolved): File lock doesn't work properly
- 12:24 PM Bug #6467 (Resolved): librados.h broken; refers to include/int_types.h
- 12:13 PM Bug #6430: OSD crashes on startup in function 'OSDMapRef OSDService::get_map(epoch_t)
- cdbfd66249cdf91c02a88af5df5a6517688a78df, specifically.
- 12:13 PM Bug #6430: OSD crashes on startup in function 'OSDMapRef OSDService::get_map(epoch_t)
- This is actually already backported to cuttlefish, but awaits 61.9. You can try running cuttlefish head.
-Sam - 12:09 PM Bug #6430 (Duplicate): OSD crashes on startup in function 'OSDMapRef OSDService::get_map(epoch_t)
- 09:55 AM Bug #6457 (Resolved): new apache/fastcgi packages appear to break 100-continue
- 06:28 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- more info:
Disabled ceph on s0, but still use it as OpenStack compute node. Started 20 VMs, and terminated them. s... - 04:56 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- Even more info: We did a bit of stress testing with OpenStack (without the server s0, the failed server), creating, t...
- 02:13 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- Some more information:
In a healthy cluster, I have spun up 12 VMs that installed some software, compiled and did ...
10/02/2013
- 11:55 PM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- The cluster has been quite busy yesterday (bc we had a number of hosts that had to be rebooted). Right now it is HEAL...
- 05:08 PM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- dmesg shows there was no blocked task. It's likely the hung task message was caused by slow requests or lock contention.
- 10:03 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- What's the status of the cluster when you see those hangs? Do you have any symptoms that let you detect the hang whil...
- 07:49 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- dmesgs attached, the mdsc and osdc files are empty:
root@h4:~# ll /sys/kernel/debug/ceph/2fe1a358-7f88-4a1b-a31b-b... - 07:44 AM Linux kernel client Support #6455: dumpling cephFS on 3.12-rc1 qemu hung tasks
- I need following information to debug the issue.
dmesg -c >/dev/null; echo w >/proc/sysrq-trigger; dmesg
cat /sys... - 07:21 AM Linux kernel client Support #6455 (Closed): dumpling cephFS on 3.12-rc1 qemu hung tasks
- We run 3.12rc1 kernels, ceph 0.67.3, and OpenStack Folsom with /var/lib/nova/instances on CephFS. The physical hosts ...
- 10:21 PM CephFS Bug #5753: ceph-fuse: segfault when getting back a traceless rename op
- and /a/teuthology-2013-10-01_23:01:09-fs-next-testing-basic-plana/29640
- 01:00 PM CephFS Bug #5753: ceph-fuse: segfault when getting back a traceless rename op
- Showed up again, /a/teuthology-2013-09-27_19:01:27-fs-dumpling-testing-basic-plana/21601
- 09:53 PM CephFS Bug #6458 (New): journaler: journal too short during replay
- Wow, that explanation of what was going on was so very wrong. Now I'm just not sure how this could have occurred.
- 06:27 PM CephFS Bug #6458: journaler: journal too short during replay
- Made a pull request too: https://github.com/ceph/ceph/pull/683
- 06:26 PM CephFS Bug #6458: journaler: journal too short during replay
- Yep, it ran pjd successfully; plenty of journal commits there!
- 06:19 PM CephFS Bug #6458 (Fix Under Review): journaler: journal too short during replay
- Pushed a patch to wip-journaler-safety, commit:a0ba5c66162af720627fcf7ba63fdc76ac97f568. I'm setting up a basic funct...
- 05:58 PM CephFS Bug #6458 (In Progress): journaler: journal too short during replay
- This is a bit more complicated than we described — we do not in fact blindly write the write_pos to our head object; ...
- 11:19 AM CephFS Bug #6458 (New): journaler: journal too short during replay
- Urgh, that last comment was mistaken.
- 10:56 AM CephFS Bug #6458 (Rejected): journaler: journal too short during replay
- That is not what happened; the underlying objects were inconsistent in RADOS.
- 10:07 AM CephFS Bug #6458 (Can't reproduce): journaler: journal too short during replay
- Got a report on irc from a user whose log was 611 bytes shorter than the header indicated it should be. His guess was...
- 09:51 PM Bug #6467: librados.h broken; refers to include/int_types.h
- ...and also other public include files seem to include it
- 09:51 PM Bug #6467: librados.h broken; refers to include/int_types.h
- I note further that librados.h did not used to unconditionally include inttypes.h,
and it's grown a new unconditiona... - 09:46 PM Bug #6467: librados.h broken; refers to include/int_types.h
- I note that "make install" does not install it
- 09:45 PM Bug #6467 (Resolved): librados.h broken; refers to include/int_types.h
- Still digging into why, but I know there was some recent reorg wrt int_types vs. inttypes
- 09:43 PM Feature #6466 (Resolved): stgt: unlimit number of images supported
- 09:04 PM Documentation #6465 (Closed): admin/build-doc should have some kind of build check for broken links
- See #6464. We should have something in the doc build process that complains
bitterly about broken links, and break... - 08:59 PM Documentation #6464 (Resolved): dangling links to install-chef.rst
- dd6e79aa772b9d56a4042601e475fa8152598b22 removed install-chef.rst, but there are
still links to it:... - 04:02 PM devops Bug #6461: ceph-deploy should at least issue a warning if there are parser errors reading ceph.conf
- [root@node-1 ~]# python -i
Python 2.6.6 (r266:84292, Jul 10 2013, 22:48:45)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-3)... - 03:59 PM devops Bug #6461: ceph-deploy should at least issue a warning if there are parser errors reading ceph.conf
- [root@node-1 ~]# vi ceph.conf
[global]
filestore_xattr_use_omap = true
mon_host = 192.168.0.2
fsid = d4991d2b-... - 03:07 PM devops Bug #6461 (Rejected): ceph-deploy should at least issue a warning if there are parser errors read...
- during ceph-deploy [--overwrite-conf] config push, if there are parser errors, no warning or error is logged.
A us... - 03:58 PM rgw Bug #6462: Cannot update object HTTP headers using swift API
- I should not that adding new headers doesn't work other, not just replacing old ones.
aaron@aaron-HP-HDX18-Noteboo... - 03:35 PM rgw Bug #6462 (Resolved): Cannot update object HTTP headers using swift API
- I swear this used to work in argonaut and works in Swift but in ceph .69. I can set headers using PUT but using POST ...
- 03:20 PM Feature #6037 (Resolved): cachepool: osd: whiteout state
- 03:20 PM Feature #6186 (Resolved): cachepool: osd: dirty state for an object in cache pool
- 03:11 PM Feature #6423 (Resolved): ceph-deploy should log command line args to logfile
- 02:50 PM Feature #6423: ceph-deploy should log command line args to logfile
- resolved by https://github.com/ceph/ceph-deploy/pull/98
- 02:44 PM CephFS Bug #1596 (Can't reproduce): mds crash during ffsb on kernel client in CInode::is_frozen
- 02:44 PM CephFS Bug #1601 (Can't reproduce): mds crash during snaps workunit
- 02:44 PM CephFS Bug #1752 (Can't reproduce): ceph-fuse isn't releasing caps without flushing data?
- 02:43 PM CephFS Bug #3601: client: With multiple clients, file remove doesn't free up space
- repushing to wip-fuse for testing
- 02:38 PM CephFS Bug #5025 (Resolved): samba smbtorture lock test fails on kclient
- lock test was fixed a while ago, commit:476e4902907dfadb3709ba820453299ececf990b test is reenabled in the suite.
- 01:56 PM Bug #4577 (Resolved): ceph pg dump_stuck dumps output even if none
- 12:54 PM CephFS Bug #6460 (Resolved): ceph-fuse: xlist crash in ~Inode on osd_op_reply
- ...
- 12:18 PM CephFS Bug #3681: kclient fsx fails nightly
- added fsx back into the kcephfs test suite. reportedly fsx now passes, but we should verify before closing this bug.
- 12:13 PM CephFS Bug #5037 (Can't reproduce): Ceph-MDS asserts after upgrade 0.56.2 -> 0.56.6
- 12:12 PM CephFS Bug #5162 (Can't reproduce): File is locked unexpected and not released anymore
- 12:07 PM CephFS Bug #5033 (Can't reproduce): oops in ceph_put_wrbuffer_cap_refs
- 12:07 PM CephFS Bug #5290: mds: crash whilst trying to reconnect
- i'm inclined to call this can't reproduce. there was a locking fix recently that covered the session_map too that co...
- 12:05 PM CephFS Bug #5418 (Resolved): kceph: crash in remove_session_caps
- 11:46 AM Bug #5981 (Resolved): osd: journal didn't preallocate
- 11:44 AM CephFS Feature #6332 (Resolved): mds: add config option disabling snapshots by default
- This got merged to master; I'm going to call that done since we're releasing Emperor soon-ish.
- 10:00 AM Bug #6457 (Resolved): new apache/fastcgi packages appear to break 100-continue
- this is causing all the rgw tests to fail
- 08:24 AM Bug #6456 (Resolved): scripts still installing into /usr/usr/sbin
- Bug #5492 dealth with scripts installing into locations like /usr/usr/sbin when PREFIX=/usr. That bug was marked Res...
- 07:08 AM Documentation #6454 (Resolved): Add dumpling to the documentation on OS/Kernel Recommendations
- Ref: http://ceph.com/docs/master/install/os-recommendations/
The latest documented release is Cuttlefish 0.61, we'... - 06:58 AM devops Feature #6365: Package up newer version of Qemu for RHEL & EL6.3 and 6.4
- Please note: qemu-kvm-0.12.1.2-2.355.el6_4.9.src.rpm has been released.
cheers,
--
Thomas@CERN - 05:52 AM rgw Feature #6133: Enhance the validation of JSON passed into radosgw-admin calls
- Validation of JSON data can be get *very* complex if we need to do anything more than trimming and very basic asserti...
- 05:36 AM rbd Bug #6368: rbd nosetests keep failing with AttributeError
- This is still failing as of today: http://qa-proxy.ceph.com/teuthology/teuthology-2013-10-01_01:10:01-ceph-deploy-nex...
- 03:19 AM Bug #6442: mon: crush_ops.sh, test.py failures on master
- Given the simplistic nature of this one-line patch that fixed a considerably complex issue, I believe some explanatio...
- 02:34 AM CephFS Bug #6450: Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- we have now upgraded the complete cluster to Dumpling (0.67.3) (also due to other problems we have experienced in the...
- 01:29 AM Bug #6429: msg/Pipe.cc: 1029: FAILED assert(m)
- Sage, here you go. Two files with tarred logs from that date. One file with 200 in the name is the 192.168.169.200 os...
- 01:22 AM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
- I should have done a little more digging in my previous update but it looks more likely that sending a HUP is where t...
- 01:03 AM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
- I've done some further investigation on this. It seems that logrotate is the culprit.
After executing the followin... - 12:28 AM devops Bug #6453 (Won't Fix): libapache2-mod-fastcgi Packages for Debian Squeeze have incorrect dependen...
- The packages provided for libapache2-mod-fastcgi for debian squeeze depend on libc >= 2.14 which is not available for...
10/01/2013
- 10:24 PM Bug #4577 (Fix Under Review): ceph pg dump_stuck dumps output even if none
- 09:11 PM CephFS Bug #6396 (Resolved): mds: recovery hits assert(!segment.empty()) when reissuing caps
- yeah looks good!
- 09:07 PM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- 09:07 PM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- By reading the mds log for #5458, I think these issues should be mostly fixed by commit b144170544(mds: properly retu...
- 09:09 PM CephFS Bug #6349 (Duplicate): MDS: failed assert !segments.empty() while rejoining after being standby-r...
- dup #6396
- 09:08 PM CephFS Bug #5458 (Duplicate): mds: standby-replay -> replay takeover does not handle racing expire/trim
- dup #6396
- 09:01 PM Bug #5981 (Fix Under Review): osd: journal didn't preallocate
- 04:02 PM Bug #6378 (Resolved): mon: osdmap crc mismatch during scrub
- 03:56 PM Bug #6442 (Resolved): mon: crush_ops.sh, test.py failures on master
- 03:42 PM Bug #6384 (Resolved): ceph tool: incorrect pool delete line returns unintelligible failure message
- 03:41 PM Bug #6429: msg/Pipe.cc: 1029: FAILED assert(m)
- Hey, do you have the log on teh other OSD too? (it's on 192.168.168.201, and should have the string "192.168.168.201...
- 01:04 PM Bug #6429: msg/Pipe.cc: 1029: FAILED assert(m)
- Sage, not sure if my logs relate to this bug, but i've been asked on #ceph to add it to this bug. I am on ubuntu 12.0...
- 02:38 PM Feature #6452 (Resolved): cachepool: snapshots
- Some stuff:
- promoting clones means creating clones without CLONE pg log operations
- promoting head needs to pull... - 01:26 PM Bug #6451 (Resolved): btrfs async transactions deadlock on 3.12-rcwhatever
- 12:40 PM Bug #6443 (Resolved): osd: leak of MOSDPGPushReply
- 12:27 PM devops Bug #6387 (Resolved): Handle HostNotFound for execnet connection errors
- Created pull request: https://github.com/ceph/ceph-deploy/pull/95
Merged with hash: ffe1fe7
We catch these ex... - 12:03 PM Bug #6446 (Duplicate): osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log...
- made two bugs for some reason
- 10:50 AM Fix #4612 (Resolved): unit_to_bytesize(), si_t, prettybyte_t use 'K' for kilo; SI recommends 'k'
- 09:22 AM rgw Cleanup #6123 (Resolved): rgw: don't warn about missing region map
- 09:17 AM rgw Bug #6445 (Resolved): rgw: leak in RGWBucketMetadataHandler::get()
- 09:16 AM rgw Bug #6444 (Resolved): rgw: leak in librados::Rados::pool_async_create_completion
- 09:05 AM devops Bug #6428 (Resolved): `ceph-deploy osd` calls missing $PATH
- Merged into ceph-deploy master branch with hash: 0ffd809
- 06:47 AM CephFS Bug #6450: Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- Jens-Christian Fischer wrote:
> Can I run a 0.67.3 MDS with the rest of the infrastructure on 0.61.8?
yes, you ca... - 05:34 AM CephFS Bug #6450: Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- Can I run a 0.67.3 MDS with the rest of the infrastructure on 0.61.8?
We are using the rc1 kernels in order to run... - 05:28 AM CephFS Bug #6450 (Need More Info): Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- The first warning was caused by a MDS bug. (you can try upgrading MDS 0.67.3 ) The rest BUGs did not look like ceph r...
- 04:57 AM CephFS Bug #6450 (Closed): Kernel bugs in 3.12-rc1, taking 2 hosts (and 1 following) down
- We are running 10 hosts with 74 OSDs on Ubuntu 13.04, Ceph 0.61.8 and Kernel 3.12-rc1
root@h5:~# ceph --version
... - 03:48 AM rgw Bug #6449 (Rejected): Initiating multipart upload fails with no Content-Length header being set
- It seems that some internal verification routine requires the "Content-Length" header being set for the "Initiate Mul...
09/30/2013
- 11:44 PM Feature #6143 (Fix Under Review): OSD: kill filestore_xattr_use_omap, leave it enabled forever, a...
- 10:04 PM Fix #4612 (Fix Under Review): unit_to_bytesize(), si_t, prettybyte_t use 'K' for kilo; SI recomme...
- 10:04 PM Fix #4612: unit_to_bytesize(), si_t, prettybyte_t use 'K' for kilo; SI recommends 'k'
- This is now parsed as input in unit_to_bytesize(), and printed in the various classes
in types.h. Fix both sides (a... - 09:35 PM Fix #6242 (Duplicate): ceph CLI should honor `--help` and not return log lines back
- The more I consider this, the more sure I am this is really a duplicate of 5634. The problem is that we don't issue ...
- 09:15 PM Subtask #3986 (Rejected): Send to ceph-dev for review
- 09:13 PM Subtask #3985 (Rejected): api: Send to DH for Review
- 09:12 PM Bug #6384 (Fix Under Review): ceph tool: incorrect pool delete line returns unintelligible failur...
- 09:11 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- well, I've created a pull request; if you want to review, now's your chance
- 04:59 PM Bug #6311 (Resolved): Some scripts assume the location of python
- 03:00 PM Bug #6311 (Fix Under Review): Some scripts assume the location of python
- 04:10 PM Bug #6447: osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log.tail)
- testing a fix on 5992-2
- 04:09 PM Bug #6447 (Resolved): osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log....
- -8> 2013-09-27 18:12:16.095433 7fecb5b54700 10 filestore(/var/lib/ceph/osd/ceph-0) _do_op 0x46e05f0 seq 287572 r ...
- 04:09 PM Bug #6446 (Duplicate): osd/PGLog.cc: 402: FAILED assert(log.head >= olog.tail && olog.head >= log...
- -12> 2013-09-27 18:12:16.095353 7fecb4b52700 10 osd.0 pg_epoch: 1532 pg[3.41( v 1518'111 (1503'101,1518'111] lb d3...
- 02:09 PM devops Bug #6428 (Fix Under Review): `ceph-deploy osd` calls missing $PATH
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/94
- 01:09 PM devops Bug #6427 (Resolved): ceph-deply osd activate breaks on error
- Merged into ceph-deploy master branch with hash: 4a9ed622913f82c75849de2e5ebcb20e26fb605f
Migrated the whole funct... - 08:37 AM devops Bug #6427 (Fix Under Review): ceph-deply osd activate breaks on error
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/93
- 04:01 AM Bug #6442 (In Progress): mon: crush_ops.sh, test.py failures on master
09/29/2013
- 09:21 PM Subtask #6391: stuck incomplete
- ubuntu@teuthology:/a/teuthology-2013-09-28_23:00:19-rados-next-testing-basic-plana/23258 ?
- 09:07 PM rgw Bug #6445 (Resolved): rgw: leak in RGWBucketMetadataHandler::get()
- ...
- 09:06 PM rgw Bug #6444 (Resolved): rgw: leak in librados::Rados::pool_async_create_completion
- ...
- 09:04 PM Bug #6443 (Resolved): osd: leak of MOSDPGPushReply
- ...
- 09:02 PM Bug #6207: Found incorrect object contents
- ubuntu@teuthology:/a/teuthology-2013-09-27_23:00:04-rados-master-testing-basic-plana/21804
- 09:01 PM Bug #6442 (Resolved): mon: crush_ops.sh, test.py failures on master
- I see a series of failures that look like the mon just comes up with bad osdmap data after (re)starting a down mon:
...
09/28/2013
- 05:32 PM Bug #6207: Found incorrect object contents
- i think we should implement opportunistic crcs in FileStore.
any time we do a write, we record in an xattr the crc...
09/27/2013
- 10:09 PM Bug #6424 (Resolved): ceph cli: -o failure to open gives backtrace, not error message
- 05:13 PM rgw Bug #6397 (Resolved): rgw: valgrind issue
- commit:1e9e34bc17564a9f7b3a84dfa9eb1aeab30dbae3 and commit:793d9d27b2398de80931d81216d22eda3b63a096
- 05:11 PM rgw Bug #6360 (Pending Backport): rgw: keystone token cache not working
- Looks good to me.
- 04:24 PM Bug #6207: Found incorrect object contents
- slider:/home/samuelj/interesting_logs/13-09-27-04:48:13-btrfsmaybezero has a possible example. notes.txt contains a ...
- 03:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
- ...
- 03:30 PM Feature #6409 (Fix Under Review): buffer: cache crc values
- 03:30 PM Feature #6408 (Fix Under Review): crc: unit test demonstrating crc for concatenation of string
- 02:02 PM Documentation #6389 (Resolved): journal_aio is set to true by default
- See http://ceph.com/docs/master/rados/configuration/journal-ref/index.html
- 01:53 PM Documentation #6389 (In Progress): journal_aio is set to true by default
- 02:01 PM Feature #6438 (Resolved): EC: implement EC client IO
- Just what it sounds like! See design docs on how this actually needs to work.
- 02:01 PM Feature #6437 (Resolved): EC: implement ECBackend recovery
- Just what it sounds like!
- 02:00 PM RADOS Feature #6436 (New): erasure-code: Downgrade testing
- We need tests to verify some behavior:
1) A cluster which has had EC enabled will not downgrade to Dumpling (and the... - 01:56 PM Bug #6400: osd crashed in dumpling due to unexpected error (EEXIST?)
- This isn't due to the JOURNAL_FULL thing, that's just noise. The assert appears to be the one which triggers when we...
- 01:53 PM Feature #6435 (Rejected): EC: [link] review and test PGBackend
- 01:49 PM Subtask #6434 (Rejected): review and test PGBackend
- the first iteration of PGBackend has been merged in master ( #5857 ) and would benefit from review and possibly tests...
- 01:15 PM rbd Feature #1790 (Resolved): rbd: have a way of establishing configured mappings at boot time
- commit:a4ddf704868832e119d7949e96fe35ab1920f06a
- 01:11 PM rbd Feature #5938 (Rejected): openstack: nova: allow live-migration without detach/reattach for rbd
- already works in grizzly
- 01:11 PM rbd Feature #6432 (Resolved): Change TGT Plugin to allow setting client name for authentication
- 01:09 PM devops Feature #5775 (In Progress): create qemu rbd package for rhel 6.5 - qemu-rbd
- 01:04 PM rgw Feature #4466 (In Progress): Quotas per bucket - synchronous
- 01:03 PM rgw Feature #6192 (Fix Under Review): rgw: DR: per object sync
- 01:03 PM rgw Feature #4340 (Fix Under Review): rgw: dr: data sync agent: implement full sync
- 01:03 PM rgw Feature #6193 (Fix Under Review): rgw: DR: per bucket sync
- 01:03 PM rgw Feature #4341 (Fix Under Review): rgw: dr: data sync agent: implement delta changes sync
- 11:30 AM devops Feature #6067 (In Progress): ceph-deploy: make mon create catch common errors
- 08:02 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Created #6410 so we can use some of the new functionality with cuttlefish too.
- 10:52 AM devops Feature #6020: radosgw-apache opinionated package
- Proposed package name is radosgw-apache. Also proposing that this be created as a subpackage of the current ceph pac...
- 10:47 AM devops Feature #6310: Get Dumpling into CentOS Ceph repo
- Waiting to hear back from Centos when 0.67.3 is available in their testing repo. But we probably want 0.67.4 to be t...
- 10:45 AM devops Feature #5282: Get Dumpling into EPEL
- Ceph-0.67.3 is in testing repos now. Sound like we want 0.67.4 to be the version that into the stable repo.
- 09:39 AM devops Bug #6410 (Resolved): support older version of ceph for mon_status commands
- Opened pull request https://github.com/ceph/ceph-deploy/pull/92
We are now using the backwards compatible command,... - 09:36 AM Bug #6429 (Need More Info): msg/Pipe.cc: 1029: FAILED assert(m)
- I assume they restarted okay? I believe this problem has been fixed in dumpling. It is a rare race having ot do wit...
- 07:00 AM Bug #6429 (Can't reproduce): msg/Pipe.cc: 1029: FAILED assert(m)
- Not sure what happened, I had restarted a server with 9 OSDs when all of a sudden around 30 of our OSD processes died...
- 09:32 AM devops Bug #6431 (Duplicate): ceph-deploy should properly delimit commands
- Duplicate of #6423
- 08:54 AM devops Bug #6431 (Duplicate): ceph-deploy should properly delimit commands
- It is currently hard to tell where ceph-deploy commands start, for example if one is deploying 10 monitors
there is ... - 07:37 AM Bug #6430 (Duplicate): OSD crashes on startup in function 'OSDMapRef OSDService::get_map(epoch_t)
- I have two OSD (0.61.8) that crash on startup. Two other OSD on the same host work just fine
Attached is the log... - 05:36 AM devops Bug #6428 (Resolved): `ceph-deploy osd` calls missing $PATH
- There are a few functions left in `ceph_deploy/osd.py` that use the old connecting library and cause issues because $...
- 05:30 AM devops Bug #6427 (Resolved): ceph-deply osd activate breaks on error
- There are undefined variables for this command that attempt to construct the error messaging...
- 03:59 AM Bug #6426 (Resolved): test_ceph_argparse broken
- 03:48 AM Bug #6426: test_ceph_argparse broken
- next is ok because it does not contain test_ceph_argparse.py
- 03:22 AM Bug #6426 (Resolved): test_ceph_argparse broken
- ...
- 03:24 AM Bug #6425 (Resolved): ceph cli: EntityAddr validation presumes presence of nonce; not required
- Joao suggested to open #6426 instead of reopening
- 02:10 AM Bug #6425 (Fix Under Review): ceph cli: EntityAddr validation presumes presence of nonce; not req...
09/26/2013
- 11:12 PM Bug #6422 (Fix Under Review): write_superblock() and write_version_stamp() not safe
- 02:08 PM Bug #6422 (Resolved): write_superblock() and write_version_stamp() not safe
- These function truncate the file before re-writing it. A crash could leave an empty file.
- 10:17 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- With both those suggestions implemented, the output looks like this:...
- 03:53 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Yeah, it's not the best message. Maybe we should special case the 'saw 0 expected 1' case to something more intellig...
- 11:23 AM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Yeah, that would probably be good. It's clearly gotten to the point that it knows what command it's looking at, but w...
- 11:14 AM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Not sure what you'd want to happen here; the "semantic reason for the failure of the command" is a bit of a stretch. ...
- 06:35 PM Bug #6425 (Resolved): ceph cli: EntityAddr validation presumes presence of nonce; not required
- 06:07 PM Bug #6425 (Fix Under Review): ceph cli: EntityAddr validation presumes presence of nonce; not req...
- https://github.com/ceph/ceph/pull/648
- 04:51 PM Bug #6425 (Resolved): ceph cli: EntityAddr validation presumes presence of nonce; not required
- Mandell Degerness notices that ceph osd blacklist rm <ip> no longer works; the Python validator
is assuming that arg... - 03:05 PM Bug #6424: ceph cli: -o failure to open gives backtrace, not error message
- 03:04 PM Bug #6424 (Resolved): ceph cli: -o failure to open gives backtrace, not error message
- Apparently the "can't open output file" path is not quite right:...
- 02:59 PM rbd Bug #6386: ceph-osd processes are having hang tasks
- I would try whatever kernel ubuntu has for precise that is > 3.8... not sure offhand what they have. If nothing else...
- 03:08 AM rbd Bug #6386: ceph-osd processes are having hang tasks
- Let me clarify the previous message. It happened once, but the hang tasks happened on many osds, not just on one. I'v...
- 03:05 AM rbd Bug #6386: ceph-osd processes are having hang tasks
- Sage,
I've seen this once on ceph 0.67.3. However, I've upgraded from 0.61.7 about 3 weeks ago and this happened o... - 02:47 PM Feature #6423 (Resolved): ceph-deploy should log command line args to logfile
- In order to help improve reading the log after the fact, ceph-deploy should log the command line args to the ./{clust...
- 02:06 PM Bug #6381: need apache-fastcgi packages built for fedora and debian
- we may need to rebuild apache-fastcgi packages for centos and rhel as well....
- 02:01 PM Subtask #5862 (Resolved): FileStore must work with ghobjects rather than hobjects
- Pull request #546
aba6efda13eb6ab4b96930e9cc2dbddebbe03f26 - 01:48 PM rgw Bug #6302 (Resolved): rgw: tasks/rgw_s3tests_multiregion.yaml tests hang
- 01:39 PM rgw Bug #6240 (Resolved): rgw: invalid read on addr in msgr via objecter
- pushed valgrind suppressions to all relevant teuthology.git branches
- 01:22 PM RADOS Feature #6421 (New): FileStore: Op unit tests
- I asked if zero-length writes to the FileStore actually worked, and Sage suggested adding some unit tests for that ki...
- 01:14 PM devops Feature #6310 (In Progress): Get Dumpling into CentOS Ceph repo
- 67.3 builds under mock on centos
- 01:13 PM Messengers Feature #6420 (New): buffer: make writemsg use splice where possible
- 01:13 PM Bug #6346 (Resolved): OSD: do not crash on bad client op input
- Merged commit:179001b42c142e0877e6c4991f88e7355c9b82ff into next via commit:b5a3978728d9435a543c00bb718f6e02438285c7
- 01:13 PM Feature #6419 (Resolved): buffer: make write_fd use splice where possible
- 01:13 PM Messengers Feature #6418 (New): buffer: make readmsg use raw_pipe where possible
- 01:12 PM Feature #6417 (Resolved): buffer: make read use raw_pipe() where possible
- 01:12 PM Feature #6416 (Resolved): buffer: create raw_pipe class; convert to buffer if inspected
- 01:11 PM Feature #6415 (Resolved): buffer: instrument c_ptr() calls
- 01:11 PM Feature #6414 (Rejected): filestore: make read() use a bufferlist method
- 01:10 PM devops Feature #6020: radosgw-apache opinionated package
- 01:09 PM Messengers Feature #6413 (New): msgr: move readmsg() into bufferlist; refactor read_message()
- 01:07 PM Messengers Feature #6412 (New): msgr: remove old rx_buffers functionality
- 01:02 PM Messengers Feature #6411 (New): msgr: move iov + sendmsg into bufferlist::sendmsg method
- ...
- 12:57 PM devops Bug #6410 (Resolved): support older version of ceph for mon_status commands
- All the `mon_status` commands that are currently implemented for dumpling versions of Ceph.
This can totally work ... - 12:56 PM Feature #6409 (Resolved): buffer: cache crc values
- 12:56 PM Feature #6408 (Resolved): crc: unit test demonstrating crc for concatenation of string
- 12:02 PM Feature #5993 (Resolved): EC: [link] Refactor recovery to use PGBackend methods
- 12:02 PM Feature #5998 (Resolved): EC: [link] FileStore must work with ghobjects rather than hobjects
- 11:30 AM devops Bug #6345 (Resolved): order of init.d script shutdown sequence
- 10:44 AM Bug #6378 (Pending Backport): mon: osdmap crc mismatch during scrub
- 10:31 AM CephFS Bug #6399 (Resolved): snaptest-0.sh fails
- In master, commit:3cffff2a1abd266abbbc97effd73b79695d29682
- 09:34 AM CephFS Bug #6399 (Fix Under Review): snaptest-0.sh fails
- 08:27 AM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- /a/teuthology-2013-09-20_23:01:15-fs-master-testing-basic-plana/8560
All these archive dirs we reference here are ... - 07:35 AM rgw Bug #6397 (Fix Under Review): rgw: valgrind issue
- 03:08 AM Tasks #4321 (Resolved): unit tests for FileStore::_detect_fs
- A new ticket can be created when there is an incentive to keep working on this topic. When and if someone find the mo...
- 03:06 AM Documentation #5058 (Resolved): docs/master/dev/osd_internals updates
- This has been transformed into an ongoing update process with no designated issue to track progress.
- 03:02 AM Feature #6274 (Resolved): mon: MonCommand.h unit tests
09/25/2013
- 11:43 PM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- where to get the mds log? (I can access your lab now)
- 01:06 PM CephFS Bug #6396 (Resolved): mds: recovery hits assert(!segment.empty()) when reissuing caps
- ...
- 09:09 PM rgw Bug #6240: rgw: invalid read on addr in msgr via objecter
- valgrind shows ...
- 05:25 PM Bug #6081: osd crashed during upgrade tests from dumpling to next in the nightlies
- ubuntu@teuthology:/a/teuthology-2013-09-25_01:35:02-upgrade-small-next-testing-basic-vps/17002
- 05:22 PM Bug #6400 (Duplicate): osd crashed in dumpling due to unexpected error (EEXIST?)
- logs: ubuntu@teuthology:/a/teuthology-2013-09-25_01:35:02-upgrade-small-next-testing-basic-vps/17000...
- 04:53 PM CephFS Bug #6399 (Resolved): snaptest-0.sh fails
- MDS backtrace:...
- 04:10 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- This is at least helped by commit:7e1c73538f44ad83db476ffa15d5121470b5154e in wip-6332 (pull request: https://github....
- 01:12 PM rgw Bug #6397 (Resolved): rgw: valgrind issue
- ...
- 12:53 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
- ...
- 12:24 PM Bug #6380: Monitor tries to bind on IPv6 address while not available yet after boot
- Sage Weil wrote:
> We've seen similar issues on fedora with ipv4; there it was just a problem with the init/systemd ... - 09:44 AM Bug #6380: Monitor tries to bind on IPv6 address while not available yet after boot
- We've seen similar issues on fedora with ipv4; there it was just a problem with the init/systemd ordering (networkman...
- 11:19 AM Bug #6346: OSD: do not crash on bad client op input
- Well there's something weird going on then, because this is post-0.69 and appears to have passed those checks:...
- 10:25 AM Bug #6392 (Resolved): crush_ops.sh failure
- 09:44 AM Bug #6392 (Resolved): crush_ops.sh failure
- ubuntu@teuthology:/a/teuthology-2013-09-24_23:00:19-rados-next-testing-basic-plana/15648
time: 418s
log: htt... - 10:16 AM Bug #6378: mon: osdmap crc mismatch during scrub
- basically we're setting different values on 'full_latest' depending on the situation:
* during trim we set it to t... - 09:42 AM Subtask #6391: stuck incomplete
- overrides: ...
- 09:41 AM Subtask #6391 (Duplicate): stuck incomplete
- ubuntu@teuthology:/a/teuthology-2013-09-22_23:00:06-rados-master-testing-basic-plana/11735/
- 09:39 AM rbd Bug #6386 (Need More Info): ceph-osd processes are having hang tasks
- We used to see this periodicially but had no real clue. At some point we stopped seeing it. I suspect that it is ju...
- 02:46 AM rbd Bug #6386 (Can't reproduce): ceph-osd processes are having hang tasks
- I am having issues with ceph-osd processes showing hang tasks messages in dmesg output on both of my ceph-osd servers...
- 09:38 AM Bug #6390 (Can't reproduce): ENOTEMPTY on TEMP coll on replay
- ubuntu@teuthology:/a/teuthology-2013-09-22_23:00:06-rados-master-testing-basic-plana/11719/
2013-09-23 01:46:26.51... - 09:30 AM Documentation #6389 (Resolved): journal_aio is set to true by default
- Since Cuttlefish, journal_aio is set to true by default.
The documentation should be updated in doc/rados/configur... - 07:35 AM Bug #6348 (Resolved): ceph-deploy new.new needs to use same seperator as conf.write
- Merged into ceph-deploy master branch with hash: 36c4c71
- 05:42 AM devops Bug #6387 (Resolved): Handle HostNotFound for execnet connection errors
- Errors like the one below should be properly handled and displayed nicely
back to the user.... - 02:41 AM Fix #6278: osd: throttle snap trimming
- Wade, could you please share with us what kernel tuning you've done? I would like to try it as I am still having some...
09/24/2013
- 04:49 PM rbd Bug #6385 (Resolved): run_xfstests.sh: doesn't work with newly-organized upstream tests
- upstream recently put tests into different groups; we currently call out specific tests that we run.
we should pro... - 04:30 PM Bug #6384 (Resolved): ceph tool: incorrect pool delete line returns unintelligible failure message
- ...
- 03:42 PM Bug #6382 (Resolved): ceph osd crush reweight is broken; bad return code check
- 02:11 PM Bug #6382 (Resolved): ceph osd crush reweight is broken; bad return code check
- it calls newcrush.adjust_item_weightf, and expects 0, but adjust_item_weight* seem to return
a count of changed weig... - 03:30 PM Documentation #6374 (Resolved): Cephx Docs Reference Service Syntax
- Removed the service syntax and referred users back to the Operating a Cluster page.
- 01:26 PM Bug #5958 (Can't reproduce): os/DBObjectMap.cc: 393: FAILED assert(!valid || cur_iter->valid())
- 01:22 PM devops Bug #6369 (Resolved): catch the missing public_addr/public_network error for mons
- Merged into ceph-deploy master branch: e67c9d0
- 09:48 AM devops Bug #6369 (Fix Under Review): catch the missing public_addr/public_network error for mons
- Opened pull request https://github.com/ceph/ceph-deploy/pull/89
- 12:24 PM Bug #6381 (Resolved): need apache-fastcgi packages built for fedora and debian
- currently, we do not have apache-fastcgi packages built for fedora 19 and debian wheezy. So, the nightlies are failin...
- 12:24 PM devops Feature #6154 (Resolved): ceph-deploy should be able to use an argument "fs-type" to specify the ...
- Merged into ceph-deploy master branch with hash: 6fb89a6
- 11:55 AM Bug #6380 (Resolved): Monitor tries to bind on IPv6 address while not available yet after boot
- Not sure yet what the problem is, but creating a issue so it's documented.
When using IPv6 only and binding the mo... - 11:49 AM Bug #6348: ceph-deploy new.new needs to use same seperator as conf.write
- Resolved by https://github.com/ceph/ceph-deploy/pull/90
- 10:32 AM Bug #6283 (Resolved): ppc build fails
- 09:18 AM Bug #6283 (Fix Under Review): ppc build fails
- 10:32 AM Bug #6370 (Resolved): osd: slow request warning exponential backoff fails at 3840 seconds
- 09:59 AM Documentation #6379 (Closed): Better document impact of putting journals on different disks
- Questions such as the following are asked frequently on the mailing list and IRC:
- What happens if the journal is l... - 09:50 AM devops Bug #5944: ceph-deploy osd needs to be moved to use the new remote helpers
- 09:44 AM rbd Bug #6267: krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- Any update?
- 09:41 AM Bug #6333 (Need More Info): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Hey-
Here is what I think we need to fully understand what is happening:
- debug ms = 1, debug osd = 20 on the ... - 09:27 AM Bug #6377 (Resolved): pg_num warn cause teuthology to stall
- lowered threshold ing teuthology's ceph.conf.template
- 08:05 AM Bug #6377 (Resolved): pg_num warn cause teuthology to stall
- The "mon: warn when pg_num is too low or appears out of whack wrt the cluster size":https://github.com/ceph/ceph/pull...
- 09:24 AM Bug #6378 (Resolved): mon: osdmap crc mismatch during scrub
- teuthology-2013-09-23_19:00:20-rados-dumpling-testing-basic-plana
had a ~30 scrub mismatch failures. possibly the... - 09:16 AM Feature #6038 (Resolved): cachepool: filestore/osd: infrastructure for large object COPY atomic r...
- 09:06 AM RADOS Bug #6246 (Resolved): crushtool dumps core with non-unique bucket IDs
- 09:02 AM Bug #6361 (Resolved): mon: 'heap' commands not working
- 09:01 AM rgw Bug #6176 (Resolved): rgw: valgrind: leak in copy_obj
- 08:41 AM Fix #6278: osd: throttle snap trimming
- We seemed to hit this issue (not the sql herring) when deep scrubs kicked off. Disabling all scrubbing and some kerne...
- 05:30 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Alright, I just tested it (the @wip-ceph-cli-env@ branch), and it works fine.
Thanks for having taken care of this... - 04:15 AM Feature #2666: rados tool: copy pool
- What's the command to copy a pool? Using "ceph -h" with latest dumpling doesn't show any command to copy pool?
09/23/2013
- 10:23 PM Documentation #6374 (Resolved): Cephx Docs Reference Service Syntax
- Replace sudo service ceph -a start | restart with a reference to the operations section. Syntax will differ based upo...
- 09:25 PM CephFS Feature #6373 (In Progress): kcephfs: qa: test fscache
- 05:24 PM Bug #6372: rados bench reports bad statistics when read --block-size > write --block-size
- I suspect the read is issued for > object size, but then just completes early, but the
stats tracking still uses th... - 05:21 PM Bug #6372 (Resolved): rados bench reports bad statistics when read --block-size > write --block-s...
- The current MB/s and average MB/s statistics for the rados read benchmark are off when the specified block size for t...
- 05:08 PM Bug #6371 (Duplicate): rados bench segfaults when read --block-size < write --block-size
- When setting the --block-size parameter for 'rados bench', if the --block-size for seq is less than the --block-size ...
- 04:29 PM Bug #6230 (Resolved): ceph osd crush move appears to be broken
- 04:23 PM Bug #6336 (Resolved): xattrs limit breaks rgw large objects
- commit:abb88d70643c3a76435b7a9d5b04ff29f7502361
- 09:41 AM Bug #6336: xattrs limit breaks rgw large objects
- Yehuda, please confirm
- 09:38 AM Bug #6336: xattrs limit breaks rgw large objects
- please review
- 03:42 PM CephFS Bug #4221 (Resolved): MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events for DECO...
- Master commit:73289b34b0be5b6612e38944794d59b5e789f841
Dumpling commit:b3d3b3747c1eef695138dac828e5fcb435309c7b - 03:12 PM Bug #6370 (Resolved): osd: slow request warning exponential backoff fails at 3840 seconds
- on cuttlefish, user reports: The OSD keeps logging this as a "slow request". The back-off logic is funny; first it d...
- 02:20 PM Bug #6322 (Resolved): mon: osdmon: write 'latest_full' after rebuilding full version from increme...
- 02:12 PM Bug #6322 (Pending Backport): mon: osdmon: write 'latest_full' after rebuilding full version from...
- 02:20 PM Bug #6323 (Resolved): mon: osdmon: don't create a huge transaction on update_from_paxos(), when r...
- 02:13 PM Bug #6323 (Pending Backport): mon: osdmon: don't create a huge transaction on update_from_paxos()...
- 02:17 PM Bug #6047 (Resolved): mon: Assert and monitor-crash when attemting to create pool-snapshots while...
- 01:02 PM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Created #6369 to track (and warn about) the missing public_addr/public_network error
- 08:01 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Created (and resolved) #6314 that addresses the case where --initial and mon starts up but has rank -1 accordingly to...
- 01:01 PM devops Bug #6369 (Resolved): catch the missing public_addr/public_network error for mons
These are the logical scenarios where we should issue a warning so that a user can fix any potential mon issues:
...- 12:49 PM devops Bug #6367 (Resolved): ceph-deploy destroy broken
- Merged in ceph-deploy master branch with hash: f551755
The call to resolve the shortname of the host in the remo... - 08:48 AM devops Bug #6367 (Fix Under Review): ceph-deploy destroy broken
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/88
- 05:22 AM devops Bug #6367 (Resolved): ceph-deploy destroy broken
- Since the new hostname shortname refactoring was done into place, the remote function
that allows one to destroy a m... - 12:43 PM Bug #6366: long TAT - due too long residence time in Ceph code
- i picked a random write, client.4406.1:23924...
- 01:23 AM Bug #6366 (Closed): long TAT - due too long residence time in Ceph code
- In a default environment (repli=2) a 4k IO take approx. 2000 micro seconds for TAT / turn-around-time from start of a...
- 10:31 AM Bug #6357 (Resolved): inverted test in osd pool create
- PR 608 landed 2d089e4644b623adb58ca8c0c924d2516efcac86
- 10:02 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Sage Weil wrote:
> Benoît Knecht wrote:
> > Do you want me to resubmit the patch with the revert of your fix includ... - 09:25 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Benoît Knecht wrote:
> Sage Weil wrote:
> > Ah, I see why. In this case we should probably revert my original fix ... - 09:19 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Sage Weil wrote:
> Ah, I see why. In this case we should probably revert my original fix too so that the options ar... - 09:03 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Benoît Knecht wrote:
> Please ignore the first patch, it didn't work if @CEPH_ARGS@ wasn't set.
Ah, I see why. I... - 07:28 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Please ignore the first patch, it didn't work if @CEPH_ARGS@ wasn't set.
- 07:09 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Well, this commit didn't solve the issue for me. Running @CEPH_ARGS="--id cinder" ceph -s@ doesn't change the client ...
- 09:56 AM Bug #6364 (Resolved): osd: copy_from an object to itself does not return an error code
- Fixed in commit:59ee51aff71fc3fdba9562f19a9a7ce2263524b6 and merged to master in commit:2b75abbd850e6988539d79c3ab564...
- 09:34 AM Bug #6364 (Fix Under Review): osd: copy_from an object to itself does not return an error code
- 09:44 AM Bug #6301 (Closed): ceph-osd hung by XFS using linux 3.10
- 09:40 AM Bug #6346: OSD: do not crash on bad client op input
- ...
- 09:34 AM Bug #6359 (Resolved): FileStore::lfn_unlink: still need to check st_nlink
- 09:31 AM devops Feature #6362 (In Progress): move teuthology required stuff off download.ceph.com
- Work is ongoing in the wip-mirror branch:
https://github.com/ceph/teuthology/tree/wip-mirror
This doesn't current... - 08:00 AM devops Bug #6314 (Resolved): catch case where mon starts up but has rank -1 accordingly to mon_status.
- Merged into ceph-deploy master branch with hash: e66d751
- 07:58 AM devops Bug #6300 (Resolved): ceph-deploy: mon create prompts for password
- Merged into ceph-deploy master branch with hash: 1c3114a
- 07:06 AM rbd Bug #6368 (Resolved): rbd nosetests keep failing with AttributeError
- We keep seeing failures for tests against rbd, I think this has something to do with the use of globals
in the test... - 04:35 AM Bug #6361 (Pending Backport): mon: 'heap' commands not working
09/20/2013
- 09:46 PM devops Feature #6365 (Resolved): Package up newer version of Qemu for RHEL & EL6.3 and 6.4
- Looks like there is a newer version of Qemu from RHEL, which has some security fixes:
ftp://ftp.redhat.com/pub/red... - 04:31 PM Bug #6364 (Resolved): osd: copy_from an object to itself does not return an error code
- I noticed this when a RadosModel run with a small number of total objects hung, and the last line was:...
- 03:56 PM devops Feature #6362 (New): move teuthology required stuff off download.ceph.com
- We want to move stuff off ceph.com as only certain people have access to that and instead move it to a lab machine ev...
- 02:05 PM rgw Bug #6360 (Fix Under Review): rgw: keystone token cache not working
- pushed a fix to wip-6360.
- 07:40 AM rgw Bug #6360 (Resolved): rgw: keystone token cache not working
- 02:05 PM rgw Bug #6176 (Pending Backport): rgw: valgrind: leak in copy_obj
- 01:37 PM Bug #6356 (Resolved): docs should warn against executing ceph-deploy as root
- Merged into ceph master branch with hash: 556956f449cef008c62352e0ae2c980156
- 01:04 PM Bug #6356: docs should warn against executing ceph-deploy as root
- Opened pull request: https://github.com/ceph/ceph/pull/613
- 12:56 PM devops Bug #6300 (Fix Under Review): ceph-deploy: mon create prompts for password
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/87
- 10:23 AM CephFS Feature #4354: mds: add an equivalent to the OSD OpTracker
- Got the OpTracker work rebased on master and pushed for review: wip-optracker, https://github.com/ceph/ceph/pull/610....
- 09:01 AM Bug #6361 (Fix Under Review): mon: 'heap' commands not working
- wip-6361, pull request 612
- 07:53 AM Bug #6361 (Resolved): mon: 'heap' commands not working
- reason is simple: ceph_heap_profiler_handle_command() in perfglue/heap_profiler.cc expects two args in the vector, t...
- 08:47 AM CephFS Bug #6284 (Resolved): client: failed xlist assert on put_inode()
- 05:46 AM Subtask #5862 (In Progress): FileStore must work with ghobjects rather than hobjects
- 05:44 AM Subtask #6113 (Resolved): add ceph osd pool create [name] [key=value]
09/19/2013
- 09:04 PM Bug #6352 (Resolved): Build from source failed
- 08:04 PM Bug #6352: Build from source failed
- make clean
./autogen.sh
./configure
make
problem still exists - 05:42 AM Bug #6352: Build from source failed
- can you try 'make distclean'? and/or a clean checkout? my guess is that automake isn't smart enough to handle the m...
- 08:01 PM Bug #6359 (Resolved): FileStore::lfn_unlink: still need to check st_nlink
- 06:41 PM rbd Bug #6293 (Resolved): Using wildcard produces wrong output
- 06:21 PM Bug #5634 (In Progress): auth startup reports "ObjectNotFound" when keyring file is unreadable
- 06:18 PM Bug #6272 (Can't reproduce): ceph command usage missing setcrushmap
- Verified with David
- 04:39 PM Bug #6357: inverted test in osd pool create
- Musing: it might be nice to have a "key=value" validation type (CephKeyVal?) to catch things like this in the front e...
- 03:40 PM Bug #6357 (Fix Under Review): inverted test in osd pool create
- "proposed fix":https://github.com/ceph/ceph/pull/608
- 03:25 PM Bug #6357 (Resolved): inverted test in osd pool create
- Because "equal != string::npos":https://github.com/ceph/ceph/blob/5216ed134b99e7dfd9e936c632b3ad2d01acd481/src/mon/OS...
- 03:08 PM Bug #5804 (Need More Info): mon: binds to 0.0.0.0:6800something port
- I did see this again on the mira045 etc. cluster, as I chatted with Joao about, and apparently mattt on IRC is experi...
- 01:37 PM CephFS Feature #6332 (Fix Under Review): mds: add config option disabling snapshots by default
- wip-6332; https://github.com/ceph/ceph/pull/606
- 01:22 PM rgw Feature #5170 (Fix Under Review): RGW: Object restriping tool to fix large objects from argonaut.
- Pushed implementation to wip-5170. It's built on top of bobtail. Adding the following commands to radosgw-admin:
<... - 11:11 AM rgw Feature #5170 (In Progress): RGW: Object restriping tool to fix large objects from argonaut.
- 01:06 PM rgw Bug #6340 (Resolved): rgw: segfault in copy_obj
- Pushed fix for both this and #6175).
- 01:05 PM rgw Bug #6175 (Resolved): rgw: valgrind: invalid reads in copy_obj
- pushed fix, backported to dumpling. Also needed to push a second fix (#6340).
- 12:23 PM Bug #6356 (Resolved): docs should warn against executing ceph-deploy as root
- This section of the docs: http://ceph.com/docs/master/start/quick-start-preflight/#configure-ssh talks about configur...
- 12:09 PM rgw Bug #6286 (Resolved): rgw: use of std::list::size() in ObjectCache
- Pushed into bobtail, cuttlefish, and dumpling.
- 11:10 AM devops Bug #6288 (Resolved): 'ceph-deploy mon create' with --cluster flag fails
- Merged to ceph-deploy master branch with hash: a4b6b6f
- 08:13 AM devops Bug #6288 (Fix Under Review): 'ceph-deploy mon create' with --cluster flag fails
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/86
- 09:25 AM Feature #6354 (Resolved): ObjectStore: allow xattrs as large as the underlying FS allows
- Right now our chained xattr implementation hard-codes a limit of 2K for each individual xattr. This is smaller than t...
- 07:31 AM devops Bug #6289 (Resolved): new remote connection needs to be able to know about sudo
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/76
Merged into ceph-deploy master branch with hash: ... - 06:17 AM Bug #6336 (Fix Under Review): xattrs limit breaks rgw large objects
- wip-6336
- 05:59 AM rbd Bug #5876 (Pending Backport): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= i...
- the fixes just went upstream to linus's tree and are not in a released kernel yet. as soon as they appear there i wi...
- 01:25 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- @Sage : in which kernel version can I found this fix please ?
- 01:26 AM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- @Sage : does this fix present upstream ? in which kernel version ?
Also available in: Atom