Whamcloud - gitweb
fs/lustre-release.git
15 years agob=17310
yury [Sat, 8 Nov 2008 13:31:43 +0000 (13:31 +0000)]
b=17310
r=shadow,johann

- make sure that no new inflight rpcs may come after ptlrpcd_deactivate_import() for both
synchronous and asynchronous sending. To do so we make sure that imp_inflight++ is done only when
permission is granted by ptlrpc_import_delay_req() which makes decision should req be sent,
deferred or killed as import is not in the state to send it in observable future. For async
sending, rpc is only counted inflight when its added to sending or delaying list instead of just
adding it to set for processing.

This fixes assert in ptlrpc_invalidate_import() and as number of other issues;

- synchronize imp_inflight and the presence on sending or delaying list for ptlrpc_queue_wait()
case. So that, now it is guaranteed that if im_inflight != 0 we may always find hanging rpc either
in sending or in delaying list;

- make sure that in ptlrcp_queue_wait() we remove rpc from sending or delaying list and dec
inflight only after ptlrpc_unregister_reply() is done. This way we make sure that accounting is
correct. Rpc can't be returned to the pool or counted finished until lnet lets us go with finished
reply unlink;

- check for inflight and rq_list in pinger;

- comments, cleanups;

15 years agorecovery-small.sh: test_55: fix obvious typos.
nikita [Sat, 8 Nov 2008 13:18:30 +0000 (13:18 +0000)]
recovery-small.sh: test_55: fix obvious typos.

15 years agoland clio.
nikita [Fri, 7 Nov 2008 23:54:43 +0000 (23:54 +0000)]
land clio.
b=14166

15 years agob=17511
yury [Fri, 7 Nov 2008 22:37:57 +0000 (22:37 +0000)]
b=17511
r=johann,adilger

  - removes deadlock possibility by disabling rehash in hash_del() operations and moving hash_add()
    out of spin_locks when calling. Hash table has own mechanisms for protecting its structures and it
    also has hash_add_unique() method for using in concurrent run contexts;

    - fixed missed lh_put() in hash_add_unique() which led to extra refs in some cases (extra ref to
    export) and inability to cleanup;

    - fixed __lustre_hash_set_theta() which set @max theta into ->lh_min_theta;

    - in lustre_hash_rehash_size() disable rehash also for the case when new and old hash sizes equal
    in corner cases (max_size or min_size). Before this fix it could be possible to do needless
    rehashes when size is actually did not change but we do this expensive operation;

    - disable rehash in hash_add_unique() if no actual add happened since entry with the same key is
    already found in the table;

    - some cleanups in hash table code;

15 years agob=17477
grev [Fri, 7 Nov 2008 20:35:25 +0000 (20:35 +0000)]
b=17477
i=Adilger
replace cleanup_and_setup_lustre fn by check_and_setup_lustre fn

15 years agoBranch HEAD
zam [Fri, 7 Nov 2008 17:57:56 +0000 (17:57 +0000)]
Branch HEAD
b=17235
i=adigler@sun.com

add -r 'deletepath' option to createmany.c; createmany.c code cleanup.

15 years agob=17477
grev [Fri, 7 Nov 2008 17:15:13 +0000 (17:15 +0000)]
b=17477
i=Adilger
check config if lustre is mounted before acc-sm run

15 years agob=14384
grev [Fri, 7 Nov 2008 16:34:28 +0000 (16:34 +0000)]
b=14384
i=Brian
assert_DIR cleanup

15 years agob=17445
yury [Fri, 7 Nov 2008 15:14:29 +0000 (15:14 +0000)]
b=17445
r=tappro,johann

- proper locking in rq pool freeing time

15 years ago- mark 45 HEAD_EXCEPT as it fails in HEAD (failure is not related to 17310 where...
yury [Fri, 7 Nov 2008 14:45:59 +0000 (14:45 +0000)]
- mark 45 HEAD_EXCEPT as it fails in HEAD (failure is not related to 17310 where this test was added) and new bug for it is filed - 17617.

15 years agoBranch HEAD
liangzhen [Fri, 7 Nov 2008 14:41:11 +0000 (14:41 +0000)]
Branch HEAD

mode of module_param is not correct

15 years agoBranch HEAD
liangzhen [Fri, 7 Nov 2008 14:25:53 +0000 (14:25 +0000)]
Branch HEAD

Support zero-copy receive of Chelsio driver

b=15093
i=Isaac
i=Maxim

15 years agob=17310
yury [Fri, 7 Nov 2008 14:01:03 +0000 (14:01 +0000)]
b=17310
r=johann,shadow

- fixes in ptlrcp to handle possible long reply unlink for HEAD.

15 years agoBranch HEAD
yangsheng [Fri, 7 Nov 2008 09:12:28 +0000 (09:12 +0000)]
Branch HEAD
b=17357

15 years agoBranch HEAD
yangsheng [Fri, 7 Nov 2008 04:39:29 +0000 (04:39 +0000)]
Branch HEAD
b=17357

Back the changes.

15 years agoBranch HEAD
bobijam [Fri, 7 Nov 2008 03:16:55 +0000 (03:16 +0000)]
Branch HEAD
b=16578
o=adilger

A faster way to get long string.

15 years agob=17235
grev [Thu, 6 Nov 2008 20:12:42 +0000 (20:12 +0000)]
b=17235
i=Alexander.Zarochentsev
i=Adilger
COS replay-dual test_21b

15 years agoBranch HEAD
zam [Thu, 6 Nov 2008 18:11:14 +0000 (18:11 +0000)]
Branch HEAD
b=15393
i=alex.zhuravlev@sun.com
i=tappro@sun.com

Commit on sharing. Eliminate inter-client dependencies between
uncommitted transactions by doing transaction commits.
Thereby clients may recovery independently.

15 years agob=16551
grev [Thu, 6 Nov 2008 11:47:15 +0000 (11:47 +0000)]
b=16551
i=Adilger
correct remote_[mds|ost] fn to work correctly on configuration with
several MDS/OSS nodes

15 years agoBranch HEAD
yangsheng [Thu, 6 Nov 2008 05:21:48 +0000 (05:21 +0000)]
Branch HEAD
b=17357
i=johann, yangsheng

Fixed the endian issues for HEAD.
Author: shadow

15 years agoBranch HEAD
huanghua [Thu, 6 Nov 2008 03:25:10 +0000 (03:25 +0000)]
Branch HEAD
b=17083
i=yury.umanets
i=nikita.danilov

Before destroying the whole mdt stack, just wait a little bit for the
obd_zombie_impexp_thread to destroy all the exports.

15 years agob=17505
zhanghc [Thu, 6 Nov 2008 02:24:44 +0000 (02:24 +0000)]
b=17505

removing mfd from 'closing_list' to fix ASSERTION(list_empty(&mfd->mfd_list))
in mdt_mfd_free in mdt_open.c

i=robert.read

15 years agoBranch HEAD
anserper [Thu, 6 Nov 2008 00:38:30 +0000 (00:38 +0000)]
Branch HEAD
b=17371
i=Johann Lombardi
i=Oleg Drokin

fix a possible race between umount  and requeue thread

15 years agob=16438
kalpak [Wed, 5 Nov 2008 10:03:55 +0000 (10:03 +0000)]
b=16438
  i=adilger
  i=girish

  Mounting a filesystem with extents feature will fail on big-endian systems since ext3-based ldiskfs is not supported on big-endian systems. This can be over-riden with "bigendian_extents" mount option.

15 years agoBranch HEAD
tianzy [Wed, 5 Nov 2008 09:20:02 +0000 (09:20 +0000)]
Branch HEAD
fix panic on debug_daemon
b=15878
i=shadow
i=zhenyu.xu

15 years agob=16438
kalpak [Wed, 5 Nov 2008 09:13:07 +0000 (09:13 +0000)]
b=16438
i=adilger
i=girish

Mounting a filesystem with extents feature will fail on big-endian systems since ext3-based ldiskfs is not supported on big-endian systems. This can be over-riden with "bigendian_extents" mount option.

15 years agob=16918
alex [Wed, 5 Nov 2008 07:31:54 +0000 (07:31 +0000)]
b=16918

 - do cache invalidation once read is complete

15 years agob=15715
jxiong [Wed, 5 Nov 2008 02:47:41 +0000 (02:47 +0000)]
b=15715
r=adilger,green

Fixed the race of destroying and enqueuing a ldlm lock at OST side.

15 years agoBranch HEAD
bobijam [Wed, 5 Nov 2008 02:03:57 +0000 (02:03 +0000)]
Branch HEAD
b=16578
i=adilger

Description: ldlm_cancel_pack()) ASSERTION(max >= dlm->lock_count + count)
Details    : If there is no extra space in the request for early cancels,
             ldlm_req_handles_avail() returns 0 instead of a negative value.

16 years agoBranch HEAD
tianzy [Tue, 4 Nov 2008 07:29:14 +0000 (07:29 +0000)]
Branch HEAD
Replace LBUG with RETURN(-EINVAL) to avoid crashing
b=5135
i=adilger
i=johann

16 years ago- test fix from 12512
tappro [Mon, 3 Nov 2008 22:09:43 +0000 (22:09 +0000)]
- test fix from 12512
  b:12512
  i:grev, adilger

16 years ago- fix recovery time growing
tappro [Mon, 3 Nov 2008 13:34:52 +0000 (13:34 +0000)]
- fix recovery time growing
  b:16389
  i:rread,nathan

16 years agob=17397
alex [Sat, 1 Nov 2008 17:43:50 +0000 (17:43 +0000)]
b=17397
i=adilger

 - always flush page left by partial truncate

16 years agob=17122
grev [Fri, 31 Oct 2008 18:30:04 +0000 (18:30 +0000)]
b=17122
i=Nikita
sanity test_100 fix

16 years agob=17540
grev [Fri, 31 Oct 2008 17:21:35 +0000 (17:21 +0000)]
b=17540
i=Nikita
test_53 fix

16 years agoBranch HEAD
adilger [Fri, 31 Oct 2008 17:01:52 +0000 (17:01 +0000)]
Branch HEAD
Remove trailing whitespace

16 years agob=16551
grev [Fri, 31 Oct 2008 16:20:31 +0000 (16:20 +0000)]
b=16551
o=Robert.Read
i=grev
test_27u fix

16 years agofile quota-large-limits-sles10.patch was initially added on branch b1_6.
anserper [Fri, 31 Oct 2008 14:13:43 +0000 (14:13 +0000)]
file quota-large-limits-sles10.patch was initially added on branch b1_6.

16 years agofile quota-large-limits-rhel5.patch was initially added on branch b1_6.
anserper [Fri, 31 Oct 2008 14:13:42 +0000 (14:13 +0000)]
file quota-large-limits-rhel5.patch was initially added on branch b1_6.

16 years agoBranch HEAD
yangsheng [Fri, 31 Oct 2008 13:31:10 +0000 (13:31 +0000)]
Branch HEAD
b=17379

16 years agoBranch HEAD
yangsheng [Fri, 31 Oct 2008 08:12:50 +0000 (08:12 +0000)]
Branch HEAD
b=17379
i=adilger, johann

Test case for recursive symlink.

16 years agoBranch HEAD
yangsheng [Fri, 31 Oct 2008 07:59:50 +0000 (07:59 +0000)]
Branch HEAD
b=17379
i=Brian(LLNL), johann

Set recursive symlink depth to 5 when kernel has 4K stack.

16 years agoupdate buildcvs
pravins [Fri, 31 Oct 2008 07:43:41 +0000 (07:43 +0000)]
update buildcvs

16 years agoBranch HEAD
bobijam [Fri, 31 Oct 2008 01:37:39 +0000 (01:37 +0000)]
Branch HEAD
b=17510
i=robert.read
i=johann

* fix a memory leak introduced by bug 11089.
* some format fix.

16 years agoBranch: HEAD
wangdi [Thu, 30 Oct 2008 21:46:32 +0000 (21:46 +0000)]
Branch: HEAD
Once the unmatched stride IO mode is detected, shrink the stride-ahead window to 0.
if it does hit cache miss, and read-pattern is still stride-io mode,
does not reset the stride window, but also does not increase the stride
window length in this case.
b=17197
i=Nikita
i=Andreas

16 years agob=17532
grev [Thu, 30 Oct 2008 18:37:15 +0000 (18:37 +0000)]
b=17532
i=Yury.Umanets
local cfg CMD fix for several mds nodes configuration

16 years agoBranch HEAD
bobijam [Thu, 30 Oct 2008 02:18:07 +0000 (02:18 +0000)]
Branch HEAD
b=16887
i=pravin.shelar
i=adilger

Address LBUG, ASSERTION(client_stat->nid_exp_ref_count == 0) failed:count -1
* add client stat on obd_nid_stat after client stat is ready.
* properly decrease exp_nid_stats' nid_exp_ref_count in lprocfs_exp_cleanup().

16 years agoRemove "CVS:" from start of lines that should be in commit message
adilger [Wed, 29 Oct 2008 20:07:34 +0000 (20:07 +0000)]
Remove "CVS:" from start of lines that should be in commit message
Fix lfs find --maxdepth wording.

16 years agobranch: HEAD
ericm [Wed, 29 Oct 2008 19:34:24 +0000 (19:34 +0000)]
branch: HEAD
AT: fix reply offset calculate and check.
b=17404
r=h.huang
r=nathan

16 years agoBranch HEAD
robert.read [Tue, 28 Oct 2008 23:17:00 +0000 (23:17 +0000)]
Branch HEAD
b=17491
i=nathan
i=rread

Quick fix patch from behlendorf1@llnl.gov.

16 years agob=17187
kalpak [Tue, 28 Oct 2008 18:19:01 +0000 (18:19 +0000)]
b=17187
i=nathan
i=manoj

Add "lfs path2fid" to get fid from path

16 years agob=16680
kalpak [Tue, 28 Oct 2008 17:59:09 +0000 (17:59 +0000)]
b=16680
i=adilger, kalpak (o=bzzz)

Detect on-disk corruption of block bitmap and better checking of preallocated blocks.

16 years agob=17477
grev [Tue, 28 Oct 2008 16:05:54 +0000 (16:05 +0000)]
b=17477
i=Adilger
i=Tappro
init facet vars for mounted lustre

16 years agoBranch HEAD
huanghua [Tue, 28 Oct 2008 14:06:30 +0000 (14:06 +0000)]
Branch HEAD
b=17192
i=robert.read
i=adilger

clear the proc stats counter. This value might be used later again.

16 years agoBranch HEAD
bobijam [Tue, 28 Oct 2008 05:34:14 +0000 (05:34 +0000)]
Branch HEAD
b=17093
o=Btian Behlendorf (behlendorf1@llnl.gov) for mgs part
o=E. Gryaznova (grev) for test framework
i=nathan.rutman
i=adilger

Do writeconf only explicitly required.

16 years agolockdep: add lockdep_{on,off}() functions.
nikita [Mon, 27 Oct 2008 12:15:58 +0000 (12:15 +0000)]
lockdep: add lockdep_{on,off}() functions.

16 years agoBranch HEAD
johann [Mon, 27 Oct 2008 12:08:33 +0000 (12:08 +0000)]
Branch HEAD
b=17385
i=green
i=shadow

grab lock reference when the lock is added to the waiting or expired list.

16 years agoBranch HEAD
zhanghc [Mon, 27 Oct 2008 06:04:19 +0000 (06:04 +0000)]
Branch HEAD

handle 'Unexpected: can't find mdc_open_data,
but the close succeeded with replayabel imp.
Please tell http://bugzilla.lustre.org/"
printed by mdc_close in mdc_request.c

b=17089
i=johann

16 years agoBranch HEAD
bobijam [Mon, 27 Oct 2008 02:15:02 +0000 (02:15 +0000)]
Branch HEAD
b=11089
i=nathan.rutman
i=adilger

per-nid client statistics for MDT.

16 years agoBranch HEAD
fanyong [Sat, 25 Oct 2008 04:37:55 +0000 (04:37 +0000)]
Branch HEAD
b=17193
i=eric.mei
i=minh.diep

1) set root permission mode as 0755 before test.
2) scripts cleanup.

16 years agoBranch HEAD
adilger [Fri, 24 Oct 2008 20:52:32 +0000 (20:52 +0000)]
Branch HEAD
Return a protocol error from ost_punch() like all other handler methods
if there is a request format error, instead of -EINVAL.

16 years agoBranch HEAD
adilger [Fri, 24 Oct 2008 20:47:38 +0000 (20:47 +0000)]
Branch HEAD
Rename "pages" pointer to "npages", because it otherwise looks like an
array of pointers to pages instead of a pass-by-reference number of pages.
b=12682

16 years agoBranch HEAD
adilger [Fri, 24 Oct 2008 20:40:56 +0000 (20:40 +0000)]
Branch HEAD
Fix whitespace, line wrapping.

16 years agob=13297
grev [Fri, 24 Oct 2008 20:10:57 +0000 (20:10 +0000)]
b=13297
add test_27u to ALWAYS_EXCEPT list

16 years agob=16551 (att 19784)
grev [Fri, 24 Oct 2008 19:46:25 +0000 (19:46 +0000)]
b=16551 (att 19784)
o=Adilger
i=grev
skip replay/recovery tests if remote MDS/OSS nodsh

b=16551 (att 19835)
i=Nathan
do skip_rem[mds|ost] check only if test suit is run; fail acc-sm if
tests suits were skipped due to nodsh

b=17326
i=Alexey.Lyashkov
remove now-useless remount/recofig for liblustre;
always add accept=all to lnet module

16 years agob=17323
yury [Fri, 24 Oct 2008 05:05:11 +0000 (05:05 +0000)]
b=17323

- fixed using "mds" in test 59b

16 years agoKill extra argument for llog_connect, and don't access to ld_tgt_count
shadow [Fri, 24 Oct 2008 05:03:41 +0000 (05:03 +0000)]
Kill extra argument for llog_connect, and don't access to ld_tgt_count
without protection.

Branch HEAD
b=16693
i=umka
i=tappro

16 years agoupdated for next bi-weekly build of 2.0.0
stinson1947 [Thu, 23 Oct 2008 23:53:36 +0000 (23:53 +0000)]
updated for next bi-weekly build of 2.0.0

16 years agofile large-scale.sh was initially added on branch b1_8_gate.
grev [Thu, 23 Oct 2008 19:33:30 +0000 (19:33 +0000)]
file large-scale.sh was initially added on branch b1_8_gate.

16 years agob=17323
yury [Thu, 23 Oct 2008 18:10:26 +0000 (18:10 +0000)]
b=17323
r=shadow

- small to test from Mike

16 years agoInitialize i_file_acl for EXT3_BAD_INO (Johann)
girish [Thu, 23 Oct 2008 16:59:43 +0000 (16:59 +0000)]
Initialize i_file_acl for EXT3_BAD_INO (Johann)
i=adilger
i=kalpak
b=17414

16 years agob=17447
yury [Thu, 23 Oct 2008 14:33:01 +0000 (14:33 +0000)]
b=17447
r=deen,adilger

- fixes memory leaks;
- cleanups and more accurate error handling.

16 years agoRemove files imported by Cariddi (osr) carelessly
mattwu [Thu, 23 Oct 2008 13:33:28 +0000 (13:33 +0000)]
Remove files imported by Cariddi (osr) carelessly

16 years agob=12800
kalpak [Thu, 23 Oct 2008 10:02:19 +0000 (10:02 +0000)]
b=12800
o=alex.zhuravlev
i=kalpak
i=adilger

Add support for tunable preallocation window and new tunables for large/small requests

16 years agoBranch HEAD
adilger [Thu, 23 Oct 2008 04:13:42 +0000 (04:13 +0000)]
Branch HEAD
Remove trailing whitespace.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 23:39:19 +0000 (23:39 +0000)]
Branch HEAD
Make releasepage check failsafe for newer kernels, per Robert's suggestion.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:33:28 +0000 (21:33 +0000)]
Branch HEAD
Improve error messages.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:32:09 +0000 (21:32 +0000)]
Branch HEAD
Start modifying test 32a, 32b (currently disabled) to handle 1.8->2.0
filesystem upgrade test.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:26:57 +0000 (21:26 +0000)]
Branch HEAD
Fix whitespace.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:25:23 +0000 (21:25 +0000)]
Branch HEAD
Move HAVE_PAGE_CONSTANT checks out-of-line via compat macros.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:19:51 +0000 (21:19 +0000)]
Branch HEAD
Remove unnecessary cast of void pointers.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:17:28 +0000 (21:17 +0000)]
Branch HEAD
copy_{to,from}_user() do not return an error code, but rather the number
of uncopied bytes (0 if all bytes were copied).  Storing this return value
into "rc" is misleading because it then seems this should be returned to
the caller of the function.

Code was audited to remote storing of the return value into "rc" and
several incorrect uses were found.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:06:44 +0000 (21:06 +0000)]
Branch HEAD
Don't print two console messages where one would do.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 21:04:39 +0000 (21:04 +0000)]
Branch HEAD
The infiniband code includes its own lockdep compatibility code and this
#defines lockdep_set_class but doesn't include mutex_lock_nested() or
down_write_nested(), causing a compiler error in obdclass/llog_cat.c.

mutex_{un,}lock_nested() and down_{read,write}_nested() are functions
under CONFIG_DEBUG_LOCK_ALLOC, but #defined to regular locks without
CONFIG_DEBUG_LOCK_ALLOC so just checking #ifndef isn't sufficient.
b=16450

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 20:56:18 +0000 (20:56 +0000)]
Branch HEAD
Fix compile warning for 2.6.9 kernels that define gfp_t but don't use
it in the ->releasepage() prototype.
Make the AC_MSG_RESULT() output consistent.

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 20:22:58 +0000 (20:22 +0000)]
Branch HEAD
Limit bio_alloc() size to the maximum possible value, or it will always fail.
b=9945
i=johann

16 years agob=15711
grev [Wed, 22 Oct 2008 19:26:12 +0000 (19:26 +0000)]
b=15711
i=Johann
recovery-small exception for FAILURE_MODE=HARD and mixed ost devices

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 18:58:20 +0000 (18:58 +0000)]
Branch HEAD
Fix debug message.

16 years agob=17442
grev [Wed, 22 Oct 2008 18:57:06 +0000 (18:57 +0000)]
b=17442
i=Nikita
do_nodes fix for case when list contains a single node $HOSTNAME

16 years agoBranch HEAD
adilger [Wed, 22 Oct 2008 18:55:40 +0000 (18:55 +0000)]
Branch HEAD
Fix ChangeLog comments

16 years agoBranch: HEAD
wangdi [Wed, 22 Oct 2008 18:32:57 +0000 (18:32 +0000)]
Branch: HEAD
rq_xid should be "LPU64", instead of "LPD64"

16 years agoSetup changed
cariddi [Wed, 22 Oct 2008 16:46:40 +0000 (16:46 +0000)]
Setup changed

16 years agob=17443
grev [Wed, 22 Oct 2008 16:39:53 +0000 (16:39 +0000)]
b=17443
i=Nikita
fix calc_osc_kbytes

16 years agob=17323
yury [Wed, 22 Oct 2008 14:25:38 +0000 (14:25 +0000)]
b=17323
r=johann,adilger

- fixes resent rpcs for those sent by set and also fixes log_cancel resent handling;
- cleanups.

16 years agoBranch HEAD
yangsheng [Wed, 22 Oct 2008 06:12:46 +0000 (06:12 +0000)]
Branch HEAD
b=16437
i=cliff.white, brian

Enable the '-m64' flag for powerpc64 patchless build.

16 years agoBranch HEAD
robert.read [Tue, 21 Oct 2008 22:30:53 +0000 (22:30 +0000)]
Branch HEAD
b=1819
i=adilger
i=nathan

Add test for new proc file.

16 years agoBranch HEAD
robert.read [Tue, 21 Oct 2008 21:40:41 +0000 (21:40 +0000)]
Branch HEAD
b=1819
i=adilger
i=nathan

Add an import file to the osc, mdc, and mgc proc dir.

16 years agob=17353
yury [Tue, 21 Oct 2008 13:53:47 +0000 (13:53 +0000)]
b=17353
r=shadow,wangdi

- fixes wrong work with llog in catalog that led to removing alive object on ost in recovery time;
- cleanups.

16 years agofix lu_device_is_md() assertions.
nikita [Tue, 21 Oct 2008 10:58:13 +0000 (10:58 +0000)]
fix lu_device_is_md() assertions.

16 years agoBranch HEAD
adilger [Tue, 21 Oct 2008 07:06:23 +0000 (07:06 +0000)]
Branch HEAD
Temporary build fix.
b=17444
i=ericm (original fix)