]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
12 years agov0.54 v0.54
Gary Lowell [Tue, 13 Nov 2012 21:18:07 +0000 (13:18 -0800)]
v0.54

12 years agorgw: fix RGWCache api
Yehuda Sadeh [Tue, 13 Nov 2012 20:09:05 +0000 (12:09 -0800)]
rgw: fix RGWCache api

RGWCache api diverted form RGWRados, crippling the cache.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agorgw_cache: change call signature to overwrite rgw_rados put_obj_meta()
caleb miles [Fri, 26 Oct 2012 19:17:05 +0000 (15:17 -0400)]
rgw_cache: change call signature to overwrite rgw_rados put_obj_meta()

Signed-off-by: caleb miles <caleb.miles@inktank.com>
12 years agorgw: unquote etag for if-match
Yehuda Sadeh [Wed, 7 Nov 2012 23:39:56 +0000 (15:39 -0800)]
rgw: unquote etag for if-match

Fixes: #3453
Passed ETag for copy/get request may be quoted.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agorgw: use thread safe version of gmtime
Sylvain Munaut [Thu, 8 Nov 2012 20:11:59 +0000 (12:11 -0800)]
rgw: use thread safe version of gmtime

Use gmtime_r instead of gmtime.

Signed-off-by: Sylvain Munaut <s.munaut@whatever-company.com>
12 years agorgw: don't convert object mtime to UTC
Yehuda Sadeh [Wed, 7 Nov 2012 21:21:15 +0000 (13:21 -0800)]
rgw: don't convert object mtime to UTC

Fixes: #3452
When we read object info, don't try to convert mtime to
UTC, it's already in UTC.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agoMerge branch 'wip-client-leaks' into next
Sage Weil [Mon, 12 Nov 2012 23:02:51 +0000 (15:02 -0800)]
Merge branch 'wip-client-leaks' into next

12 years agoclient: fix null put in ~MetaSession
Sage Weil [Mon, 12 Nov 2012 23:02:41 +0000 (15:02 -0800)]
client: fix null put in ~MetaSession

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge branch 'wip-client-leaks' into next
Sage Weil [Sat, 10 Nov 2012 10:38:26 +0000 (02:38 -0800)]
Merge branch 'wip-client-leaks' into next

12 years agosi_t was not properly converting values < 100KB
Dan Mick [Sat, 10 Nov 2012 03:17:56 +0000 (19:17 -0800)]
si_t was not properly converting values < 100KB

Signed-off-by: Dan Mick <dan.mick@inktank.com>
12 years agoosdc/ObjectCacher: only call flush callback if we transitions to clean
Sage Weil [Sat, 10 Nov 2012 02:34:22 +0000 (18:34 -0800)]
osdc/ObjectCacher: only call flush callback if we transitions to clean

If we race with e.g. truncate and are in bh_write_commit but the oset
is already clean, we should not call the flush callback (again).

This is reproduced by:

 - kludging slow osd replies into the code (e.g., 2 second delay)
 - mount ceph-fuse with --client-oc-max-dirty-age 1
 - dd if=/dev/zero of=mnt/foo count=1
   sleep 1
   truncate --size 0 mnt/foo
 -> crash

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: ensure we don't leak MClientReply
Sage Weil [Fri, 9 Nov 2012 18:25:48 +0000 (10:25 -0800)]
client: ensure we don't leak MClientReply

We are careful to clear this reference when processing it.

Add an assert here.  There's no way we can get 2 quick replies because
of the kick-back below.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-fuse: fix leak of args
Sage Weil [Fri, 9 Nov 2012 19:32:44 +0000 (11:32 -0800)]
ceph-fuse: fix leak of args

Also fix up the helper we use to have fewer sharp edges.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosdc/ObjectCacher: fix leak on readahead
Sage Weil [Fri, 9 Nov 2012 19:02:51 +0000 (11:02 -0800)]
osdc/ObjectCacher: fix leak on readahead

If we initiate io (success == false) but have no waiter, we need to
delete the OSDRead.

This affects libcephfs/ceph-fuse, but not librbd, which does no readahead.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorbd: check for second argument to mv/rename
Josh Durgin [Fri, 9 Nov 2012 20:11:18 +0000 (12:11 -0800)]
rbd: check for second argument to mv/rename

Without this check, 'rbd mv foo' crashed trying to use a NULL char* as
a string.

Reported-by: Andrey Korolyov <andrey@xdel.ru>
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
12 years agoclient: fix SnapRealm leak
Sage Weil [Fri, 9 Nov 2012 18:12:21 +0000 (10:12 -0800)]
client: fix SnapRealm leak

Start ref count at 0; get_snap_realm() will increment it after alloc.

Fix the ref drop order so that the xlist is empty.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: debug SnapRealm reference counting
Sage Weil [Fri, 9 Nov 2012 18:09:53 +0000 (10:09 -0800)]
client: debug SnapRealm reference counting

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: fix leak of Cap
Sage Weil [Fri, 9 Nov 2012 18:02:59 +0000 (10:02 -0800)]
client: fix leak of Cap

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: fix leak of session release msg on session close
Sage Weil [Fri, 9 Nov 2012 18:01:48 +0000 (10:01 -0800)]
client: fix leak of session release msg on session close

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: only start invalidator thread if cb != NULL
Sage Weil [Fri, 9 Nov 2012 17:59:39 +0000 (09:59 -0800)]
client: only start invalidator thread if cb != NULL

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-fuse: deallocate messenger, g_ceph_context on stop
Sage Weil [Fri, 9 Nov 2012 17:52:08 +0000 (09:52 -0800)]
ceph-fuse: deallocate messenger, g_ceph_context on stop

This lets us use valgrind to find leaks.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: give get_caps() out-arg a less confusing name
Sage Weil [Fri, 9 Nov 2012 14:49:59 +0000 (06:49 -0800)]
client: give get_caps() out-arg a less confusing name

No functional change.

Call this arg "have" and not "got", since we only take a ref on what we
need.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: do not gratuitously drop FILE_CACHE ref in _read()
Sage Weil [Fri, 9 Nov 2012 14:48:10 +0000 (06:48 -0800)]
client: do not gratuitously drop FILE_CACHE ref in _read()

The get_caps() had a confusing out-arg called "got" that is really what
caps we *have*; it only takes a ref on the *need* cap.  We should only
put that one explicitly (CEPH_CAP_FILE_RD).  The _write() method already
does this properly, but _read() did not.

Fixes: #3470
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: assert cap refs don't go negative
Sage Weil [Fri, 9 Nov 2012 14:06:42 +0000 (06:06 -0800)]
client: assert cap refs don't go negative

This is the root cause of #3470.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorbd: fix snap unprotect, which was succeeding while clones existed
Dan Mick [Fri, 9 Nov 2012 01:13:29 +0000 (17:13 -0800)]
rbd: fix snap unprotect, which was succeeding while clones existed

1) use right snap id when forming parent spec to search for children
2) add test case for "unprotect with extant children"

Signed-off-by: Dan Mick <dan.mick@inktank.com>
12 years agoceph.spec.in: Remove ceph version requirement from ceph-fuse package.
Gary Lowell [Wed, 7 Nov 2012 20:41:10 +0000 (12:41 -0800)]
ceph.spec.in:  Remove ceph version requirement from ceph-fuse package.

The ceph-fuse rpm package now only requires ceph as a pre-req, not a specific
version.

12 years agorgw_admin: do not throw error when start-date and end-date are not
caleb miles [Tue, 23 Oct 2012 17:36:53 +0000 (13:36 -0400)]
rgw_admin: do not throw error when start-date and end-date are not
passed to usage::trim()

Signed-off-by: caleb miles <caleb.miles@inktank.com>
12 years agoclient: kick waiters for an mds session to open on mds recovery
Sage Weil [Wed, 7 Nov 2012 12:40:55 +0000 (04:40 -0800)]
client: kick waiters for an mds session to open on mds recovery

We already kicked waiters for request, but we need to kick waiters on open
too (e.g., a client trying to mount).

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoqa: disable xfstest 45 until mount issue is resolved on precise
Sage Weil [Wed, 7 Nov 2012 12:14:12 +0000 (04:14 -0800)]
qa: disable xfstest 45 until mount issue is resolved on precise

Meh

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agocls_rbd: send proper format of key to "last_read" for dir_list
Dan Mick [Tue, 6 Nov 2012 23:28:10 +0000 (15:28 -0800)]
cls_rbd: send proper format of key to "last_read" for dir_list

rbd ls of format-2 images was looping on the first 64 (when more than 64
were present).  The key name passed to the omap layer needs to always
contain the prefix, and the "inside-the-loop next-chunk" statement
was missing the "add the prefix" call.

Also, add a test for listing 100 images, format 1 and 2.

Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
12 years agorgw: fix multipart overwrite
Yehuda Sadeh [Wed, 24 Oct 2012 20:15:46 +0000 (13:15 -0700)]
rgw: fix multipart overwrite

Fixes: #3400
Removed a few lines of code that prematurely created the head
part of the final object (before creating the manifest).

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agorgw: don't reset multipart parts when updating their metadata
Yehuda Sadeh [Wed, 24 Oct 2012 19:56:59 +0000 (12:56 -0700)]
rgw: don't reset multipart parts when updating their metadata

Fixes: #3401
The problem was that put_obj_meta() was assuming object is going
to be reset, so it was resetting the object anyway. This is not
true when dealing with the immutable multipart upload parts.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agorgw: break out of read loop if we got zero bytes
Yehuda Sadeh [Wed, 24 Oct 2012 18:26:53 +0000 (11:26 -0700)]
rgw: break out of read loop if we got zero bytes

If the part that we're reading is corrupted and we end up
reading zero bytes, we need to exit, otherwise we'd just
loop forever.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agorbd: allow removal of image even if rbd_children deletion fails
Dan Mick [Tue, 6 Nov 2012 00:13:19 +0000 (16:13 -0800)]
rbd: allow removal of image even if rbd_children deletion fails

Users have been seeing failures where rbd rm is half-done; could be
because of outstanding watches on the rbd_header object.  The state
is that rbd_children no longer contains the child, but other pieces
remain; remove considers this a failure.

Fix: test for ENOENT from remove_child, and treat that as an ignorable
error and drive on.  Simulate this in copy.sh by removing the
rbd_children object altogether, which also results in ENOENT return
from remove_child.

Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
12 years agoPG::merge_old_entry: fix case for divergent prior_version
Samuel Just [Fri, 2 Nov 2012 21:13:33 +0000 (14:13 -0700)]
PG::merge_old_entry: fix case for divergent prior_version

Previously, we asserted that a log entry with a divergent
prior_version must be a clone.  Consider the following
case:

6'11(6'2)  m foo
7'12(6'3) m bar
7'13(7'12) m bar

If this is merged with:

6'11(6'2)  m foo
8'12(6'4) m baz

we will hit the assert.  The correct behavior is simply to remove
the object as in the clone case.

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoPG: use remove_object_with_snap_hardlinks for divergent objects
Samuel Just [Fri, 2 Nov 2012 20:02:15 +0000 (13:02 -0700)]
PG: use remove_object_with_snap_hardlinks for divergent objects

Otherwise, we end up leaving snap hardlinks in the snapshot
index directories.  This eventually results in an EEXIST error
when we attempt to re-link the clone into place during
recovery.

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
12 years agoceph-disk-activate: avoid duplicating mounts if already activated
Sage Weil [Tue, 30 Oct 2012 21:17:56 +0000 (14:17 -0700)]
ceph-disk-activate: avoid duplicating mounts if already activated

If the given device is already mounted at the target location, do not
mount --move it again and create a bunch of dup entries in the /etc/mtab
and kernel mount table.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoPG: requeue snap_trimmer after scrub finishes
Mike Ryan [Wed, 31 Oct 2012 18:36:49 +0000 (11:36 -0700)]
PG: requeue snap_trimmer after scrub finishes

Previously the snap_trimmer would continuously requeue itself until the
end of scrub. This degrades performance and fills up logs for No Good
Reason.

Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
12 years agoceph-disk-prepare: poke kernel into refreshing partition tables
Sage Weil [Fri, 26 Oct 2012 04:21:18 +0000 (21:21 -0700)]
ceph-disk-prepare: poke kernel into refreshing partition tables

Prod the kernel to refresh the partition table after we create one.  The
partprobe program is packaged with parted, which we already use, so this
introduces no new dependency.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-disk-prepare: fix journal partition creation
Sage Weil [Fri, 26 Oct 2012 04:20:21 +0000 (21:20 -0700)]
ceph-disk-prepare: fix journal partition creation

The end value needs to have + to indicate it is relative to wherever the
start is.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoceph-disk-prepare: assume parted failure means no partition table
Sage Weil [Fri, 26 Oct 2012 01:14:47 +0000 (18:14 -0700)]
ceph-disk-prepare: assume parted failure means no partition table

If the disk has no valid label we get an error like

  Error: /dev/sdi: unrecognised disk label

Assume any error we get is that and go with an id label of 1.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: make pool_snap_info_t encoding backward compatible
Sage Weil [Mon, 29 Oct 2012 18:03:46 +0000 (11:03 -0700)]
osd: make pool_snap_info_t encoding backward compatible

Way back in fc869dee1e8a1c90c93cb7e678563772fb1c51fb (v0.42) when we redid
the osd type encoding we forgot to make this conditionally encode the old
format for old clients.  In particular, this means that kernel clients
will fail to decode the osdmap if there is a rados pool with a pool-level
snapshot defined.

Fixes: #3290
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agomon: fix leading error string from 'ceph report'
Sage Weil [Fri, 26 Oct 2012 21:55:31 +0000 (14:55 -0700)]
mon: fix leading error string from 'ceph report'

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoosd: fix populate_obc_watchers() assert
Sage Weil [Thu, 25 Oct 2012 00:00:01 +0000 (17:00 -0700)]
osd: fix populate_obc_watchers() assert

There is one case where populate_obc_watchers gets called when the object
is missing: during a revert.  And in that case we *should* do the populate,
since all that is getting reverted is the object version.

Fixes: #3405
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Sam Just <sam.just@inktank.com>
12 years agoosd: drop conditional check in populate_obc_watchers
Sage Weil [Mon, 22 Oct 2012 17:45:36 +0000 (10:45 -0700)]
osd: drop conditional check in populate_obc_watchers

Turn these into asserts.  The only two callers are create_object_context()
and get_object_context(), and they only get called when the object is no
longer missing.

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
12 years agoosd: populate obc watchers even when degraded
Sage Weil [Mon, 22 Oct 2012 17:45:20 +0000 (10:45 -0700)]
osd: populate obc watchers even when degraded

Bug #3142 appears to be caused by the following sequence:

 - object X missing on primary and replica
 - [assert-ver,watch], notify, unwatch requests come in, get deferred
 - object is recovered on primary, !missing, create_object_context
   - populate_obc_watchers() does nothing, since still degraded
 - notify happens now (odd but ok?)
 - replica recovered, !degraded
 - watch skips bc of bad assert
 - unwatch trips up on an assert because populate_obc_watchers never
   ran

Fix this by populating the obc watcher when !missing, not when
!degraded.  This conditional dates back to Sam's original watch/notify
cleanup in October 2011.

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
12 years agotest/libcephfs: Fix telldir/seekdir test
Sam Lang [Wed, 17 Oct 2012 17:45:20 +0000 (12:45 -0500)]
test/libcephfs: Fix telldir/seekdir test

Signed-off-by: Sam Lang <sam.lang@inktank.com>
12 years agoaddr_parsing: make , and ; and ' ' all delimiters
Sage Weil [Thu, 18 Oct 2012 00:44:12 +0000 (17:44 -0700)]
addr_parsing: make , and ; and ' ' all delimiters

Instead of just ,.  Currently "foo.com, bar.com" will fail because of the
space after the comma.  This patches fixes that, and makes all delim
chars interchangeable.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoradosgw: fix compile warning
Sage Weil [Wed, 17 Oct 2012 00:27:28 +0000 (17:27 -0700)]
radosgw: fix compile warning

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMerge branch 'next'
Gary Lowell [Tue, 16 Oct 2012 23:27:21 +0000 (23:27 +0000)]
Merge branch 'next'

12 years agodoc: Updated the cephx section of the toc for cluster ops.
John Wilkins [Tue, 16 Oct 2012 22:24:11 +0000 (15:24 -0700)]
doc: Updated the cephx section of the toc for cluster ops.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Did a little clean-up work in the cephx guide.
John Wilkins [Tue, 16 Oct 2012 22:23:34 +0000 (15:23 -0700)]
doc: Did a little clean-up work in the cephx guide.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Added a new intro for cephx authentication.
John Wilkins [Tue, 16 Oct 2012 22:22:25 +0000 (15:22 -0700)]
doc: Added a new intro for cephx authentication.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agorgw: multiple coverity fixes
Yehuda Sadeh [Tue, 16 Oct 2012 21:13:01 +0000 (14:13 -0700)]
rgw: multiple coverity fixes

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agomds: explicitly queue messages for unconnected clients
Sage Weil [Tue, 16 Oct 2012 20:03:53 +0000 (13:03 -0700)]
mds: explicitly queue messages for unconnected clients

Previously, the messenger would queue messages for a destination that
didn't exist when you were a server; that changed a while back with the
wip-msgr merge (circa v0.52).  The result is that when we force open
client sessions and queue messages, they are dropped on the floor and the
client--when it does connect--gets confusing stuff from the MDS.

Instead, explicitly queue and send these messages.  Also, *always* send
via the Connection* instead of the inst.

Fixes: #2681
Signed-off-by: Sage Weil <sage@inktank.com>
12 years agov0.43 v0.53
Gary Lowell [Tue, 16 Oct 2012 17:42:36 +0000 (17:42 +0000)]
v0.43

12 years agoMerge remote-tracking branch 'gh/wip-fedora18' into next
Sage Weil [Tue, 16 Oct 2012 16:05:55 +0000 (09:05 -0700)]
Merge remote-tracking branch 'gh/wip-fedora18' into next

12 years agoradosgw-admin manpage: Fix broken quotes
Dan Mick [Tue, 16 Oct 2012 01:18:18 +0000 (18:18 -0700)]
radosgw-admin manpage: Fix broken quotes

Signed-off-by: Dan Mick <dan.mick@inktank.com>
12 years agoadmin_socket: fix '0' protocol version
Sage Weil [Mon, 15 Oct 2012 23:37:05 +0000 (16:37 -0700)]
admin_socket: fix '0' protocol version

Broken by 895e24d198ced83ab7fed3725f12f75e3bc97b0b.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: avoid possible null deref
Sage Weil [Mon, 15 Oct 2012 21:22:31 +0000 (14:22 -0700)]
client: avoid possible null deref

CID 716910 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
At (6): Dereferencing null pointer "mds_session".

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: fix shadowing in inode ctor
Sage Weil [Mon, 15 Oct 2012 21:20:51 +0000 (14:20 -0700)]
client: fix shadowing in inode ctor

CID 728080 (#1 of 1): Incorrect sizeof expression (BAD_SIZEOF)
Taking the size of pointer parameter "layout" is suspicious.

At (2): Non-static class member field "layout.fl_stripe_unit" is not initialized in this constructor nor in any functions that it calls.
At (4): Non-static class member field "layout.fl_stripe_count" is not initialized in this constructor nor in any functions that it calls.
At (6): Non-static class member field "layout.fl_object_size" is not initialized in this constructor nor in any functions that it calls.
At (8): Non-static class member field "layout.fl_cas_hash" is not initialized in this constructor nor in any functions that it calls.
At (10): Non-static class member field "layout.fl_object_stripe_unit" is not initialized in this constructor nor in any functions that it calls.
At (12): Non-static class member field "layout.fl_unused" is not initialized in this constructor nor in any functions that it calls.
CID 717206 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (14): Non-static class member field "layout.fl_pg_pool" is not initialized in this constructor nor in any functions that it calls.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoclient: init readdir fields
Sage Weil [Mon, 15 Oct 2012 21:19:10 +0000 (14:19 -0700)]
client: init readdir fields

At (2): Non-static class member "readdir_offset" is not initialized in this constructor nor in any functions that it calls.
At (4): Non-static class member "readdir_end" is not initialized in this constructor nor in any functions that it calls.
At (6): Non-static class member "readdir_num" is not initialized in this constructor nor in any functions that it calls.
CID 717207 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (8): Non-static class member "tid" is not initialized in this constructor nor in any functions that it calls.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agoMakefile: Add CRYPTO_C(XX)FLAGS to librdb
Gary Lowell [Thu, 11 Oct 2012 18:05:10 +0000 (11:05 -0700)]
Makefile:  Add CRYPTO_C(XX)FLAGS to librdb

12 years agoMakefiles: Add ar-lib to .gitignore.
Gary Lowell [Tue, 9 Oct 2012 22:09:11 +0000 (15:09 -0700)]
Makefiles:  Add ar-lib to .gitignore.

12 years agoautogen.sh: On some platforms, the m4 is created earlier.
Gary Lowell [Tue, 9 Oct 2012 20:36:43 +0000 (13:36 -0700)]
autogen.sh:  On some platforms, the m4 is created earlier.

12 years agoautogen.sh: Create m4 directory for leveldb submodule.
Gary Lowell [Tue, 9 Oct 2012 20:10:15 +0000 (13:10 -0700)]
autogen.sh:  Create m4 directory for leveldb submodule.

12 years agoMakefiles: Update submodule reference to latestes for leveldb.
Gary Lowell [Tue, 9 Oct 2012 19:24:16 +0000 (12:24 -0700)]
Makefiles:  Update submodule reference to latestes for leveldb.

12 years agoMakefile: update submodule reference for leveldb.
Gary Lowell [Tue, 9 Oct 2012 16:28:22 +0000 (09:28 -0700)]
Makefile: update submodule reference for leveldb.

12 years agoleveldb: fix-up submodule entry.
Gary Lowell [Tue, 9 Oct 2012 06:45:45 +0000 (23:45 -0700)]
leveldb: fix-up submodule entry.

12 years agoMakefile: Improve test for boost system library.
Gary Lowell [Tue, 9 Oct 2012 05:56:05 +0000 (22:56 -0700)]
Makefile: Improve test for boost system library.

12 years agoMakefiles: Missing boost library should not be fatal.
Gary Lowell [Tue, 9 Oct 2012 02:18:56 +0000 (19:18 -0700)]
Makefiles:  Missing boost library should not be fatal.

12 years agoMakefiles: ignore the m4 macro directory
Gary Lowell [Tue, 9 Oct 2012 01:12:06 +0000 (18:12 -0700)]
Makefiles:  ignore the m4 macro directory

12 years agoMakefile: Updates to eliminates warnings, add test for boost system lib.
Gary Lowell [Mon, 8 Oct 2012 17:04:25 +0000 (10:04 -0700)]
Makefile:  Updates to eliminates warnings, add test for boost system lib.

12 years agocls_rgw: init var in ctor
Sage Weil [Mon, 15 Oct 2012 21:14:28 +0000 (14:14 -0700)]
cls_rgw: init var in ctor

CID 727992 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (2): Non-static class member "tag_timeout" is not initialized in this constructor nor in any functions that it calls.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorgw: don't add port to url if already has one
Yehuda Sadeh [Mon, 15 Oct 2012 16:43:47 +0000 (09:43 -0700)]
rgw: don't add port to url if already has one

Fixes: #3296
Specifically, is host name string already has ':', then
don't try to append theport (swift auth).

backport: argonaut
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agoceph-disk-prepare, debian/control: Support external journals.
Tommi Virtanen [Fri, 5 Oct 2012 17:57:42 +0000 (10:57 -0700)]
ceph-disk-prepare, debian/control: Support external journals.

Previously, ceph-disk-* would only let you use a journal that was a
file inside the OSD data directory. With this, you can do:

  ceph-disk-prepare /dev/sdb /dev/sdb

to put the journal as a second partition on the same disk as the OSD
data (might save some file system overhead), or, more interestingly:

  ceph-disk-prepare /dev/sdb /dev/sdc

which makes it create a new partition on /dev/sdc to use as the
journal. Size of the partition is decided by $osd_journal_size.
/dev/sdc must be a GPT-format disk. Multiple OSDs may share the same
journal disk (using separate partitions); this way, a single fast SSD
can serve as journal for multiple spinning disks.

The second use case currently requires parted, so a Recommends: for
parted has been added to Debian packaging.

Closes: #3078
Closes: #3079
Signed-off-by: Tommi Virtanen <tv@inktank.com>
12 years agologrotate: fix bash syntax
Chris Dunlop [Sun, 14 Oct 2012 05:33:47 +0000 (22:33 -0700)]
logrotate: fix bash syntax

Introduced by 32a6394be0725b4742ebe87d7537b98c7025e4f6.

Signed-off-by: Chris Dunlop <chris@onthe.net.au>
12 years agodoc: remove cephfs warning
Sage Weil [Sun, 14 Oct 2012 03:13:35 +0000 (20:13 -0700)]
doc: remove cephfs warning

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agodoc: fix file system recs
Sage Weil [Sun, 14 Oct 2012 03:12:48 +0000 (20:12 -0700)]
doc: fix file system recs

- drop xattr warning; this is not an issue with the leveldb stuff.
- the ext3 vs xattr discussion was somewhat inaccurate.  also, no longer
  relevant.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agorgw: replace bucket creation with explicit pool creation
Yehuda Sadeh [Fri, 12 Oct 2012 21:01:03 +0000 (14:01 -0700)]
rgw: replace bucket creation with explicit pool creation

Following a recent cleanup, usage should create a pool and
not a bucket.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agoMerge branch 'wip-fix-getdents'
Sam Lang [Thu, 11 Oct 2012 19:19:04 +0000 (14:19 -0500)]
Merge branch 'wip-fix-getdents'

12 years agorbd: don't issue usage on errors
Dan Mick [Wed, 10 Oct 2012 17:41:05 +0000 (10:41 -0700)]
rbd: don't issue usage on errors

Change bare calls to usage() to an informative targeted error message
Remove all calls to usage() except when requested with -h/--help
Regularize all errors to start with rbd:
Remove a few commented cerrs, wrap cerr calls at 80 cols

Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
12 years agoMerge branch 'master' of https://github.com/ceph/ceph
John Wilkins [Wed, 10 Oct 2012 22:16:17 +0000 (15:16 -0700)]
Merge branch 'master' of https://github.com/ceph/ceph

12 years agodoc: Added radosgw temp remove.
John Wilkins [Wed, 10 Oct 2012 22:15:32 +0000 (15:15 -0700)]
doc: Added radosgw temp remove.

fixes: #3278

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: Minor clean-up.
John Wilkins [Wed, 10 Oct 2012 22:14:05 +0000 (15:14 -0700)]
doc: Minor clean-up.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agodoc: minor clean-up.
John Wilkins [Wed, 10 Oct 2012 22:13:41 +0000 (15:13 -0700)]
doc: minor clean-up.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agorgw: fix compilation
Noah Watkins [Wed, 10 Oct 2012 21:59:16 +0000 (14:59 -0700)]
rgw: fix compilation

Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
12 years agoMerge branch 'master' of https://github.com/ceph/ceph
John Wilkins [Wed, 10 Oct 2012 21:38:50 +0000 (14:38 -0700)]
Merge branch 'master' of https://github.com/ceph/ceph

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agoMerge branch 'master' of https://github.com/ceph/ceph
John Wilkins [Wed, 10 Oct 2012 21:36:51 +0000 (14:36 -0700)]
Merge branch 'master' of https://github.com/ceph/ceph

12 years agoMerge branch 'wip-rbd-openstack-doc'
John Wilkins [Wed, 10 Oct 2012 21:36:13 +0000 (14:36 -0700)]
Merge branch 'wip-rbd-openstack-doc'

12 years agomon: drop command replies on paxos reset
Sage Weil [Tue, 9 Oct 2012 00:14:22 +0000 (17:14 -0700)]
mon: drop command replies on paxos reset

If paxos resets, do not send the reply for the commit we were waiting for;
let the command be reprocessed and re-proposed.

Among other things, this could lead to nondeterministic results for
'ceph osd create <uuid>'.

Signed-off-by: Sage Weil <sage@inktank.com>
12 years agodoc: Editing and cleanup.
John Wilkins [Wed, 10 Oct 2012 20:22:47 +0000 (13:22 -0700)]
doc: Editing and cleanup.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
12 years agotest: Allow randomized tests to be repeatable
Sam Lang [Wed, 10 Oct 2012 02:11:19 +0000 (21:11 -0500)]
test: Allow randomized tests to be repeatable

Outputs the random number used for the Dir_ls
test and allows setting the value through an
environment variable.

Signed-off-by: Sam Lang <sam.lang@inktank.com>
12 years agoclient: Reset cache_name pos on dirp
Sam Lang [Tue, 9 Oct 2012 22:34:48 +0000 (17:34 -0500)]
client: Reset cache_name pos on dirp

Reset the at_cache_name field on the directory
stream pointer for rewinddir.
This fixes a bug where getdents after readdir at
the end of the stream would return invalid
results after rewinddir had been called.

Signed-off-by: Sam Lang <sam.lang@inktank.com>
12 years agorbd cli tests: copy.sh was looking for old version of rbd ls -l output
Dan Mick [Wed, 10 Oct 2012 00:13:03 +0000 (17:13 -0700)]
rbd cli tests: copy.sh was looking for old version of rbd ls -l output

Signed-off-by: Dan Mick <dan.mick@inktank.com>
12 years agoclean up of rbd functionality script
tamil [Tue, 9 Oct 2012 23:42:57 +0000 (16:42 -0700)]
clean up of rbd functionality script

Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
12 years agocleaned up the perl module
tamil [Tue, 9 Oct 2012 23:40:55 +0000 (16:40 -0700)]
cleaned up the perl module

Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
12 years agocleaned up the script
tamil [Tue, 9 Oct 2012 22:50:29 +0000 (15:50 -0700)]
cleaned up the script

Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
12 years agoradosgw-admin: don't try to parse date if wasn't specified
Yehuda Sadeh [Tue, 9 Oct 2012 21:56:28 +0000 (14:56 -0700)]
radosgw-admin: don't try to parse date if wasn't specified

This fixes a regression following the merge of wip-admin-rest.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
12 years agoceph-debugpack: updates
Sage Weil [Tue, 9 Oct 2012 21:10:48 +0000 (14:10 -0700)]
ceph-debugpack: updates

- avoid copying data around; tar things directly into the tgz
- 'ceph report' instead of all the little bits
- unrotated logs only
- ensure target doesn't already exist

Signed-off-by: Sage Weil <sage@inktank.com>