]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Yan, Zheng [Mon, 14 Oct 2013 08:34:26 +0000 (16:34 +0800)]
mds: flock: fix F_GETLK
fixes #5025
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
John Wilkins [Fri, 11 Oct 2013 22:08:22 +0000 (15:08 -0700)]
doc: Created new index to incorporate side-by-side deb/rpm installs.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:07:40 +0000 (15:07 -0700)]
doc: Created installation doc for Yum priorities. Ceph-specific packages need it.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:07:08 +0000 (15:07 -0700)]
doc: Created new QEMU install for RPMs with provision for Ceph-specific packages.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:06:30 +0000 (15:06 -0700)]
doc: Created new QEMU install for debian.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:06:02 +0000 (15:06 -0700)]
doc: Added new libvirt install for RPM.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:05:36 +0000 (15:05 -0700)]
doc: Created new libvirt install for debian/ubuntu.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:05:08 +0000 (15:05 -0700)]
doc: Removed Gatway from Ceph Object Storage. Added Yum repo information.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:03:34 +0000 (15:03 -0700)]
doc: Moved installation portion to the installation section.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 22:02:38 +0000 (15:02 -0700)]
doc: Moved installation portion to the installation section.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 11 Oct 2013 21:04:36 +0000 (14:04 -0700)]
doc: Fixed hyperlinks. Cleanup of old references to Chef.
fixes: #6493
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Sage Weil [Thu, 10 Oct 2013 10:29:37 +0000 (03:29 -0700)]
test/filestore/run_seed_to_range.sh: fix -d syntax
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 11 Oct 2013 14:33:35 +0000 (07:33 -0700)]
Merge pull request #702 from ceph/wip-4405
mds: fix infinite loop of MDCache::populate_mydir().
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
John Wilkins [Thu, 10 Oct 2013 21:31:37 +0000 (14:31 -0700)]
doc: Minor correction.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Thu, 10 Oct 2013 19:21:34 +0000 (12:21 -0700)]
doc: Merge cleanup.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Thu, 10 Oct 2013 19:20:37 +0000 (12:20 -0700)]
doc: minor clean up.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Thu, 10 Oct 2013 18:47:56 +0000 (11:47 -0700)]
doc: Update from wip-doc-quickstart branch.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Yan, Zheng [Thu, 10 Oct 2013 02:35:48 +0000 (10:35 +0800)]
mds: fix infinite loop of MDCache::populate_mydir().
make MDCache::populate_mydir() only fetch bare-bone stray dirs.
After all stray dirs are populated, call MDCache::scan_stray_dir(),
it fetches incomplete stray dirs.
Fixes: #4405
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Sandon Van Ness [Tue, 8 Oct 2013 18:58:57 +0000 (11:58 -0700)]
Go back to $PWD in fsstress.sh if compiling from source.
Although fsstress was being called with a static path the directory
it was writing to was in the current directory so doing a cd to the
source directory that is made in /tmp and then removing it later
caused it to be unable to write the files in a non-existent dir.
This change gets the current path first and cd's back into it after
it is done compiling fsstress.
Issue #6479.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Reviewed-by: Alfredo Deza <alfredo.deza@inktank.com>
Sage Weil [Tue, 8 Oct 2013 14:52:42 +0000 (07:52 -0700)]
Merge pull request #700 from dachary/master
doc: fix openstack rbd installation command
Loic Dachary [Tue, 8 Oct 2013 10:02:44 +0000 (12:02 +0200)]
doc: fix openstack rbd installation command
This cannot work because client.volumes.key is not a command
ssh {your-compute-host} client.volumes.key
replace with a tee to allow for copy/paste as well as using the
cat client.volumes.key
in the following lines.
Signed-off-by: Loic Dachary <loic@dachary.org>
David Zafman [Tue, 8 Oct 2013 00:05:01 +0000 (17:05 -0700)]
Merge pull request #699 from dachary/wip-ghobject-assert
os: stronger assert on FileStore::lfn_open
Reviewed-by: David Zafman <david.zafman@inktank.com>
Loic Dachary [Mon, 7 Oct 2013 23:15:41 +0000 (01:15 +0200)]
os: stronger assert on FileStore::lfn_open
Signed-off-by: Loic Dachary <loic@dachary.org>
Greg Farnum [Mon, 7 Oct 2013 21:40:42 +0000 (14:40 -0700)]
Merge branch 'next'
Gregory Farnum [Mon, 7 Oct 2013 21:15:19 +0000 (14:15 -0700)]
Merge pull request #697 from dachary/master
This lets "make check" pass, so I like it.
Reviewed-by: Greg Farnum <greg@inktank.com>
Loic Dachary [Mon, 7 Oct 2013 21:05:01 +0000 (23:05 +0200)]
common: unintended use of the wrong bloom_filter prototype
For encoding/decoding test purposes. The generate_test_instances should
be improved to cover more encoding/decoding cases.
Signed-off-by: Loic Dachary <loic@dachary.org>
Greg Farnum [Mon, 7 Oct 2013 20:11:21 +0000 (13:11 -0700)]
ReplicatedPG: copy: use aggregate return code instead of individual Op return
It appears that the OSD is not filling in the individual return codes, and they
should be equivalent for all purposes we care about here (the only Op we are
doing is the copy-get, and if it fails we are getting its failure code).
Reported-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Mon, 7 Oct 2013 12:22:20 +0000 (05:22 -0700)]
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 the block. Translate
ENOENT -> 0 to compensate.
Fix the same error in _rmattrs().
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
Gregory Farnum [Mon, 7 Oct 2013 15:56:46 +0000 (08:56 -0700)]
Merge pull request #610 from ceph/wip-optracker
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Mon, 7 Oct 2013 11:37:20 +0000 (04:37 -0700)]
Merge remote-tracking branch 'gh/next'
João Eduardo Luís [Mon, 7 Oct 2013 11:31:36 +0000 (04:31 -0700)]
Merge pull request #695 from ceph/wip-mon-auth
fix mon double-free when dropping unhandled messages, and allow "get monmap" messages to go through without authenticating for MonCliente::get_monmap_privately()
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil [Mon, 7 Oct 2013 07:28:35 +0000 (00:28 -0700)]
Merge pull request #693 from ceph/wip-bloom
bloom_filter improvements, cleanups
Reviewed-by: Loic Dachary <loic@dachary.org>
Sage Weil [Sun, 6 Oct 2013 22:17:19 +0000 (15:17 -0700)]
mon: allow MMonGetMap without authentication
This is used by the MonClient::get_monmap_privately() helper.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 6 Oct 2013 22:12:57 +0000 (15:12 -0700)]
mon: do not put() unhandle message
If we return false because we aren't handling a message, we should not put
the ref. This fixes a double-free.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 6 Oct 2013 17:28:20 +0000 (10:28 -0700)]
common/bloom_filter: add a few assertions and checks for bit_table_ == NULL
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 6 Oct 2013 17:22:41 +0000 (10:22 -0700)]
common/bloom_filter: simplify compressible_bloom_filter encode/decode/dump
Re-use bloom_filter for this, as per Loic's suggestion. Much nicer!
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 5 Oct 2013 05:49:41 +0000 (22:49 -0700)]
common/bloom_filter: fix compress; improve argument
Fix bug in compress() when compressing to less than .5 or original.
Make the argument have sane units (target size relative to current size;
not a precentage reduction).
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 6 Oct 2013 17:18:30 +0000 (10:18 -0700)]
common/bloom_filter: fix estimated element count for compressed filters
We need to compensate for the fact that there are fewer bits than there
used to be.
This is a crappy adjustment; it is non-linear. It's clone enough for now,
though.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sun, 6 Oct 2013 04:08:44 +0000 (21:08 -0700)]
doc/release-notes: v0.70
Note that a bunch of stuff we thought would go in 0.70 is actually in 0.69,
so the update/release notes were adjusted accordingly.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 5 Oct 2013 05:50:58 +0000 (22:50 -0700)]
common/bloom_filter: methods for density, approx unique element counts
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 5 Oct 2013 05:50:30 +0000 (22:50 -0700)]
common/bloom_filter: remember original target size
This isn't strictly needed for core functionality, but it is convenient to
know.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 3 Oct 2013 23:30:29 +0000 (16:30 -0700)]
common/bloom_filter: drop raw_table_size_ member
We were storing table_size_ and raw_table_size_, where one is the size in
bits and the other is the size in bytes. This is silly. Store only the
size in bytes.
Also, bytes are always 8 bits, so use bit shifts and drop some of that
silliness too.
Move the member declarations to the top of the class so you read them
before the methods.
Fix some annoying whitespace.
Avoid allocating a 0-length array.
Mark the encoding incompatible with v1.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 3 Oct 2013 21:39:47 +0000 (14:39 -0700)]
common/bloom_filter: make compressible_bloom_filter encodable
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Sat, 5 Oct 2013 05:06:04 +0000 (22:06 -0700)]
mon/PGMap: make generated test instances obey new invariant
As of
091809b8149c7595cbcca439c5b8b75a0c42efe1 we keep an osd_map epoch
for any osd_stat update, and assert as much.
Signed-off-by: Sage Weil <sage@inktank.com>
Gary Lowell [Sat, 5 Oct 2013 02:11:36 +0000 (02:11 +0000)]
Merge branch 'next'
Sage Weil [Fri, 4 Oct 2013 23:49:41 +0000 (16:49 -0700)]
doc/release-notes: v0.67.4
Signed-off-by: Sage Weil <sage@inktank.com>
Greg Farnum [Fri, 4 Oct 2013 23:45:38 +0000 (16:45 -0700)]
Makefile: add include/histogram.h to noinst_HEADERS
Signed-off-by: Greg Farnum <greg@inktank.com>
Gregory Farnum [Fri, 4 Oct 2013 22:58:50 +0000 (15:58 -0700)]
Merge pull request #676 from ceph/wip-start-copy
Reviewed-by: Samuel Just <sam.just@inktank.com>
David Zafman [Fri, 4 Oct 2013 21:59:11 +0000 (14:59 -0700)]
Merge pull request #667 from ceph/wip-6143
Reviewed-by: Sage Weil <sage@inktank.com>
David Zafman [Mon, 30 Sep 2013 22:53:35 +0000 (15:53 -0700)]
common, os: Perform xattr handling based on detected fs type
In FileStore::_detect_fs() store discovered filesystem type in m_fs_type
Add per-filesystem filestore_max_inline_xattr_size_* variants
Add per-filesystem filestore_max_inline_xattrs_* variants
New function set_xattr_limits_via_conf()
Set m_filestore_max_inline_xattr_size based on override or fs type
Set m_filestore_max_inline_xattrs based on override or fs type
Handle conf change of any relevant value by calling set_xattr_limits_via_conf()
Change filestore_max_inline_xattr_size to override if non-zero
Change filestore_max_inline_xattrs to override if non-zero
Fixes: #6143
Signed-off-by: David Zafman <david.zafman@inktank.com>
athanatos [Fri, 4 Oct 2013 21:04:41 +0000 (14:04 -0700)]
Merge pull request #692 from ceph/wip-5992-2
Wip 5992 2
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just [Thu, 3 Oct 2013 01:00:04 +0000 (18:00 -0700)]
ReplicatedPG: lock snapdir obc during write
Otherwise, we won't block properly in prep_push_backfill_object.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Mon, 30 Sep 2013 22:54:27 +0000 (15:54 -0700)]
PGLog: on split, leave log head alone
This way last_update doesn't go backwards.
Fixes: 6447
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 27 Sep 2013 22:31:56 +0000 (15:31 -0700)]
FileStore: make _setattrs not return -ENOENT most of the time
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 20 Sep 2013 18:26:49 +0000 (11:26 -0700)]
ReplicatedPG: add debugging in recover_replicas for objects added for backfill
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 17:35:47 +0000 (10:35 -0700)]
ReplicatedPG,PG: use PGBackend methods for getattr
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 17:12:11 +0000 (10:12 -0700)]
ReplicatedPG,PG: adapt collection_list* users to PGBackend interface
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 17:33:49 +0000 (10:33 -0700)]
PG,ReplicatedPG: expose PGBackend to PG
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 17:18:57 +0000 (10:18 -0700)]
PG.cc: remove leading empty space
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 17:11:54 +0000 (10:11 -0700)]
PGBackend,ReplicatedBackend: add interfaces for scanning the pg
This will be important since the erasure coded pg will have a different
on-disk format than the replicated backend.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Tue, 17 Sep 2013 15:26:51 +0000 (08:26 -0700)]
ReplicatedPG: don't rescan the local collection if we can avoid it
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 26 Sep 2013 19:31:35 +0000 (12:31 -0700)]
common/hobject: add is_degenerate method
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Sat, 10 Aug 2013 00:59:25 +0000 (17:59 -0700)]
PGMap: calc_min_last_epoch_clean() will now also use osd_epochs
We don't want to trim past the current osd map for any up osd.
osd_epochs provides a lower bound for that epoch for each osd.
Fixes: 5869
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Fri, 4 Oct 2013 19:29:26 +0000 (12:29 -0700)]
PGMap,PGMonitor: maintain mapping of osd to recent stat epoch
Also, osd_stat will be empty for out osd.
When an osd is marked out, rather than remove it from osd_stat,
we instead 0 out the structure.
This patch also makes osd_stat_updates and osd_stat_rm private.
This should make it simpler to enforce invariants on these
mappings.
Each up osd will have a mapping since out osds are now included as
empty stats.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Gary Lowell [Fri, 4 Oct 2013 20:12:24 +0000 (20:12 +0000)]
v0.70
Sage Weil [Fri, 4 Oct 2013 20:05:46 +0000 (13:05 -0700)]
Merge pull request #690 from ceph/wip-fuse
a few ceph-fuse fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yan, Zheng <zheng.z.yan@intel.com>
Greg Farnum [Fri, 4 Oct 2013 17:50:29 +0000 (10:50 -0700)]
ReplicatedPG: copy: add op progression output
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum [Fri, 4 Oct 2013 16:47:54 +0000 (09:47 -0700)]
ReplicatedPG: copy: don't leak a ctx on failed copy ops
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum [Fri, 4 Oct 2013 16:26:02 +0000 (09:26 -0700)]
ReplicatedPG: assert that we have succeeded in do_osd_ops on copyfrom repeats
Our callback is handling errors on its own at this point.
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum [Fri, 4 Oct 2013 16:10:20 +0000 (09:10 -0700)]
ReplicatedPG: copy: switch CopyCallback to use a GenContext
Signed-off-by: Greg Farnum <greg@inktank.com>
David Zafman [Fri, 27 Sep 2013 23:23:09 +0000 (16:23 -0700)]
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.com>
athanatos [Fri, 4 Oct 2013 16:43:20 +0000 (09:43 -0700)]
Merge pull request #689 from ceph/wip-6254-model
ceph_test_rados: notice read error; do not race rollback with snap_delete
Reviewed-by: Samuel Just <sam.just@inktank.com>
athanatos [Fri, 4 Oct 2013 16:43:00 +0000 (09:43 -0700)]
Merge pull request #688 from ceph/wip-6474
osd/ReplicatedPG: fix null deref on rollback_to whiteout check
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Fri, 4 Oct 2013 04:47:26 +0000 (21:47 -0700)]
ceph_test_rados: do not let rollback race with snap delete
Note that the OSD behaves in a weird way when you rollback to a non-
existent snap, so the test probably isn't the only party at fault here.
Fixes (test half of): #6254
Backport: dumpling, cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 4 Oct 2013 04:44:06 +0000 (21:44 -0700)]
ceph_test_rados: stop on read error!
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 4 Oct 2013 04:27:36 +0000 (21:27 -0700)]
osd/ReplicatedPG: fix null deref on rollback_to whiteout check
Bring this whole if/else chain up one level so that we can capture both
ENOENT and whiteout in the same case. (And don't dereference the
pointer when we know it is NULL.)
Fixes: #6474
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 4 Oct 2013 04:23:05 +0000 (21:23 -0700)]
Merge remote-tracking branch 'gh/next'
Conflicts:
src/Makefile.am
Josh Durgin [Fri, 4 Oct 2013 03:07:13 +0000 (20:07 -0700)]
PendingReleaseNotes: fix typo
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Sage Weil [Fri, 4 Oct 2013 01:27:58 +0000 (18:27 -0700)]
Merge pull request #557 from ceph/wip-5896
mon: MonmapMonitor: make 'ceph mon add' idempotent
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 4 Oct 2013 00:05:41 +0000 (17:05 -0700)]
PendingReleaseNotes: make a note about K vs k
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Fri, 4 Oct 2013 00:03:13 +0000 (17:03 -0700)]
Merge pull request #686 from ceph/wip-rbd-cli-tests
qa: fix rbd cli tests checking size
Reviewed-by: Sage Weil <sage@inktank.com>
Greg Farnum [Thu, 3 Oct 2013 22:50:40 +0000 (15:50 -0700)]
Merge branch 'master' into wip-optracker
Conflicts:
src/osd/OpRequest.h
src/osd/PG.cc
src/osd/ReplicatedPG.cc
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum [Thu, 3 Oct 2013 00:12:06 +0000 (17:12 -0700)]
TrackedOp: specify queue sizes and warnings on a per-tracker basis
If we have multiple trackers in a daemon, we want to be able to configure
them separately. Plus, users already know how to control op sizes in the
OSD, so changing the config options (as we did in
a8bbb81b7b7b6420ea08bc4e99a39adc6c3c397a )
is not really appropriate. Instead, provider setters which can be called
at construction time (or on any other change) and use them in the OSD with
the configurables we had previously. Add an observer so you can continue
to change them at run-time
This reverts
a8bbb81b7b7b6420ea08bc4e99a39adc6c3c397a
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum [Wed, 2 Oct 2013 23:27:19 +0000 (16:27 -0700)]
TrackedOp: give people an _event_marked() notifier instead of a virtual mark_event()
This is less prone to getting broken.
Signed-off-by: Greg Farnum <greg@inktank.com>
Josh Durgin [Thu, 3 Oct 2013 22:16:09 +0000 (15:16 -0700)]
qa: fix rbd cli tests checking size
b43bc1a0b0692818d789f9f489b9aba5dd40522f changed the kilo prefix
from K to k in a few places.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Sage Weil [Thu, 3 Oct 2013 21:50:25 +0000 (14:50 -0700)]
Merge pull request #684 from git-harry/ceph_disk_lowercase_fsid
Make fsid comparison case-insensitive
Reviewed-by: Sage Weil <sage@inktank.com>
John Wilkins [Thu, 3 Oct 2013 20:30:18 +0000 (13:30 -0700)]
doc: Fixed typo.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Dan Mick [Thu, 3 Oct 2013 19:19:50 +0000 (12:19 -0700)]
Merge pull request #685 from ceph/wip-rados-ints
librados: drop #include of int_types.h from installed headers
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil [Thu, 3 Oct 2013 19:16:55 +0000 (12:16 -0700)]
librados: drop #include of int_types.h from installed headers
These are unnecessary, and breaks compilation for outside users.
Prefer inttypes.h over stdint.h.
Signed-off-by: Sage Weil <sage@inktank.com>
Loic Dachary [Thu, 3 Oct 2013 19:13:41 +0000 (12:13 -0700)]
Merge pull request #638 from ceph/wip-bloom
bloom filter cleanups, encodability, and unit tests
Sage Weil [Thu, 3 Oct 2013 18:32:50 +0000 (11:32 -0700)]
Merge pull request #653 from ceph/wip-mon-auth
mon: Monitor: dissociate msg handling from session and connection logic
Reviewed-by: Sage Weil <sage@inktank.com>
Joao Eduardo Luis [Wed, 2 Oct 2013 00:59:11 +0000 (01:59 +0100)]
mon: Monitor: reuse 'src_is_mon' bool on dispatch
Instead of making the same comparison twice with no gain at all.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Mon, 23 Sep 2013 10:34:05 +0000 (11:34 +0100)]
mon: Monitor: only handle paxos msgs from a mon && if session has exec caps
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Wed, 2 Oct 2013 00:56:55 +0000 (01:56 +0100)]
mon: Monitor: dissociate msg handling from session & connection logic
Makes for simpler logic for patches to come.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Wed, 2 Oct 2013 00:54:09 +0000 (01:54 +0100)]
mon: Monitor: drop client msg if no session exists and msg is not MAuth
If we are not a monitor and we don't have a session yet, we must first
authenticate with the cluster. Therefore, the first message to the
monitor must be an MAuth. If not, we assume it's a stray message and
just drop it.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Wed, 2 Oct 2013 00:50:29 +0000 (01:50 +0100)]
mon: Monitor: assert on absense of connection during dispatch
We expect to always have a connection associated with a message.
If that happens to not be so, assert.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Thu, 3 Oct 2013 18:07:12 +0000 (19:07 +0100)]
mon: MonmapMonitor: make 'ceph mon add' idempotent
MonMap changes lead to bootstraps. Callbacks waiting for a proposal to
finish can have several fates, depending on what happens: finished, rerun
or aborted.
In the case of a bootstrap right after a monmap change, callbacks are
rerun. Considering we queued the message that lead to the monmap change
on this queue, if we instead of finishing it end up reruning it, we will
end up trying to perform the same modification twice -- the last one will
try to modify an already existing state and we will return just that:
whatever you're attempting to do has already been done.
This patch makes 'ceph mon add' completely idempotent. If one tries to
add an already existing monitor (i.e., same name, same ip:port), one
simply gets a 'monitor foo added', with return 0, no matter how many
times one runs the command.
Fixes: #5896
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil [Thu, 3 Oct 2013 16:20:34 +0000 (09:20 -0700)]
common/bloom_filter: note that uint32_t interface requires well-mixed values
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 3 Oct 2013 16:14:34 +0000 (09:14 -0700)]
common/bloom_filter: speed up unit tests a bit
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 26 Sep 2013 00:43:40 +0000 (17:43 -0700)]
common/bloom_filter: test binning fpp behavior
Signed-off-by: Sage Weil <sage@inktank.com>