]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
10 years agomove pgp_num, pg_num check to prepare_new_pool method 4965/head
xinxin shu [Thu, 18 Jun 2015 18:11:39 +0000 (02:11 +0800)]
move pgp_num, pg_num check to prepare_new_pool method

Signed-off-by: xinxin shu <xinxin.shu@intel.com>
10 years agomon/OSDMonitor : error out if pgp_num > pg_num
xinxin shu [Mon, 15 Jun 2015 23:31:28 +0000 (07:31 +0800)]
mon/OSDMonitor : error out if pgp_num > pg_num

Fixes : #12025

Signed-off-by: xinxin shu <xinxin.shu@intel.com>
10 years agoMerge pull request #4959 from ceph/wip-crush-compat
Sage Weil [Mon, 15 Jun 2015 19:40:14 +0000 (12:40 -0700)]
Merge pull request #4959 from ceph/wip-crush-compat

Add crush_compat.h to eliminate ad hoc diff between kernel and userspace

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agoMerge pull request #4956 from oritwas/fix-cmake-2
Kefu Chai [Mon, 15 Jun 2015 16:28:58 +0000 (00:28 +0800)]
Merge pull request #4956 from oritwas/fix-cmake-2

cmake: add missing RadosDump.cc, RadosImport.cc and PoolDump.cc

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agocrush: eliminate ad hoc diff between kernel and userspace 4959/head
Ilya Dryomov [Fri, 12 Jun 2015 15:48:46 +0000 (18:48 +0300)]
crush: eliminate ad hoc diff between kernel and userspace

- map->choose_tries is not in the kernel
- 64-bit/64-bit in the kernel needs a special helper for 32-bit
  architectures, crush_compat.h provides a stub
- INT64_MIN is not in the kernel, crush_compat.h provides S64_MIN
- use dprintk inside DEBUG_INDEP sections

No functional changes.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
10 years agocrush: add crush_compat.h
Ilya Dryomov [Thu, 11 Jun 2015 13:03:01 +0000 (16:03 +0300)]
crush: add crush_compat.h

Move all the cruft that is necessary to compile shared files both in
kernel and userspace into a new crush_compat.h.  Also add a stub for
div64_s64() and limits for linux fixed width types.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
10 years agoMerge pull request #4826 from xinxinsh/wip-fix
Kefu Chai [Mon, 15 Jun 2015 14:48:14 +0000 (22:48 +0800)]
Merge pull request #4826 from xinxinsh/wip-fix

os/DBObjectMap:move iterator to first record of object otherwise iter->valid is always false

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agocrush: shared files should use kernel-doc
Ilya Dryomov [Thu, 11 Jun 2015 13:02:56 +0000 (16:02 +0300)]
crush: shared files should use kernel-doc

This reverts mapper.c hunks of 830752a52841 ("doc: fix doxygen
warnings").  It is shared with the kernel and uses kernel-doc for
in-code documentation.  If doxygen warnings are an issue, we should
probably just exclude the 7 shared files in Doxyfile - we don't have
@file in these files or EXTRACT_ALL/EXTRACT_STATIC in Doxyfile, which
means these files are essentially skipped as there is no C++ stuff in
them.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
10 years agocrush: fix style issues in shared files
Ilya Dryomov [Thu, 11 Jun 2015 12:41:55 +0000 (15:41 +0300)]
crush: fix style issues in shared files

Fix some recently introduced style issues in crush_ln_table.h,
crush.[ch], hash.[ch], and mapper.[ch].  These files are shared with
the kernel, so we need to at least not introduce anything new -
checkpatch is pretty unhappy as it is.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
10 years agocrush: move safe arithmetic functions to buider.c
Ilya Dryomov [Thu, 11 Jun 2015 09:45:56 +0000 (12:45 +0300)]
crush: move safe arithmetic functions to buider.c

Given that crush_{addition,multiplication}_is_unsafe() are only used
for compiling maps, they have no business in crush.c which is shared
with the kernel.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
10 years agocmake: add missing RadosDump.cc, RadosImport.cc and PoolDump.cc 4956/head
Orit Wasserman [Mon, 15 Jun 2015 09:39:17 +0000 (11:39 +0200)]
cmake: add missing RadosDump.cc, RadosImport.cc and PoolDump.cc

Signed-off-by: Orit Wasserman <owasserm@redhat.com>
10 years ago objectstore/store_test.cc : add tests for DBObjectMap::get_keys 4826/head
xinxin shu [Wed, 3 Jun 2015 22:56:26 +0000 (06:56 +0800)]
 objectstore/store_test.cc : add tests for DBObjectMap::get_keys

Signed-off-by: xinxin shu <xinxin.shu@intel.com>
10 years agoos/DBObjectMap : fix recurcive lock in get_keys
xinxin shu [Wed, 3 Jun 2015 22:51:39 +0000 (06:51 +0800)]
os/DBObjectMap : fix recurcive lock in get_keys

1. get_keys obtain header lock of oid
2. get iterator with get_iterator(oid), in get_iterator, it also want to get header lock of oid

Signed-off-by: xinxin shu <xinxin.shu@intel.com>
10 years agoos/DBOjectMap : iter->valid is always false if we do not initialize the iterator...
xinxin shu [Mon, 1 Jun 2015 06:28:32 +0000 (14:28 +0800)]
os/DBOjectMap : iter->valid is always false if we do not initialize the iterator with init(), seek_to_first will initialize this iterator

Signed-off-by: xinxin shu <xinxin.shu@intel.com>
10 years agoMerge pull request #4690 from branch-predictor/wip-radosbench-memjuggle
Kefu Chai [Sun, 14 Jun 2015 16:03:45 +0000 (00:03 +0800)]
Merge pull request #4690 from branch-predictor/wip-radosbench-memjuggle

tools: improve the performance of rados and rest_bench

Don't delete, recreate and re-fill buffers in rados bench. Fixes the high CPU usage by rados bench on fast SSDs
and ramdisks/memstore.

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4950 from SUSE/wip-osd-spelling
Sage Weil [Sat, 13 Jun 2015 18:59:39 +0000 (11:59 -0700)]
Merge pull request #4950 from SUSE/wip-osd-spelling

osd_types.{cc,h}: fix three typos in comments

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agoosd_types.{cc,h}: fix three typos in comments 4950/head
Nathan Cutler [Sat, 13 Jun 2015 18:36:09 +0000 (20:36 +0200)]
osd_types.{cc,h}: fix three typos in comments

Signed-off-by: Nathan Cutler <ncutler@suse.com>
10 years agoMerge pull request #4758 from xinxinsh/wip-kv-dump-transaction
Haomai Wang [Sat, 13 Jun 2015 14:49:44 +0000 (22:49 +0800)]
Merge pull request #4758 from xinxinsh/wip-kv-dump-transaction

dump keyvaluestore transaction to a file

Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Reviewed-by: Varada Kari <varada.kari@sandisk.com>
10 years agoMerge pull request #4940 from swamireddy/wip-v094-mailmap
Loic Dachary [Sat, 13 Jun 2015 09:26:43 +0000 (11:26 +0200)]
Merge pull request #4940 from swamireddy/wip-v094-mailmap

mailmap: Yuri Weinstein affiliation

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4947 from oritwas/fix-cmake
Yehuda Sadeh [Sat, 13 Jun 2015 01:45:46 +0000 (18:45 -0700)]
Merge pull request #4947 from oritwas/fix-cmake

cmake: Remove rados_sync.cc, rados_import.cc and rados_export.cc deleted files

Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
10 years agoRemove rados_sync.cc, rados_import.cc and rados_export.cc deleted files 4947/head
Orit Wasserman [Sat, 13 Jun 2015 01:21:40 +0000 (03:21 +0200)]
Remove rados_sync.cc, rados_import.cc and rados_export.cc deleted files

Signed-off-by: Orit Wasserman <owasserm@redhat.com>
10 years agomon: add 'PGs' column to 'ceph osd df'
Michal Jarzabek [Wed, 10 Jun 2015 20:47:58 +0000 (21:47 +0100)]
mon: add 'PGs' column to 'ceph osd df'

Fixes: #11882
Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
10 years agoMerge pull request #4752 from wuxingyi/wip-11749
Yehuda Sadeh [Fri, 12 Jun 2015 18:19:50 +0000 (11:19 -0700)]
Merge pull request #4752 from wuxingyi/wip-11749

rgw: fix data corruption when race condition

Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
10 years agoMerge pull request #4900 from abhidixit/trans_id
Yehuda Sadeh [Fri, 12 Jun 2015 17:17:31 +0000 (10:17 -0700)]
Merge pull request #4900 from abhidixit/trans_id

Transaction Id added in response for S3 and Swift requests

Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
10 years agomailmap: Yuri Weinstein affiliation 4940/head
Swami Reddy [Fri, 12 Jun 2015 14:17:45 +0000 (19:47 +0530)]
mailmap: Yuri Weinstein affiliation

Signed-off-by: M Ranga Swami Reddy <swamireddy@gmail.com>
10 years agoMerge pull request #4726 from tchaikov/wip-11680-check-empty-crushmap
Kefu Chai [Fri, 12 Jun 2015 01:19:51 +0000 (09:19 +0800)]
Merge pull request #4726 from tchaikov/wip-11680-check-empty-crushmap

mon: check new crush for unknown name/type

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4932 from dzafman/wip-cot-import
Loic Dachary [Thu, 11 Jun 2015 22:35:21 +0000 (00:35 +0200)]
Merge pull request #4932 from dzafman/wip-cot-import

test, tools: Improve ceph-objectstore-tool import error handling and …

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4933 from dachary/wip-releases
Sage Weil [Thu, 11 Jun 2015 20:54:07 +0000 (13:54 -0700)]
Merge pull request #4933 from dachary/wip-releases

doc: add v0.94.2 to the release timeline

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agodoc: add v0.94.2 to the release timeline 4933/head
Loic Dachary [Thu, 11 Jun 2015 20:35:25 +0000 (22:35 +0200)]
doc: add v0.94.2 to the release timeline

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agotest, tools: Improve ceph-objectstore-tool import error handling and add tests 4932/head
David Zafman [Thu, 11 Jun 2015 19:57:10 +0000 (12:57 -0700)]
test, tools: Improve ceph-objectstore-tool import error handling and add tests

Signed-off-by: David Zafman <dzafman@redhat.com>
10 years agoMerge pull request #4926 from dzafman/wip-omaptool
David Zafman [Thu, 11 Jun 2015 17:56:56 +0000 (10:56 -0700)]
Merge pull request #4926 from dzafman/wip-omaptool

ceph-osdomap-tool: Fix argument handling

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4914 from liewegas/wip-mon-pg-by-osd
Sage Weil [Thu, 11 Jun 2015 17:01:07 +0000 (10:01 -0700)]
Merge pull request #4914 from liewegas/wip-mon-pg-by-osd

mon: fix pg_by_osd in PGMap

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agoMerge pull request #4930 from ceph/wip-11959
Yan, Zheng [Thu, 11 Jun 2015 13:28:11 +0000 (21:28 +0800)]
Merge pull request #4930 from ceph/wip-11959

qa: use "sudo cp" in multiple_rsync.sh

10 years agoqa: use "sudo cp" in multiple_rsync.sh 4930/head
John Spray [Thu, 11 Jun 2015 10:11:44 +0000 (11:11 +0100)]
qa: use "sudo cp" in multiple_rsync.sh

VirtualBox has some files with weird
permissions in its /usr/lib, which was
tripping up this usually-safe operation
when run as an unprivileged user.

Fixes: #11959
Signed-off-by: John Spray <john.spray@redhat.com>
10 years agoMerge pull request #4921 from dachary/wip-11952-test-ceph-disk
Kefu Chai [Thu, 11 Jun 2015 08:42:36 +0000 (16:42 +0800)]
Merge pull request #4921 from dachary/wip-11952-test-ceph-disk

tests: ceph-disk tests need to install pip > 6.1

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agoceph-osdomap-tool: Fix argument handling 4926/head
David Zafman [Fri, 10 Oct 2014 23:58:50 +0000 (16:58 -0700)]
ceph-osdomap-tool: Fix argument handling

Signed-off-by: David Zafman <dzafman@redhat.com>
10 years agomon/PGMap: fix pgmap stat adjustment during map_pg_creates() 4914/head
Sage Weil [Thu, 11 Jun 2015 00:41:27 +0000 (17:41 -0700)]
mon/PGMap: fix pgmap stat adjustment during map_pg_creates()

PGMonitor::map_pg_creates() is the only caller that passes sumonly=true,
which is necessary to avoid modifying creating_pgs while it is iterating
over it. However, everything else we *do* want to update--especially the
osd counts.

Rename the arg and skip only the creating bit.

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agoMerge pull request #4863 from ceph/wip-9964-nosharding
David Zafman [Wed, 10 Jun 2015 23:57:15 +0000 (16:57 -0700)]
Merge pull request #4863 from ceph/wip-9964-nosharding

rados import/export (minus pgls sharding)

Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: John Spray <john.spray@redhat.com>
10 years agotest: Add --dry-run and --no-overwrite testing of rados import 4863/head
David Zafman [Wed, 10 Jun 2015 21:46:24 +0000 (14:46 -0700)]
test: Add --dry-run and --no-overwrite testing of rados import

Signed-off-by: David Zafman <dzafman@redhat.com>
10 years agotools/rados: dry-run/no-overwrite args for import
John Spray [Wed, 10 Jun 2015 12:10:08 +0000 (13:10 +0100)]
tools/rados: dry-run/no-overwrite args for import

These were supported by the old objectstoretool
hook into RadosImport: wire them up here too.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: better error message in objectstoretool
John Spray [Wed, 10 Jun 2015 11:26:46 +0000 (12:26 +0100)]
tools: better error message in objectstoretool

...for the case where someone exports a pool
with "rados export" and then tries to import
it into a PG.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotest: Switch ceph-objectstore-tool import-rados to rados import
David Zafman [Fri, 5 Jun 2015 23:08:19 +0000 (16:08 -0700)]
test: Switch ceph-objectstore-tool import-rados to rados import

Signed-off-by: David Zafman <dzafman@redhat.com>
10 years agotools: remove objectstoretool's rados-import
John Spray [Thu, 4 Jun 2015 13:13:24 +0000 (14:13 +0100)]
tools: remove objectstoretool's rados-import

Same functionality now exposed as "rados import".

This removes objectstoretool's librados dependency.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: remove old rados_sync code
John Spray [Thu, 4 Jun 2015 12:57:41 +0000 (13:57 +0100)]
tools: remove old rados_sync code

This is the code that used to sit behind the
old import/export commands that have been
disabled for some time.

Replaced by the new import/export commands.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: implement rados import/export
John Spray [Mon, 23 Mar 2015 13:20:35 +0000 (13:20 +0000)]
tools: implement rados import/export

New PoolDump (export) class to dump pool contents
in format compatible with ceph-objectstore-tool,
and wire up RadosImport class (import).

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: refactor RadosImport to pass ioctx
John Spray [Tue, 28 Apr 2015 14:45:53 +0000 (15:45 +0100)]
tools: refactor RadosImport to pass ioctx

Callers from rados.cc will already have an ioctx,
whereas objectstoretool passes in a pool name.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: remove RadosDump::debug in favour of dout
John Spray [Tue, 28 Apr 2015 11:58:51 +0000 (12:58 +0100)]
tools: remove RadosDump::debug in favour of dout

This attribute was a hangover from objectstore-tool

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: add support for pool exports in RadosImport
John Spray [Mon, 20 Apr 2015 16:59:39 +0000 (17:59 +0100)]
tools: add support for pool exports in RadosImport

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: clean up errors in ceph-objectstore-tool
John Spray [Mon, 20 Apr 2015 16:28:15 +0000 (17:28 +0100)]
tools: clean up errors in ceph-objectstore-tool

We use negative error codes everywhere else, should
use them here too.  Also add a couple of strategically
placed prints.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agotools: refactor objectstore tool
John Spray [Fri, 17 Apr 2015 20:23:23 +0000 (21:23 +0100)]
tools: refactor objectstore tool

...to expose the definitions of the object dump
format (RadosDump) for use in rados import/export.

The serialized->RADOS code is now RadosImport, and
the serialized->ObjectStore code is ObjectStoreTool.

This is a step toward #9964, which should use the
same on serialization format as the existing
objectstore-tool dumps.

Signed-off-by: John Spray <john.spray@redhat.com>
10 years agoMerge pull request #4922 from dachary/wip-releases
Sage Weil [Wed, 10 Jun 2015 19:59:54 +0000 (12:59 -0700)]
Merge pull request #4922 from dachary/wip-releases

doc: add v9.0.1 to the release timeline

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agodoc: add v9.0.1 to the release timeline 4922/head
Loic Dachary [Wed, 10 Jun 2015 19:50:07 +0000 (21:50 +0200)]
doc: add v9.0.1 to the release timeline

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agodoc/release-notes: v0.94.2
Sage Weil [Wed, 10 Jun 2015 19:48:41 +0000 (12:48 -0700)]
doc/release-notes: v0.94.2

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agodoc/release-notes: v9.0.1
Sage Weil [Wed, 10 Jun 2015 19:42:17 +0000 (12:42 -0700)]
doc/release-notes: v9.0.1

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agotests: ceph-disk tests need to install pip > 6.1 4921/head
Loic Dachary [Wed, 10 Jun 2015 19:00:42 +0000 (21:00 +0200)]
tests: ceph-disk tests need to install pip > 6.1

Otherwise it will not be able to use the wheelhouse.

http://tracker.ceph.com/issues/11952 Fixes: #11952

Signed-off-by: Loic Dachary <loic@dachary.org>
10 years agoMerge pull request #4915 from ceph/wip-cot-list
Loic Dachary [Wed, 10 Jun 2015 18:28:05 +0000 (20:28 +0200)]
Merge pull request #4915 from ceph/wip-cot-list

tools: For ec pools list objects in all shards if the pgid doesn't sp…

Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge remote-tracking branch 'gh/next'
Sage Weil [Wed, 10 Jun 2015 17:14:46 +0000 (13:14 -0400)]
Merge remote-tracking branch 'gh/next'

10 years agoMerge pull request #4910 from dachary/wip-11932-non-regression-typo
Loic Dachary [Wed, 10 Jun 2015 15:43:55 +0000 (17:43 +0200)]
Merge pull request #4910 from dachary/wip-11932-non-regression-typo

tests: ceph_erasure_code_non_regression s/stipe/stripe/

10 years agoMerge pull request #4873 from liewegas/wip-rgw-civetweb-port
Yehuda Sadeh [Wed, 10 Jun 2015 15:12:05 +0000 (08:12 -0700)]
Merge pull request #4873 from liewegas/wip-rgw-civetweb-port

rgw: strip off port from HTTP_HOST when determining bucket from URL

Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
10 years agoMerge pull request #4838 from ceph/wip-10950
Gregory Farnum [Wed, 10 Jun 2015 14:18:48 +0000 (07:18 -0700)]
Merge pull request #4838 from ceph/wip-10950

#10950: Fix confusing errors using "mds rm"

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
10 years agoMerge pull request #4835 from ceph/wip-11746
Gregory Farnum [Wed, 10 Jun 2015 14:17:43 +0000 (07:17 -0700)]
Merge pull request #4835 from ceph/wip-11746

tools: chunk reads in Dumper

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
10 years agoMerge pull request #4825 from tchaikov/wip-drop-ignored-mdsbeacon
Gregory Farnum [Wed, 10 Jun 2015 14:15:38 +0000 (07:15 -0700)]
Merge pull request #4825 from tchaikov/wip-drop-ignored-mdsbeacon

mon: drop ignored mdsbeacon

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
10 years agotests: erasure-code non regression tests must skip isa on i386 4910/head
Loic Dachary [Wed, 10 Jun 2015 13:26:00 +0000 (15:26 +0200)]
tests: erasure-code non regression tests must skip isa on i386

When the isa plugin is not present, the isa plugin payloads are not
tested. When that happens, remember that it was intentional by storing
the path that would have been tested so that the inventory is complete.

http://tracker.ceph.com/issues/11949 Fixes: #11949

Signed-off-by: Loic Dachary <loic@dachary.org>
10 years agorgw: fix data corruption when race condition 4752/head
wuxingyi [Wed, 10 Jun 2015 06:57:57 +0000 (06:57 +0000)]
rgw: fix data corruption when race condition

We should delete the object in the multipart namespace lastly to prevent a previous upload
wrongly deleting objects belong to the following upload.

Fixes: #11749
Signed-off-by: wuxingyi <wuxingyi@letv.com>
10 years agoMerge pull request #4707 from stiopaa1/IosFwdNew
Kefu Chai [Wed, 10 Jun 2015 05:22:00 +0000 (13:22 +0800)]
Merge pull request #4707 from stiopaa1/IosFwdNew

Removed unnecessary inclusion of iostream in several files

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agotools: For ec pools list objects in all shards if the pgid doesn't specify 4915/head
David Zafman [Wed, 10 Jun 2015 01:14:09 +0000 (18:14 -0700)]
tools: For ec pools list objects in all shards if the pgid doesn't specify

Signed-off-by: David Zafman <dzafman@redhat.com>
10 years agomon/PGMap: access num pgs by osd
Sage Weil [Tue, 9 Jun 2015 21:56:08 +0000 (17:56 -0400)]
mon/PGMap: access num pgs by osd

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agomon/PGMap: fix pg_by_osd
Sage Weil [Tue, 9 Jun 2015 21:55:59 +0000 (17:55 -0400)]
mon/PGMap: fix pg_by_osd

Broken since it was introduced in 7a04762fe09661cc2ac98a034626912ec0583116.

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agorgw: remove trailing :port from host for purposes of subdomain matching 4873/head
Sage Weil [Tue, 9 Jun 2015 18:15:10 +0000 (14:15 -0400)]
rgw: remove trailing :port from host for purposes of subdomain matching

Some clients (ahem, CrossFTP) include the :port in the HTTP_HOST header.
Strip it out.

Switch req_info field to a std::string and avoid copying it in preprocess.

Signed-off-by: Sage Weil <sage@redhat.com>
10 years agoMerge pull request #4775 from yuyuyu101/wip-async-crc-decouple
Sage Weil [Tue, 9 Jun 2015 17:54:11 +0000 (10:54 -0700)]
Merge pull request #4775 from yuyuyu101/wip-async-crc-decouple

AsyncMessenger: Make send/receive logic independent

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agotests: ceph_erasure_code_non_regression s/stipe/stripe/
Loic Dachary [Tue, 9 Jun 2015 14:22:43 +0000 (16:22 +0200)]
tests: ceph_erasure_code_non_regression s/stipe/stripe/

Synchronize withe the ceph-erasure-code-corpus submodule in which all
file names were modified to fix the typo.

http://tracker.ceph.com/issues/11932 Fixes: #11932

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4815 from dachary/wip-9720-erasure-code-corpus-variants
Loic Dachary [Tue, 9 Jun 2015 14:28:48 +0000 (16:28 +0200)]
Merge pull request #4815 from dachary/wip-9720-erasure-code-corpus-variants

tests: sync ceph-erasure-code-corpus to verify jerasure variants

Reviewed-by: Andreas Peters <andreas.joachim.peters@cern.ch>
10 years agoMerge pull request #4908 from dachary/wip-11931-parallel-tests
Loic Dachary [Tue, 9 Jun 2015 13:50:12 +0000 (15:50 +0200)]
Merge pull request #4908 from dachary/wip-11931-parallel-tests

tests: automake 1.11 needs parallel-tests

Reviewed-by: Nathan Cutler <ncutler@suse.com>
10 years agotests: automake 1.11 needs parallel-tests 4908/head
Loic Dachary [Tue, 9 Jun 2015 11:49:14 +0000 (13:49 +0200)]
tests: automake 1.11 needs parallel-tests

Prior to automake 1.13 the default behavior was serial-tests meaning
tests from make check were run one after the other and their output sent
to stdout/stderr. From automake 1.13 up the default became
parallel-tests which logs the output of each individual test in a
separate .log file and allows them to run in parallel.

http://lists.gnu.org/archive/html/automake/2012-12/msg00038.html

Enable parallel-tests so that tests can always run in parallel, even
with automake 1.11 which is the version found in CentOS 6.5 and Ubuntu
12.04 precise.

A nice side effect of always having the logs in separate files is that
tests do not need to worry about being too verbose because their output
will only be read for diagnostic purposes.

http://tracker.ceph.com/issues/11931 Fixes: #11931
http://tracker.ceph.com/issues/11906 Fixes: #11906

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoRemoved unnecessary inclusion of iostream 4707/head
Michal Jarzabek [Mon, 11 May 2015 16:46:12 +0000 (17:46 +0100)]
Removed unnecessary inclusion of iostream

In several files the iostream wasn't being used, so it got removed.
In other files the iostream inclusion was replaced by including iosfwd
(for forward declarations), which is much smaller header than iostream,
  so in theory should reduce compilation time.
To make this work some of the functions must have been moved from .h to .cc file.
3 functions also needed to have inline removed - this shouldn't affect
performance in any way: two of them are
probably too long to have been inlined anyway and the third one is for
error reporting, so probably won't be called too often.

test/Makefile-client.am: added linker libs

This was required to avoid linker error when linking
src/test/cls_rbd/test_cls_rbd.cc file. Makefile was specyfing
libcommon.a as a part of a linker command even though this wasn't
required and wasn't being linked against. When inline functions from
buffer.h were moved to buffer.cc(and inline was removed) the
libcommon.a library became necessary. This wouldn't link without also
including additional libraries(CRYPTO_LIBS and EXTRA_LIBS)

Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
10 years agoMerge pull request #4879 from SUSE/wip-master-specfile-cleanup
Loic Dachary [Tue, 9 Jun 2015 05:32:17 +0000 (07:32 +0200)]
Merge pull request #4879 from SUSE/wip-master-specfile-cleanup

ceph.spec.in: remove duplicate BuildRequires

Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agoMerge pull request #4784 from ceph/wip-10794
Samuel Just [Tue, 9 Jun 2015 02:04:33 +0000 (19:04 -0700)]
Merge pull request #4784 from ceph/wip-10794

ceph-objectstore-tool improvements

Reviewed-by: Samuel Just <sjust@redhat.com>
10 years agoMerge pull request #4903 from theanalyst/doc/arch-watch-notify
Josh Durgin [Mon, 8 Jun 2015 19:36:35 +0000 (12:36 -0700)]
Merge pull request #4903 from theanalyst/doc/arch-watch-notify

doc: architecture minor fixes in watch notify

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
10 years agodoc: architecture minor fixes in watch notify 4903/head
Abhishek Lekshmanan [Mon, 8 Jun 2015 18:51:58 +0000 (00:21 +0530)]
doc: architecture minor fixes in watch notify

Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@ril.com>
10 years agoceph.spec.in: remove duplicate BuildRequires 4879/head
Nathan Cutler [Sat, 6 Jun 2015 11:33:35 +0000 (13:33 +0200)]
ceph.spec.in: remove duplicate BuildRequires

Signed-off-by: Nathan Cutler <ncutler@suse.com>
10 years agoTransaction Id added in response 4900/head
Abhishek Dixit [Mon, 8 Jun 2015 17:29:54 +0000 (22:59 +0530)]
Transaction Id added in response
Signed-off-by: Abhishek Dixit dixitabhi@gmail.com
10 years agoMerge pull request #4880 from SUSE/wip-master-specfile-cleanup2
Ken Dreyer [Mon, 8 Jun 2015 16:27:16 +0000 (10:27 -0600)]
Merge pull request #4880 from SUSE/wip-master-specfile-cleanup2

ceph.spec.in: move specific BuildRequires to where they belong

Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
10 years agoMerge pull request #4893 from dachary/wip-11272-ceph-disk-false-negative 4277/head
Kefu Chai [Mon, 8 Jun 2015 14:12:46 +0000 (22:12 +0800)]
Merge pull request #4893 from dachary/wip-11272-ceph-disk-false-negative

tests: ceph-disk.sh test zap gitbuilder false negative

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agoMerge pull request #4888 from dachary/wip-11905-test-isa
Kefu Chai [Mon, 8 Jun 2015 02:38:52 +0000 (10:38 +0800)]
Merge pull request #4888 from dachary/wip-11905-test-isa

tests: skip isa tests if the plugin is not available

Reviewed-by: Kefu Chai <kchai@redhat.com>
10 years agotests: ceph-disk.sh test zap gitbuilder false negative 4893/head
Loic Dachary [Sun, 7 Jun 2015 11:52:01 +0000 (13:52 +0200)]
tests: ceph-disk.sh test zap gitbuilder false negative

When looking for an error message and testing ceph disk zap, use grep -q
to not display the error message that will be mistaken for a real error
by the gitbuilder parser.

http://tracker.ceph.com/issues/11272 Refs: #11272

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agotests: skip isa tests if the plugin is not available 4888/head
Loic Dachary [Sun, 7 Jun 2015 08:53:49 +0000 (10:53 +0200)]
tests: skip isa tests if the plugin is not available

http://tracker.ceph.com/issues/11905 Fixes: #11905

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agotests: use erasure_code_plugin_exists from ceph-helpers.sh
Loic Dachary [Sun, 7 Jun 2015 08:52:31 +0000 (10:52 +0200)]
tests: use erasure_code_plugin_exists from ceph-helpers.sh

Instead of the local plugin_exists helper that does the same.

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agotests: implement erasure_code_plugin_exists in ceph-helpers.sh
Loic Dachary [Sun, 7 Jun 2015 08:51:07 +0000 (10:51 +0200)]
tests: implement erasure_code_plugin_exists in ceph-helpers.sh

Return 0 if the erasure code *plugin* is available, 1 otherwise.

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4713 from dachary/wip-10358-erasure-code-k-1-m-1
Loic Dachary [Sun, 7 Jun 2015 07:58:26 +0000 (09:58 +0200)]
Merge pull request #4713 from dachary/wip-10358-erasure-code-k-1-m-1

ceph osd erasure-code-profile set myprofile k=1 should fail

Reviewed-by: Andreas Peters <andreas.joachim.peters@cern.ch>
10 years agotests: sync ceph-erasure-code-corpus to verify jerasure variants 4815/head
Loic Dachary [Sun, 31 May 2015 11:18:39 +0000 (13:18 +0200)]
tests: sync ceph-erasure-code-corpus to verify jerasure variants

http://tracker.ceph.com/issues/9720 Refs: #9720

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agotests: add --{show_,}path to ceph_erasure_code_non_regression
Loic Dachary [Sun, 31 May 2015 11:11:34 +0000 (13:11 +0200)]
tests: add --{show_,}path to ceph_erasure_code_non_regression

The directory in which the payload is stored is created from the plugin
parameters. The --show-path shows the directory and exits. This
directory can then be used with --path to override the path created from
the plugin parameters. This is useful to verifying that the jerasure
variant optimized with AVX, SSE4 etc. instructions can be used on the
same payload and show no difference at all. In this case the directory
used by the default jerasure variant is used for each variant and the
parameter that sets the variant to use ( --parameters jerasure-variant )
must not be taken into account to figure out the location of the
payload.

http://tracker.ceph.com/issues/9720 Refs: #9720

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4811 from dachary/wip-11346-isa
Loic Dachary [Sat, 6 Jun 2015 22:12:11 +0000 (00:12 +0200)]
Merge pull request #4811 from dachary/wip-11346-isa

ceph-erasure-code-corpus: isa: add k=10 m=4

Reviewed-by: Yuan Zhou <yuan.zhou@intel.com>
10 years agoerasure-code: add sanity check to guard against k=1 4713/head
Loic Dachary [Sun, 17 May 2015 22:29:31 +0000 (00:29 +0200)]
erasure-code: add sanity check to guard against k=1

Add a call to ErasureCode::sanity_check_k for the isa and jerasure
plugins, with associated tests.

http://tracker.ceph.com/issues/10358 Fixes: #10358

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoMerge pull request #4882 from SUSE/wip-submitting-patches-clarification
Sage Weil [Sat, 6 Jun 2015 13:24:17 +0000 (06:24 -0700)]
Merge pull request #4882 from SUSE/wip-submitting-patches-clarification

SubmittingPatches: clarify how Reviewed-by lines are added

Reviewed-by: Sage Weil <sage@redhat.com>
10 years agoSubmittingPatches: clarify how Reviewed-by lines are added 4882/head
Nathan Cutler [Sat, 6 Jun 2015 13:16:16 +0000 (15:16 +0200)]
SubmittingPatches: clarify how Reviewed-by lines are added

Signed-off-by: Nathan Cutler <ncutler@suse.com>
10 years agoMerge pull request #4878 from dachary/wip-11901-spec
Loic Dachary [Sat, 6 Jun 2015 12:37:23 +0000 (14:37 +0200)]
Merge pull request #4878 from dachary/wip-11901-spec

ceph.spec.in: add missing BuildRequires from SUSE block

Reviewed-by: Nathan Cutler <ncutler@suse.cz>
10 years agoceph.spec.in: move specific BuildRequires to where they belong
Nathan Cutler [Sat, 6 Jun 2015 11:44:20 +0000 (13:44 +0200)]
ceph.spec.in: move specific BuildRequires to where they belong

Move distro-specific BuildRequires out of "common" section and
into the appropriate %if statement in the "specific" section.
Also remove a duplicated "Requires: gdisk".

Signed-off-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Loic Dachary <ldachary@redhat.com>
10 years agoinstall-deps.sh: detect yum-builddep errors 4878/head
Loic Dachary [Sat, 6 Jun 2015 10:28:03 +0000 (12:28 +0200)]
install-deps.sh: detect yum-builddep errors

yum-builddep does not exit on error when an error happens: grep the
output for the error: string instead.

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoceph.spec.in: add missing BuildRequires from SUSE block
Loic Dachary [Sat, 6 Jun 2015 08:20:02 +0000 (10:20 +0200)]
ceph.spec.in: add missing BuildRequires from SUSE block

The %endif removed by f94f23297c05019db754ec53b4ceaea7706152c9 is restored.
The %else removed by 75e87a20dac05441b97ce99dea76fff8e3a863ac is restored.
The stray %endif added by d8abde3338b0c7df373b762e35099ad5123866bf is removed.

May 29th, in d8abde3338b0c7df373b762e35099ad5123866bf Owen added a stray
%endif after

   BuildRequires: gperftools-devel

around line 133. June 3rd, in f94f23297c05019db754ec53b4ceaea7706152c9
Ken correctly attributed the error

     "error: /srv/autobuild-ceph/gitbuilder.git/build/ceph.spec:140: Got a
      %endif with no %if"

to a stray %endif but did not remove the one causing problem and in
doing so created another problem. June 4th, in
75e87a20dac05441b97ce99dea76fff8e3a863ac Owen incorrectly fixed
this new problem by removing the %else that is near

   BuildRequires: gperftools-devel

around line 116, instead of reverting
f94f23297c05019db754ec53b4ceaea7706152c9. As a consequence the
ceph.spec.in became syntactically correct but implemented an if/else
logic different from what was intended originally and a number of
BuildRequires became exclusive to SUSE and were not installed for CentOS
7 etc.

http://tracker.ceph.com/issues/11901 Fixes: #11901

Signed-off-by: Loic Dachary <ldachary@redhat.com>
10 years agoerasure-code: implement ErasureCode::sanity_check_k
Loic Dachary [Sun, 17 May 2015 22:16:04 +0000 (00:16 +0200)]
erasure-code: implement ErasureCode::sanity_check_k

Implement the ErasureCode::sanity_check_k helper for plugins
that need to verify k >= 2.

http://tracker.ceph.com/issues/10358 Fixes: #10358

Signed-off-by: Loic Dachary <ldachary@redhat.com>