Commit Graph

31438 Commits

Author SHA1 Message Date
Sage Weil
7d398c2ae2 doc/release-notes: v0.67.6
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-14 14:20:51 -08:00
Sage Weil
f47062d8a6 Merge pull request #1237 from dachary/wip-hashpspool
mon: ceph hashpspool false clears the flag

Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Reviewed-by: Sage Weil <sage@inktank.com>
2014-02-14 09:27:33 -08:00
Loic Dachary
d8964b2f33 Merge pull request #1235 from ceph/wip-osdmaptool-pool-fix
wip-osdmaptool-pool-fix

Reviewed-by: Loic Dachary <loic@dachary.org>
2014-02-14 13:33:26 +01:00
Ilya Dryomov
0ed6a81b4b osdmaptool: add tests for --pool option
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
2014-02-14 12:24:33 +02:00
Ilya Dryomov
f98435a45f 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.

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
2014-02-14 12:24:32 +02:00
Ilya Dryomov
eedbf501e6 osdmaptool: fix --pool option for --test-map-object mode
Commit 7f1b12f2ef ("osdmaptool: add --test-map-pgs mode") broke
--pool for --test-map-object mode.  Fix it, and improve --pool option
handling for both modes while at it (report strict_strtol() errors,
check if specified pool exists).

Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
2014-02-14 12:24:25 +02:00
Greg Farnum
e44122f094 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
explicit.

Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sam Just <sam.just@inktank.com>
2014-02-13 22:01:59 -08:00
Loic Dachary
589e2fa485 mon: ceph hashpspool false clears the flag
instead of toggling it.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 19:07:36 +01:00
Sage Weil
0ae5e53e8b 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>
2014-02-13 07:00:18 -08:00
Sage Weil
39e313fcfa 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>
2014-02-13 06:59:15 -08:00
Sage Weil
9cbbc883e2 Merge branch 'wip-libcephfs-firefly-rb' of https://github.com/linuxbox2/linuxbox-ceph
Reviewed-by: Sage Weil <sage@inktank.com>

This went through the fs suite and passed:

	http://pulpito.ceph.com/sage-2014-02-12_13:38:53-fs-wip-libcephfs-testing-basic-plana
2014-02-13 06:51:37 -08:00
Loic Dachary
020e543e34 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 proposal (and the ruleset) to
be accepted and then only return that it exists.

revert 4b687ba673

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 15:50:36 +01:00
Loic Dachary
192ed6151c 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@gmail.com>
2014-02-13 15:06:27 +01:00
Loic Dachary
0c9c1577f6 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 OSDMap. An attempt to
create a rule by the same name will return success and not create it again.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 14:54:59 +01:00
Loic Dachary
c248e7cf6c 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 Dachary <loic@dachary.org>
2014-02-13 14:54:52 +01:00
Sage Weil
f8ec7ae24e Merge pull request #1230 from ceph/wip-open-truncate
mds: properly replay dentry trace for open truncate.

Reviewed-by: Sage Weil <sage@inktank.com>
2014-02-13 05:00:17 -08:00
Loic Dachary
4784a687c1 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-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:27:40 +01:00
Loic Dachary
fce4d68404 mon: add missing format argument to crush dump
Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:27:40 +01:00
Loic Dachary
cec1893310 mon: add missing format argument to crush rule dump
Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:27:40 +01:00
Loic Dachary
7ff27566fa 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: Loic Dachary <loic@dachary.org>
2014-02-13 12:27:36 +01:00
Loic Dachary
fd13307f63 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 erasure code plugins from the sources directory

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
4b687ba673 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 between the two cases.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
a7e9a7b648 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>
2014-02-13 12:14:05 +01:00
Loic Dachary
e5b6eb45ba crush: cosmetic changes to CrushWrapper::dump_rule()
Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
dcfeee66cd 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 confuse code being
moved around and the code changes.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
f77e8ea268 crush: add CrushWrapper::dump_rules() unit test
Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
462ad76a47 crush: fix leaks in TestCrushWrapper.cc
To get a meaningfull valgrind output.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 12:14:05 +01:00
Loic Dachary
ee46908b8e 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 <greg@inktank.com>
2014-02-13 10:16:40 +01:00
Loic Dachary
6ad6b092df 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 because the required crush
ruleset is pending.

It replaces a fragile time sensitive workaround that could fail because
of race conditions. It also has the benefit of increase the speed of the
test because there is no need to wait for a long time just to accomodate
the slowest machines.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 10:14:11 +01:00
Loic Dachary
8dea58843c 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 PaxosProposal.

It can be used as follows:

   echo '{"prefix":"osdmonitor_prepare_command","prepare":"osd crush tunables","profile":"bobtail"}' | nc -U out/mon.a.asok

It will transform the command into:

  {"prefix":"osd crush tunables","profile":"bobtail"}

and feed it to OSDMonitor::prepare_command_impl(). The pending OSDMap won't
be proposed because it short circuit PaxosService::dispatch. It will,
however, be proposed next time PaxosService::dispatch() gets a chance.

It cannot be used via the ceph command line.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 09:52:23 +01:00
Loic Dachary
07c494bd7c 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 only. It is meant to
be used by the developer and not the system administrator, because it
would allow a non-developer to break things in ways that would be very
difficult to diagnose. It should probably not be documented.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 09:50:46 +01:00
Loic Dachary
5ea156a09a 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 Dachary <loic@dachary.org>
2014-02-13 09:45:55 +01:00
Loic Dachary
53e92f62a0 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 parsed.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-13 09:45:55 +01:00
Yan, Zheng
d012119736 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, introduce a new
flag CEPH_XATTR_REMOVE for the setxattr request.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-02-13 12:20:41 +08:00
Yan, Zheng
6e6a333590 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_open_truncate().

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-02-13 10:40:49 +08:00
Sage Weil
9035227e9d doc/release-notes: do not downgrade from v0.67.6
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-12 18:02:58 -08:00
Sage Weil
7533b3b7b5 doc/release-notes: note about dumpling xattr backport
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-12 17:55:50 -08:00
Sage Weil
cc1e84490d PendingReleaseNotes: note about cephfs backtrace updates
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-12 17:42:16 -08:00
Sage Weil
9482850750 Merge pull request #1219 from ceph/wip-update-backtrace
mds: force update backtraces for previously created FS

Reviewed-by: Sage Weil <sage@inktank.com>
2014-02-12 17:37:07 -08:00
Sage Weil
af4c142d95 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 defaults that we want to push people
off of.

Fixes: #7399
Signed-off-by: Sage Weil <sage@inktank.com>
2014-02-12 13:18:04 -08:00
Sage Weil
dce5196973 Merge pull request #1224 from kdreyer-inktank/packaging-libdir
packaging: do not package libdir/ceph recursively
2014-02-12 10:35:07 -08:00
Alexandre Oliva
5a6c9508e0 packaging: do not package libdir/ceph recursively
Package libdir/ceph non-recursively, to avoid duplicates, and
package libdir/ceph/ceph_common.sh explicitly.

Signed-off-by: Alexandre Oliva <oliva@gnu.org>
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
2014-02-12 11:17:07 -07:00
Sage Weil
f7cf25f293 Merge pull request #1215 from ceph/wip-7385
Remove the max cached objects restriction for librbd

Reviewed-by: Sage Weil <sage@inktank.com>
2014-02-12 09:54:30 -08:00
Loic Dachary
f6afe8cc6e 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>
2014-02-12 17:25:42 +01:00
Loic Dachary
48bcbc75ea Merge pull request #1221 from dachary/wip-filestore
tests: fix packaging for s/filestore/objectstore/

Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
2014-02-12 12:52:02 +01:00
Loic Dachary
840e918fd4 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 leftovers as well.

Fixing 1a588f18ba

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-12 12:46:14 +01:00
Kri5
b88b257241 Merge pull request #1220 from dachary/wip-filestore
tests: fix objectstore tests
2014-02-12 12:26:28 +01:00
Loic Dachary
b64f1e39a8 tests: fix objectstore tests
The objectstore test from 1a588f18ba was
missing a few changes.

Signed-off-by: Loic Dachary <loic@dachary.org>
2014-02-12 11:52:37 +01:00
Loic Dachary
a065e2c0d0 Merge pull request #1212 from ywang19/master
correct one command line at building packages section

Reviewed-by: Loic Dachary <loic@dachary.org>
2014-02-12 09:06:31 +01:00
Yan, Zheng
f34eb1b85b 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 is modified,
force update its backtrace.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
2014-02-12 14:24:09 +08:00