Commit Graph

5713 Commits

Author SHA1 Message Date
Yehuda Sadeh
0c46645be3 kclient: sync writeout when not pdflush 2009-02-19 11:52:10 -08:00
Sage Weil
2d17b3a0d2 mds: only flush journal when we need to
Force a flush every tick just in case.
2009-02-19 11:01:51 -08:00
Sage Weil
0f05de942d kclient: set 'sync' flag for fsync
This will ensure that fsynced data is committed immediately by the
OSDs.
2009-02-18 14:20:05 -08:00
Sage Weil
94c5031e6d script: fix check_osd_request_latency 2009-02-18 11:53:51 -08:00
Sage Weil
cec662cc5f script: check_osd_request_latency 2009-02-18 11:47:23 -08:00
Yehuda Sadeh
ffc756ea68 conf: can turn on debug logs in startup.conf 2009-02-18 11:07:19 -08:00
Yehuda Sadeh
6a71ef7525 conf: add debug_ms option 2009-02-17 13:26:24 -08:00
Sage Weil
dbfa9c3e63 mds: don't rdlock stat fields that client has EXCL cap for 2009-02-17 12:15:39 -08:00
yehudasa
4e88a943ed add ceph_init to distribution 2009-02-17 10:57:48 -08:00
Yehuda Sadeh
d8ac8e5e5d kclient: backport changes to kernel 2.6.25 2009-02-17 10:45:34 -08:00
Yehuda Sadeh
f62e4db415 kclient: fix mdsc->snap_empty cleanup 2009-02-13 17:09:12 -08:00
Yehuda Sadeh
f0a2967f05 kclient: remove client from client list before destorying 2009-02-13 17:06:22 -08:00
Yehuda Sadeh
c5ed89a98f kclient: fix proc cleanup 2009-02-13 15:02:51 -08:00
Yehuda Sadeh
c98bb11a39 assert: some more assert_warn 2009-02-12 16:47:56 -08:00
Yehuda Sadeh
af812a0621 cosd: change some assert to assert_warn and clean exit 2009-02-12 15:05:12 -08:00
Yehuda Sadeh
5dc7beaf16 kclient: show some meaningful info in client proc entry 2009-02-12 12:43:17 -08:00
Yehuda Sadeh
172afed512 kclient: per client proc data file 2009-02-12 11:05:45 -08:00
Yehuda Sadeh
2b82ea40b2 kclient: added a proc function to read client data 2009-02-10 16:21:20 -08:00
Yehuda Sadeh
9ddbf9dbb8 kclient: proc subdir for each ceph client 2009-02-10 16:08:02 -08:00
Yehuda Sadeh
3b2cffdd61 kclient: keep global list of ceph clients 2009-02-10 15:42:51 -08:00
Yehuda Sadeh
b1203c227e assert: warn on assertion if requested for current thread 2009-02-09 16:29:43 -08:00
Yehuda Sadeh
c511d68dea added a common initialization function 2009-02-09 15:46:02 -08:00
Yehuda Sadeh
3ce47d046a tls: addeed a thread local storage infrastructure
(cherry picked from commit 1b6b128f4e2aaab016575f48f2ec50d4abe002c9)
2009-02-09 15:01:21 -08:00
Yehuda Sadeh
62ee4089c8 osd: fix log level 2009-01-30 16:24:41 -08:00
Sage Weil
7e10dfac34 mds: make sure we eval_stray when inode was replicated
Also, drop dn to end of lru if unlinked and last cap.
2009-01-30 16:03:13 -08:00
Sage Weil
db46dadae9 mds: remove traces of CDir::committed_version_equivalent
Don't think it's coming back
2009-01-30 16:03:13 -08:00
Sage Weil
306e5560a7 kclient: release CAP_LINK_RDCACHE before unlink 2009-01-30 16:03:13 -08:00
Sage Weil
83c19c81e1 vstart: fix call to stop.sh 2009-01-30 16:03:13 -08:00
Sage Weil
d37775de55 todos 2009-01-30 16:03:11 -08:00
Sage Weil
95f63ea3c7 osd: print ops args correctly 2009-01-30 16:03:11 -08:00
Sage Weil
0b75ee62d4 mds: use generic helper when removing a cap
This way we make sure to do all the right checks on the locks,
mds_caps, and to call eval_stray if the inode is unlinked.
2009-01-30 16:03:11 -08:00
Sage Weil
179f7a81e2 mds: fix try_remove_unlinked_dn
Clear dentry NEW flag when we commit it.. pretty sure that was the
old bug.  And we can't cheat the directory commit because the fnode
also gets updated.
2009-01-30 16:03:11 -08:00
Sage Weil
569c5d2e41 mds: fix purge of 0-length inode 2009-01-30 16:03:11 -08:00
Sage Weil
7b118b3d54 mds: remove unused inode purge fields 2009-01-30 16:03:10 -08:00
Yehuda Sadeh
756a4c1371 ceph_init: fix initalization 2009-01-30 15:56:36 -08:00
Yehuda Sadeh
bfb6cda4f3 ceph_init: added missing file 2009-01-30 15:48:56 -08:00
Yehuda Sadeh
c6ff2e6aaf ceph_init: initial version 2009-01-30 15:47:59 -08:00
Yehuda Sadeh
7ed99eabc3 crun: restart only processes that should have dumped core 2009-01-30 12:46:17 -08:00
Sage Weil
fe1a365365 todo 2009-01-30 11:44:34 -08:00
Sage Weil
81bf6efdea osd: put full original reqid in osd_op_reply 2009-01-30 11:44:34 -08:00
Sage Weil
4968553c22 mds: typos 2009-01-30 11:44:34 -08:00
Sage Weil
1df22a51a0 kclient: don't retain caps if inode is closed and nlink == 0 2009-01-30 11:44:33 -08:00
Sage Weil
57d8ba9990 mds: rip out old purge_inode crap 2009-01-30 11:44:33 -08:00
Sage Weil
0d8ba65980 mds: simplify purge_stray
Just delete objects and then journal completion.  No need to do
the funky purge_inode double commit crap, since we will re-eval
strays later any (and do it all again if needed).
2009-01-30 11:44:33 -08:00
Sage Weil
e32e434d43 mds: clean up opent a bit 2009-01-30 11:44:33 -08:00
Sage Weil
93e587ea7d mds: drop _do_open helper
only one caller
2009-01-30 11:44:33 -08:00
Sage Weil
f49d8ac12b mds: open O_TRUNC implemented.. but not used by kclient :/ 2009-01-30 11:44:33 -08:00
Sage Weil
1d15f8f559 mds: implement async truncate (trimtrunc); fix log segment trim vs purge bug
Logsegs were allowed to trim even with outstanding purges.. fix.
2009-01-30 11:44:33 -08:00
Sage Weil
0f11a1a7de osd: fix truncate ops; add TRIMTRUNC 2009-01-30 11:44:33 -08:00
Sage Weil
e0dcc7cf49 mds: truncate changes. not complete.
We don't clean up after we finish our truncate.
2009-01-30 11:44:33 -08:00