]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
15 years agomds: use CDir::item_new for LogSegment::new_dirfrags elist
Sage Weil [Mon, 15 Mar 2010 17:58:57 +0000 (10:58 -0700)]
mds: use CDir::item_new for LogSegment::new_dirfrags elist

15 years agoauth: update documentation on caps
Greg Farnum [Mon, 15 Mar 2010 17:37:22 +0000 (10:37 -0700)]
auth: update documentation on caps

15 years agomon: return error codes from prepare_new_pool
Greg Farnum [Mon, 15 Mar 2010 17:03:39 +0000 (10:03 -0700)]
mon: return error codes from prepare_new_pool

15 years agomon: add warning/debugging prints to prepare_new_pool
Greg Farnum [Fri, 12 Mar 2010 23:45:31 +0000 (15:45 -0800)]
mon: add warning/debugging prints to prepare_new_pool

15 years agoMerge branch 'mds_mem' into unstable
Sage Weil [Sat, 13 Mar 2010 00:48:32 +0000 (16:48 -0800)]
Merge branch 'mds_mem' into unstable

15 years agomds: be consistent about list<>::item naming (item_foo)
Sage Weil [Sat, 13 Mar 2010 00:08:36 +0000 (16:08 -0800)]
mds: be consistent about list<>::item naming (item_foo)

15 years agodlist: fix pop_front/back
Sage Weil [Fri, 12 Mar 2010 23:57:04 +0000 (15:57 -0800)]
dlist: fix pop_front/back

15 years agoxlist: clean up interface
Sage Weil [Fri, 12 Mar 2010 23:28:27 +0000 (15:28 -0800)]
xlist: clean up interface

15 years agodlist: clean up interface
Sage Weil [Fri, 12 Mar 2010 23:26:15 +0000 (15:26 -0800)]
dlist: clean up interface

15 years agomds: use elist instead of dlist
Sage Weil [Fri, 12 Mar 2010 23:26:02 +0000 (15:26 -0800)]
mds: use elist instead of dlist

15 years agoelist: simpler embedded list
Sage Weil [Fri, 12 Mar 2010 18:13:20 +0000 (10:13 -0800)]
elist: simpler embedded list

This is more or less equivalent to the linux kernel list_head:
each embedded item struct has only a next and prev pointer. As
long as the same member item is always used, at a fixed offset
from the containing class, we can go from an item to a contained
class.

The offset can either be passed to the list (head) constructor,
or to the begin(), front(), back() members explicitly.

Iterator has 3 modes.. current (list_for_each), cache_next
(list_for_each_safe), and magic (uses cached next iff current is
empty).  Magic will work most of the time... as long as we don't
re-add ourselves to a different list inside the iterator loop.
(Note that if we do, we will iterator up to the other list's
head, not detect it is a head, an get an invalid pointer and
crash.)

elist: add to makefile

elist: require offset for cosntructor

elist: fix pop_front/back

15 years agorgw: remove unused refcount data member from XMLObj. Also clears up ctor
Greg Farnum [Fri, 12 Mar 2010 22:24:17 +0000 (14:24 -0800)]
rgw: remove unused refcount data member from XMLObj. Also clears up ctor

15 years agorgw: Add documentation
Greg Farnum [Thu, 11 Mar 2010 22:49:27 +0000 (14:49 -0800)]
rgw: Add documentation

15 years agoMerge branch 'mds_mem' into unstable
Sage Weil [Fri, 12 Mar 2010 17:09:09 +0000 (09:09 -0800)]
Merge branch 'mds_mem' into unstable

15 years agocephx: initialize values
Sage Weil [Fri, 12 Mar 2010 16:40:04 +0000 (08:40 -0800)]
cephx: initialize values

15 years agosynclient: print mount error
Sage Weil [Thu, 11 Mar 2010 17:40:09 +0000 (09:40 -0800)]
synclient: print mount error

15 years agoxlist: clean up users
Sage Weil [Fri, 12 Mar 2010 05:43:56 +0000 (21:43 -0800)]
xlist: clean up users

15 years agomds: use dlist instead of xlist for main cache objects
Sage Weil [Fri, 12 Mar 2010 05:43:37 +0000 (21:43 -0800)]
mds: use dlist instead of xlist for main cache objects

15 years agodlist: simpler version of xlist without _list pointer
Sage Weil [Fri, 12 Mar 2010 05:43:23 +0000 (21:43 -0800)]
dlist: simpler version of xlist without _list pointer

15 years agomds: reduce MDSCacheObject footprint a bit
Sage Weil [Fri, 12 Mar 2010 05:11:08 +0000 (21:11 -0800)]
mds: reduce MDSCacheObject footprint a bit

Save 8 bytes.  Whoop.

15 years agomds: replica_nonce can wrap; fix asserts
Sage Weil [Fri, 12 Mar 2010 05:07:00 +0000 (21:07 -0800)]
mds: replica_nonce can wrap; fix asserts

15 years agomds: put rare state in more_bits_t in ScatterLock
Sage Weil [Fri, 12 Mar 2010 04:50:29 +0000 (20:50 -0800)]
mds: put rare state in more_bits_t in ScatterLock

Saves 48 bytes per ScatterLock, 144 bytes per CInode.

15 years agomds: show xlist overhead
Sage Weil [Fri, 12 Mar 2010 04:29:21 +0000 (20:29 -0800)]
mds: show xlist overhead

15 years agomds: move unstable SimpleLock state into separate struct
Sage Weil [Thu, 11 Mar 2010 18:52:32 +0000 (10:52 -0800)]
mds: move unstable SimpleLock state into separate struct

Allocated as needed, freed when lock returns to stable state.

Also make remaining int fields a bit smaller.

15 years agodebian: specify mirror explicitly when creating pbuilder image
Sage Weil [Fri, 12 Mar 2010 05:38:04 +0000 (21:38 -0800)]
debian: specify mirror explicitly when creating pbuilder image

15 years agomds: simplify LocalLock wrlock methods
Sage Weil [Thu, 11 Mar 2010 17:57:36 +0000 (09:57 -0800)]
mds: simplify LocalLock wrlock methods

15 years agomds: add locallock statemachine
Sage Weil [Thu, 11 Mar 2010 17:41:30 +0000 (09:41 -0800)]
mds: add locallock statemachine

This is just for consistency; it's trivial.  We lost the get_sm()
pointer test, though.

15 years agosynclient: print mount error
Sage Weil [Thu, 11 Mar 2010 17:40:09 +0000 (09:40 -0800)]
synclient: print mount error

15 years agomds: create abstract LockType that includes numeric type and state machine
Sage Weil [Thu, 11 Mar 2010 17:30:10 +0000 (09:30 -0800)]
mds: create abstract LockType that includes numeric type and state machine

This eliminates 1 field in each SimpleLock.

15 years agodebian: build binary-arch debs only from builddebs.sh
Sage Weil [Thu, 11 Mar 2010 17:05:37 +0000 (09:05 -0800)]
debian: build binary-arch debs only from builddebs.sh

Otherwise we rebuild the source .dsc, which isn't what we want.

15 years agodebian: clean out unused debhelper rules steps
Sage Weil [Wed, 10 Mar 2010 05:38:43 +0000 (21:38 -0800)]
debian: clean out unused debhelper rules steps

15 years agodebian: put debian/ in .diff.gz, not release tarball
Sage Weil [Wed, 10 Mar 2010 05:38:30 +0000 (21:38 -0800)]
debian: put debian/ in .diff.gz, not release tarball

15 years agomsgr: remove dead kill_after code bits
Sage Weil [Tue, 9 Mar 2010 23:16:54 +0000 (15:16 -0800)]
msgr: remove dead kill_after code bits

15 years agotodo multi-mds issue
Sage Weil [Tue, 9 Mar 2010 23:08:08 +0000 (15:08 -0800)]
todo multi-mds issue

15 years agomon: users can now change pool owners.
Greg Farnum [Wed, 10 Mar 2010 20:56:37 +0000 (12:56 -0800)]
mon: users can now change pool owners.

This requires them to have write permission on both the current
and the new auid.

15 years agoosd: Check auid permissions in get_pool_cap
Greg Farnum [Wed, 10 Mar 2010 18:20:44 +0000 (10:20 -0800)]
osd: Check auid permissions in get_pool_cap

15 years agomon: use MonCaps::check_privileges in prepare_new_pool
Greg Farnum [Wed, 10 Mar 2010 00:46:45 +0000 (16:46 -0800)]
mon: use MonCaps::check_privileges in prepare_new_pool

15 years agoRevert "mon: add check_privileges function to OSDMon."
Greg Farnum [Wed, 10 Mar 2010 00:42:29 +0000 (16:42 -0800)]
Revert "mon: add check_privileges function to OSDMon."
Deprecated by the existence of MonCaps::check_privileges

This reverts commit 07df67f3948e50a24365e0936bd0de3c7dc1a1f2.

15 years agomon: add check_privileges function to MonCaps
Greg Farnum [Wed, 10 Mar 2010 00:38:33 +0000 (16:38 -0800)]
mon: add check_privileges function to MonCaps

15 years agovstart: use 'allow *' notation instead of 'allow rwx'
Greg Farnum [Wed, 10 Mar 2010 00:02:31 +0000 (16:02 -0800)]
vstart: use 'allow *' notation instead of 'allow rwx'

15 years agoosd: accept 'allow *' as an admin flag that sets allow_all
Greg Farnum [Wed, 10 Mar 2010 00:01:38 +0000 (16:01 -0800)]
osd: accept 'allow *' as an admin flag that sets allow_all
in the OSDCap.

15 years agoosd: OSDCaps parses and stores auid permissions
Greg Farnum [Tue, 9 Mar 2010 23:50:08 +0000 (15:50 -0800)]
osd: OSDCaps parses and stores auid permissions

15 years agomon: AuthMonitor doesn't overwrite allow_all bit
Greg Farnum [Tue, 9 Mar 2010 22:14:22 +0000 (14:14 -0800)]
mon: AuthMonitor doesn't overwrite allow_all bit
on incoming messages, only on initial connect.

15 years agomon: Add basic operator<< to MonCaps
Greg Farnum [Tue, 9 Mar 2010 22:13:38 +0000 (14:13 -0800)]
mon: Add basic operator<< to MonCaps

15 years agomon: Accept 'allow *' as an admin flag that sets allow_all
Greg Farnum [Tue, 9 Mar 2010 22:12:45 +0000 (14:12 -0800)]
mon: Accept 'allow *' as an admin flag that sets allow_all
in MonCaps.

15 years agomon: MonCaps parses and stores auid permissions
Greg Farnum [Tue, 9 Mar 2010 22:09:36 +0000 (14:09 -0800)]
mon: MonCaps parses and stores auid permissions

Also, rename MonServiceCap -> MonCap

15 years agothread: mask all signals on child threads
Sage Weil [Tue, 9 Mar 2010 23:02:30 +0000 (15:02 -0800)]
thread: mask all signals on child threads

Mask all signals on any threads we create.  Since we don't use
signals for anything, this leaves the signal behavior to the
original parent thread or process linking in librados or
libceph.

15 years agotimer: kill unused g_timer
Sage Weil [Tue, 9 Mar 2010 22:51:05 +0000 (14:51 -0800)]
timer: kill unused g_timer

15 years agomds: create mds.$id debug log symlink
Sage Weil [Tue, 9 Mar 2010 22:05:52 +0000 (14:05 -0800)]
mds: create mds.$id debug log symlink

...in addition to the current mds$num

15 years agomds: only check for canceled _client_ requests, not slaves
Sage Weil [Tue, 9 Mar 2010 19:00:03 +0000 (11:00 -0800)]
mds: only check for canceled _client_ requests, not slaves

Slave requests don't get added to the session request list.

15 years agomds: fix MDentryUnlink
Sage Weil [Tue, 9 Mar 2010 18:41:42 +0000 (10:41 -0800)]
mds: fix MDentryUnlink

Need to replicate mds dir + stray dir dentry as well as the stray
inode, dir, dentry.  This was overlooked when the /.ceph and
per-mds directories were set up.

15 years agomessenger: don't use signal SIGUSRx anymore
Yehuda Sadeh [Mon, 8 Mar 2010 23:34:24 +0000 (15:34 -0800)]
messenger: don't use signal SIGUSRx anymore

Was used internally to wake up blocking messenger threads.

15 years agoqa: make -j on kernel build
Sage Weil [Mon, 8 Mar 2010 21:35:56 +0000 (13:35 -0800)]
qa: make -j on kernel build

15 years agoRevert "mon: Hack -- set allow_all in caps if client name is admin"
Sage Weil [Mon, 8 Mar 2010 23:10:14 +0000 (15:10 -0800)]
Revert "mon: Hack -- set allow_all in caps if client name is admin"

This reverts commit f07ce468e502b403faaef6cc5e9bd578366c9395.

15 years agomds: note when we last became non-laggy
Sage Weil [Mon, 8 Mar 2010 22:49:33 +0000 (14:49 -0800)]
mds: note when we last became non-laggy

15 years agomkcephfs: cosd mkfs as root, then chown
Sage Weil [Mon, 8 Mar 2010 22:45:33 +0000 (14:45 -0800)]
mkcephfs: cosd mkfs as root, then chown

15 years agotodo bugs
Sage Weil [Mon, 8 Mar 2010 22:45:23 +0000 (14:45 -0800)]
todo bugs

15 years agofilestore: clean up btrfs, clone range detection
Sage Weil [Mon, 8 Mar 2010 19:00:50 +0000 (11:00 -0800)]
filestore: clean up btrfs, clone range detection

Use statfs to detect btrfs, not the trans ioctl (which won't work
if you're not root!).  Use separate bool for clone range support.

15 years agocauthtool: verify set_uid arg
Sage Weil [Sat, 6 Mar 2010 00:22:33 +0000 (16:22 -0800)]
cauthtool: verify set_uid arg

15 years agomds: dump misc struct sizes to log
Sage Weil [Fri, 5 Mar 2010 00:46:03 +0000 (16:46 -0800)]
mds: dump misc struct sizes to log

15 years agomonclient: time out properly from wait_auth_rotating
Sage Weil [Fri, 5 Mar 2010 00:45:42 +0000 (16:45 -0800)]
monclient: time out properly from wait_auth_rotating

15 years agodecay: separate fixed DecayRate from DecayCounter
Sage Weil [Fri, 5 Mar 2010 00:22:56 +0000 (16:22 -0800)]
decay: separate fixed DecayRate from DecayCounter

Avoid eating a double per instance.

15 years agomds: drop useless double from DecayCounter
Sage Weil [Thu, 4 Mar 2010 23:48:41 +0000 (15:48 -0800)]
mds: drop useless double from DecayCounter

No need to store k AND halflife.

15 years agomon: Hack -- set allow_all in caps if client name is admin
Greg Farnum [Mon, 8 Mar 2010 15:47:47 +0000 (07:47 -0800)]
mon: Hack -- set allow_all in caps if client name is admin

15 years agoobjecter: librados: add optional auid param to
Greg Farnum [Mon, 8 Mar 2010 15:41:35 +0000 (07:41 -0800)]
objecter: librados: add optional auid param to
create_pool functions

15 years agoobjecter: add auid to PoolOp, fill it in during pool_op_submit
Greg Farnum [Mon, 8 Mar 2010 15:40:54 +0000 (07:40 -0800)]
objecter: add auid to PoolOp, fill it in during pool_op_submit

15 years agomon: let prepare_new_pool assign an auid.
Greg Farnum [Mon, 8 Mar 2010 14:44:51 +0000 (06:44 -0800)]
mon: let prepare_new_pool assign an auid.
Add new version that takes an MPoolOp and checks permissions
first.

15 years agomon: add check_privileges function to OSDMon.
Greg Farnum [Mon, 8 Mar 2010 14:43:24 +0000 (06:43 -0800)]
mon: add check_privileges function to OSDMon.

15 years agomsg: Add an auid field to MPoolOp; additional constructor to match
Greg Farnum [Mon, 8 Mar 2010 14:42:00 +0000 (06:42 -0800)]
msg: Add an auid field to MPoolOp; additional constructor to match

15 years agoauth: move CEPH_AUTH_UID_DEFAULT into ceph_fs.h
Greg Farnum [Sat, 6 Mar 2010 00:47:26 +0000 (16:47 -0800)]
auth: move CEPH_AUTH_UID_DEFAULT into ceph_fs.h

15 years agocauthtool: set auid in data member format instead of as (ignored) text key
Greg Farnum [Fri, 5 Mar 2010 21:48:04 +0000 (13:48 -0800)]
cauthtool: set auid in data member format instead of as (ignored) text key

15 years agomon: store auid in MonCaps
Greg Farnum [Fri, 5 Mar 2010 23:35:28 +0000 (15:35 -0800)]
mon: store auid in MonCaps

15 years agoosd: store auid in OSDCaps
Greg Farnum [Fri, 5 Mar 2010 20:31:09 +0000 (12:31 -0800)]
osd: store auid in OSDCaps

15 years agomon: fix bad return test!
Greg Farnum [Fri, 5 Mar 2010 01:16:48 +0000 (17:16 -0800)]
mon: fix bad return test!

cephx_build_service_ticket_blob returns a bool, so it's not ever
going to return <0 -- or if it somehow does that'll be true (good, not false!

15 years agoauth: add set_uid() to KeyRing, print out auid in print function
Greg Farnum [Fri, 5 Mar 2010 20:36:56 +0000 (12:36 -0800)]
auth: add set_uid() to KeyRing, print out auid in print function

15 years agoauth: Add an auid parameter to verify_authorizer and handle_request
Greg Farnum [Thu, 4 Mar 2010 23:52:31 +0000 (15:52 -0800)]
auth: Add an auid parameter to verify_authorizer and handle_request

It defaults to null, in which case it's not assigned to.

auth: add optional auid param to handle_request

15 years agocephx: Piece-wise initialization of structs is BAD!
Greg Farnum [Fri, 5 Mar 2010 19:13:59 +0000 (11:13 -0800)]
cephx: Piece-wise initialization of structs is BAD!
If you add, say, a field "auid" to the struct and it's being
piece-wise initialized then you need to change every copy to include it.
Or you assume it's just copied wholesale and then spend many hours trying
to find where it isn't. Like in this one.

15 years agoauth: rename auth_uid -> auid
Greg Farnum [Fri, 5 Mar 2010 20:48:47 +0000 (12:48 -0800)]
auth: rename auth_uid -> auid

15 years agoauth: re-add auid to EntityAuth and AuthTicket.
Greg Farnum [Thu, 4 Mar 2010 22:35:53 +0000 (14:35 -0800)]
auth: re-add auid to EntityAuth and AuthTicket.

15 years agomon: add auid field to MonCaps. Also make it a struct --
Greg Farnum [Fri, 5 Mar 2010 23:24:42 +0000 (15:24 -0800)]
mon: add auid field to MonCaps. Also make it a struct --
we want those data members accessible!"

15 years agoAfter discussing with Sage, we do want auid to be a part
Greg Farnum [Fri, 5 Mar 2010 20:37:56 +0000 (12:37 -0800)]
After discussing with Sage, we do want auid to be a part
of AuthTicket, et al. Let's do it that way.
Revert "authtool: give generated key specific uid if one is provided on the cli."

This reverts commit 3a080fa109d1c9106ac6891c97ee5e816b4ea51d.

Revert "cephx: Add auth_uid (if present) to Info for all service types"

This reverts commit 1cb95b419421e99efbebf77950b0e582907060b4.

Revert "osd: mon: caps store auth_uid as an int for fast checking"

This reverts commit 08e21ca094859143955f1c2acbef0a1451bcab90.

15 years agomds: shut up about request latency
Sage Weil [Thu, 4 Mar 2010 21:55:48 +0000 (13:55 -0800)]
mds: shut up about request latency

15 years agomds: return lease on null dentries (ENOENT lookups)
Sage Weil [Thu, 4 Mar 2010 21:34:54 +0000 (13:34 -0800)]
mds: return lease on null dentries (ENOENT lookups)

This provides the client with a lease on a dentry's nonexistence,
allowing it to avoid repetitive ENOENT lookups.

15 years agomds: behave when passed NULL *need_issue
Sage Weil [Thu, 4 Mar 2010 18:30:08 +0000 (10:30 -0800)]
mds: behave when passed NULL *need_issue

Catch two cases: *need_issue = true at top of func
(if (first ...)), and when eval() call resets need_issue again.

15 years agocrushtool: fail on parse error
Sage Weil [Thu, 4 Mar 2010 15:41:20 +0000 (07:41 -0800)]
crushtool: fail on parse error

15 years agomds: accept stray reconnects
Sage Weil [Thu, 4 Mar 2010 00:49:58 +0000 (16:49 -0800)]
mds: accept stray reconnects

Hmm.  Ultimately this is the direction we want to go, so that,
for example, a client that is forcefully disconnected can at
least attempt a reconnect (even if all its caps go ESTALE).
There are undoubtably some issues that need to be dealt with to
keep the mds from choking on weird client data, but those things
need to be fixed regardless.

15 years agofilestore: fix --mkjournal option
Sage Weil [Wed, 3 Mar 2010 22:14:42 +0000 (14:14 -0800)]
filestore: fix --mkjournal option

Read fsid off disk before creating journal.

15 years agofilestore: avoid sync_file_range(2) if not present
Sage Weil [Thu, 4 Mar 2010 17:46:21 +0000 (09:46 -0800)]
filestore: avoid sync_file_range(2) if not present

This disables the flushing 'optimization'.

15 years agofilejournal: avoid sync_file_range(2) if not present
Sage Weil [Thu, 4 Mar 2010 17:45:56 +0000 (09:45 -0800)]
filejournal: avoid sync_file_range(2) if not present

15 years agoautoconf: detect sync_file_range(2)
Sage Weil [Thu, 4 Mar 2010 17:45:44 +0000 (09:45 -0800)]
autoconf: detect sync_file_range(2)

15 years agocrushtool: allow multiple -v's to increase verbosity
Sage Weil [Thu, 4 Mar 2010 17:29:38 +0000 (09:29 -0800)]
crushtool: allow multiple -v's to increase verbosity

15 years agocrushtool: fix parsing with new boost library (compress whitespace)
Sage Weil [Thu, 4 Mar 2010 17:29:23 +0000 (09:29 -0800)]
crushtool: fix parsing with new boost library (compress whitespace)

The latest spirit breaks parsing.  It seems to choke on
whitespace (e.g., fail to parse if there is any trailing
whitespace).  I couldn't find any obvious problems with how
spirit is beign used, so work around it by stripping out any
extra whitespace from the input.  Bleh!

15 years agoosd: mon: caps store auth_uid as an int for fast checking
Greg Farnum [Thu, 4 Mar 2010 02:40:22 +0000 (18:40 -0800)]
osd: mon: caps store auth_uid as an int for fast checking

15 years agocephx: Add auth_uid (if present) to Info for all service types
Greg Farnum [Thu, 4 Mar 2010 02:40:18 +0000 (18:40 -0800)]
cephx: Add auth_uid (if present) to Info for all service types

15 years agoosd: OSDCaps have a better check for ownership
Greg Farnum [Wed, 3 Mar 2010 23:57:27 +0000 (15:57 -0800)]
osd: OSDCaps have a better check for ownership

15 years agoauthtool: give generated key specific uid if one is provided on the cli.
Greg Farnum [Wed, 3 Mar 2010 23:26:11 +0000 (15:26 -0800)]
authtool: give generated key specific uid if one is provided on the cli.

Of course, you can also now just specify it in the caps file.

15 years agoRevert a number of auth_uid commits.
Greg Farnum [Wed, 3 Mar 2010 21:02:06 +0000 (13:02 -0800)]
Revert a number of auth_uid commits.

Attempting to add an auth_uid to all the relevant structs has gotten too messy;
it *will* get messed up at some point in the future. So we're moving it into
the string map caps, and the machines can store it in their local structs
however they like.
Note to self: In future, do not attempt to extend mirrored structs without
great cause. Or else commit to making them properly-encapsulated objects.

Revert "auth: Add an auth_uid to AuthTicket. Still to do: copy it around"

This reverts commit 62c8ceba870eae66e26b4796e3adc468e0165028.

Revert "auth: misc printing and initialization fixes"

This reverts commit ae8ed243dff02a83cc33c2bf4f4e3715715c482b.

Revert "authtool: set generated key to specific uid if one is given"

This reverts commit 2ab6e75c9b0b2b1f0965ad9ce6ea6a701b6e0098.

Revert "auth: constant for unknown/unsecured user"

This reverts commit ea01f18305f5cd79fe8ff69fcbe4dc4b5f13c2f1.

Revert "auth: auth_uid needs to be in AuthCapsInfo as well."

This reverts commit d499cf5c0524b2266170f9fe1b7b53451b84aa73.

Revert "auth: Add a uid field to EntityAuth; make it a required feature"

This reverts commit 14052d4b12a7efb178af5147d761a1589c23e413.

Conflicts:

src/include/ceph_fs.h

15 years agotodo
Sage Weil [Thu, 4 Mar 2010 00:55:12 +0000 (16:55 -0800)]
todo

15 years agoinit-ceph: return success error code on missing ceph.conf if no -c
Sage Weil [Tue, 2 Mar 2010 23:41:23 +0000 (15:41 -0800)]
init-ceph: return success error code on missing ceph.conf if no -c

This will avoid errors when installing/removing the unconfigured
package.

15 years agomds: fix snapid tests in encode_inodestat
Sage Weil [Tue, 2 Mar 2010 23:35:49 +0000 (15:35 -0800)]
mds: fix snapid tests in encode_inodestat

Snapid should always be non-zero; assert as much.

This fixes bug where valid was set to false when stating dir
inodes on non-auth mds's, which in turn returned no caps to
clients and, in the case of cfuse, caused a crash.