Sage Weil
4ea86ba125
kclient: use smp_mb in place of spinlock for testing flag bit
2009-10-01 11:21:54 -07:00
Sage Weil
fe11285c4b
kclient: add smp_mb to sensitive bitops in msgr
2009-10-01 11:07:09 -07:00
Sage Weil
c30d453610
uclient: set new file layout to 0, which lets mds choose its default
2009-10-01 10:59:10 -07:00
Greg Farnum
860dca7ddc
uclient: Use much saner/not insane defaults for layout settings
2009-09-30 17:03:22 -07:00
Sage Weil
bce85f1cc5
kclient: debugfs fix; better osdmap debug output
2009-09-30 14:10:46 -07:00
Sage Weil
adb48e25d7
kclient: default pg_preferred to -1
2009-09-30 14:10:23 -07:00
Sage Weil
95c4710eba
mds: fix layout typo
2009-09-30 13:30:07 -07:00
Sage Weil
15d45e76bb
kclient: include new files in patch set
2009-09-30 12:53:49 -07:00
Sage Weil
cc9915a5a1
osd: name args in ceph_osd_op union
2009-09-30 12:47:40 -07:00
Sage Weil
21df30f61f
document data structs; kill ttl_ms in caps msg
2009-09-30 12:34:30 -07:00
Sage Weil
25bba5df97
mds: kill old rdcaps_ttl business
...
This was from when caps independently timed out.
2009-09-30 12:24:31 -07:00
Sage Weil
fa884ec13d
fix object_stripe_unit -> stripe_unit
2009-09-30 12:09:11 -07:00
Sage Weil
4874b1901b
kclient: try kmalloc, then vmalloc
...
"A still-lame-but-less-lame option here would be to attempt the kmalloc
(with __GFP_NOWARN) and if it failed, fall back to vmalloc." says akpm
2009-09-30 11:43:31 -07:00
Sage Weil
86f225b52e
kclient: audit inline
2009-09-30 11:32:03 -07:00
Sage Weil
59fc0e27d5
kclient: more fixes from akpm's review
2009-09-30 11:01:37 -07:00
Sage Weil
c064c4456d
uninline some header types
2009-09-30 10:24:28 -07:00
Sage Weil
8dbf3580a5
kclient: parse updated mdsmap
2009-09-29 14:53:15 -07:00
Sage Weil
6b68faaef8
mdsmap: another unsized int
2009-09-29 14:53:15 -07:00
Sage Weil
bc919199ca
mdsmap: use sized int type
2009-09-29 14:53:15 -07:00
Sage Weil
4dbb6fdfdb
todo
2009-09-29 14:53:15 -07:00
Sage Weil
dc6d0d9374
kclient: reorder cap ops a bit (wrt invalidation)
2009-09-29 14:53:15 -07:00
Greg Farnum
52f038e56b
Hadoop: Set the local osd to be the preferred osd for all writes.
2009-09-29 13:38:34 -07:00
Greg Farnum
ecc4bd6837
uclient: Add methods for setting a default preferred osd.
2009-09-29 13:38:34 -07:00
Greg Farnum
58fb071e0e
mds/ceph_fs: Add a preferred argument to ceph_mds_request_args and listen to it
2009-09-29 13:38:34 -07:00
Sage Weil
6ed33d57ab
mon: create lpg_num (not pg_num) lpg's
2009-09-29 11:09:38 -07:00
Sage Weil
462dd4f625
cosd: 3 monitors
2009-09-29 11:09:38 -07:00
Sage Weil
1010c20ca5
uclient: open mds sessions to export targets
2009-09-29 09:49:35 -07:00
Sage Weil
ce87f0fc8b
mds: add export targest to mds_info_t
2009-09-28 21:16:02 -07:00
Sage Weil
4fa1ba7072
osd: rev disk format
2009-09-28 15:23:56 -07:00
Sage Weil
a858ffa470
mon: create localized pgs
2009-09-28 15:23:09 -07:00
Sage Weil
6af69e0ca6
filestore: make collection dir have better name; move coll_t type around
2009-09-28 15:23:09 -07:00
Sage Weil
3c315e308b
objecter: send renew sub from maybe_request_map()
...
This broke with the last monc api change
2009-09-28 15:23:09 -07:00
Sage Weil
6e76160caf
osd: make pg_pool_t print clearer
2009-09-28 15:23:09 -07:00
Greg Farnum
5f450ec010
Merge branch 'unstable' of ceph.newdream.net:/git/ceph into unstable
2009-09-28 13:55:03 -07:00
Greg Farnum
b1b612fc19
uclient: Return EFBIG rather than EBADF on too-large file sizes.
2009-09-28 13:54:55 -07:00
Sage Weil
78648b2004
kclient: bug on bad msg in msgr
2009-09-28 13:51:11 -07:00
Sage Weil
56affd7f85
filestore: use btrfs TRANS_RESV_START ioctl if present
...
This will detect ENOSPC when starting the transaction, instead of
failing part way through.
2009-09-28 13:51:10 -07:00
Sage Weil
db66e1977f
osd: make shutdown msg higher priority
...
This makes cosd more responsive to SIGTERM.
2009-09-28 13:51:08 -07:00
Sage Weil
4fe2e6acb9
msgr: be a bit more verbose during shutdown
...
At least until this bug is found:
09.09.28 15:16:54.678277 140100507507024 -- 10.10.10.92:6800/5504/0 >> 10.10.10.88:6789/0/0 pipe(0x186ae90 sd=61 pgs=0 cs=0 ltx=1).accept replacing existing (lossy) channel
msg/SimpleMessenger.cc: In function 'void SimpleMessenger::reaper()':
msg/SimpleMessenger.cc:1925: FAILED assert(lock.is_locked())
1: /usr/bin/cosd(_ZN15SimpleMessenger6reaperEv+0x59d) [0x45493d]
2: /usr/bin/cosd(_ZN15SimpleMessenger4waitEv+0x4d) [0x45574d]
3: /usr/bin/cosd(main+0xfe0) [0x44e770]
4: /lib/libc.so.6(__libc_start_main+0xe6) [0x7f6befc145a6]
5: /usr/bin/cosd(__gxx_personality_v0+0x1b9) [0x44d4e9]
NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.
2009-09-28 13:47:50 -07:00
Sage Weil
10e4b6ea33
uclient: get_local_osd() to find an osd with the given ip
2009-09-28 13:47:22 -07:00
Sage Weil
7755f3c7de
kclient: fix generic xattr calls
...
It compiles now :)
2009-09-28 10:58:51 -07:00
Sage Weil
281acde0c1
kclient: user.ceph.layout readonly for now
2009-09-28 10:56:05 -07:00
Sage Weil
22c146fa84
osdmaptool: more usage
2009-09-28 10:09:26 -07:00
Sage Weil
a8ba4486f2
config: allow object replication from 1-10 (instead of 2-3)
2009-09-28 10:09:26 -07:00
Sage Weil
272128f225
kclient: check xattr readonly flag on setxattr, removexattr
2009-09-28 10:09:26 -07:00
Sage Weil
412eefb737
kclient: add helper to set allowed xattr prefixes
2009-09-28 10:09:25 -07:00
Sage Weil
4ac459b46d
kclient: distinguish file vs dir xattrs; move the getvxattr_cb under i_lock
2009-09-28 10:09:25 -07:00
Sage Weil
f9689a234c
kclient: do not recurse into truncate|invalidate pages
...
A single open O_TRUNC on a file dirty pages would
-> truncate
-> put_wrbuffer_refs
-> check_caps
-> invalidate ... and deadlock
So, do not invalidate here if we have a pending truncate (which
remains elevated until after the truncate finishes).
2009-09-25 15:58:16 -07:00
Greg Farnum
467926ffc5
uclient: Pass in the right variables to update_inode_file_bits!
2009-09-25 15:55:34 -07:00
Greg Farnum
4b819b9082
uclient: Rework update_inode_file_bits to mimic kclient; better debugging
2009-09-25 15:55:34 -07:00