Project

General

Profile

Activity

From 01/31/2014 to 03/01/2014

03/01/2014

11:41 PM Revision 7889acbf (ceph): ceph-manager: fix ec_pool parameters
* the crush ruleset and the pool create parameters must be identicals
k=2 m= 1
* the --property argument is invalid...
Loïc Dachary
10:54 PM Revision 59ff572f (ceph): OpTracker: clarify that unregister_inflight_op is only called if enabled
The !tracking_enabled branch actually had a leak which was unreachable
since the caller does the check for tracking_e...
Samuel Just
10:54 PM Revision 718cda6e (ceph): TrackedOp: clear_payload as well in unregister_inflight_op
We want to minimize the cost of maintaining the historic ops.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:54 PM Revision d4118e15 (ceph): MOSDECSubOpWrite: drop transaction, log_entries in clear_buffers
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:54 PM Revision 62fd382f (ceph): osd_types,PG: trim mod_desc for log entries to min size
In the event that mod_desc.bl contains pointers into a large
message buffer, we'd otherwise end up keeping around the...
Samuel Just
10:53 PM Revision fc9b8ef0 (ceph): MOSDOp: drop ops vector in clear_data()
Otherwise, clear_data on MOSDOp will leave essentially
all of the buffers intact. This is a problem since the
OpTrac...
Samuel Just
10:53 PM Revision 1ea59f6c (ceph): ReplicatedPG: delete mark_all_unfound_lost transactions after completion
This was a minor memory leak.
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum
07:13 PM Bug #7576 (Resolved): osd: large skew in pg epochs (dumpling)
Observed a cluster with pgs at very different pg epochs (~17000 and ~24000). This isn't supposed to happen on start ... Sage Weil
05:46 PM Revision 84ba4cf2 (ceph): Merge pull request #1339 from ceph/wip-7572
mon: fix 'pg dump' JSON output
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
05:13 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...

2014-03-01 00:13:39.895495 7efefcde2700 10 osd.4 pg_epoch: 76 pg[4.1( v 74'1454 lc 17'513 (0'0,74'1454] local-les=7...
David Zafman
05:05 PM Revision e19dffb8 (ceph): mon: fix 'pg dump' JSON output
This was broken by 40bdcb88. The 'acting' array had
the up_primary and acting_primary appended.
Fixes: #7572
Signe...
John Spray
03:58 PM Bug #6736 (Resolved): Bugs in per pool IOPs/recovery statistics
Loïc Dachary
03:56 PM Subtask #5487 (Closed): Factor out ObjectContext / ReplicatedPG::object_contexts
Obsoleted. Loïc Dachary
03:55 PM Subtask #6895 (Rejected): omap needs to be disablable on a per-pool basis, this needs to be requi...
Not needed. Loïc Dachary
03:10 PM Bug #7542 (Resolved): ec misdirected op
Samuel Just
01:26 PM Revision 1a4657a3 (ceph): req_state: fix uninitialized bool var
CID 717359 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "bucket_exists...
Danny Al-Gaaf
12:45 PM Revision 605e6450 (ceph): Objecter::recalc_op_target: fix uninitialized scalar variable
CID 1160848 (#1 of 1): Uninitialized scalar variable (UNINIT)
uninit_use: Using uninitialized value "best".
Init 'b...
Danny Al-Gaaf
12:33 PM Revision 754a3689 (ceph): PGMonitor: fix uninitialized scalar variable
Fix type handling in dump_stuck_pg_stats. If type is type doesn't
match to known PGMap::STUCK_* type print out a mess...
Danny Al-Gaaf
12:11 PM Revision 1747c589 (ceph): MDCache: fix potential null pointer deref
CID 716921 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "dir" to fun...
Danny Al-Gaaf
11:10 AM Revision 93c09836 (ceph): MDCache::handle_discover: fix null pointer deref
CID 716990 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might b...
Danny Al-Gaaf
10:53 AM Revision 249e2107 (ceph): FileStore: fix resource leak in queue_transactions() blackhole case
CID 1135931 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "ondisk" going out of scope leaks the ...
Danny Al-Gaaf
10:44 AM Revision 3cd751b0 (ceph): c_read_operations.cc: fix resource leak
CID 1188154 (#2 of 2): Resource leak (RESOURCE_LEAK)
overwrite_var: Overwriting "op" in "op = rados_create_read_op()...
Danny Al-Gaaf
10:36 AM Revision ad9b6d2f (ceph): c_write_operations.cc: fix some ioctx resource leaks
CID 1160833 (#3 of 3): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "ioctx" going out of scope leaks the s...
Danny Al-Gaaf
10:16 AM Revision e8533ee4 (ceph): ReplicatedBackend: check result of dynamic_cast to fix null pointer deref
CID 1188135 (#1 of 1): Unchecked dynamic_cast (FORWARD_NULL)
var_deref_model: Passing null pointer "t" to function
...
Danny Al-Gaaf
10:02 AM Revision 8d6b25a1 (ceph): mds: use "lookup-by-ino" helper to handle LOOKUPPARENT request
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
09:48 AM Bug #7572 (Resolved): Bad 'acting' array in JSON 'pg dump' output
Do you happen to know why the commit shows three times as associated to this issue ? Loïc Dachary
09:05 AM Bug #7572 (Fix Under Review): Bad 'acting' array in JSON 'pg dump' output
https://github.com/ceph/ceph/pull/1339 John Spray
08:58 AM Bug #7572 (Resolved): Bad 'acting' array in JSON 'pg dump' output

Example:...
John Spray
09:29 AM RADOS Feature #7573 (New): Add an epoch argument to 'osd crush dump'

For management apps like calamari, we would like to be able to grab the "osd dump" and "crush dump" data reliably f...
John Spray
09:21 AM Revision f3976c16 (ceph): Merge pull request #1334 from kazhang/wip-get-hit_set-parameter
OSDMonitor: enable getting hit set parameters
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
08:22 AM Revision dc20c7d6 (ceph): OSDMonitor: enable getting hit set parameters
We would like to get the hit set parameters: hit_set_type |
hit_set_period | hit_set_count | hit_set_fpp via OSDMonit...
Kai Zhang
05:57 AM Revision 332c0e24 (ceph): Merge pull request #1333 from ceph/wip-s3radoscheck-wusui
Use pgrep radosgw to determine if rados gateway is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
05:43 AM Revision 5b88856c (ceph): Use pgrep radosgw to determine if rados gateway is running.
Fixes: 7528
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
05:13 AM Revision 0ed63fd3 (ceph): client: fix Client::trim_caps()
allow trimming non-auth caps if the issued auth caps include all
caps client wants/uses.
Signed-off-by: Yan, Zheng <...
Yan, Zheng
05:13 AM Revision cdbe413c (ceph): client: update dirfragtree/fragmap according to mds request reply
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:08 AM Revision 63e34639 (ceph): Merge pull request #1326 from ceph/wip-7542
Wip 7542
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
05:04 AM Revision a7b7c311 (ceph): client: use ceph_seq_cmp() to compare cap seq/mseq
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:04 AM Revision 1ddc951b (ceph): client: remove exported caps when handling cap import message
Version 3 cap import message includes the ID of the exported
caps. It allow us to remove the exported caps if we stil...
Yan, Zheng
05:04 AM Revision 4bdecf1c (ceph): client: add imported caps when handling cap export message
Version 3 cap export message includes information about the imported
caps. It allows us to add the imported caps if t...
Yan, Zheng
05:04 AM Revision 0638d612 (ceph): client: add flushing inode to proper list when auth mds changes
add flushing inode to the new auth MDS' flushing caps list
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
05:04 AM Revision 23de48b2 (ceph): client: check inode's cap when looking up dentry
Some inodes in readdir reply may have no caps. Getattr mds request
for these inodes can return -ESTALE. The fix is co...
Yan, Zheng
05:04 AM Revision 214977ab (ceph): client: choose hash function according to dir layout
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:04 AM Revision 3dd323e2 (ceph): client: don't send cap release when removing exported cap
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:46 AM Feature #7457 (Fix Under Review): mon: prevent addition of non-empty pools as a tier
Sage Weil
12:24 AM Revision 0bf5f866 (ceph): store_test.cc: fix unchecked return value
CID 1188126 (#1 of 1): Unchecked return value (CHECKED_RETURN)
2. check_return: Calling function "ObjectStore::stat(...
Danny Al-Gaaf

02/28/2014

11:32 PM Revision a01d3ca8 (ceph): Merge pull request #213 from ceph/wip-kdb-except
Allow setting kdb to fail. Alfredo Deza
11:19 PM Revision 7eefe85c (ceph): histogram.h: fix potential div by zero
CID 1188131 (#1 of 1): Division or modulo by zero (DIVIDE_BY_ZERO)
divide_by_zero: In expression "lower_sum * 100000...
Danny Al-Gaaf
11:04 PM Revision 500206d8 (ceph): ReplicatedPG.cc: fix ressource leak, delete cb
CID 1188145 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "cb" going out of scope leaks the stor...
Danny Al-Gaaf
10:16 PM Revision fd507ed3 (ceph): Allow setting kdb to fail.
Some kernels (primarily Debian distro kernels) do not support
setting kdb. Rather than having the entire test fail.
...
Sandon Van Ness
10:09 PM Revision 84decc11 (ceph): Merge pull request #1331 from ceph/wip-cache-pool
mon/OSDMonitor: make default false-positive-probability 5%
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
07:27 PM Revision fbb1ec88 (ceph): ECBackend: don't leak transactions
Fixes: #7539
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
07:26 PM Revision b0d42644 (ceph): OSD::handle_misdirected_op: handle ops to the wrong shard
OSD recomputes op target based on current OSDMap. With an EC pg, we can get
this result:
1) client at map 512 sends a...
Samuel Just
07:13 PM Revision 4f31eb01 (ceph): Merge pull request #212 from ceph/wip-limit
Added --limit option to teuthology-suite. wusui
07:12 PM Revision 123ff9e1 (ceph): osd: stray pg ref on shutdown
Move agent_clear() from only being done when becoming replica
Do it in clear_primary_state() whenever we stop being...
David Zafman
05:35 PM Revision 07ddfcfa (ceph): Merge pull request #1332 from ceph/wip-pg-msg
mon/OSDMonitor: missing space in string
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@da...
Loïc Dachary
05:16 PM Revision 448fc0e9 (ceph): mon/OSDMonitor: missing space in string
Minor glitch. Was printing ..."exceeds per-OSD max of32)"
Signed-off-by: John Spray <john.spray@inktank.com>
John Spray
05:04 PM Revision 4b5338fa (ceph): Merge pull request #211 from ceph/wip-7554
mds_thrash #7554 Zack Cerza
04:34 PM Revision 799cde0a (ceph): Fix python-requests package dependencies.
python-ceph does not require requests, but ceph-common does (for ceph-brag).
Signed-off-by: Dan Mick <dan.mick@inkta...
Dan Mick
04:34 PM Revision 4baa632e (ceph): Merge pull request #1323 from ceph/wip-requests-dependencies
Fix python-requests package dependencies.
Backport: firefly
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:16 PM Revision bfad17bf (ceph): librados: fix ObjectIterator::operator= for the end iterator
We can't set a shared_ptr to NULL, we need to reset it instead. Add
another test for various permutations of this.
F...
Josh Durgin
04:11 PM Revision a850a387 (ceph): doc/dev/cache-pool: fix notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:06 PM Revision f0241c8a (ceph): mon/OSDMonitor: make default false-positive-probability 5%
This is a more conservative default (as in, less memory consumed) for
newly created cache pools.
Signed-off-by: Sage...
Sage Weil
03:40 PM Feature #7571 (Resolved): erasure code: implicit ruleset creation when a pool is created
"work in progress":https://github.com/ceph/ceph/pull/1350
Here is the current, mandatory, sequence to create an er...
Loïc Dachary
03:08 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
Okay, leaving this alone for the moment — that patch is a good start, and I think the MDLog stuff is actually okay (b... Greg Farnum
02:02 PM CephFS Bug #7565: Failed assert in check_rstats
What's the bug with check_rstats? Is num_head_items just not expected to be valid at this stage of replay?
Either ...
Greg Farnum
01:44 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
Unless this part has been fixed by a newer kernel, we still need to deal with it. In particular we were concerned tha... Greg Farnum
12:35 PM Bug #7539: Firefly EC pool massive memory leak during writes
Ran more tests on 0.77-619-gfbb1ec8-1saucy, still seeing lots of memory usage. Ran with optracker debugging, output ... Mark Nelson
06:55 AM Bug #7539: Firefly EC pool massive memory leak during writes
Tested wip-7542 this morning using 0.77-616-g36fda70-1saucy. Still seeing rapid memory growth (without valgrind, abo... Mark Nelson
06:58 AM Feature #7567 (Closed): mon: 'service network', 'cluster network', 'admin network'
Currently clients, daemons, monitor peers, and admins all use the same monitor IP to communicate.
Extend the monma...
Sage Weil
05:09 AM Bug #7423: erasure code: ./rados get retrieves a larger object
It is likely not the proper way to fix it. It seems to work but it may be better to make it so ECBackend.cc does not ... Loïc Dachary
05:07 AM Bug #7423 (Fix Under Review): erasure code: ./rados get retrieves a larger object
Loïc Dachary
12:34 AM Revision bd9748d5 (ceph): Added --limit option to teuthology-suite.
Use --limit to limit the number of jobs being scheduled during
teuthology-suite. Also can be used with schedule_suite...
Yuri Weinstein

02/27/2014

09:29 PM CephFS Cleanup #3742 (Resolved): Remove old Hadoop wrappers and configuration options
Noah Watkins
09:27 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Actually, yeh I'll look at this. Noah Watkins
03:30 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Is this still an issue, Noah? Greg Farnum
09:23 PM CephFS Bug #4861 (Rejected): Alter Java components to build against Java 1.6 (or 1.7)
Noah Watkins
09:23 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Closing. I'm not sure what the problem is here.. it looks like I am saying that the code builds for a super old versi... Noah Watkins
03:26 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Do you know the state of the Java code right now, Noah? I wonder if this got done already or is still a bug requiring... Greg Farnum
07:29 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
The race still exists, but I don't think it's big problem. Because even if ceph_get_dentry_parent_inode() returns a w... Zheng Yan
04:03 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
Is this still a problem? Greg Farnum
06:39 PM Revision 22825c25 (ceph): mds_thrash: Refactor gevent usage + get traceback
This simplifies the code to make MdsTrash be a greenlet
(as it logically is) rather than encapsulating one that
gets ...
John Spray
06:39 PM Revision 8dfcfa4a (ceph): mds_thrash: Fix a potential getitem on None
get_mds_status returns None for things it can't see,
so have to check for Noneness on all its outputs.
Signed-off-by...
John Spray
05:14 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
who cares 3.5 kernel? Zheng Yan
03:28 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
Sounds like this might require some protocol work and it's in the kernel client — high! Greg Farnum
05:13 PM CephFS Bug #7565: Failed assert in check_rstats
it's CDir::check_rstats() bug, not rstat corruption. Zheng Yan
04:46 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats

This is odd, because it's happening very reproducibly, is not unique to the tip of master, but apparently isn't hap...
John Spray
04:51 PM CephFS Bug #1181: mds: old_inodes crash
Snapshots
See also #4248, which may or may not have anything to do with this.
Greg Farnum
04:50 PM CephFS Bug #926: mds: fix rename between snaprealms
Snapshots Greg Farnum
04:50 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
#7326 Greg Farnum
04:48 PM CephFS Bug #2740: mds: crash in Objecter when shutting down too early
I'm pretty sure this is fixed, but let's check it out and make sure. Greg Farnum
04:45 PM CephFS Bug #3596: ceph-fuse: crash in mds rejoin
Snapshots Greg Farnum
04:44 PM CephFS Bug #2187: pjd chown/00.t failed test 97
This is either an MDS or protocol bug since we've seen it across clients. Greg Farnum
04:43 PM CephFS Bug #2863: client: does not tolerate traceless replies from mds
uclient failure-case: low priority.
I believe we've established that the kclient does not suffer from this issue, ...
Greg Farnum
04:42 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
Confirmed MDS bug! Greg Farnum
04:41 PM Bug #7458: osd: stray pg ref on shutdown
David Zafman
04:40 PM CephFS Bug #2679: POSIX file lock not released on process termination
Let's see if we can reproduce this as it's some combination of kclient, MDS, or protocol bug. Greg Farnum
04:38 PM CephFS Bug #1666: hadoop: time-related meta-data problems
Also see #7564
But low priority, for this is Hadoop
Greg Farnum
04:36 PM CephFS Bug #4212: mds: open_snap_parents isn't called all the times it needs to be
Snapshots Greg Farnum
04:36 PM CephFS Bug #4213: mds: old_parents is never cleaned up
Snapshots Greg Farnum
04:35 PM CephFS Fix #7564: synchronize MDS and client times in a way that makes pjd happy even under clock skew
See also #1666 Greg Farnum
04:28 PM CephFS Fix #7564 (Duplicate): synchronize MDS and client times in a way that makes pjd happy even under ...
See #854. We have ops happen on both the client and the MDS, and so sometimes one time wins and sometimes the other d... Greg Farnum
04:29 PM CephFS Bug #854 (Duplicate): unsynchronized clocks between kernel-client/cmds cause PJD fstest failures
I'm closing this in favor of fix ticket #7564. Greg Farnum
04:13 PM CephFS Bug #1874: Running `git gc` on a bare git repository hosted by ceph results in a bus error.
So basically two things could have gone wrong here:
1) The OSD replied with a bad tid (unlikely)
2) the client forg...
Greg Farnum
04:02 PM CephFS Bug #4370: mds: high-cpu utilization in memorymodel:_sample
Figure out if the current MemoryModel is actually useful for anything — I think it might not be. All the lovely ticke... Greg Farnum
04:01 PM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
The hangs sound like generic cap and request waitlisting issues to to me. The empty directory is tickling something i... Greg Farnum
03:57 PM CephFS Bug #4248: mds: replay does not correctly update CInode::first and ::last members
I'm going to leave this at normal even though it's a snapshotting issue — the problem's diagnosed and it's a bug in t... Greg Farnum
03:53 PM CephFS Bug #4134: mds: request locking hang under snaptests
snapshots = low Greg Farnum
03:52 PM CephFS Bug #3719 (Can't reproduce): pjd test 145 failed in the nightly runs
These logs are gone. Greg Farnum
03:45 PM CephFS Bug #4280: mds: crash on lookupsnap
Snapshots = low priority Greg Farnum
03:38 PM CephFS Bug #2445: crash when removing a non-empty directory
Let's validate behavior here — there's a good chance Zheng or somebody fixed whatever bug caused this, and we want to... Greg Farnum
03:32 PM CephFS Bug #1877: ceph.ko (3.1.6) oopses upon cephfs set_layout of a symlink to a dir
Kernel client layout crash = high. Identify if this is still a problem, and if we can trigger it using the vxattrs as... Greg Farnum
03:30 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
Need more info, samba, uclient, etc. Greg Farnum
03:29 PM Bug #7563 (Resolved): osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_up...
2014-02-27 15:13:26.966410 7f65a44d6700 20 _merge_old_entry: oe.prior_version == 0 && already missing, removing missi... Samuel Just
03:27 PM CephFS Bug #4732: uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
The blocker bug is low, so this one can't have a higher priority. Greg Farnum
03:25 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
uclient = low priority, for now. Greg Farnum
03:25 PM Bug #7542: ec misdirected op
wip-7542 Samuel Just
03:25 PM Bug #7539: Firefly EC pool massive memory leak during writes
testing wip-7542 Samuel Just
01:30 PM Bug #7539: Firefly EC pool massive memory leak during writes
ubuntu@teuthology:/a/teuthology-2014-02-26_23:00:27-rados-firefly-testing-basic-plana/106918/remote
Messing up nig...
Samuel Just
03:25 PM CephFS Bug #4188: mds crashes when cow-ing entries in formerly snapshotted dir
Snapshots = low priority. *sigh* Greg Farnum
03:21 PM CephFS Bug #5360: ceph-fuse: failing smbtorture tests
Samba against ceph-fuse (not even using libcephfs) = low priority. Greg Farnum
03:20 PM CephFS Feature #5486: kclient: make it work with selinux
I don't know anything about SELinux, nor its users. What needs to work for us to support SELinux, and how big of a st... Greg Farnum
03:19 PM CephFS Bug #5762: teuthology: Failed MPI runs lead to a hung test instead of a failure
It's a test which we can't use properly. High priority! Greg Farnum
03:18 PM CephFS Bug #6458 (Need More Info): journaler: journal too short during replay
I've bumped up #4708, so if that's the cause of this it'll be fixed when that is. If not, we need more info. Greg Farnum
03:17 PM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
#6458 could be a result of this issue, so I'm bumping up the priority. Greg Farnum
03:14 PM CephFS Bug #5950: kcephfs: cephfs set_layout -p 4 gets EINVAL
We want to use the virtual xattrs moving forward, so downgrading a bug in the cephfs tool. Greg Farnum
02:25 PM Revision f12426c3 (ceph): mds_thrash: PEP8-ize whitespace
...so that I can edit the code in a python IDE without
it lighting up like a christmas tree!
Signed-off-by: John Spr...
John Spray
01:38 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I wasn't on 3.8, it was 3.11. Unfortunately I can't use the machines I was experimenting with for this purpose anymor... Peter Waller
01:19 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
Zheng, do you have a specific bug you think this is so we can close it out? Greg Farnum
01:24 PM CephFS Bug #6741: failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
Downgrading: ceph-fuse and snapshots. Greg Farnum
01:23 PM CephFS Bug #6609: teuthology rsync workunit failure
I haven't noticed this in a while, but upgrading as it was a failure across both clients. Greg Farnum
01:22 PM CephFS Bug #5864: cfuse_workunit_suites_ffsb suite on Centos hangs with *** Got Signal Interrupt ***
This is passing in the nightlies, so if there is a bug it has to do with not only ceph-fuse, but ceph-fuse specifical... Greg Farnum
01:20 PM CephFS Bug #7206 (Need More Info): Ceph MDS Hang on hadoop workloads
Greg Farnum
01:18 PM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
We merged this to master in commit:9a040bfd46d141712c32aaa0fa8fc5de93336306, but I guess we missed closing out the ti... Greg Farnum
12:42 PM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
... Greg Farnum
11:48 AM Fix #7560 (Closed): mon: add compat set feature to mark an upgraded pg format in order to disallo...
We do not currently prevent a cuttlefish monitor from running on a dumpling store after an upgrade. Joao Eduardo Luis
11:02 AM Documentation #7558 (Resolved): broken link in install/manual-deployment/
The link under "See Monitor Config Reference - Data for details." is broken. Still think we should be spidering link... Dan Mick
08:21 AM devops Bug #6726: Official packages do not appear to be available for Saucy
We are currently building on both Saucy and Trusty, just need to push packages out to ceph.com
See
http://gitbuil...
Ian Colle
06:41 AM devops Bug #6726: Official packages do not appear to be available for Saucy
Just had a suggestion to use the raring packages from Tim Bishop on the users list.
Would be nice if we could get ...
Michael Potter
07:57 AM Bug #7248 (Fix Under Review): osd: bench set max size
https://github.com/ceph/ceph/pull/1324 Joao Eduardo Luis
06:50 AM CephFS Feature #7325: mds: tool to examine (later, manipulate) dirfrag objects
Is this intended to be an online thing (modifying live MDS state), or something that operates on the RADOS objects (i... John Spray
06:35 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
There was an earlier patch that introduced an "I'm in dispatch" flag, and a more recent one (https://github.com/ceph/... John Spray
03:59 AM Revision 154efb15 (ceph): client: don't update i_max_size when handle reply from non-auth MDS
caps from non-auth mds don't have meaningful max_size
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
03:59 AM Revision 6797d300 (ceph): client: call handle_cap_grant() for cap import message
If client sends cap message that requests new max size during
exporting caps, the exporting MDS will drop the message...
Yan, Zheng
03:59 AM Revision 9476f847 (ceph): client: allow revoking duplicated caps issued by non-auth MDS
Allow revoking duplicated caps issued by non-auth MDS if these caps
are also issued by auth MDS.
Signed-off-by: Yan,...
Yan, Zheng
03:59 AM Revision 5c55eb10 (ceph): client: check mds_wanted for imported cap
The MDS may have incorrect wanted caps after importing caps. So the
client should check the value mds has and send ca...
Yan, Zheng
03:59 AM Revision c1e40c60 (ceph): client: fix race between cap issue and revoke
If we receive new caps from the auth MDS and the non-auth MDS is
revoking the newly issued caps, we should release th...
Yan, Zheng
03:59 AM Revision 30aa2d65 (ceph): client: clear migrate seq when MDS restarts
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:11 AM Revision 9a0ef6a1 (ceph): Fix python-requests package dependencies.
python-ceph does not require requests, but ceph-common does (for ceph-brag).
Signed-off-by: Dan Mick <dan.mick@inkta...
Dan Mick

02/26/2014

11:15 PM Revision 3c87b849 (ceph): Worker logging tweaks
Change some statements' log levels; don't show bootstrap output if there
is no error.
Signed-off-by: Zack Cerza <zac...
Zack Cerza
11:02 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Dan Mick
10:41 PM Revision 0dcf3f4d (ceph): --dead implies --refresh
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
10:22 PM Revision d42f31e5 (ceph): Symlink worker log after child starts
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
07:13 PM Revision 34478127 (ceph): In find_job_info(), also look for orig.config.yaml
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
06:30 PM Revision fc33eaed (ceph): Merge pull request #1263 from ceph/wip-mds-dumper
mds: Dumper improvements
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:19 PM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
So I did a lot of testing on Fedora today. This is done so closing it out.
It looks like fedora18 was now kernel...
Sandon Van Ness
10:37 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
Ok so this is done but ceph-deploy tests are still failing...
Also that being said it looks like centos/rhel are r...
Sandon Van Ness
06:19 PM Revision c07a758c (ceph): mds: Add dump-journal-entries
This adds a somewhat-human-readable peer to
the 'dump-journal' command.
Signed-off-by: John Spray <john.spray@inktan...
John Spray
06:19 PM Revision 7a985df6 (ceph): mds: Create MDSUtility as base for Dumper/Resetter
These classes has lots of similar functionality and we may
want to add more similar things in the future.
Also, get ...
John Spray
06:15 PM Revision 410c5074 (ceph): mds: Fix Dumper shutdown
It was shutting down messenger before monclient. This
caused a sometimes-assertion when monclient tried to
reconnect...
John Spray
06:15 PM Revision d774e972 (ceph): Merge pull request #10 from ceph/wip-7485
suites/fs/basic: add mds_creation_retry
Barely-
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:10 PM Revision a3e052b6 (ceph): suites/fs/basic: add mds_creation_retry
This invokes the new mds_creation_failure task from
teuthology, ahead of mounting the FS and running the
trivial_sync...
John Spray
06:09 PM Revision f8a2a53c (ceph): Push complete info when reporting jobs as dead
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
05:51 PM Feature #7553 (Resolved): Remove classic scrub

Bobtail was the first release with chunky scrub and had maintained classic scrub code for backwards compatibility. ...
David Zafman
05:47 PM Revision 0db35b95 (ceph): Merge pull request #210 from ceph/wip-queue
Add teuthology-queue command for beanstalk Managmeent. Zack Cerza
05:46 PM Revision 700bb94b (ceph): Merge pull request #208 from ceph/wip-7485
task: Add mds_creation_failure
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:46 PM Revision 9a040bfd (ceph): Merge pull request #1283 from ceph/wip-7485
mon/MDSMonitor: Cope with failures during creation
Reviewed-by: Greg Farnum <greg@inktank.com
Gregory Farnum
05:01 PM CephFS Bug #4746: client: invalidate callback can deadlock
Demoted due to ceph-fuse and FUSE interface work. Greg Farnum
05:00 PM CephFS Bug #4829: client: handling part of MClientForward incorrectly?
Demoting due to uclient and multi-mds. Greg Farnum
04:58 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
Demoting due to uclient and Need More Info. Greg Farnum
04:57 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
Demoting due to multi-mds. Greg Farnum
04:57 PM CephFS Bug #5765: kclient: High CPU due to raw_spin_lock in ceph_cap_string
Demoting due to performance, not correctness. Greg Farnum
04:56 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
Demoting due to uclient. Greg Farnum
04:55 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
I'm pretty sure we had a discussion about your patch, but I can't find the comments and I don't remember the outcome.... Greg Farnum
04:48 PM CephFS Bug #6608: samba teuthology dbench failure
Demoting priority on samba. Greg Farnum
04:47 PM CephFS Bug #7011: ENOTEMPTY on ceph-fuse + snaptest-? test
Demoting priority on ceph-fuse and snapshots. Greg Farnum
04:47 PM CephFS Bug #6613: samba is crashing in teuthology
Demoting priority on samba. Greg Farnum
04:37 PM CephFS Feature #7326: qa: fix flock tests
I don't remember which tests these are; the locktest ones that are racy, or something else? Greg Farnum
04:35 PM CephFS Feature #7352: mds: make classes encode/decode-able
We've already merged in the MDSTable and Journaler header dumping stuff; I think that's all the stuff that you were t... Greg Farnum
04:29 PM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
Again, Zheng got this done. Greg Farnum
04:26 PM CephFS Cleanup #3742: Remove old Hadoop wrappers and configuration options
This is already done, isn't it Noah? At least, the old stuff isn't where it used to be and I didn't see it with the n... Greg Farnum
04:25 PM Linux kernel client Cleanup #2085: kclient: improve mtime update in page_mkwrite
Talk to me about this; what kind of an issue is it (and does it still apply)? Greg Farnum
04:18 PM CephFS Feature #118: kclient: clean pages when throwing out dirty metadata on session teardown
I can't find the referenced ticket anywhere. Anybody know what this is supposed to be and if it still applies? (I thi... Greg Farnum
04:10 PM devops Bug #7552 (Resolved): dregs of mkcephfs still live on
There are still references to mkcephfs in the code. These should be removed and replaced with ceph-deploy if appropri... Ian Colle
03:33 PM Bug #7549: Mon deadlock

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

I was running test/vstart_wrapped_tests.sh built from 60c9aafaf0ff033dca22606ea811c792f1cda781. It looks like mult...
David Zafman
03:12 PM Revision 7ba3200f (ceph): mds: fix nested_anchors update during journal replay
check if the inode is anchored/unanchored before updating the inode
Fixes: #7530
Signed-off-by: Yan, Zheng <zheng.z....
Yan, Zheng
03:12 PM Revision 82aba4b0 (ceph): Merge pull request #1319 from ceph/wip-primary-temp-fix
osd/OSDMap: respect temp primary without temp acting
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
02:04 PM Bug #7538 (Fix Under Review): librados: rados ls crashes on firefly due to segfault in ObjectIter...
https://github.com/ceph/ceph/pull/1322 Josh Durgin
01:17 PM Revision 6ba89851 (ceph): fix docstring typo
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
01:03 PM Revision 7cc93751 (ceph): task: Add mds_creation_failure
This is test code to accompany CephFS fix #7485.
Also fix DaemonState.wait_for_exit to clear up its 'proc'
attribute...
John Spray
11:39 AM devops Tasks #7230 (In Progress): Rebuild sync-agent packages for dumpling repo
Talked to Josh and he wants to get some more fixes in which should happen later this week. Sandon Van Ness
10:34 AM devops Tasks #7230: Rebuild sync-agent packages for dumpling repo
Packages are built but I need to test to make sure its working. Sandon Van Ness
10:20 AM Subtask #7548 (Resolved): Basic docs for Erasure Coding
"work in progress":https://github.com/ceph/ceph/pull/1362
Similar to what Greg created for tiering at http://ceph....
Neil Levine
10:18 AM Feature #7547 (Resolved): Basic docs for Cache Tiering functionality
The content at http://ceph.com/docs/master/dev/cache-pool/ is fine for the Firefly release. Can you liaise with John ... Neil Levine
09:46 AM Bug #7545: rados: notify was not recieved in ceph_test_rados_watch_notify with thrashing on emperor
this was from http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-24_19:00:20-rados-emperor-testing-basic-plana/99... Josh Durgin
09:46 AM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
This looks like it might just be a bug in the test. This is all the output from ceph_test_rados_watch_notify, with a ... Josh Durgin
07:15 AM CephFS Bug #7530: mds: failed anchor assert on replay
commit:7ba3200f1e91d803cdf84f96777641f7d18d3c01 Greg Farnum
07:09 AM Revision 1040d1b0 (ceph): osd/OSDMap: respect temp primary without temp acting
be2748c6d540891f2e1a62e7034cb44f7d04bf18 ensured that
if the temp acting mapping contains only CRUSH_ITEM_NONE,
that ...
Samuel Just
05:26 AM Revision aee6925e (ceph): Merge pull request #1264 from ceph/wip-mds-dencoder
mds: Add encode/decode/dump for use with dencoder
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:22 AM rgw Bug #7543: rgw: off-by-one bug in rgw_trim_whitespace()
I've sent a pull request to fix this bug at https://github.com/ceph/ceph/pull/1321
Please help to review it.
Xiangyu Lv
02:38 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
There is an off-by-one bug in rgw_trim_whitespace(). It results in trimming off all characters with input like " t". Xiangyu Lv
04:42 AM Revision 5a6cb3da (ceph): Merge pull request #1317 from ceph/wip-7537
Wip 7537
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
03:57 AM Revision 26f00fc5 (ceph): Make help a bit more obvious. Misc tweeks.
Put each yaml in the job_description on its own line so not so
wide of a line. Make delete default None not False in ...
Sandon Van Ness
02:00 AM Revision 20641b67 (ceph): Merge pull request #1280 from ceph/wip-7374-wusui
Fix sub check() to not exit if rgw is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:59 AM Revision 7eda448b (ceph): Merge pull request #1279 from ceph/wip-7375-wusui
Fixed sub check() to say okay if rgw is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:08 AM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
MDS map contains CompatSet::FeatureSet Zheng Yan
12:52 AM Revision 8020dcf7 (ceph): Fixed get_status() to find client.radosgw fields inside of ps output.
Fixes: 7375
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
12:49 AM Revision 8200b8a0 (ceph): Fix get_status() to find client.rados text inside of ps command results.
Added port (fixed value for right now in teuthology) to hostname.
Fixes: 7374
Signed-off-by: Warren Usui <warren.usui...
Warren Usui
12:47 AM Revision be2748c6 (ceph): OSDMap::_pg_to_up_acting_osds: use _acting_primary unless acting is empty
If the temp set for whatever reason has only CRUSH_ITEM_NONE,
we need primary to be -1.
Signed-off-by: Samuel Just <...
Samuel Just

02/25/2014

11:47 PM Revision 0eabbf14 (ceph): Merge pull request #1316 from ceph/dumpling-6922
Dumpling: Prevent extreme PG split multipliers
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:45 PM Revision fe8915ae (ceph): Merge pull request #1315 from ceph/dumpling-hashpspool
mon: OSDMonitor: allow (un)setting 'hashpspool' flag via 'osd pool set'
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:44 PM Revision 87822ccc (ceph): Merge pull request #1314 from ceph/dumpling-osd-pgstatsack
Dumpling osd pgstatsack
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:28 PM Revision f93bf33b (ceph): Merge pull request #1311 from ceph/wip-dz-scrub-fixes
Wip dz scrub fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:27 PM Revision dc079eb3 (ceph): OSDMonitor: when thrashing, only generate valid temp pg mappings
Since backfill peers are no longer placed into the acting set,
temp mappings will never exceed the pool size. Also, ...
Samuel Just
11:24 PM Bug #7542 (Resolved): ec misdirected op
OSD recomputes op target based on current OSDMap. With an EC pg, we can get this result:
1) client at map 512 sends...
Samuel Just
09:34 PM Revision 56675663 (ceph): mon: OSDMonitor: allow (un)setting 'hashpspool' flag via 'osd pool set'
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked fro...
Joao Eduardo Luis
09:10 PM Revision 9d5d931c (ceph): OSDMonitor: use a different approach to prevent extreme multipliers on ...
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d8...
Greg Farnum
09:08 PM Revision c0c4448d (ceph): OSDMonitor: prevent extreme multipliers on PG splits
Fixes: #6922
Backport: emperor
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.co...
Greg Farnum
08:42 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
5a6cb3da201ce503b4aef1744c3dc15511d15a13 Samuel Just
12:33 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
11: (OSD::PeeringWQ::_process(std::list<PG*, std::allocator<PG*> > const&, ThreadPool::TPHandle&)+0x12) [0x6a5282]
...
Samuel Just
07:55 PM Bug #7406: Seg fault in find_object_context()in recent master rados run
David Zafman
07:52 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily
David Zafman
12:55 PM Bug #7535: Switching to classic scrub unnecessarily

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

test/vstart_wrapped_tests.sh output:
pg[0.0( empty local-les=20 n=0 ec=1 les/c 20/20 14/14/6) [0,2,1] r=-1 lpr=14 ...
David Zafman
07:51 PM Revision 9e55f6f2 (ceph): Add missing fedora yamls.
Running a git add first would have been helpfull... Sandon Van Ness
07:51 PM Revision 67ed25f1 (ceph): Run ceph-deploy on fedora19 not old fedora18.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
07:50 PM Revision d741cd99 (ceph): Add missing fedora yamls.
Running a git add first would have been helpfull... Sandon Van Ness
07:42 PM Revision 9fb8231f (ceph): Run ceph-deploy on fedora19 not old fedora18.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
07:42 PM Revision c1889497 (ceph): osd: fix off-by-one is boot subscription
If we have osdmap N, we want to onetime subscribe
starting at N+1. Among other things, it means we
hear when the NOU...
Sage Weil
07:42 PM Revision 4584f606 (ceph): OSD: use the osdmap_subscribe helper
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3c...
Greg Farnum
07:42 PM Revision 61b2aeee (ceph): OSD: create a helper for handling OSDMap subscriptions, and clean them up
We've had some trouble with not clearing out subscription requests and
overloading the monitors (though only because ...
Greg Farnum
07:41 PM Revision d93d67d1 (ceph): monc: new fsub_want_increment( function to make handling subscriptions ...
Provide a subscription-modifying function which will not decrement
the start version.
Signed-off-by: Greg Farnum <gr...
Greg Farnum
07:40 PM Revision 37fbcb95 (ceph): OSD: disable the PGStatsAck timeout when we are reconnecting to a monitor
Previously, the timeout counter started as soon as we issued the reopen,
but if the reconnect process itself took a w...
Greg Farnum
07:40 PM Revision 9be395e8 (ceph): monc: backoff the timeout period when reconnecting
If the monitors are systematically slowing down, we don't want to spam
them with reconnect attempts every three secon...
Greg Farnum
07:40 PM Revision 8f4c20bd (ceph): monc: set "hunting" to true when we reopen the mon session
If we don't have a connecton to a monitor, we want to retry to another
monitor regardless of whether it's the first t...
Greg Farnum
07:39 PM Revision c6317558 (ceph): monc: let users specify a callback when they reopen their monitor session
Then the callback is triggered when a new session is established, and the
daemon can do whatever it likes. There are ...
Greg Farnum
07:34 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
Created and on the index page. Sandon Van Ness
07:13 PM Revision e04f8fd3 (ceph): Add teuthology-queue command for beanstalk Managmeent.
Supports listing entire queue of machine type and deleting test
suite runs from the queue without wiping the entire q...
Sandon Van Ness
06:27 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
Zheng Yan
09:14 AM CephFS Bug #7530: mds: failed anchor assert on replay
config used was (suites/fs/thrash/): ceph/base.yaml ceph-thrash/default.yaml clusters/mds-1active-1standby.yaml debug... John Spray
09:09 AM CephFS Bug #7530: mds: failed anchor assert on replay
Crashed on first try, log at debug-mds=10 attached John Spray
07:04 AM CephFS Bug #7530 (In Progress): mds: failed anchor assert on replay
John Spray
03:47 PM Bug #6922 (Resolved): mon: do not allow unreasonable PG splitting
Sam merged this. Greg Farnum
01:40 PM Bug #6922: mon: do not allow unreasonable PG splitting
PR: https://github.com/ceph/ceph/pull/1316 Greg Farnum
03:14 PM Feature #7540 (Resolved): Spread out deep-scrubs to avoid I/O contention
Parallel deep-scrubs have the potential to cause client I/O contention. A mechanism to spread out deep-scrubs and mak... Brian Andrus
03:02 PM Feature #7288: Deep-scrub throttle
Actually, there's a reservation system which should prevent that. The primary must reserve a slot in itself and each... Samuel Just
02:19 PM Bug #7539 (Resolved): Firefly EC pool massive memory leak during writes
EC pools appear to leak memory rather badly during writes. Looks like messages aren't being properly cleaned up. Ma... Mark Nelson
01:59 PM Bug #7538 (Resolved): librados: rados ls crashes on firefly due to segfault in ObjectIterator::op...
as seen in: http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-23_23:02:27-rbd-firefly-testing-basic-plana/99242/... Josh Durgin
11:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
hmm.. the timestamps actually match, so the shard sync failure might be the culprit. Seems like a sync agent issue (a... Yehuda Sadeh
09:36 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
I think the real issue is here, the specific agent error looks like a red herring:... Yehuda Sadeh
11:06 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
This should be fixed in ceph-qa-chef. I will run a new ceph-deploy run on vps and see how it goes. Sandon Van Ness
07:33 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
On the vm I deployed when tracking this, it only took me a 'yum upgrade leveldb' or something similar. I would think... Joao Eduardo Luis
07:19 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
All Fedora tests are still failing. We need to address this as soon as possible. I am not sure what entails upgrading... Alfredo Deza
10:48 AM Bug #7448: os/FileJournal.cc: FAILED assert(fd >= 0)
Increasing the priority on this since we cannot seem to get passing tests for ceph-deploy for months. Alfredo Deza
10:47 AM Revision 891343a7 (ceph): rados.py: add aio_remove
Add aio_remove to the Python wrapper.
Signed-off-by: Dan van der Ster <daniel.vanderster@cern.ch>
Dan van der Ster
07:25 AM CephFS Bug #7503: mds start and oops after access to cephfs
fine, ok for the ticket #7531.This one should be closed.
Yann Dupont
07:02 AM CephFS Feature #3863 (In Progress): implement a tool to lookup inode numbers without holding their path
John Spray
05:33 AM devops Bug #7356: Kill all while loops that will never end....
This is going to take some effort because there are over 100 while loops in teuthology that look dangerous.
The in...
Alfredo Deza
05:24 AM Bug #6101: ceph-osd crash on corrupted store
We applied the fix last week the crashing node.
The osd node now runs again, but see that the missing objects gets t...
Daniel Poelzleithner
03:56 AM Revision 9f7f4eda (ceph): Revert "osd/PG: fix assert when deep repair finds no errors"
This reverts commit e3e3328ec8a57f1ae2a2fd9893c51068798720a0. David Zafman
03:56 AM Revision 728e3911 (ceph): osd: Don't include primary's shard in repair result message
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
02:39 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
The patch has been accepted in libvirt upstream: http://libvirt.org/git/?p=libvirt.git;a=commitdiff;h=60f70542f97805a... Wido den Hollander
12:34 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Hi Greg,
I got a chance to test against the fix in our cluster (the leaf folder has around 1000 files), there are tw...
Guang Yang

02/24/2014

10:31 PM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
Ah, it sounds like this is happening because the MDS doesn't currently have a good versioning system to prevent too-o... Greg Farnum
10:30 PM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
This'll be a little interesting because the MDS doesn't have local storage. Evaluate if feature sets are best stored ... Greg Farnum
10:11 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
... Greg Farnum
09:22 PM Revision 25919351 (ceph): use itertools for seconds sum
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
09:21 PM Revision 60892ca9 (ceph): tests for the new while helper
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
09:01 PM Revision 38cead63 (ceph): Flip logic of checking whether a branch can report
Previously we checked if the branch being used was in a whitelist of
branches known to contain the reporting feature....
Zack Cerza
08:32 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The kmods are built from a common source RPM because ceph.ko and rbd.ko require libceph.ko to be built and available ... Ken Dreyer
08:29 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Having them in one package is fine for now, but on reflection I do think we are going to need to have these in separa... Neil Levine
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Ken Dreyer
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The packages only run depmod, and they leave modprobe to the user or to the tooling. So it sounds like we're good.
...
Ken Dreyer
03:42 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
mount.ceph and 'rbd map' will do the modprobe for the user if it's not already loaded, so there's no need for the pac... Josh Durgin
03:25 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Does the package install the module into the kernel or does the user have to do modprobe manually?
If it installs ...
Neil Levine
03:20 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
I've unified all three kmods into a single package, available on GitHub: https://github.com/kdreyer-inktank/ceph-kmod... Ken Dreyer
08:09 PM Revision 171a5e1a (ceph): add a helper for while loops
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
05:22 PM Revision 3ee71a5c (ceph): doc: troubleshooting-mons.rst: better document how to troubleshoot mons
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
05:17 PM Revision 60c9aafa (ceph): Merge pull request #1308 from ceph/wip-osdmap-inc
mon/OSDMonitor: fix osdmap encode feature logic
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:10 PM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
Sage Weil
03:16 PM CephFS Feature #4000: Design a migration path from using the AnchorTable to using lookup-by-ino
Did this already get done with Zheng's work to remove the AnchorTable? Greg Farnum
05:10 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
Sage Weil
05:09 PM CephFS Feature #3999 (Resolved): update CDir encoding
this was revved as part of zheng's omap stuff Sage Weil
05:08 PM Revision 17176015 (ceph): Merge pull request #1302 from ceph/wip-create-null
client: fix possible null dereference in create
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
04:15 PM Linux kernel client Cleanup #2847 (Resolved): libceph: osdmap definition is out of date
Sage Weil
04:15 PM Linux kernel client Feature #6991 (Resolved): support CEPH_FEATURE_OSDMAP_ENC
Sage Weil
02:07 PM rgw Bug #7526 (Resolved): "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-di...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98508... Yuri Weinstein
12:14 PM Revision 69082a69 (ceph): mds: add mds_kill_create_at for testing
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
11:24 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Seems related to #7468 Yuri Weinstein
11:23 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98483
Error...
Yuri Weinstein
10:20 AM rgw Bug #6936 (Resolved): radosgw-admin allows same user to be created multiple times
Fixed for firefly, commit:53de64122b206d11aa42fd401f88f02f2908e942 Yehuda Sadeh
10:20 AM rgw Bug #6951 (Resolved): rgw: bucket re-create fails when cache is disabled
Fixed for firefly, commit:859ed33ed7f9a96f4783dfb3e130d5eb60c622dd Yehuda Sadeh
10:16 AM rgw Bug #6830 (Resolved): S3 CompleteMultipartUploadResult has empty ETag element
Fixed, commit:2b3e3c834cd0e8b890296fa2b92ebb5de01a1bc1 Yehuda Sadeh
10:15 AM rgw Bug #7064 (Resolved): S3 request to non-existent object in non-existent bucket results in 30 seco...
Fixed, commit:3ed68eb9fac9b3d0bf9111867d609f9ea08fb202 Yehuda Sadeh
09:58 AM devops Bug #7356 (In Progress): Kill all while loops that will never end....
Alfredo Deza
09:46 AM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Consistent on firefly as well - http://pulpito.front.sepia.ceph.com/teuthology-2014-02-22_23:02:06-rbd-firefly-distro... Yuri Weinstein
08:29 AM Bug #7504: Ceph does not specify python2
Yeah I was talking about the shebang.
I understand that you can't do anything but this situation sucks. Instead of d...
Alexandre BIQUE
07:28 AM Bug #7504 (Rejected): Ceph does not specify python2
Alfredo Deza
07:21 AM Bug #7504: Ceph does not specify python2
When you say that ceph scripts should 'use explicitly python2' you mean altering the shebang line?
There is no con...
Alfredo Deza
03:59 AM Revision e92d6024 (ceph): Merge pull request #1303 from ceph/port/temp-failure-retry
compat: avoid unused warn with TEMP_FAILURE_RETRY
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:54 AM Revision 27968a74 (ceph): ceph_test_objectstore: fix i386 build (again)
test/objectstore/store_test.cc: In member function ‘void SyntheticWorkloadState::read()’:
error: test/objectstore/sto...
Sage Weil
03:49 AM Revision 5f53cf13 (ceph): Merge pull request #1307 from ceph/wip-7517
Wip 7517 Sage Weil
03:12 AM Revision 0243d29c (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:11 AM Revision 87ebe461 (ceph): upgrade/dumpling: add recent dumpling point releases
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:10 AM Revision bad8e609 (ceph): upgrade/dumpling: upgrade to latest dumpling, not emperor
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:23 AM Revision 14ea8157 (ceph): mon/OSDMonitor: fix osdmap encode feature logic
If we are encoding a full map based on an old Incremental that does not
encode the features, fall back to the quorum ...
Sage Weil
01:02 AM Bug #7521 (Won't Fix): Add more events (hold object context) to OpTracker to better analyze perfo...
This ticket is to help on the effort I sent to community for this - http://www.spinics.net/lists/ceph-users/msg07866.... Guang Yang
12:58 AM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
Zheng Yan
12:20 AM Revision 7357b6ed (ceph): PG: skip pg_whoami.osd, not pg_whoami.shard in scrub feature check
Caused by typo in 68184d4574cd507ab3a065693e392917b98e16ec.
Fixes: #7517
Signed-off-by: Samuel Just <sam.just@inktan...
Samuel Just

02/23/2014

11:32 PM Revision ae59ba3c (ceph): Merge pull request #1304 from ceph/wip-last-epoch-clean
mon: fix min_last_epoch_clean handling
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:24 PM Bug #7423: erasure code: ./rados get retrieves a larger object
As of "today":https://github.com/ceph/ceph/commit/24c89bf01c61ecedb3bc7045332c9ed0340b37dc instead of crashing it ret... Loïc Dachary
10:56 PM Revision c6a22b33 (ceph): rados/thrash/workloads: enable copy_from for the ec workloads
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:48 PM Revision dcb9946b (ceph): Merge pull request #1306 from ceph/wip-7512
wip-7512
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
09:35 PM Revision d0359f7c (ceph): PG: clarify same_primary_since updates regarding primary rank
pg_shard_t includes the position, so these checks handle
same osd/different rank properly.
Signed-off-by: Samuel Jus...
Samuel Just
09:35 PM Revision 0442b456 (ceph): Objecter/OSDMap: factor out primary_changed() into static OSDMap method
We need to reuse this logic in OSD::project_pg_history.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
09:35 PM Revision 696fa36d (ceph): OSD::project_pg_history needs to account for acting_primary/up_primary
Fixes: #7512
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:24 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
Hi Greg,
Thanks for the reply.
-bash-4.1$ sudo ceph --version
ceph version 0.76-874-g40bdcb8 (40bdcb88504aea6...
Zhi Zhang
08:15 PM Revision df3ba724 (ceph): mon/PGMap: add unit test for min_last_epoch_clean
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:15 PM Revision 73c59a02 (ceph): mon/PGMap: fix osd_epochs update
The insert() call here does not overwrite a previous entry, which means
that the osd_epochs map is never moving forwa...
Sage Weil
08:14 PM Revision 8913ab4b (ceph): ECBackend: skip canceled xattr reads as well
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:10 PM Bug #7520: Lock contention during scrubbing which could potentially hang the OSD for a couple of ...
Pull request - https://github.com/ceph/ceph/pull/1309 Guang Yang
07:41 PM Bug #7520 (Resolved): Lock contention during scrubbing which could potentially hang the OSD for a...
We are using Ceph as object store (via radosgw) and each time the cluster starts doing scrubbing, the performance deg... Guang Yang
07:49 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
Sage Weil
03:07 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
EC pool scrub bug -- reproducible
2014-02-23 15:03:57.195155 7ffbe7183700 10 osd.1 341 dequeue_op 0x51c2b40 finish...
Samuel Just
07:17 PM Revision 0e376ee7 (ceph): compat: avoid unused warn with TEMP_FAILURE_RETRY
The version of TEMP_FAILURE_RETRY found on Linux has a GNU extension
that squashes the unused return value warning wh...
Noah Watkins
07:16 PM Bug #7519 (Can't reproduce): upgrade: osd crash on cuttlefish -> v0.67.1 -> emperor
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-02-22_19:40:17-upgrade:dumpling-next---basic-plana/978... Sage Weil
07:00 PM Feature #7518 (Closed): Add inline attrs support to KeyValueStore
"header" is a structure play a role like inode in FileSystem. Attrs are accessed frequently by PG layer, make attrs i... Haomai Wang
06:18 PM Revision 23e538ef (ceph): client: fix possible null dereference in create
There are two paths that jump to the out label for which 'in' can be
NULL and outp can be non-NULL. For those cases ...
Sage Weil
06:05 PM Revision bcc18d48 (ceph): osd: increase default leveldb write buffer, cache size
The FileStore's leveldb currently uses libleveldb's defaults for cache and
write buffer size, which are both 4 MB. In...
Sage Weil
05:49 PM Revision 614a94ab (ceph): Merge pull request #1287 from kdreyer-inktank/redhat-files
packaging: file list adjustments
Tested-by: Huang Jun <hjwsm1989@gmail.com>
Sage Weil
05:45 PM Revision 7842ea91 (ceph): Merge pull request #1265 from ceph/wip-mds-misc
MDS misc. cleanup
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:05 PM Revision c4a3a86a (ceph): ceph_test_objectstore: fix i386 build error
We can't swap size_t and uint64_t; just change the len type to match.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:03 PM Revision b25c22a2 (ceph): ceph_test_objectstore: fix signed/unsigned warning
In file included from test/objectstore/store_test.cc:33:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::...
Sage Weil
05:00 PM Revision 9651b18b (ceph): os/ObjectStore: fix rebase errors
These were goofed by d74f1282cd268b4b04cfd9e90ddeac6d1dc6be7e.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:29 PM Bug #6671: FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Someone (I think it was Sam Just) helped me on #ceph to replace this OSD and rebuild data that was missing, so we wor... Tom Lanyon
04:17 PM Revision cfafa0b7 (ceph): README: add build dep
Technically it's a 'make check' dep, but close enough.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
03:52 PM Revision 1340b360 (ceph): erasure-code: test that changing the pool size is not allowed
http://tracker.ceph.com/issues/7360 fixes #7360
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
03:46 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
ubuntu@teuthology:/a/teuthology-2014-02-21_23:02:40-rgw-firefly-testing-basic-plana/96767
with full osd logs
Sage Weil
03:38 PM Revision 0e50f7a0 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:37 PM Revision 57eeebee (ceph): Merge pull request #1290 from ceph/wip-os-doc
os/ObjectStore: document interface Sage Weil
03:29 PM Revision d74f1282 (ceph): os/ObjectStore: document interface
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Allen Samuels
03:25 PM Revision 24c89bf0 (ceph): Merge pull request #1294 from ceph/wip-librados-object-iterator
fix bugs in librados::ObjectIterator
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:24 PM Revision 5c4129df (ceph): Merge pull request #1295 from yuyuyu101/keyvaluestore-enhance
Keyvaluestore enhance(backport to firely)
Pulling this into firefly because it doesn't (substantiatively) touch anyt...
Sage Weil
03:12 PM Revision 8ef0d7e6 (ceph): Merge pull request #1297 from ceph/wip-ec-bugs
Wip ec bugs
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:48 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
Sage Weil
01:02 PM Feature #7516 (Resolved): mon: reweight-by-pg
The reweight-by-utilization function is important for maintaining a tight distribution of utilizations across lots of... Sage Weil
12:54 PM Feature #7515 (Resolved): mon: 'osd crush reweight-subtree <name> <weight>'
The 'osd crush reweight ...' command only lets you reweight a single item. In a large cluster, it may be helpful to ... Sage Weil
12:21 PM Bug #7493 (Resolved): cephtool/pool_ops failure
commit:70d23b9a0ad9af5ca35a627a7f93c7e610e17549 Sage Weil
08:23 AM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
Sage Weil
07:54 AM Bug #7494 (Resolved): EC filter read op bug
Sage Weil
07:54 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
07:53 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Sage Weil
07:25 AM Bug #7491 (Resolved): rados api crashes
Sage Weil
07:21 AM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
Sage Weil
07:21 AM Feature #7514 (Resolved): qa: add ceph_test_objectstore to rados test suite
Sage Weil
06:00 AM Revision 6d8cb22e (ceph): unittest_ecbackend: fix signed/unsigned warnings
In file included from test/osd/TestECBackend.cc:20:0:
../src/gtest/include/gtest/gtest.h: In instantiation of ‘testin...
Sage Weil
05:56 AM Revision bff4a3bf (ceph): Merge pull request #1301 from ceph/wip-scrub-primary
mon/PGMonitor: fix primary osd check on deep-scrub
gitbuilders are now passing
Sage Weil
05:31 AM Revision fed655e3 (ceph): mon/PGMonitor: fix primary osd check on deep-scrub
s/!=/==/. Logic was reversed.
Broken in 40bdcb88504aea6288d461d29d24d5b0bf7aeebc.
Signed-off-by: Sage Weil <sage@i...
Sage Weil
01:35 AM Revision 5516f8c1 (ceph): Merge pull request #1300 from ceph/wip-7513
PGLog::activate_not_complete typo
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
01:24 AM Revision 7b0f3d90 (ceph): PGLog::activate_not_complete: fix log.complete_to increment typo
info.last_complete should be the entry before log.complete_to.
This appears to have been a typo introduced in
dd7105...
Samuel Just
01:18 AM Revision 885d1963 (ceph): Merge pull request #1298 from ceph/wip-subscribe
osd: fix off-by-one is boot subscription
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just

02/22/2014

10:55 PM Revision bfb3a247 (ceph): Merge pull request #1299 from ceph/wip-repair
osd/PG: fix assert when a shallow repair has fixed all errors.
Reviewed-by: David Zafman <david.zafman@inktank.com>
David Zafman
09:51 PM Revision e3e3328e (ceph): osd/PG: fix assert when deep repair finds no errors
If there are no deep repairs, we don't want to assert.
Fixes:
-1> 2014-02-21 21:13:56.393087 7f0258ff9700 0 log...
David Zafman
08:37 PM Revision 8b4cf1c0 (ceph): OSDMap: make calc_pg_rank/role const for acting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision 93983c95 (ceph): Objecter: make is_pg_changed static and const for old/newacting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision ace65fec (ceph): OSD: fix query for ec pgs
We need to parse a pg_t and translate it into an spg_t.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:37 PM Revision 9da4d40e (ceph): PGLog: test for missing using the correct shard value
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision 005b4fad (ceph): Objecter: resend op if primary role changed
Fixes: #7508
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:35 PM Revision 9b852413 (ceph): ECBackend::filter_read_op: clean up read state properly
Fixes: #7494
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:35 PM Revision 8593ad76 (ceph): ReplicatedPG::cancel_pull: ECBackend might cancel_pull on a non-missing...
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:35 PM Revision ab4c9a67 (ceph): ECUtil: clear() should reset hashes to -1, not 0
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:35 PM Revision b7de0fdb (ceph): ECTransaction: require hash_infos for deleted objects
Otherwise, an append preceded by a delete may not see the
correct HashInfo state since it won't have been cached
unti...
Samuel Just
05:35 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:27 PM Bug #7513: PGLog::activate_not_complete: log.complete_to decrement typo
https://github.com/ceph/ceph/pull/1300 Samuel Just
05:25 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:19 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
merged Samuel Just
01:48 PM Bug #7511 (Fix Under Review): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Sage Weil
04:08 PM Revision 70d23b9a (ceph): osd: fix off-by-one is boot subscription
If we have osdmap N, we want to onetime subscribe
starting at N+1. Among other things, it means we
hear when the NOU...
Sage Weil
03:57 PM Revision 90ebdcc4 (ceph): Rename keyvaluestore_check_backend to keyvaluestore_debug_check_backend
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 4b3bf3e2 (ceph): Make SequencePosition sync by each transaction
Each object modify will increase SequencePosition and sync it to disk
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Haomai Wang
01:05 PM Revision dcfe098c (ceph): Remove m_eio in KeyValueStore
KeyValueStore use kv backend to detect errors and nearly can't know the actual
reason for error.
Signed-off-by: Haom...
Haomai Wang
01:05 PM Revision 9543664b (ceph): Remove filestore_inject_stall
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 697411c8 (ceph): Add backend check option to KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 8c4d8659 (ceph): Add config tracker to KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 62c1631f (ceph): Remove eio inject codes in KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision a52d7cd0 (ceph): Add KeyValueStore op thread options
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 3e6a1fc6 (ceph): Add read/write operation to store_test.cc
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 9ed29581 (ceph): Return 0 when the offset of read exceed the length of object
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision a9fa341e (ceph): Fix incorrect read and truncate
If the first chunk of object is not read entirely, the current implementation
will contain it entirely which make wro...
Haomai Wang
01:05 PM Revision 2a363d67 (ceph): Unify object level lock in GenericObjectMap
Before we copy lock implementation from DBObjectMap which provide with two locks
for header. Here just unify it to ma...
Haomai Wang
01:05 PM Revision 88bec065 (ceph): Optimize write call add enhance error detect
A single write call may need several keys in the backend kv store. Let get these
keys one time.
Signed-off-by: Haoma...
Haomai Wang
01:05 PM Revision 6314350f (ceph): Remove unnecessary "check_coll" check
The goal of "check_coll" is aimed to ensure the collection is exists. But
the create and delete of collection already...
Haomai Wang
01:05 PM Revision ec8a4193 (ceph): Implement collection_rename interface in KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision 5eb75927 (ceph): Fix deadlock caused by hold collection obj
Collection is a special object in KeyValueStore, if exists collection modify,
this object will be hold. When exists c...
Haomai Wang
01:04 PM Revision 2b9e893a (ceph): Move perf counter and add op queue reserve throttle
The perf counter of FileStore can shared with other ObjectStore backend, so move
it to ObjectStore and adjust positio...
Haomai Wang
01:04 PM Revision c9fdceee (ceph): Add test for omap interface
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision d7be5404 (ceph): Add get_*_with_header to StripObjectHeader
In some situations, we need to ensure header is held and try to read, so read
interfaces need to accept header argume...
Haomai Wang
01:04 PM Revision 024a1204 (ceph): Use rename operation to make colection_move atomic
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision 4e7f1de9 (ceph): Adjust some interfaces to optimize caller codes
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
12:29 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
OSD::project_pg_history needs to take into account up_primary/acting_primary -- testing.
2014-02-22 01:48:56.31806...
Samuel Just
03:28 AM Revision a715c7f2 (ceph): Merge branch 'wip-6685-firefly' into firefly
Reviewed-by: Samuel Just <sam.just@inktank.com> David Zafman
02:30 AM Revision f214c3ec (ceph): Merge pull request #1293 from jwriteclub/doc-update-ceph-osd-note
Added a note that the ceph-osd command requires the cluster option.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:26 AM Revision c2782695 (ceph): Added a note that the ceph-osd command requires the cluster option.
Signed-off-by: Christopher O'Connell <jwriteclub@gmail.com> Christopher O'Connell
02:22 AM Revision 0da25e67 (ceph): librados: implement ObjectIterator copying and assignment
Copied iterators should be independent of each other, and not
rely on the same underlying ListContext or ObjListCtx.
...
Josh Durgin
01:40 AM Revision 72820a84 (ceph): Merge remote-tracking branch 'origin/wip-da-SCA-20140218' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
01:32 AM Revision d9bedb9e (ceph): Added evaluation of cluster and fixed evaluation when setting initial w...
Signed-off-by: Christopher O'Connell <jwriteclub@gmail.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Christopher O'Connell
12:06 AM Revision d8a7befb (ceph): librados: remove extra advance from objects_begin(position)
ObjectIterator::seek() already calls get_next() to update the
iterator's state. Calling it again goes one past where ...
Josh Durgin
12:06 AM Revision 8a0017ac (ceph): librados: don't destroy ObjListCtx when iterator reaches the end
There's no need to destroy it when we've used it once. It'll get destroyed
by the destructor anyway. Now that there's...
Josh Durgin

02/21/2014

11:57 PM Revision 7ae05566 (ceph): Merge pull request #1286 from ceph/wip-corpus
ceph-object-corpus: prune some old releases
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:19 PM Revision a9677e13 (ceph): Revert "ReplicatedPG::recover_backfill: adjust last_backfill to HEAD if...
This reverts commit 545135f3e1c75318940caa2c82ac32a53fc4f957.
Conflicts:
src/osd/ReplicatedPG.cc
David Zafman
10:46 PM Revision 78b65ace (ceph): Merge remote-tracking branch 'origin/port/updates' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
10:18 PM Revision 133ddb7d (ceph): packaging: match all test files
It's tedious to try to keep the list of test files up to date in the RPM
spec file. Use a wildcard to match them all....
Ken Dreyer
10:17 PM Revision 1c129dfc (ceph): packaging: add missing file
Signed-off-by: huangjun <hjwsm1989@gmail.com>
Reviewed-by: Ken Dreyer <ken.dreyer@inktank.com>
huang jun
09:57 PM Revision bd59db21 (ceph): ceph-object-corpus: prune some old releases
We do not need to test these old object encodings as they are covered by
later object collections.
Signed-off-by: Sa...
Sage Weil
09:51 PM Revision 6e284806 (ceph): schedule_suite: debug filestore = 20 too
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:15 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
... Sage Weil
09:05 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
ha, this apears to be what is breaking the unit tests on firefly/master:
http://gitbuilder.sepia.ceph.com/gitbuilder...
Sage Weil
04:21 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Experiment:
ceph osd set noup
ceph osd down 1
<osd 1 is down>
ceph osd unset noup
Expected:
<osd 1 is back u...
Dan Mick
09:10 PM Revision 68f62660 (ceph): Merge remote-tracking branch 'origin/wip-6936' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:09 PM Revision 8ebc2a26 (ceph): Merge remote-tracking branch 'origin/wip-7099' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:08 PM Revision 731d483b (ceph): Merge remote-tracking branch 'origin/wip-6830' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:07 PM Revision a19b460a (ceph): Merge remote-tracking branch 'origin/wip-6951' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:06 PM Revision 0aac04a2 (ceph): Merge remote-tracking branch 'origin/wip-7064' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:05 PM Revision d509e53d (ceph): Merge remote-tracking branch 'origin/wip-7271' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:01 PM Revision ae61abf0 (ceph): Merge pull request #205 from kdreyer-inktank/jenkins
jenkins: fail fast during job execution Alfredo Deza
09:00 PM Revision 76046cf3 (ceph): dencoder: check for radosgw build option
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
09:00 PM Revision 5373ee24 (ceph): osd: use ceph scoped shared_ptr
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
08:59 PM Revision a4f091cd (ceph): Merge pull request #8 from ceph/yuriw
Added new dumpling-emperor-x upgrade suite Zack Cerza
08:10 PM Revision f9d8c10c (ceph): removed leftover dirs again
Yuri Weinstein
07:32 PM Bug #6685 (Resolved): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
a9677e136ee4753b86ed1151ca6ff08e4b63473d David Zafman
07:22 PM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")

The fix 545135f3e1c75318940caa2c82ac32a53fc4f957 went in because it was thought that a race was occurring betwe...
David Zafman
02:15 PM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
07:31 PM Revision fee57a48 (ceph): removed one upgrade-sequence step and re-named the rest of steps
Yuri Weinstein
07:25 PM Revision 7e625d27 (ceph): Merge pull request #206 from ceph/wip-osd-debug
schedule_suite: debug osd = 20 for the time being Zack Cerza
07:15 PM Revision 70e217f0 (ceph): schedule_suite: debug osd = 20 for the time being
This will make it easier to chase the first pass of firefly bugs.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:20 PM Revision 084c6aed (ceph): Merge pull request #203 from ceph/wip-devstack
Add devstack task Alfredo Deza
06:11 PM Revision a53454ba (ceph): jenkins: fail fast during job execution
Jenkins will dynamically write the commands in its database into a
script and run it with "-x" and "-e" in order to d...
Ken Dreyer
06:08 PM Revision 6671d02d (ceph): Merge pull request #204 from ceph/wip-fix7397-wusui
Do not spawn a parallel task if dictionary entry does not exist. Zack Cerza
05:40 PM Revision fd6f61d6 (ceph): removed unfinished stress-split suite from
Yuri Weinstein
05:30 PM Revision 8ba6a2b0 (ceph): removed obsolete suite from upgrades dir and added dumpling-emperor-x p...
Yuri Weinstein
05:23 PM Revision ca600a2e (ceph): Add unit test for task.devstack.parse_os_table()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
04:22 PM Revision 0ebb1f83 (ceph): mon/MDSMonitor: Cope with failures during creation
Previously an MDS which failed in state CREATING could be
assigned the sequence BOOT->STANDBY->REPLAY at its next
sta...
John Spray
04:18 PM Revision 54116135 (ceph): Add debug output for reconnect() failures
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:57 PM Revision 05842e9f (ceph): Add explanations to asserts
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:43 PM Revision cfb7b948 (ceph): Guard against ctx.config being unset or None
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:15 PM CephFS Bug #7503: mds start and oops after access to cephfs
Ok for explanation, and as already said, all that data was test data, so I can loose it without problems. I also full... Yann Dupont
08:45 AM CephFS Bug #7503: mds start and oops after access to cephfs
MDS is getting an ENFILE (object lost) from the OSD while trying to read the OMAP from one of its stray directory obj... John Spray
07:18 AM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
this is a follow up to http://tracker.ceph.com/issues/7367, which explain the scenario.
I now attach the mds.log
Yann Dupont
02:39 PM Messengers Bug #5508 (Can't reproduce): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
Sage Weil
02:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
Sage Weil
02:37 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
Sage Weil
02:37 PM Bug #6671 (Can't reproduce): FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Sage Weil
02:36 PM Bug #6636: sockaddr_storage and uuid_t are not portable to other platforms
Sage Weil
02:35 PM Bug #6730 (Won't Fix): BUG: MAX_LOCKDEP_ENTRIES too low!
Sage Weil
02:35 PM Bug #6333 (Closed): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
See #6278 for teh snaptrimmer portion of this. the rest is somewhere between resolved, need more info, and can't repr... Sage Weil
02:33 PM Bug #6806: mon: audit cmd_getval() calls to make sure they handle failures correctly
this patch is still sitting in wip-6796-b Sage Weil
02:33 PM Bug #6633 (Resolved): osd: pgls vs osd restart/peering race misses objects
Samuel Just
02:32 PM Bug #6787: upstart is restarting daemons which we want to be dead
Sage Weil
02:30 PM Bug #7120 (Need More Info): osd: EEXIST on mkcoll on dumpling
Sage Weil
02:29 PM Bug #7170 (Can't reproduce): rados api test LibRadosMisc.CopyPP failed on next branch
Sage Weil
02:29 PM Bug #7172 (Resolved): osd: OSD failed to start with osd_leveldb_cache_size > 0
Samuel Just
02:29 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
Sage Weil
02:28 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
Samuel Just
02:28 PM Bug #7376 (In Progress): mon: >10s spent in remove_redundant_pg_temp
Sage Weil
02:28 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
Sage Weil
02:24 PM Bug #7068 (Need More Info): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.s...
Sage Weil
02:21 PM Bug #7072: logrotate not sending HUP signal
Sage Weil
02:20 PM Bug #7145 (Can't reproduce): PG::update_snap_map assert
Sage Weil
02:19 PM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
Sage Weil
02:18 PM Bug #7248: osd: bench set max size
Sage Weil
02:17 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
It looks like you've got an older ceph tool installed locally. Can you validate that the versions match? (i.e., on th... Greg Farnum
02:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
Sage Weil
02:13 PM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
Sage Weil
02:13 PM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
Sage Weil
02:12 PM Bug #7393 (Need More Info): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0...
Sage Weil
02:12 PM Bug #7458: osd: stray pg ref on shutdown
perhaps that pg work queue PGBackend implementation can use? Samuel Just
02:11 PM rbd Bug #7385 (In Progress): Objectcacher setting max object counts too low
Sage Weil
02:10 PM Bug #7398 (Need More Info): osd: ERANGE from clone
Sage Weil
02:09 PM Bug #7491 (In Progress): rados api crashes
Sage Weil
02:09 PM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
09:36 AM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
wip-7506 Samuel Just
09:35 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
simple fix, ECTransaction needs to require hash_infos for deletions and stashes.
-6> 2014-02-20 22:47:44.48251...
Samuel Just
02:09 PM Bug #7494: EC filter read op bug
Sage Weil
02:08 PM Bug #7496 (Need More Info): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
Sage Weil
02:08 PM Bug #7498 (Need More Info): stuck in recovery
Sage Weil
02:08 PM Bug #7497 (Need More Info): timeout waiting to go clean
Sage Weil
02:08 PM Bug #7495 (Need More Info): ENOTEMPTY on collection remove
Sage Weil
01:58 PM Bug #7463: ceph-rest-api fails to start with no OSDs up
Dan fixed in db88e7f385f4464f5f4de517845607391c314ef5 Brian Andrus
01:08 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
This is pretty consistent in the rbd runs - 0 vs 1 dirty objects in each of these failures: http://pulpito.front.sepi... Josh Durgin
11:57 AM Bug #7508: 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burnupi09.front...
wip-7508 Samuel Just
11:57 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Objecter doesn't take primary position into account.
2014-02-20T21:16:09.130 INFO:teuthology.task.rados.rados.0.ou...
Samuel Just
10:23 AM rbd Feature #7507 (New): krbd: Make device symlinks cluster aware
Currently when a device is mapped a udev script creates a symlink at /dev/rbd/<pool>/<imagename>
Would be nice if ...
Tyler Brekke
09:29 AM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
Ian Colle
07:22 AM Bug #7367: fail to run mds and mount rbd (v0.76)
OK, so see #7503, http://tracker.ceph.com/issues/7503.
Also see #7368, http://tracker.ceph.com/issues/7368 which...
Yann Dupont
09:02 AM Bug #7504 (Rejected): Ceph does not specify python2
Hi,
Ceph fails on archlinux because it uses python and not python2.
On Archlinux, python = python3 and to use pyt...
Alexandre BIQUE
08:30 AM CephFS Bug #7485 (Fix Under Review): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
John Spray
08:29 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)
https://github.com/ceph/ceph/pull/1283 John Spray
08:14 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)

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

Sheldon Mustard
04:18 AM Revision dadc9f7d (ceph): Do not spawn a parallel task if dictionary entry does not exist.
Fixes: 7397
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
01:04 AM Revision 6c207286 (ceph): Merge remote-tracking branch 'upstream/next'
Samuel Just
01:02 AM Revision 2bcddce8 (ceph): Merge remote-tracking branch 'upstream/wip-copyget' into next
Fixes: #7471
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
12:48 AM rgw Bug #7502 (Rejected): S3 API - deleting object always returns 204 regardless of object is existin...
When using S3 API, deleting object always returns 204 regardless of object is existing or not. This is reproducible. ... Zhi Zhang
12:01 AM Revision ba5d12f4 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite into yuriw
Yuri Weinstein
12:00 AM Revision c6e6ced1 (ceph): PG::build_might_have_unfound: skip CRUSH_ITEM_NONE
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just

02/20/2014

11:51 PM Revision b92578e5 (ceph): Remove unused import
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision fdaaee57 (ceph): Source openrc before creating volume
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 11b60fef (ceph): Change usages of StringIO.read() to getvalue()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision f7b1d922 (ceph): Wait 30s for Keystone to start
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 830748a6 (ceph): Move external docs URLs
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision aecd98d7 (ceph): Fix incorrect exception name in docstring
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 741b4de3 (ceph): Add a retry to the rbd volume verification
This was running into an auth problem intermittently that Josh Durgin
said is likely not a real problem. Still, try t...
Zack Cerza
11:46 PM Revision b638dc41 (ceph): Don't run the exercise subtask by default
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 27bad445 (ceph): Move restart_apache() to after the reboot
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 021f84ac (ceph): Simplify create_if_vm's downburst config logic
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 3dcde65c (ceph): Add note about memory requirements
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1228ac88 (ceph): Add documentation to reboot()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 61e9ac4d (ceph): Move reboot() to teuthology.misc
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision e3f336d1 (ceph): Make reconnect() use Remote.reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 5c12d360 (ceph): Add devstack.exercise subtask
The subtask runs devstack/exercise.sh
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision 85e63dd9 (ceph): Allow using different devstack branches
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 7c571274 (ceph): Forget about saving the exercise.sh log, for now
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision f53028f9 (ceph): Add a new subtask: smoke()
Currently it creates a volume, then verifies that the volume exists in
Ceph - as opposed to some other place. This is...
Zack Cerza
11:46 PM Revision 69beebc9 (ceph): get_file() returns a str, not a StringIO...
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a2a5aed4 (ceph): Add Remote.hostname property
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1c71558e (ceph): Add Remote.is_online property
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 71b4bfe2 (ceph): Remote instances can now establish SSH connections
Previously, they required an active ssh connection object to be passed
to them. That behavior is still functional.
S...
Zack Cerza
11:46 PM Revision 8dfac438 (ceph): Make Remote.is_online more accurate
To really know if the connection is active, we need to read something
from the remote host.
Signed-off-by: Zack Cerz...
Zack Cerza
11:46 PM Revision 22894969 (ceph): Use new init parameters for Remote
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 297096b5 (ceph): Add Remote.reconnect()
Also rename Remote._connect() to Remote.connect() and change its
semantics to match Remote.reconnect()
Signed-off-by...
Zack Cerza
11:46 PM Revision fe0aedf7 (ceph): Set apache ServerName, reboot, restart devstack
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a1ed3d49 (ceph): Add logging calls to each helper function
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1a0be5a0 (ceph): Tweaks to is_online and reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a4bf1f8f (ceph): Actually call Remote.reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision e73df9c8 (ceph): Make rejoin-stack.sh start screen in detached mode
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 74355e54 (ceph): Add optional 'owner' arg to sudo_write_file()
This gets passed directly to chown as 'sudo chown $owner $file'
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision b6740480 (ceph): Copy ceph auth keys over to devstack node
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision c6b5c01a (ceph): Split out devstack-ceph configuration
This is starting to get long, so create configure_devstack_and_ceph()
Signed-off-by: Zack Cerza <zack.cerza@inktank....
Zack Cerza
11:46 PM Revision b40f5f74 (ceph): Add set_libvirt_secret() and split out other steps
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 76588e97 (ceph): Add update_devstack_config_files()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision cedd1283 (ceph): Split out key generation
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision b33686f4 (ceph): Use get_file() and sudo_write_file()
... instead of copy_file()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision f5006348 (ceph): Don't pass owner to copy_key()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision b474d282 (ceph): Fix typoed virsh call
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 119b438f (ceph): Call seek(0) on StringIO objects before reading
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a55c22aa (ceph): Work around a bug in ConfigParser
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 375d7ddd (ceph): Use ConfigParser.set() instead of update()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision dfe60526 (ceph): Add copy_file() to scp files between remotes
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 10e12c2d (ceph): Add skeleton devstack task
Currently only installs devstack on one node, and creates some pools on
the ceph cluster.
Signed-off-by: Zack Cerza ...
Zack Cerza
11:46 PM Revision ed512568 (ceph): Fix linter errors.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:01 PM Revision 1f30d1ab (ceph): ECBackend: deal with temp collection details in handle_sub_write
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:56 PM Revision a3f6d9a6 (ceph): Merge pull request #201 from ceph/wip-6531-wusui
Fix formatting and add docstrings to ceph_manager.py Zack Cerza
10:51 PM Revision 30f8938e (ceph): Fix formatting and add docstrings to ceph_manager.py
Fixes: 6531
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
10:51 PM Revision b4ce61cc (ceph): Add back in print in ceph_manager that the last checkin accidentally re...
Warren Usui
10:42 PM Support #7501 (Closed): Firefly - monitor hangs when ceating EC pool with latest code in master/f...
We are so eager to test out the Firefly erasure coding features even before the RPM packages being released. Here we ... Zhi Zhang
09:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
pull request is #1280 for wip branch wip-7374-wusui Anonymous
09:22 PM rgw Bug #7374: s3_multipart_upload.pl fails
This has been pushed in its own branch to wip-7374-wusui Anonymous
09:28 PM rgw Bug #7375: s3_user_quota.pl fails
Pull request is #1279 for wip branch wip-7375-wusui Anonymous
09:21 PM rgw Bug #7375: s3_user_quota.pl fails
this has been pushed in its own branch to wip-7375-wusui
Anonymous
09:22 PM Revision c703a89d (ceph): ReplicatedPG::on_global_recover: requeue degraded, then unreadable
We need to requeue in reverse order since we are requeueing at the
front.
Signed-off-by: Samuel Just <sam.just@inkta...
Samuel Just
05:47 PM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
Dan Mick
05:30 PM Revision 4a802cd5 (ceph): Merge pull request #7 from ceph/wip-upgrade
upgrade: dumpling-next -> dumpling-x Zack Cerza
05:25 PM Revision 0ae33529 (ceph): rgw: multi object delete should be idempotent
Fixes: #7346
When doing a multi object delete, if an object does not exist then we
should return a success code for t...
Yehuda Sadeh
05:19 PM Revision 474d86ca (ceph): upgrade: dumpling-next -> dumpling-x
Make the final upgrade step unspecified so that it can be specified at
schedule time. This let us test dumpling -> f...
Sage Weil
05:19 PM Revision caf2edfc (ceph): rgw: minor cleanup
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
05:05 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
05:01 PM Revision 1307ba9c (ceph): mds: Table read failure should log at error level
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision a4d0eb1b (ceph): mds: Remove some unused #defines
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision 2762ede7 (ceph): mds/CDir: Remove a few lines of cruft
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision 81bcf430 (ceph): mds: Don't create the /.ceph directory
This was entirely unused. On existing filesystems
it will live on, on new ones it will never be created.
Signed-off...
John Spray
04:59 PM Revision 5fb90a2f (ceph): Fix generate keystone token from credentials
Request to v2.0/tokens must be a POST request and the request
should specify JSON in the content-type header and fix ...
Mouad Ben
04:27 PM rgw Bug #7499 (Resolved): rgw: bucket unlink / link isn't working
bucket link doesn't work, as we're not able to specify the bucket instance to be linked. We need to think whether we ... Yehuda Sadeh
03:22 PM Revision 541beb87 (ceph): mds: Add encode/decode/dump for use with dencoder
This is for the MDSTable subclasses: AnchorServer,
SnapServer, InoTable. AnchorServer was partially there
but didn't...
John Spray
02:48 PM Bug #7498 (Resolved): stuck in recovery
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91241
- exec:
client.0:
...
Samuel Just
02:46 PM Bug #7497: timeout waiting to go clean
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91236 Samuel Just
02:45 PM Bug #7497: timeout waiting to go clean
We might just increase the timeout for rados bench runs. Samuel Just
02:44 PM Bug #7497 (Can't reproduce): timeout waiting to go clean
2014-02-20T07:02:16.913 INFO:teuthology.task.radosbench.radosbench.0.err:[10.214.132.16]: 2014-02-20 07:02:16.911765 ... Samuel Just
02:40 PM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
-6> 2014-02-20 02:51:46.869695 7f9b5302e700 5 osd.0 pg_epoch: 152 pg[4.3( v 152'3174 (15'171,152'3174] local-les... Samuel Just
02:39 PM Bug #7495 (Resolved): ENOTEMPTY on collection remove
"can_rollback_to": 12}}]}
2014-02-20 06:28:11.741673 7fcba3c5c700 -1 os/FileStore.cc: In function 'uns...
Samuel Just
02:33 PM Bug #7494 (Resolved): EC filter read op bug
-4> 2014-02-20 00:12:48.296974 7f1623101700 5 -- op tracker -- , seq: 39278, time: 2014-02-20 00:12:48.295450, e... Samuel Just
02:24 PM Bug #7493 (Resolved): cephtool/pool_ops failure
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90946
{description: 'rados/si...
Samuel Just
02:18 PM Bug #7491 (Resolved): rados api crashes
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90865
2014-02-19T23:44:36.621...
Samuel Just
02:18 PM Bug #7490 (Closed): [docs] adding monitor section doesn't specify the need for the admin keyring
The documentation to add monitors manually does not note that the admin keyring file needs to be present
when adding...
Alfredo Deza
01:42 PM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
While attempting to add a monitor that already was in the cluster with a specific IP, instead of
reporting the actu...
Alfredo Deza
10:52 AM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
this came down to a crush flaw. there is a new tunable to address it in firefly, although it will remain off for the... Sage Weil
09:49 AM rgw Feature #7467: Make radosgw work with multiple hostnames
Yehuda Sadeh
09:20 AM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
Yehuda Sadeh
09:19 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
actually, seems that the original code is post dumpling. Yehuda Sadeh
09:13 AM rgw Bug #7453 (Pending Backport): Authentication to keystone using rgw_keystone_admin_* failed
Pushed, commit:5fb90a2f6dd5b31634efc748a977924dbdbebcb9 Yehuda Sadeh
08:11 AM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
New signed off patch Mouad Ben
08:48 AM rados-java Bug #7488: "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Yuri Weinstein wrote:
> Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing...
Yuri Weinstein
08:46 AM rados-java Bug #7488 (Rejected): "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing-basic-plana/88201
err...
Yuri Weinstein
07:20 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
See the thread "[ceph-users] ceph-mon segmentation fault"... Greg Farnum
06:48 AM devops Bug #7486 (Rejected): python-backports needs fixing for rhel
Getting warnings
/usr/lib/python2.6/site-packages/babel/__init__.py:33: UserWarning: Module backports was already ...
Sheldon Mustard
06:23 AM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)

Pretty easy to reproduce: start MDS for first time on fresh cluster (I'm using vstart here), ctrl-c it promptly, tr...
John Spray
03:06 AM Revision c5c7f6c8 (ceph): Merge branch 'next'
Conflicts:
src/test/admin_socket.cc
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
Ken Dreyer
02:45 AM Bug #7367: fail to run mds and mount rbd (v0.76)
yes, please Zheng Yan
02:33 AM Bug #7367: fail to run mds and mount rbd (v0.76)
I think this bug can be closed as we're probably not in a supported scenario.
I've been able to backup all my RBD ...
Yann Dupont
02:41 AM Revision ebd43972 (ceph): RadosModel: copyfrom should result in a dirty object
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
02:22 AM Revision 68184d45 (ceph): PG: fix scrub feature check
acting[0] isn't necessarily the primary. Start at
0 and explicitely skip the primary.
Signed-off-by: Samuel Just <s...
Samuel Just
01:31 AM Revision 715cbd31 (ceph): ReplicatedPG: ensure that ec appends are aligned
When not writing out the last chunk, _write_copy_chunk
will trim the chunk to a stripe boundary for ec pools
and adju...
Samuel Just
01:31 AM Revision 44417927 (ceph): ECBackend: handle short reads
async reads may have a length past the end of the object.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
01:31 AM Revision 67d1f364 (ceph): ReplicatedPG: assert no omap for ec pool in _write_copy_chunk and skip
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
01:31 AM Revision c337f638 (ceph): ReplicatedPG: fix stat uses to use the correct shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
01:31 AM Revision 78d9c007 (ceph): ReplicatedPG::fill_in_copy_get, use getattr_maybe_cache
Also, add user_only flag to getattr_maybe_cache and cleanup
the other user.
Signed-off-by: Samuel Just <sam.just@ink...
Samuel Just
01:30 AM Revision aa110af9 (ceph): OSDMap::_apply_primary_affinity: skip CRUSH_ITEM_NONE in non-default check
Fixes: #7482
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
12:57 AM Revision b3bb9efe (ceph): doc/release-notes: v0.77
Also pending notes for v0.78
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
12:20 AM Revision fa96de9e (ceph): doc/release-notes: v0.67.7
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/19/2014

10:54 PM Revision 1bca9c5c (ceph): v0.77
Ken Dreyer
10:14 PM CephFS Bug #6608: samba teuthology dbench failure
We're still occasional samba test failures, but I haven't diagnosed them carefully enough to know if they're this fai... Greg Farnum
10:14 PM Revision 40bdcb88 (ceph): osd/,mon/: add (up|acting)_primary to pg_stat_t
We use pg_stat_t information to determine pg create targeting.
Fixes: #7481
Signed-off-by: Samuel Just <sam.just@ink...
Samuel Just
10:01 PM Revision d78b9b01 (ceph): jenkins: add debugging output to shell script
When we migrated the Jenkins commands into Git, the exact commands are
no longer visible unless we run with "-x".
Ad...
Ken Dreyer
09:44 PM Revision c0360077 (ceph): Merge pull request #195 from ceph/wip-7003-wusui
Add docstrings to the orchestra code. Also fix minor formatting issues Zack Cerza
09:40 PM Revision 31c27e13 (ceph): Merge pull request #186 from ceph/wip-7369
Fix #7369: "sed expression must be raw string" Alfredo Deza
09:40 PM Revision e5fe884e (ceph): Merge pull request #186 from ceph/wip-7369
Fix #7369: "sed expression must be raw string" Alfredo Deza
09:37 PM Revision f3ac7870 (ceph): Fix syntax error in first docstring added.
Warren Usui
09:34 PM Revision efd59a2a (ceph): Merge pull request #190 from kdreyer-inktank/jenkins
add jenkins-pull-requests-build script Zack Cerza
09:26 PM Revision a70e93fc (ceph): Merge pull request #199 from ceph/wip-6540-wusui
Add docstrings. Fix formatting issues for rgw.py Zack Cerza
09:26 PM Revision cc3d013e (ceph): Merge pull request #196 from ceph/wip-6541-wusui
Fix docstrings in radosgw-admin-rest.py Zack Cerza
09:26 PM Revision 8d85b21c (ceph): Merge pull request #197 from ceph/wip-6535-wusui
Fix docstrings for task/blktrace.py, peering_speed_test.py, proc_thrashe... Zack Cerza
09:25 PM Revision f18dcf5b (ceph): Merge pull request #198 from ceph/wip-6539-wusui
Fix docstrings and minor formatting in task/ssh_keys.py Zack Cerza
09:23 PM Revision 9f953d42 (ceph): Merge pull request #200 from ceph/wip-6532-wusui
Fixed task/args.py docstrings. Zack Cerza
07:23 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
are you using 3.8 kernel? if you are, please try 3.12 or 3.13 Zheng Yan
01:07 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I'm on Ubuntu 13.10 and I've installed the packages distributed with it (ceph-deploy 1.2.3-0ubuntu1 and `ceph` 0.67.4... Peter Waller
07:20 PM Revision 10fee0e3 (ceph): Revert "Show hostname instead of IP in errors"
This reverts commit eafeece243607eef8209eaa8c08eecc7d1098eb1.
I was having problems with my newly-created devstack t...
Zack Cerza
07:18 PM Revision 72f260e0 (ceph): Merge pull request #1256 from ceph/wip-librados-ops-and-rvals
librados c api for object operations and a few bug fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by...
Josh Durgin
07:07 PM Revision 0427f615 (ceph): rgw: fix swift range response
Fixes: #7099
Backport: dumpling
The range response header was broken in swift.
Reported-by: Julien Calvet <julien.ca...
Yehuda Sadeh
07:06 PM Revision 2b3e3c83 (ceph): rgw: fix etag in multipart complete
Fixes: #6830
The etag member variable was not set correctly.
Reported-by: Benjamin Gilbert <bgilbert@backtick.net>
S...
Yehuda Sadeh
07:06 PM Revision 859ed33e (ceph): rgw: reset objv tracker on bucket recreation
Fixes: #6951
If we cannot create a new bucket (as it already existed), we need to
read the old bucket's info. However...
Yehuda Sadeh
07:03 PM Revision 53de6412 (ceph): radosgw-admin: don't generate access key if user exists
Fixes: #6936
We want the user creation operation to be idempotent, so if user already
exists don't generate a new acc...
Yehuda Sadeh
06:09 PM Revision d7ab4244 (ceph): v0.67.7
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com> Ken Dreyer
05:56 PM Revision f0bfff11 (ceph): add jenkins-pull-requests-build script
Move our Jenkins pull requests build script out of Jenkins' database and
into Git so that we can have greater visibil...
Ken Dreyer
05:40 PM Revision 9e8882e0 (ceph): BackedUpObject::get_xattr() pass function parameter by reference
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:37 PM Revision 53b36898 (ceph): TestRados.cc: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:35 PM Revision 86b08796 (ceph): ErasureCodeBench: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:34 PM Revision 200ebb9b (ceph): ceph_erasure_code.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
aa110af991e6d637b30d740af46f3dc2168cde01 Samuel Just
03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
wip-copyget Samuel Just
11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
Samuel Just
05:32 PM Revision e6772c76 (ceph): RGWObjManifest: prefer prefix ++/--operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:30 PM Revision 42e6da7b (ceph): ReplicatedPG: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:26 PM Revision 29c4abd8 (ceph): OSD: use !empty() instead of size() > 0
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
Anonymous
05:20 PM rgw Bug #7375: s3_user_quota.pl fails
This is the same issue as 7374. Anonymous
02:16 PM rgw Bug #7375: s3_user_quota.pl fails
This appears to be a problem in the 7375 pl script. I am taking it. Anonymous
05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
I have pushed a change for this. Anonymous
02:15 PM rgw Bug #7374: s3_multipart_upload.pl fails
This appears to be two problems in the s3_multipart_upload.pl script.
I am taking this.
Anonymous
05:17 PM Revision be857274 (ceph): PG: use !empty() instead of size() > 0
[src/osd/PG.cc:543]: (performance) Possible inefficient checking
for 'actingbackfill' emptiness.
[src/osd/PG.cc:148...
Danny Al-Gaaf
05:09 PM Revision f23ab4af (ceph): RPCRecPred: use !empty() instead of size() >= 1
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:05 PM Revision 0626df90 (ceph): KeyValueStore: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:03 PM Revision 76c17239 (ceph): KeyValueStore: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:02 PM Revision ede614a7 (ceph): FileStore: use !empty() instead of size()
[src/os/FileStore.cc:3635]: (performance) Possible inefficient checking
for 'omap_set' emptiness.
Signed-off-by: D...
Danny Al-Gaaf
04:59 PM Revision eaf66967 (ceph): DBObjectMap: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:57 PM Revision 0bf0ec0f (ceph): OSDMonitor: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:55 PM Revision 31b4107a (ceph): OSDMonitor: use !empty() instead of size() > 0
[src/mon/OSDMonitor.cc:730]: (performance) Possible inefficient checking
for 'osd_weight' emptiness.
Signed-off-by...
Danny Al-Gaaf
04:53 PM Revision a1412bdf (ceph): MDCache: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:51 PM Revision 4a48d8ed (ceph): CrushWrapper::is_valid_crush_loc(): pass function parameter by reference
[src/crush/CrushWrapper.cc:1412]: (performance) Function parameter 'loc'
should be passed by reference.
Signed-off...
Danny Al-Gaaf
04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
The last call will end with abort()... Loïc Dachary
01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
... Loïc Dachary
10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
Loïc Dachary
06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
crashes on master as of today Loïc Dachary
03:41 PM Revision 3f68a5ca (ceph): CrushWrapper: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
03:38 PM Revision dd71051a (ceph): PGLog.h: prefer prefix ++operator for non-trivial iterator
[src/osd/PGLog.h:363]: (performance) Prefer prefix ++/-- operators for
non-primitive types.
[src/osd/PGLog.h:375]: ...
Danny Al-Gaaf
03:24 PM Revision 8488e710 (ceph): Client: remove a std::string::c_str() calls
[src/client/Client.cc:6821]: (performance) Passing the result of c_str() to a
function that takes std::string as ar...
Danny Al-Gaaf
03:17 PM Revision 1099e255 (ceph): common/config.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
03:13 PM Revision c7dfdfdc (ceph): str_map.cc: prefer prefix ++operator for non-trivial iterator
[src/common/str_map.cc:55]: (performance) Prefer prefix ++/-- operators
for non-primitive types.
Signed-off-by: Da...
Danny Al-Gaaf
03:10 PM Revision 7da714af (ceph): Client.cc: use !empty() instead of size()
[src/client/Client.cc:2275]: (performance) Possible inefficient
checking for 'cap_snaps' emptiness.
[src/client/Cli...
Danny Al-Gaaf
02:40 PM Bug #7471: ec pools copyfrom broken
wip-copyget Samuel Just
02:20 PM Revision fd08b09f (ceph): ceph_argparse.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Samuel Just
11:41 AM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Mon uses acting[0] to send create messages. More importantly, pg_stat_t does not include acting_primary or up_primar... Samuel Just
02:13 PM Revision 1d1392dd (ceph): Monitor: pass function parameter by reference
[src/mon/Monitor.h:619]: (performance) Function parameter 'param_str_map'
should be passed by reference.
Signed-of...
Danny Al-Gaaf
02:05 PM Revision ab45d44a (ceph): BarrierContext: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:02 PM Revision 4adcfa59 (ceph): BarrierContext: reduce scope of 'done' variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
01:54 PM Revision 19dad031 (ceph): MonClient: pass function parameter by reference
[src/mon/MonClient.h:412]: (performance) Function parameter 'mon_name'
should be passed by reference.
Changed also...
Danny Al-Gaaf
01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
This is already done (CORS). Yehuda Sadeh
01:34 PM Feature #7484 (New): better wording when authentication fails
After having a mismatch for the client.admin.keyring in a new host that I needed to get a monitor running I was getti... Alfredo Deza
01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
Yehuda Sadeh
01:33 PM rgw Tasks #5121 (Closed): bump up librados version
Closing this one. Yehuda Sadeh
01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7 Yehuda Sadeh
01:30 PM rgw Bug #6710 (Resolved): radosgw init script does not exit 1 and tell the user if the hostname does ...
This was fixed, commit:0c610918c4ebd6fc1376027cfe6425cfdcfa0245 Yehuda Sadeh
01:29 PM devops Bug #7483 (Rejected): ceph-deploy should fetch keyrings always
If keyring files exist in the cwd and they are dated/wrong ceph-deploy will say it has them and will not attempt to r... Alfredo Deza
01:28 PM rgw Feature #5136 (Closed): rgw: revise user stats
Yeah, I have no idea what this issue is about. Now, considering that user stats have actually been revised for the us... Yehuda Sadeh
01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
There's a good chance that this was #7030. Closing. Yehuda Sadeh
01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd Yehuda Sadeh
01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
Fix looks fine to me. Can you sign-off it? Yehuda Sadeh
10:29 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
subusers are only relevant for the swift case, and the regular access-key/secret combination does not apply to them. ... Yehuda Sadeh
10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
Yehuda Sadeh
10:19 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
So these packages were on the DVD (iso downloaded from https://rhn.redhat.com/rhn/software/channel/downloads/Download... Sandon Van Ness
10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
Yehuda Sadeh
09:35 AM rados-java Bug #7479 (Won't Fix): Test failed in rados-dumpling-testing-basic-plana
Logs are in - qa-proxy.ceph.com/teuthology/teuthology-2014-02-18_19:00:09-rados-dumpling-testing-basic-plana/89421
...
Yuri Weinstein
08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
Yehuda Sadeh
08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
Yehuda Sadeh
08:06 AM Bug #7451: updatedb will index /var/lib/ceph
This should also be reported to mlocate upstream (at Fedora) and to Red Hat for RHEL 7.
Here's the upstream update...
Ken Dreyer
07:53 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
This was an issue with the osd, fixed by commit:2795339d3632df975486d51e69762f9f567fb43d. Yehuda Sadeh
06:20 AM Revision 314116e2 (ceph): PG: insert into stray set if !us_up() && !is_acting()
This is simpler than checking actingbackfill
since it may not yet be filled in.
Fixes: #7470
Signed-off-by: Samuel J...
Samuel Just
06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
crashes, investigating why Loïc Dachary
05:10 AM Revision a33874d0 (ceph): Merge pull request #1257 from ceph/wip-agent
osd: a few agent fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
05:09 AM Bug #7445 (Rejected): missing feature bit ( next )
LD_LIBRARY_PATH was set to /usr/local/bin which contained an old version of the ceph libraries, causing the problem Loïc Dachary
05:05 AM Revision 0af73755 (ceph): osd/ReplicatedPG: strengthen agent_work assertions
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:05 AM Revision a40cd507 (ceph): osd/ReplicatedPG: load older HitSets into memory
If our evict_mode is non-idle, load older HitSets into memory in the agent
work thread.
Signed-off-by: Sage Weil <sa...
Sage Weil
05:05 AM Revision a5c5d924 (ceph): osd/ReplicatedPG: EOPNOTSUPP on hit_set_get on non-replicated pools
We need to use the async read stuff for this to work.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:24 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
Just a note, bug itself is very unlikely to reproduce in a short times (one crash per 1k VM instances per month or so). Andrey Korolyov
03:46 AM Revision 1d907c60 (ceph): OSD: consider up/acting primary for new intervals
Both acting_up_affected and start_peering_interval need
to consider primary changes as well as acting/up changes.
Fi...
Samuel Just
02:42 AM Revision afbd58ea (ceph): rgw: don't try to read bucket's policy if it doesn't exist
It's going to fail anyway, just build a default policy.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:35 AM devops Feature #7475 (Rejected): ceph-disk: prepare should be idempotent
If the target device / directory is already prepared exactly as required, ceph-disk prepare should return true with a... Loïc Dachary
12:43 AM Revision 3ed68eb9 (ceph): rgw: return error if accessing object in non-existent bucket
Fixes: #7064
Instead of trying to access the object, which is impossible as we don't
even have a proper bucket info. ...
Yehuda Sadeh

02/18/2014

11:43 PM Revision b0dcc798 (ceph): radosgw-admin: gc list --include-all
A new option to the radosgw-admin gc list command that dumps *all* gc
entries, and not just the expired ones. This is...
Yehuda Sadeh
11:38 PM Revision 1ff0eefe (ceph): Merge pull request #1259 from ceph/wip-6677
rgw: add compatibility for MultipartUpload
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:37 PM Revision a2c195d8 (ceph): Merge pull request #1258 from ceph/wip-rgw-gc
radosgw-admin: gc list --include-all
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:07 PM CephFS Bug #6608: samba teuthology dbench failure
still see the issue ? Zheng Yan
10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
wip-strays Samuel Just
09:49 PM Revision b9e1341f (ceph): rados/thrash: add ec-radosbench workload
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:45 PM Revision 386650d9 (ceph): rados/thrash: add ec workloads
Adds ec workloads for snaps, small objects, read-write.
copy-from is not yet enabled.
Signed-off-by: Samuel Just <s...
Samuel Just
09:41 PM Revision 82cf9795 (ceph): Merge pull request #1261 from ceph/wip-7463
ceph_rest_api.py: don't fail if no up OSDs found on startup
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
09:25 PM Revision 609f4c56 (ceph): Throw a Timeout exception on timeout.
Signed-off-by: Mike Lundy <mike@fluffypenguin.org>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Mike Lundy
09:19 PM Revision e3715652 (ceph): task/: add ec_pool and append to rados.py
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:19 PM Revision 2718dbc3 (ceph): radosbench: simplify pool creation and add ec_pool support
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:11 PM Revision 3fb6e258 (ceph): test/rgw: manifest unitest
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:11 PM Revision b3ce1889 (ceph): cls/rgw: fix debug output
print the correct error value
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
09:11 PM Revision 19754413 (ceph): dencoder: fix for new rgw manifest code
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:11 PM Revision da64bf70 (ceph): rgw: scalable manifest object
Define a new manifest structure. The idea is that the manifest defines a
set of rules for structuring the object part...
Yehuda Sadeh
09:07 PM Revision c5d3bdf7 (ceph): Merge pull request #1214 from ceph/wip-rgw-manifest-2
Wip rgw manifest 2
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
09:07 PM Revision db88e7f3 (ceph): ceph_rest_api.py: don't fail if no up OSDs found on startup
allow find_up_osd() to return None, and have caller check for it
Fixes: #7463
Signed-off-by: Dan Mick <dan.mick@inkt...
Dan Mick
08:34 PM Revision 0dc4309b (ceph): librados: add read to c object operation api
Do the usual bufferlist to buffer conversion in a callback from the
objecter before the librados user gets called.
S...
Josh Durgin
08:34 PM Revision 2543cde7 (ceph): librados: add exec to the c object operations api
Add two versions: one that allocates a buffer of the appropriate
length for the user, but relies on the user to free ...
Josh Durgin
08:34 PM Revision f68b706e (ceph): Objecter: add a way to chain callbacks
The librados C api needs to do extra things like converting c++ data
structures or setting lengths, but some objecter...
Josh Durgin
08:34 PM Revision 242a6c85 (ceph): librados: add read xattr functions for c object operations
Only implement string xattr comparison by since integer xattr
comparison assumes ceph-encoded integers in little-endi...
Josh Durgin
08:34 PM Revision 995fea9a (ceph): librados: add omap object operations to the c api
Create an iterator type similar to XattrIter for returning results.
It just wraps the std::map to preserve sorting.
...
Josh Durgin
08:34 PM Revision bac7bb64 (ceph): librados: bump version number
This covers the many recent changes leading up to the firefly release,
including the c object operations api.
Signed...
Josh Durgin
08:34 PM Revision 7a760337 (ceph): packaging: add test programs for librados c object operations
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision 4b229f71 (ceph): qa: add librados c object operations tests to librados test script
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision e550ad79 (ceph): ReplicatedPG: avoid undefined behavior in xattr comparison
Reading past the end of a pointer returned by string.data() in c++98
is undefined. While we're fixing this, also allo...
Josh Durgin
08:34 PM Revision 77436989 (ceph): ReplicatedPG: don't copy the ops vector into OpContext
There's no need to copy it, and if we refer to the same vector from
the original MOSDOp, we can modify rvals for indi...
Josh Durgin
08:34 PM Revision 1d661ca9 (ceph): ReplicatedPG: set individual osd op rvals
This takes care of things that can fail before transaction is
executed, like omap comparison. Getting individual rval...
Josh Durgin
08:34 PM Revision 18f08cd9 (ceph): ReplicatedPG: clear osd op reply output for writes
Since the vector of OSDOps used by the reply is the same
as the one processed by do_osd_ops() now, any output data
ne...
Josh Durgin
08:34 PM Revision bfbfcd6e (ceph): ReplicatedPG: fix successful write condition
ctx->modify no longer implies that the operation is a write,
if it ever did. These days op->may_write() is checked re...
Josh Durgin
08:34 PM Revision 7a019b38 (ceph): test/librados: remove unused lines and fix return code for cmp guards
Now that return values are actually set by the osd and client, fix up
the tests that were checking the old behavior.
...
Josh Durgin
08:34 PM Revision 9630f2f0 (ceph): test/librados: create general test case classes
Using a test case allows us to remove a boatload of boilerplate code
in all the tests, and focus them more on what th...
Josh Durgin
08:34 PM Revision 8d4a5fd5 (ceph): test/librados: add a connect_cluster() helper
This mirrors the c++ version, connect_cluster_pp(), and removes the
same code from create_one_pool().
Signed-off-by:...
Josh Durgin
08:34 PM Revision d3c6f171 (ceph): test/librados: use connect_cluster_pp() instead of duplicating it
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision c6d8d0ef (ceph): test/librados/cmd: remove unnecessary pool creation
Several tests here don't use the pool at all.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
08:34 PM Revision 5497e1cb (ceph): test/librados: use a test case instead of duplicating code everywhere
These tests don't have any special requirements on their ioctx and
pools, so they can also run much faster by using d...
Josh Durgin
08:34 PM Revision ae072ac2 (ceph): test/librados: use standard rados test case for snapshot tests
Split these into two categories, self-managed and pool snapshots,
since they are mutually exclusive for a single pool...
Josh Durgin
08:34 PM Revision 5276e3cc (ceph): test/librados: refactor setup/teardown in tiering tests
These tests can either use the standard RadosTest, with one pool, or a
new test case with two pools.
The new test ca...
Josh Durgin
08:34 PM Revision c61ba410 (ceph): test/librados: add ObjectReadOperation tests
These will help prevent regressions and demonstrate what should be
expected by the c api.
Signed-off-by: Josh Durgin...
Josh Durgin
08:34 PM Revision e255bf58 (ceph): librados: add section docs for object operations
The doxygen end section of watch notify was accidentally moved when
these were added, so fix that at the same time.
...
Josh Durgin
08:34 PM Revision 50ca88a1 (ceph): librados: add some comments about constants in librados.h
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision 7f1f0b55 (ceph): librados: remove constant for CMPXATTR_NOP
This constant was just added in the public header to match the
operations in rados.h, and was not included in a stabl...
Josh Durgin
08:34 PM Revision 4f4121ae (ceph): librados: add global op flags to the c api
The c++ api did not include these in the sync versions of the calls,
so add a flags argument to the IoCtxImpl functio...
Josh Durgin
08:34 PM Revision bc03fbb4 (ceph): librados: add individual op flags for c write operations
Move flag validation to a static function so it can be shared with the
c++ api. Refer to the new C constants from the...
Josh Durgin
08:34 PM Revision 770942aa (ceph): librados: add exec to the c write operations api
Nothing special needed here, just copying the input buffer and passing
things through. Don't allow output data since ...
Josh Durgin
08:34 PM Revision 6094e437 (ceph): librados: add simple atomic read operations to c api
stat, assert_exists, and set_flags are simple and need no extra
infrastrucutre.
Signed-off-by: Josh Durgin <josh.dur...
Josh Durgin
08:34 PM Revision 6503f21a (ceph): Objecter: add a context argument to ObjectOperation::read()
The c api will need this to be able to set the output buffer length
and potentially copy from bufferlist to buffer.
...
Josh Durgin
08:34 PM Revision abca34aa (ceph): Objecter: keep ObjectOperation rval pointers for writes
Just before sending an op, prepare_mutate_op() is called, creating a
new Op. prepare_read_op() already copied over al...
Josh Durgin
08:34 PM Revision 6273ba4a (ceph): test/librados: move test.cc into its own library
This way it doesn't have to be compiled many times, and it's easier
to add new general functionality to new files wit...
Josh Durgin
08:34 PM Revision 393a2021 (ceph): Merge pull request #1227 from ceph/wip-7394
Improve the OSD and generic monitor timeout mechanisms
Reviewed-by: Sage Weil <sage@inktank.com>
Gregory Farnum
07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
1d907c60d7628429292917fbabf61d09ef8dfa6f Samuel Just
04:15 PM Bug #7469: ENXIO on ec pool write
Samuel Just
04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
testing wip-primary Samuel Just
07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
Stopping the teuthology run and running the commands manually reveals the following:... Anonymous
06:56 PM Revision 43b5cf97 (ceph): Merge remote-tracking branch 'upstream/wip-ecbackend-for-review'
Reviewed-by: Sage Weil <sage@inktank.com> Samuel Just
06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
Yehuda Sadeh
05:09 PM rbd Bug #6480 (Need More Info): librbd crashed qemu-system-x86_64
...and now there's a new similar instance, this time on rhel:... Josh Durgin
12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
Ian Colle
04:22 PM Revision 45a782ff (ceph): Merge pull request #1255 from ceph/wip-cache-perf
osd: add perfcounters for new cache and agent events
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Sage Weil
04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
03:46 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Moving to the ceph project since any scrub errors are general rados problems. Josh Durgin
03:33 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Yuri Weinstein wrote:
Logs - qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-master-testing-basic-...
Yuri Weinstein
03:30 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
There are several of those.
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-maste...
Yuri Weinstein
03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d Yehuda Sadeh
03:10 PM rgw Feature #7467 (Resolved): Make radosgw work with multiple hostnames
A ceph user has a situation in which they would like to switch to a new hostname for accessing the gateways. At the t... Brian Andrus
02:47 PM Revision 4c930a0a (ceph): Revert "Capture stderr and include in CommandFailedError"
This reverts commit d0a434923100dd16548e5f76eaffa5462c4b91d4. Alfredo Deza
02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
Yehuda Sadeh
09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
Yehuda Sadeh
02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
commit:609f4c56718d8279895b02b8163bbe1976c02bfb Josh Durgin
02:21 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
The recently added timeouts for librados should result in a specific exception type in the python bindings. Josh Durgin
01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:07 PM Bug #7463 (Fix Under Review): ceph-rest-api fails to start with no OSDs up
No reason not to start. This appears to fix it:... Dan Mick
11:26 AM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
ceph-rest-api fails to start id it can find no up OSDs:
osdid = find_up_osd(app)
File "/usr/lib/python2.6/sit...
Brian Andrus
12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
Ian Colle
12:54 PM Revision c93f14f2 (ceph): filestore_idempotent: filestore -> objectstore path change
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
Ian Colle
12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
Ian Colle
12:51 PM Revision 150e87a1 (ceph): osd: l_osd_tier_whiteout
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision dbec1096 (ceph): osd: l_osd_tier_[dirty|clean]
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision d1a185bd (ceph): osd: l_osd_agent_{wake,skip,flush,evict}
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 4bee6ff1 (ceph): osd/ReplicatedPG: clean up agent skip debug output
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 4b0a0a10 (ceph): osd: l_osd_copyfrom
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision c45a477e (ceph): osd: l_osd_tier_[try_]flush[_fail]
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 2d5371dd (ceph): osd: l_osd_tier_evict
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:45 PM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
This was observed on a 3.11 ubuntu kernel:... Josh Durgin
12:40 PM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
backported in commit:4e47a003bb3adcee690067d4037c248a93023c20 a while ago Josh Durgin
12:37 PM Feature #7464 (Rejected): Backport appropriate pieces of #7394, #7395
We put some fixes for OSDs overwhelming the monitor into master; now they need to get backported to Dumpling. Greg Farnum
12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e Greg Farnum
11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
Samuel Just
11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
Samuel Just
11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
Samuel Just
11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7366 (Resolved): EC: scrubbing
Samuel Just
11:01 AM Feature #7366: EC: scrubbing
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
Not desirable for final design Samuel Just
11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b Yehuda Sadeh
09:29 AM rgw Bug #7346 (Pending Backport): An unfound object as part of multi-object delete should return dele...
A fix was pushed, commit:8ca3d95bf633ea9616852cec74f02285a03071d5. Yehuda Sadeh
08:54 AM Bug #7451: updatedb will index /var/lib/ceph
Sage Weil wrote:
> I'm not sure the init script is the place to do it.. maybe the package postinst?
postinst is n...
Dietmar Maurer
04:12 AM Revision 11f288e5 (ceph): Objecter: track primary explicitly to detect changing primaries
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5e727bfe (ceph): RadosModel: only output if missing header is actually a problem
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 7772014a (ceph): OSD,PG: pass through EC messages
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision ae827cfe (ceph): osd_types: add swap, claim_append to ObjectModDesc
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 258af5eb (ceph): buffer: allow caller to initialize bufferhash state
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 7731a949 (ceph): ObjectStore: add bufferlist/string getattr
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 33c38301 (ceph): osd/ECUtil: add ec encode/decode util helpers
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 45b6c59e (ceph): osd/ECTransaction: add type encapsulating EC transaction
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 792f0a85 (ceph): ECBackend: flesh out ECBackend implementation
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision b90584a8 (ceph): osd/: instantiate the right backend based on pool
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision bc31c4b3 (ceph): ReplicatedPG: add some debugging if waiting_for_commit is non-empty
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision f0b69b38 (ceph): osd/: replace bufferptr with bufferlist for attrs in recovery
Now we won't have to keep converting back and forth!
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:12 AM Revision 1835c29f (ceph): ReplicatedBackend: factor out be_deep-scrub
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 26745ca8 (ceph): PGBackend/ReplicatedBackend: move the backend agnostic code into PGBack...
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 510585b7 (ceph): PGBackend/ReplicatedBackend: factor out logical to ondisk size mapping
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision ca323ff6 (ceph): ReplicatedPG: fix size checking for ECBackend pools
Allow the backend to adjust the logical object size before
checking against the ondisk size.
Signed-off-by: Samuel J...
Samuel Just
04:12 AM Revision 0661d802 (ceph): PGBackend: make getattrs virtual
This way, the backend can choose to filter private attrs.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:12 AM Revision e8820ac4 (ceph): src/osd/: add ECBackend stubs
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 6cd64a50 (ceph): messages,osd: add EC messages and associated types
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5db3b2dc (ceph): osd/: extend pg_interval_t to include primary
Otherwise, we cannot correctly determine up_from/up_thru for
old intervals. Also, we need this information to determ...
Samuel Just
04:12 AM Revision 2d3205ff (ceph): PG: skip CRUSH_ITEM_NONE in acting set in various places
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5a8c0bb9 (ceph): os/: allow objects with NO_GEN but non-NO_SHARD shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 74b8a0c0 (ceph): PG,PGBackend: expose acting and backfill_targets
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision facec765 (ceph): PGBackend: add some additional helpers.
ECBackend's primary specific logic mostly won't treat the
primary shard specially, so it'll be handy to have primary
...
Samuel Just
04:12 AM Revision 8b33d60f (ceph): PG: allow PGBackend to set criteria for PG up-ness
ECBackend needs to be able to require that a readable
set of the most recent interval to write be available
in order ...
Samuel Just
04:12 AM Revision 84e2f39c (ceph): PG,ReplicatedPG: Generalize missing_loc for ECBackend
Prior to EC pools, unfound => missing. Now, unfound (unreadable,
really) is dependent on the PGBackend requirements ...
Samuel Just
04:12 AM Revision 0b180e6a (ceph): PG::discover_all_missing: request a FULLLOG
Otherwise, we cannot correct for divergent objects in the missing
set.
Signed-off-by: Samuel Just <sam.just@inktank....
Samuel Just
04:12 AM Revision 41e19453 (ceph): PG: refactor calc_acting to handle pg_shard_t changes
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 285cf772 (ceph): PG: introduce calc_ec_acting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 109b3c9e (ceph): OSDMap: fill in get_primary_shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 904704ac (ceph): OSDMap: handle CRUSH_ITEM_NONE in acting sets
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 9d8be1b0 (ceph): Objecter: handle primary other than acting[0]
EC pool particularly might have CRUSH_ITEM_NONE as acting[0] which
is not a valid osd.
Signed-off-by: Samuel Just <s...
Samuel Just
04:12 AM Revision 035d6cc2 (ceph): osd/: refer to pg by spg_t and replica by pg_shard_t
We may have multiple pg shards on the same osd for an
ec pool. Thus, replicas must be referred to by <osd, shard>
an...
Samuel Just
04:11 AM Revision 5d01f88c (ceph): ReplicatedBackend/PGBackend: move objects_* methods into PGBackend
These also are unchanged in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:11 AM Revision 761f0b1e (ceph): PGBackend: use whoami_shard().shard in rollback*, objects*
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 31b7937b (ceph): PGBackend/ReplicatedBackend: move temp handling into PGBackend
Temp handling is also the same in ReplicatedBackend as in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:11 AM Revision fa980644 (ceph): ReplicatedBackend: excise OSDService*
This should eventually make it easier to mock out a PGBackend::Listener.
Signed-off-by: Samuel Just <sam.just@inktan...
Samuel Just
04:11 AM Revision 8b46dd1d (ceph): messages/: include shard information in various pg messages
We can no longer use the messenger source information to determine
the origin of the message since an osd might have ...
Samuel Just
04:11 AM Revision f678aefd (ceph): TestPGLog: remove test with DELETE op with prior_version = eversion_t()
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 1c93e03f (ceph): osd/: Add a shard parameter to SnapMapper to handle multiple pg shards
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision f2826fa2 (ceph): src/osd: pass in version to recover to recover_object
Otherwise we need to do some annoying contortions to
get it out of the missing sets.
Signed-off-by: Samuel Just <sam...
Samuel Just
04:11 AM Revision 44b43df4 (ceph): ObjectStore: use ghobject_t for setattrs
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 4a259516 (ceph): osd_types: introduce spg_t, pg_shard_t
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 8ca875b6 (ceph): PGBackend/ReplicatedBackend: move rollback methods into PGBackend
These will end up essentially unchanged in ECBackend as it turns out.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:10 AM Revision 09d611d2 (ceph): PGLog::merge_old_entry: simplify the oe.version > ne.version case
If ne.version < oe.version, the correct answer is to rollback oe.version
if possible regardless of what the entries a...
Samuel Just
12:41 AM Revision 5f8eedf0 (ceph): rados/thrash: test rados against cache pool with agents
Run rados model against a pool with target_max_objects set so that the
tiering agent is working against us.
Signed-o...
Sage Weil
12:26 AM Revision e6a1122b (ceph): osd: l_osd_tier_promote
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/17/2014

11:56 PM RADOS Bug #7460 (New): librados: no test for c api's global ops flags
This could be tested by creating a binary just for testing that enables logging, sets some global op flags, and grepp... Josh Durgin
11:15 PM Revision 5bc92ece (ceph): Merge pull request #1128 from ceph/wip-dirfrags
Fixes for mds cluster + directory fragments Zheng Yan
10:25 PM Revision d116e55f (ceph): PG: just ignore rollbacks on objects we have already failed to rollback
The relevant changes to missing and/or the filestore will have
already been made.
Signed-off-by: Samuel Just <sam.ju...
Samuel Just
10:25 PM Revision fd9da00e (ceph): ReplicatedPG: take snapset_obc write lock where appropriate
Otherwise, we might read it for backfill before it's fully created
on a peer.
Signed-off-by: Samuel Just <sam.just@i...
Samuel Just
10:25 PM Revision 0e7b10ac (ceph): PG::remove_snap_mapped_object: use pg_whoami.shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 3650da69 (ceph): ErasureCodeJerasure: fill in decoded if all shards are included
This causes it to match minimum_to_decode.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 13a41e14 (ceph): FileStore: permit NULL onreadable callback
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision d8b6d4c1 (ceph): ReplicatedPG: release_op_ctx_locks in all-applied, not all-committed
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision b3b2bab4 (ceph): ReplicatedPG: handle xattr cache on rollback and delete_head
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 17e6ecc8 (ceph): ReplicatedPG: find_object_context debugging: output oi
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision f020ce90 (ceph): ReplicatedPG:: remove_snap_mapped_object already removes the object
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 643b6a50 (ceph): ReplicatedPG,osd_types: seperate require_rollback from ec_pool
It's handy to allow a pool to answer false to ec_pool() and
true to require_rollback() in order to allow a replicated...
Samuel Just
10:24 PM Revision d687ed96 (ceph): ReplicatedPG: take clone write lock as well in make_writeable
Otherwise, we might start backfilling the clone before the op is
complete.
Signed-off-by: Samuel Just <sam.just@inkt...
Samuel Just
10:24 PM Revision da4652c9 (ceph): ReplicatedPG: release backfill state on_global_recover not peer recover
There may now be multiple backfill peers.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 4c1338f4 (ceph): SimpleMessenger: init_local_connection whenever my_inst changes
This is necessary to correctly handle messages to self.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 211fc4e1 (ceph): librados: add calls to expose required write alignment
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision e0b05085 (ceph): ReplicatedPG: reject unaligned writes on ec pools
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 541a7e27 (ceph): TestRados: send aligned appends on erasure pools
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 06ec9bd4 (ceph): ObjectStore: fix OP_COLL_ADD dump output
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 44f5d4de (ceph): ErasureCodeJerasure: fix alignement issues in encode/decode
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:14 PM Revision 093128a8 (ceph): Merge pull request #1139 from ceph/wip-agent
osd: basic cache tier agent
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
10:04 PM Revision 749bf40f (ceph): iozone: kill empty suite
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:18 PM Revision 66ffaa65 (ceph): kcephfs, krbd: do not thrash primary-affinity
Kenrel doesn't yet support it. See #7455
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:16 PM Revision 3d0ce693 (ceph): thrashosds: allow primary-affinity thrashing to be disabled
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision bd8fcd25 (ceph): osd: improve whiteout debug prints
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision 79976466 (ceph): ReplicatedBackend: print char ack_type as int
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision 63f5a799 (ceph): osd/ReplicatedPG: make agent skip blocked obcs
Among other things, this can interfere with an in-flight copy-from and
corrupt the pg stats.
Signed-off-by: Sage Wei...
Sage Weil
07:09 PM Revision 62532fb0 (ceph): Merge pull request #1254 from ceph/wip-barrier
libcephfs: disable barriers for now Sage Weil
07:07 PM Revision a4ca4a73 (ceph): Merge remote-tracking branch 'gh/wip-7212-sage-b'
We should carefully backport some or all of this.
Backport: emperor, dumpling
Reviewed-by: Joao Eduardo Luis <joao.l...
Sage Weil
06:27 PM Revision a71d829e (ceph): client: disable barrier support
The boost interval_set class is not available on centos6/rhel6. Until that
dependency is sorted out, fix the build.
...
Sage Weil
06:23 PM Revision 747002c6 (ceph): client: fix barrier interval
(start, end) not (start, length)
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:16 PM Revision d7457f73 (ceph): client/barrier: drop unused active_commit_interval
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:15 PM Revision ce643e00 (ceph): client: don't populate Client::barriers from read accesses
If the entry doesn't exist, no need to create it.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:28 PM Feature #7459 (Closed): ceph-rest-api: sysvinit and upstart scripts
enumerate daemon by directory in /var/lib/ceph/rest, using the same structure as the osd, mon, and other daemons.
...
Sage Weil
03:44 PM Bug #7458: osd: stray pg ref on shutdown
Sage Weil
03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
... Sage Weil
03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
http://pulpito.ceph.com/teuthology-2014-02-14_23:00:16-rados-master-testing-basic-plana/84322
http://pulpito.ceph.co...
Sage Weil
02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
Sage Weil
02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
Sage Weil
02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
Sage Weil
02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
Sage Weil
02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
Sage Weil
01:39 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
Simplest thing seems to be to unconditionally send temp object ops to the backfill targets. Then the final completio... Sage Weil
01:37 PM CephFS Bug #7422 (In Progress): client/barrier.h uses boost's interval set library, which is not availab...
The barrier code has been disabled to fix the build. Matt said he will follow up. http://marc.info/?l=ceph-devel&m=... Sage Weil
01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
Sage Weil
01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
Sage Weil
01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
reopened #7385 Sage Weil
01:33 PM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
This now leaks memory.. presumably stray Object's the cache that never get cleaned up.
Let's just increase the obj...
Sage Weil
01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
Sage Weil
01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
when this is complete, be sure to fix ceph-qa-suite.git Sage Weil
11:08 AM Bug #7212 (Pending Backport): monitor fails to start
Sage Weil
10:34 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
The problem is in rgw_user.h:void set_subuser(..) sets 'gen_access = true;'. I can't understand why it's doing that, ... Robin Johnson
08:44 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
Pavel Veretennikov wrote:
> * Strange that it worked without permission. Where had it stored the data?
It was onl...
Sage Weil
07:32 AM CephFS Bug #7424: Cannot read from zero-length file
* Strange that it worked without permission. Where had it stored the data? Pavel Veretennikov
07:31 AM CephFS Bug #7424: Cannot read from zero-length file
Yes, the problem resolved after I gave client access to default data pool
rwx pool=data
Strange that it work...
Pavel Veretennikov
06:52 AM CephFS Bug #7424: Cannot read from zero-length file
does client have permission permission to access the data pool? try using admin's keyring to mount the fs. Zheng Yan
01:19 AM CephFS Bug #7424: Cannot read from zero-length file
Ubuntu doesn't use SELinux as I know. /selinux lib is empty, only one related selinux package is present - libselinux... Pavel Veretennikov
06:25 AM Revision a1dbc9ce (ceph): qa/workunits/suites/pjd: use test suite with acl tweak
Test 45 in xacl/00.t fails on ext4 and cephfs. Just disable it.
Everything else passes.
Signed-off-by: Sage Weil <s...
Sage Weil
05:53 AM Revision c1f42770 (ceph): radosgw-admin: fix object policy read op
Fixes: #7083
This was broken when we fixed #6940. We use the same function to both
read the bucket policy and the obj...
Yehuda Sadeh
05:43 AM devops Feature #7454 (Resolved): ceph-disk: support osd removal / ceph-disk remove
There should be a *ceph-disk remove* to cleanup an OSD and the associated device / directory. This is not something a... Loïc Dachary
05:35 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
If you supply rgw_keystone_admin_user and rgw_keystone_admin_password ... instead of supplying "rgw_keystone_admin_to... Mouad Ben
05:23 AM Revision 623748e5 (ceph): mds: bump the protocol version
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
04:53 AM Revision 2a19a1be (ceph): osd/ReplicatedPG: allow is_degraded_object() to be called outside of ba...
The agent does this.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:37 AM Revision e5457dfb (ceph): mds: open sessions for rejoin imported caps
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 6e013cd6 (ceph): mds: properly set COMPLETE flag when merging dirfrags
don't keep the COMPLETE flag when merging dirfrags during journal
replay, because it's inconvenience to check if the ...
Yan, Zheng
01:37 AM Revision 0eb311d3 (ceph): mds: fix open undef dirfrags
Undef inode may contain a undef dirfrag (*). When undef inode is
opened, we should force fragment the undef dirfrag (...
Yan, Zheng
01:37 AM Revision 305d16f3 (ceph): mds: handle frag mismatch for cache rejoin weak
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 80799395 (ceph): mds: handle frag mismatch for cache expire
When sending MDSFragmentNotify to peers, also replicate the new
dirfrags. This guarantees peers get new replica nonce...
Yan, Zheng
01:37 AM Revision 9a47913d (ceph): mds: improve freeze tree deadlock detection
Current code uses the start time of freezing tree to detect deadlock.
It is better to check how long the auth pin cou...
Yan, Zheng
01:37 AM Revision 9df6861b (ceph): mds: freeze dir deadlock detection
freezing dir and freezing tree have the same deadlock cases.
This patch adds freeze dir deadlock detection, which imi...
Yan, Zheng
01:37 AM Revision 3dc51dea (ceph): mds: minor cleanup for EFragment and MMDSFragmentNotify
pass dirfrag_t to their constructors, instead of passing inode_t
and frag_t separately.
Signed-off-by: Yan, Zheng <z...
Yan, Zheng
01:37 AM Revision 98105b24 (ceph): mds: preserve dir_auth when spliting/merging dirfrags
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision ee7ac6fc (ceph): mds: allow fragmenting subtree dirfrags
We can't wait until object becomes auth pinnable after freezing a
dirfrag/subtree, because it can cause deadlock. Cur...
Yan, Zheng
01:37 AM Revision f3666ede (ceph): mds: journal dirfragtree change
Introduce new flag DIRTYDFT to CDir and EMetaBlob::dirlump, the new
flag indicates the dirfrag is newly fragmented an...
Yan, Zheng
01:37 AM Revision 4d5ceba5 (ceph): mds: fix 'force dirfrags' during journal replay
For rename operation, null dentry is first replayed, it detaches
the inode from the FS hierarchy. Then primary dentry...
Yan, Zheng
01:37 AM Revision 5b1de69a (ceph): mds: force fragment subtree bounds when replaying ESubtreeMap
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 3b90c785 (ceph): mds: fixes for thrash fragment
This patch contains 3 changes:
- limit the number of in progress fragmenting processes.
- reduce the probability of s...
Yan, Zheng
01:37 AM Revision cc77ef2d (ceph): mds: fix scattered wrlock rejoin
If unstable scatter lock is encountered when handling weak cache
rejoin, don't remove the recovering MDS from the sca...
Yan, Zheng
01:37 AM Revision 22535340 (ceph): mds: avoid race between cache expire and pushing replicas
MDentryLink and MMDSFragmentNotify push replica inode/dirfrags
to other MDS. They both are racy because, when the tar...
Yan, Zheng
01:37 AM Revision 74ef370b (ceph): mds: fix negative rstat assertion
when gathering rstat for directory inode that is fragmented to
several dirfrags, inode's rstat may temporarily become...
Yan, Zheng
01:37 AM Revision 21d209d0 (ceph): mds: wake up dentry waiters when handling cache rejoin ack
Cache rejoin ack message may fragment dirfrag, we should set the
'replay' parameter of adjust_dir_fragments() to fals...
Yan, Zheng
01:37 AM Revision 9e8dbf9e (ceph): mds: remove failed MDS from export bystanders list
make sure the importer does not wait for MExportDirNotifyAck from
the failed MDS
Signed-off-by: Yan, Zheng <zheng.z....
Yan, Zheng
01:37 AM Revision c54b3cea (ceph): mds: fix slave rename rollback
use rollback bufferlist to decide if the inode is being exported.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
01:37 AM Revision d0df8413 (ceph): mds: allow acquiring wrlock and remote wrlock at the same time
Rename may move file from one dirfrag to another dirfrag of the same
directory inode. If two dirfrags belong to diffe...
Yan, Zheng
01:37 AM Revision 3fb408ee (ceph): mds: introduce nonlocking auth pin
Add a parameter to Locker::acquire_locks() to enabled nonblocking
auth pin. If nonblocking mode is enabled and an obj...
Yan, Zheng
01:37 AM Revision 3154ee84 (ceph): mds: acquire locks required by exporting dir
Start internal MDS request to acquire locks required by exporting dir.
It's more reliable than using Locker::rdlock_t...
Yan, Zheng
01:37 AM Revision 5faa3134 (ceph): mds: acquire scatter locks when exporting dir
If auth MDS of the subtree root inode is neither the exporter MDS
nor the importer MDS and it gathers subtree root's ...
Yan, Zheng
01:37 AM Revision 2c909cda (ceph): mds: revert commit 15a5d37a
commit 15a5d37a (mds: fix race between scatter gather and dirfrag export)
is incomplete, it doesn't handles the race ...
Yan, Zheng
01:37 AM Revision 1ff77666 (ceph): mds: introduce fine-grained discover dirfrag wait queue
Current discover dirfrag code only allows discover one dirfrag at
a time. This can cause deadlock if there are direct...
Yan, Zheng
01:37 AM Revision b88034ee (ceph): mds: use discover_path to open remote inode
MDCache::discover_ino() doesn't work well for directories that are
fragmented to several dirfrags. Because MDCache::h...
Yan, Zheng
01:37 AM Revision ffe71516 (ceph): mds: handle frag mismatch for discover
When handle discover dirfrag message, choose an approximate frag if
the requested dirfrag doesn't exist. When handlin...
Yan, Zheng
01:37 AM Revision e0e25658 (ceph): mds: fix MDCache::get_force_dirfrag_bound_set()
don't force dir fragments according to the subtree bounds in resolve
message. The resolve message was not sent by the...
Yan, Zheng
01:37 AM Revision 1080fa45 (ceph): mds: fix MDCache::adjust_subtree_after_rename()
process subtree dirfrags first, then process nested dirfrags. because
the code that processes nested dirfrags treats ...
Yan, Zheng
01:37 AM Revision ee0ab2b7 (ceph): mds: fix CInode::get_dirfrags_under()
make the function work when opened dirfrags don't match the
dirfragtree.
Signed-off-by: Yan, Zheng <zheng.z.yan@inte...
Yan, Zheng

02/16/2014

10:43 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
Zheng Yan
09:57 PM CephFS Bug #7372: kcephfs: pjd tests fail
well, as far as i can tell, the pjd tests also fail on ext4 in the same way they do on ceph:... Sage Weil
09:46 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
we missed the backport of commit:b1976dd00f5b29c01791272f63a18250319f2edb Sage Weil
09:09 PM rgw Bug #7452 (Resolved): radosgw-admin nightly fails on dumpling
it seems to have been failing for a while, too:
http://pulpito.ceph.com/compare/?branch=dumpling&suite=rgw&count=1...
Sage Weil
08:56 PM Bug #7451 (Resolved): updatedb will index /var/lib/ceph
See http://git.openvz.org/?p=vzctl;a=commitdiff;h=47334979b9b5340f84d84639b2d77a8a1f0bb7cf for one example of a packa... Sage Weil
08:22 PM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
And this bug exists at least as far back as 0.72. I need a fix/workaround asap, to migrate users+subusers between two... Robin Johnson
08:20 PM rgw Bug #7450 (Resolved): "radosgw-admin key create" ignores specified access key when subuser specified
If I create to create an explicit accesskey/secret key combo, and specify a subuser, then the access key is not used.... Robin Johnson
04:26 PM Revision 75675bc8 (ceph): Merge pull request #1251 from ceph/wip-7371
ReplicatedPG: return no data if read size is trimmed to zero
Backport: emperor, dumpling
Reviewed-by: Sage Weil <sag...
Sage Weil
02:36 PM Revision 1dae27c5 (ceph): ReplicatedPG: return no data if read size is trimmed to zero
OSD should return no data if the read size is trimmed to zero by the
truncate_seq/truncate_size check. We can't rely ...
Yan, Zheng
08:27 AM Bug #7371 (Pending Backport): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ...
Sage Weil
06:33 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
Zheng Yan
01:39 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
I applied following patch... Zheng Yan
06:36 AM Revision dcb6d02c (ceph): Merge pull request #1223 from ceph/wip-7395
Improve OSD subscription handling
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:21 AM Revision 8547f43e (ceph): Merge pull request #1234 from dachary/wip-format
mon: remove format argument from osd crush dump
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:20 AM Revision 40450081 (ceph): Merge pull request #1243 from dachary/wip-ceph-disk-dumpling
ceph-disk: unit tests (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision 905df2e7 (ceph): osd/ReplicatedPG: block requests to cache PGs when they are full
If we are full and get a write request to a new object, put the op on a
wait list. Wake up when the agent frees up s...
Sage Weil
06:09 AM Revision a8129829 (ceph): osd/ReplicatedPG: simplify agent_choose_mode
Use a temp variable.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision 0dd1e071 (ceph): osd: schedule agent from a priority queue
We need to focus agent attention on those PGs that most need it. For
starters, full PGs need immediate attention so ...
Sage Weil
06:09 AM Revision 774125c7 (ceph): osd: set client incarnation for Objecter instance
Each ceph-osd process's Objecter instance has a sequence
of tid's that start at 1. To ensure these are unique
across...
Sage Weil
06:09 AM Revision c9daf8e5 (ceph): osd/ReplicatedPG: add slop to agent mode selection
We want to avoid a situation where the agent clicks on and off when the
system hovers around a utilization threshold....
Sage Weil
06:09 AM Revision e07f987d (ceph): osd/ReplicatedPG: fix evict mode selection for large target
If the target is > 1.0 for some reason (bad configuration, or high slop
value), and we are not yet full, we should be...
Sage Weil
06:09 AM Revision c2d16d72 (ceph): osd/ReplicatedPG: do not flush or evict hitsets
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision 230aad7b (ceph): osd: clear agent state when PG becomes a replica
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision 90457b17 (ceph): ceph_test_rados_api_tier: fix osd pool set json syntax
String, not int.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision dd3814f3 (ceph): osd/ReplicatedPG: do not flush|evict degraded objects
The repop won't work right; we still repair the object before making
any update.
Signed-off-by: Sage Weil <sage@inkt...
Sage Weil
06:09 AM Revision f617eba0 (ceph): osd/ReplicatedPG: do not choke on op-less flush OpContexts (from flush)
The agent initiates flush ops that don't have an OpRequest associated
with them. Make reply_ctx skip the actual repl...
Sage Weil
06:09 AM Revision 6581ce9c (ceph): osd/ReplicatedPG: ignore starvation potential when taking write lock du...
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision 11e4695a (ceph): osd: add OMAP flag to object_info_t
Set a flag if we ever set or update OMAP content on an object. This gives
us an easy indicator for the cache agent (...
Sage Weil
06:09 AM Revision 8c7bc2e8 (ceph): osd/ReplicatedPG: do not activate agent unless base pool exists
Paranoia.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision 7f854211 (ceph): osd/ReplicatedPG: do not flush omap objects to an EC base pool
The EC pool does not support omap content. If the caching/tiering agent
encounters such an object, just skip it. Us...
Sage Weil
06:09 AM Revision b92c79d2 (ceph): osd/ReplicatedPG: use reply_ctx in a few cases
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision 85e06f9d (ceph): osd/ReplicatedPG: redirect reads instead of promoting when full
If the cache pool is full, we are processing a read op, and we would
otherwise promote, redirect instead. This lets ...
Sage Weil
06:09 AM Revision 69502123 (ceph): osd/ReplicatedPG: factor clone check out of evict op code
Move the check for clones into a helper so that we will be able to use in
other places where we need to evict.
Signe...
Sage Weil
06:09 AM Revision 34fcf42c (ceph): osd/HitSet: add HitSetRef
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision 9ac03ef5 (ceph): osd/ReplicatedPG: fix finish_flush
Make sure we reallocate a pgbackend transaction at the time when we are
initiating new work.
Signed-off-by: Sage Wei...
Sage Weil
06:09 AM Revision a54f8198 (ceph): osd: agent worker thread
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision da9ed08e (ceph): osd/ReplicatedPG: basic flush and evict agent functionality
This is very basic flush and evict functionality for the tiering agent.
The flush policy is very simple: if we are a...
Sage Weil
06:09 AM Revision 18bc151b (ceph): osd/ReplicatedPG: decay tier agent histograms over time
Make decisions based on recent observations of object age distributions,
not all time history.
Signed-off-by: Sage W...
Sage Weil
06:09 AM Revision 199bdb1b (ceph): mon: test dirty stats in ceph df detail
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
06:09 AM Revision a5dabb58 (ceph): histogram: fix histogram::get_position_micro overflow
Convert the return values to uint64_t
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
06:09 AM Revision dcf20b9b (ceph): osd: add 'notieragent' flag to OSDMap
This will pause tiering agent work.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision cb4aa3a7 (ceph): osd: observe 'notieragent' osdmap flag
Pause/unpause the agent thread accordingly.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision 7bb0aa5a (ceph): osd: only enable tier agent when osd is in active state
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision f6930452 (ceph): osd: add pg_pool_t::get_random_pg_position()
Return a hash position somewhere inside a given pg.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:09 AM Revision 3bc31272 (ceph): osd/ReplicatedPG: initial agent to random hash position inside pg
When the agent starts, start at a random offset to ensure we get a more
uniform distribution of attention to all obje...
Sage Weil
06:09 AM Revision bc945248 (ceph): osd: rename test/test_osd_types.cc -> test/osd/types.cc
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision a57052cb (ceph): mon: include dirty stats in 'ceph df detail'
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 AM Revision fc28a99f (ceph): osd/ReplicatedPG: add on_finish to OpContext
Add a callback hook for whenever an OpContext completes or cancels. We
are pretty sloppy here about the return value...
Sage Weil
06:08 AM Revision 0988c843 (ceph): osd/osd_types: add cache policy fields to pg_pool_t
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:08 AM Revision 95f25ce0 (ceph): mon/OSDMonitor: allow new pool policy fields to be set
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:08 AM Revision e65c280b (ceph): osd: add pg_pool_t::get_pg_num_divisor
A PG is not always an equally sized fraction of the total pool size due to
the use of ceph_stable_mod. Add a helper ...
Sage Weil
06:07 AM Revision 8b68ad03 (ceph): histogram: calculate bin position of a value in the histrogram
Generate a lower and upper bound.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:07 AM Revision 85a82722 (ceph): histogram: rename set -> set_bin
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:07 AM Revision fb4152ae (ceph): histogram: move to common, add unit tests
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:07 AM Revision 297d54eb (ceph): histogram: add decay
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:38 AM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
Triggered while running the ceph-deploy suite on next, on debian (http://pulpito.ceph.com/sage-2014-02-15_17:05:48-ce... Joao Eduardo Luis
04:01 AM Revision 63ad9aab (ceph): thrashosds: randomly adjust primary_affinity
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:01 AM Revision dc95aef2 (ceph): ceph.conf: mon osd allow primary affinity = true
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:36 AM Revision 3e7ea33c (ceph): add autotools-generated files to .gitignore
When running "make check", Automake generates test-suite.log, along with
various *.log and *.trs files in the tree. A...
Ken Dreyer
12:59 AM Revision af848d4a (ceph): Merge pull request #1176 from ceph/wip-primary-affinity
osd: primary affinity
Added primary-affinity thrashing to thrashosd.py.
Reviewed-by: Loic Dachary <loic@dachary.org>
Sage Weil
12:49 AM Revision 6d4c1e2b (ceph): Merge pull request #1246 from dachary/wip-7188
common: ping existing admin socket before unlink Sage Weil
12:48 AM Revision f0f1cf4f (ceph): Merge pull request #1249 from dachary/wip-qa-erasure-test
qa: do not create erasure pools yet Sage Weil

02/15/2014

11:53 PM Revision d921d9b3 (ceph): qa: do not create erasure pools yet
comment out erasure pool related tests when an OSD is involved because
it does not work yet. See http://tracker.ceph....
Loïc Dachary
11:05 PM Revision 45600789 (ceph): common: ping existing admin socket before unlink
When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a...
Loïc Dachary
10:36 PM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
Sage Weil
10:19 PM Bug #7188 (Pending Backport): Admin socket files are lost on log rotation calling initctl reload ...
merged into next. want to wait a bit before backporting. Sage Weil
03:13 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
"dumpling backport":https://github.com/ceph/ceph/pull/1248 Loïc Dachary
03:11 AM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
"emperor backport":https://github.com/ceph/ceph/pull/1247 Loïc Dachary
02:55 AM Bug #7188 (Fix Under Review): Admin socket files are lost on log rotation calling initctl reload ...
"work in progress":https://github.com/ceph/ceph/pull/1246 Loïc Dachary
06:50 PM Revision f825624f (ceph): osd/OSDMap: add primary_affinity feature bit
Indicate that we support it. Indicate when an OSDMap requires it.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:50 PM Revision c360c604 (ceph): ceph_psim: some futzing to test primary_affinity
- map to acting
- count first position, primary
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:50 PM Revision ba3eef86 (ceph): mon/OSDMonitor: add 'mon osd allow primary affinity' bool option
By default, disallow adjustment of primary affinity unless the user has
opted in by adjusting their monitor config. ...
Sage Weil
06:50 PM Revision 87be7c15 (ceph): osd/OSDMap: remove bad assert
You can have an erasure poool with all CRUSH_ITEM_NONE and primary == -1.
acting is not empty.
Signed-off-by: Sage W...
Sage Weil
06:50 PM Revision c673f408 (ceph): osd/OSDMap: include primary affinity in OSDMap::print
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:50 PM Revision 8ecec02f (ceph): osd/OSDMap: apply primary_affinity to mapping
The behavior is a bit different for replicated and indep/erasure mode.
In the first case, we are rearranging the resu...
Sage Weil
06:48 PM Bug #7447 (Resolved): osd: copy_from temp objects interact awkwardly with backfill
We decide whether to send the operation based on the object named in the repop, but the temp objects do not get backf... Samuel Just
06:37 PM Revision a91d0cbc (ceph): Merge pull request #1245 from ceph/wip-brag
ceph-brag
Sebastien Han confirms that this is under the default (LGPL2) license, thus:
Signed-off-by: Sage Weil <sa...
Sage Weil
06:25 PM Revision 1d6aceb4 (ceph): upgrade: reorg
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:15 PM Revision 871a5f04 (ceph): ceph.spec: add ceph-brag
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:15 PM Revision 57d70183 (ceph): ceph-brag: add Makefile
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:15 PM Revision 4ea0a25a (ceph): debian: add ceph-brag
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:13 PM Revision fec55a21 (ceph): ceph-disk: unit tests
src/test/ceph-disk.sh replaces src/test/cli/ceph-disk/data-dir.t
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
06:08 PM Revision 7e9f03b1 (ceph): Merge pull request #1181 from dachary/wip-7277
DNM: mon: s/ENOSYS/ENOTSUP/
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Reviewed-by: Sage Weil ...
Sage Weil
06:07 PM CephFS Bug #6791 (Won't Fix): mds assert after startup - CDir::commit error (want > commited version)
Zheng Yan
05:17 PM Revision e485c95f (ceph): Merge branch 'master' of https://github.com/enovance/ceph-brag into wip...
Sage Weil
05:00 PM Feature #7058 (Resolved): osd primary affinity
Sage Weil
04:59 PM Revision cf4f7027 (ceph): mon/Elector: bootstrap on timeout
Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This...
Sage Weil
04:53 PM Revision 0679b11b (ceph): ceph-disk: cannot run unit tests
Because ceph-disk relies on hardcoded paths. The corresponding test will
be added back when ceph-disk can run from so...
Loïc Dachary
04:27 PM Bug #7445 (Need More Info): missing feature bit ( next )
Is it worth investigating the current failure of next on make check ? It will probably go away when master is merged ... Loïc Dachary
04:23 PM Bug #7445: missing feature bit ( next )
next is missing "osd crush rule create-erasure":https://github.com/ceph/ceph/commits/cb39b1367676215fc244664d83ffb3e2... Loïc Dachary
04:03 PM Bug #7445 (Rejected): missing feature bit ( next )
On ea6dc997668df98c0a553d677cf22850b476e412 running *test/mon/osd-pool-create.sh* blocks... Loïc Dachary
04:01 PM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
"revert due to accidental merge of a DNM":https://github.com/ceph/ceph/pull/1249 Loïc Dachary
07:52 AM Revision 9dae9993 (ceph): Revert "librbd: remove limit on number of objects in the cache"
This reverts commit 367cf1bbf86233eb20ff2304e7d6caab77b84fcc.
Removing the limit on objects means we leak memory, si...
Sage Weil
04:27 AM Revision 4595c44b (ceph): mon: tell MonmapMonitor first about winning an election
It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i...
Sage Weil
04:27 AM Revision 7bd2104a (ceph): mon: only learn peer addresses when monmap == 0
It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ...
Sage Weil
01:28 AM Revision 64ff4ab0 (ceph): Fixed task/args.py docstrings.
Warren Usui
01:08 AM Revision c631190a (ceph): Add docstrings. Fix formatting issues for rgw.py
Fix s3tests calls for rgw-logsocket.py.
Fixes: 6540
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
12:54 AM Revision 6db3ae85 (ceph): OSD: create a helper for handling OSDMap subscriptions, and clean them up
We've had some trouble with not clearing out subscription requests and
overloading the monitors (though only because ...
Greg Farnum
12:54 AM Revision 3c76b81f (ceph): OSD: use the osdmap_subscribe helper
Signed-off-by: Greg Farnum <greg@inktank.com> Greg Farnum
12:53 AM Revision 5b9c187c (ceph): monc: new fsub_want_increment( function to make handling subscriptions ...
Provide a subscription-modifying function which will not decrement
the start version.
Signed-off-by: Greg Farnum <gr...
Greg Farnum

02/14/2014

11:48 PM Revision 6df622b3 (ceph): Fix docstrings and minor formatting in task/ssh_keys.py
Fixes: 6539
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
11:25 PM Revision 2795339d (ceph): os/FileStore: fix ENOENT error code for getattrs()
In commit dc0dfb9e01d593afdd430ca776cf4da2c2240a20 the omap xattrs code
moved up a block and r was no longer local to...
Sage Weil
11:13 PM Revision 0af08071 (ceph): Fix docstrings for task/blktrace.py, peering_speed_test.py, proc_thrash...
recovery_bench.py.
Fixes: 6535
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
10:23 PM Revision c158de23 (ceph): test/filestore/run_seed_to.sh: avoid obsolete --filestore-xattr-use-omap
This option no longer exists.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1d4f501a015727a...
Sage Weil
10:20 PM Revision 7d398c2a (ceph): doc/release-notes: v0.67.6
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:57 PM Revision ef97f0cd (ceph): Fix docstrings in radosgw-admin-rest.py
Fixes: 6541
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
08:59 PM Revision 4015d614 (ceph): Merge pull request #188 from ceph/wip-calamari-onefile
Add Calamari test tasks, test script Zack Cerza
08:59 PM Revision 8e2cdbf5 (ceph): Merge pull request #188 from ceph/wip-calamari-onefile
Add Calamari test tasks, test script Zack Cerza
08:57 PM Revision e0ed09cf (ceph): Add docstrings to the orchestra code. Also fix minor formatting issues
(mostly column start locations).
Fixes: 7003
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
07:28 PM Revision a6eee01f (ceph): Review: switch to selecting remotes by roles in the 'normal' way
This buys us, also, the ability to select remotes by rule, i.e.
"any osd or mon gets calamari-agent installed"
Signe...
Dan Mick
07:28 PM Revision 006428c5 (ceph): Review: refactor packaging routines to common file
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
05:50 PM Revision 67e670b2 (ceph): Merge pull request #192 from ceph/wip-6537-wusui
Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py. Zack Cerza
05:50 PM Revision 132f3e8a (ceph): Merge pull request #192 from ceph/wip-6537-wusui
Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py. Zack Cerza
05:45 PM Revision e8e7cc22 (ceph): Merge pull request #194 from ceph/wip-6534-wusui
Add docstrings to internal.py Zack Cerza
05:45 PM Revision 24363351 (ceph): Merge pull request #194 from ceph/wip-6534-wusui
Add docstrings to internal.py Zack Cerza
05:45 PM Revision a3fbb6c5 (ceph): Merge pull request #193 from ceph/wip-6538-wusui
Add doc strings to Swift tests Zack Cerza
05:45 PM Revision 4eb14729 (ceph): Merge pull request #193 from ceph/wip-6538-wusui
Add doc strings to Swift tests Zack Cerza
05:44 PM Revision af61317a (ceph): Merge pull request #191 from ceph/wip-7002-wusui
Added some docstrings. Zack Cerza
05:43 PM Revision 1da78c06 (ceph): Merge pull request #187 from ceph/wip-better-debug
Debug output improvements Zack Cerza
05:43 PM Revision ad9aaf8f (ceph): Merge pull request #187 from ceph/wip-better-debug
Debug output improvements Zack Cerza
05:27 PM Revision f47062d8 (ceph): Merge pull request #1237 from dachary/wip-hashpspool
mon: ceph hashpspool false clears the flag
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Reviewed...
Sage Weil
03:45 PM Bug #7188 (In Progress): Admin socket files are lost on log rotation calling initctl reload (ubun...
Steps to reproduce:... Loïc Dachary
03:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
From a fresh install of "ubuntu 13.04":http://mirrors.ircam.fr/pub/ubuntu/releases/raring/ubuntu-13.04-server-amd64.i... Loïc Dachary
02:37 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
ceph-osd "installs a sighup handler":https://github.com/ceph/ceph/blob/emperor/src/ceph_osd.cc#L477 which "reopens lo... Loïc Dachary
12:25 PM Bug #7188: Admin socket files are lost on log rotation calling initctl reload (ubuntu 13.04 only)
Not sure if I can fix it but I'll give it a shot. Loïc Dachary
02:12 PM Feature #7442 (Resolved): mon: health warn on pg "full"
Sage Weil
02:09 PM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
Sage Weil
02:04 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
01:59 PM RADOS Feature #7440 (New): erasure-code: adapt scrub/repair teuthology tests for EC and add to nightly
Samuel Just
01:58 PM Feature #7439 (Resolved): EC: adapt unfound teuthology tests and add to nightly for EC
Samuel Just
01:58 PM Feature #7438 (Resolved): EC: adapt watch/notify stress test for EC and add to nightly
Samuel Just
01:57 PM Feature #7437 (Resolved): EC: add adapt unittest teuthology task and add to nightly
Samuel Just
01:42 PM devops Feature #7293: packaging: enable qemu to find librbd on rhev or rhel-osp
Neil Levine
01:41 PM devops Feature #7436 (Rejected): Build and test RHEL on same subversions.
Ian Colle
01:39 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
Ian Colle
01:38 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
Removed requirement for SLES/OpenSuse. Therefore, completed. Ian Colle
01:33 PM devops Feature #7046 (Resolved): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
Ian Colle
01:31 PM rgw Documentation #7434: rgw: doc user/group quota
John: can you please provide feedback to Yehuda on where he should put the new docs about the user quotas. Neil Levine
01:06 PM rgw Documentation #7434 (Resolved): rgw: doc user/group quota
Sage Weil
01:05 PM rgw Feature #6339: rgw: compact manifest data
Ian Colle
01:05 PM rgw Feature #6338: rgw: better manifest scaling
Ian Colle
12:33 PM Revision d8964b2f (ceph): Merge pull request #1235 from ceph/wip-osdmaptool-pool-fix
wip-osdmaptool-pool-fix
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:53 AM rgw Feature #6513 (In Progress): rgw: dr: Service scripts for meta/data sync agents
Josh Durgin
11:23 AM devops Bug #7427: sha1 does not exist on gitbuilder, install fails
This happened because the build failed on the rpm gitbuilder. It actually looks like many of the last few master buil... Sandon Van Ness
09:13 AM devops Bug #7427 (Resolved): sha1 does not exist on gitbuilder, install fails
... Alfredo Deza
11:13 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
After investigating what was returning this message:... Alfredo Deza
11:05 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
Merged into ceph-deploy master branch 348bf8c Alfredo Deza
07:53 AM devops Bug #7390 (Fix Under Review): ceph-deploy should remove ceph-release and call yum clean all
Pull request opened https://github.com/ceph/ceph-deploy/pull/163 Alfredo Deza
10:24 AM Revision 0ed6a81b (ceph): osdmaptool: add tests for --pool option
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com> Ilya Dryomov
10:24 AM Revision f98435a4 (ceph): osdmaptool: add --pool option for --test-map-pgs mode to usage()
--test-map-pgs mode allows to map all pgs from either all pools or just
one pool. Mention it in usage output.
Signe...
Ilya Dryomov
10:24 AM Revision eedbf501 (ceph): osdmaptool: fix --pool option for --test-map-object mode
Commit 7f1b12f2ef97 ("osdmaptool: add --test-map-pgs mode") broke
--pool for --test-map-object mode. Fix it, and imp...
Ilya Dryomov
09:26 AM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
When deploying monitors on fedora 19 VMs, the monitors fail to mkfs due to some segfault. This happens regardless of ... Joao Eduardo Luis
09:04 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:23:01-rgw-dumpling-master-basic-plana/81039/
<...
Yuri Weinstein
08:20 AM Bug #7406: Seg fault in find_object_context()in recent master rados run
I don't think snaps should ever be empty.. if it is, there is a bug somewhere that is causing it. On the one hand no... Sage Weil
08:10 AM rados-java Bug #7425 (Rejected): Error in run_seed_to_range.sh for rados-dumpling-master-basic-plana
Logs are in http://qa-proxy.ceph.com/teuthology/wusui-2014-02-13_12:24:10-rados-dumpling-master-basic-plana/81235/
...
Yuri Weinstein
06:37 AM Revision 68106102 (ceph): Add docstrings to internal.py
Fixes: 6534
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
06:25 AM CephFS Bug #7424: Cannot read from zero-length file
do you have selinux enabled Zheng Yan
02:16 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
Ubuntu 12.04 LTS 3.8.0-35-generic x64
Ceph 0.72.2-1precise from http://ceph.com/debian-emperor/
cluster b8...
Pavel Veretennikov
06:01 AM Revision e44122f0 (ceph): test: fix signed/unsigned warnings in TestCrushWrapper.cc
Irritatingly, using 0 binds to int and generates warnings
if the thing we're checking is unsigned, so we have to be
e...
Greg Farnum
05:11 AM Revision 5c36a5ce (ceph): Add doc strings to Swift tests
Fixes: 6538
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
05:11 AM Revision f4284b52 (ceph): Add doc strings to Swift tests
Fixes: 6538
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
04:36 AM Revision 567961b7 (ceph): Readjust the indentation of mon_clock_skew_check.py and mon_thrash.py.
Added docstrings.
Fixes: 6537
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
04:00 AM Revision 12b79044 (ceph): Review: Rename calamari_testdir/ to calamari/
Dan Mick
02:04 AM Bug #7423: erasure code: ./rados get retrieves a larger object
On "ecbackend-8":https://github.com/ceph/ceph/tree/wip-ecbackend-8 it fails in the same way ( the crash does not happ... Loïc Dachary
01:29 AM Bug #7423: erasure code: ./rados get retrieves a larger object
Loic Dachary wrote:
> While playing with "ECBackend pull request":https://github.com/ceph/ceph/pull/1228
> [...]
>...
Loïc Dachary
01:28 AM Bug #7423 (Resolved): erasure code: ./rados get retrieves a larger object
"work in progress":https://github.com/ceph/ceph/pull/1327
Steps to reproduce:...
Loïc Dachary
01:40 AM Revision bee587c3 (ceph): Added some docstrings.
Fixes: 7002
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
12:45 AM CephFS Bug #7422 (Resolved): client/barrier.h uses boost's interval set library, which is not available ...
http://gitbuilder.sepia.ceph.com/gitbuilder-centos6-amd64/log.cgi?log=9cbbc883e225b08b3e31cd2cf6e766688795886b
Thi...
Josh Durgin

02/13/2014

10:27 PM Bug #7420: posix_fallocate failed under CentOS 6.5 when DIO enabled
posix_allocate in FileJournal::_open_file will call pread to pre-allocate space which will return 22 because unalgine... Haomai Wang
10:19 PM Bug #7420 (Won't Fix): posix_fallocate failed under CentOS 6.5 when DIO enabled
under CentOS 6.5, when enable DIO and initialize OSD directory will cause failed:
2014-02-14 05:46:15.591387 7ffff...
Haomai Wang
10:23 PM Revision 54e9e3e7 (ceph): fixed yam typos
Yuri Weinstein
09:20 PM Revision 1a8c4347 (ceph): monc: let users specify a callback when they reopen their monitor session
Then the callback is triggered when a new session is established, and the
daemon can do whatever it likes. There are ...
Greg Farnum
09:20 PM Revision 60da8abe (ceph): monc: set "hunting" to true when we reopen the mon session
If we don't have a connecton to a monitor, we want to retry to another
monitor regardless of whether it's the first t...
Greg Farnum
09:20 PM Revision 794c86fd (ceph): monc: backoff the timeout period when reconnecting
If the monitors are systematically slowing down, we don't want to spam
them with reconnect attempts every three secon...
Greg Farnum
09:20 PM Revision 64cedf6f (ceph): OSD: disable the PGStatsAck timeout when we are reconnecting to a monitor
Previously, the timeout counter started as soon as we issued the reopen,
but if the reconnect process itself took a w...
Greg Farnum
08:20 PM Revision c71f8a60 (ceph): release build 67.6
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
07:41 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
Recent change is causing 2GB VM KVM processes to consume up to 5GB of memory during heavy write workload. Sage think... Mark Nelson
06:12 PM Revision de468594 (ceph): added distros
Yuri Weinstein
06:07 PM Revision 589e2fa4 (ceph): mon: ceph hashpspool false clears the flag
instead of toggling it.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
04:43 PM devops Bug #7417 (Resolved): libleveldb1 missing in debian-testing
The libleveldb1 package is listed as a dependency for precise/testing (http://ceph.com/debian-testing/dists/precise/m... Noah Watkins
03:38 PM Bug #7406 (Fix Under Review): Seg fault in find_object_context()in recent master rados run
Pushed wip-7406 David Zafman
03:27 PM Revision 7834535f (ceph): mon: remove format argument from osd crush dump
The --format argument of the ceph cli is used to send the desired format
argument. The format argument is always part...
Loïc Dachary
03:00 PM Revision 0ae5e53e (ceph): Merge pull request #1231 from dachary/wip-mon-create-simple
mon: do not goto reply if a ruleset exists in pending
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:59 PM Revision 39e313fc (ceph): Merge pull request #1216 from ceph/wip-null-xattr
mds: remove xattr when null value is given to setxattr()
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:55 PM Revision 1c42a6e3 (ceph): Merge pull request #1232 from ceph/dumpling-7334
backport ceph-disk improvements to dumpling
http://pulpito.ceph.com/ubuntu-2014-02-12_16:52:33-ceph-deploy-dumpling-...
Sage Weil
02:51 PM Revision 9cbbc883 (ceph): Merge branch 'wip-libcephfs-firefly-rb' of https://github.com/linuxbox2...
Reviewed-by: Sage Weil <sage@inktank.com>
This went through the fs suite and passed:
http://pulpito.ceph.com/sage-...
Sage Weil
02:50 PM Revision 020e543e (ceph): mon: do not goto reply if a ruleset exists in pending
If the crush ruleset is found in pending, do not goto reply because it
does not exist yet. Wait for the pending propo...
Loïc Dachary
02:06 PM Revision 192ed615 (ceph): Merge pull request #1202 from dachary/wip-mon-create-simple
mon: create simple should goto reply when it exists in pending
Reviewed-By: Christophe Courtaut <christophe.courtaut...
Loïc Dachary
01:54 PM Revision 0c9c1577 (ceph): mon: osd crush rule create-simple functional tests
Basic tests and a test that create the conditions where an OSDMap
is pending with a ruleset that is not yet in the OS...
Loïc Dachary
01:54 PM Revision c248e7cf (ceph): mon: osd crush rule functional tests
* A set of test for the simplest operations
* A test covering all cases of osd crush rule
Signed-off-by: Loic Dachar...
Loïc Dachary
01:00 PM Revision f8ec7ae2 (ceph): Merge pull request #1230 from ceph/wip-open-truncate
mds: properly replay dentry trace for open truncate.
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:28 AM devops Bug #7390 (In Progress): ceph-deploy should remove ceph-release and call yum clean all
Alfredo Deza
11:27 AM Revision cec18933 (ceph): mon: add missing format argument to crush rule dump
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
11:27 AM Revision fce4d684 (ceph): mon: add missing format argument to crush dump
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
11:27 AM Revision 4784a687 (ceph): mon: add ruleset name to crush rule dump
The crush rule name is made an optional first argument. If not provided, it
defaults to dumping all rules.
Signed-of...
Loïc Dachary
11:27 AM Revision 7ff27566 (ceph): mon: osd create pool test refactor
* Use test-helpers.sh instead of duplicating it
* Isolate each test in a separate function for clarity
Signed-off-by...
Loïc Dachary
11:14 AM Revision 462ad76a (ceph): crush: fix leaks in TestCrushWrapper.cc
To get a meaningfull valgrind output.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:14 AM Revision f77e8ea2 (ceph): crush: add CrushWrapper::dump_rules() unit test
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
11:14 AM Revision dcfeee66 (ceph): crush: add the dump_rule(int ruleset) method
And implement dump_rules() using dump_rule(). The indentiation and
variable names are intentionaly left as is to not ...
Loïc Dachary
11:14 AM Revision e5b6eb45 (ceph): crush: cosmetic changes to CrushWrapper::dump_rule()
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
11:14 AM Revision a7e9a7b6 (ceph): crush: display item name in CrushWrapper::dump_rule()
When an item name is available used it instead of displaying the number.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:14 AM Revision 4b687ba6 (ceph): mon: if crush rule create-simple exists return
And it is consistent with the above. Also use a slightly different
string to allow the caller to differentiate betwee...
Loïc Dachary
11:14 AM Revision fd13307f (ceph): mon: minor improvement to test-helpers.sh
* kill -9 daemons to better cope with stuck daemons
* reduce paxos propose interval to speedup tests
* look for erasu...
Loïc Dachary
10:38 AM rados-java Bug #7413 (Rejected): LibRadosTier.FlushTryFlushRaces failed on rados:basic-wip-agent-testing-bas...
Logs are in sage-2014-02-12_13:47:37-rados:basic-wip-agent-testing-basic-plana/79327... Yuri Weinstein
10:30 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
3e473d4237697872498094b41fed19b414f8d3c4 David Zafman
10:06 AM Bug #7212 (Fix Under Review): monitor fails to start
patch bb863b73c45ce5592844c2c72028ef1cfd9647f8 ; pull request: https://github.com/ceph/ceph/pull/1236 Joao Eduardo Luis
09:16 AM Revision ee46908b (ceph): Merge pull request #1222 from dachary/wip-pending-osdmap
mon: control pending OSDMap for testing
Reviewed-by: Joao Eduardo Luis <joao@inktank.com>
Reviewed-by: Greg Farnum <...
Loïc Dachary
09:14 AM Revision 6ad6b092 (ceph): mon: remove racy tests from osd-pool-create.sh
Use the admin socket to create the conditions by which a pool creation
is made to wait for the next paxos proposal be...
Loïc Dachary
08:52 AM Revision 8dea5884 (ceph): mon: add osdmonitor_prepare_command to the admin socket
It provides a developer path allowing functional tests to modify the
pending OSDMap without triggering a PaxosProposa...
Loïc Dachary
08:50 AM Revision 07c494bd (ceph): mon: add --mon-advanced-debug-mode
When this flag is true, the mon is expected to provide functionalities
that are for developer oriented debug purposes...
Loïc Dachary
08:45 AM Revision 53e92f62 (ceph): mon: split prepare_command in two
So that it is possible to call prepare_command without a session
established and a cmdmap that has already been parse...
Loïc Dachary
08:45 AM Revision 5ea156a0 (ceph): mon: Monitor::send_reply gracefully handles no connection
If req->get_connection() returns a null pointer, drop the reply instead
of crashing the monitor.
Signed-off-by: Loic...
Loïc Dachary
07:49 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
Merged into ceph dumpling branch with hash 1c42a6e Alfredo Deza
06:48 AM devops Bug #7334: ceph-disk: cannot run partprobe on used devices with EL6
Created branch dumpling-7334 and got all dumpling ceph-deploy suite tests to pass http://pulpito.ceph.com/ubuntu-2014... Alfredo Deza
04:20 AM Revision d0121197 (ceph): mds: remove xattr when null value is given to setxattr()
setxattr() should remove xattr if parameter 'value' is NULL. To
distinguish it from the zero-length value case, intro...
Yan, Zheng
02:40 AM Revision 6e6a3335 (ceph): mds: properly replay dentry trace for open truncate.
Open request created by ceph_atomic_open() wants dentry trace. But
the corresponding code is missing in Server::do_op...
Yan, Zheng
02:14 AM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
Sure, totally agree on the low priority. Florian Haas
02:02 AM Revision 9035227e (ceph): doc/release-notes: do not downgrade from v0.67.6
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:55 AM Revision 7533b3b7 (ceph): doc/release-notes: note about dumpling xattr backport
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:42 AM Revision cc1e8449 (ceph): PendingReleaseNotes: note about cephfs backtrace updates
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:37 AM Revision 94828507 (ceph): Merge pull request #1219 from ceph/wip-update-backtrace
mds: force update backtraces for previously created FS
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:52 AM Bug #7409 (Can't reproduce): "make check" doesn't work without --with-radosgw
It may looks like improper that we can't run "make check" by default configure which lack of "--with-radosgw".
tes...
Haomai Wang

02/12/2014

11:08 PM Revision 2a6ec2db (ceph): added parallel dumping-emperor-next upgrade tests
Yuri Weinstein
11:01 PM Revision ea6dc997 (ceph): Merge pull request #1225 from ceph/wip-moncap
osd/OSDCap: mon/MonCap: handle any whitespace (not just space)
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
10:45 PM Bug #7222 (Won't Fix): init-ceph failed when cluster created by "mkcephfs" and start osd firstly ...
Haomai Wang
10:42 PM Bug #7222: init-ceph failed when cluster created by "mkcephfs" and start osd firstly and
mkcephfs won't add osd id to osdmap. So if cluster created by mkcephfs, it need to add "osd crush update on start = 0... Haomai Wang
09:48 PM Revision 3e473d42 (ceph): common,os: Remove filestore_xattr_use_omap option
Now we operate just like when this was set to true
Fixes: #6143
Signed-off-by: David Zafman <david.zafman@inktank.c...
David Zafman
09:43 PM Revision c5e12f94 (ceph): add support for absence of PATH
Note that this commit is actually bisecting the changes from
Loic Dachary that touch ceph-disk only (ad515bf). As tha...
Alfredo Deza
09:38 PM Revision cee91429 (ceph): osd/OSDMap: add osd_primary_affinity fields, accessors, encoding
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:38 PM Revision 1cc8c258 (ceph): mon/OSDMonitor: add 'osd primary-affinity ...' command
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:38 PM Revision e1079382 (ceph): osd/OSDMap: fix _raw_to_up_osds for EC pools
When filtering down OSDs out of the result set (i.e., raw -> up), we can
shift positions for replicated pools but nee...
Sage Weil
09:38 PM Revision 74951cad (ceph): osd/OSDMap: pass pps value out from _pg_to_osds
The primary affinity code needs a seed to determine it's pseudo-random
behavior. Pass pps (optionally) out of _pg_to...
Sage Weil
09:37 PM Revision c531d75f (ceph): ceph-disk: make initial journal files 0 bytes
The ceph-osd will resize journal files up and properly fallocate() them
so that the blocks are preallocated and (hope...
Sage Weil
09:25 PM Revision f0655109 (ceph): Fix flake8 failures
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
09:18 PM Revision af4c142d (ceph): mon/OSDMonitor: fix legacy tunables warning
Warn on legacy tunables, not on non-optimal tunables. Optimal is a moving
target, but it is really the legacy defaul...
Sage Weil
09:17 PM Revision cff3547c (ceph): use partx for red hat or centos instead of partprobe
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 42900ff9da9f5adcac239a84ebf4d2e407c29699)
Alfredo Deza
09:17 PM Revision 836ead3e (ceph): alert the user about error messages from partx
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 9bcc42a3e6b08521694b5c0228b2c6ed7b3d312e)
Alfredo Deza
09:17 PM Revision 6ae96d3c (ceph): ceph-disk: display the command output on OSD creation failure
The string form of a CalledProcessError instance does not include the
output datamember. Add it to the Error exceptio...
Loïc Dachary
09:17 PM Revision a33ad6d1 (ceph): ceph-disk: use CalledProcessError.returncode
CalledProcessError has no errno data member
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commi...
Loïc Dachary
09:17 PM Revision 3aae5b76 (ceph): ceph-disk: fsid is a known configuration option
Use get_conf_with_default instead of get_conf because fsid is a known
ceph configuration option. It allows overriding...
Loïc Dachary
09:17 PM Revision 6ea59a3a (ceph): ceph-disk: implement --mark-init=none
It is meant to be used when preparing and activating a directory that is
not to be used with init. No file is created...
Loïc Dachary
09:17 PM Revision c473c65d (ceph): ceph-disk: run ceph-osd when --mark-init=none
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 0fcc081858fae4febbb6a613a93cfbbcedd5a320)
Loïc Dachary
09:17 PM Revision c4b66bbd (ceph): ceph-disk: create the data directory if it does not exist
Instead of failing if the OSD data directory does not exist, create
it. Only do so if the data directory is not enfor...
Loïc Dachary
09:17 PM Revision 79564874 (ceph): ceph-disk: add copyright notice
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 51ee3c04777aaf6b9609dde9bc318b5c66c70787)
Loïc Dachary
09:17 PM Revision c8b9798a (ceph): ceph-disk: implement --statedir as /var/lib/ceph
Replace hardcoded /var/lib/ceph with the STATEDIR global variable and
implement the --statedir option to override the...
Loïc Dachary
09:17 PM Revision 4a7c4e0a (ceph): ceph-disk: implement --sysconfdir as /etc/ceph
Replace hardcoded /etc/ceph with the SYSCONFDIR global variable and
implement the --sysconfdir option to override the...
Loïc Dachary
09:17 PM Revision 5ebd7c45 (ceph): ceph-disk: run the right executables from udev
When run by the udev rules, PATH is not defined. Thus,
ceph-disk-activate relies on its which() function to locate th...
Josh Durgin
09:17 PM Revision 0fe2ac47 (ceph): use the new get_command helper in check_call
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 897dfc113fe3b86f3dda53172933bfd4f8089869)
Alfredo Deza
09:17 PM Revision 2e8496a6 (ceph): ceph-disk: zap needs at least one device
If given no argument, ceph-disk zap should display the usage instead of
silently doing nothing. Silence can be confus...
Loïc Dachary
09:17 PM Revision 5df1eaa5 (ceph): ceph-disk: prepare --data-dir must not override files
ceph-disk does nothing when given a device that is already prepared. If
given a directory that already contains a suc...
Loïc Dachary
09:17 PM Revision 75bdb543 (ceph): ceph-disk: fix Error() messages formatting
Mainly using % instead of ,
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit b82ccfbfa786cd...
Loïc Dachary
09:17 PM Revision 27988cf9 (ceph): ceph-disk: remove noop try:
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit de0050596b5f56863c3486c1cd5e7ffea62e3d00)
Loïc Dachary
09:17 PM Revision 827edb93 (ceph): ceph-disk: fix activate() indent
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 324804a81c37ff89f2488e2ba106033c0e6e119e)
Loïc Dachary
09:17 PM Revision d60e952f (ceph): ceph-disk: do not hide main_activate() exceptions
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 55ca7bb2da73f1be1293710a635cfea42abd7682)
Loïc Dachary
09:17 PM Revision ccf18224 (ceph): ceph-disk: make exception handling terse in main_activate_journal
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 908348b8047e8577ecf9133f2683f91423694416)
Loïc Dachary
09:17 PM Revision 06bbea18 (ceph): ceph-disk: add --prepend-to-path to control execution
/usr/bin is hardcoded in front of some ceph programs which makes it
impossible to control where they are located via ...
Loïc Dachary
09:17 PM Revision deefb3a0 (ceph): ceph-disk: which() uses PATH first
Instead of relying on a hardcoded set of if paths. Although this has the
potential of changing the location of the bi...
Loïc Dachary
09:14 PM Revision 83b2cde2 (ceph): Merge pull request #1217 from ceph/wip-7346
rgw: multi object delete should be idempotent
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
09:12 PM Revision a0b2c746 (ceph): osd/OSDCap: handle any whitespace (not just space)
Backport: emperor, dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:10 PM Revision 824dd52b (ceph): mon/MonCap: handle any whitespace (not just space)
Backport: emperor, dumpling
Reported-by: Dmitry Borodaenko <dborodaenko@mirantis.com>
Signed-off-by: Sage Weil <sage@...
Sage Weil
09:06 PM Revision 8fc9f1b7 (ceph): use the absolute path for executables if found
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit a9334a1c8c6681305e76b361377864d0dd1e3d34)
Alfredo Deza
09:06 PM Revision a2de2f71 (ceph): remove trailing semicolon
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 43561f791607f5fd6f03d5421e1f30a29fb4194e)
Alfredo Deza
09:06 PM Revision 2cd22b5d (ceph): replace sgdisk subprocess calls with a helper
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit e19e38012bc4579054f63865e682c8c3a7829c7b)
Alfredo Deza
09:06 PM Revision e8cc27cc (ceph): Call --mbrtogpt on journal run of sgdisk should the drive require a GPT...
Signed-off-by: Jonathan Davies <jonathan.davies@canonical.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by:...
Jonathan Davies
09:05 PM Revision 3942a93f (ceph): ceph-disk: blacklist /dev/fd0
blkid -s TYPE /dev/fd0 has been verified to hang forever on a
H8DMR-82 supermicro motherboard running
3.8.0-33-gener...
Loïc Dachary
09:05 PM Revision ccc6b0c5 (ceph): Make fsid comparison case-insensitive
get_fsid and find_cluster_by_uuid are modified so ceph-disk activate and
ceph-disk activate-all will work if the fsid...
git-harry
06:46 PM rgw Bug #7374: s3_multipart_upload.pl fails
Also, use Amazon::S3 results in the same error message on a hello world perl script.
I got S3 installed via cpan (...
Anonymous
06:41 PM rgw Bug #7374: s3_multipart_upload.pl fails
Okay. I think that the Yaml file is okay. There appear to be make issues. The most noticable one is:... Anonymous
06:35 PM Revision dce51969 (ceph): Merge pull request #1224 from kdreyer-inktank/packaging-libdir
packaging: do not package libdir/ceph recursively Sage Weil
06:17 PM Revision 5a6c9508 (ceph): packaging: do not package libdir/ceph recursively
Package libdir/ceph non-recursively, to avoid duplicates, and
package libdir/ceph/ceph_common.sh explicitly.
Signed-...
Alexandre Oliva
06:10 PM Revision 367cf1bb (ceph): librbd: remove limit on number of objects in the cache
The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss...
Josh Durgin
06:10 PM Revision 4856fc29 (ceph): ObjectCacher: use uint64_t for target and max values
All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these...
Josh Durgin
06:10 PM Revision a572aafe (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j...
Josh Durgin
06:08 PM Revision 48a71e22 (ceph): librbd: remove limit on number of objects in the cache
The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss...
Josh Durgin
06:08 PM Revision 65e83a34 (ceph): ObjectCacher: use uint64_t for target and max values
All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these...
Josh Durgin
06:08 PM Revision 74ea7b2d (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j...
Josh Durgin
05:57 PM Bug #7408 (Resolved): filestore xattr use omap = true
will be in next dumpling point release. Sage Weil
05:52 PM Bug #7408: filestore xattr use omap = true
My code has been backported to Dumpling. So the filestore_xattr_use_omap will be gone from the next Dumpling release. David Zafman
04:08 PM Bug #7408: filestore xattr use omap = true
Let's see how we (Sage) decide to resolve #7404. I've created a pull request to backport my 6143 change completely. ... David Zafman
02:22 PM Bug #7408: filestore xattr use omap = true
As I understood Sage what's being done in Dumpling is to flip the default; if so then users still need a warning neve... Florian Haas
02:20 PM Bug #7408: filestore xattr use omap = true
We've generated a couple different tickets about this now that I think are crossing wires, but we're about to backpor... Greg Farnum
02:14 PM Bug #7408: filestore xattr use omap = true
David Zafman wrote:
> The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new...
Florian Haas
02:09 PM Bug #7408: filestore xattr use omap = true
The change for bug 6143 removed the configuration variable "filestore_xattr_use_omap" The new behavior is just like ... David Zafman
01:54 PM Bug #7408 (Resolved): filestore xattr use omap = true
At the core standup yesterday we talked about a really nasty bug where data loss can occur if filestore xattr use oma... Mark Nelson
05:54 PM Revision f7cf25f2 (ceph): Merge pull request #1215 from ceph/wip-7385
Remove the max cached objects restriction for librbd
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:29 PM Revision d0a43492 (ceph): Capture stderr and include in CommandFailedError
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:29 PM Revision 896412f2 (ceph): Remove spurious print
This was causing junk output like <type 'exceptions.StopIteration'>
Signed-off-by: John Spray <john.spray@inktank.com>
John Spray
05:29 PM Revision ca83b7b2 (ceph): Timestamp stdout log output
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:29 PM Revision ab2a01ff (ceph): Catch a case where we weren't getting tracebacks
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:29 PM Revision d39dd8cb (ceph): Log correct name of context during errors
(instead of GeneratorContextManager)
Signed-off-by: John Spray <john.spray@inktank.com>
John Spray
05:29 PM Revision d53a5b65 (ceph): Spelling
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
04:46 PM Revision 2b9a6bc0 (ceph): Merge pull request #182 from ceph/wip-imports
Make libvirt import optional (OS X) Zack Cerza
04:42 PM Bug #7407: Illogical defaults in Python bindings: conffile=None loads no config, conffile='' load...
The original rationale was to keep the existing behavior (not reading a conf file) and use None as a default value to... Josh Durgin
12:55 PM Bug #7407 (New): Illogical defaults in Python bindings: conffile=None loads no config, conffile='...
This feels weird:... Florian Haas
04:42 PM Revision eafeece2 (ceph): Show hostname instead of IP in errors
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
04:25 PM Revision f6afe8cc (ceph): Merge pull request #1199 from ceph/wip-doc-librados-intro
Wip doc librados intro
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
03:12 PM Revision d728b7ab (ceph): Merge pull request #189 from ceph/wip-6536-wusui
Add docstrings to s3 related tasks. Alfredo Deza
02:25 PM Fix #7394 (Fix Under Review): OSD: relax monitor ping requirements while connecting
PR: https://github.com/ceph/ceph/pull/1227 Greg Farnum
01:47 PM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
I believe this is fixed now. It appears it installed ok if you just did a yum install mod_ssl but once httpd and http... Sandon Van Ness
12:07 PM devops Bug #7283 (In Progress): centos 6 - gitbuilder mod_ssl broken dependency
I completley missed this issue bieng assigned to me. It looks like a simple issue with the dependency string containi... Sandon Van Ness
12:10 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
I haven't looked at any of the code involved for real, but that sounds like a good plan to me. *thumbs up* Greg Farnum
11:22 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
What's happening is that suicide() is getting called from another thread while the dispatch thread is inside _dispatc... John Spray
12:05 PM devops Bug #7334 (Pending Backport): ceph-disk: cannot run partprobe on used devices with EL6
Alfredo - please cherry pick to Dumpling Ian Colle
11:52 AM Revision 48bcbc75 (ceph): Merge pull request #1221 from dachary/wip-filestore
tests: fix packaging for s/filestore/objectstore/
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Loïc Dachary
11:46 AM Revision 840e918f (ceph): tests: fix packaging for s/filestore/objectstore/
The binaries file name have changed and need to be updated in the
packaging files for deb and rpm. Fix a few leftover...
Loïc Dachary
11:37 AM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
On commit 7fe10f1271dd94d4c5014a35c6362a7772dc4508
/a/teuthology-2014-02-09_23:00:13-rados-master-testing-basic-pl...
David Zafman
11:26 AM Revision b88b2572 (ceph): Merge pull request #1220 from dachary/wip-filestore
tests: fix objectstore tests Christophe Courtaut
11:06 AM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Yeah -- I don't really want to open that can of worms either, and we'll add some extra hygiene here in Calamari.
B...
John Spray
10:52 AM Revision b64f1e39 (ceph): tests: fix objectstore tests
The objectstore test from 1a588f18ba0e57df64f8a48c1393a4bc65019571 was
missing a few changes.
Signed-off-by: Loic Da...
Loïc Dachary
10:30 AM Feature #7404: backport default filestore_use_omap and superblock checking to dumpling
The original change in master removed the filestore_xattr_use_omap variable. I checked current master branch and thi... David Zafman
10:08 AM Feature #7404 (Resolved): backport default filestore_use_omap and superblock checking to dumpling
Samuel Just
10:26 AM Bug #7345 (Need More Info): LibRadosTier.Evict failed in rados suite
Deferring this since there are a bunch of other outstanding changes to this code. Greg Farnum
10:17 AM Bug #7345 (In Progress): LibRadosTier.Evict failed in rados suite
This hasn't failed in the nightlies since then (although there are other related failures which Sage is looking at), ... Greg Farnum
09:54 AM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
Sage Weil
09:52 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
> > * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
>
> We haven't conf...
Florian Haas
09:47 AM RADOS Cleanup #7402 (New): OSD: audit osdmap_subscribe calls to remove forced subscription attempts
There are a number of places where the OSD subscribes to a map and forces the MonClient to renew its subscription. I ... Greg Farnum
09:43 AM Bug #5804 (In Progress): mon: binds to 0.0.0.0:6800something port
The 0.0.0.0 portion of the address is normal. Unless a monitor has a prebuilt monmap supplied at time of creation, al... Joao Eduardo Luis
09:40 AM Fix #7395 (Fix Under Review): OSD: update osdmap subscription proactively instead of when we want...
PR at https://github.com/ceph/ceph/pull/1223 Greg Farnum
08:06 AM Revision a065e2c0 (ceph): Merge pull request #1212 from ywang19/master
correct one command line at building packages section
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
06:24 AM Revision f34eb1b8 (ceph): mds: force update backtraces for previously created FS
Update inode format version to 10, treat any previously created
inode as no backtrace. When inode with no backtrace i...
Yan, Zheng
05:17 AM Revision ed0980c9 (ceph): Merge pull request #1168 from yuyuyu101/wip-refactor-objectstore-test
Rename test/filestore to test/objectstore
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:12 AM Revision 7f76e78b (ceph): Merge pull request #1218 from yuyuyu101/wip-misc-fix
Fix bad dealloctor
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:10 AM Revision 7709d19f (ceph): Merge pull request #1211 from ceph/wip-memstore
memstore: fix touch double-allocation
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
04:21 AM Revision cee713ff (ceph): Add docstrings to s3 related tasks.
Fixes: 6536
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
04:21 AM Revision 7b638766 (ceph): Add docstrings to s3 related tasks.
Fixes: 6536
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
04:04 AM Revision b5c10bf0 (ceph): Fix bad dealloctor
Memory allocated by malloc() should be deallocated by free(), not 'delete'
Signed-off-by: Haomai Wang <haomaiwang@gm...
Haomai Wang
02:38 AM Revision 33692a2c (ceph): osdmaptool: fix cli test
Encoding the extra tunable byte threw off the output here.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
02:38 AM Revision a4b3b786 (ceph): correct one command line at building packages section
Signed-off-by: Wang, Yaguang <yaguang.wang@intel.com> yaguang wang
02:16 AM Revision fed83969 (ceph): tset_bufferlist: fix signed/unsigned comparison
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:54 AM Revision 8ca3d95b (ceph): rgw: multi object delete should be idempotent
Fixes: #7346
When doing a multi object delete, if an object does not exist then we
should return a success code for t...
Yehuda Sadeh

02/11/2014

11:44 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Josh Durgin wrote:
> Hi Wido,
>
> Attached is a patch to use the timeouts with a libvirt storage pool. I noticed ...
Wido den Hollander
06:27 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Hi Wido,
Attached is a patch to use the timeouts with a libvirt storage pool. I noticed that libvirt will actually...
Josh Durgin
10:42 PM Revision 8533b6ac (ceph): Merge pull request #1185 from ceph/wip-crush
crush: "vary_r" tunable
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
10:36 PM Bug #7401 (Resolved): rados bench takes into account second '0' for stddev calculation
For example:... Ivo Jimenez
10:02 PM Revision bf38bfb2 (ceph): rgw: set bucket permissions, cors on swift creation
Fixes: #7271
Swift bucket creation was ignoring the x-container-read,
x-container-write and the various cors related ...
Yehuda Sadeh
09:34 PM Revision e26bb356 (ceph): Add calamari setup/test tasks
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
09:28 PM Revision 2682b64c (ceph): doc: Incorporated feed back from Loic and Dan.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
09:28 PM Revision 0da9621a (ceph): doc: Adds additional terms for use with librados.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:39 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
To do additional debugging on this problem, I printed out my monmap with:
ceph mon getmap -o zzzz
got latest monm...
Eric Eastman
08:15 PM Revision e1a49e53 (ceph): ObjectCacher: remove unused target/max setters
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:14 PM Revision 0559d31d (ceph): librbd: remove limit on number of objects in the cache
The number of objects is not a significant indicated of when data
should be written out for rbd. Use the highest poss...
Josh Durgin
08:06 PM Revision db034acf (ceph): ObjectCacher: use uint64_t for target and max values
All the options are uint64_t, but the ObjectCacher was converting them
to int64_t. There's never any reason for these...
Josh Durgin
08:06 PM Revision bf8cf2d6 (ceph): ObjectCacher: remove max_bytes and max_ob arguments to trim()
These are never passed, so replace them with the defaults.
Backport: emperor, dumpling
Signed-off-by: Josh Durgin <j...
Josh Durgin
07:20 PM rgw Bug #7346 (Fix Under Review): An unfound object as part of multi-object delete should return dele...
Yehuda Sadeh
04:48 PM rgw Bug #7346 (In Progress): An unfound object as part of multi-object delete should return deleted i...
Yehuda Sadeh
07:12 PM Revision 525b2d26 (ceph): crush: add firefly tunables baseline test
This is a user's map that gives different results when the vary_r tunable
is adjusted.
Signed-off-by: Sage Weil <sag...
Sage Weil
07:12 PM Revision e3309bce (ceph): doc/rados/operations/crush: describe new vary_r tunable
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
07:12 PM Revision d136eb4c (ceph): mon: allow firefly crush tunables to be selected
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
07:11 PM Revision 37f840b4 (ceph): crushtool: new cli tests for the vary-r tunable
These illustrate the variation in mapping results as the vary_r tunable
is adjusted. Note:
1- For the vary_r=0 case...
Sage Weil
05:44 PM Revision 453d72b2 (ceph): don't use notcmalloc flavor for valgrind
We now have the suppressions to avoid this. Yay!
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:49 PM rgw Bug #7271 (In Progress): container create via swift doesn't register ACL
Yehuda Sadeh
04:48 PM Revision e20a55d9 (ceph): crush: add infrastructure around new chooseleaf_vary_r tunable
- encoding
- feature bit
- decompile/compile
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:48 PM Revision f944ccc2 (ceph): crush: add SET_CHOOSELEAF_VARY_R step
This lets you adjust the vary_r tunable on a per-rule basis.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:48 PM Revision e88f843c (ceph): crush: add infrastructure around SET_CHOOSELEAF_VARY_R rule step/command
This will let you vary the vary_r tunable on a per-rule basis.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:41 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
IMO this is a big can of worms having to do with Ceph itself; I'm willing to bet that *none* of the internal routines... Dan Mick
04:32 PM Revision 4889234f (ceph): Merge pull request #1210 from dachary/dumpling
common: admin socket fallback to json-pretty format (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:31 PM Revision 30a346b5 (ceph): Merge pull request #1208 from dachary/emperor
common: admin socket fallback to json-pretty format (emperor)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:30 PM Revision dd200c92 (ceph): Merge pull request #1207 from dachary/wip-7378
common: admin socket fallback to json-pretty format
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:14 PM Revision c36a6ed4 (ceph): Merge pull request #1198 from dachary/wip-mailmap
mailmap updates
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
02:45 PM Fix #7395: OSD: update osdmap subscription proactively instead of when we want a new map
Waiting for the gitbuilders to build the branch so I can run it through thrashing. Greg Farnum
10:12 AM Fix #7395 (Resolved): OSD: update osdmap subscription proactively instead of when we want a new map
In most circumstances, the OSD does a one-time subscription for the "next map" from what it has. But in a few places,... Greg Farnum
01:14 PM rbd Bug #7385 (Fix Under Review): Objectcacher setting max object counts too low
https://github.com/ceph/ceph/pull/1215 Josh Durgin
06:07 AM rbd Bug #7385: Objectcacher setting max object counts too low
Does it make sense to be exposing this to librbd/client.cc at all vs just directly setting it via a config option? (o... Mark Nelson
12:48 PM Bug #6101: ceph-osd crash on corrupted store
(18:02:26) sage: poelzi: looks reasonable. can you make it log to the cluster log about the error, though? IIRC it ... Daniel Poelzleithner
01:31 AM Bug #6101: ceph-osd crash on corrupted store
Daniel Poelzleithner wrote:
> We deleted the rados block that was in the stack trace, but deleting it did not solve ...
Florian Haas
12:27 PM Bug #7398 (Resolved): osd: ERANGE from clone
ubuntu@teuthology:/a/teuthology-2014-02-10_23:01:27-rbd-master-testing-basic-plana/76311... Sage Weil
11:33 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
Florian Haas wrote:
> * filestore_xattr_use_omap can be enabled in a running cluster with no known side effects,
...
Sage Weil
07:25 AM Feature #6143: OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xattr threshh...
This issue has caused data corruption in at least one user (Inktank PS is well aware of this).
Since
* https://g...
Florian Haas
09:59 AM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
Right now, the OSD will time out a monitor after 30 seconds if it fails to ack a PGStats message. But sometimes, the ... Greg Farnum
09:53 AM Bug #7393 (Duplicate): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whit...
from new scrub before test teardown. Sage Weil
09:41 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
yay Sage Weil
09:41 AM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
Sage Weil
09:38 AM Revision 9e43f939 (ceph): mailmap: Dmitry Smirnov is with Debian GNU/Linux
Reviewed-by: Dmitry Smirnov <onlyjob@member.fsf.org>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
09:38 AM Revision ac16fd6e (ceph): mailmap: Derek Yarnell is with University of Mississippi
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
09:37 AM Revision 0869fcb4 (ceph): mailmap: Eric Mourgaya is with Credit Mutuel Arkea
and name normalization
Reviewed-by: Eric Mourgaya <eric.mourgaya@arkea.com>
Signed-off-by: Loic Dachary <loic@dachar...
Loïc Dachary
09:18 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
Loïc Dachary
12:18 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon

Line numbers are relative to b9a127e
src/client/Client.cc:113 is not safe
src/osdc/Objecter.cc:2509 i...
Loïc Dachary
08:41 AM Revision 04e78f89 (ceph): common: admin socket fallback to json-pretty format
If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ...
Loïc Dachary
08:36 AM Revision 30a604d2 (ceph): common: admin socket fallback to json-pretty format
If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ...
Loïc Dachary
08:21 AM Revision 165e76d4 (ceph): common: admin socket fallback to json-pretty format
If the format argument to a command sent to the admin socket is not
among the supported formats ( json, json-pretty, ...
Loïc Dachary
06:36 AM devops Bug #7391 (Resolved): ceph-deploy should pass the verbose flag to ceph-disk
Any and all output from ceph-disk is useful, no need to be quiet about it because it makes it extremely hard
to debu...
Alfredo Deza
05:53 AM devops Bug #7390 (Resolved): ceph-deploy should remove ceph-release and call yum clean all
When uninstalling ceph (or when purging) not removing ceph-release and not calling yum clean all leaves yum in a terr... Alfredo Deza
05:52 AM Revision e98e344d (ceph): client ownership info validation corrected
Babu Shanmugam
05:44 AM Revision f2f4eb5b (ceph): Updated client code to complete PUT and DELETE requests
Babu Shanmugam
03:04 AM Revision 69682ad1 (ceph): memstore: fix touch double-allocation
Reported-by: Allen Samuels <allen.samuels@sandisk.com>
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:55 AM Bug #7093: osd: peering can send messages prior to auth
I would like to add the following comment because I have learned that this is related to an issue we have seen in the... Florian Haas
12:25 AM Revision 51957433 (ceph): Merge pull request #184 from ceph/wip-pg-scrub-from-ceph-wusui
Scrub osds when ceph task finishes Zack Cerza
12:02 AM Revision f9bad673 (ceph): MonClient: add a timeout on commands for librados
Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan...
Josh Durgin
12:02 AM Revision 979b4cba (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab...
Josh Durgin
12:02 AM Revision dde21dc8 (ceph): librados: check and return on error so timeouts work
Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT....
Josh Durgin
12:02 AM Revision 327ca1a4 (ceph): rados: check return values for commands that can now fail
A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
...
Josh Durgin
12:02 AM Revision e06f8199 (ceph): qa: add script for testing rados client timeout options
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 9e62beb80b6c92a97ec36c0db5ea39e417661...
Josh Durgin
12:02 AM Revision 69b1e5e5 (ceph): Objecter: implement mon and osd operation timeouts
This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th...
Josh Durgin

02/10/2014

11:59 PM Cleanup #7388 (Closed): ceph osd find has no format argument
Although it appears to "handle a format argument":https://github.com/ceph/ceph/blob/v0.76/src/mon/OSDMonitor.cc#L2231... Loïc Dachary
11:54 PM Revision b39f1486 (ceph): librados: add timeout to wait_for_osdmap()
This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po...
Josh Durgin
11:53 PM Revision 713cef05 (ceph): conf: add options for librados timeouts
These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked...
Josh Durgin
11:52 PM Revision 576465fa (ceph): Merge pull request #1209 from fghaas/master
doc: highlight that "raw" is the only useful RBD format for QEMU John Wilkins
11:45 PM Revision 6af657bd (ceph): qa: add script for testing rados client timeout options
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from commit 9e62beb80b6c92a97ec36c0db5ea39e417661...
Josh Durgin
11:45 PM Revision 21a0b674 (ceph): rados: check return values for commands that can now fail
A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
...
Josh Durgin
11:45 PM Revision 2c42dd26 (ceph): librados: check and return on error so timeouts work
Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT....
Josh Durgin
11:45 PM Revision 28fe564c (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab...
Josh Durgin
11:45 PM Revision 1d2ea9ef (ceph): MonClient: add a timeout on commands for librados
Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan...
Josh Durgin
11:45 PM Revision 30dafacd (ceph): Objecter: implement mon and osd operation timeouts
This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th...
Josh Durgin
11:30 PM Revision 9292cc21 (ceph): doc: highlight that "raw" is the only useful RBD format for QEMU
Explain why people should be using the "raw" image format for RBD
volumes created for use by QEMU: using any other fo...
Florian Haas
11:24 PM Revision 2aa0d758 (ceph): librados: add timeout to wait_for_osdmap()
This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po...
Josh Durgin
11:21 PM Revision 55d254d5 (ceph): conf: add options for librados timeouts
These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked...
Josh Durgin
10:12 PM Revision 32aa9fdf (ceph): Merge branch wip-librados-timeout
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.org>
Josh Durgin
09:40 PM Revision ad6d412e (ceph): Fix #7369: "sed expression must be raw string"
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
09:09 PM Revision af5d0fcd (ceph): Merge pull request #1205 from ceph/wip-7334
use `partx` for CentOS/RHEL instead of `partprobe`
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
08:59 PM Revision 78240c26 (ceph): Merge pull request #1204 from ceph/wip-fsetpipesz-fix
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:53 PM Revision d389e617 (ceph): msg/Pipe: add option to restrict delay injection to specific msg type
This makes it possible to test timeouts reliably by delaying certain
messages effectively forever, but still being ab...
Josh Durgin
08:53 PM Revision 8e9459e8 (ceph): librados: check and return on error so timeouts work
Some functions could not previously return errors, but they had an
int return value, which can now receive ETIMEDOUT....
Josh Durgin
08:53 PM Revision 79c18743 (ceph): rados: check return values for commands that can now fail
A few places were not checking the return values of commands, since
they could not fail before timeouts were added.
...
Josh Durgin
08:53 PM Revision 9e62beb8 (ceph): qa: add script for testing rados client timeout options
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:53 PM devops Feature #6020: radosgw-apache opinionated package
For reference, Gary's WIP branch is here: https://github.com/ceph/ceph/tree/wip-6020 Ken Dreyer
08:53 PM Revision 3e1f7bbb (ceph): Objecter: implement mon and osd operation timeouts
This captures almost all operations from librados other than mon_commands().
Get the values for the timeouts from th...
Josh Durgin
08:53 PM Revision 671a76d6 (ceph): MonClient: add a timeout on commands for librados
Just use the conf option directly, since librados is the only caller.
Signed-off-by: Josh Durgin <josh.durgin@inktan...
Josh Durgin
08:09 PM Revision 9bcc42a3 (ceph): alert the user about error messages from partx
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
08:09 PM Revision 42900ff9 (ceph): use partx for red hat or centos instead of partprobe
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
08:06 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
> mon_lease_ack_timeout = 10
> mon_accept_timeout = 10
Thanks Sage! After changing the above configuration to 30, t...
Guang Yang
05:57 PM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
The (compiled) osdmap attached. Guang Yang
09:40 AM Bug #7376: mon: >10s spent in remove_redundant_pg_temp
can you attach a copy of your osdmap so we can see what the time might be spent on?
in the meantime, you can incre...
Sage Weil
01:24 AM Bug #7376 (Resolved): mon: >10s spent in remove_redundant_pg_temp
We have a cluster which has 3 monitors, most recently, due to server restart (for both OSDs and Monitors), the cluste... Guang Yang
07:49 PM Revision 97617c99 (ceph): Fix broken symlinks.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
06:44 PM Bug #6101: ceph-osd crash on corrupted store
The patch removes the assert in case the trim event is done an a non existing context.
I think this is save and shou...
Daniel Poelzleithner
06:19 PM Revision 2c5783cc (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
05:49 PM rgw Bug #7374: s3_multipart_upload.pl fails
I believe that this is a yaml file problem (Same issue as 7375). I am investigating. Anonymous
04:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
The problem could also be in the packaging Anonymous
04:27 PM rgw Bug #7374: s3_multipart_upload.pl fails
I've been looking at this. There may be a problem with the script in that a directory is not there that the script e... Anonymous
05:48 PM rgw Bug #7375: s3_user_quota.pl fails
I believe that the yaml files are not right here. This is probably a ceph-qa-suite problem. I am still investigatin... Anonymous
05:37 PM Revision 450163ec (ceph): configure: don't check for arpa/nameser_compat.h twice
Nuke redundant check and move the real one into the common
AC_CHECK_HEADERS stanza.
Signed-off-by: Ilya Dryomov <ily...
Ilya Dryomov
05:37 PM Revision a5f479c2 (ceph): configure: fix F_SETPIPE_SZ detection
Currently CEPH_HAVE_SETPIPE_SZ is not set even if F_SETPIPE_SZ is
available, because AC_COMPILE_IFELSE test program a...
Ilya Dryomov
05:37 PM Revision 69262720 (ceph): common/buffer: fix build breakage for CEPH_HAVE_SETPIPE_SZ
common/buffer.cc fails to build if CEPH_HAVE_SETPIPE_SZ is defined.
Fix it.
Signed-off-by: Ilya Dryomov <ilya.dryomo...
Ilya Dryomov
05:28 PM Revision ceffee40 (ceph): Make sure osd_scrub_pgs gets called if healthy call fails.
Fixes: 7198
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
05:14 PM Revision f6bac22d (ceph): Merge pull request #6 from ceph/wip-set-inline
fs: Fix bad "mds set inline_data" syntax Sage Weil
05:11 PM Feature #6507 (Resolved): librados shouldn't block indefinitely when cluster doesn't respond
merged in commit:32aa9fdf666063e4c5539b5e850f04af37e30b2e to master, backported to dumpling around commit:30dafacd0b5... Josh Durgin
05:11 PM Revision b2d34313 (ceph): fs: Fix bad "mds set inline_data" syntax
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
04:35 PM Revision c1d2a997 (ceph): libcephfs: fix documentation for ceph_readlink
ceph_readlink() and ceph_ll_readlink() both return the number of bytes
copied on success, which the callers need to g...
Casey Bodley
03:52 PM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
"dumpling backport":https://github.com/ceph/ceph/pull/1210
"emperor backport":https://github.com/ceph/ceph/pull/1208
Loïc Dachary
03:12 PM Bug #7378 (Fix Under Review): ceph --format plain --admin-socket mon.asok crashes the mon
"work in progress":https://github.com/ceph/ceph/pull/1207
Loïc Dachary
09:55 AM Bug #7378: ceph --format plain --admin-socket mon.asok crashes the mon
For what it's worth, it's not a blocker for me. The "plain" format is documented to not being supported and it only h... Loïc Dachary
07:25 AM Bug #7378 (Resolved): ceph --format plain --admin-socket mon.asok crashes the mon
Steps to reproduce, from the src dir on todays master:... Loïc Dachary
03:46 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Urgh, redmine apparently can't cope with unicode either! Here's what the snipped should look like http://pastebin.co... John Spray
03:45 PM Bug #7387 (Resolved): Malformed JSON command output when non-ASCII strings are present

Ceph accepts non-ascii input when setting e.g. the name of a pool. Subsequently, when using human-formatted CLI ou...
John Spray
03:29 PM rbd Bug #7385: Objectcacher setting max object counts too low
This is set by librbd or ceph-fuse's Client.cc after creating the objectcacher. There's already a config option for C... Josh Durgin
03:19 PM rbd Bug #7385 (Resolved): Objectcacher setting max object counts too low
It appears that the objectcacher is setting max object counts based on the max dirty data size and object size. With... Mark Nelson
03:24 PM RADOS Documentation #7386 (Won't Fix): librados: document rados_osd_op_timeout and rados_mon_op_timeout...
These were added in https://github.com/ceph/ceph/pull/1192. They shouldn't be used generally, but are useful for libr... Josh Durgin
02:04 PM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
merged into ceph's master branch af5d0fc Alfredo Deza
12:36 PM devops Bug #7334 (Fix Under Review): ceph-disk: cannot run partprobe on used devices with EL6
pull request opened https://github.com/ceph/ceph/pull/1205 Alfredo Deza
01:46 PM Revision dbaf71aa (ceph): mailmap: Moritz Möller is with Bigpoint.com
Reviewed-by: Moritz Möller <mm@mxs.de>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
01:42 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
I change the ceph-disk a little bit:
In mount_active, mount the disk using default mount options, then activate it t...
Kai Zhang
11:35 AM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
After the disk are prepared, udev notices the disk label and this rule calls ceph-disk-activate: https://github.com/c... Josh Durgin
09:51 AM devops Bug #7381 (Rejected): ceph-deploy lies with OSDs failures
... Alfredo Deza
08:58 AM Tasks #7377 (Resolved): security Certificate is out of date
Greg Farnum
07:49 AM Tasks #7377: security Certificate is out of date
Greg Farnum wrote:
> I think this should be resolved already, based on an email discussion.
Yes, thats correct. T...
gr kooi
06:45 AM Tasks #7377: security Certificate is out of date
I think this should be resolved already, based on an email discussion. Greg Farnum
01:39 AM Tasks #7377 (Resolved): security Certificate is out of date
The certificate of https://ceph.com/git/?p=ceph.git;a=blob_plain;f=keys/release.asc is ended yesterday (8-2-2014).
A...
gr kooi
07:08 AM Revision 4cf2c726 (ceph): Server changes to deploy in a production env
1. Added the wsgi entry point app.wsgi
2. Updated client code to mandate the update-metadata to have url to publish a...
Babu Shanmugam
05:32 AM Bug #7367: fail to run mds and mount rbd (v0.76)
Quick follow Up ;
with 0.76 OSD, MON, MDS: Creating new volume , formatting, mounting leads to normal comportment.
...
Yann Dupont
04:53 AM Revision ccd9b5eb (ceph): test_striper: fix warning
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/09/2014

09:01 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/ Sage Weil
09:01 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
http://pulpito.ceph.com/teuthology-2014-02-08_23:02:22-rgw-next-distro-basic-plana/ Sage Weil
08:57 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
My guess is that this is due to the new ACL code.
http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-08_23:05...
Sage Weil
06:37 PM Revision 39b393d7 (ceph): Merge remote-tracking branch 'gh/wip-7329' into next
Sage Weil
03:59 PM Bug #7262: ceph-disk-activate: custom mount options aren't handled correctly for non-default-name...
Hi, I was trying to fix this today. But in my cluster, disk was activated automatically right after ceph-disk-prepare... Kai Zhang
03:05 PM CephFS Bug #7372 (Closed): kcephfs: pjd tests fail
... Sage Weil
03:02 PM Bug #7371 (Resolved): libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
ubuntu@teuthology:/a/teuthology-2014-02-08_23:05:12-kcephfs-next-testing-basic-plana/73644
tasks:
- chef: null
-...
Sage Weil
10:38 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
see #7329 for the first two failures. Sage Weil
10:38 AM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
Sage Weil
04:20 AM Revision 575566b1 (ceph): ceph_test_rados_api_tier: try harder to trigger the flush vs try-flush ...
It seems to be reasonable easy to complete a flush before the next client
request is processed. Crazy...
Same with ...
Sage Weil
12:12 AM Revision 270714d5 (ceph): Merge pull request #1201 from ceph/wip-7370
crush: fix tries/retries bug that was recently introduced
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary

02/08/2014

11:58 PM Revision 7fe10f12 (ceph): Merge pull request #1115 from jcsp/tell_cleanup
Remove some almost-duplicate COMMAND definitions
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:33 PM Revision cf2d71ce (ceph): Merge pull request #1127 from dmsimard/log_links
Doc: Fix 404 broken links to logging and debug configuration
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Revi...
Loïc Dachary
09:15 PM Bug #6003: journal Unable to read past sequence 406 ...
ubuntu@teuthology:/a/sage-2014-02-08_15:50:23-rados:thrash-wip-agent-testing-basic-plana/72854 Sage Weil
09:14 PM Bug #7329: osd: LibRadosTier.FlushTryFlushRaces failures
Sage Weil
08:27 PM Revision a8e6c9fb (ceph): crush: add chooseleaf_vary_r tunable
The current crush_choose_firstn code will re-use the same 'r' value for
the recursive call. That means that if we ar...
Sage Weil
08:24 PM Revision bb44c0d5 (ceph): crushtool: add cli test for off-by-one tries vs retries bug
See bug #7370. This passes on dumpling and breaks prior to the #7370 fix.
Backport: emperor, dumpling
Signed-off-by...
Sage Weil
08:23 PM Revision f17caba8 (ceph): crush: allow crush rules to set (re)tries counts to 0
These two fields are misnomers; they are *retry* counts.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:21 PM Revision 795704fd (ceph): crush: fix off-by-one errors in total_tries refactor
Back in 27f4d1f6bc32c2ed7b2c5080cbd58b14df622607 we refactored the CRUSH
code to allow adjustment of the retry counts...
Sage Weil
08:21 PM Revision ed32c400 (ceph): crushtool: add cli test for off-by-one tries vs retries bug
See bug #7370. This passes on dumpling and breaks prior to the #7370 fix.
Backport: emperor, dumpling
Signed-off-by...
Sage Weil
04:23 PM Revision 5bc8e9e4 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
04:22 PM Revision 75c55258 (ceph): qa/workunits/rest: use larger max_file_size
64k is the min.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:14 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
"resolved by":https://github.com/ceph/ceph/pull/1201 Loïc Dachary
12:20 PM RADOS Bug #7370 (Resolved): crush: off-by-one with tries behavior
i broken crush tries behavior when refactoring in commit:27f4d1f6bc32c2ed7b2c5080cbd58b14df622607 Sage Weil
02:31 PM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
471c67828cf98224f89bd8efb28d377f8d745b7a Samuel Just
02:30 PM Feature #7366: EC: scrubbing
Samuel Just
02:30 PM Feature #7361: EC: arrange for chunks to have some padding where we can later add checksums
Samuel Just
01:56 PM devops Feature #5214: Kernel gitbuilders for rpm distros
Forgot to update this as it was getting pretty late last night. I got gitbuilders up for:
rhel7beta
rhel6 (6.5)
...
Sandon Van Ness
01:10 PM Revision 17c8a230 (ceph): mailmap: Yan, Zheng name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:10 PM Revision a2dae0d7 (ceph): mailmap: Somnath Roy is with SanDisk
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:10 PM Revision 5d20c8da (ceph): mailmap: Ray Lv is with Yahoo!
Reviewed-by: Ray Lv <xiangyulv@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:41 AM Revision 1a588f18 (ceph): Rename test/filestore to test/objectstore
Now ObjectStore support three backend types, so we need to make each backend
share unit test to avoid duplicate codes...
Haomai Wang
06:27 AM Revision 3d656600 (ceph): script to test rgw multi part uploads using s3 interface
Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
(cherry picked from commit 5d59dd9cd67834d991b038323bcbc3e8f8612...
Tamilarasi muthamizhan
06:22 AM Revision 9506377c (ceph): rgw task for multipart upload script
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
06:15 AM Revision 5d59dd9c (ceph): script to test rgw multi part uploads using s3 interface
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
04:08 AM CephFS Feature #7352: mds: make classes encode/decode-able
It's maybe a bit less broad than it sounds (in my mind at least) -- I'm concentrating on the in-rados representations... John Spray
02:25 AM Subtask #5857 (Resolved): Refactor recovery to use PGBackend methods
Loïc Dachary
02:24 AM Subtask #5856 (Resolved): Refactor Backfill to use PGBackend methods
Loïc Dachary
01:39 AM Feature #7195: librados: complete C write object operation bindings
"implementation":https://github.com/ceph/ceph/commit/33717b4f60ce0ba7088164182b99eaf48cf0486f Loïc Dachary
01:10 AM Revision d4e5db58 (ceph): Merge branch 'next' of github.com:ceph/ceph into next
Tamilarasi muthamizhan
01:09 AM Revision 0bac064e (ceph): added script to test rgw user quota
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
01:07 AM Revision b4a2a2b0 (ceph): s/rgw_user_quota.pl/rgw_user_quota.yaml
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan

02/07/2014

11:49 PM Revision 8cb3dad5 (ceph): doc: Added Python doc.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
11:48 PM Revision 22afd6ca (ceph): doc: Added inline literal tag.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
11:47 PM Revision aaa2799f (ceph): doc: Adds Python to index and sets maxdepth to 2.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
11:35 PM Revision 24d89e24 (ceph): task for rgw user quota testing
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
11:34 PM Revision 0f2386a1 (ceph): script to test rgw user quota functionality
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
10:54 PM Revision 69f29d17 (ceph): Move osd_scrub_pgs call to finally block of ceph main task.
Fixes: 7198
Signed-off-bye: Warren Usui <warren.usui@inktank.com>
Warren Usui
10:04 PM Revision 935f8b3e (ceph): client/fuse_ll: adapt to new ll_ interface
This adapts the FUSE client to David Zafman's proposed interface
changes.
(Includes pieces of NFS interface widening...
Matt Benjamin
10:04 PM Revision e2dc1b6b (ceph): libcephfs: expose new client ll_ interface
This patch exposes all changes made for interfacing with Ganesha
and layout support and David Zafman's proposed modif...
Matt Benjamin
10:04 PM Revision acf2e493 (ceph): libcephfs: add ceph_ll_lookup_root()
Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com> Andrey Kuznetsov
10:04 PM Revision 55a20c03 (ceph): libcephfs: add ceph_ll_listxattr
Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com> Andrey Kuznetsov
10:04 PM Revision 77047ee4 (ceph): libcephfs: add an xattr ll test
Signed-off-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com> Andrey Kuznetsov
10:04 PM Revision afcc7eb4 (ceph): mds: include requested caps (namely, xattrs) on getattr reply
For xattrs, we only include them in the reply if we are issuing caps on
them. However, in the getattr case, we need ...
Sage Weil
10:04 PM Revision 349b8168 (ceph): client, libcephfs: make readlink sane
Supply a buffer and copy the data into it. Do not ever expose internal
pointers from libcephfs's own cache.
Signed-...
Andrey Kuznetsov
10:04 PM Revision c1b07149 (ceph): client: For rebase need to fix ll_readlink() call in Synthetic client
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
10:04 PM Revision 16ae4f84 (ceph): fuse: fix for missing ll_ref on create
when the 'Inode **outp' argument was added to ll_create(), it was
changed to only take the ll_ref if outp was not NUL...
Casey Bodley
10:04 PM Revision dad91b5e (ceph): client: direct read/write methods that bypass cache, cap checks
These methods were created to implement pNFS data server support,
bypassing cap checks since the pNFS MDS holds a cap...
Adam C. Emerson
10:04 PM Revision 9ad8f571 (ceph): client/SyntheticClient: adapt to new ll_* interface
(Includes pieces of NFS interface widening by Adam.)
Signed-off-by: Matt Benjamin <matt@linuxbox.com>
Matt Benjamin
10:04 PM Revision b700768b (ceph): client: expose layout information
This allows us to construct pNFS layouts and DS filehandles that
match the Ceph clustering, placement, and striping s...
Adam C. Emerson
09:47 PM Revision e08210dd (ceph): client: switch ll_* methods to Inode* arguments
This commit implements a set of API changes proposed by
"David Zafman" <david.zafman@inktank.com>.
The principle cha...
Matt Benjamin
08:58 PM Revision 3752660d (ceph): client/Client: make open fhp argument optional
This is more natural for both FUSE and Ganesha.
Signed-off-by: Matt Benjamin <matt@linuxbox.com>
Matt Benjamin
08:58 PM Revision 23577c8e (ceph): client/Client: return 1 from readdir cb on full
This appears to save us a bit of extra work trying to fill up the buffer
further than it can be filled.
Signed-off-b...
Adam C. Emerson
08:55 PM Revision ff046296 (ceph): client: add barrier and types
This gives us a framework to implement commit operations that are
guaranteed to terminate even if unstable writes com...
Matt Benjamin
08:54 PM Revision 7f6d755c (ceph): client: whitespace
Signed-off-by: Matt Benjamin <matt@linuxbox.com> Adam C. Emerson
08:50 PM Revision 7f9fdc33 (ceph): osdc/Objecter: whitespace
Signed-off-by: Matt Benjamin <matt@linuxbox.com> Adam C. Emerson
08:48 PM Revision 548ccd9e (ceph): mds/Server: whitespace
Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Matt Benjamin <matt@linuxbox.com>
Adam C. Emerson
06:21 PM Revision b04ae134 (ceph): Merge pull request #1197 from ceph/wip-osdmap-primary
osd/OSDMap: populate *primary when pool dne
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:38 PM Revision 3a5fa876 (ceph): osd/OSDMap: populate *primary when pool dne
This fixes a valgrind error from OSD::handle_osd_map where primary is not
initialized and is compared after the call ...
Sage Weil
05:26 PM Revision 4cca38ca (ceph): Merge pull request #1173 from ceph/wip-7109
Fix #7109: Prevent removal of default data pool
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
04:43 PM Revision 5b7e2b22 (ceph): rgw: initialize variable before call
Need to initialize the truncated variable, as we sometimes ignore error
response (e.g., with ENOENT), and in such cas...
Yehuda Sadeh
04:43 PM Revision ebe505b9 (ceph): Merge pull request #1191 from ceph/wip-rgw-vg
rgw: initialize variable before call
Revewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:10 PM Revision ed438aaa (ceph): Merge pull request #1194 from dachary/wip-erasure-code-directory
erasure code directory
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
03:56 PM Bug #7368 (Can't reproduce): ceph osd repair * blocks after some minutes and prevent other ceph p...
Hello,
this is a follow up of http://tracker.ceph.com/issues/7367
An unfortunate update To 0.75 endend with lots ...
Yann Dupont
03:46 PM CephFS Feature #7352: mds: make classes encode/decode-able
This is...remarkably broad. Do we have an order of priorities or anything? :) Greg Farnum
03:45 PM CephFS Fix #7109 (Resolved): disallow removing the first data pool
Merged into master in commit:4cca38c Greg Farnum
03:39 PM Bug #7367: fail to run mds and mount rbd (v0.76)
Hello, all & thanks to loic for taking the time to make a bugreport.
The problem occured on one of my cluster, th...
Yann Dupont
02:19 PM Bug #7367: fail to run mds and mount rbd (v0.76)
Is this a CephFS or an RBD bug report?
(Perhaps it should be two different ones. :p)
Greg Farnum
02:16 PM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
... Loïc Dachary
03:12 PM Revision 0e9adf73 (ceph): Merge pull request #1178 from ceph/wip-osdmaptool
osdmaptool: add --test-map-pgs mode
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Loic Dachary <loic@...
Sage Weil
03:10 PM Revision b98eaa5c (ceph): osdmaptool: test --import/export-crush
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
03:10 PM Revision 45d31f09 (ceph): osdmaptool: tests for --test-map-pgs
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
03:10 PM Revision 362825c4 (ceph): osdmaptool: fix cli tests
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:10 PM Revision 7c310368 (ceph): osdmaptool: s/simple.t/missing-argument.t/
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
03:10 PM Revision 7f1b12f2 (ceph): osdmaptool: add --test-map-pgs mode
This command will map all pgs from all pools (or just one pool) to osds
and summarize the placement and calculate the...
Sage Weil
03:10 PM Revision 9caaef71 (ceph): osdmaptool: allow a completely random placement
This useful for comparison purposes and sanity-checking the results.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
02:11 PM Revision bb6d3f81 (ceph): rest/test.py: use larger max_file_size for mds set test
Current min is 64k.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:40 PM Revision f584de57 (ceph): With functionality test cases. Test it using 'python setup.py test'
Babu Shanmugam
01:26 PM Feature #7366 (Resolved): EC: scrubbing
Fill in the ECBackend methods for shallow and deep scrubbing Samuel Just
11:41 AM Revision 302fc924 (ceph): mon: s/ENOSYS/ENOTSUP/
On Linux ENOTSUP is remapped
/usr/include/x86_64-linux-gnu/bits/errno.h
/* Linux has no ENOTSUP error code. */
...
Loïc Dachary
10:25 AM Revision e1e6c458 (ceph): Completed model and controller code
1. GET, PUT and DELETE request are added
2. Removed public folder as it will never be used
Babu Shanmugam
09:59 AM Bug #6101: ceph-osd crash on corrupted store
We deleted the rados block that was in the stack trace, but deleting it did not solve the problem.
The node still cr...
Daniel Poelzleithner
09:31 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Is it actually that much work to enable? We'll want it in the future and it'll be easier if it's set up using the cor... Greg Farnum
09:24 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Greg Farnum wrote:
> Unless you've already done so, the agent will also need to be recast the same way. We might as ...
Sage Weil
09:15 AM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
Unless you've already done so, the agent will also need to be recast the same way. We might as well make this work pr... Greg Farnum
09:13 AM devops Bug #7334 (In Progress): ceph-disk: cannot run partprobe on used devices with EL6
Alfredo Deza
04:57 AM Subtask #7363 (Rejected): erasure code: reduce the chunk size to a minimum
make sure the jerasure cauchy technique does not oversize chunks, see "related mail thread":http://www.spinics.net/li... Loïc Dachary
04:23 AM Bug #7354: osd: LibRadosTier.PromoteSnap failure
"pulpito report":http://pulpito.ceph.com/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69541/
"cor...
Loïc Dachary
04:07 AM Feature #7266: erasure code : implement locality (was pyramid)
"primary affinity":https://github.com/ceph/ceph/pull/1176 Loïc Dachary
03:13 AM Revision 42a64e19 (ceph): Revert test case of "mon: OSDMonitor: do not allow changing an erasure-...
This reverts part of commit c8c4cc6e81816069886af6bff968712993554759.
Fixes: #7355
Signed-off-by: David Zafman <dav...
David Zafman
12:54 AM Revision 0aa25b17 (ceph): Some suggested changes, both errors and rewordings
Python and C code examples tweaked a bit
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
12:48 AM rgw Bug #6621 (Resolved): quota: the max-size and max-objects value when zero
Tamilarasi muthamizhan
12:29 AM rgw Bug #6621 (In Progress): quota: the max-size and max-objects value when zero

Tamilarasi muthamizhan

02/06/2014

09:32 PM Fix #6483: osd: does not fill in OSDOp::rval member
Running this through the rados suite. It's in wip-librados-op-rvals, which is on top of https://github.com/ceph/ceph/... Josh Durgin
09:32 PM Fix #6483 (Fix Under Review): osd: does not fill in OSDOp::rval member
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Feature #7194 (Fix Under Review): librados: omap in the c api
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Feature #7193 (Fix Under Review): librados: object operation bindings for reads
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:31 PM Bug #7250 (Fix Under Review): osd: string xattr comparison can have undefined behavior
https://github.com/ceph/ceph/pull/1195 Josh Durgin
09:30 PM Feature #7195 (Fix Under Review): librados: complete C write object operation bindings
https://github.com/ceph/ceph/pull/1195 Josh Durgin
07:53 PM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
Samuel Just
07:52 PM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
nvm Samuel Just
07:18 PM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
42a64e19b7a06c1b3e0fd40e2d9c572103e3e426 David Zafman
03:07 PM Bug #7355 (In Progress): assert(0) in_make_pg() because EC getting enabled
David Zafman
11:49 AM Bug #7355: assert(0) in_make_pg() because EC getting enabled
2014-02-06T01:24:45.644 INFO:teuthology.task.workunit.client.0.err:[10.214.133.32]: + ceph osd pool delete fuggg fugg... David Zafman
11:45 AM Bug #7355 (Resolved): assert(0) in_make_pg() because EC getting enabled
David Zafman
07:18 PM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
"Work in progress":https://github.com/ceph/ceph/pull/1267
Once OSDs can handle Erasure Coding we should add back t...
David Zafman
04:10 PM rados-java Bug #7359: [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-plana suite
Same issue was reported in ceph project - BUG #7354 Yuri Weinstein
03:52 PM rados-java Bug #7359 (Duplicate): [ FAILED ] LibRadosTier.FlushWriteRaces in rados-master-testing-basic-pl...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:00:49-rados-master-testing-basic-plana/69709... Yuri Weinstein
01:38 PM Subtask #7358 (Rejected): erasure code : plugin upgrade documentation
when a plugin is upgraded and its behavior changes, it must be renamed. That is until there is a more sophisticated p... Loïc Dachary
01:36 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
For Firefly it is enough to document. If a new backward compatible plugin is introduced in Giant, it will need to hav... Loïc Dachary
09:36 AM Subtask #7292: erasure code: plugin backward compatibility
Or maybe a increasing version and mandatory backward compatibility is all we need and compatset is overkill Loïc Dachary
05:50 AM Subtask #7292 (Need More Info): erasure code: plugin backward compatibility
Is there a better way to prepare an upgrade path without over engineering it ? Loïc Dachary
02:18 AM Subtask #7292: erasure code: plugin backward compatibility
"work in progress":https://github.com/ceph/ceph/pull/1193 Loïc Dachary
01:45 AM Subtask #7292 (In Progress): erasure code: plugin backward compatibility
Loïc Dachary
12:45 PM devops Bug #7356 (Rejected): Kill all while loops that will never end....
Ok maybe with the one exception of one of mine that is for VPS creation... If the host machine is down then it will j... Sandon Van Ness
12:36 PM Revision 30fd0c55 (ceph): Intial version of the server code.
1. Database modelling is done
2. PUT request is completed
Babu Shanmugam
11:49 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
Hi,
I am seeing the same issue on my clusters with 3 monitors. I am running:
ceph --version
ceph version 0.7...
Eric Eastman
11:45 AM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure

During master run and a also my branch which has a backfill fix we have seen the following test case failures:
L...
David Zafman
11:12 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
Duplicate of #7336. Already fixed on next. Yehuda Sadeh
10:34 AM rgw Bug #7353 (Duplicate): Failed tests in rgw-master-testing-basic-plana suite
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-05_23:02:36-rgw-master-testing-basic-plana/69941/
...
Yuri Weinstein
10:31 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
Thanks Sage -- I can confirm that the issue does not appear when echo'ing directly into the file. So evidently it was... Florian Haas
09:40 AM Bug #7350: osd: scrub does not detect recently touched and then renamed backend files
the problem is that vi is renaming the file and we cache recently opened files. use echo asdf >> file or similar to ... Sage Weil
04:18 AM Bug #7350 (Won't Fix): osd: scrub does not detect recently touched and then renamed backend files
This is on Dumpling (0.67.5-1precise).
Steps to reproduce:
> Create a single-byte RADOS object and read it back...
Florian Haas
10:28 AM Revision fc963acf (ceph): erasure-code: move test files to a dedicated directory
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
10:28 AM Revision 7baa62f6 (ceph): erasure-code: move source files to a dedicated directory
The src/erasure-code directory contains the erasure-code plugin system
and the jerasure plugin. It is moved out of OS...
Loïc Dachary
09:57 AM Feature #6507 (Fix Under Review): librados shouldn't block indefinitely when cluster doesn't resp...
https://github.com/ceph/ceph/pull/1192 Josh Durgin
07:48 AM Documentation #6465: admin/build-doc should have some kind of build check for broken links
No updates here, assigning back to John since this looks like a problem with the build.
The one change added to th...
Alfredo Deza
07:00 AM CephFS Feature #7352: mds: make classes encode/decode-able
working on this at https://github.com/ceph/ceph/tree/wip-mds-dencoder John Spray
06:57 AM CephFS Feature #7352 (In Progress): mds: make classes encode/decode-able
Sage Weil
06:55 AM CephFS Feature #7352 (Resolved): mds: make classes encode/decode-able
Sage Weil
06:54 AM CephFS Feature #7319 (In Progress): qa: multimds, no failure
Sage Weil
01:41 AM Feature #7238 (In Progress): erasure code : implement LRC plugin
refactoring to not introduce new API functions as it turns out to be more complicated Loïc Dachary
01:38 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
Alignment is calculated using "LARGEST_VECTOR_WORDSIZE":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39b... Loïc Dachary
01:06 AM Subtask #7158 (Resolved): EC: flesh out how the ceph tool should be used to manage ec pools and c...
http://tracker.ceph.com/issues/7146 was created and implemented. There does not seem to be a need for more tools.
...
Loïc Dachary
12:38 AM Revision 471c6782 (ceph): Merge pull request #1188 from dachary/wip-7339
DNM: define pg_pool_t::stripe_width and set from erasure-code plugin on erasure pool creation
Reviewed-by: Samuel Ju...
Loïc Dachary

02/05/2014

11:47 PM Revision 5cc99fec (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
11:46 PM Revision f0bc87a3 (ceph): created upgrades:dumpling-next suite to test parallel upgrades
and partial upgrades.
Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
Tamilarasi muthamizhan
11:26 PM Revision 5422c41d (ceph): s/rgw_tests.sh/s3_bucket_quota.pl
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
11:20 PM Revision 330612dc (ceph): schedule_suite: be slightly more verbose
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:19 PM Revision 9ecf3467 (ceph): rgw: initialize variable before call
Need to initialize the truncated variable, as we sometimes ignore error
response (e.g., with ENOENT), and in such cas...
Yehuda Sadeh
09:15 PM Revision 81e3c621 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
09:04 PM Revision 3d435310 (ceph): Merge pull request #1190 from ceph/wip-snaptest-next
qa/workunits/snaps: New allow_new_snaps syntax Sage Weil
09:00 PM Revision ce0e3bd1 (ceph): qa/workunits/snaps: New allow_new_snaps syntax
These were probably just obscuring other failures.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: John Spr...
John Spray
07:46 PM Revision 0d2cbe64 (ceph): Merge pull request #185 from ceph/wip-7342
Enable killing runs that haven't even started yet Alfredo Deza
07:44 PM Revision 22b0057f (ceph): mon: test osd pool create pg_pool_t::stripe_width behavior
* Check that the default from the configuration options is found in the
output of osd dump
* Check that specifying ...
Loïc Dachary
07:43 PM Revision 7759473e (ceph): Enable killing runs that haven't even started yet
This requires passing --machine-type.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
07:40 PM Revision dfc90cf3 (ceph): mon: osd pool create sets pg_pool_t::stripe_width
It does nothing if the pool is replicated. Otherwise it uses
osd_pool_erasure_code_stripe_width as the desired stripe...
Loïc Dachary
07:40 PM Revision 33b8ad81 (ceph): common: add osd_pool_erasure_code_stripe_width
and document it.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:33 PM Revision 798b56a6 (ceph): unittests: update osdmaptools with stripe_width
stripe_width 0 now shows on every osd dump.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:31 PM Revision 11c11ba9 (ceph): mon: add erasure-code pg_pool_t::stripe_width
Contains the actual stripe size used by erasure coded pools. It is
initialized to zero by default and has to be expli...
Loïc Dachary
07:26 PM Revision c2bd8464 (ceph): valgrind: fix msync suppression
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
07:19 PM Revision b0f37078 (ceph): Merge pull request #1187 from ceph/port/fixes
portability fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:59 PM Feature #7347 (New): Per CRUSH type mon_osd_down_out_interval
Ability to have different mon_osd_down_out_interval values for different CRUSH types.
For example, you could set:
...
Alexandre Marangone
04:42 PM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
Loïc Dachary
12:09 PM Subtask #7339 (Fix Under Review): erasure code: add stripe width to pg_pool_t
"work in progress":https://github.com/ceph/ceph/pull/1188 Loïc Dachary
01:39 AM Subtask #7339 (Resolved): erasure code: add stripe width to pg_pool_t
* add *erasure_code_stripe_width* to config_opts.h
* on *osd pool create*, set the pg_pool_t::stripe_width to be get...
Loïc Dachary
04:37 PM Revision 994bdeaf (ceph): os/kvstore: trivial portability fixes
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
04:37 PM Revision 6fda45b1 (ceph): os/kvstore: remove used var
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
04:37 PM Revision 922e5cf8 (ceph): osd: fix type mismatch warning
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
04:35 PM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
Upon trying to issue a multiple delete operation on a bucket that contains an unfound object, we return:
@<?xml ve...
Brian Andrus
04:27 PM Revision 377a8458 (ceph): common: simpler erasure code technique
Change the default technique from Cauchy to ReedSolomon. Although it is
less efficient the alignment constraints are ...
Loïc Dachary
03:44 PM RADOS Feature #7205: erasure-code: update HITSET_GET to somehow use a CEPH_OSD_OP_READ op
This func does two things: either returns in in-memory structure, or generates the right archived hitset that spans t... Sage Weil
03:20 PM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
No pattern has emerged, except that it happened twice in rapid succession after a long period of not happening (weeks... Nathaniel Filardo
08:28 AM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
Hi Nathaniel,
What kind of workload are you running? Have you noticed any pattern
wrt when it occurs, what might...
Ilya Dryomov
03:15 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
Logs are in - http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68114
...
Yuri Weinstein
11:51 AM Feature #7344: osd: add additional heartbeat on cluster interface
If we have to do heartbeating over the exact same connection we send our other traffic on, is there any advantage to ... Greg Farnum
11:24 AM Feature #7344 (Resolved): osd: add additional heartbeat on cluster interface
A user had a switch configuration problem (no jumbo frames) that prevented progress on the cluster interface but allo... Sage Weil
11:46 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
11:18 AM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")

As unsigned values CEPH_SNAPDIR (snapdir) > CEPH_NOSNAP (head). The code wants to collapse both into a single last...
David Zafman
10:20 AM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
11:20 AM Bug #7343 (Resolved): Failures in valgrind in rados suite
logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-04_23:00:02-rados-next-distro-basic-plana/68416/te... Yuri Weinstein
09:30 AM devops Bug #6595 (Resolved): Hardcoded install path in ceph-disk
All subprocess calls in ceph-disk will use a PATH helper to find the correct executables regardless if $PATH is set o... Alfredo Deza
09:28 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
Pull request https://github.com/ceph/ceph-deploy/pull/160
Merged into master with hash b50345e
Alfredo Deza
09:26 AM devops Bug #7276 (Resolved): ceph-deploy: -n arg is ignored
Merged into ceph-deploy's master branch with hash c036cbd Alfredo Deza
08:37 AM devops Bug #7276 (Fix Under Review): ceph-deploy: -n arg is ignored
pull request opened https://github.com/ceph/ceph-deploy/pull/162 Alfredo Deza
07:18 AM devops Bug #7276 (In Progress): ceph-deploy: -n arg is ignored
Ah good catch. That does absolutely nothing. Will have to remove that. Alfredo Deza
07:27 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
> Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about wh... Florian Haas
07:18 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Locking in RADOS is strictly voluntary; making it a mandatory thing would require keeping global knowledge about whic... Greg Farnum
01:03 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Dan Mick wrote:
> Another way to state this: rbd images are defined such that if an object doesn't exist within the ...
Florian Haas
05:33 AM Revision eb18c0a8 (ceph): Merge pull request #1183 from ceph/wip-7336
rgw: fix rgw_read_user_buckets() use of max param
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:45 AM Feature #7340 (Duplicate): rados.py does not expose object locking
Commit d8415663b62edb812d087cba40b03b933e3e4556 exposed @rados_lock_exclusive()@, @rados_lock_shared()@, @rados_unloc... Florian Haas

02/04/2014

09:04 PM Revision decfe7c2 (ceph): increase mon verbosity in logs
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
09:04 PM Revision a07db3ca (ceph): increase mon verbosity for all ceph-deploy tasks
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
06:37 PM Revision 04b1ae46 (ceph): rgw: fix rgw_read_user_buckets() use of max param
Fixes: #7336
The rgw_read_user_buckets() treated the max param as the max number of
entries to request in a single o...
Yehuda Sadeh
06:10 PM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Another way to state this: rbd images are defined such that if an object doesn't exist within the defined size of the... Dan Mick
11:20 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
There's a big difference between what happens if the objects get zapped versus rendered unreadable — if unreadable, t... Greg Farnum
10:54 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
OK. Now the recent rgw/xattr bug has shown that it is possible for a Ceph application to mess up objects so badly tha... Florian Haas
10:29 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Just the first; as you say, it's how we do TRIM and that implementation is very common behavior among storage systems. Greg Farnum
10:25 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
> Nonexistent objects are *defined* as zeros in RBD.
Erm, OK. I take it that this is also how TRIM/DISCARD is imp...
Florian Haas
10:14 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Nonexistent objects are *defined* as zeros in RBD. We'd have to distinguish between deliberately nonexistent and lost... Greg Farnum
10:10 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
Greg Farnum wrote:
> At present this is expected behavior. In order to raise an error we would need to know that the...
Florian Haas
09:42 AM Bug #7335: librbd does not raise "Object Not Found", instead returning NUL bytes
At present this is expected behavior. In order to raise an error we would need to know that the object was supposed t... Greg Farnum
09:32 AM Bug #7335 (Won't Fix): librbd does not raise "Object Not Found", instead returning NUL bytes
Test case attached. @test_remove_object@ fails. Prose description:
* Create RBD image
* Remove RADOS object belon...
Florian Haas
05:18 PM Revision 12f4688a (ceph): Merge pull request #1182 from ceph/wip-mds-cluster
mds: avoid sending duplicated discovers during recovery
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:34 PM Revision 105eac4f (ceph): Merge pull request #1177 from dachary/wip-erasure-code-command
erasure code command
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
04:17 PM Revision fdeb18e2 (ceph): mon: MDSMonitor: Forbid removal of first data pool
Because inodes from other pools now store their backtrace
on the first/default data pool, it is special and may not
b...
John Spray
04:14 PM Revision c7d265a9 (ceph): mon: OSDMonitor: Refuse to delete CephFS pools
To avoid confusing CephFS, don't permit deletion
of pools which are in use as the metadata pool
or any of the data po...
John Spray
02:58 PM Revision e80b084f (ceph): erasure-code: add ceph_erasure_code debug command
It loads a designated erasure-code plugin and calls its
methods. It is convenient to figure out and tune the number o...
Loïc Dachary
01:43 PM Revision 68e6dada (ceph): mds: avoid sending duplicated discovers during recovery
If MDS just entered the rejoin state, it should not kick discovers
because the discovers were just sent. Similarly, i...
Yan, Zheng
01:17 PM Revision bec12096 (ceph): erasure-code: benchmark moves to a dedicated directory
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
12:27 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
12:08 <@sage> alram joao wido: on issue 5804 i'm guessing ssh access and debugging is the trick,
altho...
Alexandre Marangone
12:13 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
really think that log message would go a long way toward helping. Dan Mick
11:58 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
I'm able to reproduce this fairly consistently on the Ceph VM Wido is mentioning.
Any information/debug settings t...
Alexandre Marangone
12:00 PM Bug #6685 (Fix Under Review): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present ...
David Zafman
11:21 AM Revision 0d6095ce (ceph): Merge pull request #1180 from dachary/wip-7313
mon: check cluster features before rule create-erasure
Reviewed-by: Sage Weil <sage@inktank.com>
Loïc Dachary
10:48 AM rgw Bug #7336 (Fix Under Review): rgw: limit on list buckets broken
Yehuda Sadeh
10:22 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
The limit param that is used in swift when listing buckets does not work correctly on latest master. Yehuda Sadeh
10:48 AM Revision ad8c6660 (ceph): mon: check cluster features before rule create-erasure
Encapsulate the logic used when creating an erasure coded pool into the
check_cluster_features helper.
check_cluster...
Loïc Dachary
10:38 AM Revision c40e4d4f (ceph): Merge pull request #1144 from dachary/wip-7146
osd crush rule create-erasure
gitbuilder is green/yellow for wip-7146
Reviewed-By: Christophe Courtaut <christophe....
Loïc Dachary
10:28 AM Subtask #7277: EC: on erasure pool creation, size needs to be fixed to K+M, size must not subsequ...
resolved with https://github.com/dachary/ceph/commit/c8c4cc6e81816069886af6bff968712993554759 and later amended by ht... Loïc Dachary
03:11 AM Subtask #7277 (Resolved): EC: on erasure pool creation, size needs to be fixed to K+M, size must ...
Loïc Dachary
09:22 AM Revision c8c4cc6e (ceph): mon: OSDMonitor: do not allow changing an erasure-coded pool's size
Fixes: 7277
Reviewed-by: Loic Dachary <loic@dachary.org>
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis
08:46 AM devops Bug #7334 (Resolved): ceph-disk: cannot run partprobe on used devices with EL6
commit:42900ff9da9f5adcac239a84ebf4d2e407c29699
https://bugzilla.redhat.com/show_bug.cgi?id=614357.
After ceph-...
Alexandre Marangone
07:16 AM Revision fdc967d8 (ceph): pybind: cosmetic changes to tests
* untabify
* re-indent
* 2014 to copyright notice
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
S...
Loïc Dachary
07:16 AM Revision 3370973f (ceph): pybind: osd crush rule create-erasure tests
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:16 AM Revision 5f9f300a (ceph): unittests: reduce paxos propose interval to increase speed
The MONs are stressed more often and there is less aggregation of the
pending requests. But the unit tests are only m...
Loïc Dachary
07:16 AM Revision 5bb4ca4d (ceph): vstart: load erasure code plugins from sources
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:16 AM Revision 9cb2215e (ceph): mon: osd-pool-create shows logs on error
extracting the logs would otherwise require a modification of the test
file to not clobber the directory containing t...
Loïc Dachary
07:16 AM Revision 0ca7ed80 (ceph): mon: osd-pool-create test initialization
* reduce the paxos propose interval speed up tests
* load erasure code plugins from sources
Reviewed-By: Christophe ...
Loïc Dachary
07:16 AM Revision d8d747d7 (ceph): mon: osd-pool-create test must kill -9
If a MON is stuck, kill -15 won't be enough and the test will hang
forever.
Reviewed-By: Christophe Courtaut <christ...
Loïc Dachary
07:16 AM Revision d40841cb (ceph): mon: osd-pool-create test enforce -e
Use
! grep foo || exit 1
instead of
grep foo && exit 1
so that all commands have a successful exit code. Ot...
Loïc Dachary
07:16 AM Revision 59ba03b3 (ceph): mon: test erasure code pool creation
* The sequence now is a) create ruleset, b) create pool.
* Check that not specifying the ruleset when an erasure code...
Loïc Dachary
07:16 AM Revision 428c75e1 (ceph): mon: osd-pool-create test EAGAIN when pending
Test that if the ruleset is found in the pending paxos proposal, the
pool creation will try again.
Reviewed-By: Chri...
Loïc Dachary
07:16 AM Revision 7b15cb1b (ceph): mon: osd-pool-create test no longer use hardcoded ruleset
For erasure-code the ruleset must be specified instead of relying on an
hardcoded value. Adapt the test to this for t...
Loïc Dachary
07:06 AM Revision 6caac92c (ceph): mon: pool creation helper for size
The size of the replicated pools are by default set to
osd_pool_default_size but it may vary depending on the pool ty...
Loïc Dachary
07:06 AM Revision 61c45fe0 (ceph): mon: pool create helper for crush ruleset
The crush ruleset of the replicated pools are by default set to
osd_pool_default_crush_replicated_ruleset but it may ...
Loïc Dachary
07:06 AM Revision caefb8a2 (ceph): mon: erasure code plugin loader helper
The get_erasure_code helper loads the erasure code plugin found in the
erasure-code-plugin string of the properties a...
Loïc Dachary
07:06 AM Revision 8259e51d (ceph): mon: compute the size of erasure-coded pools
It is K+M ( data chunks + coding chunks ) as returned by the
get_chunk_count() method of the erasure code plugin.
ht...
Loïc Dachary
07:06 AM Revision 1acc73bb (ceph): mon: compute the ruleset of erasure-coded pools
The default ruleset of an erasure coded pool may depend on the
parameters used to configure it. In the case of a pyra...
Loïc Dachary
07:06 AM Revision cb39b136 (ceph): mon: osd crush rule create-erasure
Delegates the creation of the rule to the erasure code plugin associated
with the specified pool.
Reviewed-By: Chris...
Loïc Dachary
07:06 AM Revision ad09023e (ceph): pybind: fix tests that do not fail as expected
A missing argument make the test fail indeed, but the intended test is
to demonstrate something else ( either charact...
Loïc Dachary
07:06 AM Revision 2dca7371 (ceph): erasure-code: the plugin is in a convenience library
So that it can be used by mon without linking with libosd
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmai...
Loïc Dachary
07:06 AM Revision 6ca9b246 (ceph): erasure-code: add crush ruleset creation API
Because only the erasure code plugin knows enough to create a ruleset
that is best suited for a given set of paramete...
Loïc Dachary
07:06 AM Revision f019c906 (ceph): erasure-code: implement example create_ruleset
And the associated unit tests.
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic ...
Loïc Dachary
07:06 AM Revision 02869f8d (ceph): erasure-code: implement ErasureCodeJerasure::create_ruleset
It is based on CrushWrapper::add_simple_ruleset, using a "default" root
and "host" failure domain by default. They ca...
Loïc Dachary
07:06 AM Revision cc66c6a0 (ceph): erasure-code: test ErasureCodeJerasure::create_ruleset
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:06 AM Revision 0cac2025 (ceph): mon: helper for pool properties parsing
Add the prepare_pool_properties to convert the properties vector into a
properties map suitable for either initializi...
Loïc Dachary
07:06 AM Revision 9d766cab (ceph): mon: no default ruleset except for replicated pools
Remove the hardcoded default ruleset for erasure coded pools and only
keep it for replicated pools. Move the logic up...
Loïc Dachary
07:02 AM CephFS Feature #7319: qa: multimds, no failure
Enable the marginal suite multi-mds tests. Greg Farnum
06:59 AM CephFS Feature #7316: improve mds state dumps (memory usage, completeness)
https://wiki.ceph.com/Planning/Sideboard/mds%3A_dumpability Greg Farnum
06:52 AM CephFS Feature #7333 (In Progress): client: evaluate multiple O_APPEND writers
This needs done for kclient and libcephfs. Extending the size of the file is potentially racy with updates to inode's... Sage Weil
06:50 AM CephFS Fix #7109 (Fix Under Review): disallow removing the first data pool
https://github.com/ceph/ceph/pull/1173 Greg Farnum
06:20 AM Revision a8fcffb9 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
06:18 AM Revision 2bcc6006 (ceph): Implement the rest of the checks for automatic pg scrubbing.
osd_scrub_pgs now:
1.) Insures that all pgs are clean and active.
2.) Performs the scrub of all OSDs.
3.) Waits until...
Warren Usui
05:55 AM Revision e47e49d2 (ceph): doc/release-notes: v0.77 draft notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:50 AM devops Bug #7331 (Resolved): invalid logging call in ceph-deploy
... Alfredo Deza
05:40 AM Revision 2c504ea1 (ceph): doc/release-notes: v0.76
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:22 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Wido den Hollander wrote:
> > Florian Haas wrote:
> > > Just for clarification: when you say...
Wido den Hollander
05:02 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Wido den Hollander wrote:
> Florian Haas wrote:
> > Just for clarification: when you say "it" blocked forever, are ...
Florian Haas
02:34 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Wido den Hollander wrote:
> > > * Did you only test with an RBD storage *pool*, or do you als...
Wido den Hollander
05:12 AM Revision 60ca6f69 (ceph): client: fix warnings
client/Client.cc: In member function 'int Client::_read(Fh*, int64_t, uint64_t, ceph::bufferlist*)':
warning: client/...
Sage Weil
04:26 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Josh Durgin wrote:
> Wido den Hollander wrote:
> > Josh Durgin wrote:
> > > It makes sense to add as an option for...
Wido den Hollander
03:37 AM Revision 9b2b2c28 (ceph): misc.py: helper roles_to_remotes for generic use
roles_to_remotes will take a config key, 'roles' by default,
and search cluster.remotes for those roles, returning a ...
Dan Mick
03:22 AM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
"pull request":https://github.com/ceph/ceph/pull/1180
Loïc Dachary
03:00 AM Subtask #7146 (Resolved): implement osd crush rule create-erasure
Loïc Dachary
03:00 AM Revision 1829d2c9 (ceph): librados: add timeout to wait_for_osdmap()
This is used by several pool operations independent of the objecter,
including rados_ioctx_create() to look up the po...
Josh Durgin
02:57 AM Revision 0dcceff1 (ceph): conf: add options for librados timeouts
These will be implemented in subsequent patches.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
01:50 AM Revision eb9ffd5a (ceph): mon: use 'mds set inline_data ...' for enable/disable of inline data
This makes the management interface a bit more consistent.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:50 AM Revision 8e30db8f (ceph): rest: add a few rest api tests
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:50 AM Revision a23a2c8f (ceph): os/KeyValueStore: fix warning
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:50 AM Revision 408b0c8e (ceph): mon: fix 'mds set allow_new_snaps'
We had already added this as a flag (set/unset) when I generalized the
'mds set_max_mds' to be 'ceph mds set <var> <v...
Sage Weil
01:48 AM Revision 3e56cc08 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
12:37 AM Revision 33338c5c (ceph): Merge pull request #1179 from dachary/wip-force-proposal
mon: do not force proposal when no osds
Backport: emperor, dumpling
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:25 AM Revision e5ed1b29 (ceph): mon: do not force proposal when no osds
If there are no OSDs, there is no need to propose to paxos. It does not
hurt on a production cluster but it matters w...
Loïc Dachary

02/03/2014

11:06 PM Revision 9f4edb61 (ceph): Merge pull request #1151 from ceph/wip-performance-configs
Performance improvements and config options
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Josh Durgin <jo...
Gregory Farnum
10:39 PM Revision f9b9f524 (ceph): Merge branch 'next'
Ken Dreyer
09:14 PM Bug #7329 (Resolved): osd: LibRadosTier.FlushTryFlushRaces failures
sage-2014-02-03_16:41:22-rados:basic-wip-agent-testing-basic-plana/64994... Sage Weil
08:03 PM Feature #6507 (In Progress): librados shouldn't block indefinitely when cluster doesn't respond
Wido den Hollander wrote:
> Josh Durgin wrote:
> > It makes sense to add as an option for librados users like the l...
Josh Durgin
12:45 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Josh Durgin wrote:
> It makes sense to add as an option for librados users like the libvirt storage pool. The defaul...
Wido den Hollander
12:37 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
didn't mean to change these Josh Durgin
12:21 PM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
It makes sense to add as an option for librados users like the libvirt storage pool. The default is blocking for thin... Josh Durgin
02:41 AM Feature #6507: librados shouldn't block indefinitely when cluster doesn't respond
Dan Mick wrote:
> 1) I solved this in the python bindings with a separate timer thread, which is always possible in ...
Wido den Hollander
06:26 PM Revision 3b990136 (ceph): v0.76
Ken Dreyer
06:26 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
I just wanted to inform you that since 0.7, I don't have to patch and recompile ceph-mds to get it to start every upd... Jérôme Poulin
05:22 PM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
Sage Weil
06:07 PM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
Running ceph osd reweight-by-utilization resulted in stuck pgs.... Tyler Brekke
05:30 PM rbd Bug #7327 (Resolved): Assertion failure in rbd_object_request_destroy()
Running Debian kernel 3.12.6 (debian package linux-image-3.12-1-amd64_3.12.6-2_amd64) inside a Xen DomU, we occasiona... Nathaniel Filardo
05:28 PM CephFS Bug #6623 (Resolved): mds: update backtraces on existing clusters
Sage Weil
05:27 PM CephFS Feature #1448 (Resolved): test hadoop on sepia
Sage Weil
05:25 PM CephFS Bug #4489 (Can't reproduce): ceph fs hangs on file stat
Sage Weil
05:25 PM CephFS Bug #5485 (Can't reproduce): failed cifs mount
Sage Weil
05:23 PM CephFS Bug #4685 (Can't reproduce): BUG: unable to handle kernel NULL pointer dereference at
Sage Weil
05:20 PM CephFS Bug #5753 (Duplicate): ceph-fuse: segfault when getting back a traceless rename op
Sage Weil
05:19 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
Sage Weil
05:18 PM CephFS Bug #4909 (Can't reproduce): mds: stalled/stuck directory (standby)
Sage Weil
05:02 PM Revision c301ec68 (ceph): client: use 64-bit value in sync read eof logic
The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk...
Sage Weil
05:02 PM Revision f2684c93 (ceph): client: use 64-bit value in sync read eof logic
The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk...
Sage Weil
05:01 PM CephFS Feature #3863: implement a tool to lookup inode numbers without holding their path
Sage Weil
05:01 PM CephFS Feature #3863 (Resolved): implement a tool to lookup inode numbers without holding their path
Sage Weil
05:00 PM CephFS Feature #1693 (Resolved): libcephfs: Support TRIM (hole punching)
Sage Weil
04:59 PM CephFS Feature #3867 (Resolved): optionally do not use an anchor table
Sage Weil
04:58 PM CephFS Cleanup #2177 (Resolved): mds: play nicely with omap
Sage Weil
04:58 PM CephFS Feature #7326 (New): qa: fix flock tests
Sage Weil
04:57 PM CephFS Feature #7325 (New): mds: tool to examine (later, manipulate) dirfrag objects
Sage Weil
04:57 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
Sage Weil
04:56 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
Sage Weil
04:55 PM CephFS Feature #7322 (New): qa: inline data + thrashing
Sage Weil
04:55 PM CephFS Feature #7321 (Duplicate): qa: multimds thrasher
Sage Weil
04:54 PM CephFS Feature #7320 (Fix Under Review): qa: thrash directory fragmentation
Define killpoints for directory fragmentation. Create tests as in https://github.com/ceph/ceph/pull/28004 Sage Weil
04:54 PM CephFS Feature #7319 (Resolved): qa: multimds, no failure
Sage Weil
04:54 PM CephFS Feature #7318 (Duplicate): qa: ceph-fuse + sync mode
Sage Weil
04:54 PM Revision 7ff2b541 (ceph): client: use 64-bit value in sync read eof logic
The file size can jump to a value that is very much larger than our current
position (for example, it could be a disk...
Sage Weil
04:53 PM CephFS Feature #7317 (Resolved): mds: behave with fs fills (e.g., allow deletion)
Sage Weil
04:53 PM CephFS Feature #7316 (New): improve mds state dumps (memory usage, completeness)
Sage Weil
04:52 PM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
Sage Weil
04:40 PM Cleanup #7314 (In Progress): remove dead code from OSDMonitor::should_propose
"located here":https://github.com/ceph/ceph/blob/v0.75/src/mon/OSDMonitor.cc#L763 Loïc Dachary
02:47 PM Subtask #7313 (Resolved): erasure-code: rule create-erasure requires CEPH_FEATURE_CRUSH_V2
before asking the erasure-code plugin to create the rule, check if CEPH_FEATURE_CRUSH_V2 is supported by all daemons Loïc Dachary
12:59 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Wido den Hollander wrote:
> > * Did you only test with an RBD storage *pool*, or do you also have *domains* running ...
Florian Haas
12:46 PM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT ...
Wido den Hollander
10:55 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Thanks Wido. As explained in the original description we went off 1.1.1 here due to a SIGABRT bug.
Two questions:
...
Florian Haas
06:00 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
So I've played around with this today and I can't fully reproduce it.
I have a machine running with libvirt 1.1.1-...
Wido den Hollander
01:48 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Florian Haas wrote:
> Right, but why should the qemu process stall if all the MONs are available, and only a few RBD...
Wido den Hollander
01:42 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Right, but why should the qemu process stall if all the MONs are available, and only a few RBDs are shot? (if they ar... Florian Haas
12:56 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
I'm going to try to figure this out, I'm setting up a test env right now.
I think it's libvirt which can't handle ...
Wido den Hollander
12:32 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
With Wido having confirmed that the issue exists, I'm bumping the severity to critical.
Wido, if you could offer y...
Florian Haas
11:26 AM Bug #7178 (Resolved): sample.ceph.conf needs update
commit:e268e9562dd0831fe40702e56bfbdf8f6cb80b1a Josh Durgin
09:45 AM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Work-in-progress kmod packaging here: https://github.com/kdreyer-inktank/ceph-kmod-rpm
Originally I'd planned to b...
Ken Dreyer
08:32 AM devops Bug #7312 (Resolved): ERROR: Running exception handlers
Failed in:
teuthology-2014-01-31_19:35:02-upgrade:small-next-testing-basic-vps/61907
logs in http://qa-proxy.ceph...
Yuri Weinstein
07:37 AM devops Bug #7311 (Closed): GPG/packaging failures
apt complained throughout the install process... Alfredo Deza
07:25 AM rbd Bug #7310 (Can't reproduce): rbd snap unprotect test failing
... Alfredo Deza
06:51 AM CephFS Bug #5411 (Resolved): teuthology: bad object dereference
Sage Weil
05:21 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Greg Farnum wrote:
> Which op threads and filestore threads are you talking about? The splitting happens whenever th...
Guang Yang
01:16 AM Revision 021d94ca (ceph): fs/basic: test with inline data
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/02/2014

05:40 PM Revision e4ff4720 (ceph): Merge remote-tracking branch 'gh/next'
Conflicts:
src/mon/OSDMonitor.cc
src/osd/OSDMap.h
Sage Weil
05:19 PM Feature #7058 (Fix Under Review): osd primary affinity
Sage Weil
05:18 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
05:16 PM Revision 29eac1d1 (ceph): Merge remote-tracking branch 'gh/wip-inline'
Passed fs suite, sage-2014-02-01_22:18:10-fs-wip-inline-testing-basic-plana,
modulo a snap test error in the suite.
...
Sage Weil
07:53 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
Hey Wido,
thanks for responding to this, and doubly for doing so on a weekend. Much appreciated.
> I'm aware of...
Florian Haas
06:30 AM Subtask #7307 (Rejected): erasure-code: chunk_size must not be architecture dependant
The "get_chunk_size() method":https://github.com/ceph/ceph/blob/4c4e1d0d470beba7690d1c0e39bfd1146a25f465/src/osd/Eras... Loïc Dachary
06:05 AM Revision be3ea71c (ceph): valgrind: another tcmalloc suppression
With this I can run a simple job with a normal build (not
notcmalloc) and valgrind does not complain. Fingers crosse...
Sage Weil
05:51 AM Subtask #7146 (Fix Under Review): implement osd crush rule create-erasure
"work in progress":https://github.com/ceph/ceph/pull/1144 Loïc Dachary
05:42 AM Subtask #7277 (In Progress): EC: on erasure pool creation, size needs to be fixed to K+M, size mu...
"setting the size of the pool":https://github.com/ceph/ceph/pull/1144#issuecomment-33899812 Loïc Dachary
05:00 AM Revision 9c3a4d8a (ceph): Merge pull request #1165 from mo22/client_fuse_multithreading
client: ceph-fuse use fuse_session_loop_mt to allow multithreaded operat...
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil

02/01/2014

10:57 PM Feature #7288: Deep-scrub throttle
Yes but if you have one scrub per OSD and you have a replication of 3. It could be easily happen that one OSD has 3 o... Stefan Priebe
09:01 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
ubuntu@teuthology:/a/teuthology-2014-01-31_23:00:01-rados-master-testing-basic-plana/62166 Sage Weil
02:22 PM Bug #7178: sample.ceph.conf needs update
Fully merged by Josh Durgin -- thanks.
This bug can be closed now (I have no rights to do that).
Dmitry Smirnov
11:40 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
I'm aware of this. It's not only with RBD though, the same happens with libvirt when you use NFS and a export is dead... Wido den Hollander
05:58 AM Revision 2f85b8c8 (ceph): doc: Incorporated feedback.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:33 AM Bug #7216: ASSERT AuthMonitor::update_from_paxos on 0.72.2
I'm sorry to say, all my data is considered lost right now. I like Ceph architecture very much but cannot use due to ... Grigory Gorelov

01/31/2014

11:54 PM Revision 27b5f2b8 (ceph): common/shared_cache.hpp: avoid list::size()
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:54 PM Revision ee48c871 (ceph): common/shared_cache.hpp: compact to a single lookup where possible
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:54 PM Revision 03f7f771 (ceph): Throttler: optionally disable use of perfcounters
These can be expensive enough that we want to disable them. We're already
mostly set up for it to be optional, so jus...
Greg Farnum
11:54 PM Revision 98ae0592 (ceph): Throttle: Turn off throttle based on max bytes
If max throttle bytes is 0, throttle should not be doing anything.
This check is introduced in the beginning of each ...
Somnath Roy
11:54 PM Revision 8e194888 (ceph): TrackedOp: optionally disable the actual tracking operations
To avoid op contention on global locks, optionally disable the
op tracking. Create an "osd_op_tracker" config to cont...
Greg Farnum
11:54 PM Revision 5fde828d (ceph): cmp.h: boost tuple comparison is replaced by regular comparison
Profiler was showing this boost tuple comparison is expensive.
So, it is replaced by regular comparison.
Signed-off-...
Somnath Roy
11:54 PM Revision 684e5c45 (ceph): Pipe, cephx: Message signing under config option
The config option was present earlier but the option is checked
not in the beginning, so, it was doing some stuff. No...
Somnath Roy
11:29 PM Revision e8717163 (ceph): Scrub osds when ceph task finishes
Fixes: 7198
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
10:32 PM Revision 183deb89 (ceph): osd: do not send peering messages during init
Do not send any peering messages while we are still working our way
through init().
Fixes: #7093
Signed-off-by: Sage...
Sage Weil
10:20 PM Revision b717e11b (ceph): Merge pull request #1174 from alram/master
doc: rgw: el6 documentation fixes John Wilkins
09:55 PM Revision ee4cfda1 (ceph): doc: rgw: el6 documentation fixes
- fix a couple of typo for repo configuration and service restart
- the ceph package must be installed on RPM distro ...
Alexandre Marangone
09:41 PM Revision c1bc7fcc (ceph): Merge pull request #180 from ceph/wip-7278
install.py: look for 'local' in config directly, don't warn if not found Zack Cerza
09:41 PM Revision 8213ebbd (ceph): Merge pull request #183 from ceph/wip-enhance
Wip enhance Zack Cerza
09:30 PM Revision a321b6e7 (ceph): README.rst: describe new pp object and unlock_on_failure option.
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
09:12 PM Revision 915cb5d4 (ceph): Merge pull request #181 from ceph/wip-thrash-exception
Fix MDS wait when get_mds_status returns None Zack Cerza
09:07 PM Revision 1845a5ab (ceph): interactive.py: add handy "pp" for prettyprinting at the prompt
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
09:07 PM Revision 77ec4311 (ceph): internal.py: add global config key 'unlock_on_failure'
When testing new tasks, it's a drag to have to keep manually unlocking
the targets. Default behavior is to keep them...
Dan Mick
08:53 PM Revision b80e5102 (ceph): Make libvirt import optional (OS X)
John Spray
08:49 PM Revision aaf9b51c (ceph): Fix MDS wait when get_mds_status returns None
John Spray
08:35 PM Revision dffe6019 (ceph): Merge pull request #1162 from ceph/wip-5997
Fixes: #5997
Reviewed-by: Samuel Just <sam.just@inktank.com>
David Zafman
07:08 PM Feature #7288: Deep-scrub throttle
As it is we have config value osd_max_scrubs which defaults to 1. This should cause each OSD to only scrub a single ... David Zafman
12:13 PM Feature #7288 (Resolved): Deep-scrub throttle
Currently, it appears many PGs are allowed to enter a deep-scrubbing state. Due to the more intensive nature of a dee... Brian Andrus
07:00 PM Revision 37447e75 (ceph): osd: Add scrub_supported() backend interface
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
07:00 PM Revision f9128e89 (ceph): osd: Move PG::_scan_list() to backend as ReplicatedBackend::be_scan_list()
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
07:00 PM Revision 34eb549c (ceph): osd: Move the rest of scrubbing routines to the backend
Move enum scrub_error_type to osd_types.h
Move PG::_compare_scrub_objects to ReplicatedBackend::be_compare_scrub_obje...
David Zafman
07:00 PM Revision e1bfed52 (ceph): common: buffer::ptr::cmp() is a const function
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
07:00 PM Revision ce1ea619 (ceph): osd: Change be_scan_list() arg to const
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
07:00 PM Revision 48fbccec (ceph): osd: Change some be_compare_scrub_objects() args to const
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
03:57 PM Revision 560f5f1f (ceph): OSDMap: fix deepish_copy_from
Start with a shallow copy!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d0f13f54146694a197...
Sage Weil
03:57 PM Revision d5080799 (ceph): OSDMonitor: use deepish_copy_from for remove_down_pg_temp
This is a backport of 368852f6c0a884b8fdc80a5cd6f9ab72e814d412.
Make a deep copy of the OSDMap to avoid clobbering t...
Sage Weil
03:57 PM Revision 61914d82 (ceph): OSDMap: deepish_copy_from()
Make a deep(ish) copy of another OSDMap. Unfortunatley we can't make the
compiler-generated copy operator/constructo...
Sage Weil
03:19 PM Revision 802692ed (ceph): os/KeyValueStore: fix warning
./os/KeyValueStore.h: In member function ‘std::string KeyValueStore::strip_object_key(uint64_t)’:
warning: ./os/KeyVa...
Sage Weil
03:09 PM Bug #7093 (Pending Backport): osd: peering can send messages prior to auth
Backported this to dumpling in commit:183deb899bc6b1b7b2a1ec639425e45786e56b01
Do we also want to backport it to e...
Greg Farnum
03:00 PM Revision f8316f1a (ceph): Merge branch 'wip-inline' of git://github.com/kylinstorage/ceph
Conflicts:
src/include/ceph_features.h
Sage Weil
02:39 PM Documentation #6547: should document magic data/journal partition types
No, thanks, fixed Dan Mick
02:34 PM Documentation #6547: should document magic data/journal partition types
hmm, is this meant to be in the calamari product? John Spray
02:13 PM devops Feature #7293 (Resolved): packaging: enable qemu to find librbd on rhev or rhel-osp
qemu-kvm-rhev will dynamically load librbd if /usr/lib64/qemu/librbd.so.1 exists.
The librbd package needs to add ...
Josh Durgin
02:02 PM Subtask #7292 (Rejected): erasure code: plugin backward compatibility
The goal is to allow Giant to install upgraded backward compatible erasure-code plugins so that pools created with Fi... Loïc Dachary
02:01 PM Feature #7291 (New): EC: add mechanism for mon to detect and whitelist EC plugins which are globa...
Otherwise, we might end up with a situation where the mon believes an EC plugin is usable and creates such a pool, bu... Samuel Just
01:58 PM Feature #7035: cachepool: agent: blocking eviction (when cache pool is 'full')
Ian Colle
01:57 PM Feature #7034: cachepool: agent: basic eviction
Ian Colle
01:56 PM Feature #7033: cachepool: agent: trivial flushing
Ian Colle
01:53 PM Fix #7215 (Resolved): mon: prevent old monitors which do not support new encodings from joining t...
This is merged (and so are some fixes around it), just didn't get the automated tests debugged but they can go elsewh... Greg Farnum
01:27 PM devops Feature #6882 (Resolved): downburst: list available distro/versions
This is done in branch wip-list-distros which was merged a while ago. Sandon Van Ness
01:24 PM devops Feature #7047 (In Progress): rhel7: build process for rbd.ko, ceph.ko kernel modules
Ian Colle
01:24 PM devops Feature #7046 (In Progress): rhel7: gitbuilder for rbd.ko, ceph.ko kernel modules
Ian Colle
01:22 PM devops Feature #7094 (Resolved): f20 gitbuilder
Ian Colle
01:22 PM devops Fix #7095 (Resolved): fix f19 gitbuilder
Ian Colle
01:08 PM rgw Feature #6338: rgw: better manifest scaling
Currently a gateway object includes in the manifest a list of all the rados objects that it uses. Every time we acces... Yehuda Sadeh
12:54 PM rgw Feature #6338 (In Progress): rgw: better manifest scaling
Ian Colle
12:54 PM rgw Feature #6339 (In Progress): rgw: compact manifest data
Ian Colle
12:32 PM Subtask #5861 (Resolved): Refactor scrub to use PGBackend methods
dffe6019c3698ca1661c94984df9629241c3e1ef David Zafman
12:31 PM Feature #5997 (Resolved): EC: [link] Refactor scrub to use PGBackend methods
dffe6019c3698ca1661c94984df9629241c3e1ef David Zafman
10:37 AM Feature #7287 (New): Make units of measurement constant and definable in ceph commands
From the customer:
It would be great if it were possible to lock the units for ceph reporting
ceph -w /ceph -s ...
Brian Andrus
10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
Samuel Just
10:30 AM Feature #7286 (Closed): EC: ReplicatedPG needs to maintain a pending_last_update tracking the mos...
While ReplicatedBackend always calls log_operation from within the call to log_operation, this won't be true of ECBac... Samuel Just
10:28 AM Feature #7285 (Rejected): EC: ReplicatedPG needs to maintain a pending_last_update tracking the m...
This is necessary because though with ReplicatedBackend, log_operation will be called from within the submit_transact... Samuel Just
10:22 AM Feature #7284 (Resolved): EC: pg_pool_t should include stripe_width information set at pool creat...
Samuel Just
10:12 AM Bug #7256: ceph osd crashed at ReplicatedPG::trim_object on next
maybe dup of #6101 ? Daniel Poelzleithner
09:59 AM devops Bug #7283 (Resolved): centos 6 - gitbuilder mod_ssl broken dependency
From the doc, I'm using http://gitbuilder.ceph.com/apache2-rpm-centos6-x86_64-basic/ref/master to install httpd on th... Alexandre Marangone
09:49 AM CephFS Fix #7109: disallow removing the first data pool
https://github.com/ceph/ceph/pull/1173 John Spray
09:47 AM rbd Bug #7282 (Resolved): Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connect...
This isn't fully confirmed yet, because we haven't found a reliable way to reproduce. In short, it seems that if you ... Florian Haas
07:49 AM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
> "2014-01-31 05:32:26.722560 osd.5 10.214.131.11:6810/5928 5 : [ERR] 3.12 3
> tried to pull 1518ccf2/plana1...
Sage Weil
07:47 AM Revision c489e440 (ceph): install.py: look for 'local' in config directly, don't warn if not found
Fixes: #7278
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
05:01 AM Revision 3a53d6de (ceph): Merge pull request #1171 from ceph/wip-osdmap-features
mon: encode full osdmap with same feature bits as the incremental
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil
12:47 AM rbd Bug #7076 (Resolved): rbd: check for watchers before removing an image
Ilya Dryomov
12:04 AM Revision abcc17bf (ceph): Merge pull request #1169 from dachary/wip-ceph-disk
Reviewed-by: Sage Weil <sage.weil@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
 

Also available in: Atom