Commit Graph

9425 Commits

Author SHA1 Message Date
Sage Weil
a7ae330d22 qa: make -j on kernel build 2010-03-08 15:10:45 -08:00
Sage Weil
c9506f71ad Revert "mon: Hack -- set allow_all in caps if client name is admin"
This reverts commit f07ce468e5.
2010-03-08 15:10:14 -08:00
Sage Weil
e0c3c15e2b mds: note when we last became non-laggy 2010-03-08 14:51:24 -08:00
Sage Weil
0383878c4f mkcephfs: cosd mkfs as root, then chown 2010-03-08 14:51:24 -08:00
Sage Weil
d77caf22a6 todo bugs 2010-03-08 14:51:24 -08:00
Sage Weil
822ae4a1bb 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.
2010-03-08 14:51:24 -08:00
Sage Weil
ca02d68cc6 cauthtool: verify set_uid arg 2010-03-08 14:51:23 -08:00
Sage Weil
dc38d48948 mds: dump misc struct sizes to log 2010-03-08 14:51:20 -08:00
Sage Weil
9c8eef20b0 monclient: time out properly from wait_auth_rotating 2010-03-08 14:49:43 -08:00
Sage Weil
fb5ecb9be9 decay: separate fixed DecayRate from DecayCounter
Avoid eating a double per instance.
2010-03-08 14:49:43 -08:00
Sage Weil
fdb85cad0d mds: drop useless double from DecayCounter
No need to store k AND halflife.
2010-03-08 14:49:43 -08:00
Greg Farnum
f07ce468e5 mon: Hack -- set allow_all in caps if client name is admin 2010-03-08 07:47:47 -08:00
Greg Farnum
9199dd2d9e objecter: librados: add optional auid param to
create_pool functions
2010-03-08 07:42:16 -08:00
Greg Farnum
14cdfd4337 objecter: add auid to PoolOp, fill it in during pool_op_submit 2010-03-08 07:42:16 -08:00
Greg Farnum
fbe08c7830 mon: let prepare_new_pool assign an auid.
Add new version that takes an MPoolOp and checks permissions
first.
2010-03-08 07:42:16 -08:00
Greg Farnum
07df67f394 mon: add check_privileges function to OSDMon. 2010-03-08 07:42:15 -08:00
Greg Farnum
1b7119f943 msg: Add an auid field to MPoolOp; additional constructor to match 2010-03-08 07:41:59 -08:00
Greg Farnum
3b1bf4bdda auth: move CEPH_AUTH_UID_DEFAULT into ceph_fs.h 2010-03-05 16:47:26 -08:00
Greg Farnum
4020dd1a0b cauthtool: set auid in data member format instead of as (ignored) text key 2010-03-05 15:46:54 -08:00
Greg Farnum
6d6eba3313 mon: store auid in MonCaps 2010-03-05 15:46:54 -08:00
Greg Farnum
c898ba546d osd: store auid in OSDCaps 2010-03-05 15:46:54 -08:00
Greg Farnum
1b211e5ef3 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!
2010-03-05 15:46:54 -08:00
Greg Farnum
036f923a8e auth: add set_uid() to KeyRing, print out auid in print function 2010-03-05 15:46:54 -08:00
Greg Farnum
846acac212 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
2010-03-05 15:46:54 -08:00
Greg Farnum
4637d18f1a 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.
2010-03-05 15:46:54 -08:00
Greg Farnum
f58c41b993 auth: rename auth_uid -> auid 2010-03-05 15:46:54 -08:00
Greg Farnum
1d2516df5f auth: re-add auid to EntityAuth and AuthTicket. 2010-03-05 15:46:54 -08:00
Greg Farnum
d4c9453458 mon: add auid field to MonCaps. Also make it a struct --
we want those data members accessible!"
2010-03-05 15:46:54 -08:00
Greg Farnum
4dd6b8d274 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 3a080fa109.

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

This reverts commit 1cb95b4194.

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

This reverts commit 08e21ca094.
2010-03-05 15:46:54 -08:00
Sage Weil
e93146631a mds: shut up about request latency 2010-03-04 13:55:48 -08:00
Sage Weil
f4d9916826 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.
2010-03-04 13:34:54 -08:00
Sage Weil
1f49bff216 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.
2010-03-04 10:30:08 -08:00
Sage Weil
18173b53cc crushtool: fail on parse error 2010-03-04 10:02:15 -08:00
Sage Weil
0f11eee59e 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.
2010-03-04 10:02:09 -08:00
Sage Weil
265ad9ece4 filestore: fix --mkjournal option
Read fsid off disk before creating journal.
2010-03-04 10:02:06 -08:00
Sage Weil
1477ec73e3 filestore: avoid sync_file_range(2) if not present
This disables the flushing 'optimization'.
2010-03-04 09:46:21 -08:00
Sage Weil
71b9a19481 filejournal: avoid sync_file_range(2) if not present 2010-03-04 09:45:56 -08:00
Sage Weil
3a76b63f8d autoconf: detect sync_file_range(2) 2010-03-04 09:45:44 -08:00
Sage Weil
6a296bf71a crushtool: allow multiple -v's to increase verbosity 2010-03-04 09:29:38 -08:00
Sage Weil
dd43f083d0 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!
2010-03-04 09:29:23 -08:00
Greg Farnum
08e21ca094 osd: mon: caps store auth_uid as an int for fast checking 2010-03-03 19:48:23 -08:00
Greg Farnum
1cb95b4194 cephx: Add auth_uid (if present) to Info for all service types 2010-03-03 19:48:17 -08:00
Greg Farnum
363647b99e osd: OSDCaps have a better check for ownership 2010-03-03 17:15:48 -08:00
Greg Farnum
3a080fa109 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.
2010-03-03 17:15:48 -08:00
Greg Farnum
c8e4f54fff 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 62c8ceba87.

Revert "auth: misc printing and initialization fixes"

This reverts commit ae8ed243df.

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

This reverts commit 2ab6e75c9b.

Revert "auth: constant for unknown/unsecured user"

This reverts commit ea01f18305.

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

This reverts commit d499cf5c05.

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

This reverts commit 14052d4b12.

Conflicts:

	src/include/ceph_fs.h
2010-03-03 17:15:48 -08:00
Sage Weil
ed1239707d todo 2010-03-03 16:55:12 -08:00
Sage Weil
51081fa307 init-ceph: return success error code on missing ceph.conf if no -c
This will avoid errors when installing/removing the unconfigured
package.
2010-03-03 14:40:31 -08:00
Sage Weil
e307f2b76b 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.
2010-03-03 14:40:28 -08:00
Sage Weil
0ee0a8d465 mds: fix null pointer deref in resolve on mostly-empty mds
We may not have any dirfrags during resolve if the mds crashed
while stopping.
2010-03-03 09:47:37 -08:00
Sage Weil
d844ddee5d journal: set committing_seq in commit_start
We need to set committing_seq when we first block access to the
fs in commit_start(), NOT in commit_started(), as by that time
we may have queued all sorts of additional entries for the
journal.  The committing_seq is all about syncing up with the
live fs (via op_apply_start), not what's queued for the journal.
2010-03-03 09:47:00 -08:00