Whamcloud - gitweb
ericm [Fri, 12 Aug 2005 23:52:48 +0000 (23:52 +0000)]
fix default path for lacl_upcall.
alex [Fri, 12 Aug 2005 21:35:11 +0000 (21:35 +0000)]
r=adilger
- two equal statements in a row
ericm [Fri, 12 Aug 2005 21:35:03 +0000 (21:35 +0000)]
various message adjustment (more verbose) for remote acl upcall and lsd
upcalls, for debugging.
alex [Fri, 12 Aug 2005 21:32:49 +0000 (21:32 +0000)]
b=7272
- additional debug
adilger [Fri, 12 Aug 2005 19:05:21 +0000 (19:05 +0000)]
Branch b1_4
Put only the filenames into the cvs-merge-conflicts file, so that
vi `cat cvs-merge-conflicts` works.
alex [Fri, 12 Aug 2005 19:01:54 +0000 (19:01 +0000)]
- ph_subsys can be 7 symbols in HEAD
ericm [Fri, 12 Aug 2005 18:52:50 +0000 (18:52 +0000)]
do reverse idmapping for remote perm fetch.
ericm [Fri, 12 Aug 2005 17:36:56 +0000 (17:36 +0000)]
fix someone's typo.
yury [Fri, 12 Aug 2005 15:15:33 +0000 (15:15 +0000)]
- two ASSERTs int filter_parent() changed to ASSERTF with failed values for debug purposes.
yury [Fri, 12 Aug 2005 13:29:02 +0000 (13:29 +0000)]
- expanded error message in lov md sanity check function.
yury [Fri, 12 Aug 2005 12:36:43 +0000 (12:36 +0000)]
- fixed memory leak in ll_setxattr_internal()
yury [Fri, 12 Aug 2005 12:21:14 +0000 (12:21 +0000)]
- many fixes about using ENTRY, RETURN, GOTO and EXIT.
- md_close() chnaged to use mdc_op_data like other md_* functions instead of using obdo.
- fixed prototype declaration for llapi_lov_get_uuids() - bug #6900
- fixed error message in ll_gns_mount_object() - bug #7146
- a lot of fixes about memory allocation/freeing:
- checks is memory is actually allocated by OBD_ALLOC() before sing it and do appropriate
actions otherwise.
- fixed many leaks on error paths.
- fixed missed OBD_FREE(capa_hash) in capa_cache_cleanup()
- fixed few on stack allocatoins of mdc_op_data in new landed stuff.
- in smfs_mount_cache() fixes correct cleanup in the cases of memory allocation failures.
Do mntput() for new mounted cache_mnt on error path.
- in smfs_umount_cache() nullify smb->smsi_cache_ftype and smb->smsi_ftype after freeing
them, to prevent attempt to free again if smfs_umount_cache() is called second time.
niu [Fri, 12 Aug 2005 08:08:15 +0000 (08:08 +0000)]
revert previous commit: only transfer one record once time
ericm [Fri, 12 Aug 2005 07:12:41 +0000 (07:12 +0000)]
more of b7300: fix (actually hack around) the getattr reply buffer
positioning: make remote acl always occupy 2 buffers, just like local
acl.
niu [Fri, 12 Aug 2005 06:17:18 +0000 (06:17 +0000)]
- don't call obd_set_info() on the NULL mdc export on rename.
- transfer only one audit record on one notify.
- make sure the connection has been established before using the mdc export on name reconstruction.
wangdi [Fri, 12 Aug 2005 04:55:41 +0000 (04:55 +0000)]
Branch HEAD
add type check in set_crypt
wangdi [Fri, 12 Aug 2005 03:40:39 +0000 (03:40 +0000)]
Branch: HEAD
fix typo usage for set_crypt
ericm [Thu, 11 Aug 2005 23:47:58 +0000 (23:47 +0000)]
add some error message, try to catch the occasional lsd upcall failure.
adilger [Thu, 11 Aug 2005 20:03:10 +0000 (20:03 +0000)]
Branch HEAD
Disable hlist macros unless compiling liblustre. In b1_4 there are compat
macros in lustre_compat25.h that handle difference between 2.4 and 2.6
kernels instead of defining replacement macros.
ericm [Thu, 11 Aug 2005 18:09:48 +0000 (18:09 +0000)]
suppress a unnecessary message.
ericm [Thu, 11 Aug 2005 18:06:50 +0000 (18:06 +0000)]
fix regression introduced by capabilities.
b=7300
yury [Thu, 11 Aug 2005 11:55:33 +0000 (11:55 +0000)]
- fixes for making liblustre at least buildable (including fixes to compilation bug found by Brian recently)
yury [Thu, 11 Aug 2005 11:52:47 +0000 (11:52 +0000)]
- fixes needed for building liblustre
wangdi [Thu, 11 Aug 2005 08:45:05 +0000 (08:45 +0000)]
Branch: HEAD
some fixes about crypto api
1)some fixes about init inode key
2)some fixes about compute new mac
yury [Thu, 11 Aug 2005 07:32:52 +0000 (07:32 +0000)]
- set only LOV_EA in mds_reint_setattr() in the case of CMOBD reint as setting sid and pid will confuse master MDS.
- set mds_security to "null" in lustre_connect_mds() if not specified or panic is possible.
adilger [Wed, 10 Aug 2005 17:23:16 +0000 (17:23 +0000)]
Land b_release_1_4_4 onto HEAD (20050810_0253)
Check for error writing to acceptor $PIDFILE.
Accptor reports when it has exited to syslog, so we can trace if it is a
culprit in the "bind: address already in use" problem.
b=5509
b=7283
brian [Wed, 10 Aug 2005 17:16:58 +0000 (17:16 +0000)]
Backout "liblustre now builds" commit. It breaks building in utils:
../../lustre/include/linux/lustre_sec.h:541: error: field `c_hash' has incomplete type
wangdi [Wed, 10 Aug 2005 14:08:05 +0000 (14:08 +0000)]
Branch: HEAD
some fixes about crypto api
yury [Wed, 10 Aug 2005 13:03:33 +0000 (13:03 +0000)]
- many fixes in liblustre related stuff. By now liblustre is at least build-able in HEAD.
niu [Wed, 10 Aug 2005 10:17:59 +0000 (10:17 +0000)]
- check connection before calling obd_set_info to set ids on an specified mdc.
- typo fix in mds_set_info.
adilger [Wed, 10 Aug 2005 07:05:06 +0000 (07:05 +0000)]
Branch HEAD
Bump keepalive interval to send fewer total keepalives.
Trying to determine if this is cause of BG/L EMAC "flood" issue at
cleanup time.
tappro [Tue, 9 Aug 2005 22:42:00 +0000 (22:42 +0000)]
- rc code is not failure is > 0
- only files on OSS should be audited
- audit_fill_id_rec is valid only on mds. Moved to mds_audit.c
- audit_ost_get_id() gets lustre id for OSS object for audit log
eeb [Tue, 9 Aug 2005 15:24:44 +0000 (15:24 +0000)]
* #ifdef for extra proc_dointvec parameter under linux 2.6.8 in ranal and
openibnal (bz 7217)
* remove WIRE_ATTR from iibanl kib_md_t (it's not a wire struct)
eeb [Tue, 9 Aug 2005 14:50:26 +0000 (14:50 +0000)]
* fixed openibnal/iibnal wire structs to use WIRE_ATTR. This (for openibnal)
is part of a fix for bz 7217
wangdi [Tue, 9 Aug 2005 14:26:52 +0000 (14:26 +0000)]
Branch HEAD
get the correct uid, gid and mode when compute the new acl
lsy [Tue, 9 Aug 2005 12:04:07 +0000 (12:04 +0000)]
Land b_hd_capa onto HEAD (20050809_1942)
alex [Tue, 9 Aug 2005 10:55:17 +0000 (10:55 +0000)]
- put fill fid in a punch request
wangdi [Tue, 9 Aug 2005 10:12:37 +0000 (10:12 +0000)]
Branch: b_hd_crypto
some fixes about crypto api
1)some debug info fix
2)reorganize the code for mds_set_gskey
tappro [Tue, 9 Aug 2005 05:32:49 +0000 (05:32 +0000)]
- add mountoptions argument to lmv.sh
alex [Mon, 8 Aug 2005 23:15:01 +0000 (23:15 +0000)]
- let's learn where uninitialized objects come from
tappro [Mon, 8 Aug 2005 23:03:16 +0000 (23:03 +0000)]
b=7277
dentry is used before initialization.
alex [Mon, 8 Aug 2005 22:57:45 +0000 (22:57 +0000)]
b=4268
- additional debug info
alex [Mon, 8 Aug 2005 22:55:08 +0000 (22:55 +0000)]
- add second mountpoint in the config
yury [Mon, 8 Aug 2005 18:40:52 +0000 (18:40 +0000)]
- landed b_hd_mdref (mostly WB cache fixes)
wangdi [Mon, 8 Aug 2005 15:07:14 +0000 (15:07 +0000)]
Branch: HEAD
some minor fixes about sanity-crypto test scripts
tappro [Mon, 8 Aug 2005 14:37:01 +0000 (14:37 +0000)]
- another issue from landing day
tappro [Mon, 8 Aug 2005 13:52:44 +0000 (13:52 +0000)]
- root fid is 2 not 1
- remove unneeded debug
eeb [Mon, 8 Aug 2005 12:50:12 +0000 (12:50 +0000)]
* Incorporated latest GMNAL updates from HP.
Compiled but not run yet.
wangdi [Mon, 8 Aug 2005 09:26:28 +0000 (09:26 +0000)]
Branch: HEAD
some minor fixes about mks crypto
niu [Mon, 8 Aug 2005 09:07:31 +0000 (09:07 +0000)]
split dir after setting id in ea (in lfs dirstripe case)
-b 7265
niu [Mon, 8 Aug 2005 08:16:53 +0000 (08:16 +0000)]
needn't get rootid while reconstruct pathname
alex [Sun, 7 Aug 2005 16:53:26 +0000 (16:53 +0000)]
- mds_validate_size() vs. mds_reint_unlink() race is absolutely legal
alex [Sun, 7 Aug 2005 16:28:09 +0000 (16:28 +0000)]
b=7267,7034
- dedicated threads for serving OST_DESTROY and MDS_CLOSE
alex [Sun, 7 Aug 2005 16:14:49 +0000 (16:14 +0000)]
- don't mix var declarations and code
alex [Sun, 7 Aug 2005 16:14:12 +0000 (16:14 +0000)]
- throw needless debugging bits away
alex [Sun, 7 Aug 2005 14:23:39 +0000 (14:23 +0000)]
- couple minor optimizations
alex [Sun, 7 Aug 2005 14:22:58 +0000 (14:22 +0000)]
- don't pass pid in case of slave creation.
checking for non-zero fid is a wrong practice
alex [Sun, 7 Aug 2005 11:18:14 +0000 (11:18 +0000)]
b=7264
- mballoc must not be used during orphan cleanup
tappro [Sun, 7 Aug 2005 08:33:06 +0000 (08:33 +0000)]
- small fixes after landing
alex [Sun, 7 Aug 2005 07:11:03 +0000 (07:11 +0000)]
- show n_link to learn the race
alex [Sat, 6 Aug 2005 14:54:40 +0000 (14:54 +0000)]
- minor fixes after landing day
alex [Sat, 6 Aug 2005 14:27:49 +0000 (14:27 +0000)]
- show correct id in debug line
alex [Sat, 6 Aug 2005 14:25:33 +0000 (14:25 +0000)]
- return back original OST/MDS sizes
alex [Sat, 6 Aug 2005 12:30:49 +0000 (12:30 +0000)]
- test 19 should take one more internal ea into account (parent fid)
alex [Sat, 6 Aug 2005 12:19:37 +0000 (12:19 +0000)]
- missing back slash caused flood of complains from portals_debug_msg()
alex [Sat, 6 Aug 2005 12:18:13 +0000 (12:18 +0000)]
- one more merging mess
alex [Sat, 6 Aug 2005 12:15:46 +0000 (12:15 +0000)]
- typo from merging
alex [Sat, 6 Aug 2005 12:15:15 +0000 (12:15 +0000)]
- minor cleanups in that patch, quilt pop was claiming about old version
ericm [Sat, 6 Aug 2005 01:59:00 +0000 (01:59 +0000)]
landing b_hd_sec, b6818, b7244
tappro [Sat, 6 Aug 2005 01:06:14 +0000 (01:06 +0000)]
- b_hd_audit landing
alex [Fri, 5 Aug 2005 23:31:06 +0000 (23:31 +0000)]
- minor correction
alex [Fri, 5 Aug 2005 23:14:57 +0000 (23:14 +0000)]
- return right path back
alex [Fri, 5 Aug 2005 23:06:35 +0000 (23:06 +0000)]
- some versions of python don't eat single member set w/o comma
alex [Fri, 5 Aug 2005 23:04:04 +0000 (23:04 +0000)]
b=7039
- lov_change_cbdata() must iterate over all namespaces regardless activeness
alex [Fri, 5 Aug 2005 22:45:06 +0000 (22:45 +0000)]
- track time recovery took and dump a log if it took >obd_timeout * 2
(to simplify debugging tests 11 and 17)
alex [Fri, 5 Aug 2005 22:42:43 +0000 (22:42 +0000)]
- additional debug in ldlm_lock_decref()
alex [Fri, 5 Aug 2005 22:22:41 +0000 (22:22 +0000)]
- during last landing old version of the patch was checked in. fixed
alex [Fri, 5 Aug 2005 22:09:12 +0000 (22:09 +0000)]
- code duplicate we got during landing b_hd_crypto
brian [Fri, 5 Aug 2005 20:42:37 +0000 (20:42 +0000)]
Add missing file from distribution.
alex [Fri, 5 Aug 2005 20:34:14 +0000 (20:34 +0000)]
- repair lmv.sh - it was broken for months
nikita [Fri, 5 Aug 2005 18:12:10 +0000 (18:12 +0000)]
comment for ll_readahead_state and assertion in osc_send_oap_request() from b1_4
wangdi [Fri, 5 Aug 2005 14:48:14 +0000 (14:48 +0000)]
Branch: HEAD
typo fix after land
wangdi [Fri, 5 Aug 2005 14:45:34 +0000 (14:45 +0000)]
Branch: HEAD
land crypto api
alex [Fri, 5 Aug 2005 09:12:57 +0000 (09:12 +0000)]
- warn about the race in filter_intent_policy(), just to make sure it
relates to errors mds gets sometimes
alex [Thu, 4 Aug 2005 21:49:13 +0000 (21:49 +0000)]
b=7039
- don't skip locks on inactive imports
alex [Thu, 4 Aug 2005 19:14:37 +0000 (19:14 +0000)]
b=7039
- dump additional debug info
alex [Thu, 4 Aug 2005 13:32:51 +0000 (13:32 +0000)]
- missing \n
alex [Thu, 4 Aug 2005 13:04:54 +0000 (13:04 +0000)]
b=7039
- check for llite inode magic
alex [Thu, 4 Aug 2005 12:06:55 +0000 (12:06 +0000)]
- no more flooding
alex [Thu, 4 Aug 2005 11:40:59 +0000 (11:40 +0000)]
b=7039
- more debugging info
alex [Thu, 4 Aug 2005 11:33:40 +0000 (11:33 +0000)]
b=7049
- remove needless debugging checks
niu [Thu, 4 Aug 2005 09:45:49 +0000 (09:45 +0000)]
give a warnning if somebody don't pass lustre id to ost, it should be
error assertion in future.
liangzhen [Thu, 4 Aug 2005 09:00:13 +0000 (09:00 +0000)]
Fix of careless (miss ;;)
niu [Thu, 4 Aug 2005 08:46:29 +0000 (08:46 +0000)]
store lustre id in ost object's EA.
liangzhen [Thu, 4 Aug 2005 07:56:21 +0000 (07:56 +0000)]
CFLAGS for compiling in Tiger
alex [Wed, 3 Aug 2005 21:56:47 +0000 (21:56 +0000)]
b=7049
- try to unmap buffers from bd-mapping
alex [Wed, 3 Aug 2005 13:29:38 +0000 (13:29 +0000)]
b=7049
- it's enough to check for block number
alex [Wed, 3 Aug 2005 12:18:42 +0000 (12:18 +0000)]
b=7049
- it's better to unmap buffers holding no truncate sem
note: unmap_underlying_metadata() is commented out to see whether
a race happens at all
alex [Wed, 3 Aug 2005 12:04:15 +0000 (12:04 +0000)]
b=7049
- check for aliases in bd-mapping for writes only
alex [Wed, 3 Aug 2005 10:20:08 +0000 (10:20 +0000)]
b=7049
- let's check whether dirty pages/buffers in bd-mapping