]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
13 years agolockdep: enable in common_init
Sage Weil [Thu, 28 Jun 2012 23:23:30 +0000 (16:23 -0700)]
lockdep: enable in common_init

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agodoc: fixed --cap error and a few additional bits of cleanup.
John Wilkins [Mon, 2 Jul 2012 20:05:26 +0000 (13:05 -0700)]
doc: fixed --cap error and a few additional bits of cleanup.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: Added sudo and cleaner instruction for unmap.
John Wilkins [Mon, 2 Jul 2012 15:55:36 +0000 (08:55 -0700)]
doc: Added sudo and cleaner instruction for unmap.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: updated usage on RBD kernel object commands.
John Wilkins [Mon, 2 Jul 2012 15:35:10 +0000 (08:35 -0700)]
doc: updated usage on RBD kernel object commands.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agoMerge pull request #15 from fghaas/wip-rgw-doc
John Wilkins [Mon, 2 Jul 2012 15:07:23 +0000 (08:07 -0700)]
Merge pull request #15 from fghaas/wip-rgw-doc

radosgw documentation improvements

13 years agoMerge pull request #17 from fghaas/rgw-manpage
Sage Weil [Mon, 2 Jul 2012 15:03:33 +0000 (08:03 -0700)]
Merge pull request #17 from fghaas/rgw-manpage

doc: drop mention of MDS capabilities from radosgw man page

13 years agodoc: drop mention of MDS capabilities from radosgw man page 17/head
Florian Haas [Mon, 2 Jul 2012 14:54:08 +0000 (16:54 +0200)]
doc: drop mention of MDS capabilities from radosgw man page

Signed-off-by: Florian Haas <florian@hastexo.com>
13 years agodoc: add design doc for rbd layering
Josh Durgin [Sat, 30 Jun 2012 02:20:33 +0000 (19:20 -0700)]
doc: add design doc for rbd layering

I'm still not sure about the names for the command line
operations, but they can be changed later if better ones
come up.

Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
13 years agofilestore: set min flush size
Sage Weil [Mon, 7 May 2012 21:37:38 +0000 (14:37 -0700)]
filestore: set min flush size

If a write is smaller than some threshold, do not bother to flush it; let
the fs do that (efficiently, we hope) at commit time.  Focus on the big
writes.

Signed-off-by: Sage Weil <sage@newdream.net>
13 years agoPG: reset_recovery_pointers in activate if missing is empty
Samuel Just [Fri, 29 Jun 2012 22:49:41 +0000 (15:49 -0700)]
PG: reset_recovery_pointers in activate if missing is empty

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agovstart.sh: don't clobber keyring if not -n
Dan Mick [Fri, 29 Jun 2012 22:25:52 +0000 (15:25 -0700)]
vstart.sh: don't clobber keyring if not -n

Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
13 years agodoc: document new 'osd crush move ...' command
Sage Weil [Fri, 29 Jun 2012 21:22:14 +0000 (14:22 -0700)]
doc: document new 'osd crush move ...' command

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: fix 'osd crush move <item> <loc ...>'
Sage Weil [Fri, 29 Jun 2012 21:16:05 +0000 (14:16 -0700)]
mon: fix 'osd crush move <item> <loc ...>'

 - fix arg count check
 - avoid updating crush map if it is already correct

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoMerge branch 'wip-crushwrapper2'
Sage Weil [Fri, 29 Jun 2012 19:34:13 +0000 (12:34 -0700)]
Merge branch 'wip-crushwrapper2'

Reviewed-by: Sage Weil <sage@inktank.com>
13 years agomon: add 'osd crush move <name> <loc ...>' command
Sage Weil [Fri, 29 Jun 2012 17:53:11 +0000 (10:53 -0700)]
mon: add 'osd crush move <name> <loc ...>' command

Move an existing bucket to a new position in the hierarchy.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocrush: add move_bucket() method
Caleb Miles [Fri, 29 Jun 2012 17:54:16 +0000 (10:54 -0700)]
crush: add move_bucket() method

Move an existing bucket to a new location in the hierarchy.

Signed-off-by: Caleb Miles <caselim@gmail.com>
13 years agocrush: get_loc -> get_immediate_parent
Caleb Miles [Fri, 29 Jun 2012 17:54:08 +0000 (10:54 -0700)]
crush: get_loc -> get_immediate_parent

Signed-off-by: Caleb Miles <caselim@gmail.com>
13 years agoPG::merge_old_entry: handle clone prior_version case
Samuel Just [Fri, 22 Jun 2012 16:07:45 +0000 (09:07 -0700)]
PG::merge_old_entry: handle clone prior_version case

A clone can have a prior_version after log_tail and still not have
a corresponding log entry since the prior_version would be the
head object.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoReplicatedPG: adjust log.complete_to based on rmissing
Samuel Just [Tue, 19 Jun 2012 19:48:23 +0000 (12:48 -0700)]
ReplicatedPG: adjust log.complete_to based on rmissing

log.complete_to can actually move backwards due to objects
missing because of divergent entries.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoReplicatedPG: clear peer_(missing|log)_requested in check_recovery_sources
Samuel Just [Mon, 25 Jun 2012 04:38:57 +0000 (21:38 -0700)]
ReplicatedPG: clear peer_(missing|log)_requested in check_recovery_sources

Otherwise, we might fail to re-request the information from a
previously down osd.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoPG: check_recovery_sources on each map
Samuel Just [Wed, 20 Jun 2012 16:29:18 +0000 (09:29 -0700)]
PG: check_recovery_sources on each map

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agodoc: radosgw: further simplify Apache rewrite rule 15/head
Florian Haas [Fri, 29 Jun 2012 05:50:50 +0000 (07:50 +0200)]
doc: radosgw: further simplify Apache rewrite rule

Sufficient to just pass the query string, drop params.

Signed-off-by: Florian Haas <florian@hastexo.com>
13 years agoMerge pull request #16 from fghaas/doc-osd
Sage Weil [Fri, 29 Jun 2012 05:25:14 +0000 (22:25 -0700)]
Merge pull request #16 from fghaas/doc-osd

doc: document osd tell bench

13 years agodoc: document osd tell bench 16/head
Florian Haas [Thu, 28 Jun 2012 19:07:22 +0000 (21:07 +0200)]
doc: document osd tell bench

Signed-off-by: Florian Haas <florian@hastexo.com>
13 years agodoc: minor edits.
John Wilkins [Thu, 28 Jun 2012 18:41:08 +0000 (11:41 -0700)]
doc: minor edits.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agobuffer.h: fix operator> and operator>= increment error
Samuel Just [Thu, 28 Jun 2012 18:27:07 +0000 (11:27 -0700)]
buffer.h: fix operator> and operator>= increment error

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoradosgw Apache configuration: simplify rewrite rule
Florian Haas [Thu, 28 Jun 2012 07:46:28 +0000 (09:46 +0200)]
radosgw Apache configuration: simplify rewrite rule

Use a simpler RewriteRule as suggested here:
http://marc.info/?l=ceph-devel&m=133951986510085&w=2

13 years agoFix example radosgw Apache configuration
Florian Haas [Thu, 28 Jun 2012 07:43:00 +0000 (09:43 +0200)]
Fix example radosgw Apache configuration

Follow RFC2606, use example.com everywhere.

13 years agopg: report scrub status
Mike Ryan [Wed, 27 Jun 2012 21:14:30 +0000 (14:14 -0700)]
pg: report scrub status

Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
13 years agopg: track who we are waiting for maps from
Mike Ryan [Wed, 27 Jun 2012 20:30:45 +0000 (13:30 -0700)]
pg: track who we are waiting for maps from

Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
13 years agopg: reduce scrub write lock window
Mike Ryan [Tue, 26 Jun 2012 23:25:27 +0000 (16:25 -0700)]
pg: reduce scrub write lock window

Wait for all replicas to construct the base scrub map before finalizing
the scrub and locking out writes.

Signed-off-by: Mike Ryan <mike.ryan@inktank.com>
13 years agorest-bench: mark request as complete later
Yehuda Sadeh [Wed, 27 Jun 2012 00:16:11 +0000 (17:16 -0700)]
rest-bench: mark request as complete later

We marked a request as complete in the callback, however
it might be that we're still inside S3_runall_request_context()
which means that request is not really complete yet.
Possibly fixes bug #2652.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agorgw-admin: use correct modifier with strptime
Yehuda Sadeh [Wed, 27 Jun 2012 00:28:51 +0000 (17:28 -0700)]
rgw-admin: use correct modifier with strptime

Bug #2658: used %I (12h) instead of %H (24h)

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agodoc: removing old 'todo' configuration reference.
John Wilkins [Tue, 26 Jun 2012 19:30:01 +0000 (12:30 -0700)]
doc: removing old 'todo' configuration reference.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: converted daemon references from nasty tables to lines.
John Wilkins [Tue, 26 Jun 2012 19:24:23 +0000 (12:24 -0700)]
doc: converted daemon references from nasty tables to lines.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: a few minor tweaks to radosgw to cleanup navigation.
John Wilkins [Tue, 26 Jun 2012 15:28:10 +0000 (08:28 -0700)]
doc: a few minor tweaks to radosgw to cleanup navigation.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: Published RADOS GW docs and install as is for now. Needs more work.
John Wilkins [Tue, 26 Jun 2012 15:21:05 +0000 (08:21 -0700)]
doc: Published RADOS GW docs and install as is for now. Needs more work.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agoCrushTester.cc: removed last broken bits of obsolete method
caleb miles [Tue, 26 Jun 2012 07:05:27 +0000 (00:05 -0700)]
CrushTester.cc: removed last broken bits of obsolete method

Signed-off-by: caleb miles <caleb.miles@inktank.com>
13 years agoCrushTester.cc: removed obsolete method for collapsing a CRUSH map
caleb miles [Tue, 26 Jun 2012 07:02:24 +0000 (00:02 -0700)]
CrushTester.cc: removed obsolete method for collapsing a CRUSH map

Signed-off-by: caleb miles <caleb.miles@inktank.com>
13 years agoCrushTester: eliminated compiler warning
caleb miles [Tue, 26 Jun 2012 06:58:52 +0000 (23:58 -0700)]
CrushTester: eliminated compiler warning

Signed-off-by: caleb miles <caselim@gmail.com>
13 years agoradosgw-admin: improve man page
Florian Haas [Sat, 23 Jun 2012 09:50:24 +0000 (10:50 +0100)]
radosgw-admin: improve man page

* remove "OpenStack user" information (deprecated, should no
  longer be used. No reason to keep mentioning it)
* fix description of --uid
* mention subusers
* add key management commands

Signed-off-by: Florian Haas <florian@hastexo.com>
13 years agodoc: explain how to configure Ceph for radosgw
Florian Haas [Thu, 14 Jun 2012 21:07:44 +0000 (23:07 +0200)]
doc: explain how to configure Ceph for radosgw

* explain creating auth creds for radosgw
* explain Apache config for radosgw
* explain starting daemons for radosgw
* explain creating users for radosgw
* explain creating subusers for radosgw
* explain using swift client against radosgw
* Explain user:subuser to tenant:user mapping in Swift

Signed-off-by: Florian Haas <florian@hastexo.com>
13 years agoMerge branch 'master' of github.com:ceph/ceph
caleb miles [Tue, 26 Jun 2012 06:14:09 +0000 (23:14 -0700)]
Merge branch 'master' of github.com:ceph/ceph

13 years agorgw: send both swift x-storage-token and x-auth-token
Yehuda Sadeh [Thu, 21 Jun 2012 22:40:27 +0000 (15:40 -0700)]
rgw: send both swift x-storage-token and x-auth-token

older clients need x-storage-token, newer x-auth-token

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agorgw: radosgw-admin date params now also accept time
Yehuda Sadeh [Thu, 21 Jun 2012 22:17:19 +0000 (15:17 -0700)]
rgw: radosgw-admin date params now also accept time

The date format now is "YYYY-MM-DD[ hh:mm:ss]". Got rid of
the --time param for the old ops log stuff.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agorgw-admin: fix usage help
Yehuda Sadeh [Thu, 21 Jun 2012 20:14:47 +0000 (13:14 -0700)]
rgw-admin: fix usage help

s/show/trim

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agoupstart: fix regex
Tommi Virtanen [Mon, 25 Jun 2012 22:14:33 +0000 (15:14 -0700)]
upstart: fix regex

Signed-off-by: Tommi Virtanen <tv@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com>
13 years agoMerge branch 'next'
Sage Weil [Mon, 25 Jun 2012 21:45:21 +0000 (14:45 -0700)]
Merge branch 'next'

13 years agomon: don't tick the PaxosServices if we are currently slurping.
Greg Farnum [Mon, 25 Jun 2012 20:04:15 +0000 (13:04 -0700)]
mon: don't tick the PaxosServices if we are currently slurping.

They aren't prepared to deal with the on-disk state being inconsistent.

Signed-off-by: Greg Farnum <greg@inktank.com>
13 years agoobjecter: do not feed session to op_submit()
Sage Weil [Wed, 20 Jun 2012 18:07:29 +0000 (11:07 -0700)]
objecter: do not feed session to op_submit()

The linger_send() method was doing this, but it is problematic because the
new Op doesn't get its pgid or acting vector set correctly.  The result is
that the request goes to the right OSD, but has the wrong pgid, and makes
the OSD complain about misdirected requests and drop it on the floor.  It
didn't affect the test results because we weren't testing whether the
watch was working in that case.

Instead, we'll just recalculate and get the same value the parent linger
op did.  Which is fine, and goes through all the usual code paths so
nothing is missed.

Also, increment num_homeless_ops before we recalc_op_target(), so that we
don't (harmlessly, but confusingly) underflow.

Fixes: #2022
Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoObjectStore::Transaction: initialize pool_override in all constructors
Samuel Just [Sun, 24 Jun 2012 20:30:53 +0000 (13:30 -0700)]
ObjectStore::Transaction: initialize pool_override in all constructors

use_pool_override and pool_override weren't initialized in these two
constructors.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoobjecter: do not feed session to op_submit()
Sage Weil [Wed, 20 Jun 2012 18:07:29 +0000 (11:07 -0700)]
objecter: do not feed session to op_submit()

The linger_send() method was doing this, but it is problematic because the
new Op doesn't get its pgid or acting vector set correctly.  The result is
that the request goes to the right OSD, but has the wrong pgid, and makes
the OSD complain about misdirected requests and drop it on the floor.  It
didn't affect the test results because we weren't testing whether the
watch was working in that case.

Instead, we'll just recalculate and get the same value the parent linger
op did.  Which is fine, and goes through all the usual code paths so
nothing is missed.

Also, increment num_homeless_ops before we recalc_op_target(), so that we
don't (harmlessly, but confusingly) underflow.

Fixes: #2022
Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoosd_types.cc: remove hobject_t decode asserts
Samuel Just [Fri, 22 Jun 2012 00:08:20 +0000 (17:08 -0700)]
osd_types.cc: remove hobject_t decode asserts

These asserts were useful for ensuring that pool is passed
in in the correct places, but they prevent the encoder
testing from working.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agomon: note that monmap may be reencoded later
Sage Weil [Thu, 21 Jun 2012 14:33:47 +0000 (07:33 -0700)]
mon: note that monmap may be reencoded later

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: encoding new monmap using quorum feature set
Sage Weil [Thu, 21 Jun 2012 14:31:47 +0000 (07:31 -0700)]
mon: encoding new monmap using quorum feature set

It is probably unlikely that someone will expand the mon cluster with a
mixed feature set, but we know the quorum features here, so we should use
them.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: conditionally encode mon features for remote mon
Sage Weil [Thu, 21 Jun 2012 14:27:49 +0000 (07:27 -0700)]
mon: conditionally encode mon features for remote mon

The only time we encode these is when forwarding messages.  Encoding using
the destination's feature set.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: conditionally encode PGMap[::Incremental] with quorum features
Sage Weil [Thu, 21 Jun 2012 14:23:56 +0000 (07:23 -0700)]
mon: conditionally encode PGMap[::Incremental] with quorum features

This allows a mon cluster to transition to the new encoding during a
rolling upgrade.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: conditionally encode auth incremental with quorum feature bits
Sage Weil [Thu, 21 Jun 2012 03:41:17 +0000 (20:41 -0700)]
mon: conditionally encode auth incremental with quorum feature bits

If the quorum does not yet all have the MONENC feature, stick to the old
encoding.

It might be more polite to require a super-quorum before switching over,
and take note so that thereafter we can stick to the new encoding, but
that has more moving parts and I'm not sure it's worth the complexity.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: track intersection of quorum member features
Sage Weil [Thu, 21 Jun 2012 03:33:41 +0000 (20:33 -0700)]
mon: track intersection of quorum member features

When we form a quorum, also note the intersection of the quorum members'
feature bits.  This will inform decisions about what encodings we use.

This is an imperfect strategy because the quorum may change, and we may
have a mon with old code join in and not understand what is going on.
However, it does ensure that a majority of the members run new code, so in
the absence of other failures we can make progress.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: conditionally encode old monmap when peer lacks feature
Sage Weil [Thu, 21 Jun 2012 02:08:34 +0000 (19:08 -0700)]
mon: conditionally encode old monmap when peer lacks feature

This allows a rolling upgrade from 0.47.2 to 0.48.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoOSD,PG,ObjectStore: handle messages with old hobject_t encoding
Samuel Just [Wed, 20 Jun 2012 19:55:38 +0000 (12:55 -0700)]
OSD,PG,ObjectStore: handle messages with old hobject_t encoding

Messages that embed an hobject_t need to have the pool field fixed
on messages from old peers.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agodoc: ceph osd crush add is now ceph osd crush set
Travis Rhoden [Thu, 21 Jun 2012 19:25:02 +0000 (15:25 -0400)]
doc: ceph osd crush add is now ceph osd crush set

Mailing list thread: http://www.spinics.net/lists/ceph-devel/msg06199.html

Signed-off-by: Travis Rhoden <trhoden@gmail.com>
13 years agologrotate: reload all upstart instances
Sage Weil [Thu, 21 Jun 2012 19:42:53 +0000 (12:42 -0700)]
logrotate: reload all upstart instances

upstart doesn't let you wildcard all instances of a given job, so we
slog through initctl list output, and reload any running daemons.

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Tommi Virtanen <tv@inktank.com>
13 years agodocs: clarify example in radosgw-admin
Yehuda Sadeh [Thu, 21 Jun 2012 18:34:20 +0000 (11:34 -0700)]
docs: clarify example in radosgw-admin

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agofilestore: remove btrfs start/end transaction ioctl code
Sage Weil [Thu, 21 Jun 2012 18:17:34 +0000 (11:17 -0700)]
filestore: remove btrfs start/end transaction ioctl code

This was an ill-conceived approach to getting atomic transactions out of
btrfs.  It doesn't offer rollback, which means that any error means we need
to wedge the file system and reboot in order to avoid corrupting the
data set.  And that's silly!

Snapshots are more robust and only marginally slower (because we have to
quiesce our writes while waiting for the snap to start, and btrfs resume
work in-kernel slightly faster...maybe).

Fixes: #2623
Signed-off-by: Sage Weil <sage@inktank.com>
13 years agomon: make pool deletion dne error code consistently ENOENT
Sage Weil [Thu, 21 Jun 2012 18:16:39 +0000 (11:16 -0700)]
mon: make pool deletion dne error code consistently ENOENT

This matches the check in _prepare_remove_pool() now.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agodocs: update usage logging info
Yehuda Sadeh [Thu, 21 Jun 2012 17:46:55 +0000 (10:46 -0700)]
docs: update usage logging info

added some text under radosgw, examples under radosgw-admin

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agoMerge remote-tracking branch 'gh/stable' into next
Sage Weil [Thu, 21 Jun 2012 15:20:17 +0000 (08:20 -0700)]
Merge remote-tracking branch 'gh/stable' into next

13 years agodoc: Normalized shell script syntax. Added generic cookbook path.
John Wilkins [Wed, 20 Jun 2012 22:10:23 +0000 (15:10 -0700)]
doc: Normalized shell script syntax. Added generic cookbook path.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: Changed libvirt-dev to libvirt-bin, and cleaned up ./autogen.sh
John Wilkins [Wed, 20 Jun 2012 21:29:58 +0000 (14:29 -0700)]
doc: Changed libvirt-dev to libvirt-bin, and cleaned up ./autogen.sh

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: Typo.
Tommi Virtanen [Wed, 20 Jun 2012 19:55:29 +0000 (12:55 -0700)]
doc: Typo.

Signed-off-by: Tommi Virtanen <tv@inktank.com>
13 years agov0.47.3 v0.47.3
Sage Weil [Wed, 20 Jun 2012 17:57:41 +0000 (10:57 -0700)]
v0.47.3

13 years agofilestore: disable 'filestore fiemap' by default
Sage Weil [Fri, 15 Jun 2012 17:00:54 +0000 (10:00 -0700)]
filestore: disable 'filestore fiemap' by default

We've seen this failing on both btrfs (Guido) and XFS (Oliver).  This works
around #2535.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoOSD: clear_temp: split delete into many transactions
Samuel Just [Tue, 19 Jun 2012 21:29:48 +0000 (14:29 -0700)]
OSD: clear_temp: split delete into many transactions

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
13 years agoMerge branch 'wip-clsrbd'
Sage Weil [Tue, 19 Jun 2012 22:19:21 +0000 (15:19 -0700)]
Merge branch 'wip-clsrbd'

Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
13 years agodoc: document usage log
Yehuda Sadeh [Tue, 19 Jun 2012 22:17:53 +0000 (15:17 -0700)]
doc: document usage log

Modify radosgw, radosgw-admin man page

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agocls_rbd: note overlap units
Sage Weil [Tue, 19 Jun 2012 21:31:21 +0000 (14:31 -0700)]
cls_rbd: note overlap units

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: fix uninitialized var in cls_rbd_parent
Sage Weil [Sat, 16 Jun 2012 20:08:06 +0000 (13:08 -0700)]
cls_rbd: fix uninitialized var in cls_rbd_parent

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: clean up doxygen, whitespace a bit
Sage Weil [Sat, 16 Jun 2012 14:50:46 +0000 (07:50 -0700)]
cls_rbd: clean up doxygen, whitespace a bit

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: include dumpers, test instances for our types
Sage Weil [Sat, 16 Jun 2012 00:41:04 +0000 (17:41 -0700)]
cls_rbd: include dumpers, test instances for our types

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: rename parent size -> overlap
Sage Weil [Sat, 16 Jun 2012 00:29:35 +0000 (17:29 -0700)]
cls_rbd: rename parent size -> overlap

The use of 'size' to describe the amount that we overlap with the parent
was confusing; overlap is more intuitive (to me, at least!).

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: handle parent overlap
Sage Weil [Sat, 16 Jun 2012 00:27:25 +0000 (17:27 -0700)]
cls_rbd: handle parent overlap

Two things:

 * when we set a parent, the overlap is the min of our size and the
   parent's size.
 * when we resize, our overlap may shrink.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: make snapshots inherit the head's parent
Sage Weil [Sat, 16 Jun 2012 00:03:47 +0000 (17:03 -0700)]
cls_rbd: make snapshots inherit the head's parent

When you take a snapshot, the snap gets the current parent of the head, if
any.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: check for LAYERING feature for parent methods
Sage Weil [Fri, 15 Jun 2012 17:42:49 +0000 (10:42 -0700)]
cls_rbd: check for LAYERING feature for parent methods

You need to set the feature on the image before you can use these methods.
We *could* allow get_parent, but that just means they'll get ENOENT instead
of ENOEXEC, and the latter is more informative.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd: implement get_parent, set_parent, remove_parent
Sage Weil [Mon, 18 Jun 2012 21:22:53 +0000 (14:22 -0700)]
cls_rbd: implement get_parent, set_parent, remove_parent

Implement methods to get/set/remove the parent pointer on child images.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agocls_rbd_client: use snapid_t type
Sage Weil [Fri, 15 Jun 2012 22:38:27 +0000 (15:38 -0700)]
cls_rbd_client: use snapid_t type

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoMerge remote-tracking branch 'gh/next'
Sage Weil [Tue, 19 Jun 2012 21:29:43 +0000 (14:29 -0700)]
Merge remote-tracking branch 'gh/next'

Conflicts:
src/osd/PG.cc

13 years agorgw: set s->header_ended before flushing formatter
Yehuda Sadeh [Mon, 18 Jun 2012 21:44:38 +0000 (14:44 -0700)]
rgw: set s->header_ended before flushing formatter

otherwise we don't account the formatter in s->bytes_sent.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agorgw: log user and not bucket owner for service operations
Yehuda Sadeh [Mon, 18 Jun 2012 21:28:25 +0000 (14:28 -0700)]
rgw: log user and not bucket owner for service operations

For operations that are done on the service (e.g., list buckets)
we need to log the user that did the operation, and not the bucket
owner.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agorgw: initalize s->enable_usage_log
Yehuda Sadeh [Mon, 18 Jun 2012 21:27:51 +0000 (14:27 -0700)]
rgw: initalize s->enable_usage_log

Missing initialization, we ended up not logging every operation.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
13 years agoosd: use derr (instead of cerr) for convertfs
Sage Weil [Tue, 19 Jun 2012 17:12:40 +0000 (10:12 -0700)]
osd: use derr (instead of cerr) for convertfs

This will appear in the log *and* stderr (if we're running in the
foreground).

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoosd: close stderr on daemonize
Sage Weil [Tue, 19 Jun 2012 17:11:01 +0000 (10:11 -0700)]
osd: close stderr on daemonize

This spams stderr in an ugly way.  Users should look at the logs.

In particular, filestore upgrades spam the console, which is unpleasant.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agoPG: improve find_best_info
Samuel Just [Tue, 19 Jun 2012 16:11:57 +0000 (09:11 -0700)]
PG: improve find_best_info

07f853db3982e68b952a337cf91cbf7ec0709de9 is actually too conservative,
it suffices to find any info with a last_update of at least the least
last_update from the last period to go active.  An info from a previous
interval is acceptable if the last interval never reported a commited
operation and thus still has the same last_update.

Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
13 years agoosdcap: make grammar build on spirit 2.2/boost 1.42
Sage Weil [Tue, 19 Jun 2012 16:39:01 +0000 (09:39 -0700)]
osdcap: make grammar build on spirit 2.2/boost 1.42

This is a stupid workaround, but it makes the compilation error go away.

Signed-off-by: Sage Weil <sage@inktank.com>
13 years agodoc: Added a snapshot page with outline. Needs additional info.
John Wilkins [Tue, 19 Jun 2012 17:15:35 +0000 (10:15 -0700)]
doc: Added a snapshot page with outline. Needs additional info.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agodoc: Added prerequisite of running Ceph cluster.
John Wilkins [Tue, 19 Jun 2012 17:10:51 +0000 (10:10 -0700)]
doc: Added prerequisite of running Ceph cluster.

Signed-off-by: John Wilkins <john.wilkins@inktank.com>
13 years agoPG: reg_last_pg_scrub on pg resurrection
Samuel Just [Mon, 18 Jun 2012 16:26:12 +0000 (09:26 -0700)]
PG: reg_last_pg_scrub on pg resurrection

This may solve the unreg_last_pg_scrub assert.

see #2453.

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoceph_osd: move auto-upgrade to after fork
Samuel Just [Mon, 18 Jun 2012 21:02:28 +0000 (14:02 -0700)]
ceph_osd: move auto-upgrade to after fork

Signed-off-by: Samuel Just <sam.just@inktank.com>
13 years agoMerge branch 'master' of github.com:ceph/ceph
John Wilkins [Mon, 18 Jun 2012 21:29:27 +0000 (14:29 -0700)]
Merge branch 'master' of github.com:ceph/ceph

13 years agolibrbd: simplify refresh sequence checks
Sage Weil [Mon, 18 Jun 2012 21:11:37 +0000 (14:11 -0700)]
librbd: simplify refresh sequence checks

- incremental seq each request
- set last to the last completed seq
- drop the now-redundant bool

Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>