Greg Farnum
6b9f7806ee
uclient: Better fix for insert_dentry_inode to work with pre-built Dentrys.
2009-09-22 13:02:50 -07:00
Greg Farnum
a905078731
uclient: get_or_create should return out-of-date lease Dentrys too
2009-09-22 13:02:50 -07:00
Greg Farnum
c57f0d0190
uclient: encode_cap_releases shouldn't update caps if inode isn't in the cache
2009-09-22 13:02:50 -07:00
Greg Farnum
e46c72007a
uclient: First attempt at preemptive cache dropping in the functions.
2009-09-22 13:02:50 -07:00
Greg Farnum
df48cadcee
uclient: Don't *always* set_dentry_wanted() on MClientRequests.
2009-09-22 13:02:50 -07:00
Greg Farnum
99c58ba57d
uclient: Only make the MClientRequest in send_request itself.
...
Add a few more functions to MetaRequest so we can use those in choose_mds.
2009-09-22 13:02:50 -07:00
Greg Farnum
5fd3cf0ad3
uclient: More debugging. May want to back off the inode printout to
...
not include caps_issued.
2009-09-22 13:02:50 -07:00
Greg Farnum
425dcc1dc5
uclient: changed link and insert_dentry_inode to behave with pre-built dentrys
2009-09-22 13:02:50 -07:00
Greg Farnum
f3c78bee11
uclient: Attempt preemptive cap dropping on mknod.
2009-09-22 13:02:50 -07:00
Greg Farnum
3ea4fbfdc1
uclient: dout statements in new functions.
2009-09-22 13:02:50 -07:00
Greg Farnum
4acdb0545e
uclient: Fixes for get_or_create
2009-09-22 13:02:50 -07:00
Greg Farnum
f8c02856d7
uclient: Functions to create Dentrys prior to gettin caps from mds.
2009-09-22 13:02:50 -07:00
Sage Weil
eed8bc07cc
remove extra whitespace
2009-09-22 12:29:33 -07:00
Sage Weil
8b4c05d80a
kclient: fix bit test logic
...
This fixes the fault messages with <NULL> in them; we now print
the proper message, and in a timely fashion.
2009-09-22 12:26:52 -07:00
Sage Weil
73cfce7355
kclient: use pr_fmt to prefix module name
...
This doubles up the ceph:ceph: if we have CONFIG_DYNAMIC_DEBUG, but
that's not our fault.
2009-09-22 12:15:33 -07:00
Sage Weil
949f1bf48a
kclient: prefix frag_ functions with ceph_
...
It was suggested this would avoid any potential conflict with TCP.
It's a good idea to keep the namespace clean anyway.
2009-09-22 11:50:29 -07:00
Sage Weil
c6faf6a15f
kclient: kill out_qlen
...
This is apparently buggy (not immediately obvious why) but it's
only really useful for debugging anyway (it makes it easier to
match up message sequence numbers). Rip it out.
2009-09-22 11:27:32 -07:00
Sage Weil
1744628de2
make inline string functions non-inline
2009-09-22 11:17:22 -07:00
Sage Weil
c2b4dc3d05
kclient: whitespace
2009-09-22 10:17:40 -07:00
Sage Weil
ab3c421eb9
v0.15
2009-09-22 10:13:11 -07:00
Sage Weil
c6e5d6e432
Makefile: include ioctl-number.patch
2009-09-22 10:10:40 -07:00
Sage Weil
1f1ec71ab1
msgr: don't print source in msg debug output
2009-09-22 10:10:27 -07:00
Sage Weil
13e6f345cf
todo
2009-09-22 10:00:31 -07:00
Sage Weil
48866c2f94
monclient: change pick_new_mon -> reopen_session
2009-09-22 09:59:23 -07:00
Sage Weil
88fd161523
monclient: avoid dup subscribe messages
2009-09-22 09:58:07 -07:00
Sage Weil
d8c8da8649
osd: subscribe to monmap
2009-09-22 09:55:21 -07:00
Sage Weil
cf3192dd39
todo
2009-09-21 16:52:40 -07:00
Sage Weil
0a338c1d9d
kclient: fix le encoding bugs (yay sparse)
2009-09-21 16:52:19 -07:00
Sage Weil
f5b46bf0fa
kclient: clean whitespace
2009-09-21 16:49:56 -07:00
Sage Weil
ee04c5657c
kclient: include object name in DATALOC ioctl result
2009-09-21 16:40:00 -07:00
Sage Weil
1af730352d
kclient: include ioctl-number doc file in patch set
2009-09-21 16:26:50 -07:00
Sage Weil
c0c3444e96
kclient: no need for static ceph_buffer
2009-09-21 16:26:35 -07:00
Sage Weil
0f22324d86
mds: fix mds standby map handling
...
Borken by c6ddbdb467
2009-09-21 15:11:26 -07:00
Sage Weil
84c1a14488
mon: consolidate sub request msgs; cleaner api
...
Caller must call renew_subs() explicitly when they want to start
the subscription(s).
2009-09-21 14:55:59 -07:00
Sage Weil
98e6da670f
mon: allow sub for monmap
2009-09-21 14:45:45 -07:00
Sage Weil
c2c9ecd1dd
mon: fix up subscribe infrastructure to use msgr connection for sessions
...
Session state is now cleaned up when connections drop. More
efficient in-memory structures.
2009-09-21 14:30:19 -07:00
Sage Weil
f65d127ee3
msgr: pass Connection* to msgr error handlers
...
This lets the error handlers get at session state (if any).
2009-09-21 14:24:35 -07:00
Sage Weil
35dc047356
mon: fix client id preallocation
...
Broken by b2c7655093
2009-09-21 14:06:15 -07:00
Sage Weil
9a45979b08
monclient: send a single mount request
2009-09-21 14:05:57 -07:00
Sage Weil
316f716d05
uclient: use ref in constructor for MClientRequest
2009-09-21 12:01:06 -07:00
Sage Weil
5dfe8fae0c
kclient: two msgpool modes: blocking (ala mempool_t) and !blocking (strict)
...
Only warn on !blocking pool depletion!
2009-09-18 16:42:09 -07:00
Sage Weil
84aec7d312
kclient: fix symlink kmalloc under spinlock
2009-09-18 16:32:26 -07:00
Sage Weil
71b2ee0f2c
strerror -> strerror_r
2009-09-18 16:17:04 -07:00
Sage Weil
6f00f11155
kclient: rename msgpool type
2009-09-18 14:57:35 -07:00
Sage Weil
c517d7f53c
kclient: use msgpools for osd requests, replies
2009-09-18 14:54:04 -07:00
Sage Weil
ebc6e6cba4
uclient: fix null pointer ref
2009-09-18 14:18:43 -07:00
Sage Weil
61948498cf
kclient: fix up ceph_client init error handling
2009-09-18 14:15:44 -07:00
Sage Weil
f0f10d6309
kclient: fix patchset comment
2009-09-18 14:05:10 -07:00
Sage Weil
d0efb5a7f5
kclient: fall back to WARN + new allocation if msgpool is depleted
2009-09-18 14:04:50 -07:00
Sage Weil
3be2b62b3f
kclient: use msgpools for other monc messages
2009-09-18 13:08:25 -07:00
