]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
12 years agoMerge pull request #324 from dalgaaf/wip-da-CID-727979
Sage Weil [Tue, 28 May 2013 17:27:25 +0000 (10:27 -0700)]
Merge pull request #324 from dalgaaf/wip-da-CID-727979

kv_flat_btree_async.cc: fix AioCompletion resource leak

12 years agoosd/OSDMap: fix Incremental dump
Sage Weil [Tue, 28 May 2013 16:16:17 +0000 (09:16 -0700)]
osd/OSDMap: fix Incremental dump

The front hb addr entry may not be present.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #322 from guilhem/patch-1
Sage Weil [Tue, 28 May 2013 15:43:10 +0000 (08:43 -0700)]
Merge pull request #322 from guilhem/patch-1

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agokv_flat_btree_async.cc: fix AioCompletion resource leak 324/head
Danny Al-Gaaf [Tue, 28 May 2013 10:38:57 +0000 (12:38 +0200)]
kv_flat_btree_async.cc: fix AioCompletion resource leak

Call AioCompletion::release() if the completion is no longer needed.

CID 727979 (#1-2 of 2): Resource leak (RESOURCE_LEAK)
  leaked_storage: Variable "a" going out of scope leaks the storage
  it points to.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agoRemove mon socket in post-stop 322/head
Guilhem Lettron [Mon, 27 May 2013 10:41:53 +0000 (12:41 +0200)]
Remove mon socket in post-stop

If ceph-mon segfault, socket file isn't removed.

By adding a remove in post-stop, upstart clean run directory properly.

Signed-off-by: Guilhem Lettron <guilhem@lettron.fr>
12 years agoPendingReleaseNotes: notes about enabling HASHPSPOOL
Sage Weil [Tue, 28 May 2013 04:16:46 +0000 (21:16 -0700)]
PendingReleaseNotes: notes about enabling HASHPSPOOL

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosdmaptool: fix cli tests
Sage Weil [Tue, 28 May 2013 04:12:29 +0000 (21:12 -0700)]
osdmaptool: fix cli tests

Now that the default pool flags have changed.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #321 from dalgaaf/wip-da-CID-727981
Sage Weil [Mon, 27 May 2013 20:55:54 +0000 (13:55 -0700)]
Merge pull request #321 from dalgaaf/wip-da-CID-727981

kv_flat_btree_async.cc: fix AioCompletion resource leak

12 years agoMerge pull request #320 from dalgaaf/wip-da-CID-727983
Sage Weil [Mon, 27 May 2013 20:55:24 +0000 (13:55 -0700)]
Merge pull request #320 from dalgaaf/wip-da-CID-727983

kv_flat_btree_async.cc: fix resource leak

12 years agodoc: Updated rgw.conf example.
John Wilkins [Sat, 25 May 2013 22:13:01 +0000 (15:13 -0700)]
doc: Updated rgw.conf example.

fixes: #4608

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Updated RGW Quickstart.
John Wilkins [Sat, 25 May 2013 22:11:49 +0000 (15:11 -0700)]
doc: Updated RGW Quickstart.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Updated index for newer terms.
John Wilkins [Sat, 25 May 2013 22:11:06 +0000 (15:11 -0700)]
doc: Updated index for newer terms.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agopg_pool_t: enable FLAG_HASHPSPOOL by default
Samuel Just [Fri, 24 May 2013 23:20:38 +0000 (16:20 -0700)]
pg_pool_t: enable FLAG_HASHPSPOOL by default

Fixes: #5160
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
12 years agokv_flat_btree_async.cc: fix AioCompletion resource leak 321/head
Danny Al-Gaaf [Fri, 24 May 2013 12:47:49 +0000 (14:47 +0200)]
kv_flat_btree_async.cc: fix AioCompletion resource leak

Call AioCompletion::release() if the completion is no longer
needed to free the resources.

CID 727981 (#3 of 3): Resource leak (RESOURCE_LEAK)
  leaked_storage: Variable "top_aioc" going out of scope leaks the
  storage it points to.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agokv_flat_btree_async.cc: fix resource leak 320/head
Danny Al-Gaaf [Fri, 24 May 2013 12:29:14 +0000 (14:29 +0200)]
kv_flat_btree_async.cc: fix resource leak

Call AioCompletion::release() if the completion is no longer
needed to free the resources.

CID 727983 : Resource leak (RESOURCE_LEAK)
  leaked_storage: Variable "aioc" going out of scope leaks the
  storage it points to.

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agodoc: Updated Ceph FS Quick Start.
John Wilkins [Fri, 24 May 2013 00:02:17 +0000 (17:02 -0700)]
doc: Updated Ceph FS Quick Start.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Added troubleshooting to Ceph FS index.
John Wilkins [Fri, 24 May 2013 00:01:51 +0000 (17:01 -0700)]
doc: Added troubleshooting to Ceph FS index.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Added separate troubleshooting for MDS and Ceph FS.
John Wilkins [Fri, 24 May 2013 00:01:29 +0000 (17:01 -0700)]
doc: Added separate troubleshooting for MDS and Ceph FS.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Updates for ceph-deploy and cuttlefish.
John Wilkins [Thu, 23 May 2013 18:45:14 +0000 (11:45 -0700)]
doc: Updates for ceph-deploy and cuttlefish.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agoMerge pull request #312 from ceph/wip-osd-hb
Sage Weil [Thu, 23 May 2013 17:17:14 +0000 (10:17 -0700)]
Merge pull request #312 from ceph/wip-osd-hb

Reviewed-by: Samuel Just <sam.just@inktank.com>
12 years agoMerge branch 'next'
Sage Weil [Thu, 23 May 2013 15:49:10 +0000 (08:49 -0700)]
Merge branch 'next'

12 years agomodified: src/init-ceph.in
Xiaoxi Chen [Thu, 23 May 2013 01:33:27 +0000 (09:33 +0800)]
modified:   src/init-ceph.in
fixed bug in init script, the "df" should be run on remote host by do_cmd,
and use $host instead of "hostname -s"

Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com>
(cherry picked from commit 1dd99f0fc91ee6d417325689f24601aa335b94c2)

Conflicts:

src/init-ceph.in

12 years agomsgr: increase port range to 6900-7300 (from -7100)
Sage Weil [Thu, 23 May 2013 15:40:23 +0000 (08:40 -0700)]
msgr: increase port range to 6900-7300 (from -7100)

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #307 from xiaoxichen/master
Sage Weil [Thu, 23 May 2013 15:45:55 +0000 (08:45 -0700)]
Merge pull request #307 from xiaoxichen/master

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agomodified: src/init-ceph.in 307/head
Xiaoxi Chen [Thu, 23 May 2013 01:33:27 +0000 (09:33 +0800)]
modified:   src/init-ceph.in
fixed bug in init script, the "df" should be run on remote host by do_cmd,
and use $host instead of "hostname -s"

Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com>
12 years agoosd: ping both front and back interfaces 312/head
Sage Weil [Wed, 22 May 2013 15:44:52 +0000 (08:44 -0700)]
osd: ping both front and back interfaces

Send ping requests to both the front and back hb addrs for peer osds.  If
the front hb addr is not present, do not send it and interpret a reply
as coming from both.  This handles the transition from old to new OSDs
seamlessly.

Note both the front and back rx times.  Both need to be up to date in order
for the peer to be healthy.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomsgr: add Messenger reference to Connection
Sage Weil [Wed, 22 May 2013 15:13:21 +0000 (08:13 -0700)]
msgr: add Messenger reference to Connection

This allows us to get the messenger associated with a connection.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomsgr: take an arbitrary set of ports to avoid binding to
Sage Weil [Wed, 22 May 2013 00:20:45 +0000 (17:20 -0700)]
msgr: take an arbitrary set of ports to avoid binding to

We used to only need to avoid 2 ports; now we need 3.  Make it a set so we
don't have this problem later.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: bind front heartbeat messenger to public_addr
Sage Weil [Wed, 22 May 2013 00:10:01 +0000 (17:10 -0700)]
osd: bind front heartbeat messenger to public_addr

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: send hb front addr to monitor at boot
Sage Weil [Tue, 21 May 2013 23:44:00 +0000 (16:44 -0700)]
osd: send hb front addr to monitor at boot

We still aren't binding it to anything yet, or putting it in the OSDMap.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: create front and back hb messenger instances
Sage Weil [Tue, 21 May 2013 23:43:24 +0000 (16:43 -0700)]
osd: create front and back hb messenger instances

The hb_front messenger is not used yet.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd/OSDMap: encode front heartbeat addr
Sage Weil [Tue, 21 May 2013 23:48:43 +0000 (16:48 -0700)]
osd/OSDMap: encode front heartbeat addr

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd/OSDMap: hb_addr -> hb_back_addr
Sage Weil [Tue, 21 May 2013 23:39:00 +0000 (16:39 -0700)]
osd/OSDMap: hb_addr -> hb_back_addr

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd/OSDMap: new_hb_up -> new_hb_back_up
Sage Weil [Tue, 21 May 2013 22:41:46 +0000 (15:41 -0700)]
osd/OSDMap: new_hb_up -> new_hb_back_up

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd/OSDMap: new_up_internal -> new_up_cluster
Sage Weil [Wed, 22 May 2013 23:03:36 +0000 (16:03 -0700)]
osd/OSDMap: new_up_internal -> new_up_cluster

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: Add asserts for seg faults caused by corrupt OSDs
David Zafman [Wed, 22 May 2013 05:10:41 +0000 (22:10 -0700)]
osd: Add asserts for seg faults caused by corrupt OSDs

fixes: #5139

Signed-off-by: David Zafman <david.zafman@inktank.com>
12 years agoosd: skip mark-me-down message if osd is not up
Sage Weil [Wed, 22 May 2013 22:03:50 +0000 (15:03 -0700)]
osd: skip mark-me-down message if osd is not up

Fixes crash when the OSD has not successfully booted and gets a
SIGINT or SIGTERM.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd, mds: shut down async signal handler on exit
Sage Weil [Wed, 22 May 2013 21:56:24 +0000 (14:56 -0700)]
osd, mds: shut down async signal handler on exit

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorbd image_read.sh: ensure rbd is loaded
Alex Elder [Wed, 22 May 2013 21:50:19 +0000 (16:50 -0500)]
rbd image_read.sh: ensure rbd is loaded

Make sure rbd is loaded before proceeding with the script.

Signed-off-by: Alex Elder <elder@inktank.com>
12 years agomessages/MOSDMarkMeDown: fix uninit field
Sage Weil [Wed, 22 May 2013 21:29:37 +0000 (14:29 -0700)]
messages/MOSDMarkMeDown: fix uninit field

Fixes valgrind warning:
==14803== Use of uninitialised value of size 8
==14803==    at 0x12E7614: sctp_crc32c_sb8_64_bit (sctp_crc32.c:567)
==14803==    by 0x12E76F8: update_crc32 (sctp_crc32.c:609)
==14803==    by 0x12E7720: ceph_crc32c_le (sctp_crc32.c:733)
==14803==    by 0x105085F: ceph::buffer::list::crc32c(unsigned int) (buffer.h:427)
==14803==    by 0x115D7B2: Message::calc_front_crc() (Message.h:441)
==14803==    by 0x1159BB0: Message::encode(unsigned long, bool) (Message.cc:170)
==14803==    by 0x1323934: Pipe::writer() (Pipe.cc:1524)
==14803==    by 0x13293D9: Pipe::Writer::entry() (Pipe.h:59)
==14803==    by 0x120A398: Thread::_entry_func(void*) (Thread.cc:41)
==14803==    by 0x503BE99: start_thread (pthread_create.c:308)
==14803==    by 0x6C6E4BC: clone (clone.S:112)

Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomds: weaken reconnect assertion
Sage Weil [Wed, 22 May 2013 21:11:40 +0000 (14:11 -0700)]
mds: weaken reconnect assertion

See #5031.  This appears to be populated with another mds's mdsdir; just
not asserting avoids the problem for the time being.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #316 from ceph/wip-sysvinit
Sage Weil [Wed, 22 May 2013 20:25:42 +0000 (13:25 -0700)]
Merge pull request #316 from ceph/wip-sysvinit

Reviewed-by: Dan Mick <dan.mick@inktank.com>
12 years agosysvinit: fix osd weight calculation on remote hosts 316/head
Sage Weil [Wed, 22 May 2013 16:47:29 +0000 (09:47 -0700)]
sysvinit: fix osd weight calculation on remote hosts

We need to do df on the remote host, not locally.

Simlarly, the ceph command uses the osd key, which exists remotely; run it there.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agosysvinit: use known hostname $host instead of (incorrectly) recalculating
Sage Weil [Wed, 22 May 2013 16:47:03 +0000 (09:47 -0700)]
sysvinit: use known hostname $host instead of (incorrectly) recalculating

We would need to do hostname -s on the remote node, not the local one.
But we already have $host; use it!

Reported-by: Xiaoxi Chen <xiaoxi.chen@intel.com>
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #314 from ceph/wip-4228
Sage Weil [Wed, 22 May 2013 17:33:35 +0000 (10:33 -0700)]
Merge pull request #314 from ceph/wip-4228

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoOSDMonitor: skip new pools in update_pools_status() and get_pools_health()
Samuel Just [Tue, 21 May 2013 22:22:56 +0000 (15:22 -0700)]
OSDMonitor: skip new pools in update_pools_status() and get_pools_health()

New pools won't be full.  mon->pgmon()->pg_map.pg_pool_sum[poolid] will
implicitly create an entry for poolid causing register_new_pgs() to assume that
the newly created pgs in the new pool are in fact a result of a split
preventing MOSDPGCreate messages from being sent out.

Fixes: #4813
Backport: cuttlefish
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoceph-syn: specify which types of addresses to pick 314/head
Joao Eduardo Luis [Wed, 22 May 2013 16:52:27 +0000 (17:52 +0100)]
ceph-syn: specify which types of addresses to pick

Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agoceph-mds: specify which types of addresses to pick
Joao Eduardo Luis [Wed, 22 May 2013 16:52:15 +0000 (17:52 +0100)]
ceph-mds: specify which types of addresses to pick

Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agoMerge pull request #315 from ceph/wip-4507
Sage Weil [Wed, 22 May 2013 17:15:51 +0000 (10:15 -0700)]
Merge pull request #315 from ceph/wip-4507

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agomon: PaxosService: drop atomic_t on 'proposing' 315/head
Joao Eduardo Luis [Mon, 6 May 2013 16:10:15 +0000 (17:10 +0100)]
mon: PaxosService: drop atomic_t on 'proposing'

We don't need this to be atomic -- a simple boolean is enough.

Fixes: #4507
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agoceph-osd: specify which types of addresses to pick
Joao Eduardo Luis [Wed, 22 May 2013 16:52:03 +0000 (17:52 +0100)]
ceph-osd: specify which types of addresses to pick

Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agoceph-mon: only care about public addr during pick_addresses()
Joao Eduardo Luis [Mon, 6 May 2013 15:51:30 +0000 (16:51 +0100)]
ceph-mon: only care about public addr during pick_addresses()

Fixes: #4228
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agocommon: add mask argument to pick_addresses() to specify what we need
Joao Eduardo Luis [Mon, 6 May 2013 15:33:53 +0000 (16:33 +0100)]
common: add mask argument to pick_addresses() to specify what we need

Fixes: #4228
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
12 years agoceph: remove cli test
Sage Weil [Wed, 22 May 2013 16:39:11 +0000 (09:39 -0700)]
ceph: remove cli test

This is about to be removed by wip-ceph-cli anyway.  And it broke in
commit 132d5bf7f9af7de9e2028e20c95ba91637da5875.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #297 from dalgaaf/wip-da-CID-727982
Sage Weil [Wed, 22 May 2013 15:54:56 +0000 (08:54 -0700)]
Merge pull request #297 from dalgaaf/wip-da-CID-727982

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #310 from dalgaaf/wip-da-CID-fixes-4
Sage Weil [Wed, 22 May 2013 15:37:09 +0000 (08:37 -0700)]
Merge pull request #310 from dalgaaf/wip-da-CID-fixes-4

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agomds/Migrator.cc: fix possible dereference NULL return value 310/head
Danny Al-Gaaf [Wed, 22 May 2013 15:28:06 +0000 (17:28 +0200)]
mds/Migrator.cc: fix possible dereference NULL return value

CID 716997 (#1 of 1): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "in" when
  calling "MDSCacheObject::is_auth() const".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/Migrator.cc: fix possible dereference NULL return value
Danny Al-Gaaf [Wed, 22 May 2013 15:25:16 +0000 (17:25 +0200)]
mds/Migrator.cc: fix possible dereference NULL return value

ID 716998 (#1 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "in" when
  calling "operator <<(std::ostream &, CInode &)".

CID 716998 (#2 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "in" when
  calling "MDCache::add_replica_dir(ceph::buffer::list::iterator &,
  CInode *, int, std::list<Context *, std::allocator<Context *> > &)".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/Migrator.cc: delete some empty lines at EOF
Danny Al-Gaaf [Wed, 22 May 2013 15:23:40 +0000 (17:23 +0200)]
mds/Migrator.cc: delete some empty lines at EOF

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/Migrator.cc: fix possible dereference NULL return value
Danny Al-Gaaf [Wed, 22 May 2013 15:21:59 +0000 (17:21 +0200)]
mds/Migrator.cc: fix possible dereference NULL return value

CID 716999 (#1 of 1): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "in" when
  calling "CInode::put_stickydirs()".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agoMerge pull request #309 from dalgaaf/wip-da-CID-fixes-3-v2
Sage Weil [Wed, 22 May 2013 15:20:49 +0000 (08:20 -0700)]
Merge pull request #309 from dalgaaf/wip-da-CID-fixes-3-v2

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agomds/Migrator.cc: fix dereference NULL return value
Danny Al-Gaaf [Wed, 22 May 2013 15:17:01 +0000 (17:17 +0200)]
mds/Migrator.cc: fix dereference NULL return value

CID 717000 (#1 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "dir" when
  calling "operator <<(std::ostream &, CDir &)".

CID 717000 (#2 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "dir" when
  calling "Migrator::import_reverse_unfreeze(CDir *)".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/Migrator.cc: fix possible NULL pointer dereference
Danny Al-Gaaf [Wed, 22 May 2013 15:06:40 +0000 (17:06 +0200)]
mds/Migrator.cc: fix possible NULL pointer dereference

Move dout() calls behind the related asserts to prevent possible NULL
pointer dereference.

CID 717001 (#1 of 1): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "diri" when calling
  "operator <<(std::ostream &, CInode

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/Server.cc: fix possible NULL pointer dereference 309/head
Danny Al-Gaaf [Fri, 17 May 2013 12:38:24 +0000 (14:38 +0200)]
mds/Server.cc: fix possible NULL pointer dereference

Add asserts to solve these CID issues:

CID 717002 (#1 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "dir"
  when calling "CDir::lookup(std::string const &, snapid_t)".
CID 717002 (#2 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "dir"
  when calling "CDir::lookup(std::string const &, snapid_t)".

CID 717003 (#1 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "dn" when
  calling "operator <<(std::ostream &, CDentry &)"
CID 717003 (#2 of 2): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "straydn"
  when calling "CDentry::push_projected_linkage()".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agosrc/rbd.cc: silence CID COPY_PASTE_ERROR warning
Danny Al-Gaaf [Fri, 17 May 2013 12:15:23 +0000 (14:15 +0200)]
src/rbd.cc: silence CID COPY_PASTE_ERROR warning

CID 1021212 (#1 of 1): Copy-paste error (COPY_PASTE_ERROR)
  copy_paste_error: "r" in "r = -*__errno_location()" looks like
  a copy-paste error. Should it say "fd" instead?

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/MDS.cc: fix dereference null return value
Danny Al-Gaaf [Wed, 22 May 2013 13:42:52 +0000 (15:42 +0200)]
mds/MDS.cc: fix dereference null return value

Fix for:

returned_null: Function "SessionMap::get_session(entity_name_t)" returns
  null (checked 12 out of 14 times)

CID 739601 (#1 of 1): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null
  "this->sessionmap.get_session(entity_name_t::CLIENT(client.v))" when
  calling "MDS::send_message_client_counted(Message *, Session *)"

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomds/MDCache.cc: fix possible NULL pointer dereference
Danny Al-Gaaf [Wed, 15 May 2013 16:14:06 +0000 (18:14 +0200)]
mds/MDCache.cc: fix possible NULL pointer dereference

Assert if 'cur' is NULL.

CID 966616 (#1 of 1): Dereference null return value (NULL_RETURNS)
  dereference: Dereferencing a pointer that might be null "cur" when
  calling "CInode::is_dir()".

Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
12 years agomon: implement --extract-monmap <filename>
Sage Weil [Tue, 21 May 2013 21:36:11 +0000 (14:36 -0700)]
mon: implement --extract-monmap <filename>

This will make for a simpler process for
  http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-monitors-from-an-unhealthy-cluster

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit c0268e27497a4d8228ef54da9d4ca12f3ac1f1bf)

12 years agodoc: update mon cluster rescue process for cuttlefish+
Sage Weil [Tue, 21 May 2013 21:45:29 +0000 (14:45 -0700)]
doc: update mon cluster rescue process for cuttlefish+

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoFix usage for "ceph osd lost"
David Zafman [Tue, 21 May 2013 21:43:41 +0000 (14:43 -0700)]
Fix usage for "ceph osd lost"

Will be superceded, but use this commit to backport

Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
12 years agomon: implement --extract-monmap <filename>
Sage Weil [Tue, 21 May 2013 21:36:11 +0000 (14:36 -0700)]
mon: implement --extract-monmap <filename>

This will make for a simpler process for
  http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-monitors-from-an-unhealthy-cluster

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #306 from Elbandi/wip-fuse-ioctl
Sage Weil [Tue, 21 May 2013 21:26:40 +0000 (14:26 -0700)]
Merge pull request #306 from Elbandi/wip-fuse-ioctl

ceph-fuse: add ioctl support

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoceph-monstore-tool: implement getmonmap
Sage Weil [Tue, 21 May 2013 20:27:42 +0000 (13:27 -0700)]
ceph-monstore-tool: implement getmonmap

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorgw: protect ops log socket formatter
Yehuda Sadeh [Fri, 3 May 2013 19:57:00 +0000 (12:57 -0700)]
rgw: protect ops log socket formatter

Fixes: #4905
Ops log (through the unix domain socket) uses a formatter, which wasn't
protected.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agoceph-fuse: add ioctl support 306/head
Andras Elso [Tue, 21 May 2013 19:51:55 +0000 (21:51 +0200)]
ceph-fuse: add ioctl support

Signed-off-by: Andras Elso <elso.andras@gmail.com>
12 years agoceph-disk: fix stat errors with new suppress code
Sage Weil [Tue, 21 May 2013 19:52:03 +0000 (12:52 -0700)]
ceph-disk: fix stat errors with new suppress code

Broken by 225fefe5e7c997b365f481b6c4f66312ea28ed61.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorbd image_read.sh: test different clone object orders
Alex Elder [Tue, 21 May 2013 17:25:53 +0000 (12:25 -0500)]
rbd image_read.sh: test different clone object orders

An rbd clone image can be created with an object order that differs
from that of its parent.  This patch adds testing for that in
qa/workunits/rbd/image_read.sh.  By default, clone images will be
created with an object size twice as big as that of its parent.

For simplicity, when a clone's object order differs from its parent
the order will be either one more than or one less than that of its
parent image, meaning its object size is either double or half of
the size of objects used in the parent.

Signed-off-by: Alex Elder <elder@inktank.com>
12 years agorbd image_read.sh: add clone-of-clone testing
Alex Elder [Tue, 21 May 2013 15:05:03 +0000 (10:05 -0500)]
rbd image_read.sh: add clone-of-clone testing

Add testing to verify that a snapshot of a clone and a clone of
that snapshot both produce the correct results when read.

Signed-off-by: Alex Elder <elder@inktank.com>
12 years agorbd image_read.sh: allocate local file at create time
Alex Elder [Tue, 21 May 2013 15:05:03 +0000 (10:05 -0500)]
rbd image_read.sh: allocate local file at create time

Move the dd command that touches the last byte in a local file
into create_image() where it belongs (out of fill_original()).

Signed-off-by: Alex Elder <elder@inktank.com>
12 years agorbd image_read.sh: a few cleanups
Alex Elder [Tue, 21 May 2013 15:05:03 +0000 (10:05 -0500)]
rbd image_read.sh: a few cleanups

The function boolean_toggle() in qa/workunits/rbd/image_read.sh is
defined but never used.  My intentions were good though.  Fix it and
use it for argument parsing.

Change the minimum supported object order so it matches what the
command line interface enforces.

Assign the initial value of TEST_CLONES from the environment if it's
available.

Change defaults to use format 2 and test clones.

Output details about the parameters of the run even if not being
verbose.

Make the order of assignment of argument variables consistent.

And fix a typo unmap_image().

Signed-off-by: Alex Elder <elder@inktank.com>
12 years agorbd: prevent import of a dir
Sage Weil [Tue, 21 May 2013 19:15:49 +0000 (12:15 -0700)]
rbd: prevent import of a dir

Fixes: #2865
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-monstore-tool: be more verbose when replaying a trace
Sage Weil [Tue, 21 May 2013 18:04:25 +0000 (11:04 -0700)]
ceph-monstore-tool: be more verbose when replaying a trace

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-monstore-tool: compact command
Sage Weil [Tue, 21 May 2013 18:04:09 +0000 (11:04 -0700)]
ceph-monstore-tool: compact command

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-monstore-tool: dump-keys command
Sage Weil [Tue, 21 May 2013 18:03:34 +0000 (11:03 -0700)]
ceph-monstore-tool: dump-keys command

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #303 from ceph/wip-librbd-config-create
Josh Durgin [Tue, 21 May 2013 18:16:53 +0000 (11:16 -0700)]
Merge pull request #303 from ceph/wip-librbd-config-create

Reviewed-by: Sage Weil <sage.weil@inktank.com>
12 years agoMerge branch 'next'
Sage Weil [Tue, 21 May 2013 15:26:57 +0000 (08:26 -0700)]
Merge branch 'next'

Conflicts:
debian/ceph.prerm

12 years agoMerge pull request #304 from javacruft/wip-invoke-rc.d
Sage Weil [Tue, 21 May 2013 15:25:21 +0000 (08:25 -0700)]
Merge pull request #304 from javacruft/wip-invoke-rc.d

Use invoke-rc.d in maintainer scripts

12 years agoos/LevelDBStore: fix compression selection
Sage Weil [Tue, 21 May 2013 15:16:56 +0000 (08:16 -0700)]
os/LevelDBStore: fix compression selection

We were always disabling compression.

Fixes: #5131
Reported-by: Sylvain Munaut <s.munaut@whatever-company.com>
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoUse invoke-rc.d in maintainer scripts 304/head
James Page [Tue, 21 May 2013 08:20:53 +0000 (09:20 +0100)]
Use invoke-rc.d in maintainer scripts

Upstart configurations and sysv init scripts should be started and stopped
using invoke-rc.d in maintainer scripts.

This ensures the correct behaviour across both Debian (sysv) and Ubuntu (upstart)
and in restricted environments such as schroot where start/stop of services from
maintainer scripts is normally disabled.

Signed-off-by: James Page <james.page@ubuntu.com>
12 years agoPG: kill some dead IndexedLog methods
Samuel Just [Mon, 20 May 2013 22:44:23 +0000 (15:44 -0700)]
PG: kill some dead IndexedLog methods

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
12 years agoOSD: kill old split code, it's been dead for a while
Samuel Just [Mon, 20 May 2013 22:19:35 +0000 (15:19 -0700)]
OSD: kill old split code, it's been dead for a while

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
12 years agoMerge pull request #260 from ceph/wip-suppress
Sage Weil [Mon, 20 May 2013 21:40:22 +0000 (14:40 -0700)]
Merge pull request #260 from ceph/wip-suppress

Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
12 years agodebian: stop sysvinit on ceph.prerm
Sage Weil [Mon, 20 May 2013 20:34:27 +0000 (13:34 -0700)]
debian: stop sysvinit on ceph.prerm

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomds: better error check on sessionmap load
Sage Weil [Mon, 20 May 2013 20:34:05 +0000 (13:34 -0700)]
mds: better error check on sessionmap load

Would have helped with #5104.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomon: be a bit more verbose about osd mark down events
Sage Weil [Mon, 20 May 2013 19:41:30 +0000 (12:41 -0700)]
mon: be a bit more verbose about osd mark down events

Put these in the cluster log; they are interesting.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMakefile: add -Wformat-security
Sage Weil [Mon, 20 May 2013 16:09:25 +0000 (09:09 -0700)]
Makefile: add -Wformat-security

Clean up the formatting a bit here too.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge remote-tracking branch 'gh/next'
Sage Weil [Mon, 20 May 2013 19:22:29 +0000 (12:22 -0700)]
Merge remote-tracking branch 'gh/next'

12 years agoMerge pull request #301 from javacruft/wip-upstart-tasks
Sage Weil [Mon, 20 May 2013 16:10:04 +0000 (09:10 -0700)]
Merge pull request #301 from javacruft/wip-upstart-tasks

Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoMerge pull request #300 from javacruft/wip-format-security
Sage Weil [Mon, 20 May 2013 16:07:10 +0000 (09:07 -0700)]
Merge pull request #300 from javacruft/wip-format-security

Fix -Werror=format-security errors

12 years agoceph df: fix si units for 'global' stats
Mike Kelly [Thu, 16 May 2013 16:29:50 +0000 (12:29 -0400)]
ceph df: fix si units for 'global' stats

si_t expects bytes, but it was being given kilobytes.

Signed-off-by: Mike Kelly <pioto@pioto.org>
(cherry picked from commit 0c2b738d8d07994fee4c73dd076ac9364a64bdb2)