Activity
From 01/30/2013 to 02/28/2013
02/28/2013
- 11:50 PM Revision d6724525 (ceph): crush-map.rst: fix chooseleaf syntax in ssd example
- Fixes: 4304
Backport: bobtail
Reviewed-by: Greg Farnum <greg@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktan... - 10:59 PM Revision 6a9cda7e (ceph): Merge pull request #84 from dalgaaf/wip-da-sca-style
- Some more smaller fixes
Reviewed-by: Sage Weil <sage@inktank.com> - 09:45 PM Revision ffc0ff68 (ceph): init-ceph: kick off ceph-create-keys when starting mons
- We don't have a particularly tidy way to kick off ceph-create-keys from
sysvinit. So, do something simple, ugly, and... - 09:44 PM Revision 1e0b2d89 (ceph): init-ceph: fix default admin socket path used for status
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:33 PM Revision 0cbe406f (ceph): osd: show retry attempt in MOSDOp operator<<
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:01 PM Revision c47c02dd (ceph): msg/Pipe: allow tuning of TCP receive buffer size
- Performance tests on high-end machines have indicated the Linux autotuning
of the receive buffer sizes can cause thro... - 09:00 PM Revision e10c1d14 (ceph): msg/Pipe: move setting of socket options into a common method
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 07:10 PM Revision 50b4f72e (ceph): FileJournal::wrap_read_bl: adjust pos before returning
- Otherwise, we may feed an offset past the end of the journal to
check_header in read_entry and incorrectly determine ... - 07:10 PM Revision ee943c8b (ceph): FileJournal::wrap_read_bl: adjust pos before returning
- Otherwise, we may feed an offset past the end of the journal to
check_header in read_entry and incorrectly determine ... - 07:08 PM Revision 5d54ab15 (ceph): FileJournal::wrap_read_bl: adjust pos before returning
- Otherwise, we may feed an offset past the end of the journal to
check_header in read_entry and incorrectly determine ... - 06:45 PM Revision 6cba9245 (ceph): librbd/internal.cc: remove unused variable total_write
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:41 PM Revision c12d91e9 (ceph): librbd/internal.cc: reduce scope of 'int r'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:34 PM Revision bed61fca (ceph): librados/librados.cc: don't check unsigned 'len' against less than zero
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:33 PM Revision a2b14cf6 (ceph): librados/librados.cc: reduce scope of 'ret' in rados_objects_list_next()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:30 PM Revision f441d38c (ceph): librados/librados.cc: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:24 PM Revision 56902d72 (ceph): librados/RadosClient.cc: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast. Add some missing
includes to make the static_cast work.
Signed-off-by:... - 05:29 PM Revision 43e9edd0 (ceph): Merge pull request #82 from dalgaaf/wip-da-spec
- ceph.spec.in: add new Requires from ceph-disk-prepare
Reviewed-by: Sage Weil <sage@inktank.com> - 05:28 PM Revision 30a0852e (ceph): Merge pull request #83 from dalgaaf/wip-da-realloc
- crush/builder.c: fix realloc handling
Reviewed-by: Sage Weil <sage@inktank.com> - 05:07 PM Revision 2f66b493 (ceph): crush/builder.c: fix realloc handling
- Fix handling of realloc. If realloc() fails it returns NULL, assigning
the return value of realloc() directly to the ... - 04:59 PM Bug #4271 (Resolved): osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid)
- this was a messenger bug, fixed by commit:0f42eddef5da6c1babe9ed51ceaa3212a42c2ec4
technically a dup of #3675 - 04:57 PM Tasks #4198: osd: define data loss plan of attack for cuttlefish
- What else is left to do here?
- 04:51 PM CephFS Feature #4074 (In Progress): qa: add traceless reply test to fs suite
- 04:44 PM Subtask #4306 (Resolved): make the new snap trimmer design work with split
- Short of a primitive to cheaply move extents of keys from object a to object b we will have to live with lazily clean...
- 04:38 PM Subtask #2203 (In Progress): implement new design
- 04:13 PM Revision 9b87690f (ceph): crush/builder.c: fix sizeof handling of bucket->h.items
- Fix sizeof handling for realloc/malloc of bucket->h.items. items are
of type __s32 and not __u32 (sizeof gives the sa... - 03:57 PM Bug #4304 (Resolved): Doc: Crush map page has incorect syntax
- Not actually in bobtail, fixed in
d6724525e1a70e80101fecd445f7bf96892cdd88 - 03:50 PM Bug #4304: Doc: Crush map page has incorect syntax
- it'd also be nice to know what "indep" means compared to "firstn" :)
- 03:44 PM Bug #4304 (Resolved): Doc: Crush map page has incorect syntax
- in the ssd/platter example, need firstn
- 03:53 PM RADOS Feature #4305 (New): CRUSH: it should be possible use ssd as primary and hdd for replicas but sti...
- http://ceph.com/docs/master/rados/operations/crush-map/
rule platter {
ruleset 3
type replicated
min_size... - 03:43 PM rbd Tasks #4210 (Fix Under Review): get ceph and all libraries versions+patches in EPEL
- Josef said earlier this week that he has submitted the epel branch. I'm not sure if that means the builds are now ha...
- 03:34 PM rbd Tasks #4210: get ceph and all libraries versions+patches in EPEL
- Not libvirt, but librbd, librados, etc.
- 03:12 PM Revision 56777b08 (ceph): cls_rbd.cc: remove another unused variable
- Remove 'new_snaps' since it only used for a sizeof() call,
get the size directly from the data type of new_snaps inst... - 02:56 PM Revision 9f98b80f (ceph): cls_rbd.cc: remove unused variable
- Remove unused variable 'len', left over from commit
0b0009cfe8429072ba2af6f6843537d5501b27c3.
Signed-off-by: Danny A... - 01:58 PM Revision d75cf466 (ceph): CInode.h: use static_cast instead of C-Style cast
- Use static_cast<const T>() instead of C-Style cast. Change CInode* to
const, since it never changed.
Signed-off-by: ... - 01:56 PM devops Feature #4209 (Resolved): make ceph-create-keys work on non-upstart systems
- ceph.git commit:ffc0ff68e017747bbb1459520a0908ec75f32931
- 01:45 PM Revision 4f1cd469 (ceph): CDentry.h: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 01:16 PM Revision 5c3f5c5b (ceph): ceph.spec.in: add new Requires from ceph-disk-prepare
- Added new Requires from ceph-disk-prepare: cryptsetup, gptfdisk,
parted and util-linux.
Signed-off-by: Danny Al-Gaaf... - 01:12 PM Bug #4298: misdirected op in ffsb test
- 12:34 PM Bug #4298 (Resolved): misdirected op in ffsb test
- Logs: ubuntu@teuthology:/a/teuthology-2013-02-27_20:00:05-regression-last-master-basic/13866...
- 01:02 PM Messengers Feature #2100 (Resolved): msgr: Prevent throttled clients from slowing down non-throttled connect...
- commit:c47c02dd87064032762d6a79f58b441f624fc8ed
- 12:48 PM Feature #4299 (Resolved): crush: command to set additional parents for an interior node or leaf
- Currently you can have an OSD is multiple roots, but you need to generate the crushmap manually to do so.
Request ... - 12:01 PM Bug #4297: OSD: memory leak, do_notifies
- Confirmed, all osds are running v0.56.3.
- 12:00 PM Bug #4297 (Rejected): OSD: memory leak, do_notifies
- From the list:
From: "Bryan K. Wright" <bkw1a@ayesha.phys.virginia.edu>
Sender: ceph-devel-owner@vger.kernel.org
... - 11:47 AM rbd Bug #4285: rbd copy.sh test failing on counting images
- triggered again last night, ubuntu@teuthology:/a/teuthology-2013-02-28_01:00:03-regression-next-testing-basic$ less 1...
- 11:41 AM rbd Bug #4285: rbd copy.sh test failing on counting images
- I haven't been able to reproduce this yet, but I suspect it's the previous remove that failed. Unfortunately there ar...
- 11:24 AM rbd Subtask #4125: kernel messenger: support multiple sources of data
- > That field has no semantic meaning. All it does is
> control the alignment of the memory the OSD reads
> into, w... - 11:00 AM rbd Subtask #4125: kernel messenger: support multiple sources of data
- That field has no semantic meaning. All it does is control the alignment of the memory the OSD reads into, which wil...
- 10:33 AM rbd Subtask #4125: kernel messenger: support multiple sources of data
- Another thing about that field. In ceph_osdc_build_request(),
the 64-bit "off" value is subject to this:
... - 10:30 AM rbd Subtask #4125: kernel messenger: support multiple sources of data
- I've been winding my way through code this morning and
I've discovered there's something in the ceph message
protoc... - 11:11 AM Bug #4296: Journal: read_entry fails on wrap around
- 5d54ab154ca790688a6a1a2ad5f869c17a23980a
- 11:08 AM Bug #4296 (Resolved): Journal: read_entry fails on wrap around
- ubuntu@teuthology:/a/sage-log1/12400
- 10:48 AM CephFS Feature #4295: mds: Actually purge deleted directories
- And Sage points out the reason it's not done so far is because fragmentation mucks it up a bit....
- 10:48 AM CephFS Feature #4295 (Resolved): mds: Actually purge deleted directories
- Right now we never actually delete a directory object when it gets unlinked in the filesystem.
1) Identify the reaso... - 09:44 AM Bug #4283: ceph weight of host not recalculated after taking osd out
- Ah, right. I was thinking we'd have a problem where all new data maps to the small one, but of course as long as the ...
- 09:01 AM Bug #4283: ceph weight of host not recalculated after taking osd out
- Greg: it doesn't, no... the weights are unchanged. But the behavior he is seeing where data from an out osd is shift...
- 08:18 AM Bug #4283: ceph weight of host not recalculated after taking osd out
- @Sage, the CRUSH tunables work changes when host weights are recalculated? In particular, doesn't this change mean th...
- 09:33 AM CephFS Fix #4286: SLES 11 - cfuse: disable 'big_writes'and 'atomic_o_trunc
- Need to figure out what version of fuse added those flags.
- 08:52 AM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Yes
- 05:04 AM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Great, thanks. Can only upgrade a single osd (out of around 16) to this branch and keep the others running using argo...
- 07:20 AM rbd Bug #4284: rbd: bio getting set more than once in a message?
- My test to verify my explanation seems to have done so.
I had a message print when get_reply() was called. This
... - 06:59 AM rbd Bug #4284: rbd: bio getting set more than once in a message?
- After further consideration I don't think this is going to
be good enough. My goal here is to allow multiple blocks... - 06:28 AM rbd Bug #4284: rbd: bio getting set more than once in a message?
- Testing once more with key debug messages enabled that will I
think allow me to prove my explanation is correct. - 06:42 AM Linux kernel client Bug #3967 (Fix Under Review): libceph: complete linger requests only once
- A fix for this has been posted for review.
Subject: [PATCH] libceph: complete lingering requests only once
An o... - 06:38 AM Linux kernel client Bug #3967 (In Progress): libceph: complete linger requests only once
- I have a fix and I have verified that linger requests do
in fact get completed more than once. (I already knew
thi... - 05:54 AM Revision caa0af25 (ceph): Merge branch 'wip-4222'
- Fix for Bug 4222. Add libcephfs-test.jar to the ceph-test package.
Signed-off-by: Gary Lowell <gary.lowell@inktank... - 05:04 AM Revision 5ce08094 (ceph): fix ceph-object-corpus submodule commit
- Broken by 58f4cd53b9a29ec16c863fde8e790381dee20253
Signed-off-by: Sage Weil <sage@inktank.com> - 02:43 AM Revision 58f4cd53 (ceph): doc: rbd-cloudstack: fix bullet list, missing words, change ! to .
- 02:25 AM Revision b65ca564 (ceph): ceph-test.install: Add libcephfs-test.jar to package.
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 12:10 AM Revision f5cfd9af (ceph): Merge branch 'wip-4281'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 12:03 AM Revision be3581ec (ceph): doc: Consolidated Ubuntu and Ubuntu 12.10 requirements.
- fixes: #4288
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
02/27/2013
- 11:54 PM Revision fac4959d (ceph): mon: PaxosServices: don't ignore get_version(ver,bl) return value
- get_version(version_t,bufferlist) can only return one of two values:
-ENOENT iff the version doesn't exist
zero i... - 11:53 PM Revision ded84b1b (ceph): doc: Added dependencies for ubuntu 12.10.
- fixes: #4288
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 11:43 PM Revision cfcaceac (ceph): debian: require cryptsetup-bin
- This is needed for ceph-disk-prepare's dmcrypt support.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:07 PM Bug #3945: osd: dynamically link to leveldb
- Backports of leveldb should only be needed for squeeze, oneiric, sles, and opensuse. Squeeze also requires a snappy b...
- 10:56 PM Bug #3945: osd: dynamically link to leveldb
- Danny's pull request updated the README file. Thanks for the reminder.
- 09:38 PM Bug #3945: osd: dynamically link to leveldb
- We should also update README to include the new packages
- 09:06 AM Bug #3945: osd: dynamically link to leveldb
- 06:44 AM Bug #3945: osd: dynamically link to leveldb
- The problem is that quantal only have libleveldb1 version 0+20120530.gitdd0d562-2 (check http://packages.ubuntu.com/s...
- 05:06 AM Bug #3945: osd: dynamically link to leveldb
- packages on gitbuilder currently appear to be broken. An update attempt this morning shows:
nhm@burnupiX:~$ sud... - 10:45 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Created branch bobtail-leveldb with leveldb changes.
- 10:42 PM CephFS Tasks #4222 (Resolved): Add libcephfs-test.jar to ceph-test deb package
- Resolved with commit:
commit b65ca564b6ec7324ba43e4d35a2d114b4f7220ea
Author: Gary Lowell <glowell@inktank.com>
... - 10:41 PM Revision 5e278b85 (ceph): vstart.sh: give mon. key mon = 'allow *' caps
- This is needed for ceph-create-keys to do its thing.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:27 PM Revision 202ae8e7 (ceph): doc: fixed link and form edit.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:27 PM Revision 783555f7 (ceph): doc: Added auth entry to index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:26 PM Revision 7f7b2e74 (ceph): doc: Removed auth entries from general. Part of an auth-specific sectio...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:26 PM Revision 712fca64 (ceph): doc: Added comment to enable message. Added link to Auth Config Reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:25 PM Revision c0ed9011 (ceph): doc: Added Auth Config Reference as standalone config reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:36 PM rbd Bug #4284: rbd: bio getting set more than once in a message?
- I'm too tired to offer a guarantee, but I'm pretty sure
this is what's going on. A connection fault occurs while
r... - 05:18 PM rbd Bug #4284: rbd: bio getting set more than once in a message?
- OK, back again after a meeting.
I was thinking about it, and I wonder whether this has to
do with a message that ... - 12:53 PM rbd Bug #4284: rbd: bio getting set more than once in a message?
- We are in the path where an osd response message has
been received, and the messenger has called its
alloc_message ... - 12:28 PM rbd Bug #4284: rbd: bio getting set more than once in a message?
- I have reproduced the problem--just. I haven't had a chance
to look at it but I think I will soon be able to identi... - 09:17 AM rbd Bug #4284 (Resolved): rbd: bio getting set more than once in a message?
- I have to reproduce this again because my target machine
that hit this got rebooted. But a recent proposed change
... - 08:28 PM Revision c5b55f9b (ceph): Fix pass/fail display on exit.
- Signed-off-by: Warren Usui <warren.usui@inktank.com>
- 08:28 PM Revision 09979541 (ceph): Implement email task.
- Email.py was added so that the emailto attribute could be passed,
and to prevent 'module object has no attribute: ema... - 07:21 PM Revision f62c5ab8 (ceph): osd: allow log trimming during recovery
- We rely on min_last_complete_ondisk being accurate; as long as we have logs
from that point, the current replicas wil... - 07:04 PM Revision c980b763 (ceph): ceph-fuse: add ceph options for all current fuse options
- This will make it easier to disable these for end users, and for platforms
with old libfuse versions that don't suppo... - 06:54 PM Revision bf2cad1a (ceph): Merge pull request #81 from dalgaaf/wip-da-sca-style-1
- Fix some smaller style issues
Reviewed-by: Sage Weil <sage@inktank.com> - 06:50 PM Revision cf0d4f86 (ceph): mon: MonitorDBStore: return -ENOENT on get() if key doesn't exist
- And adjust version_t get(string,string) so that, in case of -ENOENT, it
returns 0 (when a key doesn't exist, assumes ... - 06:40 PM Revision 1e6e8aeb (ceph): ceph-fuse: fix install_debs call with new syntax
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:36 PM Revision 1a581d0d (ceph): kv_flat_btree_async.cc: remove unused variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:32 PM Revision b6884e8e (ceph): kv_flat_btree_async.cc: remove some unreachable break statements
- Remove unreachable break statements after return calls in a switch.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bise... - 06:18 PM Revision ebdf67f3 (ceph): key_value_store/cls_kvs.cc: remove unused variable dupmap
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 06:14 PM Revision ca71457b (ceph): bloom_filter.hpp: check for self assignment
- Check for self assignment in operator= to avoid problems with
dynamic memory (cppcheck).
Signed-off-by: Danny Al-Gaa... - 06:09 PM Bug #4271: osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid)
- 2013-02-27 16:48:25.907737 7f624039e700 10 osd.3 pg_epoch: 9 pg[2.3( v 9'1918 (9'917,9'1918] local-les=4 n=5 ec=1 les...
- 05:18 PM Bug #4271 (In Progress): osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid)
- ubuntu@plana25:~/cephtest/archive/log$ grep rb.0.1010.7a6d8d3c.000000000003 osd.3.log | grep -- -- | grep -v sub_...
- 10:42 AM Bug #4271: osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid)
- hit this again, ubuntu@teuthology:/a/sage-2013-02-27_09:23:30-rbd-next-testing-basic$ less 13513/teuthology.log
- 05:53 PM Revision 8d35a660 (ceph): crush/builder.c: reduce scope of oldsize in crush_add_rule()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:45 PM Revision d9d075e9 (ceph): debian: let dpkg calculate the shlibs dep for leveldb (if any)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:27 PM Revision afa811ca (ceph): CrushCompiler.cc: remove duplicate if/else branches
- Fix duplicate content of a if/else branch. Remove the
complete if/else around the content.
Signed-off-by: Danny Al-G... - 05:22 PM Revision 9a40ab3a (ceph): common/secret.c: reduce the scope of some variables
- Reduce the scope of error_buf to the place where it's used.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:01 PM Revision 4b242f9a (ceph): pick_address.cc: pass const string by refrence
- Pass 'const string networks' by reference to find_ip_in_subnet_list().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 05:00 PM Revision 7b7e9124 (ceph): obj_bencher.cc: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:53 PM Revision 4ac5edd2 (ceph): config.cc: remove unused variable 'val' from parse_injectargs()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:50 PM Revision 7aab4808 (ceph): code_environment.cc: move variable ret in get_process_name()
- Move 'ret' in get_process_name() to the correct block to suppress
warning about unused variable in cppcheck.
Signed-... - 04:49 PM Revision de3f80cd (ceph): ceph_context.cc: remove unused variable 'args' from do_command
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 04:43 PM Revision 0449c3ae (ceph): Merge pull request #79 from dalgaaf/wip-da-leveldb
- Some fixes related to switch to system leveldb
Reviewed-by: Sage Weil <sage@inktank.com> - 04:36 PM Revision babb3299 (ceph): Merge pull request #80 from dalgaaf/wip-da-4261
- ceph_argparse.cc: accept also 0/1 for boolean injectargs
Reviewed-by: Sage Weil <sage@inktank.com> - 04:29 PM rbd Feature #3417 (In Progress): krbd: read path (layering)
- 04:28 PM rbd Subtask #2855 (Closed): krbd: copy-up on write to clone
- Tracking effort under 3419
- 04:27 PM rbd Feature #3419 (New): krbd: copy-up on write to clone
- 04:25 PM rbd Subtask #2854 (Closed): krbd: write path
- Tracking under 3418
- 04:25 PM rbd Feature #3418 (In Progress): krbd: write path (layering)
- 04:23 PM rbd Subtask #2852 (Closed): krbd: open parent on open
- Move this tracking to 3416
- 04:21 PM rbd Feature #3416 (In Progress): krbd: open parent on open
- 04:21 PM rbd Feature #2851: krbd: RBD layering support
- Josh created the new feature tickets so they'd show up in redmine backlog - subtasks don't.
- 04:11 PM Bug #4281 (Resolved): mon: FAILED assert(success) on LogMonitor
- commit:f5cfd9af3c1b7fd5c585377cdf42e84c0abed64c
- 04:04 PM Documentation #4288 (Resolved): New requirements to build Ceph from source
- Added dependencies to Ubuntu. See http://ceph.com/docs/master/install/build-prerequisites/#ubuntu
- 03:47 PM Documentation #4288 (In Progress): New requirements to build Ceph from source
- 12:38 PM Documentation #4288 (Resolved): New requirements to build Ceph from source
- On Ubuntu 12.10 libsnappy-dev and libleveldb-dev are now required to build Ceph from source.
- 03:54 PM Revision cd4dc834 (ceph): cls_crypto.cc: remove some unused variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:51 PM Revision 924040ba (ceph): cls_acl.cc: remove unused variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:48 PM Revision b20d0248 (ceph): common/armor.c: reduce scope of some variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:40 PM Revision 289d8164 (ceph): ceph_argparse.cc: accept also 0/1 for boolean injectargs
- Accept also 0 (as false) and 1 (true) as arguments for
boolean option on injectargs.
Fixes: #4261
Signed-off-by: Da... - 03:39 PM devops Feature #4209: make ceph-create-keys work on non-upstart systems
- When you have a minute, hold your nose and checkout wip-create-keys. Tested on debian wheezy and it works fine.
- 02:45 PM devops Feature #4209 (Fix Under Review): make ceph-create-keys work on non-upstart systems
- 03:14 PM Revision a7e797d7 (ceph): TextTable: pass const string by refrence to define_column()
- Pass 'const string heading' by reference to define_column().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:04 PM Revision 90c407ee (ceph): CephBroker.h: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:59 PM devops Feature #3344 (Resolved): ceph-disk-prepare?: provide some sort of tool to clear out a disk, with...
- added a whiel back, commit:b2ff6e8c9d96dee2c063b126de7030a5c2ae0d02
- 02:53 PM Revision 85e36c15 (ceph): SyntheticClient.cc: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:40 PM devops Feature #3920: ceph-deploy: support other deb-based distros
- ceph-deploy commit:502acf2c0f0d31636ab739df6eff072dea9ac3e5
- 02:40 PM devops Feature #3920 (Resolved): ceph-deploy: support other deb-based distros
- 02:40 PM devops Feature #3919 (Resolved): ceph-deploy: remove upstart dependency
- 02:39 PM Revision f42a63ba (ceph): debian/control: fix Depends
- Remove request for libleveldb1 version > 1.2. Every libleveldb1 package
should work, otherwise the SO name/version of... - 01:47 PM Revision 43161532 (ceph): debian/control: add libleveldb-dev to Build-Depends:
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:47 PM Revision 2becb35a (ceph): README: add leveldb-dev to package list needed for build
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:39 PM Revision f811f727 (ceph): ceph.spec.in: fix leveldb handling
- There is no need to add leveldb as 'Requires:'. The RPM build system
will find this dependency by itself.
Add leveld... - 01:27 PM Revision 37d148ba (ceph): configure.ac: check for libsnappy
- Since libsnappy is needed by leveldb, check if the lib is installed
before check for leveldb.
Signed-off-by: Danny A... - 01:26 PM Revision 83dbaf65 (ceph): add src/leveldb to .gitignore
- Add src/leveldb to .gitignore in master, since the directory
may get checked out by older branches. Ignore it since i... - 01:22 PM Revision 8162215d (ceph): remove leveldb from master branch
- Since we now build against system leveldb and no longer
against a git submodule, drop the submodule from git master.
... - 12:58 PM Feature #3775: log: stop logging in statfs reports usage above some threshold
- 12:55 PM Feature #4203 (Resolved): kernel: support for new pool hashing feature
- 12:55 PM Fix #4192 (Resolved): osd: fix log trimming
- commit:f62c5ab8e86e20c05b3e21feb06a145f301adb92
- 12:28 PM Bug #4287 (Duplicate): Rbd volumes from pools with hyphen in name are not mappable if cephx is used
- The fix is already in the bobtail branch, in addition to master and next.
- 12:03 PM Bug #4287 (Duplicate): Rbd volumes from pools with hyphen in name are not mappable if cephx is used
- ceph 0.56.3...
- 11:45 AM Feature #4106: Monitor free space on crush pools
- sorry, i misunderstood ian's question.
i think what this is looking for is looking at the osd_stat summations (use... - 11:26 AM Feature #4106 (Duplicate): Monitor free space on crush pools
- 11:18 AM rgw Feature #4098: rgw: multi-site: Global Bucket Namespace
- This feature should be available in the Dumpling release due at the beginning of August.
- 11:10 AM CephFS Fix #4286 (Rejected): SLES 11 - cfuse: disable 'big_writes'and 'atomic_o_trunc
- encounted error when mounting a cfuse volume on SLES 11.
unknown option: big-writes
unknown option: atomic_o_trun... - 11:02 AM rbd Bug #4285 (Resolved): rbd copy.sh test failing on counting images
- ...
- 09:56 AM Bug #3816: osd/OSD.cc: 3318: FAILED assert(osd_lock.is_locked())
- I've attached the log of osd.0 and osd.3 which both crashed again.
- 09:06 AM Bug #3816 (Need More Info): osd/OSD.cc: 3318: FAILED assert(osd_lock.is_locked())
- 08:34 AM Bug #3816: osd/OSD.cc: 3318: FAILED assert(osd_lock.is_locked())
- Can you capture a bit of log leading up to the crash? debug osd = 0/20
- 06:52 AM Bug #3816: osd/OSD.cc: 3318: FAILED assert(osd_lock.is_locked())
- I just tried the fix on another cluster where I was seeing this, but still see OSDs crash:...
- 09:37 AM Bug #4282 (Need More Info): auth: could not find secret_id=0
- Can you please do
ceph osd tell \* injectargs '--debug-monc 20 --debug-auth 20 --debug-ms 1'
and then see if y... - 08:36 AM Bug #4261 (Resolved): injectargs can't parse boolean values correctly
- 07:48 AM Bug #4261: injectargs can't parse boolean values correctly
- see https://github.com/ceph/ceph/pull/80 for a fix to accept also 0/1 for boolean options on injectargs.
- 07:58 AM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- The issue for not completing multiple lingering requests
more than once is http://tracker.ceph.com/issues/3967.
(Ju... - 05:02 AM Revision c0c33834 (ceph): install: poll for packages if wait-for-package: true
- If the yaml has
wait-for-package: true
then block and poll for the packages to appear if they are not already
ther... - 05:01 AM Revision b33714a5 (ceph): test: add hadoop-internal test
- Add a test for our branch of the Hadoop code.
Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Sam Lang <sam... - 05:01 AM Revision 454e1618 (ceph): install: fix branch/tag/sha1 selection
- We were only allowing selection of packages by branch!
Signed-off-by: Sage Weil <sage@inktank.com> - 05:00 AM Revision f985106d (ceph): test: update java tests
- Add additional packages to be installed
for the java tests. This is required
due to recent changes to teuthology.
... - 04:07 AM Revision ea546aef (ceph): Build: Change build to always use system leveldb
- Dynamically link to the leveldb installed on the system rather than
statically linking ceph copy. Remove the --with-... - 02:28 AM Revision a34e7c6f (ceph): ceph-test.install: remove cepkfs-test.jar
- This was merged prematurely to mast.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 01:53 AM Revision 0e239e64 (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 01:50 AM Revision 8c6f5221 (ceph): osd: leave osd_lock locked in shutdown()
- No callers expect the lock to be dropped.
Fixes: #3816
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked fr... - 01:45 AM Revision 75ce88fb (ceph): doc: fix rst for watch/notify internals
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:36 AM Revision c313423c (ceph): OpRequest: rmw_flags may actually be 0
- If the operation includes only an invalid method,
the flags will be 0.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com... - 01:29 AM Revision d6b4a7be (ceph): Merge branch 'next'
- 01:29 AM Revision 0666b630 (ceph): ceph-test.install: Add libcephfs-test.jar.
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 01:11 AM Revision 1da4087e (ceph): Merge pull request #78 from Elbandi/master
- Some fixes and functions for libcephfs and client
Reviewed-by: Sage Weil <sage@inktank.com> - 12:53 AM Revision 1d8e1195 (ceph): client: add some new functions: lchmod, fsetattr, lutime
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:53 AM Revision ac9ed33a (ceph): client: allow change file owner or group only
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:52 AM Revision 7bd84006 (ceph): client: use get_filehandle
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:52 AM Revision 3cc0551b (ceph): client: fix log data
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:52 AM Revision c5d78f4a (ceph): libcephfs: fix default parameters document for ceph_open_layout
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 12:47 AM Revision d908c30d (ceph): ceph_manager: use an exception type
- Otherwise this obscures the error
Signed-off-by: Sage Weil <sage@inktank.com> - 12:11 AM Revision 3768050f (ceph): Merge pull request #76 from dalgaaf/wip-da-sca-style
- Fix some style related issues found by cppcheck
Reviewed-by: Sage Weil <sage@inktank.com>
02/26/2013
- 11:53 PM Revision b271b656 (ceph): Merge remote-tracking branch 'gh/wip-4256'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 11:47 PM Revision 6810111c (ceph): mon: Monitor: adjust sync start criteria considering a peon's bootstrap
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:47 PM Revision cf20ea6e (ceph): mon: Monitor: check for an argument to 'quorum' before reading the array
- Fixes: #4218
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 11:47 PM Revision ebf47175 (ceph): mon: give useful errors to user when store is missing
- We used to assert() instead, which didn't shed enough light on the cause
and could confuse the user into believing so... - 11:47 PM Revision b5c9e59f (ceph): PendingReleaseNotes: mention ceph-mon requiring the creation of data dir
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:47 PM Revision d9962cc3 (ceph): mon: Paxos: bootstrap if we have fallen behind when we start collecting
- Fixes: #4256
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 10:55 PM Revision f58601d6 (ceph): librbd: fix rollback size
- The duplicate calls to get_image_size() and get_snap_size() replaced
by 5806226cf0743bb44eaf7bc815897c6846d43233 unco... - 10:32 PM CephFS Feature #4277: Move built hadoop artificats to download URL
- The output of the gitbuilders are staged to gitbuilder.ceph.com, the release process (different set of scripts) produ...
- 02:17 PM CephFS Feature #4277 (Closed): Move built hadoop artificats to download URL
- We are at the point now where we are building some useable jar files that we'd like to reference from the Hadoop docu...
- 10:07 PM Revision a324d999 (ceph): msg: fix entity_addr_t::is_same_host() for IPv6
- We weren't checking the memcmp return value properly! Aie...
Backport: bobtail
Signed-off-by: Sage Weil <sage@inkta... - 10:07 PM devops Feature #3920 (In Progress): ceph-deploy: support other deb-based distros
- 10:07 PM Revision c8dd2b67 (ceph): msg: fix entity_addr_t::is_same_host() for IPv6
- We weren't checking the memcmp return value properly! Aie...
Backport: bobtail
Signed-off-by: Sage Weil <sage@inkta... - 10:04 PM devops Feature #4209: make ceph-create-keys work on non-upstart systems
- wip-create-keys
- 09:12 PM Revision 5b468e25 (ceph): mon: fix other debug dumps
- These should only kick in at high debug levels. Moving any "work" between
the dout() and dendl lines puts them insid... - 09:06 PM Bug #4283: ceph weight of host not recalculated after taking osd out
- Thanks for the quick info. Seems like I have to wait for bobtail to use them, right? I'm already using the other thre...
- 08:57 PM Bug #4283 (Closed): ceph weight of host not recalculated after taking osd out
- This is a known problem with the old (and unfortuantely still default) CRUSH behavior. You can fix this with a comma...
- 08:40 PM Bug #4283 (Closed): ceph weight of host not recalculated after taking osd out
- Today I experienced an osd failure and marked that osd (osd.1) out. It was a big osd so had a weight of 2. Another sm...
- 08:38 PM Revision be313909 (ceph): msgr: print dump before asserting (if that is enabled)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:35 PM Revision 20b09339 (ceph): msgr: dump corrupt message to log (at high debug levels)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:29 PM Revision 33d91cce (ceph): Merge remote-tracking branch 'gh/next'
- 08:26 PM Revision 6d89b34e (ceph): osd: allow (some) log trim when degraded, but not during recovery
- We allow some trim during degraded, although we keep more entries around to
improve our chances of a restarting OSD o... - 08:26 PM Revision 86df164d (ceph): osd: restructure calc_trim
- No functional change, except that we log more debug, yay!
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: S... - 08:26 PM Revision 0ba8db6b (ceph): osd: allow pg log trim during (non-classic) scrub
- Chunky (and deep) scrub do not care about PG log trimming. Classic scrub
still does.
Deep scrub can take a long tim... - 08:25 PM Revision dd123333 (ceph): Merge remote-tracking branch 'gh/wip_4257'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 07:45 PM Bug #4282 (Resolved): auth: could not find secret_id=0
- root@ceph-osd-2-1:/var/log/ceph# ceph -v
ceph version 0.56.2 (586538e22afba85c59beda49789ec42024e7a061)
ON osd:
... - 07:33 PM Revision c1cffc71 (ceph): mon: avoid expensive dump unless log will gather
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:13 PM Bug #4250: mon: crash in finish_proposal after recovery
- recent logs: ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11462
- 06:27 PM Bug #4250: mon: crash in finish_proposal after recovery
- I haven't been able to reproduce this, but given the stack trace, I have a feeling that it was fixed by commit:98408f...
- 07:10 PM Revision 95a379aa (ceph): ceph_common.sh: tolerate missing mds, mon, osds in conf
- With set -e this seems to fail (at least on some machines) if, say, there
is no MDS in the conf file. This fixes it.... - 07:09 PM Revision 95c13bf5 (ceph): Merge branch 'wip-4119'
- Fix for bug 4119r, create directories under /var/lib/ceph.
- 07:02 PM Bug #4253: radosgw: segfault in lockdep register
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11592
- 06:57 PM rbd Bug #4255: osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11554
2013-02-25T03... - 06:53 PM Revision 6bd09695 (ceph): testing: updating hadoop-internal test
- Small tweaks to the hadoop-internal test
to better use existing environment varaibles
and in response to the recent t... - 06:51 PM Revision 12740642 (ceph): CephBroker.cc: fix condition
- from cppcheck:
Fix Suspicious condition (assignment + comparison); Clarify
expression with parentheses.
Signed-off... - 06:50 PM Bug #3690 (In Progress): osd crashed in FileStore::_do_transaction
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11496
2013-02-25 02... - 06:46 PM Revision f0ae3804 (ceph): test: removing dead code
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
- 06:46 PM Revision 50060281 (ceph): test: updating libcephfs-java tests
- Recent changes in teuthology necessitate
changes to libcephfs-java test case.
Signed-off-by: Joe Buck <jbbuck@gmail.... - 06:43 PM Bug #4254: osd: failure to recover before timeout on rados bench and thrashing; negative stats
- recent log:
ubuntu@teuthology:/a/teuthology-2013-02-25_01:00:05-regression-master-testing-gcov/11488
ubuntu@teuthol... - 06:31 PM Revision 4ce34616 (ceph): Client.cc: reduce the scope of some variables
- Reduce the scope of some variables.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:23 PM Bug #4281: mon: FAILED assert(success) on LogMonitor
- wip-4281 contains a patch on commit:b4e1006b99a22955149ec26777c81572007fa20d
- 06:07 PM Bug #4281 (Resolved): mon: FAILED assert(success) on LogMonitor
- The bug is highly reproducible by running 'ceph -w', and presents itself in the form of:...
- 06:18 PM Revision 60b9b108 (ceph): Client.cc: use static_cast instead of C-Style cast
- Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:18 PM Revision e00bff22 (ceph): teuthology: remove CEPH_JAVA_PATH
- Since teuthology now uses debian packages,
we do not need to set this in workunit.
The one test that uses this now te... - 06:15 PM Revision 9af61cb6 (ceph): teuthology: add an extra_packages flag to install
- Some tests require additional packages
(e.g., java bindings, hadoop bindings).
Extend the install task to allow for t... - 06:00 PM Revision 455832a7 (ceph): Merge pull request #75 from alram/master
- Typo: pool should be root in rados/operations/crush-map.rst
Reviewed-by: Sage Weil <sage@inktank.com> - 05:51 PM Bug #4274 (Duplicate): osd: FAILED assert(osd_lock.is_locked())
- this is actually a dup of #3816.. reported by you! :) Cherry-picked the fix to bobtail, commit:8c6f52215240f48b5e4d...
- 01:06 PM Bug #4274 (Duplicate): osd: FAILED assert(osd_lock.is_locked())
- So I just got a notice from my test cluster that is was unhealthy.
I checked and 7 out of 12 OSDs died with the sa... - 05:50 PM Revision 26e8577d (ceph): Paxos.h: pass string name function parameter by reference
- Pass 'const string name' function parameter by reference.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:47 PM Revision dc55c293 (ceph): Typo: pool should be root in rados/operations/crush-map.rst
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 05:32 PM Feature #3484 (In Progress): mon: 'ceph df'
- 05:22 PM Documentation #4227: networks section still doesn't explain global vs specific
- Sage: yeah, that wasn't the question; the question was, say you have public/cluster nets
in global; can you specify ... - 04:50 PM Documentation #4227: networks section still doesn't explain global vs specific
- the sections behave in the usual way, where [type.foo] overrides [type] overrides [global].
- 05:01 PM CephFS Bug #4134: mds: request locking hang under snaptests
- Oh, and actually the client is the one with the seq of 2 while the MDS only thinks it should have a seq of 1. Curious...
- 02:48 PM CephFS Bug #4134 (In Progress): mds: request locking hang under snaptests
- The request is attempting to read a snapshotted inode, but the inode is still in the LOCK_SNAP_SYNC state from when i...
- 05:00 PM Revision 8f7d56c5 (ceph): Merge pull request #73 from dalgaaf/wip-da-sca-cppcheck-emptiness
- fix more emptiness checks
Reviewed-by: Sage Weil <sage@inktank.com> - 04:58 PM Revision 25768c2a (ceph): Merge pull request #74 from dalgaaf/wip-da-sca-misc
- mds/journal.cc: fix assert in replay()
Let's see how many bugs this has been hiding... :)
Reviewed-by: Sage Weil <s... - 04:35 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Unfortunately there doesn't appear to be a way to detect that with leveldb's current API. (If there was, I would exp...
- 03:02 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Will you also add checks to ensure ceph doesn't start if the on disk data is incompatible with the version of the lib...
- 10:10 AM Bug #3948 (In Progress): problems from leveldb static linkage and leveldb downgrade
- We'll create a branch off of Bobtail with the fix for 3945.
- 04:32 PM CephFS Bug #4280: mds: crash on lookupsnap
- Logs and core in kai:/home/gregf/logs/4280
- 04:31 PM CephFS Bug #4280 (Resolved): mds: crash on lookupsnap
- While running qa/workunits/snaps/snaptest-snap-rm-cmp.sh:...
- 04:25 PM Bug #4279 (Resolved): mon: received but didn't forward osd boot message
- on a cluster of 6 osds, we get osd boot messages from ~4 osds, and forward only some of them to the leader. this rep...
- 03:35 PM Feature #4278 (New): add ability to make ceph ignore io errors for non-meta/internal data
- Right now a ceph osd crashes/ exits if it gets an io error. In many cases - i assume - ceph could simply continue run...
- 03:27 PM Revision ef20382d (ceph): osd/ReplicatedPG.cc: remove unused variables
- Remove unused variable declarations.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:24 PM Revision fd5ce75b (ceph): osd_types.cc: add parenthesis around expression
- Add parenthesis around expressions like (x && y & z).
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:23 PM Revision c0da0e12 (ceph): OSDMap.cc: add parenthesis around expression
- Add parenthesis around expressions like (x && y & z).
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:13 PM Revision 83eadd89 (ceph): PGMonitor.cc: add parenthesis around expression
- Add parenthesis around expressions like (x && y & z).
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:03 PM Revision 43e2b51a (ceph): Client.cc: add parenthesis around expression
- Add parenthesis around expressions like (x && y & z).
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:56 PM rbd Bug #4272 (Resolved): rbd snap rollback broken on next
- commit:f58601d681d3aee6541119ab830ba5e2a9ec3a13
- 12:23 PM rbd Bug #4272 (Resolved): rbd snap rollback broken on next
- ...
- 02:56 PM Revision d783f95c (ceph): CephxProtocol.cc: catch end_of_buffer by reference
- Follow 'Throw by value, catch by reference' to void copying and
potential slicing the exception.
Signed-off-by: Dann... - 02:54 PM Revision bf10e5e9 (ceph): CephxProtocol.cc: catch error by reference
- Follow 'Throw by value, catch by reference' to void copying and
potential slicing the exception.
Signed-off-by: Dann... - 02:47 PM Revision d0e48ebb (ceph): crushtool.cc: remove unneeded function declaration
- Remove unneeded function declarations (data_analysis() is unused and
usage() is not needed).
Signed-off-by: Danny Al... - 02:21 PM Revision a6b3cc78 (ceph): mds/journal.cc: fix assert in replay()
- Fix assert in replay(), check if mds->sessionmap.version is cmapv
instead of assign cmapv to mds->sessionmap.version... - 12:44 PM Feature #4199: mon: data loss: low disk space handling
- 12:42 PM Feature #4273: osd: prioritize recovery for degraded pgs
- 12:40 PM Feature #4273 (Resolved): osd: prioritize recovery for degraded pgs
- When recovering from a disk/ osd crash ceph should put priority on degraded pgs. This would be the cluster in a safe ...
- 12:28 PM Bug #4257 (Resolved): osd: clearing recovery state on pg removal races with applying pushes
- commit:dd123333b8e432e1b84b67b500437949d2e75dff
- 12:19 PM Bug #4271 (Resolved): osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid)
- on latest next, including the most recent osd ooo reply fixes:...
- 11:13 AM devops Feature #4119 (Resolved): rpm: create /var/lib/ceph/* directories
- Resolved with the following commit:
commit 1c8ffc5852d573181a29e0cd9b2e83cc46381f71
Author: Gary Lowell <glowell@... - 11:12 AM rbd Cleanup #4262 (Fix Under Review): libceph: drop redundant page info assignments
- 11:08 AM RADOS Tasks #4269 (New): qa: test pool rename
- Make sure caps matching pool name work correctly after a pool is renamed.
- 11:07 AM Fix #4225 (Resolved): objecter: watch is treated as a read (linger) operation
- 11:07 AM Fix #4192 (In Progress): osd: fix log trimming
- 11:04 AM rgw Feature #3990 (In Progress): rgw: dr: implement new version objclass
- 10:46 AM Bug #4268 (Can't reproduce): mon: timecheck: teuthology task fails due to unreported timecheck fr...
- The leader didn't report he's own timecheck entry on the report, leading the teuthology task to fail for absence of s...
- 10:25 AM Revision 88555e72 (ceph): KeyValueDBMemory.cc: use empty() instead of size() == 0
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:19 AM Revision 4059d94a (ceph): ReplicatedPG.cc: use empty() instead of size() == 0
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:16 AM Revision a2d842f9 (ceph): FileStore.cc: use if(!empty()) instead of if(size())
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:15 AM Revision e3b27b7b (ceph): mon_store_converter.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:13 AM Revision ed83d4b9 (ceph): Paxos.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:01 AM Revision 14716fd2 (ceph): Monitor.h: use empty() instead of !size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 10:01 AM Revision 7a81b07f (ceph): Monitor.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 09:36 AM CephFS Bug #4266 (Won't Fix): crush placement from crushtool mismatches observed behavior for pools othe...
- The --x is only coincidentally related to the second part of hte pgid (currently). If you want to map a specific pgi...
- 08:05 AM CephFS Bug #4266 (Won't Fix): crush placement from crushtool mismatches observed behavior for pools othe...
- Because OSDs add the pool id to the pg number to form the x passed to crush_do_rule, whereas crushtool just gets an x...
- 09:27 AM Feature #4267 (Resolved): osd: mark self immediately down on orderly (SIGINT, SIGTERM) shutdown
- If you kill a daemon, it should take the time to tell the monitor it is going down. This will avoid having to wait f...
- 07:51 AM Revision 1c8ffc58 (ceph): ceph.spec.in: Create placeholder directorys under /var/lib/ceph (Bug 4...
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 05:12 AM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Of course it's not going to be easy... The problem showed up
this time at offset 2199533527040 instead of 219953839... - 03:35 AM Revision aa79077c (ceph): configure.ac: Add test for c++ compiler.
- The AC_PROG_CXX macro sets a flag if a C++ compiler is found
but does not fail if one is not found, it left to applic... - 03:15 AM Revision 3ebabb34 (ceph): Add timer.py and display summary info in run.py.
- Signed-off-by: Warren Usui <warren.usui@inktank.com>
- 03:15 AM Revision 51fa5fb2 (ceph): nuke: blow away /home/ubuntu/cephtest too
- (along with /tmp/cephtest)
Signed-off-by: Sage Weil <sage@inktank.com> - 03:14 AM Revision b744f423 (ceph): radosgw-admin: Bug fixes for issue 4251.
- Fixes errors introduced by d44fb14762c3d7e2853a8e4be012cd8e4557124e.
Signed-off-by caleb.miles <caleb.miles@inktank.... - 02:27 AM Revision 0b968f51 (ceph): Add rbd locking/fencing test
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 02:17 AM Revision ccdafa06 (ceph): test_lock_fence.sh, rbdrw.py: rbd lock/fence test
- qa/workunits/rbd/test_lock_fence.sh runs using test/rbdrw.py
rbdrw.py creates an image, locks it, and runs an I/O lo... - 01:54 AM Revision bee8dffc (ceph): nuke: blow away /home/ubuntu/cephtest too
- (along with /tmp/cephtest)
Signed-off-by: Sage Weil <sage@inktank.com> - 01:48 AM Revision 1f142741 (ceph): Merge remote-tracking branch 'gh/wip-4249-master'
- 01:48 AM Revision 9096d706 (ceph): Merge remote-tracking branch 'gh/wip-4249' into next
- 01:41 AM Revision 21471c1e (ceph): Merge remote-tracking branch 'gh/wip-4252'
- 01:32 AM Revision 8ce9490e (ceph): rgw: no lockdep on radosgw
- This currently crashes because of linking problems, see #4253.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:55 AM Revision 98408f5c (ceph): mon: PaxosService: remove lingering uses of paxos getters and wait methods
- We should use the PaxosServices getters, setters, and wait methods when and
wherever possible. These must have falle... - 12:50 AM Revision 9d472ca7 (ceph): systest: restrict list error acceptance
- Only ignore errors after the midway point if the midway_sem_post is
defined.
Signed-off-by: Josh Durgin <josh.durgin... - 12:50 AM Revision b64d2617 (ceph): systest: fix race with pool deletion
- The second test have pool deletion and object listing wait on the same
semaphore to connect and start. This led to er... - 12:49 AM Revision 29642d33 (ceph): Merge remote-tracking branch 'gh/wip-4147'
- 12:29 AM Revision 9e6025b6 (ceph): doc: Added subnet example and verbiage to network settings.
- fixes: #4049
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 12:12 AM Revision 5e5530be (ceph): doc: Added content to remove REJECT rules from iptables.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:09 AM Revision 9c693d7e (ceph): test_rbd: move flatten tests back into TestClone
- They need the same setup, and it's easy enough to run specific
subtests. Making them a separate subclass accidentally... - 12:02 AM Revision 3e8d11b4 (ceph): Add timer.py and display summary info in run.py.
- Signed-off-by: Warren Usui <warren.usui@inktank.com>
02/25/2013
- 11:59 PM Revision 55bd7687 (ceph): qa: enable watch-notify dependent test
- This works now that watch-notify has been reworked a bit.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 11:56 PM Revision 345aa2df (ceph): test_rbd: close image before removing it
- This error was masked before by watch notify not differentiating
between watches from the same client with different ... - 11:29 PM Revision 79c4e7e9 (ceph): osd: pull requeued requests off one at a time
- Pull items off the finished queue on at a time. In certain cases, an
event may result in new items betting added to ... - 11:29 PM Revision 79d68ae8 (ceph): osd: requeue pg waiters at the front of the finished queue
- We could have a sequence like:
- op1
- notify
- op2
in the finished queue. Op1 gets put on waiting_for_pg, the not... - 11:28 PM Revision 9ab0fd75 (ceph): doc: Added a small ref section for osd config reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:27 PM Revision 3ef6d5bd (ceph): doc: Updated osd configuration reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:02 PM Revision 5b24a68b (ceph): systest: restrict list error acceptance
- Only ignore errors after the midway point if the midway_sem_post is
defined.
Signed-off-by: Josh Durgin <josh.durgin... - 10:55 PM Revision b0271e39 (ceph): systest: fix race with pool deletion
- The second test have pool deletion and object listing wait on the same
semaphore to connect and start. This led to er... - 10:28 PM Bug #3444 (Duplicate): Qemu librbd aio
- 10:09 PM Revision 2b7deeea (ceph): qa: output rados test names as they run
- So we don't have to figure out which test is running from the output,
which can be difficult with the system tests.
... - 09:58 PM Revision 3a6ce5d0 (ceph): mds: open mydir after replay
- In certain cases, we may replay the journal and not end up with the
dirfrag for mydir open. This is fine--we just ne... - 09:33 PM Bug #3631 (Resolved): osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid) during ...
- commit:56c5a07708d52de1699585c9560cff8b4e993d0a
- 09:30 PM Revision a01dea6a (ceph): ReplicatedPG::C_OSD_CommittedPushedObject take epoch submitted
- What we really care about is that the epoch in which the Context
was submitted is at complete() time >= last_peering_... - 09:30 PM Revision 04ee8f47 (ceph): ReplicatedPG::C_OSD_CommittedPushedObject: use intrusive_ptr for pg
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:30 PM Revision 67225339 (ceph): PG::build_scrub_map: detect race with peering via last_peering_reset
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:30 PM Revision 62999ea2 (ceph): PG,ReplicatedPG: use pg_has_reset_since to discard old async events
- Local async events are obsolete if the pg is deleting or if the
epoch at which they were created is prior to last_pee... - 09:12 PM Revision 31ef4a12 (ceph): ceph.conf: debug ms = 1 for monitors
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:12 PM Revision d7337364 (ceph): exec, pexec: set TESTDIR
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:12 PM Revision 24eeb0da (ceph): rbd: drop udev
- The packages have these rules now.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:12 PM Revision a60e7b59 (ceph): rbd: set TESTDIR when running xfstests
- [elder@inktank.com: fixed typo]
Signed-off-by: Sage Weil <sage@inktank.com> - 08:32 PM Bug #4265 (Won't Fix): ceph-deploy new doesn't support multiple monitors on one host.
- It appears that ceph-deploy is treating both monitor name and hostname as ipaddress.
- 08:12 PM Revision c4537347 (ceph): librbd: remove unused internal method
- get_snap_size() has been replaced by get_image_size(snap_id) everywhere.
Signed-off-by: Josh Durgin <josh.durgin@ink... - 08:12 PM Revision db5fc227 (ceph): Merge branch 'wip-4249' into wip-4249-master
- Make snap_rollback() only take a read lock on snap_lock, since
it does not modify snapshot-related fields.
Conflicts:... - 07:44 PM Bug #3945: osd: dynamically link to leveldb
- The leveldb backports (and libsnappy) available for for platforms that need them.
- 07:40 PM Feature #4005: Add perftools to the kernel debian package script
- Patch submitted to the kernel build maintainer.
- 07:39 PM Bug #3955 (Resolved): Configure should explicity check for c++ compiler.
- Resolved with:
commit aa79077c2442e518c11f3d1885461d734909370b
Author: Gary Lowell <glowell@inktank.com>
Date: ... - 07:36 PM Revision 5806226c (ceph): librbd: drop snap_lock before invalidating cache
- Writeback will take the snap_lock, so read everything we need under it
before invalidating the cache. This avoids a r... - 07:29 PM Bug #4027 (Resolved): ceph-fuse on opensuse12 has the wrong requirement name for libfuse dependency
- Cleaning up the requires list, resolves the issue with libfuse naming, by removing it.
commit 9952f2dd509b436a3cf1... - 07:20 PM rgw Bug #4251 (Resolved): radosgw-admin test fails on master
- 07:19 PM rgw Bug #4251: radosgw-admin test fails on master
- Resolved commit: b744f423614898c1084d5a8b48b9c54de2a7f570
- 07:12 PM rbd Bug #4237 (Resolved): krbd: ignore zero-length requests
- This has been committed.
commit 4dda41d3d76747414586a4bad5615b550e0986b1
Author: Alex Elder <elder@inktank.com>
... - 07:11 PM rbd Bug #4238 (Resolved): krbd: still more barrier fixes
- This has been committed.
commit 632b88cadece050ca925d74bda250c4a320c5cc7
Author: Alex Elder <elder@inktank.com>
... - 07:11 PM rbd Bug #4235 (Resolved): krbd: add some dout() trace calls
- This has been committed.
commit 37206ee5bede14d59306fea3af4c0105d4712342
Author: Alex Elder <elder@inktank.com>
... - 07:10 PM rbd Cleanup #4234 (Resolved): libceph: encapsulate flag setting
- This has been committed.
commit c9ffc77adebf9dfe3026ede6c8b3c61586b485b7
Author: Alex Elder <elder@inktank.com>
... - 07:09 PM rbd Bug #4184 (Resolved): krbd: fix some sparse problems
- Josh reviewed these patches, and I have updated, re-tested
and committed them.
cc344fa rbd: eliminate sparse warn... - 07:01 PM rbd Feature #3190 (Resolved): qa: test fencing
- commit:ccdafa067afed74b209537ae45ff8b49bb5fab3b
- 05:49 PM rbd Bug #4249 (Resolved): librbd: recursive lock of snap_lock during snap_rollback
- commit:9096d70642880946b0b477e33f7debabbefec9fa
- 12:26 PM rbd Bug #4249 (Fix Under Review): librbd: recursive lock of snap_lock during snap_rollback
- wip-4249
- 05:41 PM rbd Bug #4252 (Resolved): rbd python bindings: error removing image on list_children
- commit:21471c1ef4cf02e068a6e6c49cd41e95efec952a
- 04:46 PM rbd Bug #4252 (Fix Under Review): rbd python bindings: error removing image on list_children
- wip-4252, test broke with the watch-notify changes
- 04:02 PM rbd Bug #4252 (In Progress): rbd python bindings: error removing image on list_children
- 05:33 PM Bug #4253: radosgw: segfault in lockdep register
- I updated the suite to not run lockdep against radosgw for now.
- 02:44 PM Bug #4253: radosgw: segfault in lockdep register
- Probably due to dual linkage with libcommon (libglobal -> libcommon, librados -> libcommon) whereas libglobal is link...
- 12:45 PM Bug #4253: radosgw: segfault in lockdep register
- Can't reproduce it locally, only using the specific binary package. Looks like some linking issue:...
- 05:10 PM Revision 7f61072a (ceph): Merge pull request #71 from dalgaaf/wip-da-sca-c_str
- fix some c_str() usage
Reviewed-by: Sage Weil <sage@inktank.com> - 05:08 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- The output did not indicate that rbd thought it
did something wrong.
That is, the object request came back and in... - 04:08 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Requests to write 4096 bytes came back from the osd with a
written count of 2048 bytes.
Now I'm afraid I have to ... - 01:23 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- > BTW fixed the rbd namer thing; pull latest teuthology.git.
Well, "fixed" is generous. It had a bug, which I've ... - 12:09 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- BTW fixed the rbd namer thing; pull latest teuthology.git.
- 11:12 AM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I was reporting if an error code got returned from
the osd. However the loop device function that
reports the "Wri... - 11:04 AM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- The tests I started running this morning finally hit number 259.
It did have the problem, but I got no messages from... - 09:09 AM rbd Bug #4242 (In Progress): krbd: xfstest 259 failure (FS size near 4TB)
- I tried to reproduce this with a smaller subset of tests
(just 258 and then 259 repeatedly) over the weekend but
th... - 05:06 PM Revision 9d92ad6e (ceph): rados: crank up mon debugging for the mon thrashing tests
- At least for now!
Signed-off-by: Sage Weil <sage@inktank.com> - 05:03 PM Fix #4128 (Resolved): osd: fix pgid=(pool,seed) -> crush input mapping
- 05:03 PM Feature #3403 (Resolved): librados: expose a list of watchers on an object
- 05:03 PM Feature #4203 (Fix Under Review): kernel: support for new pool hashing feature
- 04:58 PM rbd Tasks #4210 (Rejected): get ceph and all libraries versions+patches in EPEL
- EPEL does not take packages already in RHEL.
- 04:53 PM Revision 35ce9d63 (ceph): Merge pull request #72 from dalgaaf/wip-da-comp-sign-unsign
- Monitor.cc: fix -Wsign-
Reviewed-by: Sage Weil <sage@inktank.com> - 04:52 PM Revision d1724bfe (ceph): Merge pull request #70 from dalgaaf/wip-da-fix-spec
- Add missing files to spec and debian files
Reviewed-by: Sage Weil <sage@inktank.com> - 04:50 PM Bug #4147 (Resolved): librados: st_rados_list_objects failure
- 04:50 PM Bug #4147: librados: st_rados_list_objects failure
- commit:29642d33c3595c3d6db9c4c364b9ee69663cfc3d
- 03:40 PM Bug #4147 (Fix Under Review): librados: st_rados_list_objects failure
- There was a race in the test. Fix is in wip-4147.
- 04:35 PM Tasks #3779 (Resolved): update osd config ref as appropriate
- Updated the OSD configuration reference. Filestore and journal need updating too.
- 04:31 PM Documentation #4049 (Resolved): public/cluster network doc should mention that multiple subnets a...
- Added verbal mention and syntax example to public network and cluster network.
- 04:21 PM Revision 3fdf4393 (ceph): doc: Moved admonition to kernel mount.
- fixes: #4146
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 04:19 PM Revision 516935bc (ceph): doc: Added verbiage to describe single host deadlocks.
- fixes: #3076
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 04:15 PM Documentation #4260 (In Progress): centos/suse default reject rule in iptables
- For now, I've added a description to the monitor troubleshooting section. This should be added to troubleshooting sec...
- 02:14 PM Documentation #4260: centos/suse default reject rule in iptables
- Not an FS issue! :)
- 10:18 AM Documentation #4260 (Resolved): centos/suse default reject rule in iptables
Saw this on Ken's centos vms, but it sounds like the same issue may occur on suse. The default OS install adds a r...- 03:43 PM rbd Subtask #4263 (Fix Under Review): libceph: clearly abstract message data operations
- These patches have been posted for review.
[PATCH 0/4] libceph: abstract setting message data info
[PATCH 1/4] li... - 03:33 PM rbd Subtask #4263 (Resolved): libceph: clearly abstract message data operations
- Currently the fields in a message structure related
what constitutes the data portion of a message are
manipulated ... - 03:38 PM Revision 67103a88 (ceph): Monitor.cc: fix -Wsign-compare
- Fix -Wsign-compare, make 'i' unsigned int.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:15 PM rbd Cleanup #4262: libceph: drop redundant page info assignments
- These patches have been posted for review (marking
this "Feedback").
[PATCH 0/3] libceph: focus calc_layout() on ... - 03:03 PM rbd Cleanup #4262: libceph: drop redundant page info assignments
- Three patches implement this change. The net result is
that calc_layout() becomes focused only on filling in the
o... - 02:53 PM rbd Cleanup #4262 (Resolved): libceph: drop redundant page info assignments
- In calc_layout(), there are some assignments to osd request
fields r_num_pages and r_page_alignment. These assignme... - 03:14 PM rbd Bug #4240 (Fix Under Review): libceph: fix a osd request memory leak
- This has been posted for review.
[PATCH] libceph: fix a osd request memory leak - 02:36 PM Revision cf167a1f (ceph): debian: add new files
- Add new (installed) files to debian install files.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:34 PM Revision 4b77deb4 (ceph): ceph.spec.in: add new files
- Add new files to spec file since they get installed.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 02:28 PM Revision 6ae10fe7 (ceph): Client.cc: don't pass c_str() if std::string is expected
- Don't pass c_str() to _lookup(). The function expect a std::string
as second parameter.
Signed-off-by: Danny Al-Gaaf... - 02:08 PM Bug #4261: injectargs can't parse boolean values correctly
- To be explicit, 'ceph osd tell \* -- --filestore-flusher=false' works.
There is a bug here though: parsing boolean... - 12:18 PM Bug #4261: injectargs can't parse boolean values correctly
- or more consistently with other tools, use ...
- 12:13 PM Bug #4261: injectargs can't parse boolean values correctly
- --no-foo, or --foo=0
the problem with your #2 is the cli is parsing it. add a space inside the quotes - 11:13 AM Bug #4261 (Resolved): injectargs can't parse boolean values correctly
- The issue wasn't quickly evident after a quick skim of the code, but this report came in on ceph-users (for bobtail) ...
- 01:55 PM Messengers Feature #2100: msgr: Prevent throttled clients from slowing down non-throttled connections (TCP b...
- I went over the code and it all looks good! (Modulo testing for impact, etc of course.)
Reviewed-by: Greg Farnum <gr... - 01:51 PM CephFS Bug #4248: mds: replay does not correctly update CInode::first and ::last members
- This isn't currently journaled correctly, in addition to not setting its snapid ranges correctly. There's nothing tha...
- 11:19 AM CephFS Bug #4248 (In Progress): mds: replay does not correctly update CInode::first and ::last members
- Okay, that didn't fix the problem. The stray dir now was snapids [3, HEAD] instead of [4, HEAD], but the inode remain...
- 01:10 PM Revision 350481f9 (ceph): Paxos.h: fix dangerouse use of c_str()
- No need to use c_str() in get_statename(), simply return a
std::strin instead.
Signed-off-by: Danny Al-Gaaf <danny.a... - 01:02 PM Bug #3971 (Rejected): can't attach rbd image volume to instance
- Not a bug, just an old package.
- 12:27 PM rbd Bug #4255 (Duplicate): osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
- 12:14 PM Bug #4256 (In Progress): mon/Paxos.cc: 534: FAILED assert(begin->last_committed == last_committed)
- This bug is caused by what I most feared that could happen with the single-paxos approach, but it always remained a t...
- 10:30 AM Feature #2611 (Resolved): mon: Single-Paxos
- commit:9af94eea209fc2555f66214f01f3edddc35d4209
- 09:51 AM CephFS Feature #3821 (New): qa: run backuppc as part of qa suite
- 08:23 AM Documentation #4146 (Resolved): cephfs quickstart: clarify mounting on same node
- Moved admonition to kernel mount section, and added link to an FAQ entry explaining the issue in greater detail.
- 08:22 AM Documentation #3076 (Resolved): doc: Explain how loopback mounts (using kclient, ceph-fuse should...
- Added new section to the FAQ providing details. Provided links in quick start admonitions to the FAQ.
02/24/2013
- 09:31 PM Revision 9217c4ac (ceph): debian: make gdisk, parted requirements, not recommendations.
- ceph-prepare-disk (and thus ceph-deploy) need this.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:22 PM Revision 0be28af0 (ceph): Merge remote-tracking branch 'gh/next'
- 03:51 PM Revision 8dcbf8b6 (ceph): specify deterministic admin socket path for admin_socket.py tests
- Otherwise we don't know the path because the default now includes $pid.
- 03:24 PM Revision 6bae2a5d (ceph): Grammar typo
- Signed-off-by: Neil Levine <neil.levine@inktank.com>
- 03:24 PM Revision 35c951f3 (ceph): Minor wording change.
- Signed-off-by: Neil Levine <neil.levine@inktank.com>
- 03:24 PM Revision 3896896c (ceph): Changes to the OS support, multi-data center, and hypervisor questions.
- Signed-off-by: Neil Levine <neil.levine@inktank.com>
- 08:58 AM Bug #4257: osd: clearing recovery state on pg removal races with applying pushes
- nevermind.. just need to call start_peering_interval() to set last_peering_interval. testing wip-4257.
- 08:47 AM Bug #4257: osd: clearing recovery state on pg removal races with applying pushes
- Actually, I think this might be a bug in the non-removal case too. We call cancel_recovery() from start_peering_inte...
- 08:31 AM Bug #4257 (Resolved): osd: clearing recovery state on pg removal races with applying pushes
- The sync on_removal() call to clear_recovery() conflicts with push transactions that are in-flight to the filestore.....
- 07:37 AM Bug #4256 (Resolved): mon/Paxos.cc: 534: FAILED assert(begin->last_committed == last_committed)
- ...
- 12:36 AM Revision 0cd215ee (ceph): mds: reencode MDSMap in MMDSMap if MDSENC feature is not present
- In some cases the MMDSMap message from mon -> client passes from leader ->
peon -> client, and the leader doesn't enc...
02/23/2013
- 08:43 PM rbd Bug #4255 (Duplicate): osdc/ObjectCacher.cc: 517: FAILED assert(i->empty())
- ...
- 04:38 PM Revision c07e8ea7 (ceph): qa/run_xfstests.sh: use $TESTDIR instead of /tmp/cephtest
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:34 PM Revision 8235b16c (ceph): osd: an interval can't go readwrite if its acting is empty
- Let's not forget that min_size can be zero.
Fixes: #4159
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked ... - 12:52 PM Feature #4230: librados: node.js bindings
- Email was rejected by redmine. This was sent to ceph-devel:
----
Hi Wido,
Also cc'ing ceph-devel.
Few month... - 12:12 PM Bug #4254 (Resolved): osd: failure to recover before timeout on rados bench and thrashing; negati...
- snippet:...
- 12:10 PM Bug #4253 (Can't reproduce): radosgw: segfault in lockdep register
- this is failing in the master branch:...
- 12:08 PM rbd Bug #4252 (Resolved): rbd python bindings: error removing image on list_children
- ...
- 10:32 AM rgw Bug #4251 (Resolved): radosgw-admin test fails on master
- ...
- 10:30 AM Bug #4250 (Resolved): mon: crash in finish_proposal after recovery
- ...
- 08:31 AM rbd Bug #4249 (Resolved): librbd: recursive lock of snap_lock during snap_rollback
- ...
- 12:24 AM Revision 704db850 (ceph): mkcephfs: create mon data dir prior to ceph-mon --mkfs
- ceph-mon now expects this directory to already exist.
Signed-off-by: Sage Weil <sage@inktank.com>
02/22/2013
- 11:38 PM Revision 10f50d35 (ceph): doc: Added a lot of info to OSD troubleshooting.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:37 PM Revision e68f2c85 (ceph): doc: Added mention of Admin Socket interface and brief description.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:35 PM Revision 73317bd7 (ceph): doc: Changed title to OSD and PG, indicating both subjects are covered.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:34 PM Revision ab7039d6 (ceph): doc: Added references from monitoring OSD to troubleshooting OSD.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:33 PM Revision 97cc7389 (ceph): doc: set maxdepth to 2, so TOC isn't so long with new OSD troubleshooting.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:15 PM Revision 7c940836 (ceph): client: use 4MB f_bsize and f_frsize for statfs
- Old stat(1) reports:
Block size: 1048576 Fundamental block size: 1048576
and the df(1) arithmetic works out. ... - 10:57 PM Revision 64267eb3 (ceph): test/librados/watch_notify: fix warning
- In file included from test/librados/watch_notify.cc:8:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::As... - 10:40 PM Revision 53586e71 (ceph): ceph-object-corpus: re-update
- This was set by 9af94eea209fc2555f66214f01f3edddc35d4209, then single
paxos merge, then accidentally reverted by the ... - 10:23 PM Revision e4fd70fc (ceph): Merge remote-tracking branch 'gh/wip-rbd-flatten-deadlock'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 10:19 PM Revision 2dae6a68 (ceph): PG::proc_replica_log: oinfo.last_complete must be *before* first entry ...
- Fixes: #4189
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:16 PM Revision e03657e4 (ceph): Merge remote-tracking branch 'gh/wip-objecter-fsx'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 09:41 PM Revision 05a87798 (ceph): rbd_xfstests: re-enable test 049
- Test 049 is now passing, so add it back to the set that runs
nightly. It only takes 10-15 seconds to run, so it shou... - 09:14 PM Bug #4079: osd: journal aio deadlock
- Another possible clue. Things seemed to be going reasonably
well on this run, but sometime during test 78 things we... - 09:00 PM Feature #4207 (Fix Under Review): osd/librados: add ops to list snaps for an object
- 11:35 AM Feature #4207 (In Progress): osd/librados: add ops to list snaps for an object
- 08:50 PM Revision d612a9ab (ceph): Merge branch 'wip-3403-4-rebase'
- Feature: #3403
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:51 PM Revision d8021a1a (ceph): nuke: sudo for killall
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:44 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- I"m seeing this fairly consistently now.
- 01:03 PM rbd Bug #4242: krbd: xfstest 259 failure (FS size near 4TB)
- Whoops, it was 4 TB (2^42) not 4 GB.
I'll update what I originally wrote shortly. - 01:00 PM rbd Bug #4242 (Closed): krbd: xfstest 259 failure (FS size near 4TB)
- I have now seen this at least twice. I think it's inconsistent
but it might be important. Not marking it high yet,... - 05:15 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- we think this is due to pg log trimming. see wip-osd-log-trim and wip-pglog
- 04:27 PM Messengers Feature #2100: msgr: Prevent throttled clients from slowing down non-throttled connections (TCP b...
- yeah, sure! still needs testing, tho, too.
- 04:17 PM Messengers Feature #2100: msgr: Prevent throttled clients from slowing down non-throttled connections (TCP b...
- This need a review? :)
- 03:48 PM Messengers Feature #2100: msgr: Prevent throttled clients from slowing down non-throttled connections (TCP b...
- 04:26 PM Bug #4226 (Resolved): Monitor crash happens when running Teuthology
- also updated ceph-deploy and mkcephfs, commit:704db850131643b26bafe6594946cacce483c171
- 09:14 AM Bug #4226: Monitor crash happens when running Teuthology
- Sure thing.
- 09:02 AM Bug #4226: Monitor crash happens when running Teuthology
- we need to test that mkcephfs now does this. also, can you blow away the current PendingReleaseNotes (ceph.git root ...
- 03:03 AM Bug #4226: Monitor crash happens when running Teuthology
- This is due to a new requirement for the monitor before --mkfs can be issued: the creation of the monitor's data path...
- 03:33 PM rbd Bug #3958 (Resolved): rbd fsx fails with EBUSY
- 03:32 PM CephFS Bug #3794 (Resolved): uclient: reports sizes wrong in some cases
- 03:10 PM CephFS Bug #3794: uclient: reports sizes wrong in some cases
- Assuming we aren't pushing this into a stable release without more testing, both the patch and backport are
Review... - 02:58 PM CephFS Bug #3794 (Fix Under Review): uclient: reports sizes wrong in some cases
- wip-statvfs
- 03:31 PM CephFS Bug #3793 (Resolved): wrong size reported in some distributions/toolchains
- 'ceph: fix statvfs fr_size' in kernel tree.
- 02:58 PM CephFS Bug #3793: wrong size reported in some distributions/toolchains
- I pushed a wip-statvfs which fixes this for ceph-fuse.
- 03:22 PM CephFS Bug #4248 (Fix Under Review): mds: replay does not correctly update CInode::first and ::last members
- wip-4248-snapid-journaling
Also pushing out a v0.57-based branch to the user to try out. - 03:17 PM CephFS Bug #4248 (Resolved): mds: replay does not correctly update CInode::first and ::last members
- This came in over the mailing list....
- 03:14 PM rbd Bug #1070 (Rejected): krbd: ^C doesn't work
- Yeah, marking rejected. thanks for digging in!
- 03:08 PM rbd Bug #1070: krbd: ^C doesn't work
- I can't relate them but this is involved in at
least some of the code involved:
http://tracker.ceph.com/issues/38... - 03:00 PM rgw Bug #4247 (Resolved): rgw: swift list bucket entities missing attrs (in xml)
- <container> instead of <container name="foo">
<subdir> instead of <subdir name="bar"> - 02:24 PM rbd Fix #3665 (Resolved): librbd: deadlock during flatten
- commit:e4fd70fcec3a9abb7f19517326e46f58031c4196
- 02:13 PM rbd Bug #913 (Resolved): krbd: handle race between notify and rbd device shutdown
- This is very old. And--provided I understand it--it is resolved
in the current rbd code.
When a mapped rbd image... - 02:04 PM Bug #4246: osd/msgr: rebound to an addr a peer osd already had open
- see commit:e229f8451d37913225c49481b2ce2896ca6788a2. i think maybe an explicit handshake is needed here on each conn...
- 02:01 PM Bug #4246 (Resolved): osd/msgr: rebound to an addr a peer osd already had open
- On osd.1, we see...
- 01:51 PM rgw Feature #4245 (New): Support some subset of Amazon Identity Management
- Currently we are not able to provide any of the fine grained control over resource permissions that Amazon Identity M...
- 01:50 PM rbd Bug #4244 (Resolved): rbd xfstests: re-enable xfstests 049 in nightly run
- Pushed to ceph-qa-suite/master....
- 01:38 PM rbd Bug #4244 (Resolved): rbd xfstests: re-enable xfstests 049 in nightly run
- Running test 049 repeatedly is passing for me now. I'm not sure
when or how it got fixed but I'm going to re-enable... - 01:48 PM rgw Bug #3682 (Resolved): valgrind errors seen when running rgw tests in nightlies
- Please open a new ticket for any future valgrind errors discovered in nightlies.
- 01:46 PM rgw Bug #4124: Using "response-content-type" arguments causes duplicated Content-Type in response
- Apache might be filtering the duplicate header I guess. I use lighttpd as a fastcgi front end.
- 01:39 PM rgw Bug #4124 (New): Using "response-content-type" arguments causes duplicated Content-Type in response
- Not seen on Apache.
- 01:40 PM rbd Bug #2572 (Resolved): krbd: writeback errors?
- I've run xfstests 49 a bunch of times consecutively
and I am no longer seeing this issue.
I'm about to run it 100... - 01:37 PM rgw Bug #2650 (In Progress): rgw: swift key creation overrides subuser access mask
- 01:36 PM rgw Bug #2366: rgw: bucket index update rely on pg state
- Will be worked in coordination with DR/Georeplication work.
- 01:34 PM rgw Bug #4048 (Resolved): API mismatch between RGW and Swift
- 01:23 PM rbd Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- Just checked, problem with blkdeviotune still exists in the 1.0.2.
- 11:53 AM rbd Bug #2700: blkdeviotune method at libvirt doesn`t work on RBD volumes
- This is something that we should fix. Is it still an issue in current libvirt?
- 01:20 PM rbd Bug #2654 (Resolved): Stale rbd volume cannot be unmaped
- Somewhere along the way, this got fixed....
- 01:15 PM rbd Bug #4243 (Resolved): rbd cli: usage confusing for snapshot operations
- The correct usage for creating a snapshot seems to be:...
- 01:14 PM CephFS Bug #4035 (Rejected): Ceph doesn't recover from fault on Opensuse (cfuse tests & rbd-cli tests)
- 01:11 PM CephFS Bug #3818 (Duplicate): kclient: fsx fails in mapread
- 01:09 PM CephFS Bug #3681: kclient fsx fails nightly
- Should review entire kernel locking around truncate.
- 01:08 PM CephFS Bug #3681: kclient fsx fails nightly
- 12:45 PM CephFS Bug #2277: qa: flock test broken
- It's not an issue because these tests aren't being run any more. They should be run, though. ;)
That said, this wa... - 12:30 PM CephFS Bug #2277 (Closed): qa: flock test broken
- No longer an issue.
- 12:35 PM CephFS Bug #4241 (Duplicate): SELinux fails because it can't set xattrs
- ...
- 12:31 PM Bug #2329 (Resolved): fix detection of C++11 atomic header
- 12:28 PM Bug #2207: osd: crash when op length is greater than op input data
- Still exists in current code.
- 12:27 PM Bug #2186 (Can't reproduce): osd: shutdown race
- Not seen in current code.
- 12:26 PM Bug #2184 (Resolved): audit calls to populate_obc_watchers and add watch/notify to RadosModel
- Done - this code has been replaced.
- 12:25 PM Bug #2182 (Resolved): audit osd reads for reads from potentially unstable objects
- Resolved by various commits that rewrote this area of code.
- 12:23 PM CephFS Bug #1874 (New): Running `git gc` on a bare git repository hosted by ceph results in a bus error.
- 12:21 PM Bug #1691 (Can't reproduce): rados export failures
- Not seen in current code.
- 12:19 PM Messengers Bug #1674: daemons crash when sent random data
- 12:12 PM Bug #3801 (Won't Fix): Cascading OSD failures beginning with common/HeartbeatMap.cc: 78: FAILED a...
- Fixed in Bobtail, won't backport to Argonaut.
- 12:11 PM Bug #3595 (Won't Fix): ceph-osd and ceph-mds crash on Debian Squeeze
- Won't fix, as other squeeze users are having success.
- 12:07 PM Bug #4065 (Can't reproduce): Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- Appears to be disk issue.
- 12:05 PM rbd Bug #3939 (Duplicate): krbd: circular locking report in sysfs code
- Duplicate of 3925. I *did* write it up before.
- 12:02 PM rbd Bug #3950 (Can't reproduce): krbd: new assertion failure running concurrent rbd test
- Not seeing this in current code.
- 11:59 AM rbd Bug #3871 (In Progress): krbd: initial header read may be out of date
- 11:58 AM rbd Bug #3743 (Won't Fix): krbd: errors on submitted requests are ignored
- This was found in old request code and therefore will not be fixed.
- 11:38 AM rbd Bug #3936 (Rejected): rbd: Strange dd speed behaviour (server side issue?)
- Network issue.
- 11:37 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- Need to reproduce with:...
- 11:35 AM rbd Bug #3697 (Duplicate): rbd copy.sh test failing in nightly
- #3958
- 11:34 AM rbd Bug #3980 (Won't Fix): rbd image created with size zero on a mixed cluster crashes rbd
- Problem not in Bobtail and future releases. Won't fix.
- 11:32 AM rbd Bug #3524 (Duplicate): test_librbd_fsx: crash after flatten
- Same as #3665
- 11:26 AM rbd Bug #3703 (Can't reproduce): osd: crash while encrypting
- 11:12 AM rbd Bug #4240 (Resolved): libceph: fix a osd request memory leak
- If an invalid layout is provided to ceph_osdc_new_request(), its
call to calc_layout() might return an error. At th... - 11:02 AM Feature #4239 (New): Automatically determine routing data based on host routing data (entirely de...
- IPv6 has interesting features, such as the expectation that hosts have multiple addresses per interface (local link, ...
- 10:51 AM Bug #4228: mon uses pick_addresses if invoked with mkfs or without mon addr; fails if no cluster ...
- Here is an example ceph.conf file both for this test case and for possible inclusion in to the documentation site.
- 09:39 AM rbd Bug #4184: krbd: fix some sparse problems
- Forgot to set target version.
- 09:38 AM rbd Bug #4184 (Fix Under Review): krbd: fix some sparse problems
- Re-posted for review. The patches have been re-based on
top of fixes for 4234, 4235, 4237, and 4238. - 09:37 AM rbd Cleanup #4234: libceph: encapsulate flag setting
- Posted for review. (Marked this as "Feedback" because
I can't mark a cleanup issue "need review")... - 06:22 AM rbd Cleanup #4234 (In Progress): libceph: encapsulate flag setting
- Forgot to indicate this was underway.
- 06:02 AM rbd Cleanup #4234 (Resolved): libceph: encapsulate flag setting
- While working on http://tracker.ceph.com/issues/4079 I created
some helper routines to wrap around the code that tes... - 09:36 AM rbd Bug #4235 (Fix Under Review): krbd: add some dout() trace calls
- Posted for review....
- 06:23 AM rbd Bug #4235 (Resolved): krbd: add some dout() trace calls
- While working on http://tracker.ceph.com/issues/4079 I added
some calls to dout() to some of the new request code. ... - 09:36 AM rbd Bug #4238 (Fix Under Review): krbd: still more barrier fixes
- Posted for review....
- 07:21 AM rbd Bug #4238 (Resolved): krbd: still more barrier fixes
- While looking at http://tracker.ceph.com/issues/4079 I
concluded that the fix I put in for this might still
not be ... - 09:35 AM rbd Bug #4237 (Fix Under Review): krbd: ignore zero-length requests
- Posted for review....
- 06:40 AM rbd Bug #4237 (Resolved): krbd: ignore zero-length requests
- The old request code simply ignored zero-length requests
as soon as they were seen. The new request code currently
... - 09:00 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Yes the cluster has returned to a working state and osd's are staying up with the new code.
- 07:33 AM Revision 31050340 (ceph): objecter: don't resend linger ops unnecessarily
- recalc_linger_op_target() was checking and then setting
linger_op->pgid and linger_op->active, but these were only se... - 07:23 AM Revision 15bb9ba9 (ceph): objecter: initialize linger op snapid
- Since they are write ops now, it must be CEPH_NOSNAP or the OSD
returns EINVAL.
Signed-off-by: Josh Durgin <josh.dur... - 06:41 AM rbd Feature #4236: krbd: properly handle flush commands
- Note that http://tracker.ceph.com/issues/4237 describes
making the new request code ignore all zero-length commands.... - 06:38 AM rbd Feature #4236 (Duplicate): krbd: properly handle flush commands
- REQ_FLUSH and REQ_FUA are intended to implement drive
cache flushes and barrier semantics. I don't know
precisely ... - 05:55 AM Linux kernel client Bug #4233 (Resolved): krbd: verify use of all GFP_* flags
- The memory allocations done in the kernel rbd client
use variously GFP_KERNEL, GFP_IO, and GFP_ATOMIC.
I'm not en... - 05:50 AM Revision cfe92392 (ceph): librados: expose a list of watchers on an object
- Add new op CEPH_OSD_OP_LIST_WATCHERS
Add Objecter handling
Signed-off-by: David Zafman <david.zafman@inktank.com> - 05:50 AM Revision af339aee (ceph): Add ObjectReadOperation and IoCtx functions
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:50 AM Revision 1c3241e3 (ceph): Add listwatchers command to rados
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:50 AM Revision 56481176 (ceph): Add test for list_watchers() C++ interface
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:50 AM Revision bf5cf331 (ceph): Add rados_types.h header file
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:45 AM Revision 8c05af5d (ceph): configuration parsing: give better error for missing =
- A ceph.conf line with "key" and no "= value" currently shows
"unexpected character while parsing putative key value,
... - 03:04 AM Bug #4218: mon: segfault on 'ceph quorum'
- Patch on wip-4218 commit:2d615aca6c14808813e54efd31f73f271b7c69a4
- 02:49 AM Feature #4232 (Resolved): librados: Improve Java bindings
- This is related to: #4231
The current state of the Java bindings is uncertain.
Two projects exist:
* Java RADO... - 02:45 AM rbd Feature #4231 (Closed): librbd: Java bindings
- As it seems right now the new CloudStack code will require more complex RBD operations which can not be accomplished ...
- 02:42 AM Feature #4230 (Resolved): librados: node.js bindings
- Although I don't have a use-case at this specific point it would be very cool to have node.js bindings.
From the d... - 01:55 AM Revision dc181224 (ceph): osd/PG: fix typo, missing -> omissing
- From ce7ffc34408bf32c66dc07e6f42d54b7ec489d41.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:39 AM Revision 94ae7254 (ceph): test_librbd_fsx: fix image closing
- Always close the image we opened in check_clone(), and check the
return code of the rbd_close() called before cloning... - 01:31 AM Revision de4fa95f (ceph): osd: make watch OSDOp print sanely
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:31 AM Revision 6c08c7c1 (ceph): objecter: separate out linger_read() and linger_mutate()
- A watch is a mutation, while a notify is a read. The mutations need to
pass in a proper snap context to be fully cor... - 01:30 AM Revision 60ebf02a (ceph): Merge branch 'next'
- 01:30 AM Revision dd007db3 (ceph): ceph_common.sh: fix iteration of items in ceph.conf
- This broke in c8f528a4070dd3aa0b25c435c6234032aee39b21.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:04 AM Revision 045a8668 (ceph): task: ceph: create monitor data directories prior to --mkfs
- The new monitor store does not create the data directory on --mkfs. We
must create it instead, much like what happens... - 01:02 AM Revision 6cb53740 (ceph): ceph-conf.rst: missing '=' in example network settings
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:44 AM Revision c1b75c6b (ceph): task: mon_thrash: Thrash multiple monitors and 'maintain-quorum' option
- We now add a new option 'thrash-many' that by being set to true will break
the default behaviour of killing only one ... - 12:44 AM Revision d28bb05a (ceph): task: mon_thrash: Add 'seed' and 'store-thrash' options
- This patch introduces an option to thrash a monitor store when we thrash
the monitors, as well as a 'store-thrash-pro... - 12:21 AM Revision 278be217 (ceph): ceph.conf: log file, not log dir
- Signed-off-by: Sage Weil <sage@inktank.com>
02/21/2013
- 11:45 PM Revision 9af94eea (ceph): Merge remote-tracking branch 'gh/wsp.bobtail.2merge'
- 11:37 PM Revision ce7ffc34 (ceph): PG::proc_replica_log: adjust oinfo.last_complete based on omissing
- Otherwise, search_for_missing may neglect to check the missing
set for some objects assuming that if the need version... - 11:08 PM Revision c85ba563 (ceph): install: ignore apt-get update failures on package removal
- At that point we don't really care.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:08 PM Revision 17be13b2 (ceph): ceph: fix log, /var/run/ceph stupid
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:47 PM Revision a862d8bf (ceph): Fix unused vars, unused imports, and aliasing
- Found by pyflakes
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 10:42 PM Revision 8086d1d8 (ceph): Merge remote-tracking branch 'upstream/wip_clone_attrs'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 10:37 PM Revision 23669be9 (ceph): radosgw-admin: fix errors found by pyflakes
- Using the wrong variable, and true/false are capitalized in python.
Signed-off-by: Josh Durgin <josh.durgin@inktank.... - 10:30 PM Revision 79f09bf3 (ceph): MDS: remove a few other unnecessary is_base() checks
- We should let users remove xattrs as well as set them. ;) And
the check in handle_client_setlayout was totally useles... - 10:21 PM Revision 9f82ae60 (ceph): mds: allow xattrs on the root inode
- This was previously disallowed because Once Upon a Time, the root
inode wasn't persisted to disk and was an entirely ... - 09:46 PM Bug #4229 (Resolved): conf parsing gives very confusing message if no '=' present on setting line
- commit:8c05af5dc3c398dda4c196a64f344db7ea69d209 pushed to next
- 09:32 PM Bug #4229: conf parsing gives very confusing message if no '=' present on setting line
- looks good to me!
- 07:11 PM Bug #4229: conf parsing gives very confusing message if no '=' present on setting line
- Something like this:...
- 06:50 PM Bug #4229 (Resolved): conf parsing gives very confusing message if no '=' present on setting line
- A doc bug caused a user to attempt to include settings of the form
public network <addr>
i.e. missing the equal... - 09:44 PM Revision 84ef1649 (ceph): mds: parse ceph.*.layout vxattr key/value content
- Use qi to parse a strictly formatted set of key/value pairs. Be picky
about whitespace. Any subset of recognized ke... - 09:44 PM Revision 6bd8781d (ceph): mds: use inode_t::layout for dir layout policy
- This cherry-pick is going in the reverse direction of normal. That's
because this direction makes for the minimal cha... - 09:28 PM Revision fea77682 (ceph): osdc/Objecter: unwatch is a mutation, not a read
- This was causing librados to unblock after the ACK on unwatch, which meant
that librbd users raced and tried to delet... - 09:28 PM Revision 81bd9964 (ceph): FileStore::_clone: use _fsetattrs rather than _setattrs
- The omap portion of the clone happened above in DBObjectMap::clone.
Only the fs stored attrs need to be explicitely c... - 09:26 PM Revision 5b48e63c (ceph): FileStore::_setattrs: use _fsetattrs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:26 PM Revision c33c51f0 (ceph): FileStore: add _fsetattrs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:25 PM Revision 2ec04f96 (ceph): FileStore::_setattrs: only do omap operations if necessary
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:24 PM Revision 83fad1c7 (ceph): FileStore::_setattrs no need to grab an Index lock for the omap operations
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:59 PM Revision 08efb158 (ceph): Merge pull request #67 from jaharkes/content_length
- Handle empty CONTENT_LENGTH environment variable.
- 08:52 PM Revision 8b0eef29 (ceph): ceph_manager: fix asok string formatting
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:51 PM Revision ad00fc72 (ceph): Fix failing > 4MB range requests through radosgw S3 API.
- When a range request is made for more than rgw_get_obj_max_req_size
bytes the first returned chunk sets 'ret' to STAT... - 08:45 PM Revision 5c0a2f40 (ceph): ceph: make /var/run/ceph writeable by non-root too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:42 PM Revision e5a01317 (ceph): Merge pull request #66 from jaharkes/range_requests
- Fix failing > 4MB range requests through radosgw S3 API.
- 08:36 PM Revision 96896eb0 (ceph): Handle empty CONTENT_LENGTH environment variable.
- nginx seems to be providing a CONTENT_LENGTH environment variable with no data
when the request body is empty.
Signe... - 08:35 PM Revision 1d62baf1 (ceph): ceph: fix /var/log/ceph chown/cmod typo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:29 PM Revision c83a01d4 (ceph): Fix failing > 4MB range requests through radosgw S3 API.
- When a range request is made for more than rgw_get_obj_max_req_size
bytes the first returned chunk sets 'ret' to STAT... - 07:37 PM Bug #4079: osd: journal aio deadlock
- Here is the yaml file I used for reproducing this....
- 03:40 PM Bug #4079: osd: journal aio deadlock
- The process:
20767 ? D 0:00 /sbin/mkfs.xfs -f -l su=32k /dev/rbd3
Its "before" kernel stack trace:
[... - 02:40 PM Bug #4079: osd: journal aio deadlock
- After lots of failed attempts to fix this I have what
I hope to be something helpful.
I've added dout() calls to ... - 05:43 AM Bug #4079: osd: journal aio deadlock
- I don't think the barrier improved anything.
All of those state changes should be happening
under protection of a m... - 07:35 PM Revision e1573ea1 (ceph): ceph.conf: use default locations for admin socket; fix client log file
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:32 PM Revision 4277265d (ceph): osd: an interval can't go readwrite if its acting is empty
- Let's not forget that min_size can be zero.
Fixes: #4159
Signed-off-by: Sage Weil <sage@inktank.com> - 07:26 PM Revision a1ae8562 (ceph): librbd: make sure racing flattens don't crash
- The only way for a parent to disappear is a racing flatten completing,
or possibly in the future the image being forc... - 07:19 PM Revision 995ff0e3 (ceph): librbd: use rwlocks instead of mutexes for several fields
- Image metadata like snapshots, size, and parent is frequently read,
but rarely updated. During flatten, we were depen... - 07:15 PM Revision e0f8e5a8 (ceph): common: add lockers for RWLocks
- This makes them easier to use, especially instead of existing mutexes.
Signed-off-by: Josh Durgin <josh.durgin@inkta... - 07:05 PM Revision 2574d875 (ceph): make /var/log/ceph writeable by non-root; make clients log to it
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:46 PM Bug #4228 (Resolved): mon uses pick_addresses if invoked with mkfs or without mon addr; fails if ...
- The monitor uses pick_addresses(), which tries to find interfaces with addresses on both
cluster and public nets if... - 06:44 PM Revision c8d0889d (ceph): Merge branch 'next'
- Conflicts:
src/osd/ReplicatedPG.cc - 06:43 PM Revision 6d8dfb18 (ceph): osd: clear recovery state on pg removal
- This ensures we release our in-progress recovery counters, which prevents
recovery from getting blocked indefinitely ... - 06:38 PM Revision 94e5deeb (ceph): test: fix run-rbd-tests pool deletion
- Use the new safety check
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 06:29 PM Revision 6612b040 (ceph): ceph-object-corpus: use temporary 'wsp.master.new' corpus until we get ...
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:16 PM rbd Fix #3665 (Fix Under Review): librbd: deadlock during flatten
- wip-rbd-flatten-deadlock
- 06:04 PM Revision beafca57 (ceph): Merge branch 'wsp.bobtail.2merge' into wsp.bobtail.master
- Conflicts:
src/.gitignore
src/Makefile.am
src/include/ceph_features.h
src/mon/MDSMonitor.cc
src/mon/PGMonitor.cc - 06:02 PM Revision cb85fb7d (ceph): mon: ceph-mon: convert an old monitor store to the new format
- With the single-paxos patches we shifted from an approach with multiple
paxos instances (one for each paxos service) ... - 06:02 PM Revision 89f92049 (ceph): test: ObjectMap: add a generic leveldb store tool
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 04dac7ee (ceph): vstart.sh: Create mon data directory before --mkfs
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision 86f6a342 (ceph): mon: Paxos: trim through Paxos
- Instead of directly modifying the store whenever we want to trim our Paxos
state, we should do it through Paxos, prop... - 06:02 PM Revision cd4de773 (ceph): mon: PaxosService: rework full version stashing
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision b33d4eac (ceph): mon: Paxos: get rid of slurp-related code
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:02 PM Revision d8a5cf6b (ceph): mon: MonitorDBStore: add store iterators to obtain chunks for sync
- We created an interface specific to the MonitorDBStore, which can be used
to create iterators to obtain chunks for sy... - 06:02 PM Revision 6db25a38 (ceph): message: MMonSync: Monitor Synchronization message
- The monitor's synchronization process requires a specific message type
to carry the required informations. Since this... - 06:02 PM Revision cab3411b (ceph): mon: Monitor: Add monitor store synchronization support
- Synchronize two monitor stores when one of the monitors has diverged
significantly from the remaining monitor cluster... - 06:02 PM Revision 091fa826 (ceph): os: LevelDBStore: scrap init() and create open() and create_and_open()
- The init() function always implicitly created a new store if it was
missing.
This patches makes init() a private fun... - 06:02 PM Revision 19e5098a (ceph): mon: Add an offline monitor store converter
- This tool will convert an old monitor store format (bobtail) to the new
key/value store-backed, single-paxos format.
... - 06:02 PM Revision a5e2dcb3 (ceph): mon: Single-paxos and key/value store support
- We are converting the monitor subsystem to a Single-Paxos architecture,
backed by a key/value store. The previous arc... - 05:49 PM Documentation #4227 (Resolved): networks section still doesn't explain global vs specific
- The network section implies that you must set both the [global] and the [<daemon>] settings for network addresses, an...
- 05:21 PM Revision 36ed407e (ceph): mds: use inode_t::layout for dir layout policy
- Remove the default_file_layout struct, which was just a ceph_file_layout,
and store it in the inode_t. Rip out all t... - 04:54 PM Bug #4226 (Resolved): Monitor crash happens when running Teuthology
- INFO:teuthology.orchestra.run.err:ceph_mon.cc: In function 'int main(int, const char**)' thread 7f731684a780 time 201...
- 03:50 PM rbd Bug #4186: rbd: add another "udevadm settle" in the CLI
- awesome, I fixed this without even knowing it existed! :)
- 03:44 PM Bug #4189: osd/ReplicatedPG.cc: 4994: FAILED assert(log.objects.count(soid) ...
- ce7ffc34408bf32c66dc07e6f42d54b7ec489d41 should take care of this. (The Fixes: tag in the commit is wrong, should ha...
- 03:03 PM Bug #4189: osd/ReplicatedPG.cc: 4994: FAILED assert(log.objects.count(soid) ...
- ubuntu@teuthology:/a/sage-ooo7/8851/ another example
- 02:50 PM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- I've looked at the logs, and I think #4091 should fix this. The high ping times tend to occur around when the cache f...
- 02:24 PM Fix #4225 (Resolved): objecter: watch is treated as a read (linger) operation
- Fixing this for the (simpler) unwatch case. For watch, we need to refactor linger() a bit to capture both the notify...
- 02:22 PM CephFS Bug #4220 (Resolved): MDS is inconsistent about whether layouts are allowed on the root directory
- Right, this is in the generic xattr code, not the new vxattr stuff. Sage says this is because the root inode used to ...
- 02:03 PM CephFS Bug #4220: MDS is inconsistent about whether layouts are allowed on the root directory
- If you go through the "handle_client_setdirlayout" interface (ie, cephfs tool), the MDS will let you set a layout on ...
- 10:47 AM CephFS Bug #4220 (Resolved): MDS is inconsistent about whether layouts are allowed on the root directory
- I can't seem to set layouts on the root directory with ceph-fuse. Perhaps I'm doing something else wrong, but check o...
- 02:00 PM rgw Feature #4224 (New): rgw: unitest to check get object with range > 4MB
- 01:59 PM rgw Bug #4223 (Resolved): rgw: failing > 4MB range requests through radosgw S3 API
- 01:39 PM rgw Bug #4223: rgw: failing > 4MB range requests through radosgw S3 API
- Does not happen in bobtail, related to recent changes in streaming read object
- 12:49 PM rgw Bug #4223 (Resolved): rgw: failing > 4MB range requests through radosgw S3 API
- Fixed with commit:c83a01d4e8dcd26eec24c020c5b79fcfa4ae44a3
- 01:50 PM CephFS Bug #1435 (Resolved): mds: loss of layout policies upon mds restart
- Change pushed to bobtail (commit:36ed407e0f939a9bca57c3ffc0ee5608d50ab7ed) and next (commit:6bd8781dda524f04bb56bcdac...
- 01:49 PM CephFS Cleanup #1499 (Resolved): mds: clean up directory layouts
- Okay, I tested this according to the procedure described below (I wanted to write some scripts, but the non-manual po...
- 11:59 AM Bug #4216: osd: dbojectmap incorrectly skipping ops
- A bit below continuing on the same thread (7f6a9d4e1700):
2013-02-20 21:43:56.597514 7f6a9d4e1700 20 filestore dbo... - 08:37 AM Bug #4216: osd: dbojectmap incorrectly skipping ops
- root@plana46:~# gdb /usr/bin/ceph-osd /tmp/1361425499.5801.core
if you want to look at hte core - 08:36 AM Bug #4216: osd: dbojectmap incorrectly skipping ops
- from gdb:...
- 08:33 AM Bug #4216 (Resolved): osd: dbojectmap incorrectly skipping ops
- ubuntu@teuthology:/a/sage-ooo6/8248 crashed with a bad array index in remove_object_with_snap_hardlinks because a sna...
- 11:38 AM Bug #4116 (Resolved): common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Evan, going to assume this is resolved.. let me know if not! #4192 will track the long-term fix.
- 11:36 AM Bug #4159 (Resolved): after setting pool size to zero, osd's segv and apparently can't recover
- commit:4277265d99647c9fe950ba627e5d86234cfd70a9
- 11:29 AM devops Feature #4119 (In Progress): rpm: create /var/lib/ceph/* directories
- 11:28 AM CephFS Tasks #4222 (In Progress): Add libcephfs-test.jar to ceph-test deb package
- 11:26 AM CephFS Tasks #4222 (Resolved): Add libcephfs-test.jar to ceph-test deb package
- The file libcephfs-test.jar is not present in any of the deb packages.
The file ceph.spec was changed to include thi... - 10:48 AM CephFS Bug #4221 (Resolved): MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events for DECO...
- By far the most common form of corrupt event is one that's somehow the wrong size — and that hits an assert in LogEve...
- 10:44 AM Bug #4217 (Resolved): osd: recovery hangs indefinitely
- commit:6d8dfb18feb4ce263453039fc0afdb1462279e9a
- 10:11 AM Bug #4217 (Fix Under Review): osd: recovery hangs indefinitely
- wip-4217 now passes the test
- 08:57 AM Bug #4217 (Resolved): osd: recovery hangs indefinitely
- this has been popping up in qa and mistakenly interpreted as just slow, but recovery is in fact blocking indefinitely...
- 10:29 AM devops Feature #4219 (Rejected): gitbuilder: make it skip nobuild-* branches
- 09:44 AM Bug #4218 (Resolved): mon: segfault on 'ceph quorum'
- As reported by Travis Rhoden on ceph-users:...
- 05:49 AM Revision 4431e1ef (ceph): install: be slightly more efficient
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:46 AM Revision 00986ce0 (ceph): install: be more careful about package removal
- - call apt separately for each package; it will error out annoyingly if
there is one in the list not in the APT sourc... - 05:36 AM Revision 7d8a72a3 (ceph): ceph-fuse: install -dbg package, too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:23 AM Revision 425f5dd8 (ceph): clusters: add mds to fixed-1.yaml
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:17 AM Revision e747abef (ceph): rbd/librbd: fix the cache mode facet
- This appears to have been broken, which means we weren't actually testing
any of the non-default cache modes (writeth... - 05:02 AM Revision c64cd201 (ceph): radosgw-admin: fix sleep syntax error
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:21 AM Revision b4fd196c (ceph): mds: parse ceph.*.layout vxattr key/value content
- Use qi to parse a strictly formatted set of key/value pairs. Be picky
about whitespace. Any subset of recognized ke... - 01:09 AM Revision 5551aa5b (ceph): mds: parse ceph.*.layout vxattr key/value content
- Use qi to parse a strictly formatted set of key/value pairs. Be picky
about whitespace. Any subset of recognized ke... - 12:27 AM Revision ecb563b2 (ceph): install: install libcephfs1[-dbg]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:21 AM Revision 28f11d03 (ceph): ceph_manager: drop extra line
- Ooops, from 0c990f3add7fe2a08d13511f3c7bf814eb6558f1.
Signed-off-by: Sage Weil <sage@inktank.com>
02/20/2013
- 11:27 PM Revision 9996bdbe (ceph): run: print pass/FAIL as final line
- Makes it easy to tell at a glance if your last test passed or not.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:20 PM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Sigh. The attachment might help...
- 11:18 PM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Confirmed here, with ceph-0.56.3 and qemu-1.3.1.
See attached test output.
A summary is, the average ping time,... - 10:10 PM Revision 6c2f4a2b (ceph): Merge remote-tracking branch 'origin/wip-3634'
- 10:10 PM Revision 2a51e328 (ceph): Merge remote-tracking branch 'origin/wip-3634'
- 09:29 PM Revision b531aa36 (ceph): Merge branch 'wip_watch_cleanup'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 09:29 PM Revision 7af32997 (ceph): osd/: move ObjectContext over to osd_types.h
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision ebdf66df (ceph): Watch/Notify: rework watch/notify
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 8ece91ff (ceph): ReplicatedPG: accept watch cookie value with notify ack
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 661a2832 (ceph): librados/: include watch cookie in notify_ack
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 9a399afd (ceph): doc: add some internal docs for watch/notify
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 0202bf29 (ceph): ReplicatedPG: allow multiple watches in one transaction
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 7fe7eff9 (ceph): Timer.cc: use complete() rather than finish()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 359c0dfd (ceph): ReplicatedPG: add intrusive_ptr hooks
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:29 PM Revision 22ec5bc3 (ceph): PG: check object_contexts on flushed
- At FlushedEvt, all outstanding io should be complete and
the object_contexts map should be empty.
Signed-off-by: Sam... - 09:25 PM Revision 8713f18d (ceph): osd: remove force hack for testing the HASHPSPOOL code
- Also from 8cc2b0f1243b2717af1de329a7fa6a8b5350db68.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:15 PM rbd Bug #3958 (In Progress): rbd fsx fails with EBUSY
- reproducing with logs, vapre f.yaml.out, to confirm this is just the osd's EBUSY. which we should fix.
- 08:52 PM Revision ceb390f6 (ceph): mon: allow syslog level and facility for cluster log to be controlled
- Allow user to control the minimum level to go to syslog for the client-
and server-side submission paths for the clus... - 08:51 PM Bug #4182 (Can't reproduce): FileStore::_do_copy_range got short read result
- i am hopeful that this is a result of the collection repaly bugs, fixes cultimating commit:5fc83c8d9887d2a916af11436c...
- 08:50 PM Bug #4148 (Resolved): osd: snap collections mismatch from thrashing
- this appears to be resolved after commit:5fc83c8d9887d2a916af11436ccc94fcbfe59b7a
- 08:49 PM Bug #4204 (Resolved): kclient: regression triggered by direct io path
- this is working now that alex yanked that commit.
- 08:49 PM Bug #4110 (Resolved): assertion in DeleteOp::_begin
- this appears to be resolved after commit:5fc83c8d9887d2a916af11436ccc94fcbfe59b7a
- 08:47 PM Revision c3d130cd (ceph): mon: Monitor: keyring always on mon_data/keyring by default
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:47 PM Revision 14619675 (ceph): mon: MonitorDBStore: Add a key/value store to be used in the monitor
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:39 PM Revision 0201cc80 (ceph): rgw: refactor header grants
- Move definition to a static array.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:32 PM Revision eb0f49d4 (ceph): rgw_acl: Support ACL grants in headers.
- Issue 3669: Support S3 ACL grants specified in request headers. Allow
requests, excluding POST object, to specify ACL... - 06:37 PM Revision 04f3fe4e (ceph): mon: fix new pool type
- I broke this in 8cc2b0f1243b2717af1de329a7fa6a8b5350db68.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:22 PM Revision 2e1b02bf (ceph): osd: lock pg in build_past_intervals_parallel()
- Methods called by write_if_dirty() (get_osdmap()) assert that the pg
is locked.
Backport: bobtail
Signed-off-by: Sag... - 05:40 PM devops Feature #2699 (New): crowbar: change barclamp-glance to use rbd
- There are a minimal number of changes available in git@github.com:gregsfortytwo/barclamp-glance.git; I thought a bit ...
- 05:35 PM CephFS Bug #1435 (Fix Under Review): mds: loss of layout policies upon mds restart
- Okay, after discussing with Sage we've decided that placing the directory layouts into the inode_t::layout field is t...
- 11:36 AM CephFS Bug #1435 (Won't Fix): mds: loss of layout policies upon mds restart
- This patch to use the inode layout instead of default_layout shouldn't be helping — directory layouts aren't written ...
- 05:33 PM CephFS Feature #4215 (Resolved): mds: support setfattr on ceph.dir.layout
- Ah, it was just a lost commit! Resolved by commit:5551aa5b3b5c2e9e7006476b9cd8cc181d2c9a04, among others.
(It will p... - 02:43 PM CephFS Feature #4215: mds: support setfattr on ceph.dir.layout
- Oh, as a feature this isn't any particular priority. Just an optimization, really.
- 02:40 PM CephFS Feature #4215: mds: support setfattr on ceph.dir.layout
- Oh, and indeed, looking at the source code:...
- 02:37 PM CephFS Feature #4215 (Resolved): mds: support setfattr on ceph.dir.layout
- ...
- 05:24 PM Feature #3757 (Resolved): osd: Watch/Notify cleanup
- b531aa3688d9e8831837c23abac0bdaba04ec793
- 05:00 PM rgw Feature #4098: rgw: multi-site: Global Bucket Namespace
- This request should be covered by the spec Yehuda sent to the ML:
http://article.gmane.org/gmane.comp.file-systems... - 04:52 PM CephFS Cleanup #1499 (Fix Under Review): mds: clean up directory layouts
- Okay, this patch is required to fix the loss of directory layouts issue (#1435) in Bobtail, so I rebased it on that b...
- 04:44 PM Revision 473beb53 (ceph): qa: mon/pool_ops.sh: fix last test
- Got this one backwards, bah!
Signed-off-by: Sage Weil <sage@inktank.com> - 04:11 PM Messengers Feature #2100: msgr: Prevent throttled clients from slowing down non-throttled connections (TCP b...
- see wip-tcp to tune this via ceph.conf. please test!
- 03:40 PM Bug #4162 (Resolved): mon: Single-Paxos: on sync, corrupted paxos store
- Forgot to kill teuthology, and the same job has been hammering the branch for two days now, and everything is still g...
- 02:31 PM Feature #4214 (Duplicate): osd: optionally tolerate and repair EIO on deep scrub reads
- 02:13 PM rgw Feature #3634 (Resolved): rgw: improve teuthology radosgw-admin test
- Merged, commit:6c2f4a2bbef63ef91344887bf8f001a2574503c5
- 01:58 PM rgw Feature #3402 (Resolved): rgw: improve tests for multipart upload
- Done, commit:409567582772efd5f98bc40bb48cb07e3b034f14
- 12:58 PM rgw Feature #3669 (Resolved): rgw: support acl grants through http headers
- Merged into next, commit:eb0f49d4b68062701b842b9cfdde708868769bef
- 12:53 PM Feature #3704 (Resolved): mon: add min log level to send cluster msgs to syslog
- commit:ceb390f672fa8cc3823fac588ac19cb18b2a7777
- 12:50 PM rbd Cleanup #4053 (Resolved): ceph: cleanup ceph page vector functions
- Committed to the testing branch.
9e0eb85 ceph: remove a few bogus declarations
b324814 libceph: use void pointers... - 12:49 PM rbd Subtask #4007 (Resolved): libceph: support STAT osd operation
commit fbfab53966b279f9cdb36b96ffa1e22f042c96ff
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 8 09:55:48...- 12:42 PM Bug #4079: osd: journal aio deadlock
- For a while I was pretty hopeful, because it appeared that
with these barriers in place I was getting slowness less
... - 09:06 AM Bug #4079: osd: journal aio deadlock
- Well, it absolutely looks like it *can* happen.
I found cases where different CPUs set and cleared
the WRITE_PENDIN... - 06:45 AM Bug #4079: osd: journal aio deadlock
- I am running xfstests 258 and 259 over rbd, repeating
10 times. The first three iterations took about 1 second
and... - 12:42 PM rbd Fix #3665 (In Progress): librbd: deadlock during flatten
- 12:04 PM CephFS Bug #4213 (Resolved): mds: old_parents is never cleaned up
- The CInode::old_parents map is never cleaned up, even if all the snapshots for which a parent is valid have all been ...
- 12:01 PM CephFS Bug #4212 (Closed): mds: open_snap_parents isn't called all the times it needs to be
- Prompted by a bug report/paper-over patch from Alexandre, I had a talk with Sage about snapshots. It came out that we...
- 11:55 AM Bug #4159: after setting pool size to zero, osd's segv and apparently can't recover
- reproduction: ceph osd set pool rbd size zero actually didn't kill the OSDs; ./rados -p rbd ls hung, unsurprisingly, ...
- 11:26 AM rbd Feature #4211 (Rejected): get good qemu, libvirt versions+patches in CentOS+
- 11:26 AM rbd Tasks #4210 (Resolved): get ceph and all libraries versions+patches in EPEL
- 11:16 AM rgw Bug #4178: s3-tests: fix list_multipart_uploads
- Done, commit:fd33286494a221030eb9128f446337e7f3cfdef9
- 11:13 AM rgw Bug #4178 (Resolved): s3-tests: fix list_multipart_uploads
- 11:15 AM rgw Bug #4150: rgw: copy object into itself leaks tail references
- Done, commit:34f885be536d0ac89c10fd29b1518751d2ffc547
- 11:12 AM rgw Bug #4150 (Resolved): rgw: copy object into itself leaks tail references
- 11:15 AM rgw Bug #4177: rgw: list multipart uploads not listing objects
- Done, commit:db99fb4417b87301a69cb37b00c35c838b77197e
- 11:12 AM rgw Bug #4177 (Resolved): rgw: list multipart uploads not listing objects
- 11:08 AM rgw Feature #4072 (Resolved): Allow binding on a tcp port
- commit:ac59ebd
- 10:59 AM devops Feature #4118 (Rejected): rpm: include upstart stuff in (some) rpms
- 10:01 AM CephFS Feature #3730 (Closed): Support replication factor in Hadoop
- Woot.
- 09:53 AM Bug #4206: concurrent rados bench processes don't work well for seq reads
- I don't think the prefix is used when doing reads though — just the last benchmark run which finished is picked. We s...
- 09:36 AM Bug #4206: concurrent rados bench processes don't work well for seq reads
- There is a distinct prefix.. can you include teh exact commands that (sometimes) reproduce this?
- 08:24 AM Bug #4206 (Resolved): concurrent rados bench processes don't work well for seq reads
- Running concurrent rados bench processes results in various different problems when performing reads from the same po...
- 09:44 AM Feature #3336 (Closed): java: create teuthology task for running unit test suite
- Commit 791a8224f0c3e00cb509188f7712b2e69b499876 added the qa test and commit bb2924d431d3825e2e0c5a1b3260b3334a016f54...
- 09:43 AM CephFS Feature #4208: Add more replication pool tests for Hadoop / Ceph bindings
- Something like this added to the current custom test should do the trick?...
- 09:32 AM CephFS Feature #4208 (Rejected): Add more replication pool tests for Hadoop / Ceph bindings
- We should add a test (or several) for the scenario where the user specifies a level of replication that does not exac...
- 09:42 AM devops Feature #4209 (Resolved): make ceph-create-keys work on non-upstart systems
- 09:40 AM devops Feature #3916 (Resolved): ceph-disk-activate: non-upstart trigger (udev?)
- 09:40 AM devops Feature #3993 (Resolved): upstart/sysvinit: control whether crush position is readjusted on start
- 09:40 AM devops Feature #4112 (Resolved): ceph-deploy: support mds
- 09:16 AM Feature #4207 (Resolved): osd/librados: add ops to list snaps for an object
- Add an op to list snapshot metadata for an object. Similar to the list watchers change in #3403, need to define a ty...
- 06:24 AM Revision 0c990f3a (ceph): ceph_manager: eventually time out while waiting for admin socket
- Otherwise we get stuck in a loop if an osd crashes unexpectedly, the
task never fails, and we don't collect all the e... - 06:15 AM Revision 3de89969 (ceph): schedule_suite.sh: drop obligatory install task
- Added these to ceph-qa-suite.git instead.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:04 AM Revision 9617dcc6 (ceph): Merge branch 'unstable'
- Conflicts:
teuthology/task/workunit.py - 05:04 AM Revision cccadb9b (ceph): Merge branch 'unstable'
- Conflicts:
teuthology/task/workunit.py - 05:02 AM Revision acab0682 (ceph): add explicit install task before ceph task
- 02:00 AM Revision 3692ccd6 (ceph): doc: make the cephfs man page marginally more truthful
- Put it in the right place this time.
Signed-off-by: Greg Farnum <greg@inktank.com> - 02:00 AM Revision 5f92adca (ceph): rgw: fix multipart uploads listing
- Fixes: #4177
Backport: bobtail
Listing multipart uploads had a typo, and was requiring the
wrong resource (uploadId i... - 02:00 AM Revision a44df934 (ceph): rgw: don't copy object when it's copied into itself
- Fixes: #4150
Backport: bobtail
When object copied into itself, object will not be fully copied: tail
reference count... - 01:59 AM Revision db99fb44 (ceph): rgw: fix multipart uploads listing
- Fixes: #4177
Backport: bobtail
Listing multipart uploads had a typo, and was requiring the
wrong resource (uploadId i... - 01:58 AM Revision 34f885be (ceph): rgw: don't copy object when it's copied into itself
- Fixes: #4150
Backport: bobtail
When object copied into itself, object will not be fully copied: tail
reference count... - 01:48 AM Revision efc49475 (ceph): man: make the cephfs man page marginally more truthful
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:16 AM Revision de892bba (ceph): Merge branch 'wip-pool'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 12:12 AM Revision b90167d6 (ceph): mon: move OSDMap feature bit calculation into an OSDMap method
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:12 AM Revision 128cb17d (ceph): osd/OSDMap: note OSDHASHPSPOOL feature when pool FLAG_HASHPSPOOL is set
- This allows the osd and mon to enforce feature bits on their connections.
Signed-off-by: Sage Weil <sage@inktank.com>
02/19/2013
- 11:59 PM Revision 8cc2b0f1 (ceph): osd: introduce HASHPSPOOL pool flag, feature to avoid overlapping pg pl...
- The existing code will overlay the placement of PGs from pools because
it simply adds the ps to the pool as the CRUSH... - 11:54 PM Revision 96e153ae (ceph): qa: mon/pool_ops.sh: test pool set size
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:54 PM Revision 7bd49d02 (ceph): qa: mon/pool_ops.sh: fix pool tests
- The '! command' doesn't fail properly, even with -e, in bash (wtf!).
Also, the last pool deletion command succeeds b... - 11:52 PM Revision c86f9239 (ceph): Merge remote-tracking branch 'gh/wip-4159'
- 11:33 PM Revision 4eb9bf21 (ceph): test/bufferlist: fix warning
- In file included from test/bufferlist.cc:31:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::AssertionRes... - 11:12 PM Bug #4065: Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- I am using btrfs and it seems the disk in question is failing. Sadly I didn't notice before. I suspect this is the ca...
- 10:55 PM Revision d0424ebc (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 10:53 PM Revision bcb210c6 (ceph): Merge branch 'next'
- 10:05 PM Revision 3ff0fe0f (ceph): testing: updating hadoop-internal test
- Small tweaks to the hadoop-internal test
to better use existing environment varaibles.
Signed-off-by: Joe Buck <jbbu... - 10:05 PM Revision f1bff178 (ceph): qa: sample test for new replication tests
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
- 09:50 PM Revision 60d9465b (ceph): doc/release-notes: v0.57
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:26 PM Revision 81704665 (ceph): rados: fix ceph_test_filejournal test
- Assume it is in the $PATH.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:07 PM Bug #4204: kclient: regression triggered by direct io path
- I'm having a lot of trouble testing this.
I can write to files in a ceph file system. But direct I/O
writes give... - 05:31 PM Bug #4204: kclient: regression triggered by direct io path
- I'm certain it's because of this commit: 29c3c8b721a96b4a82f4224527c7103e5e910b80
Which was done for this issue: ... - 04:56 PM Bug #4204 (Resolved): kclient: regression triggered by direct io path
- this probably related to recent changes in the testing branch (which fails); master passes....
- 06:55 PM Revision 91d6be83 (ceph): PG: remove weirdness log for last_complete < log.tail
- In the case of a divergent object prior to log.tail,
last_complete may end up before log.tail.
Backport: bobtail
Fix... - 06:52 PM Revision dbadb3e2 (ceph): PG: remove weirdness log for last_complete < log.tail
- In the case of a divergent object prior to log.tail,
last_complete may end up before log.tail.
Backport: bobtail
Fix... - 06:41 PM Revision f1841e41 (ceph): osd: pull requeued requests off one at a time
- Pull items off the finished queue on at a time. In certain cases, an
event may result in new items betting added to ... - 06:41 PM Revision 56c5a077 (ceph): osd: requeue pg waiters at the front of the finished queue
- We could have a sequence like:
- op1
- notify
- op2
in the finished queue. Op1 gets put on waiting_for_pg, the not... - 06:41 PM Revision 5fc83c8d (ceph): os/FileStore: check replay guard on src for collection rename
- This avoids a problematic sequence like:
- rename A/ -> B/
- remove B/1...100
- destroy B/
- cre... - 06:07 PM Revision 9a7a9d06 (ceph): v0.57
- 05:56 PM Bug #4006 (Resolved): osd: repeating 'wrong node' message in log
- This is believed to be fixed with the merge of wip-osd-msgr (and wip-bobtail-osd-msgr backport). If anybody sees thi...
- 05:48 PM CephFS Cleanup #4166: ceph: simplify ceph_sync_write() page_align
- This commit caused regressions. I pulled it out and
I'm not going to re-open it again.
- 05:30 PM Fix #4205: librados: Improve Watch-notify semantics
- I think this is simply a matter of making the notify fail (return an error to teh notifier) if any of the watches fai...
- 05:20 PM Fix #4205 (Resolved): librados: Improve Watch-notify semantics
- In the new implementation Sam set up, and apparently in the old code as well, a notify can succeed without getting a ...
- 05:12 PM Revision 4002d70a (ceph): osd: fix printf warning on pg_log_entry_t::get_key_name
- warning: osd/osd_types.cc:1716:76: format '%lu' expects argument of type 'long unsigned int', but argument 5 has type...
- 05:08 PM Revision f80f8493 (ceph): qa: test_mon_workloadgen: use default config file path
- I'm not sure why we wouldn't. Also, this makes this test work without
annoying plumbing to pass the explicit path th... - 05:02 PM Revision 6d338591 (ceph): qa: mon/workloadgen.sh: drop TEST_CEPH_CONF code
- The binaries already pick up on CEPH_CONF, which will be set as needed.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:44 PM Revision 8ca2274c (ceph): rbd: udevadm settle before unmap
- udev runs blkid on device close, and other such nonsense that can
make unmap fail with EBUSY. Settle before we unmap... - 04:42 PM Feature #4203 (Resolved): kernel: support for new pool hashing feature
- 04:40 PM Tasks #4198 (In Progress): osd: define data loss plan of attack for cuttlefish
- 04:39 PM Tasks #4198: osd: define data loss plan of attack for cuttlefish
- - tool to manipulate pgs (remove, export, import)
- osd should stop accepting writes when near-full
- tool/meth... - 02:46 PM Tasks #4198 (Resolved): osd: define data loss plan of attack for cuttlefish
- 04:36 PM Revision b45f67e0 (ceph): test: correcting hadoop-internal tests
- Changing the hadoop-internal tests to use the
newly added $TESTDIR environment variable.
Also, removed unneeded varia... - 04:35 PM Revision d2dbab1f (ceph): testing: adding a Hadoop wordcount test
- Signed-off-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Sam Lang <sam.lang@inktank.com> - 04:29 PM Revision 30b8d653 (ceph): mon: restrict pool size to 1..10
- See: #4159
Signed-off-by: Sage Weil <sage@inktank.com> - 04:12 PM Fix #4128 (Fix Under Review): osd: fix pgid=(pool,seed) -> crush input mapping
- 02:52 PM Fix #4128 (In Progress): osd: fix pgid=(pool,seed) -> crush input mapping
- 03:52 PM Bug #4160 (Resolved): it should be illegal to set pool size to 0
- commit:c86f9239a2fd87dc6021481227864f1316f97c29
- 09:39 AM Bug #4160 (Fix Under Review): it should be illegal to set pool size to 0
- wip-4159
- 03:11 PM Fix #4202 (Rejected): osd: pg delete
- 03:08 PM Feature #4201 (Resolved): osd: data loss: pg export/import/remove
- 03:02 PM Feature #4199: mon: data loss: low disk space handling
- Warn and shut down the monitor
- 02:47 PM Feature #4199 (Resolved): mon: data loss: low disk space handling
- 02:57 PM Feature #4200 (Resolved): mon: break pgmap into separate leveldb keys
- 02:46 PM Feature #4197 (Resolved): osd: data loss: low space handling
- 02:45 PM Feature #4196 (Resolved): osd: data loss: journal corruption
- 02:36 PM rgw Feature #4097: rgw: s3 static website
- - requires implementing xml parser for request input
- implementing default error response handlers - 02:11 PM rgw Feature #4097: rgw: s3 static website
- Root domain support == static web site hosting, e.g., when accessing a bucket it'll go directly to the index object, ...
- 02:35 PM rgw Feature #4099: rgw: Object Expiration
- - need to have some clean-up process
- should we provide a strict 'removed at' point of time, or a more relaxed 'r... - 02:34 PM rbd Feature #2770 (In Progress): krbd: define tasks to add osd_client compound class op support
- 02:23 PM rbd Feature #2770 (Resolved): krbd: define tasks to add osd_client compound class op support
- 02:22 PM rbd Feature #4021 (Resolved): rbd: openstack: add ability to copy volume to image for rbd
- 02:20 PM rbd Feature #4195 (Duplicate): rbd: migrate an active image between pools
- 02:06 PM rgw Feature #3992 (In Progress): rgw: refactor internal user API for RGW Admin
- 02:06 PM rgw Feature #3988 (In Progress): rgw: dr: region mgt changes: define/implement internal API
- 02:06 PM rgw Feature #3669 (Fix Under Review): rgw: support acl grants through http headers
- 02:04 PM Bug #4194 (Can't reproduce): osd, librados: listing objects got premature ENOENT
- ...
- 01:56 PM rgw Bug #3813 (Resolved): radosgw doesn't have a logrotate script
- Fixed, commit:c8eace6ff0bbb38bf317b9db2ffba57c3d128693
- 01:23 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I pushed a wip-4116-workaround branch with a workaround that will make it trim the log. It might be a painful restar...
- 09:50 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Okay, the problem here is that it's not trimming the log because the PG is degraded. We need to fix that ASAP. I'll...
- 09:43 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Here is the current output of 'pg 4.0 query'
- 09:40 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- excellent. can you paste the output from 'ceph pg 4.0 query' so we can verify that that ginormous log got trimmed?
... - 01:21 PM Fix #4192: osd: fix log trimming
- I thought not trimming the log was a deliberate choice for faster catchup. Sounds like we need to define a better pol...
- 01:17 PM Fix #4192 (Resolved): osd: fix log trimming
- We should trim the log even when we're degraded.
Define 'osd pg max log' or similar to control how big we let it g... - 01:01 PM Feature #3403 (Fix Under Review): librados: expose a list of watchers on an object
- 11:55 AM CephFS Fix #4191 (Resolved): qa: mulitiple mds in nightly (non-failure case)
- 11:46 AM CephFS Feature #4190 (Resolved): qa: add mds thrashing to nightly
- 11:43 AM CephFS Feature #4002 (Resolved): mds: design fsck
- Okay, this is as done as it needed to be.
- 11:40 AM rbd Subtask #4007: libceph: support STAT osd operation
- Josh has reviewed this. Testing again before committing
to be included in the testing branch. - 11:39 AM rbd Cleanup #4053: ceph: cleanup ceph page vector functions
- Josh has reviewed these, and I've rebased them onto
the top of the testing branch. I'm going to test some
before u... - 11:13 AM Feature #3769 (Resolved): osd: scrub should verify snap collection existence, membership
- 11:10 AM Cleanup #4176: poor use of DIR_? subdirs in osds
- You mean by dropping any use of the filesystem at all?
- 11:06 AM Cleanup #4176: poor use of DIR_? subdirs in osds
- Yeah, that bit could be made more efficient. Actually though, with leveldb, we could drop pg collections altogether...
- 10:03 AM Cleanup #4176: poor use of DIR_? subdirs in osds
- Sam groaned about more complicated code when I mentioned this to him, so I'm sending it his way to adjudicate. ;)
- 03:27 AM Cleanup #4176: poor use of DIR_? subdirs in osds
- I first noticed it stracing ceph-osds. Each access in my cluster is preceded by 2-3 useless stats (besides ones that...
- 11:03 AM Bug #4174: osd: last_complete 0'0 < log.tail 36'18330 on ffsb kclient and osd thrashing
- dbadb3e2921297882c5836c67ca32bb8ecdc75db(master) and 91d6be8353259ca30dc87062422e9ae334c3c344(bobtail)
- 11:02 AM Bug #4174 (Resolved): osd: last_complete 0'0 < log.tail 36'18330 on ffsb kclient and osd thrashing
- commit:dbadb3e2921297882c5836c67ca32bb8ecdc75db
- 10:42 AM Bug #2947 (Resolved): osd: out of order reply
- commit:56c5a07708d52de1699585c9560cff8b4e993d0a
I've been hammering on this test for a while and it's turning up s... - 10:37 AM Bug #4113 (Can't reproduce): osd: EOPNOSUPP on pginfo removal
- 10:36 AM rbd Bug #4184 (In Progress): krbd: fix some sparse problems
- I have resolved all of the reports that remain in the
code currently in the testing branch. There are a
few report... - 10:18 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- Oh, n/m, hurray for our sysadmins fixing hasty upgrades. :)
- 10:18 AM Bug #3720: Ceph Reporting Negative Number of Degraded objects
- I reproduced it by:
1. Creating 160GB of rbd devices, x2 replication
2. Offline 1 node with 12 OSDs (out of 5 nod... - 10:16 AM CephFS Feature #3730: Support replication factor in Hadoop
- Yes. I should have closed this and opened a separate ticket for the tests. I'm planning to close it as soon as Joe wi...
- 10:14 AM CephFS Feature #3730 (In Progress): Support replication factor in Hadoop
- Isn't this now merged or something? :)
- 09:43 AM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
- I was thinking the offset for readdir might be 32-bits.. but i may be wrong there.
- 08:57 AM rbd Bug #4183 (Resolved): rbd: EBUSY on unmap right after io
- commit:45a4fe09151bcdeaaa2c3b5dbd089a91deaa055f
- 08:45 AM rbd Bug #4186 (Resolved): rbd: add another "udevadm settle" in the CLI
- commit:8ca2274cc09c6a9925cbe86ccaf68db7898956e8
- 05:06 AM rbd Bug #4186: rbd: add another "udevadm settle" in the CLI
- The change looks good to me.
Reviewed-by: Alex Elder <elder@inktank.com>
- 08:27 AM Bug #4159: after setting pool size to zero, osd's segv and apparently can't recover
- I wasn't able to reproduce this. Dan, what was the sequence to reproduce?
- 08:25 AM Bug #4189 (Resolved): osd/ReplicatedPG.cc: 4994: FAILED assert(log.objects.count(soid) ...
- ...
- 04:32 AM Revision 45a4fe09 (ceph): qa: rbd map-snapshot-io: udevadm settle
- Udev runs blkid on device close, thwarting any rbd unmap that
immediately follows use of the device. Explicitly sett... - 03:07 AM CephFS Bug #4188 (Can't reproduce): mds crashes when cow-ing entries in formerly snapshotted dir
- I have a dir that I used to snapshot before I switched to hardlink trees. I create files and subdirs in it, then, wh...
- 01:07 AM Revision 8e0be548 (ceph): debian: allow extra args to get passed to ./configure via the environment
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:43 AM Revision 1a0e201d (ceph): ceph: fix valgrind log check
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:24 AM Revision 50331e04 (ceph): cleanup-run.sh: figure out owner
- Signed-off-by: Sage Weil <sage@inktank.com>
02/18/2013
- 11:40 PM Revision 60fee7a9 (ceph): schedule_suite.sh: include install task in all jobs
- This is probably temporary. It's simpler than adding the task to every
job in the suite. We'll want to do that late... - 11:40 PM Revision 2653b5a0 (ceph): install: clean up flavor, distro, arch detection
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:22 PM Revision 84d7f37f (ceph): testing: export TESTDIR in workunit task.
- Some command-line tools need to reference the path
to the test directory, which is created at run-time.
We export thi... - 11:06 PM Revision 3f7c9bca (ceph): move the install to a separate task.
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:41 PM Revision 7889c541 (ceph): Strip any trailing whitespace from rbd showmapped
- More recent versions of ceph append a bit of whitespace to the line
after the name of the /dev/rbdX device; this caus... - 09:39 PM Revision 176a3408 (ceph): testrados -> ceph_test_rados
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision b1c9864a (ceph): ceph: install -dbg packages, too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 38b30c64 (ceph): ceph: make gitbuilder host configurable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision ed82d875 (ceph): fix a few archive/log stragglers
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 2a344c10 (ceph): rgw: sudo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 4869b494 (ceph): lock: allow filtering by description, description substring
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision bf6e846d (ceph): cleanup-run.sh: <owner> <run name>
- Sloppy... this assumes the run is in the description as the archive dir.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:39 PM Revision 333c7260 (ceph): rbd: remove merge cruft
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 4dc6c8b2 (ceph): install radosgw
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision a54200d4 (ceph): nuke: tolerate failed dpkg --configure -a/apt-get -f install
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 45ddbe63 (ceph): rgw: specify keyring location
- Otherwise we look at the default /var/lib/ceph/radosgw/ceph-$id/keyring.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:39 PM Revision c9d3dea3 (ceph): avoid secretfile, except for kclient
- Only mount.ceph needs the secret in a standalone file. Remove other users,
and simplify that one.
Signed-off-by: Sa... - 09:39 PM Revision bc9ecf78 (ceph): ceph: pass package version to apt-get install
- This avoids problems when a different or newer version of the package is
already installed.
Signed-off-by: Sage Weil... - 09:39 PM Revision 7a61b237 (ceph): ceph: don't uninstall librados, librbd
- This forces uninstall of kvm too, which is expensive.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:39 PM Revision d1d36241 (ceph): ceph: use default data, keyring locations
- This required reordering the cluster setup so that we do the ceph-osd
--mkfs --mkkey prior to gathering keys and init... - 09:39 PM Revision 88ebc27f (ceph): ceph: store logs in normal location
- We need to switch around how these are compressed and pulled, since they
aren't in the regular archive dir anymore.
... - 09:39 PM Revision 0ad55b36 (ceph): cfuse -> ceph-fuse
- 09:39 PM Revision 4eb047b4 (ceph): sudo for admin socket commands
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 969a6def (ceph): ceph-fuse: sudo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision d8b6bf94 (ceph): ceph: create /var/run/ceph
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision a529bb72 (ceph): ceph: install ceph-mds, ceph-common
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 28116db6 (ceph): nuke: remove librados, librbd
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 27fec237 (ceph): ceph: simpilfy package removal
- apt-get doesn't have a nice way to tell if the package is not install and
we don't need to purge it. Well, not one I... - 09:39 PM Revision 3400ea39 (ceph): nuke: whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision 149be936 (ceph): nuke: dpkg --configure -a and apt-get -f install
- Installing debs means we are more likely to hit a case where we interrupt
apt/dpkg. Try to mop up as best we can in ... - 09:39 PM Revision eadefec8 (ceph): ceph: put client keyrings in /etc/ceph/ceph.$name.keyring
- And make it world readable, for ubuntu's sake.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:39 PM Revision 8b971611 (ceph): ceph: simplify apt-key management
- Run apt-key as root. No need to initialize ubuntu user's gpg. Fix
whitespace.
Signed-off-by: Sage Weil <sage@inktan... - 09:39 PM Revision c525e106 (ceph): Install ceph debs and use installed debs
- The ceph task installs ceph using the debian
packages now, and all invocations of binaries installed
in {tmpdir}/bina... - 09:39 PM Revision 5235fc18 (ceph): ceph: fix purge
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:39 PM Revision fa1f8947 (ceph): Install ceph debs and use installed debs
- The ceph task installs ceph using the debian
packages now, and all invocations of binaries installed
in {tmpdir}/bina... - 09:38 PM Revision d790eeb4 (ceph): nuke: testrados -> ceph_test_rados
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:37 PM Revision c68f687c (ceph): rbd: use 2 node cluster, mostly.
- Not for the collection that includes KVM tests.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:30 PM Revision e250815a (ceph): rgw: use 2 node cluster
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:24 PM Revision f05f90b5 (ceph): rados: use 2 instead of 3 machines
- Put the client on the same node as some of the osds. This shouldn't cause
any problems. It will make timing a bit d... - 09:20 PM Revision 267aac25 (ceph): add fixed-2 cluster
- 08:37 PM rbd Bug #4186 (Fix Under Review): rbd: add another "udevadm settle" in the CLI
- see wip-4186
- 06:04 PM rbd Bug #4186 (Resolved): rbd: add another "udevadm settle" in the CLI
- In http://tracker.ceph.com/issues/4183 it was reported that
unmapping an image was failing because it was busy.
F... - 07:24 PM Revision 231dc1be (ceph): qa: rbd/map-snapshot-io: remove image when done
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:58 PM Revision 1a7a57ac (ceph): qa: fix quoting of wget URLs
- Broke this in ae0c2bbb50ab04467b5223a4f61bfca4b0830142.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:53 PM Revision 3612ed61 (ceph): osd: log weirdness if caller_ops hash gets bigger than the log
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:10 PM rbd Bug #4183 (In Progress): rbd: EBUSY on unmap right after io
- Reassigning to Sage.
Sage, I see you've been working on ceph qa/rbd/map-snapshot-io.sh
and I don't want to interf... - 06:05 PM rbd Bug #4183: rbd: EBUSY on unmap right after io
- ...
- 06:04 PM rbd Bug #4183: rbd: EBUSY on unmap right after io
- OK, I think I understand now.
It turns out that "blkid" is running again on the
device after its final close. Th... - 05:51 PM rbd Bug #4183: rbd: EBUSY on unmap right after io
- We now are very careful about allowing an image to be unmapped
if it's still open, whereas previously we would allow... - 11:24 AM rbd Bug #4183: rbd: EBUSY on unmap right after io
- NOTE: I adjusted the test to add the sleep 1 until this is fixed.
- 11:23 AM rbd Bug #4183 (Resolved): rbd: EBUSY on unmap right after io
- the map-snapshot-io.sh does...
- 05:34 PM Bug #4185 (Won't Fix): Python multiprocessing exhibiting odd behaviour with librados
- The following code snippet yields unexpected results:...
- 05:31 PM Revision 61605f81 (ceph): rados: don't pass ceph.conf path to workloadgen
- The workunit tasks sets CEPH_CONF as needed, which the binaries already
understand. - 05:18 PM Revision c2f2e563 (ceph): Merge pull request #65 from javacruft/wip-ocf-rbd
- Strip any trailing whitespace from rbd showmapped
Reviewed-by: Sage Weil <sage@inktank.com> - 05:18 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- sage, the rados command i'm using have start responding again.. I had to move through a few osd's changing the time ...
- 02:55 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I've set it to 45... and its sucking up memory... and the oom killer got it... I'll see if i can add swap.. it wa...
- 02:52 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- It's not a user object; its the internal pg log of recent requests. No way to change it without surgery...
Let u... - 02:44 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- is there a way to determine what object it is, i expect all my object to be about 13M, nowhere near a gig. i'll adju...
- 02:40 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Woah, okay.. one of your pgs has a 1.3GB log object: 'read_log 0~1381204356'. That is what it is trying to write out ...
- 02:16 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- See attached log
- 02:01 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Hmm, it's not clear why it would get stuck there. Can you reproduce this with 'debug osd = 10'?
The earlier log y... - 10:44 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Most of the Threads are in Wait() or tcp_wait.. i'll attach full thread bt's
I just used gdb to dump the info(in ... - 10:14 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- It looks like IndexedLog::caller_ops is growing without bound; trying to reproduce that, although it is likely unrela...
- 09:58 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Sage, I've been testing for many days now, and two of my OSD's dump core after consuming lots of memory. I've poked ...
- 05:13 PM rbd Bug #4184 (Resolved): krbd: fix some sparse problems
- The Linux kernel has a tool called "sparse" that scans
the source tree and reports various code problems that
the c... - 05:07 PM rbd Cleanup #4164 (Resolved): libceph: update rados.h and related code
- commit 0315a7770983bbe69211efed1aaee08324acd54c
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 15 11:42:30 ... - 05:05 PM rbd Subtask #4126 (Resolved): kernel osd client: kill off some dead code
- 87f979d ceph: kill ceph_osdc_writepages() "nofail" parameter
fbf8685 ceph: kill ceph_osdc_writepages() "dosync" para... - 05:01 PM rbd Cleanup #4165 (Resolved): libceph: update ceph_fs.h and related code
- commit dd6f5e105d85e02bc41db0891eb07152b1746ad9
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 15 11:42:30 ... - 05:00 PM CephFS Cleanup #4166 (Resolved): ceph: simplify ceph_sync_write() page_align
- commit 29c3c8b721a96b4a82f4224527c7103e5e910b80
Author: Alex Elder <elder@inktank.com>
Date: Fri Feb 15 22:10:16 ... - 04:38 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- I'm just spitting in the wind here, but maybe we're leaking the xattrs that get shipped over the wire? That occurred ...
- 09:16 AM Bug #4179 (Resolved): osd: memory leak during deep scrub on bobtail
- ...
- 04:35 PM Cleanup #4176: poor use of DIR_? subdirs in osds
- Have you seen this when examining OSD stores? The use of the same hash as they're split with is quite deliberate — it...
- 06:59 AM Cleanup #4176 (Closed): poor use of DIR_? subdirs in osds
- Since the lowest bits of the hash are used to decide in which PG to place an object, using the same lowest bits withi...
- 04:24 PM Revision ad84ea07 (ceph): Strip any trailing whitespace from rbd showmapped
- More recent versions of ceph append a bit of whitespace to the line
after the name of the /dev/rbdX device; this caus... - 02:03 PM Bug #4162: mon: Single-Paxos: on sync, corrupted paxos store
- Sounds ok!
- 02:32 AM Bug #4162: mon: Single-Paxos: on sync, corrupted paxos store
- This hasn't been triggered since the patch.
Any objections on the approach? - 12:55 PM Feature #3704 (Fix Under Review): mon: add min log level to send cluster msgs to syslog
- wip-mon-syslog
- 12:43 PM Fix #4128 (Fix Under Review): osd: fix pgid=(pool,seed) -> crush input mapping
- 11:03 AM Bug #4182 (Can't reproduce): FileStore::_do_copy_range got short read result
- ...
- 09:56 AM Bug #2947: osd: out of order reply
- 09:35 AM Bug #4110: assertion in DeleteOp::_begin
- Similar:...
- 08:54 AM rgw Bug #4178 (Resolved): s3-tests: fix list_multipart_uploads
- The test should have caught #4177 but it didn't.
- 08:52 AM rgw Bug #4177 (Resolved): rgw: list multipart uploads not listing objects
- instead of 'uploads', need to use 'uploadId'
- 06:40 AM Revision 6fa37493 (ceph): remove rados-multifs link
- 06:13 AM Revision 7a5fd05e (ceph): misc: replace : with - in testdir name
- The :'s break the list in $PATH.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:52 AM Revision 42fba772 (ceph): Merge pull request #64 from dalgaaf/wip-bobtail-memleaks
- cherry-pick some memleak fixes from master to bobtail
- 05:47 AM Revision 133d0ea2 (ceph): buffer: drop large malloc tests
- These succeed on my machine and eat unseemly amounts of RAM.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:47 AM Revision 7fcbfdc0 (ceph): buffer: put big buffer on heap, not stack
- This fixes a segfault on my x86_64 wheezy box.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:30 AM Revision fb472a57 (ceph): unit tests for src/common/buffer.{cc,h}
- Implement unit tests covering most lines of code ( > 92% ) and all
methods as show by the output of make check-covera... - 05:21 AM Revision 94e7c148 (ceph): mon: fix pgmap stat smoothing
- <facepalm>
Signed-off-by: Sage Weil <sage@inktank.com> - 05:10 AM Revision aa537df6 (ceph): doc/release-notes: add note about upgrade to v0.56.3
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:30 AM Bug #4175 (Resolved): mon: Single-Paxos: during proposal of learned value, assert(have_pending)
- Wasn't triggered for the last 8 hours.
- 01:13 AM Revision 0c8d7823 (ceph): rados: remove empty multifs collection
- 01:10 AM Tasks #4066 (Resolved): unit tests for src/include/buffer.h
- 01:08 AM Bug #4170 (Resolved): buffer::ptr::cmp reports a == ab
02/17/2013
- 08:44 PM Bug #2947: osd: out of order reply
- a sequence of messages, all tagged with epochs greater than ours, put on waiting_for_map
- op1 for pg 0.f
- notif... - 07:46 PM Bug #3971: can't attach rbd image volume to instance
- Thanks Josh Durgin.
I found that one of compute node (ubuntu 12.04) had installed the old version of librbd.
B... - 06:39 PM Revision 28e7212d (ceph): ceph_common: fix check for defined/undefined entities in conf
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:03 PM Bug #4103 (Duplicate): mon: Single-Paxos: on MonitorDBStore, segfault during sync
- This bug was just a symptom of the same cause that popped in #4162, where we were able to pinpoint with much more acc...
- 05:58 PM Bug #4037 (Resolved): mon: Single-Paxos: on Paxos, FAILED assert(begin->last_committed == last_co...
- 05:57 PM Bug #4026 (Resolved): mon: Single-Paxos: abort on LogMonitor::update_from_paxos
- 05:57 PM Bug #4040 (Resolved): mon: Single-Paxos: on PGMonitor, FAILED assert(0 == "update_from_paxos: err...
- 05:54 PM Bug #4175 (Resolved): mon: Single-Paxos: during proposal of learned value, assert(have_pending)
- ...
- 05:46 PM Revision d20bf07e (ceph): buffer::ptr::cmp only compares up to the smallest length
- When running
bufferptr a("A", 1);
bufferptr ab("AB", 2);
a.cmp(ab);
it returned zero because. cmp only compar... - 11:38 AM Tasks #4066: unit tests for src/include/buffer.h
- https://github.com/dachary/ceph/commit/f2f22cff2ec73fc27445a8bd7f017a427387d3d2
- 09:29 AM Subtask #2739 (Resolved): mon: Single-Paxos: Sync: Synchronize the store of a drifted monitor
- This is all done. There is some much necessary history cleanup, especially given that there were a couple of bug fix...
- 09:26 AM Subtask #2736 (Resolved): mon: Single-Paxos: Sync: Implement message passing
- This is all done. We may need to update some commit messages and do a general history cleanup before getting it upst...
- 09:25 AM Subtask #3069 (Rejected): mon: Single-Paxos: messaging: log MMonSync messages for offline matching
- This is not something that we really need, and it's usefulness is very much close to none. Logs are more than enough...
- 04:55 AM Revision fecc3c3a (ceph): ceph-disk-prepare: -f for mkfs.xfs only
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:30 AM Bug #4162: mon: Single-Paxos: on sync, corrupted paxos store
- The current approach is:
* we (say, mon.3) contact the first monitor to reply to a probe with a higher paxos versi... - 12:49 AM Revision aff0bb6f (ceph): debian: fix start of ceph-all
- Tolerate failure, and do ceph-all, not ceph-osd-all.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:03 AM Feature #3273: mon: simple dm-crypt key management
02/16/2013
- 11:42 PM Bug #4174 (Resolved): osd: last_complete 0'0 < log.tail 36'18330 on ffsb kclient and osd thrashing
- on bobtail branch:...
- 10:51 PM Revision c4573b74 (ceph): fix operator>=(bufferlist& l, bufferlist& r)
- bufferlist a;
a.append("A");
bufferlist ab;
ab.append("AB");
a >= ab failed, throwing an instance of 'ceph::bu... - 06:35 PM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- Uhh, sorry, I forgot an artifact of the first patch made to the bug-fix patch. s/default_layout_()/default_layout/g ...
- 06:31 PM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- The attached patch seems to fix the problem. It's clear I'm not entirely happy with the idea of testing the inode la...
- 12:17 PM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- I've been looking some more into this. It seems that my hunch was correct: the loss seems to occur at cluster recove...
- 05:47 PM Bug #4170: buffer::ptr::cmp reports a == ab
- Proposed fix http://marc.info/?l=ceph-devel&m=136106547211918&w=4
- 04:58 PM Bug #4170 (Resolved): buffer::ptr::cmp reports a == ab
- When running...
- 05:40 PM Revision ad6655e9 (ceph): rgw/rgw_rest.cc: fix 4K memory leak
- Fix 4K memory leak in case RGWClientIO::read() fails in
read_all_chunked_input().
Error from cppcheck was:
Checking ... - 05:39 PM Revision 37ef3f4b (ceph): Merge remote-tracking branch 'gh/wip-deploy'
- Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
- 05:39 PM Revision 3de69275 (ceph): SyntheticClient.cc: fix some memory leaks in the error handling
- Fix some memory leaks in case of error handling due to failed
client->open() calls.
Error from cppcheck was:
[src/cl... - 05:38 PM Revision f19d228c (ceph): rgw/rgw_xml.cc: fix realloc memory leak in error case
- Fix error from cppcheck:
[src/rgw/rgw_xml.cc:212]: (error) Common realloc mistake: 'buf'
nulled but not freed upon... - 05:38 PM Revision b0c6be95 (ceph): os/FileStore.cc: fix realloc memory leak in error case
- Fix error from cppcheck:
[src/os/FileStore.cc:512]: (error) Common realloc mistake: 'fiemap'
nulled but not freed ... - 05:38 PM Revision f3e5cedb (ceph): common/fiemap.cc: fix realloc memory leak
- Fix error from cppcheck:
[src/common/fiemap.cc:73]: (error) Common realloc mistake: 'fiemap'
nulled but not freed ... - 03:01 PM Bug #4162: mon: Single-Paxos: on sync, corrupted paxos store
- I haven't been following this code at all, but: having that sort of circular message path tends to introduce all kind...
- 04:36 AM Bug #4162 (Resolved): mon: Single-Paxos: on sync, corrupted paxos store
- We've been thrashing the monitors pretty hard, and in this case the assert was triggered as follows:
- mon.3 sent ... - 02:55 PM devops Feature #4169 (New): redmine: configure email thing
- Date: Sat, 16 Feb 2013 10:24:00 +0100
From: Loic Dachary <loic@dachary.org>
To: Ceph Development <ceph-devel@vger.k... - 02:52 PM Bug #4157 (Resolved): operator>=(bufferlist& l, bufferlist& r) throws on a >= ab
- commit:c4573b745c3ffd5b67d9e210569b6318f6591d26
- 01:14 AM Bug #4157: operator>=(bufferlist& l, bufferlist& r) throws on a >= ab
- The pull request is closed
Minimal patch sent via email http://marc.info/?l=ceph-devel&m=136100588219116&w=4 - 11:14 AM Tasks #4066 (Fix Under Review): unit tests for src/include/buffer.h
- 09:41 AM Feature #4076 (Resolved): ceph-disk-prepare/activate: basic dm-crypt support
- commit:37ef3f4b72371f9cc09748877d7e58bd0885e12f
- 09:12 AM CephFS Cleanup #4166: ceph: simplify ceph_sync_write() page_align
- The following has been posted for review to resolve
this issue:
[PATCH] ceph: simplify ceph_sync_write() page_ali... - 08:12 AM CephFS Cleanup #4166 (Resolved): ceph: simplify ceph_sync_write() page_align
- (This work is done.)
ceph: simplify ceph_sync_write() page_align calculation
In ceph_sync_write() there is some... - 09:11 AM rbd Cleanup #4165: libceph: update ceph_fs.h and related code
- The following have been posted for review to resolve
this issue.
[PATCH 0/2] libceph: update ceph_fs.h and relate... - 08:11 AM rbd Cleanup #4165: libceph: update ceph_fs.h and related code
- (Another related commit)
libceph: update ceph_mds_state_name() and ceph_mds_op_name()
Update ceph_mds_state_nam... - 08:10 AM rbd Cleanup #4165 (Resolved): libceph: update ceph_fs.h and related code
- (This work is done. I'm just documenting it because it's really
distinct from http://tracker.ceph.com/issues/4126.)... - 09:10 AM rbd Subtask #4126 (Fix Under Review): kernel osd client: kill off some dead code
- (Oops, I forgot to mark this in progress yesterday.)
The following have been posted for review to resolve this
is... - 09:04 AM Cleanup #4168 (Rejected): ceph: update ceph_fs.h to match kernel
- This issue updated the kernel's version of "ceph_fs.h" so it
includes new definitions added to the user space side.
... - 08:58 AM rbd Cleanup #4164: libceph: update rados.h and related code
- The following have been posted for review to resolve this:
[PATCH 0/3] libceph: update rados.h and related code (4... - 08:07 AM rbd Cleanup #4164: libceph: update rados.h and related code
- (Another commit related to this.)
libceph: update ceph_osd_op_name()
Update ceph_osd_op_name() to include the n... - 08:06 AM rbd Cleanup #4164: libceph: update rados.h and related code
- (Another commit related to this.)
libceph: add ceph_osd_state_name()
Add the definition of ceph_osd_state_name(... - 08:05 AM rbd Cleanup #4164 (Resolved): libceph: update rados.h and related code
- (This work is done, I'm just documenting it because it's really
something distinct from http://tracker.ceph.com/issu... - 08:55 AM Cleanup #4167: ceph: update rados.h to match kernel
- I'm of two minds about how to represent special errno's
defined in the interface between distinct modules (ceph
use... - 08:42 AM Cleanup #4167 (Rejected): ceph: update rados.h to match kernel
- This issue updated the kernel's version of "rados.h" so it
includes new definitions added to the user space side.
... - 08:29 AM rbd Cleanup #4163: libceph: improve packing in struct ceph_osd_req_op
- This has been posted for review.
[PATCH] libceph: improve packing in struct ceph_osd_req_op - 08:00 AM rbd Cleanup #4163 (Resolved): libceph: improve packing in struct ceph_osd_req_op
- (This is done, just documenting it because it's not directly
related to http://tracker.ceph.com/issues/4126)
The ... - 01:21 AM Revision f45e9be2 (ceph): Merge branch 'next'
- 12:54 AM Revision 58837b2b (ceph): Merge remote-tracking branch 'upstream/wip-4075'
- Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 12:26 AM Revision c45fbc75 (ceph): Merge pull request #62 from dalgaaf/wip-da-sca-cppcheck-performance-3
- More performance patches
Reviewed-by: Sage Weil <sage@inktank.com> - 12:26 AM Revision 3f5c2527 (ceph): qa: rbd/map-snapshat-io: unmap image when done
- Signed-off-by: Sage Weil <sage@inktank.com>
02/15/2013
- 10:20 PM CephFS Feature #4161 (Resolved): MDS: add file layout to head object
- In support of #4145, we're going to need a way to get a file's layout even if we lose the containing directory. Add a...
- 10:18 PM Revision c6ac0ddf (ceph): ceph-disk-prepare: add initial support for dm-crypt
- Keep keys in /etc/ceph/dmcrypt-keys.
Identify partition instances by the partition UUID. Identify encrypted
partiti... - 10:18 PM Revision e090a92a (ceph): udev: trigger on dmcrypted osd partitions
- Automatically map encrypted journal partitions.
For encrypted OSD partitions, map them, wait for the mapped device t... - 10:18 PM Revision d950d832 (ceph): ceph-disk-prepare: always force mkfs.xfs
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 10:18 PM Revision e7040f55 (ceph): ceph-disk-activate: pull mount options from ceph.conf
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 10:18 PM Revision b1c0fccb (ceph): ceph-disk-activate: use full paths for everything
- We are run from udev, which doesn't get a decent PATH.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:18 PM Revision 95835de9 (ceph): ceph-disk-prepare: do partprobe after setting final partition type
- This is necessary to kick udev into processing the updated partition and
running its rules.
Signed-off-by: Sage Weil... - 10:04 PM Revision ea6cfb59 (ceph): ReplicatedPG: handle missing set even for old format
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:57 PM Revision bc74429c (ceph): qa: rbd/map-snapshot-io.sh: chown rbd device stuff
- This is fugly, but sudo -E doesn't work. Fix this after we are installing
debs and the path doesn't matter anymore!
... - 08:55 PM Revision 29b44666 (ceph): cls/lock/cls_lock.cc: use !lockers.empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 08:55 PM Revision d50a22d6 (ceph): ceph_authtool.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 08:55 PM Revision 28bf6cba (ceph): mds/CDentry.h: use projected.empty() instead of projected.size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 08:55 PM Revision 49028367 (ceph): mds/MDSMap.h: use up.empty() instead of up.size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 08:55 PM Revision 5c3e6570 (ceph): client/Client.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 08:55 PM Revision adb807c8 (ceph): src/client/SyntheticClient.cc: use !subdirs.empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 07:22 PM Revision ab17aaf2 (ceph): OSD: add leveldblog compatibility flag for OSD
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:22 PM Revision 16b37187 (ceph): PG: verify log versions during read_log
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:11 PM Revision 1ef94200 (ceph): osd: move pg log into leveldb
- log from wip-pginfo
Fix bugs in PG::read_log() handling
Eliminate compiler warnings
Feature #4075: osd: move pg log ... - 07:11 PM Revision 5f92b6cb (ceph): PG: write_log if we read an old-format log
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:13 PM Bug #2947: osd: out of order reply
- woot, reproduced with logs: ubuntu@teuthology:/a/sage-s1/1886
- 06:00 PM Bug #4160 (Resolved): it should be illegal to set pool size to 0
- One can use, at least, ceph osd pool set to set a pool size of 0. Bad things happen if you do this;
I think the OSD... - 05:56 PM Bug #4159 (Resolved): after setting pool size to zero, osd's segv and apparently can't recover
- While it's *probably* the case that the various tools should disallow setting pool size to 0, currently it's possible...
- 05:33 PM Revision f931cad8 (ceph): schedule_suite.sh: fix s3branch
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:23 PM Feature #4075 (Resolved): osd: move pg log into leveldb
- commit:58837b2b544a0d5a789633d702d5e68e6818d013
- 05:20 PM CephFS Feature #3857 (Resolved): mds: enforce unique mds names in mdsmap
- commit:c8f090aed96d615b081f5b9aa36c74092371ae1e
- 05:20 PM Revision 160490cd (ceph): doc: radosgw: document config without 100-continue and custom fastcgi
- Reported-by: carsonoid on github
Signed-off-by: Sage Weil <sage@inktank.com> - 05:20 PM Revision ae0c2bbb (ceph): qa: pull qa stuff from ceph.com ceph.git mirror
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:12 PM Revision 9513f2f2 (ceph): rbd_fsx: binary name now has ceph_ prefix
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:04 PM Revision 467f7a7b (ceph): config: Add small note about default number of PGs
- It's still not clear to end users this should go into the
mon or global section of ceph.conf
Until this gets resolve... - 04:55 PM Revision 78450fed (ceph): Merge remote-tracking branch 'origin/wip-hadoop-docs'
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:54 PM Revision f62952f4 (ceph): Merge pull request #59 from dalgaaf/wip-da-add-errorhandling
- add error handling to test_sync_*.c
Reviewed-by: Sage Weil <sage@inktank.com> - 04:48 PM Revision 69a8bbd8 (ceph): Merge remote-tracking branch 'gh/next'
- 04:43 PM CephFS Feature #3573 (Rejected): ceph-fuse: Add ioctl support
- 04:41 PM CephFS Feature #2195 (Resolved): Allow removal of last MDS if there's no filesystem
- this works now.. 'fail' and them 'rmfailed'.
- 04:04 PM Feature #1625 (Rejected): changing ceph-mon ip address needs monmap change on every mon machine
- such is life
- 04:04 PM Cleanup #1876 (Resolved): osd: EINVAL on all client command decoding errors
- this was cleaned last fall
- 04:03 PM Feature #1808 (Rejected): filestore: gracefully handle EMFILE
- 04:01 PM Feature #1606 (Rejected): osd: bound missing set memory usage
- 03:59 PM Fix #1857: osd: reimplement shutdown()
- see wip-osd-leak
- 03:58 PM Fix #1857: osd: reimplement shutdown()
- 03:49 PM Feature #136 (Rejected): sensible grammar for monitor commands
- 03:37 PM Bug #4157 (Fix Under Review): operator>=(bufferlist& l, bufferlist& r) throws on a >= ab
- Proposed fix https://github.com/ceph/ceph/pull/63
- 02:50 PM Bug #4157 (Resolved): operator>=(bufferlist& l, bufferlist& r) throws on a >= ab
- ...
- 01:59 PM rbd Cleanup #4156 (Resolved): qa: don't chown rbd stuff in rbd/* workunits
- Once we are doing proper installs, we can call sudo as needed and not worry about $PATH etc.
- 01:58 PM Bug #4149 (Resolved): qa: map-snapshot-io.sh fails with EPERM
- commit:bc74429c8b3a5c4dfe49505cf5e0f42de28bf0b4
- 01:33 PM Bug #4149 (In Progress): qa: map-snapshot-io.sh fails with EPERM
- 09:10 AM Bug #4149 (Resolved): qa: map-snapshot-io.sh fails with EPERM
- this seems to happen consistently. not sure why this fails but, say, map-unmap.sh does not...
- 01:37 PM devops Feature #4155 (New): migrate mirrors onto cephfs
- 01:30 PM rgw Tasks #4154 (New): gather configuration files for non-Apache RGW deployments
- In order to head off user issues for non-Apache RGW deployments we should collect/create configuration files for some...
- 01:08 PM devops Feature #4152 (New): redmine: show priority in backlogs view
- 01:06 PM rgw Feature #4151 (New): Add transparent header support
- Would like to see PUT requests like those Amazon supports with a cache-control header, to do something similar with t...
- 10:43 AM devops Feature #3916 (Fix Under Review): ceph-disk-activate: non-upstart trigger (udev?)
- 10:42 AM CephFS Bug #4061 (Can't reproduce): mds crashed at LogEvent::decode
- Burnupi60 had some hardware issue so I had it reimaged. I reinstalled the master branch and am not able to reproduce ...
- 09:28 AM rgw Bug #4150 (Resolved): rgw: copy object into itself leaks tail references
- 09:22 AM Revision 6f3f1739 (ceph): test_sync_io.c: add error handling
- Add error handling for open(), posix_memalign() and malloc().
Reuse code for read_* and write_* functions.
Signed-of... - 09:21 AM Revision 26cdb6a6 (ceph): test_short_dio_read.c: add error handling
- Add error handling for open() calls.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 09:08 AM Bug #4148 (Resolved): osd: snap collections mismatch from thrashing
- ...
- 09:07 AM Bug #4147 (Resolved): librados: st_rados_list_objects failure
- ...
- 07:54 AM Documentation #4146 (Resolved): cephfs quickstart: clarify mounting on same node
- Right now the warning is in the intro, and seems to apply to everything, but this restriction only matters when using...
- 01:33 AM Revision 2c42bfc0 (ceph): doc: update rados troubleshooting for slow requests
- The example was out of date. Adding a note about how to look at the request
queue on the OSD.
Reported-by: Chris Du...
02/14/2013
- 11:40 PM Revision 290a352c (ceph): osd/OSDCap: add unit test for parsing pools/objects with _ and -
- Hunting #4122, where a user saw
2013-02-13 19:39:25.467916 7f766fdb4700 10 osd.0 10 session 0x2c8cc60 client.libvir... - 11:40 PM Revision f4791635 (ceph): osd/OSDCap: tweak unquoted_word parsing in osd caps
- Newer versions of spirit (1.49.0-3.1ubuntu1.1 in quantal, in particular)
dislike the construct with alnum and replace... - 11:39 PM Revision a6534bc8 (ceph): osd/OSDCap: add unit test for parsing pools/objects with _ and -
- Hunting #4122, where a user saw
2013-02-13 19:39:25.467916 7f766fdb4700 10 osd.0 10 session 0x2c8cc60 client.libvir... - 11:39 PM Revision 6c504d96 (ceph): osd/OSDCap: tweak unquoted_word parsing in osd caps
- Newer versions of spirit (1.49.0-3.1ubuntu1.1 in quantal, in particular)
dislike the construct with alnum and replace... - 10:57 PM Revision 4dfcad44 (ceph): OSD: always activate_map in advance_pgs, only send messages if up
- We should always handle_activate_map() after handle_advance_map() in
order to kick the pg into a valid peering state ... - 09:46 PM Revision 2ce28ef1 (ceph): osd/OSDCap: add unit test for parsing pools/objects with _ and -
- Hunting #4122, where a user saw
2013-02-13 19:39:25.467916 7f766fdb4700 10 osd.0 10 session 0x2c8cc60 client.libvir... - 08:38 PM Revision a14bae60 (ceph): rgw: user can specify 'rgw port' to listen on a tcp port.
- 'rgw socket path' overrides 'rgw port'.
An 'rgw host' can be set to listen on a specific ip (default is 0.0.0.0)
Sig... - 08:37 PM Revision 93bfb361 (ceph): test/filestore/chain_xattr: remove testfile; disable LOGFILE
- These make the gitbuilder checks unhappy.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:39 PM Revision 84ef4a89 (ceph): Merge branch 'master' of github.com:ceph/ceph
- 07:36 PM Revision ffda2eab (ceph): Merge branch 'wip-danny-perf-checks'
- 07:34 PM Revision 1de16ac1 (ceph): osd: log error when ondisk snap collections do not match
- This way we notice when it happens instead of blindly moving on.
Backport: bobtail
Signed-off-by: Sage Weil <sage@in... - 07:31 PM Revision c8f090ae (ceph): Merge remote-tracking branch 'origin/wip-mds-names'
- 06:57 PM CephFS Feature #4145 (Resolved): MDS: design and implement a backwards-scanning fsck
- We've discussed this a little bit, but we eventually want a mechanism that looks through all the RADOS objects in our...
- 06:55 PM CephFS Feature #4144 (New): MDS: forward scrub: do not abort a scrub if its hierarchy gets migrated
- Once scrub can survive part of its hierarchy moving, modify it so that it also can survive its containing hierarchy m...
- 06:54 PM CephFS Feature #4143 (New): MDS: forward scrub: do not abort a scrub if part of its subtree gets migrated
- Following #4142, modify the scrub and add infrastructure as needed so that a scrub continues if part of the hierarchy...
- 06:51 PM CephFS Feature #4142 (Duplicate): MDS: forward scrub: Implement cross-MDS scrubbing
- Following #4141, implement the mechanisms necessary so that an MDS can start a remote scrub in order to complete a lo...
- 06:45 PM CephFS Feature #4141 (New): MDS: forward scrub: Implement non-blocking scrub
- Once we have a blocking scrub (#4140), convert it to be non-blocking. If necessary it can block the dentry which is c...
- 06:44 PM Revision 971b1612 (ceph): osd: fix read_log error/warning messages to mon
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:43 PM CephFS Feature #4140 (New): MDS: forward scrub: add infrastructure to perform a blocking scrub of all au...
- Write functionality for the MDS so that on command it will do a blocking scrub of all data in a tree for which it is ...
- 06:38 PM CephFS Feature #4139 (Resolved): MDS: forward scrub: add scrub_stamp infrastructure and a function to sc...
- Add the scrub stamps necessary for the scrubbing algorithm described in our forward scrub proposal; be efficient abou...
- 06:34 PM CephFS Feature #4138 (Resolved): MDS: forward scrub: add functionality to verify disk data is consistent
- Design and implement a mechanism that, given a CInode, it will go check the actual disk state of that inode for consi...
- 06:33 PM CephFS Feature #4137 (New): MDS: Implement a forward-scrubbing mechanism.
- Design and implement a system that checks the filesystem for consistency by starting at the root node.
So far we'v... - 06:31 PM Revision 61eb0e96 (ceph): Merge pull request #40 from dachary/master
- Unit tests for chain_xattr.cc
Reviewed-by: Sage Weil <sage@inktank.com> - 06:27 PM Revision a30017fb (ceph): rgw/rgw_usage.cc use empty() to check for emptiness
- Use !empty() instead of 'size()' to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny... - 06:27 PM Revision e2af5b3e (ceph): rgw/rgw_user.cc: use empty() to check for emptiness
- Use !empty() instead of 'size()' to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny... - 06:27 PM Revision a8614b86 (ceph): scratchtoolpp.cc: print some more results
- Print some more results to fix issue found by cppcheck:
[src/scratchtoolpp.cc:111] -> [src/scratchtoolpp.cc:114]:
... - 06:27 PM Revision e551dd4c (ceph): test_keyvaluedb_iterators.cc: use empty() to check for emptiness
- Use !empty() instead of 'size() > 0' to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <d... - 06:27 PM Revision 9da963ef (ceph): test_object_map.cc: use empty() to check for emptiness
- Use !empty() instead of 'size()' to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny... - 06:27 PM Revision 47413b3d (ceph): FileStoreTracker.cc: use empty() to check for emptiness
- Use !empty() instead of size() to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.a... - 06:27 PM Revision f923be5d (ceph): TestFileStoreState.cc: use empty() to check for emptiness
- Use empty() instead of '!size()' to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny... - 06:27 PM Revision 37bb45f2 (ceph): test_mon_workloadgen.cc: use empty() to check for emptiness
- Use empty() instead of '!size()' and "size() == 0" to check for emptiness
for performance reasons and since it's more... - 06:27 PM Revision f9bf1275 (ceph): src/test/osd/RadosModel.h: use empty() to check for emptiness
- Use empty() instead of size() to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al... - 06:27 PM Revision 18348857 (ceph): test_filejournal.cc: use empty() to check for emptiness
- Use !empty() instead of size() to check for emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.a... - 06:27 PM Revision 82023784 (ceph): tools/common.cc. use !empty() to check for non-emptiness
- Use !empty() instead of size() to check for non-emptiness for
performance reasons.
Signed-off-by: Danny Al-Gaaf <dan... - 06:27 PM Revision ab1166cd (ceph): rest_bench.cc: use empty() to check for emptiness
- Use empty() instead of 'size() == 0' or 'size() < 1' to check
for emptiness for performance reasons.
Signed-off-by: ... - 06:27 PM Revision 533fd7a8 (ceph): wireshark/ceph/packet-ceph.c: fix some issues from cppcheck
- Fix some smaller performance related issues from cppcheck due to
"Variable '..xy..' is reassigned a value before the ... - 06:27 PM Revision 4c11a5d1 (ceph): librbd/internal.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision d0896404 (ceph): mds/CDir.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision a65c71ca (ceph): mds/CInode.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision 3ed962be (ceph): mds/Locker.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision 1755fd97 (ceph): mds/MDCache.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision aa2ae6a2 (ceph): mds/MDS.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision e57d9913 (ceph): mds/MDSMap.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision f244fd73 (ceph): mds/SnapServer.cc: use !empty() instead of size() to check for emptiness
- Use !empty() instead of size() for performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:27 PM Revision 60440839 (ceph): mds/journal.cc: use !empty() instead of size() to check for emptiness
- Use !empty() instead of size() for performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:27 PM Revision e980d52c (ceph): rgw/rgw_main.cc: use empty() instead of size() to check for emptiness
- Use empty() instead of 'size() == 0' for performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:27 PM Revision 005fe42c (ceph): rgw/rgw_op.cc: use empty() instead of size() to check for emptiness
- Use empty() instead of 'size() == 0' for performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:27 PM Revision dfe1b452 (ceph): rgw/rgw_rados.cc: : use empty() to check for emptiness
- Use empty() instead of '!size()' for performance reasons.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 06:27 PM Revision b14994e5 (ceph): rgw/rgw_rest_swift.cc: don't pass c_str() result to std::string argument
- Fix issue found by cppcheck:
[src/rgw/rgw_rest_swift.cc:770]: (performance) Passing the result of
c_str() to a func... - 06:27 PM Revision 338e1680 (ceph): rgw/rgw_admin.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision 59f8c8d8 (ceph): rgw/rgw_gc.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision fb811ecf (ceph): rgw/rgw_log.cc: don't pass c_str() result to std::string argument
- Fix issue found by cppcheck:
[src/rgw/rgw_log.cc:340]: (performance) Passing the result of c_str() to a
function t... - 06:27 PM Revision c4f1c079 (ceph): cls/rbd/cls_rbd.cc: use !empty() instead of 'size() > 0'
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision 810d23e9 (ceph): cls_refcount.cc: use empty() instead of !size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision e719e0a2 (ceph): common/WorkQueue.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision d6c4a62f (ceph): obj_bencher.cc: use empty() instead of 'size() == 0' to check for empti...
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision f4cae000 (ceph): crush/CrushWrapper.cc: don't pass c_str() result to std::string argument
- Fix issue found by cppcheck:
[src/crush/CrushWrapper.cc:352]: (performance) Passing the result of
c_str() to a fun... - 06:27 PM Revision 30fe1077 (ceph): crushtool.cc: use !empty() instead of 'size() > 0' to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision fc0a1087 (ceph): cls_kvs.cc: use !empty() instead of 'size() > 0' to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:27 PM Revision 15248ae1 (ceph): kv_flat_btree_async.cc: use empty() instead of size() to check for empt...
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:26 PM Revision 4950a1b3 (ceph): osdmaptool.cc: : use empty() instead of 'size() < 1'
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:26 PM Revision 95eda326 (ceph): rados.cc: use omap.empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:26 PM Revision c115bdb4 (ceph): rbd.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 06:26 PM Revision 8c1cb215 (ceph): rgw/rgw_admin.cc: prevent useless value assignment
- Fix issue found by cppcheck:
[src/rgw/rgw_admin.cc:710] -> [src/rgw/rgw_admin.cc:714]:
(performance) Variable 'ret'... - 06:19 PM Revision fb6561e7 (ceph): Objecter.cc: prevent useless value assignment
- Fix issue found by cppcheck:
[src/osdc/Objecter.cc:989] -> [src/osdc/Objecter.cc:992]: (performance)
Variable 'chec... - 05:22 PM Revision e259f3c8 (ceph): Merge pull request #57 from dalgaaf/wip-da-mkcephfs-init-2
- Fix some init/mkcephfs related issues
Reviewed-by: Sage Weil <sage@inktank.com> - 05:12 PM Revision 97c6ce0a (ceph): init-ceph.in: create pid and log dir only on start
- Create pid and log dir only on start and not e.g. also on
stop. These calls are useless in other situtations than sta... - 05:12 PM Revision aa4cae66 (ceph): ceph_common.sh: check if $sshdir exist, otherwise create it
- Check if $sshdir exist. If not, create it before cd to the
directory.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bi... - 05:12 PM Revision d029b936 (ceph): init-ceph.in: replace "/var/run/" by already used $RUN_DIR
- Fix handling of admin socket. The current script already use
$RUN_DIR to define a default, which is /var/run. Replace... - 05:07 PM Revision ffbc085d (ceph): Merge pull request #53 from dachary/wip-4123
- fix buffer::list::zero(unsigned o, unsigned l) to act on all buffer::ptr
Backport: bobtail
Reviewed-by: Sage Weil <s... - 05:03 PM rbd Subtask #3272: send/receive rbd snapshots
- From Sage - "I think this breaks down into a few different pieces:
1) Decide what output format to use. We want t... - 05:02 PM rbd Subtask #3387: librbd: expose changed objects since a given snapshot
- 8 points
- 05:01 PM Revision 6365ded4 (ceph): Merge pull request #54 from javacruft/wip-pthread-linking
- LDADD PTHREAD_LIBS to fix librados-config linking
Reviewed-by: Sage Weil <sage@inktank.com> - 05:01 PM Revision e31baeeb (ceph): Merge pull request #56 from trhoden/doc_cephx
- Make cephx key creation syntax consistent
Reviewed-by: Sage Weil <sage@inktank.com> - 04:56 PM Revision c4306cb9 (ceph): Merge pull request #55 from dalgaaf/wip-da-cleanup-specfile
- Cleanup some requirements of spec file
Reviewed-by: Sage Weil <sage@inktank.com> - 04:25 PM rbd Feature #4021 (Fix Under Review): rbd: openstack: add ability to copy volume to image for rbd
- 04:25 PM rbd Subtask #4019 (In Progress): rbd: openstack: simplify volume booting with new api: add boot optio...
- 04:12 PM rbd Subtask #4019: rbd: openstack: simplify volume booting with new api: add boot option to volumes
- 3 points
- 04:25 PM rbd Subtask #4020 (In Progress): rbd: openstack: simplify volume booting with new api: make image boo...
- 04:12 PM rbd Subtask #4020: rbd: openstack: simplify volume booting with new api: make image boot button add s...
- 2 points
- 04:24 PM rbd Subtask #4018 (In Progress): rbd: openstack: simplify volume booting with new api: modify boot pa...
- 04:24 PM rbd Feature #4017 (In Progress): rbd: openstack: simplify volume booting with new api
- 04:23 PM Revision 7eefe0b7 (ceph): doc: Update create example to use 'allow ' syntax
- The ceph auth get-or-create example here is the only place on the
page that does not use 'allow <perms.' syntax. I f... - 04:19 PM Revision 51a0a220 (ceph): doc: Move pool=... syntax inside of single quotes
- When specifying caps, the entire 'allow ...' bit needs to be in the
single quotes, including the pool= part.
Signed-... - 04:12 PM Linux kernel client Bug #3762 (Duplicate): kernel osd client: verify support for multiple ops per request
- I'm marking this as a duplicate. There are other issues
(most notably http://tracker.ceph.com/issues/2770) that
co... - 04:11 PM Bug #2691: osd/ReplicatedPG.cc: 5888: FAILED assert(latest->is_update())
- I might have a similar assetion here on bobtail (ceph version 0.56.3 (6eb7e15a4783b122e9b0c85ea9ba064145958aa5)):
... - 04:02 PM rbd Bug #3947 (Resolved): krbd: read zeroing freed bio?
- This got resolved in version 2 of the "new request code,"
which is now present in the testing branch. - 03:56 PM Bug #4042 (Resolved): osd crash in recovery state: FAILED assert(0 == "we got a bad state machine...
- commit:4dfcad44431855ba7d68a1ccb41dc3cb5db6bb50
- 02:13 PM Bug #4042 (Fix Under Review): osd crash in recovery state: FAILED assert(0 == "we got a bad state...
- wip_4042 I think should take care of it.
- 09:41 AM Bug #4042 (New): osd crash in recovery state: FAILED assert(0 == "we got a bad state machine event")
- 03:41 PM Bug #4122 (Resolved): osd: possible corruption of osd caps
- commit:6c504d96c1e4fbb67578fba0666ca453b939c218
- 03:31 PM Bug #4122 (Fix Under Review): osd: possible corruption of osd caps
- wip-4122
- 02:58 PM Bug #4122: osd: possible corruption of osd caps
- AHA, fails on quantal:...
- 01:48 PM Bug #4122 (Need More Info): osd: possible corruption of osd caps
- That output line is *right* after OSDCap::parse() is called, and the result appears to be wrong. My guess is that the...
- 03:37 PM Bug #4079: osd: journal aio deadlock
- Is there any chance clock skew could have an impact?
I just got these messages. I don't suppose this is a
problem ... - 03:22 PM Bug #4079: osd: journal aio deadlock
- I should also mention, I'm running against the current "next"
branch from the ceph repository. At that moment, that... - 03:15 PM Bug #4079: osd: journal aio deadlock
- As Sage suggested, I tried with an older kernel. Actually,
I just tried it with the newly updated master branch, wh... - 10:31 AM Bug #4079: osd: journal aio deadlock
- And finally test 75 completed, taking 18,723 seconds,
more than 5 hours.
Again, forward progress, absurdly slow.
... - 09:03 AM Bug #4079: osd: journal aio deadlock
- I haven't done a lot of this, but here's something I find in
the client log after turning on all debug output for th... - 07:40 AM Bug #4079 (In Progress): osd: journal aio deadlock
- I tried running just tests 74 and 75 this morning, and running
just those two (twice each, as well as doing that sev... - 03:12 PM rbd Feature #4136 (Duplicate): rbd xfstests: update list of tests run
- The latest version of xfstests includes tests numbered
up to 296. The last test we run is 278. Some of the
update... - 02:27 PM Revision 01f82b84 (ceph): ceph.spec.in: remove librados2 requirement from librbd1
- Remove librados2 requirement from librbd1. The RPM build system
will find the dependency by itself.
Signed-off-by: D... - 02:24 PM Bug #4065: Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- There appears to be a corrupt attribute on one of the objects on that OSD. If this is reproducible, can you restart ...
- 02:11 PM Revision 9952f2dd (ceph): ceph.spec.in: cleanup requirements of fuse packages
- Cleanup the Requires: list of the fuse packages. Remove fuse-libs,
libstdc++, libuuid. Don't add libraries to the lis... - 01:33 PM Feature #4135 (Resolved): osd: noscrub, nodeepscrub osdmap flags
- 01:10 PM Revision 03fe4793 (ceph): LDADD PTHREAD_LIBS to fix librados-config linking
- librados-config depends on libglobal which in turn
reference symbols in pthread; this caused issues
when linking due ... - 12:47 PM devops Documentation #4111 (Resolved): installing RPMs - documented install release key command fails
- Fixed. DH has it set so it only allows RC4-SHA:
SSLCipherSuite RC4-SHA
I added a custom parameter to the http... - 12:46 PM Revision 02a353e5 (ceph): fix buffer::list::zero(unsigned o, unsigned l) to act on all buffer::ptr
- When buffer::list::zero was called on a buffer::list with "ABC" and
"DEF" in two different buffer::ptr with buffer::l... - 11:22 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I using the 0.56.3 rpms that were releases yesterday for elg.x86_64, with a larger journal of 5G now, but two of my o...
- 10:51 AM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I using the 0.56.3 rpms that were releases yesterday for elg.x86_64, with a larger journal of 5G now, but two of my o...
- 11:02 AM CephFS Bug #4134: mds: request locking hang under snaptests
- For reference, the hung request is client.4104:75.
- 11:00 AM CephFS Bug #4134 (Resolved): mds: request locking hang under snaptests
- Haven't diagnosed this yet, but I ran into it while testing for #3819. Logs in kai:~/logs/4134.
First step, just fig... - 11:01 AM CephFS Feature #3819: mds: re-add snaptests to qa suite
- Currently blocked by #4134, and possibly other things. Will work on that as I get time, but focusing on other stuff t...
- 09:53 AM CephFS Feature #3819 (In Progress): mds: re-add snaptests to qa suite
- 10:24 AM Feature #3757 (Fix Under Review): osd: Watch/Notify cleanup
- 09:45 AM devops Feature #4130 (Resolved): ceph-deploy: be polite about pushing ceph.conf
- If it is not present, push it. If it is the same, do nothing. If it is different, print a nice warning for the user...
- 09:40 AM Bug #4043 (Resolved): osd: validate/scrub collections
- commit:ed2bb387708511b4910758d77c5a9754193eb48a
- 09:36 AM rgw Bug #4124 (Fix Under Review): Using "response-content-type" arguments causes duplicated Content-T...
- 08:07 AM rgw Bug #4124: Using "response-content-type" arguments causes duplicated Content-Type in response
- 05:59 AM rgw Bug #4124: Using "response-content-type" arguments causes duplicated Content-Type in response
- Here's a fix that worked for me.
- 05:38 AM rgw Bug #4124 (Resolved): Using "response-content-type" arguments causes duplicated Content-Type in r...
- Title says it all ... If I do a GET and use the"response-content-type" to ensure the 'Content-Type' header in the res...
- 09:25 AM Bug #4027 (Fix Under Review): ceph-fuse on opensuse12 has the wrong requirement name for libfuse ...
- 06:43 AM Bug #4027: ceph-fuse on opensuse12 has the wrong requirement name for libfuse dependency
- See https://github.com/ceph/ceph/pull/55
- 09:24 AM Fix #4128 (Resolved): osd: fix pgid=(pool,seed) -> crush input mapping
- The current code does hash(pool + seed) which makes pgs from adjacent pools overlap and share the same osds. This is...
- 09:14 AM Bug #4123 (Resolved): buffer::list::zero overflows and returns before completion
- commit:ffbc085de1ef931e4c6a55b2d649d862f671bdb9
- 05:06 AM Bug #4123 (Fix Under Review): buffer::list::zero overflows and returns before completion
- 05:06 AM Bug #4123: buffer::list::zero overflows and returns before completion
- Here is the proposed fix https://github.com/ceph/ceph/pull/53
- 02:58 AM Bug #4123: buffer::list::zero overflows and returns before completion
- The test to check if the pointer is past the end of range to be zeroed is reversed. It is "o+l >= p":https://github.c...
- 02:52 AM Bug #4123 (Resolved): buffer::list::zero overflows and returns before completion
- h3. Overflow
When "buffer::list::zero":https://github.com/ceph/ceph/blob/0327cbaa2ab48b8da8aad181f55ce4e48fe3946c/... - 07:11 AM Revision 690ae053 (ceph): ceph-disk-activate: catch daemon start errors
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:11 AM Revision b7b9af5c (ceph): debian: start/stop ceph-all event on install/uninstall
- This helps us avoid the confusing situation with upstart where an individual
daemon job is running (like ceph-osd id=... - 07:06 AM rbd Subtask #4125: kernel messenger: support multiple sources of data
- Here's a short list of smaller tasks I can identify right
now in order to implement this. I may create a new issue
... - 05:57 AM rbd Subtask #4125 (Resolved): kernel messenger: support multiple sources of data
- We need to allow the osd client to have an array of osd ops
such that each can supply its own buffer for sending and... - 06:59 AM Bug #3945: osd: dynamically link to leveldb
- leveldb 1.9 for openSUSE/SLE11SP2: https://build.opensuse.org/package/show?package=leveldb&project=home%3Adalgaaf%3Ac...
- 06:25 AM rbd Subtask #4127 (Resolved): kernel osd client: clearly separate read and write data buffers
- The osd client (and messenger) have generally speaking one
field representing *either* the data to be sent *or* the
... - 06:18 AM Revision 1af749eb (ceph): upstart/ceph-osd: make crush update on start optional
- By default, we will do some (minimal) CRUSH tree adjustment. However,
we make this update optional.
Fixes: #3993
Si... - 06:18 AM Revision f06b45e6 (ceph): ceph-disk-activate: specify full path for blkid, initctl, service
- /sbin apparently isn't in the path when udev runs us.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:18 AM Revision d1904b2a (ceph): ceph-disk-activate: auto detect init system
- Look for an option 'init' in ceph.conf. Otherwise, check if we're ubuntu.
If so, use upstart. Otherwise, use sysvin... - 06:18 AM Revision 5bd85ee5 (ceph): udev: trigger ceph-disk-activate directly from udev
- There is no need to depend on upstart for this.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:14 AM rbd Subtask #4126 (Resolved): kernel osd client: kill off some dead code
- While looking through how to implement multiple ops I have
noticed that there's some dead code in the osd client, or... - 05:56 AM Bug #4036: init-ceph: assumes write access to /var/run/ceph
- /var/run/ceph is used not only for the socket files, but also for the pid files by default.
I would guess it's a ... - 05:40 AM rbd Subtask #2854: krbd: write path
- This work actually did begin last week, after getting STAT
calls implemented (see http://tracker.ceph.com/issues/400... - 05:35 AM rbd Tasks #2853: krbd: read path
- This work is close to complete, in that I have shown
that a lot of functionality seems to work correctly.
I was n... - 05:24 AM rbd Feature #2770: krbd: define tasks to add osd_client compound class op support
- After the walk through described above, I spent a little more
time thinking about the messenger aspect of allowing m... - 01:43 AM Revision ccdcae3a (ceph): doc/release-notes: v0.56.3
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:25 AM Revision 0c1eb423 (ceph): Merge branch 'wip_4113'
- Reviewed-by: Sage Weil <sage@inktank.com>
02/13/2013
- 11:02 PM Revision 1334a424 (ceph): PG,OSD: convert write_info users to write_if_dirty
- Also, explicitely dirty info and biginfo where necessary.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:41 PM Feature #3892: osd: move pg info into leveldb
- commit 188f3ea6867eeb6e950f6efed18d53ff17522bbc
Author: David Zafman <david.zafman@inktank.com>
Date: Mon Feb 11 ... - 10:41 PM Feature #3891: osd: move purged_snaps out of info
- commit 188f3ea6867eeb6e950f6efed18d53ff17522bbc
Author: David Zafman <david.zafman@inktank.com>
Date: Mon Feb 11 ... - 10:39 PM Feature #4075 (In Progress): osd: move pg log into leveldb
- 10:10 PM Revision 5d6d6884 (ceph): rados: testrados -> ceph_test_rados
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:32 PM Revision f4b70c89 (ceph): PG: minor style change for append_log and read_info
- They exceeded 80 characters on a line!
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:32 PM Revision 93b3da6a (ceph): PG: place biginfo on the infos object next to the info and epoch keys
- This is simpler and possibly more efficient.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:32 PM Revision 34ed5daa (ceph): OSD: init infos_object in OSD::init()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:32 PM Revision f3bc8dfe (ceph): PG: use helpers to generate info and epoch keys
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:56 PM Revision 7e192077 (ceph): libcephfs: Fix shutdown segfault
- client->shutdown() should only be called once, but with
new inited flag, we were calling it twice. This sets
the ini... - 08:47 PM Revision e9c77035 (ceph): Merge branch 'wip-deploy'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 08:44 PM Revision 6879e8b3 (ceph): doc: Minor clarification.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:43 PM Revision 760b5ff3 (ceph): OSD: dirty big_info in build_past_intervals_parallel
- Otherwise, the newly generated intervals won't get written!
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:39 PM Revision b2ff6e8c (ceph): ceph-disk-prepare: refactor to support DIR, DISK, or PARTITION for data...
- Lots of code reorganization collapsed into a single commit here.
- detect whether the user gave us a directory, disk... - 08:39 PM Revision 792e45c6 (ceph): upstart/ceph-hotplug: tell activate to start via upstart
- This will mark the OSD data dir as upstart-managed.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:39 PM Revision e011ad12 (ceph): upstart: ceph-hotplug -> ceph-osd-activate
- This is a more meaningful name.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:39 PM Revision 64ec2d42 (ceph): doc: Made a few clarifications from feedback.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:35 PM Revision fd4a9210 (ceph): ceph-disk-activate: add --mark-init INITSYSTEM option
- Do not assume we will manage via upstart; let that be passed down via the
command line.
Signed-off-by: Sage Weil <sa... - 08:35 PM Revision 191d5f75 (ceph): ceph-disk-activate: detect whether PATH is mount or dir
- remove in-the-way symlinks in /var/lib/ceph/osd
This is simpler. Just detect what the path is and Do The Right Thin... - 08:35 PM Revision 07655288 (ceph): ceph-disk-activate: factor mounting out of activate
- The activate stuff is generic for any OSD, regardless of whether we want
to mount it or not. Pull that part out.
Si... - 08:30 PM Revision 50cbd105 (ceph): debian: implement purge postrm script for ceph, ceph-mds
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:30 PM Revision b8aa4769 (ceph): init-ceph: consider sysvinit-tagged dirs as local
- If there is a 'sysvinit' file in the daemon directory in the default
location (/var/lib/ceph/$type/ceph-$id), conside... - 08:30 PM Revision c8f528a4 (ceph): init-ceph: iterate/locate local sysvinit-tagged directories
- Search /var/lib/ceph/$type/ceph-$id and start/stop those daemons if
present and tagged with the sysvinit file.
Signe... - 08:30 PM Revision 4698b6a1 (ceph): upstart/ceph-hotplug: drop -- in ceph-disk-activate args
- We would like to transition to
ceph-disk-activate --mount DEV
and away from a generic multi-definition PATH argume... - 08:30 PM Revision 809143f1 (ceph): ceph-create-keys: create mds bootstrap key
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:30 PM Revision e80675a0 (ceph): debian: include /var/lib/ceph/bootstrap-mds in package
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:30 PM Revision 23ad3a46 (ceph): debian: put ceph-mds upstart conf in ceph-mds package
- Fixes: #3157
Signed-off-by: Sage Weil <sage@inktank.com> - 08:28 PM Revision af2372ca (ceph): ceph-disk-prepare: align mkfs, mount config options with mkcephfs
- 'osd mkfs ...', not 'osd fs mkfs ...'. Sigh. Support both.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:06 PM Revision 617bde95 (ceph): doc: Added many Q/A sections to the FAQ.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:10 PM Revision 6eb7e15a (ceph): v0.56.3
- 04:50 PM Revision db41f261 (ceph): schedule_suite.sh: choose s3branch based on teuthology branch
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:47 PM Revision f5eb845a (ceph): rgw: change json formatting for swift list container
- Fixes: #4048
There is some difference in the way swift formats the
xml output and the json output for list container.... - 04:43 PM Bug #4122 (Resolved): osd: possible corruption of osd caps
- Three users have reported some kind of caps problem I haven't been able to reproduce (EPERM on some operation depende...
- 04:30 PM Revision 670a1482 (ceph): qa: fix mon/osd.sh
- It needs to be a valid osd id that we try to remove (that doesn't exist).
Signed-off-by: Sage Weil <sage@inktank.com> - 03:53 PM Revision 7aefe923 (ceph): specfile: Add ceph-coverage to list of binaries
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 03:05 PM CephFS Feature #3819: mds: re-add snaptests to qa suite
- Pushed a fix to wip-mds-snap-fix that Sage checked out and will merge it once I've run through the rest of the snapte...
- 01:50 PM CephFS Feature #3819: mds: re-add snaptests to qa suite
- Well, actually adding them is simple enough, but I first started a snaps run on vstart and it's crashing the MDS on a...
- 02:29 PM Revision 612f65b1 (ceph): Objecter.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 02:24 PM Revision 722d12c8 (ceph): ObjectCacher.cc: use empty() instead of !size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 02:21 PM Revision 475967f9 (ceph): ReplicatedPG.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 02:18 PM Revision d9a06382 (ceph): PG.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 02:03 PM Revision 5d899969 (ceph): OSD.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:59 PM Revision f94f7979 (ceph): LFNIndex.cc: use !holes.empty() instead of 'size() > 0'
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:58 PM Revision 4893def5 (ceph): HashIndex.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:56 PM Revision f65679b4 (ceph): FileStore.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:51 PM Revision b0ec071a (ceph): DBObjectMap.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:46 PM Revision dd855b3e (ceph): monmaptool.cc: use empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:42 PM Revision 0b312342 (ceph): PGMonitor.cc: use !empty() instead of size() to check for emptiness
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:42 PM devops Feature #3993 (Fix Under Review): upstart/sysvinit: control whether crush position is readjusted ...
- 01:41 PM Revision 6f0175e5 (ceph): OSDMonitor.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:40 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- whoops, grabbed the mtime, they are all about 13380480 bytes.
Evan Felix wrote:
> the objects in question are abo... - 01:38 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I'll try the new code when it is released. for now i've resized the journal on one of the problems osd's( osd 2) wit...
- 01:20 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- No, you'd have to shut down the OSD, do a journal flush, and then re-create the journal. It's sparsely documented at ...
- 01:13 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- the objects in question are about 1360713573, though i only do small updates inside the file. does changing the size...
- 12:58 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- That JOURNAL TOO SMALL message indicates you're sending single operations which are larger than your journal. And ind...
- 12:55 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- 12:55 PM Bug #4116 (Need More Info): common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- 12:55 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- Evan Felix wrote:
> I've also seen these Journal errors at times:
> 2013-02-13 12:45:55.029747 7f71cabfd700 1 jour... - 12:47 PM Bug #4116: common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I've also seen these Journal errors at times:
2013-02-13 12:45:55.029747 7f71cabfd700 1 journal check_for_full at 6... - 10:48 AM Bug #4116 (Resolved): common/HeartbeatMap.cc: 79: FAILED assert(0 == "hit suicide timeout")
- I have been experiencing slowness lately, with lots of messages in ceph -w about operations taking a long time. Durin...
- 01:38 PM Revision 8fcd31f6 (ceph): Monitor.cc: use empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:34 PM Revision f7078b4a (ceph): MonCaps.cc: use !empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:21 PM devops Feature #3912: ceph-deploy: break osd into create/destroy
- Greg Farnum wrote:
> We did also want an OSD destroy command in the future; is there a separate ticket for that?
... - 01:13 PM devops Feature #3912: ceph-deploy: break osd into create/destroy
- We did also want an OSD destroy command in the future; is there a separate ticket for that?
- 01:15 PM devops Feature #3913: ceph-deploy: break mon into create/destroy
- We don't have a way to destroy mons yet, do we?
- 01:14 PM devops Feature #4032: ceph-disk-prepare should allow the definition of an OSD id
- One path forward is to make the 'osd create <uuid>' optionally take the osd id we would like, and use it if available...
- 01:10 PM Revision d7705edf (ceph): OSDMonitor.h: use !reporters.empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 01:10 PM devops Feature #3918 (Resolved): ceph-deploy: osd create HOST:DIR[:JOURNAL]
- this is captured by ceph-disk-prepare. commit:b2ff6e8c9d96dee2c063b126de7030a5c2ae0d02
- 01:09 PM devops Feature #4008 (Resolved): ceph-deploy: make sure new version works with old ceph-disk_*
- 01:09 PM devops Feature #3914 (Resolved): ceph-disk-activate: support sysvinit
- commit:fd4a921085a861e4aa428376219bb39055731f2b
- 01:09 PM devops Feature #3157 (Resolved): upstart: move mds scripts to ceph-mds package.
- commit:23ad3a46a0099e263f43e0f0c1df1d21cfe58b3f
- 01:08 PM devops Feature #3911 (Resolved): sysvinit: allow daemon enumeration via dirs
- commit:c8f528a4070dd3aa0b25c435c6234032aee39b21
- 01:08 PM devops Feature #3917 (Resolved): ceph-dir-prepare command
- handled by ceph-disk-prepare now
commit:e9c770358e32decb49c4806f83998b740b1cf0d2 - 12:59 PM Revision a3970e56 (ceph): CephxProtocol.h: pass CryptoKey by reference to decode_decrypt()
- Fix issues found by cppcheck:
[src/auth/cephx/CephxProtocol.h:469]: (performance) Function
parameter 'key' should ... - 12:59 PM Revision 6b8458d7 (ceph): CInode.h: use !old_inodes.empty() instead of size()
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 12:59 PM Revision 180cae5e (ceph): AuthMonitor.cc: use !pending_auth.empty() instead of 'size() > 0'
- Use empty() since it should be prefered as it has, following the
standard, a constant time complexity regardless of t... - 12:57 PM CephFS Bug #4114 (Resolved): libcephfs: segfault on
- commit:7e192077ffc77f6c2a534c32f0fdf57a7d05ee7f
- 10:48 AM CephFS Bug #4114 (Fix Under Review): libcephfs: segfault on
- Pretty minor fix to set the inited flag to false. But wip-4114 could use a review.
- 09:08 AM CephFS Bug #4114 (In Progress): libcephfs: segfault on
- 08:32 AM CephFS Bug #4114 (Resolved): libcephfs: segfault on
- ...
- 12:45 PM devops Feature #4119 (Resolved): rpm: create /var/lib/ceph/* directories
- 12:45 PM devops Feature #4118 (Rejected): rpm: include upstart stuff in (some) rpms
- 11:21 AM Documentation #4117 (Closed): Document various language bindings better
- Currently the language bindings for librados, librbd and libcephfs are not documented.
We should add more links to... - 11:21 AM Bug #3883 (Won't Fix): osd: leaks memory (possibly triggered by scrubbing) on argonaut
- 10:26 AM Bug #3690 (Resolved): osd crashed in FileStore::_do_transaction
- resolved a bit later that day, commit:0942e005448efb60ab31fe98f156d1f1b0e377cd and others.
- 10:07 AM CephFS Feature #606 (Duplicate): mds: optionally store parent attr on file objects
- #3540. We decided it wouldn't be optional.
- 09:34 AM CephFS Bug #4115 (Rejected): packaging: broken ceph-test-dbg binaries
- Sage points out that those are just the debug symbols...
- 09:26 AM CephFS Bug #4115 (Rejected): packaging: broken ceph-test-dbg binaries
- The ceph-test-dbg package installs test binaries to /usr/lib/debug/usr/bin/, but the binaries themselves don't have e...
- 09:22 AM Feature #3853 (Resolved): qa: include iogen in qa suite
- 09:21 AM Feature #4076 (In Progress): ceph-disk-prepare/activate: basic dm-crypt support
- 09:21 AM Feature #3757 (In Progress): osd: Watch/Notify cleanup
- 09:12 AM Bug #4064 (Resolved): osd: filestore assert on FORREMOVAL_* collection removal
- commit:0942e005448efb60ab31fe98f156d1f1b0e377cd
- 08:27 AM Bug #4113 (Can't reproduce): osd: EOPNOSUPP on pginfo removal
- ...
- 06:10 AM rbd Feature #3761: kernel messenger: need to support multiple ops per request
- Here's what I'm prototyping.
I'm going to try to expand the definition of the trail portion of
a message so inste... - 05:12 AM rbd Feature #3761 (In Progress): kernel messenger: need to support multiple ops per request
- In order to support multiple ops for osd requests we're
going to have to do some work on the messenger as well.
I'm... - 05:44 AM Revision f21543f0 (ceph): librbd: unprotect any non-unprotected snapshot
- Include snapshots in the UNPROTECTING state as well, which can occur
after an unprotect is interrupted.
Fixes: #4100... - 05:44 AM Revision 65969f8f (ceph): java: make CephMountTest use user.* xattr names
- Changes to the xattr code in Ceph require
a few tweaks to existing test cases.
Specifically, there is now a ceph.file... - 05:31 AM Revision 7309bccc (ceph): schedule_suite.sh: take option teuthology branch arg
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:24 AM Revision 0c663ca8 (ceph): schedule_suite.sh: ensure ceph and kernel branches exist
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:20 AM Revision 9d6eccbf (ceph): osd/PG: initialize info_struct_v in ctor
- Otherwise we randomly assert on the first write_info() for newly created
PGs. Introduced by 188f3ea6867eeb6e950f6efe... - 02:36 AM Revision 7c2e2b99 (ceph): java: make CephMountTest use user.* xattr names
- Changes to the xattr code in Ceph require
a few tweaks to existing test cases.
Specifically, there is now a ceph.file... - 01:53 AM Revision 977ba79b (ceph): doc: clarified ceph id vs. ceph name, and fixed a typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:18 AM Revision 188f3ea6 (ceph): osd/PG: store pg_info_t in leveldb (omap), purged_snaps separately
- Separate the purged_snaps portion of pg_info_t (the one that gets big).
Feature #3891: osd: move purged_snaps out of... - 01:12 AM Revision 0e985279 (ceph): doc: Added some of the troubleshooting steps into the libvirt procedure...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:55 AM Revision 0fec0fde (ceph): Merge branch 'next'
- Conflicts:
src/include/ceph_features.h - 12:43 AM Revision fe283813 (ceph): librbd: unprotect any non-unprotected snapshot
- Include snapshots in the UNPROTECTING state as well, which can occur
after an unprotect is interrupted.
Fixes: #4100... - 12:19 AM devops Documentation #4111: installing RPMs - documented install release key command fails
- Documentation is correct. There is some sort of ssl protocol error with libcurl on centos6. Some of the other rpm d...
02/12/2013
- 11:36 PM Revision c036dc7c (ceph): doc: fix command syntax
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 11:12 PM Revision 376cca2d (ceph): deb: Add ceph-coverage to ceph-test deb package
- Teuthology uses the ceph-coverage script extensively
and expects it to be installed by the ceph task. Add
the script... - 10:44 PM Revision 5517000f (ceph): cephtool: Add add_data_pool command to help
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 10:44 PM Revision ed6c3ff5 (ceph): qa/workunits: Add vxattr set pool test script
- Add a test script that tests for creating a pool
and then setting the layout for a (pre-existing)
file to that pool.
... - 10:44 PM Revision d8c6b08e (ceph): mds: Add retry field to MDRequest
- The MDRequest can be retried via the RetryRequest finisher,
we add a retry field that gets incremented before each
re... - 10:44 PM Revision 78ff229a (ceph): mds: Setting pool on a file requires latest osdmap
- If we create a file, then create a pool, then try to
set the pool on the file with the vxattr, no mds operation
trigg... - 10:23 PM devops Documentation #4111: installing RPMs - documented install release key command fails
- It may need to point to the github repository instead of the ceph mirror. I found that worked ok with github:
[ub... - 05:04 PM devops Documentation #4111 (Resolved): installing RPMs - documented install release key command fails
- attempting a bobtail rpm installation for centos got the following when executing the suggested command
[qauser... - 10:18 PM Revision 1b05517a (ceph): msg/Messenger: rename option
- It's unhandled, not unexpected.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:17 PM Revision de5247ed (ceph): Merge pull request #50 from dalgaaf/wip-da-sca-clang-overloaded-virt-2
- mds/LogEvent.h: change print() signature to const
- 10:15 PM Revision e68fcec7 (ceph): mon: handle -EAGAIN in completion contexts
- We can get ECANCELED, EAGAIN, or success out of the completion contexts,
but in the EAGAIN case (meaning there was an... - 10:15 PM Revision 0453140d (ceph): mon: retry PGStats message on EAGAIN
- If we get EAGAIN from a paxos restart/election/whatever, we should
restart the message instead of just blindly acking... - 10:15 PM Revision 14fddc3c (ceph): mon: fix typo in C_Stats
- Broken by previous commit.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3cf3710be0b4cccc8d... - 10:14 PM Revision 20ec4905 (ceph): osd: only share maps on hb connection of OSD_HBMSGS feature is set
- Back in 1bc419a7affb056540ba8f9b332b6ff9380b37af we started sharing maps
with dead osds via the heartbeat connection,... - 10:14 PM Revision cbf63b63 (ceph): osd: tolerate unexpected messages on the heartbeat interface
- We should note but not crash on unexpected messages. Announce this awesome
new "capability" via a feature bit.
Sign... - 10:11 PM Revision 302b26ff (ceph): osd: only share maps on hb connection of OSD_HBMSGS feature is set
- Back in 1bc419a7affb056540ba8f9b332b6ff9380b37af we started sharing maps
with dead osds via the heartbeat connection,... - 10:10 PM Revision afda30ae (ceph): osd: tolerate unexpected messages on the heartbeat interface
- We should note but not crash on unexpected messages. Announce this awesome
new "capability" via a feature bit.
Sign... - 10:10 PM Revision 2cb6bcc9 (ceph): Revert "Makefile: name binary ceph-filestore-dump"
- This reverts commit f0b2e32af69d7d009837832066a1445c45bbc362.
Be consistent with everything else. - 10:10 PM Revision a88f9bea (ceph): .gitignore: fix ceph_filestore_dump name
- Underscores!
Signed-off-by: Sage Weil <sage@inktank.com> - 10:10 PM Revision 1e68ccf6 (ceph): msg/Messenger: do not crash on unhandled message
- This is just polite.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:50 PM devops Feature #3920 (New): ceph-deploy: support other deb-based distros
- 09:48 PM devops Feature #3907 (Resolved): ceph-deploy: be verbose about what is run and what is done (with -q)
- 09:48 PM devops Feature #4008: ceph-deploy: make sure new version works with old ceph-disk_*
- 09:45 PM devops Feature #3913 (Resolved): ceph-deploy: break mon into create/destroy
- 09:45 PM devops Feature #3912 (Resolved): ceph-deploy: break osd into create/destroy
- 09:39 PM Revision 102a5196 (ceph): Merge remote-tracking branch 'gh/wip-bobtail-osd-msgr' into bobtail
- 09:17 PM Revision 0c65cd5f (ceph): mds/LogEvent.h: change print() signature to const
- Fix print() function of src/mds/LogEvent.h, declare as
virtual void print(ostream& out) const {...}
Adapt functions... - 06:55 PM Revision e2b8e0f1 (ceph): modified the perl file name
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:17 PM devops Feature #3157 (Fix Under Review): upstart: move mds scripts to ceph-mds package.
- 06:16 PM Revision 0942e005 (ceph): Merge branch 'wip-4064-sam'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:16 PM devops Feature #4112 (Resolved): ceph-deploy: support mds
- 06:15 PM Revision 7edf8acf (ceph): os: use coll_t:is_pg_prefix() check instead of is_pg()
- The objectstore code was trying to parse out a pgid from the collection
name and using the is_pg() helper, which inco... - 06:15 PM Revision 66ddffb7 (ceph): osd: make coll_t::is_pg() correctly validate the snapid suffix
- The strtoull() man page suggests resetting errno and using that to
check for a parsing error. This ensures the OSD::... - 06:15 PM Revision d8891d5a (ceph): os/FileStore: do not tolerate ENOENT on collection_add
- If we get ENOENT on a collection_add that is a bad thing; do not ignore
the error. This was hiding #4071 for some ti... - 06:15 PM Revision b184ff58 (ceph): FileStore: _split_collection should not create the collection
- This will simplify adding a replay guard to create_collection.
Backport: bobtail
Signed-off-by: Samuel Just <sam.jus... - 06:15 PM Revision 411770c4 (ceph): FileStore: set replay guard on create_collection
- This should prevent sequences like:
rmcoll a
mkcoll a
touch a foo
<crash>
from causing trouble by preventing the rm... - 06:04 PM Feature #4075: osd: move pg log into leveldb
- Proposed code for this change is in branch wip-4075. This was originally developed by Sage in the wip-pginfo branch ...
- 05:54 PM Revision ea98fbb9 (ceph): doc: Removed legacy comment regarding Keystone integration.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:53 PM Revision 522a81e9 (ceph): doc: Added link to <disk> reference. Added minor clarifications.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:34 PM rbd Bug #4100 (Resolved): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- commit:fe283813b44a7c45def6768ea0788a3a0635957e and commit:bfb4482c4596759b464caf45f8f30368898519d8 in bobtail.
- 09:37 AM rbd Bug #4100: rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- Dan - please review the wip branch.
- 05:20 PM Feature #3891 (Resolved): osd: move purged_snaps out of info
- 05:20 PM Feature #3892 (Resolved): osd: move pg info into leveldb
- 04:27 PM rgw Bug #3682: valgrind errors seen when running rgw tests in nightlies
- ubuntu@teuthology:/a/teuthology-2013-02-12_01:00:03-regression-next-testing-basic/5247
- 04:24 PM Bug #4110 (Resolved): assertion in DeleteOp::_begin
- log: ubuntu@teuthology:/a/teuthology-2013-02-12_01:00:03-regression-next-testing-basic/5133...
- 03:52 PM rbd Bug #3958: rbd fsx fails with EBUSY
- ubuntu@teuthology:/a/teuthology-2013-02-11_20:00:06-regression-bobtail-master-basic/4941
- 03:43 PM Bug #4109 (Duplicate): incorrect degraded count
- ubuntu@teuthology:/a/teuthology-2013-02-11_20:00:06-regression-bobtail-master-basic/4909$
2013-02-11T22:08:22.398 ... - 03:23 PM rgw Feature #4108 (Duplicate): rgw: optionally put bucket index data in separate pool
- 03:09 PM CephFS Bug #4105: mds: fix up the Dumper
- 02:00 PM CephFS Bug #4105 (Resolved): mds: fix up the Dumper
- The messenger/objecter locking is wrong, and my quick stab at a fix resulted in lockdep warnings and things. Spend so...
- 03:01 PM Feature #4107 (Duplicate): Usage quota for rados pools
- The ability to set a quota (either by percentage or cap) on how much data can be stored in a rados pool using the sam...
- 02:51 PM Feature #4106 (Resolved): Monitor free space on crush pools
- The ability to monitor free space on individual crush pools. Currently rados df does not provide this information.
- 02:44 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- Yeah, if it's working for some other people I don't think we want to change the current config without taking the tim...
- 02:40 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- It's also working great for at least one customer on squeeze. But I don't think we can prioritize digging in given s...
- 01:04 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- It was most noticeable with the MDS, but I bet we'd see it a lot more with our present OSD design as well now and it ...
- 12:57 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- IIRC this was mostly a problem for ceph-mds. And probably working at all is better than inflated memory usage in the...
- 12:42 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- How bizarre:...
- 12:13 PM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- > dpkg -s ceph
Version: 0.56.2-1~bpo60+1
> dpkg -s libgoogle-perftools0
Version: 1.5-1
> dpkg -s libtcmalloc-... - 11:21 AM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- I actually run these on Debian pretty often and don't have any issues, so I'm a bit confused. Can you grab a backtrac...
- 02:40 PM CephFS Bug #4060 (Resolved): mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- commit:a04c01f6822b165bf339d41eda29fcc5fa555f53
- 02:23 PM CephFS Bug #4061: mds crashed at LogEvent::decode
- Hmm, actually this one might be different from the other. It's a client cap update event, and the event on disk claim...
- 01:59 PM CephFS Bug #4061: mds crashed at LogEvent::decode
- Probably the same Tamil, yes. This should be a little easier to debug if we get it again in the future following last...
- 11:10 AM CephFS Bug #4061: mds crashed at LogEvent::decode
- There was no load yet. I was attempting the ceph-fuse mount test after the update.
Today I have ceph version 0.... - 11:05 AM CephFS Bug #4061: mds crashed at LogEvent::decode
- looks like it is same as bug#3773
- 09:44 AM CephFS Bug #4061: mds crashed at LogEvent::decode
- Ken, what was the workload you were running on this before the crash?
- 02:11 PM rbd Feature #2770: krbd: define tasks to add osd_client compound class op support
- The way the osd client handles an object class method right now
assumes that outbound data (headed from the client t... - 10:18 AM rbd Feature #2770: krbd: define tasks to add osd_client compound class op support
- ...
- 10:16 AM rbd Feature #2770: krbd: define tasks to add osd_client compound class op support
- ...
- 01:22 PM Revision 5659a4eb (ceph): mon: Remove global version code introduced around bobtail's release
- This patch reverts most of the global version (gv) related patches that
were introduced around bobtail's release as a... - 01:22 PM Revision 77799a5b (ceph): auth: cephx: KeyServer: add 'has_secrets()' function
- We need this in the AuthMonitor to assess if we should encode a full version
of the KeyServer and submit it to the Pa... - 11:42 AM rbd Feature #4104: osd_client: support passing page array as data for CALL op
- I guess this needs to be considered an rbd task if it is
to show up as a subtask for 2770. - 11:41 AM rbd Feature #4104 (Resolved): osd_client: support passing page array as data for CALL op
- The rbd object "copyup" operation is defined as a class method
operation. Currently when a class method needs to su... - 11:18 AM Bug #3972: new boost dependency: libboost-program-options
- 11:10 AM rgw Feature #3991 (In Progress): rgw: dr: region mgt changes: define datastructures
- 11:08 AM Bug #3434: Unknown variables in test_xattr_support
- Giving to Ian for proper distribution. :)
- 10:59 AM Feature #3403 (In Progress): librados: expose a list of watchers on an object
- 10:56 AM Bug #3433: Error: Store.__init__() takes no parameters
- I'm not really sure where obsync is tracked — Ian, can you figure that out?
- 10:49 AM Bug #3172 (Resolved): ceph::buffer::bad_alloc downloading a large object using rados
- I believe this got fixed in commit:234becd3447a679a919af458440bc31c8bd6b84f.
Previously it was trying to read a full... - 10:41 AM CephFS Bug #733: cmds crash: mds/LogEvent.cc:88: FAILED assert(p.end())
- This is at least the same crash as #4061, although it'd be nice to get one of these with logging on the caused end in...
- 10:15 AM Documentation #3711 (Resolved): crush-map.rst: choose firstn talks about "N", but does not clearl...
- 10:09 AM Bug #4103 (Duplicate): mon: Single-Paxos: on MonitorDBStore, segfault during sync
- ...
- 08:32 AM Documentation #4102 (Resolved): doc: in crush-map-rules, wrong spec for step take
At: http://ceph.com/docs/master/rados/operations/crush-map/#crush-map-rules
It says:
step take <bucket-type>
...- 07:27 AM Cleanup #4101 (Rejected): buffer::list::iterator constructor should be private
- The ...
- 06:21 AM Revision bd6d4989 (ceph): ceph-filestore-dump: Improve error message
- Fix error message when encountering already in use
OSD store.
Signed-off-by: David Zafman <david.zafman@inktank.com>... - 06:02 AM Revision 8864c730 (ceph): Merge branch 'wip-mds-encode-rebased'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 04:49 AM Revision f0b2e32a (ceph): Makefile: name binary ceph-filestore-dump
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:44 AM Revision 29222872 (ceph): doc: Added procedures for using libvirt VMs with Ceph.
- fixes: #3432
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 02:38 AM Revision 1b7fc30a (ceph): .gitignore: fix typo and missing vstart.sh output
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 02:11 AM Revision 2783fce2 (ceph): work unit for rbd cli tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:49 AM Revision f923c8cd (ceph): doc: document hadoop replication config
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:43 AM Revision d4d11a50 (ceph): adding task for rbd cli tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:29 AM Revision 7c8d3d05 (ceph): added new cli tests
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 01:12 AM Revision 3f4d8532 (ceph): Merge remote-tracking branch 'gh/next'
- 12:49 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Journal is 1G in RAM. Since there are no writers at all yet, I don't think that journal is filled and causes device s...
- 12:47 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Tried on regular 1G ethernet (other client server). Works well. Speed is stable and no such effect.
I don't under...
02/11/2013
- 10:15 PM CephFS Feature #3543 (Closed): mds: new encoding
- After an fs suite run passed all tests except for libcephfs-java (which was known bad at the branch point), iogen whi...
- 10:14 PM Revision a62d5198 (ceph): Unit tests for chain_xattr.cc
- Create a new test file covering most (> 97%) of src/os/chain_xattr.{cc,h}
lines of code. The following functions are ... - 09:25 PM Revision 31e911b6 (ceph): osd: update snap collections for sub_op_modify log records conditionaly
- The only remaining caller is sub_op_modify(). If we do have a non-empty
op transaction, we want to do this update, r... - 09:25 PM Revision 715d8717 (ceph): osd: include snaps in pg_log_entry_t::dump()
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:24 PM Revision 54b6dd92 (ceph): osd: unconditionally encode snaps buffer
- Previously we would only encode the updated snaps vector for CLONE ops.
This doesn't work for MODIFY ops generated by... - 09:24 PM Revision 8b05492c (ceph): osd: improve debug output on snap collections
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:04 PM Bug #4065: Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- Last 1000 lines of the log, no problem.
- 02:16 PM Bug #4065 (Need More Info): Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- 02:15 PM Bug #4065: Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- I suspect the log included more output. Can you attach the previous 1000 lines?
-Sam - 07:46 PM Documentation #3432 (Resolved): move explanation for rbd on libvirt to new docs
- I've put together a full procedure including using virt-manager. There are notes to use "virsh edit" and to specifica...
- 07:30 PM Revision ab89e934 (ceph): Revert "rgw: plain format always appends eol to data"
- This commit breaks the swift unit test. The reason is that it
makes it so that returned error status ends with eol, w... - 07:25 PM rbd Bug #4100 (Fix Under Review): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with...
- wip-snap-unprotect
- 05:34 PM rbd Bug #4100 (Resolved): rbd: unprotecting a snapshot in the "UNPROTECTING" state fails with EINVAL
- As reported on ceph-users, an unprotect earlier was taking too long (possibly due to inactive pgs) and was killed. Th...
- 07:02 PM Revision ab99d8e1 (ceph): Merge branch 'wip-da-rename-ceph-test'
- 05:57 PM Revision 133295ed (ceph): libcephfs: fix for #4068
- If client->init() fails in mount, then client->shutdown()
should not be called. This patch uses a bool to ensure
that... - 05:43 PM Revision a39a48c1 (ceph): Merge pull request #47 from dalgaaf/wip-da-sca-cppcheck-clang-2
- fix more issues from clang(++) and cppchecker
Reviewed-by: Sage Weil <sage@inktank.com> - 05:08 PM Revision 755b4bb3 (ceph): .gitignore: add local ones for ocf and man
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 04:48 PM Revision 3d5969d6 (ceph): qa/rbd: +x on map-snapshot-io.sh
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:44 PM rgw Feature #4099 (Resolved): rgw: Object Expiration
- would like to see an implementation for object expiration for the RadosGW.
- 04:41 PM rgw Feature #4098 (Resolved): rgw: multi-site: Global Bucket Namespace
- a feature request, basically they want to support multiple regions. I've copied the request below.
> We would like... - 04:29 PM rgw Feature #4097 (Resolved): rgw: s3 static website
- would like to see root domain support so that customers can run their static sites directly from rgw.
http://aws.a... - 04:04 PM Revision b26dc4e0 (ceph): test: fix run-rbd-tests
- The python tests were not renamed
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 04:04 PM Revision c52dbd57 (ceph): .gitignore: re-add vstart dirs and tags, fix typo
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 03:47 PM Revision ebe70d7a (ceph): Mutex.cc: fix implicitly-defined namespace 'std'
- Fix warning from clang(++):
common/Mutex.cc:14:17: warning: using directive refers to
implicitly-defined namespace... - 03:42 PM Revision c7970bba (ceph): ceph_authtool.cc: fix implicitly-defined namespace 'std'
- Fix warning from clang(++):
ceph_authtool.cc:15:17: warning: using directive refers to
implicitly-defined namespace... - 03:35 PM rbd Feature #4095 (Rejected): rbd: 2-phase commit for snapshot creation
- To ensure snapshots are created as close as possible to when the user intended, instead of just waiting for a notify,...
- 03:13 PM Revision d5c771a3 (ceph): rados/monthrash: run some mon tests
- 03:13 PM Revision 8d5ca943 (ceph): rados: separate out mon thrasher from thrasher collection
- Run a different set of tests.
- 02:59 PM Revision 6e3c2d93 (ceph): peer: add recovery delay to make test behave
- Otherwise it was (very) racy!
- 02:55 PM Bug #2803: filer: probe crash
- turned debugging on and the logs are placed in ubuntu@burnupi06:~/log_2803
- 10:30 AM Bug #2803: filer: probe crash
- 02:33 PM rbd Subtask #4092: rbd: re-read header when watch is re-established
- Yes, I'll create corresponding tasks for krbd once I get the rest of the general ones in.
- 02:09 PM rbd Subtask #4092: rbd: re-read header when watch is re-established
- This same issue would apply to the kernel rbd client also,
right? - 01:32 PM rbd Subtask #4092 (Resolved): rbd: re-read header when watch is re-established
- This avoids races that would result in a snapshot not being created correctly, like:...
- 01:55 PM CephFS Bug #4061: mds crashed at LogEvent::decode
- sorry Greg, I pulled the information from ken and filed this bug. Please let me know if you need more info.
- 01:36 PM CephFS Bug #4061: mds crashed at LogEvent::decode
- IIRC I was waiting on some other info from Ken for this. Is that coming? :)
- 01:39 PM CephFS Feature #3730: Support replication factor in Hadoop
- Initial set of tests are in the Hadoop tree and working. Need to add them to Teuthology test thingy. There are now tw...
- 01:38 PM Bug #2890: monitor: "recognize" heap commands
- I've had this sitting in my queue for a long time; can you check if it's still an issue and do something appropriate ...
- 01:34 PM Bug #4071 (Resolved): osd: snap coll not created on scrub trim repop
- 4 patches culimating in commit:31e911b63d326bdd06981ec4029ad71b7479ed70
- 01:24 PM rbd Subtask #4091 (Resolved): ObjectCacher: optionally make readx/writex calls never block
- The idea is to prevent any aio calls from blocking client (i.e. qemu) threads.
This was what Sage was thinking as ... - 12:41 PM rbd Subtask #4090 (New): rbd: investigate sources of client-side latency
- Some possible sources:
* lock contention
* unnecessary data copying
* contention on queues
* throttling in messen... - 12:39 PM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
- The only way I can think of that a 32-bit client would be different is in the inode assignment; could it be running i...
- 05:37 AM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
- 12:00 AM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
- Tried with updated to 0.56.2. Found no troubles, but actually environment changed, since I removed 32-bit kernel clie...
- 12:39 PM rbd Feature #4089 (Closed): rbd: improve small I/O performance
- Root task for general improvement.
- 12:38 PM Bug #3690 (In Progress): osd crashed in FileStore::_do_transaction
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-10_01:00:02-regression-master-testing-gcov/4059...
- 12:36 PM rbd Feature #4088 (Resolved): rbd: optionally copy-on-read instead of copy-on-write
- This can be beneficial in some use cases (such as when there's high latency to the original pool, but not the new pool).
- 12:31 PM rbd Feature #4087: rbd: bitmaps for tracking object existence
- Also, I wonder at what point it becomes worthwhile to
use something different from bitmaps (such as extents
that de... - 12:29 PM rbd Feature #4087: rbd: bitmaps for tracking object existence
- I was thinking this weekend of creating this issue exactly.
Are you envisioning keeping these with the image heade... - 12:27 PM rbd Feature #4087 (Resolved): rbd: bitmaps for tracking object existence
- This would improve layered image performance, and enable quick, conservative usage for an image. It should be possibl...
- 12:27 PM Bug #4079: osd: journal aio deadlock
- Below is a chart with test number, an example of a test
run with results more in line with what's expected, and
the t... - 11:48 AM Bug #4079 (Resolved): osd: journal aio deadlock
- I don't really understand this yet. I have seen it occurring
with the new request code. I thought there could be a... - 12:24 PM rbd Feature #4086 (Resolved): rbd: rate-limiting
- Enforce policies like max-iops from a client point of view. The objecter throttling is too low-level, especially when...
- 12:15 PM rbd Feature #4085 (New): qemu-rbd: allow storing snapshot of ram associated with snapshot of disk
- This way the entire state of a VM can be restored, instead of just the disks.
- 12:12 PM rbd Feature #4084 (Resolved): rbd: incremental backups
- Root task for the feature in general
- 12:06 PM rbd Feature #4083 (New): rbd-fuse: expose snapshots (and maybe other pools)
- Maybe only do so for an image when asked, but optionally always show all pool and snapshots? Need to think about the ...
- 12:03 PM rbd Feature #4082 (Rejected): rbd-fuse: improve performance
- Use aio, different IoCtxs per image, and the C++ librbd api for fewer data copies.
- 12:02 PM rbd Feature #4081 (New): rbd-fuse: improve usage, make consistent with other ceph tools
- Use the common command line/conf file/env var parsing. Re-write internals to c++ instead of C as needed.
- 12:01 PM Documentation #4080 (Closed): We should document what needs to be touched when adding a build dep...
- Recently the build started depending a a new package (boost-program-options); when it was added, the
gitbuilders we... - 11:58 AM Bug #2761: osd: failed to recover before timeout expired
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-09_20:00:03-regression-bobtail-master-basic/3922
- 11:55 AM rgw Bug #3682 (In Progress): valgrind errors seen when running rgw tests in nightlies
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-09_20:00:03-regression-bobtail-master-basic/3989
- 11:51 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- What size is the journal on your osds? You may just be seeing a slowdown when the journals fill up, and must be flush...
- 07:57 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- It may be a network issue as well. Is it easy for you by chance to try with regular ethernet (say, gig instead of 10...
- 07:43 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- > 3.7.2-ceph
That tells me a lot, and in fact makes me suspect it might
not be rbd that's the cause.
What can ... - 07:41 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- During slow periods iostat shows no operations on OSDs. First of all I've thought about sceduler and iowait problems,...
- 07:38 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Linux hosting-cloud1-s1.zzzing.ru 3.7.2-ceph #1 SMP Wed Jan 16 23:25:11 NOVT 2013 x86_64 GNU/Linux
Kernel config: ... - 04:29 AM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- I'm sorry if I missed it, but can you tell me the version
of the kernel you are working with? Running "uname -a"
m... - 11:51 AM rbd Bug #3664: osdc/ObjectCacher.cc: 517: FAILED assert(!i->size())
- recent log: ubuntu@teuthology:/a/teuthology-2013-02-09_20:00:03-regression-bobtail-master-basic/3977...
- 11:30 AM rbd Feature #2770 (In Progress): krbd: define tasks to add osd_client compound class op support
- At our sprint planning meeting we discussed this. The task
was too large and unknown to provide a meaningful estima... - 11:17 AM Bug #2947 (In Progress): osd: out of order reply
- recent logs: ubuntu@teuthology:/a/teuthology-2013-02-10_01:00:02-regression-master-testing-gcov/4134...
- 11:08 AM rbd Bug #4033 (Resolved): krbd: add barriers near done flag operations
- I just committed this to the ceph-client/testing branch:
commit 4ad2b189c1a52ce8ae1d6d2528c512021a2f1654
Author: ... - 11:08 AM rbd Bug #4010 (Resolved): krbd: turn off interrupts for open/remove locking
- I just committed this to the ceph-client/testing branch.
commit 4cfc31e59fc6521ee0950782a028eccb3f5c9096
Author: ... - 10:49 AM CephFS Feature #4073: qa: add message delay injection to test suite
- I'm rewording the title, because its similar to #3570, which has tests already in the marginal suite. The purpose of...
- 10:00 AM CephFS Feature #4073 (Resolved): qa: add message delay injection to test suite
- 10:38 AM Revision 69552ff0 (ceph): test_mon_workloadgen.cc: fix -Wgnu
- Fix warning from clang(++):
test/mon/test_mon_workloadgen.cc:311:23: warning: in-class
initializer for static data... - 10:38 AM Revision d6b205f1 (ceph): librados/librados.cc: fix implicitly-defined namespace 'std'
- Fix warning from clang(++):
librados/librados.cc:15:17: warning: using directive refers to
implicitly-defined names... - 10:38 AM Revision d427d982 (ceph): src/msg/msg_types.h: pass function parameter by reference
- Fix "Function parameter 'm' should be passed by reference." from cppchecker.
Signed-off-by: Danny Al-Gaaf <danny.al-... - 10:38 AM Revision 3b77687c (ceph): common/AsyncReserver.h: use empty() instead of size()
- Fix warning for usage of queue.size() in do_queues(). Use empty()
since it should be prefered as it has, following th... - 10:38 AM Revision 69867072 (ceph): common/WorkQueue.h: use empty() instead of size()
- Fix warning for usage of out->size() in _void_dequeue(). Use empty()
since it should be prefered as it has, following... - 10:38 AM Revision aad71dfd (ceph): src/log/Entry.h: pass function parameter by reference
- Fix "(performance) Function parameter 's' should be passed by reference."
from cppchecker.
Signed-off-by: Danny Al-G... - 10:38 AM Revision 72ff8061 (ceph): src/mon/PGMonitor.cc: remove unused variable
- Remove unused variable to fix:
mon/PGMonitor.cc:170:11: warning: unused variable 'now'
[-Wunused-variable]
Signed... - 10:38 AM Revision 99f21750 (ceph): src/msg/Messenger.h: pass function parameter by reference
- Fix "(performance) Function parameter 'm' should be passed by reference."
from cppchecker.
Signed-off-by: Danny Al-G... - 10:38 AM Revision 76798eab (ceph): src/osd/OSD.h: use empty() instead of size()
- Fix warning for usage of *.size(). Use empty() since it should be
prefered as it has, following the standard, a const... - 10:38 AM Revision 1f0fd504 (ceph): src/osd/PG.h: use empty() instead of size()
- Fix warning for usage of objects.size(). Use empty() since it
should be prefered as it has, following the standard, a... - 10:38 AM Revision 79c95a65 (ceph): common/config.h: declaration of config_option as struct
- Change declaration of config_option from 'class' to 'struct' since
it's defined as struct and used this way (access m... - 10:35 AM CephFS Bug #4068 (Closed): libcephfs: if client->init() fails, shutdown() erroneously calls client->shut...
- Commit 133295ed001a950e3296f4e88a916ab2405be0cc resolves this issue. The failure case no longer throws an assert but ...
- 10:00 AM CephFS Bug #4068: libcephfs: if client->init() fails, shutdown() erroneously calls client->shutdown(), r...
- Reviewed by Sage and Slang.
- 09:34 AM CephFS Bug #4068 (Fix Under Review): libcephfs: if client->init() fails, shutdown() erroneously calls cl...
- Josh - can you please review Joe's wip branch?
- 10:35 AM Feature #4076: ceph-disk-prepare/activate: basic dm-crypt support
- Initial implementation will:
- keep keys in /etc/ceph somewhere (/etc/ceph/disk-keys/* ?
- identify keys by GPT... - 10:33 AM Feature #4076 (Resolved): ceph-disk-prepare/activate: basic dm-crypt support
- 10:25 AM Feature #4075 (Resolved): osd: move pg log into leveldb
- 10:01 AM CephFS Feature #4074 (Resolved): qa: add traceless reply test to fs suite
- 09:48 AM CephFS Feature #4002 (In Progress): mds: design fsck
- 09:39 AM Bug #4051 (Duplicate): osd: inconsistent snapcolls on argonaut
- 09:38 AM CephFS Bug #4035 (Need More Info): Ceph doesn't recover from fault on Opensuse (cfuse tests & rbd-cli te...
- the fault message itself is nothing to worry about; just a socket error that we normally recover from. can you clari...
- 09:36 AM Bug #4052: OSD High memory usage (8-12GB) right after start
- Just to clarify: please try the latest bobtail branch. Ignore wip_bobtail_f. Thanks!
- 09:36 AM Bug #4059 (Duplicate): osd: ENOTEMPTY unhandled for remove op
- 09:04 AM Bug #3979 (Rejected): Ceph 0.56.2 RPM does not install
- Pretty weird! I wonder if the permissions/mode on /etc/ceph are what RPM expects if it would skip the chown entirely...
- 08:55 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Got bored; I took an strace of this. Looks like it's failing tying to chown /etc/ceph:
5589 chown("/etc/ceph", 0... - 08:03 AM rgw Feature #4072: Allow binding on a tcp port
- here is my pull request:
https://github.com/ceph/ceph/pull/46 - 08:01 AM rgw Feature #4072 (Resolved): Allow binding on a tcp port
- For the moment, rgw can only bind on an unix socket.
It's very good for performance when using a local apache2.
I... - 07:41 AM Bug #4070 (Resolved): memory leak
- commit:749218f155969fd87a6194b26acd00a9332d522d
- 02:08 AM Revision 778c45cd (ceph): Merge pull request #44 from dachary/wip-4070
- buffer::ptr self assignment bug + patch
Reviewed-by: Sage Weil <sage@inktank.com> - 02:04 AM Revision 29195745 (ceph): Merge remote-tracking branch 'danny/wip-da-sca-memleaks'
- Reviewed-by: Sage Weil <sage@inktank.com>
02/10/2013
- 11:56 PM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- eth1 and ib0 connected to ceph cloud.
- 11:53 PM rbd Bug #3936: rbd: Strange dd speed behaviour (server side issue?)
- Ifstat output looks like:...
- 10:16 PM Bug #3955 (In Progress): Configure should explicity check for c++ compiler.
- 10:15 PM Bug #4030 (Resolved): Missing Fedora 18 release packages
- The fedora18 gitbuilder has been updated to the released version, packages for daily builds can be found on gitbuilde...
- 07:52 PM Revision f213669f (ceph): .gitignore: cleanup and sort entries
- Cleanup old entries and sort the existing entries. Remove no longer
existing entries/files. Move some entries from to... - 06:00 PM Revision 125cb719 (ceph): ceph-test.install: updated filelist
- Add some files which are part of the ceph-test package on RPM based
distributions already: ceph_test_mon_workloadgen,... - 05:56 PM Revision 6cecdd86 (ceph): spec/debian: don't install rest-bench twice
- Don't install rest-bench in ceph.spec.in section for ceph-test and
ceph-test.install twice. This file is already part... - 05:33 PM Revision 7b89ee66 (ceph): ceph-test: give binaries from ceph-test package useful names
- The files from the ceph-test subpackage are installed to /usr/bin,
give them more useful names to make sure that the ... - 05:04 PM Bug #4071 (Fix Under Review): osd: snap coll not created on scrub trim repop
- wip-4071
- 11:32 AM Bug #4071 (Resolved): osd: snap coll not created on scrub trim repop
- on replica:...
- 02:32 PM Revision 749218f1 (ceph): buffer::ptr self assignment bug + patch
- After
buffer::ptr a(1);
a = a;
a call to a.get_raw() will return a null pointer and there will be
no pointer refere... - 09:27 AM Bug #4069 (Resolved): OSD crashed and failed to start again
- This issue was fixed in commit:3293b31b44c9adad2b5e37da9d5342a6e4b72ade, released in v0.56.2. There were some other ...
- 03:48 AM Bug #4069: OSD crashed and failed to start again
- Removed and formatted again to XFS and started well but a lot of data should be replicated from other OSDs.
- 02:33 AM Bug #4069 (Resolved): OSD crashed and failed to start again
- I was using 0.56 and found that all the OSDs on one host is down. When I tried to restart I got nothing successful, b...
- 09:05 AM Revision d48cc789 (ceph): rgw/rgw_xml.cc: fix realloc memory leak in error case
- Fix error from cppcheck:
[src/rgw/rgw_xml.cc:212]: (error) Common realloc mistake: 'buf'
nulled but not freed upon... - 09:05 AM Revision e6591db6 (ceph): wireshark: fix some memory leaks
- Fix some memory leaks in packet-ceph.c. Error from cppcheck was:
[wireshark/ceph/packet-ceph.c:215]: (error) Memory ... - 09:05 AM Revision f0ba8075 (ceph): SyntheticClient.cc: fix some memory leaks in the error handling
- Fix some memory leaks in case of error handling due to failed
client->open() calls.
Error from cppcheck was:
[src/cl... - 09:05 AM Revision 89df090e (ceph): rgw/rgw_rest.cc: fix 4K memory leak
- Fix 4K memory leak in case RGWClientIO::read() fails in
read_all_chunked_input().
Error from cppcheck was:
Checking ... - 09:05 AM Revision f26f1470 (ceph): common/fiemap.cc: fix realloc memory leak
- Fix error from cppcheck:
[src/common/fiemap.cc:73]: (error) Common realloc mistake: 'fiemap'
nulled but not freed ... - 09:05 AM Revision c92a0f55 (ceph): os/FileStore.cc: fix realloc memory leak in error case
- Fix error from cppcheck:
[src/os/FileStore.cc:512]: (error) Common realloc mistake: 'fiemap'
nulled but not freed ... - 06:37 AM Bug #4070: memory leak
- Here is the proposed fix https://github.com/ceph/ceph/pull/44
- 06:29 AM Bug #4070 (Resolved): memory leak
- The "assignment operator of buffer::ptr":https://github.com/ceph/ceph/blob/master/src/common/buffer.cc#L286 leaks whe...
- 06:19 AM Tasks #4066: unit tests for src/include/buffer.h
- https://github.com/ceph/ceph/pull/41
- 05:00 AM Revision 4d054e2e (ceph): qa: fix iogen script
- Wait 10 minutes and then stop.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 75c40fac603a3d... - 04:41 AM Revision 2c6afa05 (ceph): test_libcephfs: fix xattr test
- Ignore the ceph.*.layout xattrs.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit b0d4dd21c7be... - 04:40 AM Revision 41537d4d (ceph): osd: do not spam system log on successful read_log
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1948a02bc888fadafc29cf2e6f0a92129c68fd4c) - 02:58 AM Revision abc80ffc (ceph): java: make CephMountTest use user.* xattr names
- Changes to the xattr code in Ceph require
a few tweaks to existing test cases.
Specifically, there is now a ceph.file...
02/09/2013
- 09:36 PM Revision c31aff5f (ceph): rgw: plain format always appends eol to data
- Beforehand we just prepended the eol to the next line, so that
the last line also gets eol.
Signed-off-by: Yehuda Sa... - 09:35 PM Revision 3e4d79fe (ceph): rgw: change json formatting for swift list container
- Fixes: #4048
There is some difference in the way swift formats the
xml output and the json output for list container.... - 09:22 PM Bug #4064: osd: filestore assert on FORREMOVAL_* collection removal
- this was the job:...
- 09:15 PM Bug #4064: osd: filestore assert on FORREMOVAL_* collection removal
- Related (i think) crash, on latest next:...
- 09:11 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- quick update: chasing a relate issue, hold off on upgrading a bit longer.
- 06:51 PM CephFS Bug #4068: libcephfs: if client->init() fails, shutdown() erroneously calls client->shutdown(), r...
- branch wip-4068-buck has one possible fix for this issue (but maybe not the cleanest option).
- 06:27 PM CephFS Bug #4068: libcephfs: if client->init() fails, shutdown() erroneously calls client->shutdown(), r...
- title should be "erroneously calls" and not the inverse.
- 06:24 PM CephFS Bug #4068 (Closed): libcephfs: if client->init() fails, shutdown() erroneously calls client->shut...
- In src/libcephfs.cc mount() function:
if the client->init() call fails, shutdown() gets called. Assuming that the ... - 05:41 PM Revision 6d199e22 (ceph): Merge branch 'next'
- 05:40 PM Revision b19b6dce (ceph): osd: fix load_pgs collection handling
- On a _TEMP pg, is_pg() would succeed, which meant we weren't actually
hitting the cleanup checks. Instead, restructu... - 05:40 PM Revision 1f80a0b5 (ceph): osd: fix load_pgs handling of pg dirs without a head
- If there is a pgid that passes coll_t::is_pg() but there is no head, we
will populate the pgs map but then fail later... - 05:40 PM Revision ead68b47 (ceph): Merge branch 'next'
- Conflicts:
src/mon/PGMonitor.h - 05:37 PM Revision 073f58ed (ceph): OSD::load_pgs: first scan colls before initing PGs
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 04:36 PM Bug #4067: Argonaut fails to build on fedora18
- Argonaut for new users is a low priority.. As long as bobtail and master are working we can focus elsewhere.
- 12:08 PM Bug #4067 (Won't Fix): Argonaut fails to build on fedora18
- The fedora18 argonaut build fails on a reference to boost-system. This is likely an issue with configure finding out...
- 05:47 AM Revision 0d68f3a8 (ceph): test/crypto: fix narrowing conversion warning
- warning: test/crypto.cc:49:3: narrowing conversion of ‘136’ from ‘int’ to ‘char’ inside { } is ill-formed in C++11 [-...
- 05:09 AM Revision 20255d98 (ceph): doc: update commands for fetching release PGP keys
- Use https to ceph.com. The gitweb URLs aren't as pretty, but our
cert is at least valid!
Signed-off-by: Sage Weil <... - 04:26 AM Feature #3850 (Closed): Add json output for ceph pg dump and ceph osd tree
- This has been idle for about a month now. Previous update gives insight on the ticket's request. Feel free to reopen ...
- 01:28 AM Tasks #4066 (Resolved): unit tests for src/include/buffer.h
- The "tests":https://github.com/ceph/ceph/blob/fadb5ae75ab70f55ce039113c856d09cf20699cb/src/test/bufferlist.cc for "bu...
02/08/2013
- 11:38 PM Bug #4065 (Can't reproduce): Crash of 0.56.2 OSD on Ubuntu 12.04 LTS
- Hi.
I am new to this and new to ceph. So please bear with me...
I tried to setup a ceph cluster here at home to t... - 11:33 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- Simon Frerichs wrote:
> Hi Sage,
>
> i checked two osds one start with this branch each and they crashed.
> I'll... - 11:30 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- Hi Sage,
i checked two osds one start with this branch each and they crashed.
I'll do another check later. Our cl... - 11:20 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- Hi Simon-
Is the osd crashing on startup *every* time? From the trace it looks like there is an invalid xattr set... - 05:13 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- i'll add an heap dump soon.
i just restarted another osd with wip_bobtail_f, also crashing:... - 02:22 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- hi Josh, burnupi57 running on wip-f branch might help.
we have this running from last week for the memory leak testing. - 02:01 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- Yeah, if you can still reproduce it, a heap profile of an osd that's using excessive memory would be great....
- 01:42 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- Josh Durgin wrote:
> I haven't been able to reproduce this locally.
do you need more information / log output? - 01:39 PM Bug #4052: OSD High memory usage (8-12GB) right after start
- I haven't been able to reproduce this locally.
- 02:00 AM Bug #4052: OSD High memory usage (8-12GB) right after start
- ...
- 01:50 AM Bug #4052: OSD High memory usage (8-12GB) right after start
- as requested current cluster status:
2013-02-08 10:48:40.125733 mon.0 [INF] pgmap v25369962: 2112 pgs: 1460 acti... - 01:43 AM Bug #4052 (Can't reproduce): OSD High memory usage (8-12GB) right after start
- Hi,
some of our osds need 8-12GB RAM right after startup.
Sage mentioned wip_bobtail_f might fix it but this bra... - 09:58 PM Revision e7bc4b8d (ceph): mds: cap_reconnect_t uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:58 PM Revision f1e08e6c (ceph): mds: add ENCODING to the incompat set
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:58 PM Revision d414875a (ceph): mds: remove very dead commented-out code
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:58 PM Revision 77612336 (ceph): mds: enable SnapInfo, snaplink_t, sr_t dencoder usage
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:51 PM Bug #4064: osd: filestore assert on FORREMOVAL_* collection removal
- ...
- 09:50 PM Bug #4064 (Resolved): osd: filestore assert on FORREMOVAL_* collection removal
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2013-02-08_12:11:07-rados-master-testing-basic/2870$ ...
- 09:27 PM Revision 38dd59ba (ceph): doc: Removed unnecessary/contradictory options.
- fixes: #4058
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 09:18 PM Revision 19c94666 (ceph): doc: Fixed order of option.
- fixes: #4046
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 09:17 PM Revision d557bcfb (ceph): mds: ESubtreeMap more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision d727b129 (ceph): mds: ETableClient event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision f82dce8d (ceph): mds: ETableClient more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision ac8f25c0 (ceph): mds: ETableServer event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 8f75db34 (ceph): mds: ETableServer more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 05461e8d (ceph): mds: EUpdate event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 3fb1b219 (ceph): mds: EUpdate more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 4123d011 (ceph): mds: use modern encoding for LogEvent
- It's a pretty simple encoding, but if we ever want to encode more than
the event type and the event itself we'll be g... - 09:17 PM Revision 6a6f75e8 (ceph): mds: inode_load_vec_t now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 5c812213 (ceph): mds: dirfrag_load_vec_t now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 7cbae702 (ceph): mds: mds_load_t now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 07b24cf2 (ceph): mds: SessionMap now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision de9c1a15 (ceph): MDS: EMetaBlob more modernization for encoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision a1ed7418 (ceph): mds: EOpen event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 5db5433e (ceph): mds: EResetJournal event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision b578ef27 (ceph): mds: EResetJournal modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 3f469baa (ceph): mds: ESession event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 709ff3d7 (ceph): mds: ESession more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 8e8ecb47 (ceph): mds: ESessions now uses modern encoding
- To facilitate this (since it had no versioning previously), it
gets a new encoding number and LogEvent::decode() sets... - 09:17 PM Revision 3cea0ca7 (ceph): mds: ESessions more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision a64153f9 (ceph): mds: ESlaveUpdate event now uses modern encoding everywhere
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 637e99fd (ceph): mds: link_rollback more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 85c67fe8 (ceph): mds: rmdir_rollback more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 70bc6afa (ceph): mds: rename_rollback more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 1842f461 (ceph): mds: ESlaveUpdate more modernization for dencoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 7998524d (ceph): mds: ESubtreeMap event now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 8906ae9a (ceph): mds: remove unused EString event
- While we're at it, #include LogEvent.h from each of
the log events, some of which didn't include it previously!
Sign... - 09:17 PM Revision b079733b (ceph): mds: EFragment event uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision a25683f3 (ceph): mds: EImportFinish event uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 83c1a3c4 (ceph): mds: EImportStart event uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 60730271 (ceph): mds: EMetaBlob and its sub-parts use modern encoding now
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision deb0d45c (ceph): mds: EMetaBlob::full_bit more modernization for dencoder
- While we're doing so, make the frag stream operator const!
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision 09a2d66e (ceph): mds: EMetaBlob::remotebit more modernization for dencoder
- And set defaults for the default constructor.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision 196313b4 (ceph): mds: EMetaBlob::nullbit modernization for dencoder
- And set defaults in the default constructor.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision 821b74e9 (ceph): MDS: EMetaBlob::dirlump more modernization for encoder
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 0fe7a086 (ceph): mds: old_rstat_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision d5a6a251 (ceph): DecayCounter: use modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision 95cee97e (ceph): AnchorServer: use modern encoding for server state
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision d8a7b876 (ceph): CInode: use modern encoding for encode_store
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision eb060bb4 (ceph): CInode: use modern encoding for encode_export/decode_import
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 6e797e00 (ceph): InoTable: use modern encoding for encode_state and decode_state
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision 7bad5078 (ceph): SnapServer: use modern encoding for server_state
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision d21de810 (ceph): mds: ECommitted now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:17 PM Revision f886f31e (ceph): mds: EExport event uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 PM Revision ff63530d (ceph): mds: Capability (and sub-structs) now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 06:04 PM Revision f11beb95 (ceph): radosgw-admin: fix cli test
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1b05b0edbac09d1d7cf0da2e536829df05e48573) - 05:59 PM Revision 3cf3710b (ceph): mon: fix typo in C_Stats
- Broken by previous commit.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:21 PM CephFS Bug #4060: mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- Also, I've tested this fix with a basic script:
set -e
mnt=$1
touch ${mnt}/foo.$$
rados mkpool foo.$$
poolid=$... - 05:20 PM CephFS Bug #4060 (Fix Under Review): mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- Pushed a proposed fix to wip-4060. Needs review.
- 03:18 PM CephFS Bug #4060 (In Progress): mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- Even with add_data_pool I get EINVAL, so I'm reopening this. I've verified that (as before), the osdmap on the mds ...
- 02:57 PM CephFS Bug #4060 (Rejected): mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- You need to add it to the MDSMap first ("ceph mds add datapool [x]" or something), and the server does at least wait ...
- 02:53 PM CephFS Bug #4060 (Resolved): mds: vxattr ceph.file.layout.pool doesn't check latest osdmap
- touch foo
create pool d2
setfattr -n ceph.file.layout.pool -v d2 foo
> returns EINVAL
The problem is that the p... - 05:19 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- the bit that looks fishy here is m_flush_mutex.__nusers. can you see what that thread is doing in gdb?
maybe it's... - 04:58 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- ...
- 04:55 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- A log dump shows nothing, so I'm guessing the log is corrupted such that it keeps logging to more and more memory wit...
- 04:49 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- Something like that (or some kind of bug in the logging system that only gets hit with syslog or when not logging) wo...
- 04:48 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- Oh, how interesting...I wonder if this is syslog not having enough network bandwidth? Or (in the more general sense) ...
- 04:45 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- On wip-f, one osd grew to consume 70% of ram. The heap profiler tells us:...
- 06:16 AM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- I've also started to see this and will try to get some heap profiling done to report back.
* ceph version 0.56.1 (... - 05:18 PM Revision 2bdf753d (ceph): mon: assert valid context return values
- We recognized EAGAIN, ECANCELED, and success only.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Lui... - 05:18 PM Revision 3322e96b (ceph): Merge branch 'next'
- 05:09 PM Revision 4837063d (ceph): mon: retry PGStats message on EAGAIN
- If we get EAGAIN from a paxos restart/election/whatever, we should
restart the message instead of just blindly acking... - 05:09 PM Revision 17827769 (ceph): mon: handle -EAGAIN in completion contexts
- We can get ECANCELED, EAGAIN, or success out of the completion contexts,
but in the EAGAIN case (meaning there was an... - 05:08 PM Bug #4006: osd: repeating 'wrong node' message in log
- I am also seeing this message in the radosgw.log file for .56-623. The error appears when restarting rgw and again d...
- 05:08 PM Bug #4063 (Duplicate): filer: probe crash on wip-bobtail-osd-msgr branch
- 05:02 PM Bug #4063: filer: probe crash on wip-bobtail-osd-msgr branch
- restarting the mds/all daemons in the cluster does not help, still hitting the same issue again.
leaving the clust... - 04:56 PM Bug #4063: filer: probe crash on wip-bobtail-osd-msgr branch
- repasting the core dump...
- 04:56 PM Bug #4063 (Duplicate): filer: probe crash on wip-bobtail-osd-msgr branch
- ceph version 0.56.2-15-g2ebf4d0 [wip-bobtail-osd-msgr]
test set up: burnupi06, burnupi07
hit this when running ... - 03:47 PM devops Feature #4062 (Rejected): Add data collection to the gitbuilders
- Need to track how long the builds are taking.
- 03:42 PM CephFS Bug #4061 (Can't reproduce): mds crashed at LogEvent::decode
- hit this on burnupi60, when upgrading from ceph v0.56-598-gb970d05 to 0.56.2-12-gcc16791 on 4 feb and it seems to be ...
- 01:58 PM CephFS Bug #4044 (Rejected): replay failure between MDS and client
- Never mind, this turned out to be another encoding issue. Phew!
- 01:28 PM Documentation #3432 (In Progress): move explanation for rbd on libvirt to new docs
- 01:27 PM Documentation #4058 (Resolved): fstab documentation has invalid or misleading options
- Removed extraneous/contradictory options, committed and pushed. Fix should be up shortly.
- 11:26 AM Documentation #4058 (Resolved): fstab documentation has invalid or misleading options
- http://ceph.com/docs/master/cephfs/fstab/ states "the Ceph file system will mount automatically on startup". However...
- 01:22 PM CephFS Feature #3543: mds: new encoding
- Okay, that was an easy bug to fix. Hurray!
(The LogEvent encoding was off a little bit.)
Running it through anoth... - 01:17 PM Documentation #4046 (Resolved): Typo in ceph.com docs webpage
- Fixed and checked in. Should appear shortly.
- 01:12 PM Bug #4059 (Duplicate): osd: ENOTEMPTY unhandled for remove op
- This occurred on wip_bobtail_f in a local vstart 11-osd cluster which I was trying to use to reproduce #4052 by causi...
- 11:19 AM rgw Cleanup #4057 (New): Update Admin API spec with comments
- Incorporate received comments into admin API specification
- 09:54 AM Bug #3895: librados test hang during mon thrashing
- commit:17827769f1fe6d7c4838253fcec3b3a4ad288f41
- 09:20 AM Bug #3895 (Resolved): librados test hang during mon thrashing
- 09:05 AM Bug #3895: librados test hang during mon thrashing
- wip-mon-eagain looks good
- 09:36 AM Bug #4043: osd: validate/scrub collections
- 09:22 AM rgw Feature #3973 (New): rgw: Handle requests sent in non-UTC time
- Moved to a feature for possible future consideration.
- 01:18 AM rgw Feature #3973: rgw: Handle requests sent in non-UTC time
- Yehuda, i admit that i looks like the client is sending the wrong date, although it would be nice if radosgw could co...
- 09:07 AM Linux kernel client Bug #3997 (Resolved): xfs: insert memory barriers before wake_up_bit()
- Our work is done! Thanks!
- 09:03 AM Linux kernel client Bug #3997: xfs: insert memory barriers before wake_up_bit()
- Ben has committed my fix to the upstream XFS tree.
I'm not sure when it will hit Linus' tree, but I
think we can ca... - 08:36 AM rbd Cleanup #4053: ceph: cleanup ceph page vector functions
- Apparently for cleanup there is no "need review" so I'm
marking this "Feedback". I've posted a series of patches
t... - 08:30 AM rbd Cleanup #4053 (Resolved): ceph: cleanup ceph page vector functions
- This is just documenting some cleanup activity I've done
that I'm about to post for review.
- delete bogus (re)decl... - 08:21 AM rbd Subtask #4007 (Fix Under Review): libceph: support STAT osd operation
- A patch implementing this has been posted to the
ceph-devel mailing list for review.
[PATCH] libceph: allow STAT ... - 07:25 AM Revision ec1085e5 (ceph): Merge remote-tracking branch 'gh/wip-bobtail-vxattrs' into bobtail
- 07:25 AM Revision 66d77585 (ceph): mon: enforce reweight be between 0..1
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com>
(cherry picked from commit... - 07:24 AM Revision 8bab3a1c (ceph): PG: dirty_info on handle_activate_map
- We need to make sure the pg epoch is persisted during
activate_map.
Backport: bobtail
Reviewed-by: Sage Weil <sage@i... - 07:24 AM Revision dffa386b (ceph): osd: flush peering queue (consume maps) prior to boot
- If the osd itself is behind on many maps during boot, it will get more and
(as part of that) flush the peering wq to ... - 07:20 AM Revision 5a02d6de (ceph): Merge branch 'next'
- 06:51 AM Revision 1b05b0ed (ceph): radosgw-admin: fix cli test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:31 AM Revision 2eaa7281 (ceph): keys: renew autobuild.asc key
- This expired today. Change it to never expire, like the Ubuntu release
keys.
Signed-off-by: Sage Weil <sage@inktank... - 06:19 AM Revision f3ba46d3 (ceph): Merge remote-tracking branch 'gh/next'
- 01:16 AM Revision 8a2de334 (ceph): Merge remote-tracking branch 'origin/master' into wip-2941-3
- 12:59 AM Revision 278dfe50 (ceph): rgw: stream get_obj operation
- Fixes: #2941
Instead of iterating through the parts one by one when reading
an object, we can now send multiple reque... - 12:59 AM Revision 3383618d (ceph): throttle: optional non perf counter mode
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:34 AM Revision a56eb88c (ceph): Merge to include --machine-type and changes to --summary
- Added the ability to support multiple types of machines with
--machine-type added to teuthology-lock when used with -... - 12:16 AM Revision ed2bb387 (ceph): OSD: check pg snap collections on start up
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:16 AM Revision 55f85796 (ceph): OSD::load_pgs: first scan colls before initing PGs
- Backport: bobtail
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 12:06 AM Revision 75d86e47 (ceph): Made teuthology-lock --summary machine type aware.
- Signed-off-by: Sandon Van Ness <sandon@van-ness.com>
02/07/2013
- 11:38 PM Bug #4051 (Duplicate): osd: inconsistent snapcolls on argonaut
- latest run:...
- 11:04 PM Bug #3895 (Fix Under Review): librados test hang during mon thrashing
- tracked this down; see wip-mon-eagain
qa run against rados api tests seems to confirm that this fixes it (previous... - 01:07 PM Bug #3895: librados test hang during mon thrashing
- Attached mon logs from a recent run after the rados test seemed to hang for a big (100 mon elections or so). The log...
- 12:49 PM Bug #3895: librados test hang during mon thrashing
- Attached log files for this from hung runs (librados and kernel untar).
- 10:54 PM Revision f6af1e76 (ceph): rgw: fix bucket_owner assignment
- s->bucket_acl may be null, so reverting to old behavior.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 10:54 PM Revision 70532d19 (ceph): rgw: get bucket_owner from policy
- We already read the bucket policy, we can get the bucket
owner from there.
Signed-off-by: Yehuda Sadeh <yehuda@inkta... - 10:54 PM Revision e345dfe0 (ceph): Feature 3667: Support extra canned acls.
- Support the bucket-owner-read and bucket-owner-full
canned acls.
Signed-off-by caleb miles <caleb.miles@inktank.com>... - 10:27 PM Revision fa47e77a (ceph): ReplicatedPG: check store for temp collection in have_temp_coll
- We may not have "created" the temp collection since OSD restart
before removing the PG. have_temp_coll must also loo... - 09:55 PM Revision a18045f0 (ceph): rgw: a tool to fix clobbered bucket info in user's bucket list
- This fixes bad entries in user's bucket list that may have occured
due to issue #4039. Syntax:
$ radosgw-admin user... - 09:55 PM Revision a00c77ab (ceph): rgw: bucket recreation should not clobber bucket info
- Fixes: #4039
User's list of buckets is getting modified even if bucket already
exists. This fix removes the newly cre... - 09:53 PM Revision 47c9f46a (ceph): rgw: a tool to fix clobbered bucket info in user's bucket list
- This fixes bad entries in user's bucket list that may have occured
due to issue #4039. Syntax:
$ radosgw-admin user... - 09:53 PM Revision 6c8d6381 (ceph): rgw: bucket recreation should not clobber bucket info
- Fixes: #4039
User's list of buckets is getting modified even if bucket already
exists. This fix removes the newly cre... - 09:48 PM Bug #4050 (Resolved): recovery assert failure, osd/PG.cc: 6255: FAILED assert(query.query.type ==...
- 2013-02-07 20:58:49.461754 7f518f18c700 -1 osd/PG.cc: In function 'boost::statechart::result PG::RecoveryState::Repli...
- 09:26 PM Revision 030bc7c2 (ceph): Added support for multiple types of machines.
- Added the ability to support multiple types of machines with
--machine-type added to teuthology-lock when used with -... - 09:26 PM Revision 9cb6c33f (ceph): rgw: a tool to fix clobbered bucket info in user's bucket list
- This fixes bad entries in user's bucket list that may have occured
due to issue #4039. Syntax:
$ radosgw-admin user... - 09:25 PM Revision 9d006ec4 (ceph): rgw: bucket recreation should not clobber bucket info
- Fixes: #4039
User's list of buckets is getting modified even if bucket already
exists. This fix removes the newly cre... - 09:09 PM Revision 78454794 (ceph): Merge branch 'wip-cephtool' into next
- Usage/errmsg fixups for the ceph CLI tool
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:06 PM Revision 36cf4d0c (ceph): ceph: fix 'pg' error message to direct user toward better input
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:06 PM Revision 73872e71 (ceph): ceph: use "config set" consistently in help/error msgs
- apparently it was once known as set_config. Fix up everything to
refer to the new name. Also, fix up the help messa... - 09:06 PM Revision eb9d6cac (ceph): osd: fix name of setomapval admin-daemon command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 09:06 PM Revision c44846e0 (ceph): ceph: ceph mon delete doesn't exist; ceph mon remove is the command
- Fix up cli test as well (doc is already correct)
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 09:06 PM Revision 1042060f (ceph): mds: error messages for export_dir said 'migrate_dir'
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:31 PM Feature #3891 (Fix Under Review): osd: move purged_snaps out of info
- 07:47 PM Revision 5896b971 (ceph): modified the script to run on both argonaut and bobtail.
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:44 PM Revision dbce1d0d (ceph): PG: dirty_info on handle_activate_map
- We need to make sure the pg epoch is persisted during
activate_map.
Backport: bobtail
Reviewed-by: Sage Weil <sage@i... - 06:25 PM Revision 94323535 (ceph): mds: rename mds_traceless_replies to mds_inject_traceless_reply_probabi...
- Sage pointed out we should try for consistent naming on these debug
options, and this option is like our other inject... - 06:21 PM Revision af95d934 (ceph): osd: flush peering queue (consume maps) prior to boot
- If the osd itself is behind on many maps during boot, it will get more and
(as part of that) flush the peering wq to ... - 06:10 PM Documentation #3432: move explanation for rbd on libvirt to new docs
- The secondary issue is only without cephx, it's true, but the bigger issue of "we *really*
need this documentation i... - 06:08 PM Documentation #4049 (Resolved): public/cluster network doc should mention that multiple subnets a...
- public network and cluster network allow comma-separated (at least) lists of subnets. It is of course assumed
that ... - 05:16 PM rgw Feature #2941 (Resolved): rgw: improve streaming read performance
- Merged, commit:8a2de334fed5c56919063bba8c60a3c73bd6534c
- 05:11 PM rgw Bug #4048 (Resolved): API mismatch between RGW and Swift
- As discussed with Yehuda, when using RadosGW with a delimiter:
curl -H 'x-auth-token: 909e3793e499425fb90364738107da... - 05:08 PM rbd Bug #4047 (Resolved): removing a non-existing rbd image logs error in osd logs
- when removing a non-existing rbd image floods osd logs even when the debug is turned off. This can be avoided.
ubu... - 04:31 PM Documentation #4046 (Resolved): Typo in ceph.com docs webpage
- In this section:
http://ceph.com/docs/master/rados/operations/operating/#stopping-a-cluster
the example command:... - 04:22 PM rbd Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
- ceph version 0.56.2-7-gc3468f7 (c3468f76a5e68a6426f03e508d8ecf26950fca2a)
Trying to unprotect a snapshot, that is ... - 04:09 PM Feature #3982 (Resolved): Performance tests on branches that change the way pg info is stored
- 02:54 PM rgw Feature #3667 (Resolved): rgw: support extra canned acl params
- Merged commit:e345dfe04a64fcd0d37c9e0717b6714038c302ae
- 02:14 PM CephFS Bug #4044 (Rejected): replay failure between MDS and client
- While testing #3543 (but that shouldn't be related to this issue), I restarted the MDS and ran into a case where the ...
- 02:11 PM CephFS Feature #3543: mds: new encoding
- 3Still haven't gotten in on teuthology (soon!), but I did some local upgrade testing. I was able to upgrade from mast...
- 01:58 PM Bug #4042: osd crash in recovery state: FAILED assert(0 == "we got a bad state machine event")
- Nope. I've looked at it when reporting this issue, but I couldn't find a core file. I'd expected one to be in /, but ...
- 01:51 PM Bug #4042 (Need More Info): osd crash in recovery state: FAILED assert(0 == "we got a bad state m...
- Hey Wido- Do you have have the core by chance?
- 08:40 AM Bug #4042 (Resolved): osd crash in recovery state: FAILED assert(0 == "we got a bad state machine...
- I just rebooted a couple of my 0.56.2 nodes and out of 12 OSDs one went down with:...
- 01:55 PM rgw Bug #4039 (Resolved): rgw: bucket info discrepencies
- Fixed, commit:9d006ec40ced9d97b590ee07ca9171f0c9bec6e9.
Recovery tool, commit:9cb6c33f0e2281b66cc690a28e08459f2e62ca... - 11:06 AM rgw Bug #4039 (In Progress): rgw: bucket info discrepencies
- 01:49 PM rbd Bug #4003 (Resolved): rbd: EBUSY errors from rbd unmap
- closing this. phew!
- 01:45 PM Bug #4043 (Resolved): osd: validate/scrub collections
- check that existent collections is correct.
one option is to just do this during startup (along with some optional... - 11:23 AM Bug #4036: init-ceph: assumes write access to /var/run/ceph
- I was mistaken about vstart clusters; it's restarting them just fine. Changed the bug description to more correctly d...
- 10:09 AM CephFS Cleanup #1499: mds: clean up directory layouts
- I've rebased on top of the wip-mds-encode-rebased branch as wip-1499-mds-layouts, although I notice it's failing some...
- 10:09 AM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- I've been totally unable to come up with a scenario for how this could happen via code inspection, so I think I'm jus...
- 09:54 AM Bug #3995: OSD heartbeat-crashes during startup
- All right, I'll try to confirm if I see the problem again.
Thank you. - 09:47 AM Bug #3995 (Resolved): OSD heartbeat-crashes during startup
- Artem Grinblat wrote:
> Sage, no, as I've said in comment #1, after a couple of restarts the OSD returned to normal.... - 09:43 AM Bug #3995: OSD heartbeat-crashes during startup
- Sage, no, as I've said in comment #1, after a couple of restarts the OSD returned to normal.
- 09:39 AM Bug #3995 (Need More Info): OSD heartbeat-crashes during startup
- Artem, does it do this on every startup? Can you test wip_bobtail_f and see if it resolves the problem?
Thanks! - 09:52 AM rgw Feature #3973: rgw: Handle requests sent in non-UTC time
- from RFC 2616:...
- 09:39 AM rgw Feature #3973: rgw: Handle requests sent in non-UTC time
- 12:26 AM rgw Feature #3973: rgw: Handle requests sent in non-UTC time
- Ian, i dont think this is an client issue. Checking the AWS documentation (http://docs.aws.amazon.com/AmazonS3/latest...
- 08:14 AM Bug #4041 (Can't reproduce): mon: Single-Paxos: on Paxos, leader didn't trim old versions
- Possibly after being killed at some point, the leader ignored earlier versions when it trimmed its state, such that t...
- 07:44 AM Bug #4040: mon: Single-Paxos: on PGMonitor, FAILED assert(0 == "update_from_paxos: error parsing ...
- Triggered again, same symptoms, and it appears as if the issue is a skipped version on the store:
from the origina... - 04:25 AM Bug #4040: mon: Single-Paxos: on PGMonitor, FAILED assert(0 == "update_from_paxos: error parsing ...
- Also, I suspect this might be causing the same problem described on #4026
- 04:24 AM Bug #4040: mon: Single-Paxos: on PGMonitor, FAILED assert(0 == "update_from_paxos: error parsing ...
- Something got messed up when updating the 'last_committed' version on mon.f, which by the way has fallen some 10 vers...
- 04:01 AM Bug #4040 (Resolved): mon: Single-Paxos: on PGMonitor, FAILED assert(0 == "update_from_paxos: err...
- ...
- 06:02 AM Revision ed9103aa (ceph): rgw: parse testdir into apache.conf
- Also fix up the template to use {{field}} for stuff we don't want to parse.
There is probably a better way...
Signed... - 06:01 AM Revision 75c40fac (ceph): qa: fix iogen script
- Wait 10 minutes and then stop.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:44 AM Revision 67bbb9c7 (ceph): osd_recovery: add missing testdir arg
- 01:14 AM Revision 561ea14c (ceph): ceph_manager: take int or string to osd_admin_socket
- This fixes a failure on dump_stuck.
- 12:47 AM Revision 46d7dbd3 (ceph): client: trigger the completion in _flush when short-cutting
- We missed a shortcut return from _flush() when doing
e9a6694d0151b79c3a3b44cee5df8e3d4dcbfc2c, so _fsync() calls
were...
02/06/2013
- 11:46 PM Bug #3945: osd: dynamically link to leveldb
- The current version of leveldb that is being used by ceph is 1.2. The wip-leveldb has version 1.9 which is the lates...
- 09:34 PM Revision 08b82b3e (ceph): mds: add "mds traceless replies" debug option
- This option specifies (in the range 0-1) the percentage of modifying
operations that should be responded to without i... - 07:45 PM Revision 9871cf27 (ceph): logrotate.conf: Silence rgw logrotate some more
- Apply the same change as commit d02340d90c9d30d44c962bea7171db3fe3bfba8e to
the radosgw logrotate.conf.
Signed-off-b... - 07:44 PM Revision d02340d9 (ceph): silence logrotate some more
- I was getting email with logrotate error output from “which invoke-rc.d”
on systems without an invoke-rc.d. This pat... - 06:43 PM Revision f81e0952 (ceph): Merge remote-tracking branch 'gh/wip-danny-cleanups'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:38 PM Revision 0aea4dba (ceph): Merge remote-tracking branch 'gh/wip-3768'
- 06:22 PM Revision c0e1070f (ceph): test: fix Throttle unit test.
- A bunch of these are slightly racy so they're enclosed in loops. This
particular one, though, changes the Throttle st... - 05:06 PM Revision 3fbb5522 (ceph): radosbench: fix missing format value
- tdir is substituted in at the end. There is probably a better way to do
this. - 05:04 PM Revision 936f314a (ceph): rgw: fix testdir format on f
- Format the path, not filehandle
- 05:02 PM Revision 1948a02b (ceph): osd: do not spam system log on successful read_log
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:48 PM CephFS Bug #4038 (Resolved): ceph-fuse: various hangs
- He says it fixed the problem, and it's in master now. (commit: 46d7dbd3472f26926c6d048bfc3c150074bfd283)
- 04:32 PM CephFS Bug #4038: ceph-fuse: various hangs
- There's a shortcut return in CInode::_flush() that wasn't setting the new completion to done (when called from _fsync...
- 04:01 PM CephFS Bug #4038 (Resolved): ceph-fuse: various hangs
- ...
- 04:42 PM Revision 3acc4d2c (ceph): rbd-fuse: fix for loop in open_rbd_image()
- Remove uninitialized usage of 'int i' as i++ from 'for' loop.
The variale 'i' is never used in this loop and initiali... - 04:42 PM Revision b1fc10ef (ceph): messages/MOSDRepScrub.h: initialize member variable in constructor
- Initialize chunky and deep bool member variables in the constructor
with false.
Signed-off-by: Danny Al-Gaaf <danny.... - 04:42 PM Revision db0dbe5d (ceph): msg/Message.h: fix C-style pointer casting
- Replace C-style pointer casting with correct static_cast<>().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:42 PM Revision 42682963 (ceph): WorkQueue.h: fix cast
- Replace C-style pointer casting with correct static_cast<>().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:42 PM Revision a4042cc3 (ceph): ceph_crypto.cc: remove unused shutdown() outside crypto ifdef's
- Fix "out-of-line declaration of a member must be a definition
[-Wout-of-line-declaration]". Remove ceph::crypto::shut... - 04:42 PM Revision ad526c0e (ceph): obj_bencher.cc: use vector instead of VLA's
- Fix "variable length array of non-POD element type" error. (-Wvla)
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisec... - 04:42 PM Revision 0327cbaa (ceph): include/buffer.h: fix operator=
- Fix operator=: return "iterator&" instead of 'iterator'. Check if 'this'
equals 'other' before set anything.
Signed-... - 04:42 PM Revision d54bd170 (ceph): include/types.h: change operator<< function parameter
- Fix "Function parameter 'v' should be passed by reference." from cppchecker.
Use 'const pair<A,B>& v' similar to the ... - 04:42 PM Revision 22e48b57 (ceph): include/xlist.h: fix C-style pointer casting
- Replace C-style pointer casting with correct static_cast<>().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:41 PM rgw Bug #4039 (Resolved): rgw: bucket info discrepencies
- bucket (re)creation ends up clobbering the bucket info stored under user's info.
- 03:22 PM Bug #4037 (Resolved): mon: Single-Paxos: on Paxos, FAILED assert(begin->last_committed == last_co...
- ...
- 01:38 PM CephFS Feature #3626 (Resolved): mds: debug mode to generate traceless replies to clients
- 01:38 PM CephFS Feature #3626: mds: debug mode to generate traceless replies to clients
- Merged into master in commit:08b82b3ef6b43283e35fd4e56eb5c78651345bea.
- 01:26 PM CephFS Feature #3626 (Fix Under Review): mds: debug mode to generate traceless replies to clients
- wip-4036 (commit:4ebba50a15584c89e0c5e4c6e48618055ceb96d8). Testing it now with pjd on a vstart cluster with no trace...
- 12:52 PM Bug #4036 (Resolved): init-ceph: assumes write access to /var/run/ceph
- I noticed this when using init-ceph on a vstart cluster:...
- 12:26 PM rgw Bug #4011 (Resolved): rgw: multipart upload complete does not clean up parts from index
- Fixed, commit:b663c097d1e6f41aed9abeadaae80f66fc71f5ec
Recovery tool, commit:2d8faf8e5f15e833e6b556b0f3c4ac92e4a4151... - 11:49 AM rbd Subtask #4007: libceph: support STAT osd operation
- This has turned out to be simple change. It was needed in
rbd as well, and I'll just add support to both under this... - 09:19 AM rbd Subtask #4007: libceph: support STAT osd operation
- It wasn't really possible to know this up front but
it looks like this is trivial. I've basically
completed it but... - 11:32 AM rgw Feature #3973 (Need More Info): rgw: Handle requests sent in non-UTC time
- Moritz - this seems like an issue with aws-sdk-ruby not reporting time in UTC, rather than our inability to handle a...
- 11:01 AM CephFS Bug #4035 (Rejected): Ceph doesn't recover from fault on Opensuse (cfuse tests & rbd-cli tests)
- I'm not sure if this is exclusive to fs but on an opensuse, single node cluster, when running cfuse and rbd tests a f...
- 10:56 AM rbd Bug #3697 (In Progress): rbd copy.sh test failing in nightly
- 10:38 AM Bug #3768 (Resolved): perl is required for logrotate, we need to include Perl as a dependency
- commit:0aea4dba040b8caaeb5c4079728078541e5bb2c1
- 10:08 AM CephFS Fix #4034 (Resolved): mds: fix replayed ino creation extra_bl
- I haven't tested this, but I noticed during code inspection for other things that I believe all our recent fixes for ...
- 09:59 AM Bug #4026 (In Progress): mon: Single-Paxos: abort on LogMonitor::update_from_paxos
- 09:59 AM Bug #4026: mon: Single-Paxos: abort on LogMonitor::update_from_paxos
- Haven't been able to reproduce this nor to find an obvious cause for this to have happened.
After inspecting the s... - 09:37 AM devops Feature #4032: ceph-disk-prepare should allow the definition of an OSD id
- Ah, right. I was thinking we could get into badness over that disagreement, but of course everything checks the real ...
- 09:27 AM devops Feature #4032: ceph-disk-prepare should allow the definition of an OSD id
- Greg Farnum wrote:
> I don't think we want to do this. The problem is that if we plug in a new OSD that has the same... - 09:21 AM devops Feature #4032: ceph-disk-prepare should allow the definition of an OSD id
- I don't think we want to do this. The problem is that if we plug in a new OSD that has the same ID as the previous on...
- 05:55 AM devops Feature #4032 (Rejected): ceph-disk-prepare should allow the definition of an OSD id
- When replacing disks in existing boxes, sometimes it's useful to keep the existing OSD numbering, rather than start a...
- 08:56 AM rbd Bug #3958: rbd fsx fails with EBUSY
- this is causing several failures on master runs.. something has changed.
latest:
ubuntu@teuthology:/a/sage-2013-... - 08:55 AM Bug #3810 (Resolved): btrfs corrupts file size on 3.7
- 08:31 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- The testing I've been doing now has shown no problems
now that teuthology has been updated.
The two other issues ... - 06:16 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- Seems to have done the trick! The kernel_untar_build.sh
task just finished for me without error, and it failed
rel... - 05:06 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- That sounds promising, I hope it works!
This was actually the last thing I was looking at last
night while waitin... - 08:18 AM Bug #3854: mon: clock skew tests failing on master
- This was fixed by commit:d74b31b24db647a8b7c80d1552fa6f0b02c54ba4 and commit:c54781618569680898e77e151dd7364f22ac4aa1
- 07:31 AM Revision ed3c3615 (ceph): nuke: don't try unmount if we're rebooting everything anyway
- This can cause issues when unmount hangs. Our automatic runs reboot
everything unconditionally, so this caused a bunc... - 07:28 AM Revision c6504bab (ceph): nuke: make tmpfs check only umount tmpfs
- This would catch things like /tmp/cephtest/mnt.client.0, which are
used by cfuse, rbd, and kclient. - 07:20 AM rbd Bug #4033 (Fix Under Review): krbd: add barriers near done flag operations
- A fix for this has been posted for review.
[PATCH] rbd: add barriers near done flag operations
- 06:15 AM rbd Bug #4033 (Resolved): krbd: add barriers near done flag operations
- I fixed this problem while investigating the rbd hangs
in http://tracker.ceph.com/issues/4003.
Somehow, I missed ... - 07:19 AM Revision 82273e95 (ceph): rbd: fix rbd image unmount
- The testdir param was missing. Avoid this class of errors by unmounting
exactly what we mounted. - 07:01 AM Revision 60990459 (ceph): rbd: set env before running sudo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:53 AM devops Bug #4031 (Won't Fix): ceph-disk-activate hardcodes journal path, ignores configuration
- I'm having my ceph.conf configured to store journals in a different place, like:
[osd]
osd journal = /var/lib/ceph... - 01:56 AM Revision 27fb0e63 (ceph): rgw: a tool to fix buckets with leaked multipart references
- Checks specified bucket for the #4011 symptoms, optionally fix
the issue.
sytax:
radosgw-admin bucket check --buck... - 01:55 AM Revision 50c1775d (ceph): rgw: radosgw-admin object unlink
- Add a radosgw-admin option to remove object from bucket index
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cher... - 01:48 AM Revision cc167914 (ceph): rgw: a tool to fix buckets with leaked multipart references
- Checks specified bucket for the #4011 symptoms, optionally fix
the issue.
sytax:
radosgw-admin bucket check --buck... - 01:31 AM Revision 9eff2ee1 (ceph): Merge remote-tracking branch 'gh/wip-osd-commands'
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com> - 01:08 AM Revision 4d6964fc (ceph): rgw: radosgw-admin object unlink
- Add a radosgw-admin option to remove object from bucket index
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cher... - 12:35 AM Revision 3b635423 (ceph): mon: move list_rules into CrushWrapper method
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:35 AM Revision 9f4d4ac9 (ceph): crush: add list_rules() method
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:14 AM Revision 7f237be2 (ceph): Makefile: Add rgw/logrotate.conf source tarball
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
02/05/2013
- 11:56 PM Bug #4030 (Resolved): Missing Fedora 18 release packages
- In the docs on OS recommendations:
http://ceph.com/docs/master/install/os-recommendations/
It is mentioned that... - 11:52 PM Revision 16235a7a (ceph): rgw: radosgw-admin object unlink
- Add a radosgw-admin option to remove object from bucket index
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:52 PM Revision 2d8faf8e (ceph): rgw: a tool to fix buckets with leaked multipart references
- Checks specified bucket for the #4011 symptoms, optionally fix
the issue.
sytax:
radosgw-admin bucket check --buck... - 11:52 PM Revision b663c097 (ceph): rgw: unlink multipart upload parts when completing upload
- Fixes: #4011
When completing the multipart upload, we also need to unlink the
parts from the bucket index. Originally... - 11:43 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- This was backing up qa stuff because the rbd.py qa task wasn't unmounting during cleanup. That bit is now fixed. I ...
- 10:54 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- new theory:
the reason umount hangs is because nuke is killing the client and osds at the same time. the umount i... - 10:41 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I found that unmount was hanging too. I think somehow the
completion of the I/O is not getting propagated up when
... - 10:33 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- aha:...
- 10:15 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- btw i am able to reproduce the EBUSY with just...
- 08:28 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I've added some instrumentation and find that the rbd
client is not dropping its watch at the end of the
kernel_unt... - 12:51 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- The interrupt issue has been fixed, but the other issue
(rbd device can't be unmapped because EBUSY) remains.
I h... - 11:35 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I ran the kernel_untar_build.sh workunit using the
ceph "master" branch and the ceph-client "testing"
branch and go... - 11:13 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I think I found *a* problem, possibly not *the* problem.
This commit:
bc7a62ee5 rbd: prevent open for image ... - 11:04 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I am able to reproduce this problem by running
the kernel_untar_build.sh workunit.
I ran the test using the ceph ... - 08:53 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- > Alex, unless there is another high priority regression, can you
> look at this first?
Yes I will. - 08:52 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- Sam Lang wrote:
> I was able to verify that this happens with an older version of teuthology, one without the change... - 08:41 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I was able to verify that this happens with an older version of teuthology, one without the changes I've made recentl...
- 05:18 AM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I had the impression this might be a problem that
is holding up completion of the nightly test suite.
But I'm not... - 11:20 PM Revision 99ea3030 (ceph): logrotate.conf: Remove unneeded loop and update new rgw version.
- Remove an unneeded for loop from the ceph logrotate.conf, and
update the new rgw logrotate.conf to reload the radosgw... - 10:54 PM Revision c8eace6f (ceph): rgw: create a separate logrotate file for radosgw
- Fixes: #3813
Since radosgw package is separate from the ceph package,
it also needs to have a separate logrotate. The... - 10:31 PM Revision 43a01c99 (ceph): crush: factor out (trivial) crush_destroy_rule()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:31 PM Revision b9bd482d (ceph): crush: remove_rule() method
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:31 PM Revision a19cdd49 (ceph): osdmap: method to check if a crush ruleset is in use
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:31 PM Revision 2c559a7a (ceph): mon: 'osd crush rule rm <name>'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:31 PM Revision b79067a8 (ceph): qa: add workunits/mon/crush_ops.sh
- Test creating, listing, removing crush rules via the mon.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:31 PM Revision c370d85b (ceph): mon: 'osd crush rules list|ls'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:30 PM Revision 9da6290c (ceph): crush: factor out dump_rules from dump
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:30 PM Revision b6036a58 (ceph): mon: 'osd crush dump'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:30 PM Revision a04d3f0a (ceph): mon: 'osd crush rule create-simple <name> <root> <failure_domain_type>'
- Simple command to create simple rules.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:29 PM Revision 1a386d6c (ceph): crush: add_simple_rule() command
- Method to create a very generic rule the distributes objects across the
specified failure domain type underneath the ... - 10:26 PM Revision d7ada58a (ceph): crush: fix get_rule_id() return value
- There are 0 callers, yay!
Signed-off-by: Sage Weil <sage@inktank.com> - 10:26 PM Revision 3105700d (ceph): mon: 'osd find <osd-id>' command
- Simple command to find the ip, host, rack, etc. for an OSD. This is better
than 'ceph osd dump | grep ^osd.NNN\ '.
... - 10:26 PM Revision 4f992ea3 (ceph): crush: add rule_exists()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:20 PM Revision 100e9056 (ceph): misc: Close connections on reboot
- When nodes are rebooted, the connections remain open
even after calling reconnect and setting up new ssh
sessions to ... - 10:07 PM Bug #4028 (Duplicate): rbd: qa runs failing to remove image after unmap
- sorry, this is actuall a dup of #4003.
- 09:55 PM Bug #4028: rbd: qa runs failing to remove image after unmap
- Is this the fault of the rbd task? What should
be removing the image? - 08:57 PM Bug #4028 (Duplicate): rbd: qa runs failing to remove image after unmap
- Pretty consistently reproducible with kernel rbd tasks against master branch, and either master or testing kernel.
- 09:48 PM Revision b3ffc718 (ceph): Merge branch 'wip-2753-fsync-errors'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 09:29 PM Revision 72c7bcd5 (ceph): mds: MDSCacheObjectInfo now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:29 PM Revision 49b0be58 (ceph): mds: rename MDSTableServer::_pending to mds_table_pending_t
- And move it from MDSTableServer into mdstypes.cc, so we can use it
in ceph-dencoder more gracefully (coming up next!)... - 09:29 PM Revision 924fb18f (ceph): mds: mds_table_pending_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 78632adc (ceph): mds: modernize SimpleLock on-wire encoding
- This is a wire protocol change.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:29 PM Revision 21901d21 (ceph): mdsmap: uninline encode/decode
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 771204b2 (ceph): mds: move conditional MDSMap encoding into single encode method
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 50ab924a (ceph): mds: MDSMap now uses modern encoding
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:29 PM Revision ad40bdd8 (ceph): MDSMap: mds_info_t now uses modern encoding
- We have to update the older-style MDSMap encodings to generate
the previous versions for clients as well.
Signed-off... - 09:29 PM Revision 90d93d94 (ceph): mds: build dencoder with more stuff
- Add libosdc and perfglue/disabled_heap_profiler to the
dencoder, because those are required for the MDS stuff
we're a... - 09:29 PM Revision c058285d (ceph): mds: uninline Capability encoders
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:29 PM Revision 08124fc7 (ceph): mds: SnapInfo, snaplink_t, sr_t now use modern encoding
- This commit doesn't enable the dencoder integration due
to some build and compile issues, but we'll turn it
on later.... - 09:29 PM Revision 3e728931 (ceph): client: rename client/SnapRealm files to avoid automake build conflict
- We are about to move the MDS' SnapRealm into its own files, which conflicts.
The MDS is more important, so it wins th... - 09:29 PM Revision f1baa79c (ceph): mds: move SnapRealm into its own h/cc files
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:29 PM Revision 34f7c715 (ceph): mds: inode_back{trace,pointer}_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 2888830f (ceph): mds: default_file_layout now uses modern encoding
- And move implementations into mdstypes.cc from CInode and common/types.
mdstypes.cc sadly lives in libcommon; as seve... - 09:29 PM Revision a892671a (ceph): mds: frag_info_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:29 PM Revision cda5590e (ceph): mds: rename struct default_file_layout to file_layout_policy_t
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 9cf9c54c (ceph): mds: nest_info_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 49eb4d68 (ceph): mds: client_writeable_range_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 87da20bf (ceph): mds: fold byte_range_t into client_writeable_range_t
- As part of this, fold byte_range_t into it as a sub-struct
and eliminate its free-standing functions (it's too small
... - 09:29 PM Revision 843a3521 (ceph): mds: inode_t now uses modern encoding
- And we move implementations and the dumper into mdstypes.cc (from
mdstypes.h and common/types.cc).
Signed-off-by: Sa... - 09:29 PM Revision 7e85a178 (ceph): remove common/types.cc
- It no longer has a purpose; the functions it used to host are now
implemented in mds/mdstypes.cc and more properly be... - 09:29 PM Revision bd4897b8 (ceph): mds: old_inode_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 44865800 (ceph): mds: fnode_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 91555e22 (ceph): mds: move durable Session bits into session_info_t
- This keeps the on-disk structure explicitly separate from the in-memory
functional stuff.
Signed-off-by: Sage Weil <... - 09:29 PM Revision f57f4244 (ceph): mds: session_info_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision d580a581 (ceph): mds: string_snap_t now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision 43468a3b (ceph): osd: remove DecayCounter header
- Neither the OSD nor the PG makes any use of this.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:29 PM Revision ccba2ced (ceph): mds: add CEPH_FEATURE_MDSENC feature bit
- This will cover the MDS cluster on upgrade, and determine which encoding
of the MDSMap they use for clients.
Signed-... - 09:29 PM Revision e35b89ec (ceph): mds: Anchor now uses modern encoding
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:28 PM Revision ece1c0f8 (ceph): mon: check correct length of command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:47 PM Bug #3971: can't attach rbd image volume to instance
- 1) The log shows an attempt to open volume-ade3b6fb-2386-4d10-9472-16cd4f955faa; this isn't the same volume you show ...
- 08:41 PM Bug #3971: can't attach rbd image volume to instance
- The log shows it trying to access an rbd_header.volume-ade3b6fb-2386-4d10-9472-16cd4f955faa object without looking at...
- 08:15 PM Bug #3971: can't attach rbd image volume to instance
- 1) The log shows an attempt to open volume-ade3b6fb-2386-4d10-9472-16cd4f955faa; this isn't the same volume you show ...
- 07:48 PM Bug #3971: can't attach rbd image volume to instance
- yes sure, restarted all.
Please refer to the attached file for more detail.
Thanks. - 03:49 PM Bug #3971: can't attach rbd image volume to instance
- Did you restart the monitors and osds after you set auth supported = none in the global section of every /etc/ceph/ce...
- 08:16 PM Bug #4027 (Resolved): ceph-fuse on opensuse12 has the wrong requirement name for libfuse dependency
- Instead of fuse-libs it should require libfuse2. This is likely specific to opensuse, but should double check others...
- 07:13 PM Revision 13e22262 (ceph): Merge pull request #39 from dachary/master
- Relax Throttle::_reset_max conditions and associated unit tests
- 07:06 PM Revision 64ded02c (ceph): Relax Throttle::_reset_max conditions and associated unit tests
- Removes a condition in Throttle::_reset_max by which the waiting queue is only
Signal()ed if the new maximum is lower... - 06:29 PM Revision ca2d6459 (ceph): os: default to 'journal aio = true'
- Hooray, testing indicates this is a win!
Signed-off-by: Sage Weil <sage@inktank.com> - 06:20 PM Revision e43a13c0 (ceph): Merge pull request #36 from cmello/master
- libexpat dependency
- 05:57 PM Revision 26f7db11 (ceph): Merge pull request #38 from alram/master
- Fixes in ./docs/radosgw/config.rst
- 05:33 PM RADOS Feature #3807 (Resolved): crush: simple commands to create common rules
- commit:9eff2ee13dc03f245a11c91f4ed7d5bc15c55aef
- 05:31 PM rgw Bug #4011: rgw: multipart upload complete does not clean up parts from index
- actually does not affect bobtail. Will still need to port the fix tool to bobtail.
- 12:55 PM rgw Bug #4011 (Resolved): rgw: multipart upload complete does not clean up parts from index
- 05:17 PM Bug #4026 (Resolved): mon: Single-Paxos: abort on LogMonitor::update_from_paxos
- While running teuthology with 20+ monitors, the monitor workloadgen with 10 osds, and mon thrasher, we triggered the ...
- 04:38 PM Revision da10b58d (ceph): task/ceph_manager: Fix NoneType config issue
- kill_mon is getting a config set to None, which blows
up now due to the check for powercycle. Initialize
the config ... - 04:22 PM CephFS Feature #3626 (In Progress): mds: debug mode to generate traceless replies to clients
- Server::set_trace_dist() sets several things on the reply:
*snapbl
*head.is_dentry
*head.is_target
*trace_bl
H... - 02:35 PM CephFS Bug #1435: mds: loss of layout policies upon mds restart
- Wait, never mind. Too excited and didn't look closely enough at the projected node struct! :)
- 01:56 PM CephFS Bug #4023 (New): kclient: d_revalidate is abusing d_parent
- See Viro's email to linux-fsdevel, http://marc.info/?l=linux-fsdevel&m=135968126020360&w=2 .
We probably need t... - 01:52 PM CephFS Bug #2753 (Resolved): Writes to mounted Ceph FS fail silently if client has no write capability o...
- wip-2753-fsync errors merged and pushed in commit:b3ffc718c93b7daa75841778b5d50ea3bc5fcc53 and fsync works properly o...
- 01:47 PM CephFS Feature #4022 (New): client: qa: test non-cached operation (force sync mode)
- Right now it's possible to run the client without going through the cacher. This isn't tested at all right now. It's ...
- 01:47 PM rbd Feature #4021 (Resolved): rbd: openstack: add ability to copy volume to image for rbd
- 01:46 PM rbd Subtask #4020 (Resolved): rbd: openstack: simplify volume booting with new api: make image boot b...
- 01:44 PM rbd Subtask #4019 (Resolved): rbd: openstack: simplify volume booting with new api: add boot option t...
- 01:44 PM rbd Subtask #4018 (Resolved): rbd: openstack: simplify volume booting with new api: modify boot panel...
- 01:42 PM rbd Feature #4017 (Resolved): rbd: openstack: simplify volume booting with new api
- 01:42 PM rbd Feature #4013 (In Progress): rbd: openstack: extend nova boot api to support going from image to ...
- 01:24 PM rbd Feature #4013 (Resolved): rbd: openstack: extend nova boot api to support going from image to volume
- 01:41 PM rbd Subtask #4016 (Resolved): rbd: openstack: extend nova boot api: modify libvirt driver to support ...
- 01:40 PM rbd Subtask #4015 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-...
- 01:40 PM rbd Subtask #4014 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-api
- 01:13 PM rbd Bug #4012 (Won't Fix): rbd: image creation behaviour has to be uniform across bobtail and argonau...
- rbd allows images to be created with size 0 in bobtail, but it fails in argonaut.
similarly,while in bobtail it do... - 12:52 PM rbd Bug #4010 (Fix Under Review): krbd: turn off interrupts for open/remove locking
- Posted for review.
[PATCH] rbd: turn off interrupts for open/remove locking
- 12:49 PM rbd Bug #4010 (Resolved): krbd: turn off interrupts for open/remove locking
- This fix is done. The problem was discovered while
investigating http://tracker.ceph.com/issues/4003.
This commi... - 11:40 AM Bug #4009 (Duplicate): osd reports map e6 wrongly marked me down
- ...
- 10:37 AM Bug #3683 (In Progress): mon: leak of MMonPaxos
- ubuntu@teuthology:/a/teuthology-2013-02-04_20:00:03-regression-bobtail-master-basic/15658
- 10:34 AM devops Feature #4008 (Resolved): ceph-deploy: make sure new version works with old ceph-disk_*
- 10:12 AM rbd Bug #3697: rbd copy.sh test failing in nightly
- recent log : ubuntu@teuthology:/a/teuthology-2013-02-04_20:00:03-regression-bobtail-master-basic/15773
- 09:49 AM Linux kernel client Bug #3997 (Fix Under Review): xfs: insert memory barriers before wake_up_bit()
- The first patch was ACK'd by Dave Chinner.
The second one he explained wasn't needed,
because an atomic increment a... - 07:42 AM rbd Subtask #4007 (Resolved): libceph: support STAT osd operation
- In order to do layered writes we need to check whether
an object to be written exists before issuing the write.
Thi... - 06:06 AM Revision 2ebf4d06 (ceph): osd: kill unused addr-based send_map()
- Not used, old API, bad.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e359a862199c8a94cb238... - 06:06 AM Revision bac5b144 (ceph): osd: share incoming maps via Connection*, not addrs
- Kill a set of parallel methods that are using the old addr/inst-based
msgr APIs, and instead use Connection handles. ... - 06:06 AM Revision 9ca3a165 (ceph): osd: pass new maps to dead osds via existing Connection
- Previously we were sending these maps to dead osds via their old addrs
using a new outgoing connection and setting th... - 06:06 AM Revision 4cb28b6e (ceph): osd: requeue osdmaps on heartbeat connections for cluster connection
- If we receive an OSDMap on the cluster connection, requeue it for the
cluster messenger, and process it there where w... - 06:05 AM Revision e4f7ff8c (ceph): msgr: add get_loopback_connection() method
- Return the Connection* for ourselves, so we can queue messages for
ourselves.
Signed-off-by: Sage Weil <sage@inktank... - 06:05 AM Revision 6af5da7a (ceph): mds: handle ceph.*.layout.* setxattr
- Allow individual fields of file or dir layouts to be set via setxattr.
Signed-off-by: Sage Weil <sage@inktank.com>
(... - 06:05 AM Revision d386622c (ceph): mds: allow dir layout/policy to be removed via removexattr on ceph.dir....
- This lets a user remove a policy that was previously set on a dir.
Signed-off-by: Sage Weil <sage@inktank.com>
(cher... - 06:05 AM Revision 62ed62f5 (ceph): qa: add layout_vxattrs.sh test script
- Test virtual xattrs for file and directory layouts.
TODO: create a data pool, add it to the fs, and make sure we can... - 06:05 AM Revision c0af056e (ceph): mdsmap: backported is_data_pool()
- This roughly corresponds to mainline commit 99d9e1d.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:20 AM Revision d41b5411 (ceph): Edit endpoint-create in ./doc/radosgw/config.rst
- internalurl and adminurl are mandatory. Typo in publicurl.
- 05:14 AM Revision 6e603301 (ceph): Edit rgw keystone url in ./doc/radosgw/config.rst
- Won't work with the public port, it needs to be the admin port.
- 05:09 AM Revision af8cac11 (ceph): Note on host in ./doc/radosgw/config.rst
- Some people have configured host with a FQDN or an IP
which prevents /etc/init.d/radosgw start to launch the daemon. - 12:42 AM Revision 4b4dba30 (ceph): doc: Updated to note bobtail supports RGW + Keystone.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
02/04/2013
- 10:49 PM Revision e2e1de27 (ceph): cli test: add pg deep-scrub option to test
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 10:23 PM Bug #4006 (Resolved): osd: repeating 'wrong node' message in log
- Two users now (paravoid an xiaoxi in #ceph) have reported seeing repeated "... - wrong node!" messages in the osd log...
- 10:14 PM Revision eba8697e (ceph): cli test: add pg deep-scrub option to test
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 08:56 PM Revision 4a6924a5 (ceph): install: remove perl dependency
- Change the filter in logrotate to use sed instead of perl, and remove the
package dependency on perl.
Signed-off-by:... - 08:09 PM Revision 0407af46 (ceph): mds: fix client view of dir layout when layout is removed
- We weren't handling the case where the projected node has NULL for the
layout properly. Fixes the client's view when... - 08:09 PM Revision 8ce834d3 (ceph): client: note presence of dir layout in inode operator<<
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 84751489ca208964e617516e04556722008ddf67) - 08:09 PM Revision 99824b93 (ceph): client: list only aggregate xattr, but allow setting subfield xattrs
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ba32ea9454d36072ec5ea3e6483dc3daf9199903) - 08:09 PM Revision 809cff48 (ceph): client: implement ceph.file.* and ceph.dir.* vxattrs
- Display ceph.file.* vxattrs on any regular file, and ceph.dir.* vxattrs
on any directory that has a policy set.
Sign... - 08:09 PM Revision 13babca3 (ceph): client: move xattr namespace enforcement into internal method
- This captures libcephfs users now too.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit febb96... - 08:09 PM Revision 65ab5174 (ceph): client: allow ceph.* xattrs
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ad7ebad70bf810fde45067f78f316f130a243b9c) - 07:52 PM rgw Bug #3294: Ceph S3 API test
- I researched this error many times by results are so bad,
Thank to "lollipop king", you are very good :D
--
Ta... - 07:45 PM Revision 804ffc63 (ceph): Add "pg deep-scrub..." missing from ceph usage output
- Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:33 PM Revision 6f3c1cd2 (ceph): rgw_rest: Make fallback uri configurable.
- Some HTTP servers, notabily lighttp, do not set SCRIPT_URI, make the fallback
string configurable.
Signed-off-by: ca... - 07:28 PM Bug #3979: Ceph 0.56.2 RPM does not install
- Gary,
I did that on a freshly kickstarted system already. I'm unsure how much fresher I can get the system without ... - 06:57 PM Bug #3979: Ceph 0.56.2 RPM does not install
- Hi Steven -
I looked at the kickstart file and I did not see anything that looked suspicious. At the moment we're... - 07:24 PM Revision f57d1b4c (ceph): rgw: fix setting of NULL to string
- Fixes: #3777
s->env->get() returns char * and not string and can return NULL.
Also, remove some old unused code.
Sig... - 07:23 PM Revision 9019fbbe (ceph): rgw: fix setting of NULL to string
- Fixes: #3777
s->env->get() returns char * and not string and can return NULL.
Also, remove some old unused code.
Sig... - 06:50 PM Bug #3768 (Fix Under Review): perl is required for logrotate, we need to include Perl as a depend...
- 06:50 PM Bug #3736 (Resolved): kernel build: failures starting in 3.8-rc1
The problem that resulting in this bug being opened originally has been solved with the update patch. I've created...- 06:45 PM Feature #4005 (New): Add perftools to the kernel debian package script
- Currently on the kernel gitbuilder we install a patch to the debian package script in order to build the performance ...
- 06:41 PM Bug #4004 (In Progress): Intermittent kernel build failures
- 06:39 PM Bug #4004 (Can't reproduce): Intermittent kernel build failures
- From time to time the kernel builds will fail in the packaging step with a gzip internal error, usually EINVAL on a w...
- 06:39 PM Revision 2f41f81d (ceph): misc: don't use colon in default run name
- LD_LIBRARY_PATH does not work with colons (and backslash does not escape them.)
- 06:39 PM Revision 55687240 (ceph): OSD: check for empty command in do_command
- Fixes: #3878
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
(... - 06:35 PM Bug #3788 (Resolved): debian source packages are missing
- Resolved with the following commits:
commit e3e0b40f1b44e2458e47f31bedaa91408dc294c9
Author: Gary Lowell <gary.lo... - 05:53 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- I really can't tell who's got a watch on the header
object. It should be getting removed when the object
gets unma... - 05:02 PM rbd Bug #4003: rbd: EBUSY errors from rbd unmap
- There is clearly something that is keeping the rbd image
from getting removed. I reproduced this with just running
... - 04:12 PM rbd Bug #4003 (In Progress): rbd: EBUSY errors from rbd unmap
- This sounds familiar, but I'm going to look a little
more closely to see if I can learn why it's happening.
- 04:03 PM rbd Bug #4003 (Resolved): rbd: EBUSY errors from rbd unmap
- From the teuthology kernel untar task on rbd, we get EBUSY trying to unmap. I'm investigating that this isn't someho...
- 05:27 PM Revision 60432d9b (ceph): perf_counters.cc: remove twice included header files
- Cleanup includes, remove twice included "global/global_init.h" and
"common/ceph_context.h".
Signed-off-by: Danny Al-... - 05:27 PM Revision 558b238c (ceph): testmsgr.cc: remove twice included <sys/stat.h>
- Cleanup includes, remove twice included <sys/stat.h>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision c81a9d4a (ceph): ceph-filestore-dump.cc: remove twice included <iostream>
- Cleanup includes, remove twice included <iostream>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision e0acc330 (ceph): xattr_bench.cc: remove twice included <time.h>
- Cleanup includes, remove twice included <time.h>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision 81979909 (ceph): MDS.cc: remove twice included common/errno.h
- Cleanup includes, remove twice included common/errno.h.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision c8aeb93d (ceph): small_io_bench*.cc: remove twice included <iostream>
- Cleanup includes, remove twice included <iostream>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision d141f79b (ceph): tp_bench.cc: remove twice included <iostream>
- Cleanup includes, remove twice included <iostream>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision 94210414 (ceph): test_idempotent.cc: remove twice included "os/FileStore.h"
- Cleanup includes, remove twice included "os/FileStore.h".
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision b22d641d (ceph): workload_generator.cc: remove twice included "common/debug.h"
- Cleanup includes, remove twice included "common/debug.h"
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:27 PM Revision b70d563f (ceph): testxattr.cc: remove twice included <iostream>
- Cleanup includes, remove twice included <iostream>.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:14 PM Revision 4e29c95d (ceph): mon: enforce reweight be between 0..1
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com> - 04:48 PM CephFS Bug #2753 (Fix Under Review): Writes to mounted Ceph FS fail silently if client has no write capa...
- Okay, I've checked that the kernel client deals correctly with an fsync (it'll return EPERM). The client branch wip-2...
- 03:49 PM CephFS Feature #3540: mds: maintain per-file backpointers on first file object
- Comments on Github for this.
- 02:21 PM CephFS Feature #3540: mds: maintain per-file backpointers on first file object
- I've pushed the additional changes for rename and sentinel to the wip-bt2 branch. Those bits are still untested, but...
- 10:45 AM CephFS Feature #3540 (In Progress): mds: maintain per-file backpointers on first file object
- The initial review happened last week; Sam has some updates for the rename and sentinel object infrastructure now but...
- 02:58 PM CephFS Cleanup #1499: mds: clean up directory layouts
- there is an old branch that does this. note that this code changed with the wip-vxattrs work, so the rebase needs to ...
- 02:34 PM CephFS Feature #3953: kclient: get/set layout via virtual xattrs
- in testing branch, passing tests. yay!
- 02:33 PM CephFS Feature #3953 (Resolved): kclient: get/set layout via virtual xattrs
- 02:30 PM Bug #3810: btrfs corrupts file size on 3.7
- I believe the btrfs patch fixed this issue. I consider this bug closed.
- 02:15 PM rgw Cleanup #3777: rgw: audit code for reading NULL env variables
- commit:9019fbbe8f84f530b6a8700dfe99dfeb03e0ed3d
- 01:41 PM rgw Cleanup #3777 (Resolved): rgw: audit code for reading NULL env variables
- Fixes merged into bobtail, next, master.
- 01:24 PM rgw Feature #2941: rgw: improve streaming read performance
- Bunch of comments on Github for this.
Given some of them it also needs more testing before going into master. :) - 12:36 PM CephFS Feature #4002 (Resolved): mds: design fsck
- 10:40 AM Bug #3787: Ceph OSD crashes on ceph tell osd.x
- ushed to bobtail, commit:55687240b2de20185524de07e67f42c3b1ae6592
- 10:37 AM Bug #3787: Ceph OSD crashes on ceph tell osd.x
- Should this be backported to Bobtail?
- 10:35 AM CephFS Feature #3242 (New): samba: push plugin upstream
- I believe we decided to hold off on putting more effort into this.
- 10:34 AM CephFS Feature #3542 (Duplicate): mds: migration path for existing anchors, anchortables, etc.
- Closing in favor of #4000 and #4001.
- 10:34 AM Bug #3938 (Can't reproduce): ceph-mon crashed on mixed bobtail-argonaut cluster (2 argonaut mons,...
- After a couple of days trying to reproduce this issue (and massively failing at it), and given the lack of debug info...
- 10:33 AM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
- Actually do whatever #4000 specifies.
- 10:31 AM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
- We're currently engaged in work to do lookup-by-ino when we get an ino we don't recognize. However, any old installs ...
- 10:27 AM CephFS Feature #3999 (Resolved): update CDir encoding
- Either following or as part of #2177, we should update CDir on-disk encoding (and possibly wire encoding) to be versi...
- 10:25 AM CephFS Cleanup #3998 (Resolved): mds: split up mdstypes
- Right now we have mdstypes and it contains both MDS-exclusive and client-shared structs. Split it up into "metadata_t...
- 10:03 AM CephFS Feature #3543: mds: new encoding
- Got an early review from Sage; now waiting for a merge review and for test results from the FS suites, which are dela...
- 09:59 AM CephFS Bug #3951 (Resolved): ceph-fuse: permissions error on create
- Fixed in master commit:cf7c3f7d3fc7b8dc3a08a4fbe4ca1c10f2cb6054 and tested that it solves the problem.
- 09:45 AM CephFS Bug #3935 (Need More Info): kclient: Big directory access bugs (multiple), mixed 32- and 64-bit c...
- 08:18 AM Linux kernel client Bug #3997: xfs: insert memory barriers before wake_up_bit()
- And here is something Sage provided that led me to believe
this could be the source of the problem. I'm not sure ho... - 08:17 AM Linux kernel client Bug #3997: xfs: insert memory barriers before wake_up_bit()
- Sorry, I meant to include these in the last one:
[PATCH 1/2] xfs: memory barrier before wake_up_bit()
[PATCH 2/2]... - 08:16 AM Linux kernel client Bug #3997: xfs: insert memory barriers before wake_up_bit()
- I have posted two patches to the XFS mailing list for review.
I am also waiting for a build to complete before doing... - 08:03 AM Linux kernel client Bug #3997 (Resolved): xfs: insert memory barriers before wake_up_bit()
- I looked at this briefly last week and found what could explain
a hang on an osd node due to a bug in XFS. I ran it... - 04:09 AM Revision 55c1bcf6 (ceph): Add testdir param to get_valgrind_args() calls
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
02/03/2013
- 05:38 PM Revision a5ba4f6a (ceph): Merge branch 'wip-misc-fixes'
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 05:28 PM Revision b970d054 (ceph): qa: smalliobenchrbd workunit
- Run a bunch of parallel smalliobenchrbd processes.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:09 PM Revision 887e93e7 (ceph): nuke.py: Allow name of job/run to be specified
- Nuke will cleanup the base test directory by default, but can
cleanup the test directory for a given run if specified... - 05:09 PM Revision 46d3ff94 (ceph): run.py: Add target name to logging info
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 04:59 PM Revision 4be48a6e (ceph): Merge remote-tracking branch 'gh/wip-rbd-bench'
- Conflicts:
ceph.spec.in
debian/ceph-test.install
src/.gitignore - 04:18 PM Revision ada803db (ceph): rbd: fix .format() call with {1} syntax
- IndexError: tuple index out of range
- 03:28 PM Bug #3995: OSD heartbeat-crashes during startup
- Good news: the OSD has recovered after a couple of restarts.
- 01:58 PM Bug #3995 (Resolved): OSD heartbeat-crashes during startup
- OSD can't start, it does something then crashes with a heartbeat assertion.
Debian, ceph version 0.56.2 (586538e22af... - 02:55 PM Bug #3996 (Resolved): mon: 'ceph mon add' results in dubious return message
- Disclaimer: this might be only present on the current single-paxos branch (maybe due to some mistaken conflict resolu...
- 05:01 AM Revision fe9fb49e (ceph): ceph_manager: use get() for self.config powercycle checks
- I think this is what is going on...
Traceback (most recent call last):
File "/var/lib/teuthworker/teuthology-maste... - 02:11 AM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- It's not really urgent, but being able to upgrade to latest argonaut (and if that works for 2-3 days) to latest bobta...
02/02/2013
- 08:56 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Corin Langosch wrote:
> After the downgrade my cluster is still stable and no osd crashed so far.
>
> What can I ... - 02:55 AM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- After the downgrade my cluster is still stable and no osd crashed so far.
What can I do to upgrade to latest argon... - 05:00 PM Revision 7280980f (ceph): Fixup latest commits that use /tmp/cephtest.
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 04:41 PM Bug #3966 (Resolved): osdthrasher: does tell on osd just after restarting it
- fixed in tuethology commit:fadc22c0b9e1755b1d1826fcfe8be71e28574bc9
- 04:40 PM Bug #3854 (Resolved): mon: clock skew tests failing on master
- 04:40 PM Bug #3994 (Closed): ceph-osd crash under little to no load
- ...
- 02:10 PM Bug #3994: ceph-osd crash under little to no load
- Also potentially of interest is the kernel log having some btrfs checksum failures:
btrfs csum failed ino 583798 ext... - 02:09 PM Bug #3994: ceph-osd crash under little to no load
- It died again, here is the log output:
https://pastee.org/fbgch - 02:07 PM Bug #3994 (Closed): ceph-osd crash under little to no load
- One of my osd's crashed a number of times in a row, and was repeatably enough that I had time to set the debugging le...
- 07:26 AM Revision 606b5c15 (ceph): Merge branch 'wip-rpm-update3'
- Patches to ceph.spec.in and addition of rbd-fuse package.
02/01/2013
- 11:39 PM Revision bd4f1d5c (ceph): adding task for iogen
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:07 PM Revision d9fff40f (ceph): task/chdir-coredump: Use readlink -e
- realpath isn't available everywhere, use readlink -e instead.
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 08:07 PM Revision 9a9fe73e (ceph): task/ceph: Fix typo in previous commit
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 07:31 PM Revision 04210c26 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 07:30 PM Revision d050fe1e (ceph): doc: Minor edits.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:01 PM Revision 9de9ebcf (ceph): nuke: get_testdir_base needs to be imported
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 06:35 PM Revision 0797be3f (ceph): rgw: key indexes are only link to user info
- Instead of keeping multiple copies of the user info,
we just treat the key index as a pointer to the actual
user info... - 05:45 PM Revision edfe5eed (ceph): nuke: Fix cleanup of test dir
- Nuke used to remove /tmp/cephtest, now it tries to
remove the test dir, which it may not have the name
for. Instead ... - 05:37 PM Revision 4ebd90eb (ceph): task/ceph: Initialize disk_config maps
- The mount_options and fstype maps need to be
initialized properly for later.
Signed-off-by: Sam Lang <sam.lang@inkta... - 04:53 PM Revision 150a3d7d (ceph): misc: Don't include existing partitions in devs
- We don't want to include /dev/sda1, etc. in the
list of devices to use.
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 04:33 PM devops Feature #3907 (Fix Under Review): ceph-deploy: be verbose about what is run and what is done (wit...
- 04:33 PM devops Feature #3913 (Fix Under Review): ceph-deploy: break mon into create/destroy
- 04:33 PM devops Feature #3920 (Fix Under Review): ceph-deploy: support other deb-based distros
- 04:32 PM devops Feature #3918 (Fix Under Review): ceph-deploy: osd create HOST:DIR[:JOURNAL]
- 04:32 PM devops Feature #3993 (Resolved): upstart/sysvinit: control whether crush position is readjusted on start
- 04:16 PM Revision 3806dc5e (ceph): task/ceph: Fix device list
- dict.items() returns a tuple, whereas we want
the values().
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 03:13 PM Revision 64e39667 (ceph): misc: get_wwn_id_map() needs to return dict
- If we can't find device ids, we need to return
a dict, not a list.
Signed-off-by: Sam Lang <sam.lang@inktank.com> - 02:52 PM rgw Feature #3667 (Fix Under Review): rgw: support extra canned acl params
- 02:50 PM rgw Feature #3992 (Resolved): rgw: refactor internal user API for RGW Admin
- 02:43 PM rgw Feature #3991 (Resolved): rgw: dr: region mgt changes: define datastructures
- 02:42 PM rgw Feature #3990 (Resolved): rgw: dr: implement new version objclass
- 02:40 PM rgw Feature #3989 (Resolved): rgw: dr: region mgt changes: radosgw admin changes
- 02:38 PM rgw Feature #3988 (Resolved): rgw: dr: region mgt changes: define/implement internal API
- 02:36 PM rgw Feature #3987 (In Progress): rgw: dr: region mgt changes: extend json parser with json decoder
- 02:36 PM rgw Feature #3987 (Resolved): rgw: dr: region mgt changes: extend json parser with json decoder
- 02:31 PM Linux kernel client Feature #3974 (Resolved): libceph: use data length rather than nr_pages
- commit 012d5bda1c0f229494c67098d00edfa24c531ea5
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 31 16:02:00 ... - 02:24 PM Revision dcf99e43 (ceph): nuke: Optionally check console status
- Only check the ipmi console status if the ipmi
parameters have been defined in .teuthology.yaml.
Signed-off-by: Sam ... - 02:20 PM Revision ac4ba69d (ceph): misc: Fix get_wwn_id_map() to be optional
- Not all plana nodes have symlinks setup when
we check /dev/disk/by-id/wwn-*. Instead of failing
here, just use the /... - 02:18 PM rbd Subtask #3741 (Resolved): krbd: rework request tracking code
- commit 9ac90ea3d8dd6ab82f3665a132ca29e6ada56ad8
Author: Alex Elder <elder@inktank.com>
Date: Thu Nov 22 00:00:08 ... - 02:17 PM rbd Feature #3754 (Closed): krbd: use new request tracking code for notify ack
- commit 1c8c3c5c571607a188203142020d80aa58e5e280
Author: Alex Elder <elder@inktank.com>
Date: Fri Nov 30 17:53:04 ... - 02:16 PM rbd Tasks #3755: krbd: use new request tracking code for sync object operations
- commit 5d08568324f53368f927cc10927b1b105533c044
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 17 12:25:27 ... - 01:44 PM rbd Tasks #3755 (Resolved): krbd: use new request tracking code for sync object operations
- commit 304819b1a49937753ee01aa7ccf8d66547a0be36
Author: Alex Elder <elder@inktank.com>
Date: Sat Jan 19 00:30:28 ... - 02:11 PM rbd Feature #3877 (Closed): krbd: don't wait for notify ack to complete
- commit a8a34efcac7a33e7631fe8bf25530bd4be0417f8
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 17 12:18:46 ... - 01:57 PM devops Feature #3909 (Resolved): ceph-deploy: update install for bobtail/argonaut urls
- 01:56 PM devops Feature #3923 (Resolved): ceph-deploy: discover HOST
- 01:48 PM Subtask #3986 (Rejected): Send to ceph-dev for review
- 01:48 PM Subtask #3985 (Rejected): api: Send to DH for Review
- 01:47 PM Feature #3984 (Resolved): api: Send Out DRAFT REST API for Review
- 01:46 PM Revision 933cc3c3 (ceph): run.py: Fix argument parsing for --name
- With the addition of the --name argument to the
teuthology program (run.py), jobs were failing
because --name was bei... - 01:45 PM Feature #3983 (Resolved): api: create initial DRAFT REST API Design
- 01:38 PM rbd Bug #3940 (Resolved): krbd: decrement obj request count when deleting
- commit 150fde1984ec8454c163e4f89a50416cd68edbc4
Author: Alex Elder <elder@inktank.com>
Date: Fri Jan 25 17:08:55 ... - 01:38 PM rbd Bug #3937 (Resolved): krbd: crash in rbd_assert(osd_req == obj_request->osd_req)
- commit 8d93192992301f8c3a288c8cf4dc8598ac4b8427
Author: Alex Elder <elder@inktank.com>
Date: Fri Jan 25 17:08:55 ... - 01:37 PM rbd Bug #3427 (Resolved): krbd: unmap does not remove block device properly
- commit bc7a62ee52cffc735cb8383b6d26648883f1a01e
Author: Alex Elder <elder@inktank.com>
Date: Mon Jan 14 12:43:31 ... - 01:37 PM Linux kernel client Bug #3800 (Resolved): libceph: check compatibility between ceph modules
- commit 4f6e0e37c103675df11c8e3d836d64cd24b31734
Author: Alex Elder <elder@inktank.com>
Date: Wed Jan 30 11:13:33 ... - 01:36 PM Linux kernel client Bug #3799 (Resolved): libceph/rbd: bio refs are messed up
- commit dfcc01f9f093ea960289e40ca2e73334c708c0f2
Author: Alex Elder <elder@inktank.com>
Date: Wed Jan 30 11:13:33 ... - 01:36 PM Linux kernel client Bug #3798 (Resolved): libceph/rbd: take reference to all bio's in list
- commit dfcc01f9f093ea960289e40ca2e73334c708c0f2
Author: Alex Elder <elder@inktank.com>
Date: Wed Jan 30 11:13:33 ... - 01:35 PM Linux kernel client Bug #3976: libceph: add some #ifdef CONFIG_BLOCK in messenger
- Sorry, I made a mistake and had to rebase.
commit 1eded6f9903ff388e7af08b2037fc3f3981cdfb2
Author: Alex Elder <el... - 01:32 PM Linux kernel client Bug #3976 (Resolved): libceph: add some #ifdef CONFIG_BLOCK in messenger
- commit a88b6b32770dc97b303cda7eade2feade3b945df
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 31 16:02:01 ... - 01:35 PM Linux kernel client Bug #3875: osd_client: don't use r_num_pages for bio requests
- Sorry, I made a mistake and had to rebase.
commit 012d5bda1c0f229494c67098d00edfa24c531ea5
Author: Alex Elder <el... - 01:32 PM Linux kernel client Bug #3875 (Resolved): osd_client: don't use r_num_pages for bio requests
- commit 06224afd90f261256b1e0a0db2334f39c21872a9
Author: Alex Elder <elder@inktank.com>
Date: Thu Jan 31 16:02:00 ... - 12:54 PM Feature #3982: Performance tests on branches that change the way pg info is stored
- Includes creating teuthology tasks.
- 12:48 PM Feature #3982: Performance tests on branches that change the way pg info is stored
- Need to look at xfs and btrfs (possibly ext4) with small IOs to determine whether to put the fixed sized chunk of the...
- 12:37 PM Feature #3982 (Resolved): Performance tests on branches that change the way pg info is stored
- 12:48 PM rbd Bug #1740 (Resolved): krbd: don't return head data when reading from a non-existent snapshot
- This was fixed a while ago.
- 12:32 PM Feature #3891 (In Progress): osd: move purged_snaps out of info
- 12:07 PM rgw Feature #3981 (New): rgw: handle really large buckets
- 11:58 AM rbd Bug #3980 (Won't Fix): rbd image created with size zero on a mixed cluster crashes rbd
- creating a rbd image with size 0 is allowed in bobtail but not on argonaut.
on a mixed cluster running argonaut[bu... - 11:13 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Nope, pretty vanilla install, other than the kernel.
I've attached the kickstart file. The cluster is managed by ... - 10:51 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Still failing on the chown of /etc/ceph ? Are you by any chance using selinix features, or anything that might cause...
- 10:19 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Nope, issue persists on a fresh install of the node. I'm not sure what information would be helpful, but if you let ...
- 09:44 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Nope, Running CentOS 6.3 with a custom kernel (3.6.9-vanilla at the moment). Give me about half an hour and I'll kic...
- 09:42 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Hi Steven -
Are you running Arch Linux ? If so, can you tell me the version, and also the versions of the rpm and... - 09:39 AM Bug #3979: Ceph 0.56.2 RPM does not install
- Hi,
I installed and upgraded Ceph RPMS on my fresh CentOS VM without issue. I can provide more information if needed. - 09:29 AM Bug #3979 (In Progress): Ceph 0.56.2 RPM does not install
- 09:00 AM Bug #3979 (Rejected): Ceph 0.56.2 RPM does not install
- Hey all,
I run a local Ceph mirror for a cluster. I mirrored the 0.56.2 RPMS this morning and went to update my nod... - 10:53 AM rgw Bug #3620 (Resolved): rgw:improve multiple user access keys scalability
- Fix merged into master, commit:0797be3f86df8b413256d69e3770ec39ed6e6912.
- 09:50 AM Feature #3890 (Resolved): osd: create tool to extract pg info and pg log from filestore
- 05:51 AM Revision fd1512fc (ceph): Build: Add -n to files and description for rbd-fuse in ceph.sepc.in
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 05:04 AM Revision de01bddb (ceph): Makefile: Install new rdb-fuse.8 man page
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 04:35 AM Revision 16cf9dc6 (ceph): build: Add new rbd-fuse package
- rdb-fuse is a new facility to map ceph rdb images to files.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com> - 04:32 AM Revision 7d1e8254 (ceph): Revert "Don't install rbd-fuse binary"
- This reverts commit 35e5d74e5c5786bc91df5dc10b5c08c77305df4e.
-> fix build instead - 03:29 AM Revision 334568e0 (ceph): rbd-fuse: quick and dirty manpage
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:44 AM Revision 91f8c3c8 (ceph): rbd-fuse: quick and dirty manpage
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:52 AM Revision 340b1cfe (ceph): ceph-filestore-dump.cc: don't use po::value<string>()->required()
- Don't use po::value<string>()->required() since this breaks build on
RHEL/CentOs6. Check if the options are set as in... - 12:34 AM Revision 1ee46c5e (ceph): doc: Added more detail to SSD section. Links to performance blogs.
- fixes: #3960
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 12:19 AM Revision c6d26efc (ceph): Merge pull request #37 from alram/master
- Add important note in doc/radosgw/config.rst
01/31/2013
- 11:58 PM Revision 2292fa6a (ceph): Add important note in doc/radosgw/config.rst
- For CentOS and similar, FastCgiWrapper is turned on by default.
This causes Apache to spawn radosgw processes. - 10:17 PM Revision 129a6600 (ceph): ceph-filestore-dump.cc: don't use po::value<string>()->required()
- Don't use po::value<string>()->required() since this breaks build on
RHEL/CentOs6. Check if the options are set as in... - 10:16 PM Revision 4c1d8d08 (ceph): ceph.spec.in: don't move libcephfs_jni files around
- Don't move libcephfs_jni files around from %{_libdir} to /usr/lib/jni/
in the buildroot. They should be placed in %{_... - 10:16 PM Revision 6e09cb9b (ceph): ceph.spec.in: extend fix for libedit-devel on special SUSE versions
- Extend fix for libedit-devel on special SUSE versions, use ncurses
also on src/ocf/Makefile and src/java/Makefile
Si... - 10:16 PM Revision 9235271a (ceph): ceph.spec.in: fix file section for ceph-resource-agents
- Create needed dirs (/usr/lib/ocf/resource.d/ceph) for the ceph-resource-agents
subpackage.
Signed-off-by: Danny Al-G... - 10:16 PM Revision 9b16036e (ceph): ceph.spec.in: move libcephfs_jni.so to ceph-devel
- Move libcephfs_jni.so to the ceph-devel package since so-files they
shouldn't be part of the library package.
Signed... - 09:06 PM Revision 3f53c3f0 (ceph): Validate format strings for CLS_ERR/CLS_LOG
- cls_log needed __attribute__((format(printf..)) to allow the compiler
to crosscheck format strings and arguments. Af... - 08:59 PM Revision fadc22c0 (ceph): ceph_manager: wait for admin socket on restart, use for set_config
- Fixes: #3966
Signed-off-by: Samuel Just <sam.just@inktank.com> - 08:51 PM rbd Bug #3978 (Resolved): krbd qa: concurrent.sh test leaves something read-only
- I don't know what exactly is happening here, but it appears
that after running the "rbd/concurrent.sh" workunit, if
... - 08:01 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Well, after downgrading them they seem to work stable again. If it's related to leveldb, then upgrading leveldb as th...
- 07:50 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Both osd.7 and osd.15 have corrupted leveldb state. It's likely related to downgrading and then upgrading leveldb.
- 07:40 PM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Hi Sage!
Today I was brave and upgraded two more nodes (one has 1 osd, the other 3 osds). I worked for some time b... - 07:18 PM Bug #3971: can't attach rbd image volume to instance
- Does 'rbd ls volumes' show volume-5529a8cd-28db-4a72-a0f0-f7b2a221cf8d?
-> yes, i can see it - 07:01 PM Bug #3971: can't attach rbd image volume to instance
- +These're all information need to verify:
root@master:~# dpkg -l | grep librbd
ii librbd1 ... - 01:44 PM Bug #3971: can't attach rbd image volume to instance
- Does 'rbd ls volumes' show volume-5529a8cd-28db-4a72-a0f0-f7b2a221cf8d?
If so, could you provide a few more detail... - 02:20 AM Bug #3971 (Rejected): can't attach rbd image volume to instance
- my env:
libvirt-bin: 0.9.13-0ubuntu12.1~cloud0
ceph : 0.56.1
+ i tried disable module apparmor from system.
+... - 05:57 PM Cleanup #3977 (Resolved): Do a great stream operator const cleanup!
- I just spent a little while trying to figure out why the compiler couldn't resolve operator<< (the stream operator) o...
- 05:55 PM Revision 97c6619d (ceph): qa: update the rbd/concurrent.sh workunit
- A few changes, now that a few rbd problems have been fixed.
First, the more substantive changes:
- Generate a sou... - 05:37 PM Documentation #3960: [Document bug]MON and MDS do not need a ssd for data storage.
- John Wilkins:
What do you mean by:
>One way Ceph accelerates filesystem performance is to segregate the storage of ... - 04:35 PM Documentation #3960 (Resolved): [Document bug]MON and MDS do not need a ssd for data storage.
- I removed the reference to monitors, added detail on sequential write throughput, and a link to an example for a CRUS...
- 05:14 PM Revision 8f9267cf (ceph): thrashosds: note assumption for powercycling
- 02:55 PM Revision 8e566f6f (ceph): marginal/osd_powercycle: OSD powercycle thrashing
- Tasks to run while thrashing osds using ipmi to powercycle.
This currently runs in the marginal suite only.
Signed-o... - 02:45 PM Linux kernel client Bug #3976 (Resolved): libceph: add some #ifdef CONFIG_BLOCK in messenger
- There are two spots in the messenger code that would
cause a build failure if CONFIG_BLOCK weren't define.
I've a... - 02:23 PM Revision 77e8d801 (ceph): Remove console.py
- Handling of ipmi via the console is now done through the
Console class in teuthology/orchestra/remote.py.
Signed-off... - 02:23 PM Revision 8f720454 (ceph): Assign devices to osds using the device wwn
- Linux doesn't guarantee device names (/dev/sdb, etc.)
are always mapped to the same disk. Instead of assigning
nomin... - 02:23 PM Revision 58111595 (ceph): Support power cycling osds/nodes through ipmi
- This patch defines a RemoteConsole class associated
with each Remote class instance, allowing
power cycling a target ... - 02:23 PM Revision 87b98496 (ceph): add --name option to teuthology
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 02:23 PM Revision ace4cb07 (ceph): Replace /tmp/cephtest/ with configurable path
- Teuthology uses /tmp/cephtest/ as the scratch test directory for
a run. This patch replaces /tmp/cephtest/ everywher... - 02:23 PM Revision 3eb19c81 (ceph): Replace /tmp/cephtest/ with configurable path
- Teuthology uses /tmp/cephtest/ as the scratch test directory for
a run. This patch replaces /tmp/cephtest/ everywher... - 02:21 PM rbd Bug #3975 (Rejected): librbd: xfstests 008 failed inside qemu
- This one's not a problem. This test pokes random holes in a
file (or maybe fills random spots). And when done it s... - 02:05 PM rbd Bug #3975 (Rejected): librbd: xfstests 008 failed inside qemu
- From xfstests output in ubuntu@teuthology:/a/teuthology-2013-01-29_20:00:04-regression-bobtail-master-basic/7794/remo...
- 02:12 PM devops Feature #3912 (Fix Under Review): ceph-deploy: break osd into create/destroy
- 02:12 PM devops Feature #3923 (Fix Under Review): ceph-deploy: discover HOST
- commit:56b996b76f37fb6a7c3ffc812e87a8cbd6f8c3b8
- 02:12 PM devops Feature #3909 (Fix Under Review): ceph-deploy: update install for bobtail/argonaut urls
- commit:3c1e4d1d73556560e06686843ed1010174b5ffda
- 02:01 PM Bug #3970 (Resolved): cls_log should be declared with __attribute__(format..) so -Wformat validat...
- commit:3f53c3f016ab0db1a33848ac406239dc07204ea2
- 01:59 PM Linux kernel client Feature #3974 (Resolved): libceph: use data length rather than nr_pages
- While looking at http://tracker.ceph.com/issues/3875 I learned
that the nr_pages field in a ceph message is never re... - 01:58 PM Revision 14730276 (ceph): Fixes for syntax errors found by pyflakes.
- This patch includes minor fixes to the teuthology
python code for syntax errors found by running
check-syntax.sh (whi... - 01:56 PM Revision 3390cc30 (ceph): Scripts to use pyflakes to check python syntax.
- pyflakes runs a basic syntax checker against python code.
The added check-syntax.sh script and Makefile run pyflakes
... - 01:00 PM Bug #3966: osdthrasher: does tell on osd just after restarting it
- pushed fix to master, fadc22c0b9e1755b1d1826fcfe8be71e28574bc9 (teuthology)
- 12:15 PM Revision c3468f76 (ceph): PGMap: fix -Wsign-compare warning
- Fix -Wsign-compare compiler warning:
mon/PGMap.cc: In member function 'void PGMap::apply_incremental
(CephContext*,... - 11:22 AM Bug #3906: ceph-mon leaks memory during peering
- So, today I upgraded my whole cluster to 0.56.2, then added a bunch more OSDs (from 84 -> 144). At peering time monit...
- 09:09 AM rgw Feature #3973 (New): rgw: Handle requests sent in non-UTC time
- Executing a S3 Request using the following Date Header...
- 07:35 AM Bug #3972 (Resolved): new boost dependency: libboost-program-options
- libboost-program-options is now required to build master, this prerequisite is not mentioned in the documentation.
- 06:50 AM Revision 0758faba (ceph): Add ceph-filestore-dump to the packaging
- Feature: #3890
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 05:18 AM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- I disabled scrubbing using
> ceph osd tell \* injectargs '--osd-scrub-min-interval 1000000'
> ceph osd tell \* in... - 12:16 AM Revision 8fd8534b (ceph): osd_types: add recovery counts to object_sum_stats_t
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 4aea19ee60fbe1106bdd71de2d172aa2941e8aab) - 12:16 AM Revision 8ab77bd4 (ceph): osd: track recovery ops in stats
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a2495f658c6d17f56ea0a2ab1043299a59a7115b) - 12:16 AM Revision 8d2d396c (ceph): mon/PGMap: include timestamp
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 76e9fe5f06411eb0e96753dcd708dd6e43ab2c02) - 12:16 AM Revision 7f149cf6 (ceph): mon/PGMap: report recovery rates
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 208b02a748d97378f312beaa5110d8630c853ced) - 12:16 AM Revision 7fd7a5ee (ceph): mon/PGMap: report IO rates
- This does not appear to be very accurate; probably the stat values we're
displaying are not being calculated correctl... - 12:16 AM Revision 5a6b9af9 (ceph): mon: smooth pg stat rates over last N pgmaps
- This smooths the recovery and throughput stats over the last N pgmaps,
defaulting to 2.
Signed-off-by: Sage Weil <sa...
01/30/2013
- 11:41 PM Revision ab778cb1 (ceph): doc: v0.56.2 release notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:21 PM Revision 4a950aa9 (ceph): Move read_log() function to prep for next commit
- Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 10:21 PM Revision 3c8d7d78 (ceph): osd: create tool to extract pg info and pg log from filestore
- New application ceph-filestore-dump created that mounts filstore
and can dump info or log in JSON when an OSD is not ... - 08:52 PM Revision a63fac32 (ceph): task: mon_clock_skew_check: use absolute value when comparing mon_skew
- The monitors may report either positive or negative clock skews, and by
not using an absolute value we were constantl... - 08:52 PM Revision 89e09fa9 (ceph): task: mon_clock_skew_check: mark as ran once if an expected skew was found
- ... even if we didn't get a clean/finished result from the monitors
This ought to significantly cut the waiting time... - 07:50 PM Revision b571f8ee (ceph): PGMap: fix -Wsign-compare warning
- Fix -Wsign-compare compiler warning:
mon/PGMap.cc: In member function 'void PGMap::apply_incremental
(CephContext*,... - 07:32 PM Revision b0d4dd21 (ceph): test_libcephfs: fix xattr test
- Ignore the ceph.*.layout xattrs.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:02 PM Bug #3970: cls_log should be declared with __attribute__(format..) so -Wformat validates the form...
- 04:57 PM Bug #3970 (Resolved): cls_log should be declared with __attribute__(format..) so -Wformat validat...
- It'll involve some changes to callers to fix all the harmless errors, but may find some significant
ones and avoid a... - 04:49 PM Bug #3938 (In Progress): ceph-mon crashed on mixed bobtail-argonaut cluster (2 argonaut mons, 1 b...
- Have a cluster set-up and ready to start trying to reproduce this in the morning.
- 02:13 PM Bug #3938: ceph-mon crashed on mixed bobtail-argonaut cluster (2 argonaut mons, 1 bobtail)
- No, didn't have it set up. I could probably reproduce if necessary.
- 04:32 PM devops Feature #3965: upstart: ulimit -n hardcoded; doesn't use 'max open files' config setting
- I guess there are settings in the upstart config files, but they aren't derived from ceph.conf.
I imagine there are w... - 11:09 AM devops Feature #3965 (Rejected): upstart: ulimit -n hardcoded; doesn't use 'max open files' config setting
- 3900 tweaked the setting of ulimit -n "max open files" on all daemons in the cluster, but,
at present, we only have... - 03:37 PM CephFS Feature #3540 (Fix Under Review): mds: maintain per-file backpointers on first file object
- Initial implementation in wip-bt. Needs review.
- 02:13 PM Bug #3883: osd: leaks memory (possibly triggered by scrubbing) on argonaut
- The burnupi57 cluster (wip-f) does not appear to be leaking after all, the osds seem to have leveled off at around 35...
- 02:10 PM rbd Bug #3937: krbd: crash in rbd_assert(osd_req == obj_request->osd_req)
- The patch is reviewed and ready to push to the testing
branch, and I will do that in a day or so.
I'm going to le... - 02:09 PM rgw Feature #3968 (Resolved): https should work for rest-bench
- Trying to set the protocol to https by using the --protocol=https flag does not work. ...
- 02:08 PM rbd Bug #3940: krbd: decrement obj request count when deleting
- Reviewed and ready to push to master. Will do that in a day or so.
- 02:07 PM rbd Bug #3427: krbd: unmap does not remove block device properly
- Reviewed and ready to push to the ceph-client "testing" branch.
I'm going to wait a day or two before pushing this... - 01:34 PM Linux kernel client Bug #3967 (Resolved): libceph: complete linger requests only once
- Currently if a linger request gets resubmitted by the osd
client, its callback function (if provided) will get calle... - 01:05 PM Documentation #3960 (In Progress): [Document bug]MON and MDS do not need a ssd for data storage.
- You are correct. The machines and processes would only boot a bit faster. The way to accelerate metadata servers is t...
- 12:12 PM Bug #3966 (Resolved): osdthrasher: does tell on osd just after restarting it
- figured out where the thrasher errors are coming from:...
- 11:31 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- ...and to answer your other question Alex, there's now a workunit test Sage just added
in c782d2ac531cbb7650968e62f0... - 11:00 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- Josh thinks 32-bitness probably doesn't matter, and remembers problems with snapshots that were fixed long ago; I gue...
- 10:55 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- I don't know if Sage tested 32-bit, or if it matters, and no, that script was just a reproduction scenario; as far as...
- 06:25 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- So is this then a request to port whatever it was that
fixed the problem back to 3.2?
If so, how do we prioritize... - 01:10 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- added test to suite, commit:c782d2ac531cbb7650968e62f0b24e6136a64359
- 12:15 AM rbd Bug #3964: krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd image with sn...
- This works fine on current testing 3.6.0-00210-g8cc17ca
- 11:16 AM rbd Bug #3961 (Resolved): 32-bit cls_rbd tries cls_log with %d for 64-bit int, segfaults
- commit:e253830abac76af03c63239302691f7fac1af381 on next
- 09:37 AM rbd Subtask #3741: krbd: rework request tracking code
- My testing on this code is nearly complete. However, I'm going
to hold off on pushing this (along with the changes ... - 06:34 AM rbd Subtask #3741: krbd: rework request tracking code
- 09:30 AM Linux kernel client Bug #3740 (Resolved): ceph-client: change to be based on 3.8-rc2
- I have finished my testing and have now updated the
ceph-client "testing" branch to be based on 3.8-rc5,
with the p... - 06:14 AM Linux kernel client Bug #3740: ceph-client: change to be based on 3.8-rc2
- I discussed this with Sage yesterday. We're now up to
Linux 3.8-rc5. Merging our testing branch into v3.5-rc5
pro... - 09:08 AM Revision 0c872491 (ceph): rbd: add rbd_cli_misc with map-snapshot-io.sh
- 09:06 AM Revision c782d2ac (ceph): qa: add test for rbd map and snapshots
- This tests for the behavior reported in #3964. It passes on the current
code, but fails on 3.2 in squeeze (and 32-bi... - 09:05 AM Revision 6b493502 (ceph): Merge remote-tracking branch 'gh/next'
- 08:56 AM Linux kernel client Bug #3798 (In Progress): libceph/rbd: take reference to all bio's in list
- It looks like the extra reference that the osd client requires
of the first bio on the list isn't necessary. Nor wo... - 08:41 AM Linux kernel client Bug #3800: libceph: check compatibility between ceph modules
- Sage, I already implemented the fix, and it's pretty trivial,
and it's generally useful. By "won't fix" do you mean... - 07:54 AM Revision 586538e2 (ceph): v0.56.2
- 07:40 AM Linux kernel client Bug #3799 (In Progress): libceph/rbd: bio refs are messed up
- Looking at the code here, the osd client isn't really doing
anything with the bio pointer. It is simply a middleman... - 07:34 AM Revision bcb8dfad (ceph): cls_rbd, cls_rgw: use PRI*64 when printing/logging 64-bit values
- caused segfaults in 32-bit build
Fixes: #3961
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil ... - 07:32 AM Revision e253830a (ceph): cls_rbd, cls_rgw: use PRI*64 when printing/logging 64-bit values
- caused segfaults in 32-bit build
Fixes: #3961
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil ... - 06:47 AM rbd Bug #3927 (Closed): krbd: I/O errors (ENXIO) during rbd/kernel.sh workunit
- It turns out this new behavior is a good thing, we're just
reporting errors now where we apparently did not previous... - 06:47 AM rbd Bug #3745 (Rejected): krbd: individual response errors are ignored
- I no longer believe this is a problem. Although there is no
aggregate result value for a collection of osd requests... - 06:36 AM Linux kernel client Bug #3959 (Duplicate): krbd: decrement img_request->obj_request_count when deleting
- Found it! http://tracker.ceph.com/issues/3940
already documents this. - 06:35 AM rbd Feature #3877: krbd: don't wait for notify ack to complete
- 06:35 AM rbd Tasks #3755: krbd: use new request tracking code for sync object operations
- 06:35 AM rbd Feature #3754: krbd: use new request tracking code for notify ack
- 03:48 AM Revision 77f57411 (ceph): mds: move lexical_cast and assert re-#include to the top
- We should keep the re-#includes immediately following the offender, and
documented.
Signed-off-by: Sage Weil <sage@i... - 03:11 AM Bug #3948: problems from leveldb static linkage and leveldb downgrade
- Hi Sage,
does it matter that the OSD is now down for around 1-2 days or will it just pickup any changes made to th... - 03:00 AM Revision 35e5d74e (ceph): Don't install rbd-fuse binary
- fixes packaging warnings
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 02:43 AM Revision 23923ee9 (ceph): mds/Server.cc: fix warring assert.h's
- New include boost/lexical_cast.hpp apparently drags in the system
assert.h on quantal and squeeze at least, breaking ... - 02:42 AM Revision 25e9a0be (ceph): mon: require name for 'auth add ...' command
- Otherwise we interpret the empty string as 'unknown.'.
Fixes: #3956
Signed-off-by: Sage Weil <sage@inktank.com> - 02:19 AM Bug #3595: ceph-osd and ceph-mds crash on Debian Squeeze
- root@cluster:~# ceph-osd
Segmentation fault
root@cluster:~# ceph-osd -h
Segmentation fault
root@cluster:~# ceph-... - 01:07 AM Revision a731da99 (ceph): Merge remote-tracking branch 'origin/wip-fuse-create-fix'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 01:05 AM Revision e9a6694d (ceph): client: return errors to the user if fsync fails
- To do so, we allow callers of _flush(Inode) to pass in a Context
as well. This Context is then given to the ObjectCac... - 01:03 AM RADOS Feature #3807 (Fix Under Review): crush: simple commands to create common rules
- see wip-osd-commands
- 12:49 AM Revision 5a7c5088 (ceph): init-ceph: make ulimit -n be part of daemon command
- ulimit -n from 'max open files' was being set only on the machine
running /etc/init.d/ceph. It needs to be added to ... - 12:48 AM Revision 84a024b6 (ceph): init-ceph: make ulimit -n be part of daemon command
- ulimit -n from 'max open files' was being set only on the machine
running /etc/init.d/ceph. It needs to be added to ... - 12:34 AM Revision c2e50e58 (ceph): Merge remote-tracking branch 'gh/wip-recovery-stats-b'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 12:26 AM Revision 1564c3a0 (ceph): Merge branch 'wip-vxattr'
- Reviewed-by: Sam Lang <sam.lang@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:25 AM Revision ba32ea94 (ceph): client: list only aggregate xattr, but allow setting subfield xattrs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:25 AM Revision 84751489 (ceph): client: note presence of dir layout in inode operator<<
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:25 AM Revision 09f28541 (ceph): mds: fix client view of dir layout when layout is removed
- We weren't handling the case where the projected node has NULL for the
layout properly. Fixes the client's view when... - 12:25 AM Revision ebebf72f (ceph): mds: handle ceph.*.layout.* setxattr
- Allow individual fields of file or dir layouts to be set via setxattr.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:25 AM Revision db31a1f9 (ceph): mds: allow dir layout/policy to be removed via removexattr on ceph.dir....
- This lets a user remove a policy that was previously set on a dir.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:25 AM Revision 61fbe27a (ceph): qa: add layout_vxattrs.sh test script
- Test virtual xattrs for file and directory layouts.
TODO: create a data pool, add it to the fs, and make sure we can... - 12:24 AM Revision e51299fb (ceph): mds: open mydir after replay
- In certain cases, we may replay the journal and not end up with the
dirfrag for mydir open. This is fine--we just ne... - 12:24 AM Revision ad7ebad7 (ceph): client: allow ceph.* xattrs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:24 AM Revision febb9650 (ceph): client: move xattr namespace enforcement into internal method
- This captures libcephfs users now too.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:24 AM Revision 3f82912a (ceph): client: implement ceph.file.* and ceph.dir.* vxattrs
- Display ceph.file.* vxattrs on any regular file, and ceph.dir.* vxattrs
on any directory that has a policy set.
Sign...
Also available in: Atom