Whamcloud - gitweb
yangsheng [Fri, 4 Jul 2008 03:13:09 +0000 (03:13 +0000)]
Branch b1_6
b=16190
i=johann, shadow, zhenyu.xu
Update to RHEL5 kernel-2.6.18-92.1.6.el5.
johann [Thu, 3 Jul 2008 07:31:29 +0000 (07:31 +0000)]
Branch b1_6
b=15950
i=wangdi
i=shadow
The direct IO path doesn't call check_rpcs to submit a new RPC once
one is completed. As a result, some RPCs are stuck in the queue
and are never sent.
Merge brw_interpret() and brw_interpret_oap().
yangsheng [Thu, 3 Jul 2008 04:59:23 +0000 (04:59 +0000)]
Branch b1_6
b=16189
i=johann, zhenyu.xu
Update to RHEL4 kernel-2.6.9-67.0.20.
yangsheng [Thu, 3 Jul 2008 04:10:31 +0000 (04:10 +0000)]
Branch b1_6
b=16041
i=shadow
i=zhenyu.xu
Fixed the wrong name.
adilger [Wed, 2 Jul 2008 21:17:39 +0000 (21:17 +0000)]
Branch b1_6
Add description of setstripe parameters to lfs man page.
b=15754
shadow [Wed, 2 Jul 2008 06:32:09 +0000 (06:32 +0000)]
cleanup usage obd_set_info_async, obd_get_info.
fix KEY_IS macro
Branch b1_6
b=14032
i=johann
i=deen
anserper [Tue, 1 Jul 2008 21:59:36 +0000 (21:59 +0000)]
Branch b1_6
b=15754
i=Johann(johann)
i=ZhiYong(tianzy)
llapi_quotactl manual page
anserper [Tue, 1 Jul 2008 21:49:30 +0000 (21:49 +0000)]
file llapi_quotactl.3 was added on branch b1_6 on 2008-07-01 21:59:36 +0000
kalpak [Tue, 1 Jul 2008 13:48:49 +0000 (13:48 +0000)]
b=15284
i=shadow
libattr package may not be installed on all systems
tianzy [Tue, 1 Jul 2008 13:26:03 +0000 (13:26 +0000)]
Branch b1_6
when setquota is executed, quota limitation on slaves is always reset which leads
to this bug. Now only first setquota and cancelling quota will reset quota
limitation on slaves.
b=16053
i=andrew.perepechko
i=johann
tianzy [Tue, 1 Jul 2008 10:12:47 +0000 (10:12 +0000)]
Branch b1_6
this bug only happens when inode quota limitation is very low(less than 12), so that inode quota unit is 1 at initialization. Now least quota qunit is 2,
instead of 1.
b=15758
i=andrew.perepechko
i=johann
bwzhou [Tue, 1 Jul 2008 08:20:51 +0000 (08:20 +0000)]
Branch b1_6
b=11990
r=johann, bobijam
zeroed param upon every mount point
kalpak [Tue, 1 Jul 2008 05:37:18 +0000 (05:37 +0000)]
b=15284
i=adilger
i=johann
OST crashes and subsequent e2fsck can lead to objects being moved to lost+found directory. Using the "ll_recover_lost_found_objs" tool, these objects can be retrieved and data can be salvaged by using the object ID saved in the fid.
kalpak [Tue, 1 Jul 2008 05:36:47 +0000 (05:36 +0000)]
file ll_recover_lost_found_objs.c was added on branch b1_6 on 2008-07-01 05:37:17 +0000
kalpak [Tue, 1 Jul 2008 04:14:52 +0000 (04:14 +0000)]
b=13128
i=adilger
i=johann
add -gid,-group,-uid-,-user options to lfs find
bobijam [Tue, 1 Jul 2008 02:32:20 +0000 (02:32 +0000)]
Branch b1_6
b=12653
i=green, johann
Description: sanity test 65a fails if stripecount of -1 is set
Details : handle -1 striping on filesystem in ll_dirstripe_verify
adilger [Mon, 30 Jun 2008 20:38:13 +0000 (20:38 +0000)]
Branch b1_6
Add RHEL5 back into ChangeLog for 1.6.5.
wangdi [Mon, 30 Jun 2008 18:59:15 +0000 (18:59 +0000)]
Branch b1_6
Two minor fixes for stride read-ahead.
b=14483
i=adilger
shadow [Mon, 30 Jun 2008 15:33:31 +0000 (15:33 +0000)]
don't panic with sparse OST's indexes.
Branch b1_8
b=16014
i=tappro
i=deen
shadow [Mon, 30 Jun 2008 12:23:57 +0000 (12:23 +0000)]
badly clear PG_Writeback bit in ll_ap_completion can produce false
positive assertion
Branch b1_6
b=14742
i=nikita
i=johan
kalpak [Sun, 29 Jun 2008 10:09:29 +0000 (10:09 +0000)]
b=13103 (patch by adilger)
i=kalpak,girish
upstream e2fsprogs calls uninit_groups feature as uninit_bg. So mkfs.lustre should check for uninit_bg feature also
deen [Sat, 28 Jun 2008 09:26:53 +0000 (09:26 +0000)]
In ldlm_resource_add_lock(), call to ldlm_resource_dump()
starve other threads from the resource lock for a long time in
case of long waiting queue, so change the debug level from
D_OTHER to the less frequently used D_INFO.
b=15953
i=adilger
i=nathan.rutman
adilger [Sat, 28 Jun 2008 05:15:13 +0000 (05:15 +0000)]
Branch b1_6
Ensure all module symbols from ldiskfs and OFED are available.
b=16112
i=brian
i=shadow
wangdi [Fri, 27 Jun 2008 17:28:18 +0000 (17:28 +0000)]
Branch:b1_6
missing stride_start_offset in stride-read-ahead.
b=16172
i=Oleg,Johann
adilger [Fri, 27 Jun 2008 09:47:32 +0000 (09:47 +0000)]
Branch b1_6
Allow both "clear" and "clear\n" to be given to ldlm.namespaces.*.lru_size
Minor whitespace and line wrap cleanup.
b=13868
grev [Fri, 27 Jun 2008 09:34:00 +0000 (09:34 +0000)]
b=5188
add test_68 to ALWAYS_EXCEPT list
bwzhou [Fri, 27 Jun 2008 03:10:10 +0000 (03:10 +0000)]
Branch b1_6
b=15881
r=robert.read
rewrite sanity 129
adilger [Thu, 26 Jun 2008 20:04:45 +0000 (20:04 +0000)]
Branch b1_6
Ignore generated file.
yury [Thu, 26 Jun 2008 11:49:30 +0000 (11:49 +0000)]
b=15863
r=shadow,wangdi
- fixes about missed llcd_put().
anserper [Wed, 25 Jun 2008 21:04:42 +0000 (21:04 +0000)]
Branch b1_6
b=14010
anserper [Wed, 25 Jun 2008 20:59:32 +0000 (20:59 +0000)]
Branch b1_6
b=14010
i=Alexey(shadow)
i=Andreas(adilger)
type fixes
grev [Wed, 25 Jun 2008 19:54:25 +0000 (19:54 +0000)]
b=16165
i=Jian.Yu
localize TYPE
ericm [Wed, 25 Jun 2008 17:59:23 +0000 (17:59 +0000)]
branch: b1_6
drop request with 0 timeout estimation.
b=14071
r=nathan
r=robert
anserper [Wed, 25 Jun 2008 13:38:24 +0000 (13:38 +0000)]
Branch b1_6
b=15754
i=Johann(johann)
i=ZhiYong(tianzy)
lfs enhancements (limits specifiers for setquota)
bwzhou [Wed, 25 Jun 2008 00:29:29 +0000 (00:29 +0000)]
Branch b1_6
b=13285
initialize save_errno
grev [Tue, 24 Jun 2008 20:55:57 +0000 (20:55 +0000)]
b=16153
i=Johann
h2o2ib t-f fn
grev [Tue, 24 Jun 2008 17:21:16 +0000 (17:21 +0000)]
fix typo introduced by grev 2008-02-12 rev 1.35.2.16
grev [Tue, 24 Jun 2008 16:34:06 +0000 (16:34 +0000)]
b=15711
i=Tappro
insanity does not use insanity-local cfg any more
grev [Tue, 24 Jun 2008 16:31:48 +0000 (16:31 +0000)]
b=15711
i=Tappro
t-f and insanity fix to work properly with FAILURE_MODE=HARD
bwzhou [Tue, 24 Jun 2008 16:27:58 +0000 (16:27 +0000)]
Branch b1_6
b=13285
r=adilger, bobijam (cid-1579)
johann, deen (cid-1613)
johann, bobijam (cid-1685)
Coverity bugs
johann [Tue, 24 Jun 2008 08:35:55 +0000 (08:35 +0000)]
Branch b1_6
b=15677
i=zhenyu.xu
Tiny fix when the MDS is also the client node. Don't change the checksum
type on MDS's OSCs.
yangsheng [Tue, 24 Jun 2008 02:57:16 +0000 (02:57 +0000)]
Branch b1_6
b=15865
i=johann, shadow
Update kernel to RHEL5 2.6.18-53.1.21.el5.
Fixed the build failed for IA64 arch.
bobijam [Tue, 24 Jun 2008 01:48:38 +0000 (01:48 +0000)]
Branch b1_6
b=15924
i=green, johann
Description: do not process already freed flock
Details : flock can possibly be freed by another thread before it reaches
to ldlm_flock_completion_ast.
brian [Fri, 20 Jun 2008 16:34:24 +0000 (16:34 +0000)]
b=15316
Forgotten kernel config file in the previous landing.
yangsheng [Fri, 20 Jun 2008 05:43:42 +0000 (05:43 +0000)]
Branch b1_6
b=15593
i=shadow, johann
Force to remove SUID when the do_truncate() be called in 2.6.22 kernel.
tappro [Thu, 19 Jun 2008 06:02:39 +0000 (06:02 +0000)]
b=15936. Unified last_rcvd for MDS/OSS
i: nathan, adilger
adilger [Wed, 18 Jun 2008 22:28:08 +0000 (22:28 +0000)]
Branch b1_6
Add ChangeLog entry.
b=14693
brian [Wed, 18 Jun 2008 16:44:12 +0000 (16:44 +0000)]
b=15870
i=adilger
Forgot to remove the ChangeLog entry when I backed this patch out.
grev [Wed, 18 Jun 2008 13:02:36 +0000 (13:02 +0000)]
re-vert shadow 1.42.10.80 and 1.42.10.84 commits:
move debug code && sync to appropiate place
bobijam [Wed, 18 Jun 2008 01:35:01 +0000 (01:35 +0000)]
Branch b1_6
b=14480
o=green
i=shadow, bobijam
Description: LBUG during stress test
Details : Need properly lock accesses the flock deadlock detection list.
grev [Tue, 17 Jun 2008 17:13:06 +0000 (17:13 +0000)]
b=16090
i=Deen
move export ${facet}_svc from start fn to mount_facet fn
ericm [Tue, 17 Jun 2008 16:42:04 +0000 (16:42 +0000)]
branch: b1_6
don't report service est. for MSG_ERR during recovery.
b=15815
r=rread
r=nathan
shadow [Tue, 17 Jun 2008 12:27:27 +0000 (12:27 +0000)]
revert debug code.
shadow [Tue, 17 Jun 2008 06:48:44 +0000 (06:48 +0000)]
kernel page fault handler can return two special 'pages' in error case, don't
try dereference NOPAGE_SIGBUS and NOPAGE_OMM.
b=15837
i=nikita
i=green
grev [Mon, 16 Jun 2008 13:55:23 +0000 (13:55 +0000)]
b=14384
i=Adilger
remove tdir creation from run_one: the test has to create tdir by
itself if it needs this dir
yangsheng [Mon, 16 Jun 2008 09:41:49 +0000 (09:41 +0000)]
Branch b1_6
b=15592
i=oleg, johann
Correctly handle the FS_RENAME_DOES_D_MOVE flag in Lustre.
bwzhou [Sun, 15 Jun 2008 17:15:52 +0000 (17:15 +0000)]
Branch b1_6
b=14693
r=nathan
Don't return an error for conf_param processing failures
bwzhou [Sun, 15 Jun 2008 14:34:41 +0000 (14:34 +0000)]
Branch b1_6
b=13285
r=adilger, deen
not to fail the import when -EFBIG is returned
anserper [Fri, 13 Jun 2008 23:41:18 +0000 (23:41 +0000)]
branch b1_6
b=14010
i=shadow
i=green
update WRITE to OBD_BRW_WRITE
kalpak [Fri, 13 Jun 2008 10:09:39 +0000 (10:09 +0000)]
b=15932
i=adilger,alex
- if blocks per group is less than blocksize*8, set rest of the bitmap to 1.
- check return of ext2_find_next_le_bit for overflow.
bobijam [Fri, 13 Jun 2008 01:24:26 +0000 (01:24 +0000)]
Branch b1_6
b=14134
i=johann
minor fix handling '/etc/mtab' issue.
brian [Thu, 12 Jun 2008 20:14:42 +0000 (20:14 +0000)]
b=15870
i=adilger
Backing this out as it tries to solve a problem that doesn't really exist
and causes build breakage in doing so.
I have advised the customer that opened this bug as to how they can fix
thier OFED source pool to match the interface provided by the
kernel-ib-devel RPM, which is our reference implementation.
grev [Thu, 12 Jun 2008 09:54:17 +0000 (09:54 +0000)]
fix for
b=15255
i=Adilger
umount $MOUNT2 only if it is set
bobijam [Thu, 12 Jun 2008 02:41:15 +0000 (02:41 +0000)]
Branch b1_6
b=15345
o=johann
i=bobijam, nathan
check --writeconf flag when forcing the index.
grev [Wed, 11 Jun 2008 20:33:00 +0000 (20:33 +0000)]
Cleanup wrong mount_facet message
(introduced by deen rev 1.42.10.74)
grev [Wed, 11 Jun 2008 17:39:06 +0000 (17:39 +0000)]
b=14384
i=Adilger
test_9 test_10a fixes: do not break DIR value
yangsheng [Wed, 11 Jun 2008 09:00:53 +0000 (09:00 +0000)]
Branch b1_6
b=15667
i=johann, andrew
Remove the useless function echo_client_ubrw().
shadow [Wed, 11 Jun 2008 06:46:24 +0000 (06:46 +0000)]
timeout and assert in invalidate import.
b=15716
i=rread
i=johann
komaln [Tue, 10 Jun 2008 13:45:35 +0000 (13:45 +0000)]
b=14471
i=adilger
replace /proc/fs/lustre access with lctl {get,set}_param in test-framework.sh
bwzhou [Tue, 10 Jun 2008 04:26:21 +0000 (04:26 +0000)]
Branch b1_6
b=15436
r=nathan, bobijam
remove failover mgs setting from mkfs_lustre
robert.read [Mon, 9 Jun 2008 22:58:49 +0000 (22:58 +0000)]
Branch b1_6
b=15929
i=grev
Cleanup PATH in tests so absolute paths are used, and
each path is added at most once.
grev [Mon, 9 Jun 2008 20:25:13 +0000 (20:25 +0000)]
b=16019
i=Maxim.Patlasov
get rid of quotation in "options lnet"
anserper [Sun, 8 Jun 2008 16:53:25 +0000 (16:53 +0000)]
*** empty log message ***
anserper [Sun, 8 Jun 2008 16:46:13 +0000 (16:46 +0000)]
Branch b1_6
b=15779
i=Johann
i=ZhiYong
Do not LBUG when different versions of lquota.ko and fsfilt_ldiskfs.ko used
yury [Sat, 7 Jun 2008 08:59:41 +0000 (08:59 +0000)]
b=15226
r=nikita,shadow
- fixes about packing/unpacking pool SLV and Limit while pool and its ns may be in finalization stage;
- cleanups, comments.
robert.read [Thu, 5 Jun 2008 23:03:15 +0000 (23:03 +0000)]
Branch b1_6
b=13537
i=grev
The old test was using the used space rather than free space. This fixes
that and also cuts the amount by half, so we don't completely fill up the
fs. It also caps the size at 1GB, like the previous version.
robert.read [Thu, 5 Jun 2008 22:59:31 +0000 (22:59 +0000)]
Branch b1_6
b=15928
i=grev
Reset the current directory after the each test completes.
walter [Thu, 5 Jun 2008 15:11:29 +0000 (15:11 +0000)]
add racer scripts on b1_6
yangsheng [Wed, 4 Jun 2008 23:18:23 +0000 (23:18 +0000)]
Branch b1_6
b=15741
i=johann, zhenyu.xu
Update to RHEL5 kernel-2.6.18-53.1.19.el5.
deen [Wed, 4 Jun 2008 18:10:44 +0000 (18:10 +0000)]
Fix bug number.
yangsheng [Wed, 4 Jun 2008 15:18:34 +0000 (15:18 +0000)]
Branch b1_6
b=15742
i=johann, zhenyu.xu
Update kernel to RHEL4 kernel-2.6.9-67.0.15.
shadow [Wed, 4 Jun 2008 15:07:16 +0000 (15:07 +0000)]
disable test 129 until it's will be fixed for run with CLIENTONLY="yes"
runs.
yury [Tue, 3 Jun 2008 08:14:35 +0000 (08:14 +0000)]
b=15440
r=shadow,nikita
- fixes missed CFS_INIT_LIST_HEAD(&ns->ns_list_chain);
- cleanups about ns list maintaining;
- cleanups about function names;
- call ldlm_namespace_unregister() before waiting for refc == 0 as ldlm_namespace_unregister() drops ns refc.
komaln [Tue, 3 Jun 2008 06:45:50 +0000 (06:45 +0000)]
b=14471
i=nathan, andreas
To add -N option in lctl get_param which will print only path names.
yangsheng [Fri, 30 May 2008 08:24:03 +0000 (08:24 +0000)]
Branch b1_6
b=15594
i=adilger, shadow
The dd has a change of behaviour in 2.6.22 kernel. It might return
a partial read from read() system-call in some case.
bobijam [Fri, 30 May 2008 02:53:32 +0000 (02:53 +0000)]
Branch b1_6
b=14134
i=nathan, johann
Description: enable MGS and MDT services start separately
Details : add a 'nomgs' option in mount.lustre to enable start a MDT with
a co-located MGS without starting the MGS, which is a complement
to 'nosvc' mount option.
vitaly [Thu, 29 May 2008 22:38:27 +0000 (22:38 +0000)]
Branch b1_6
b=15904
i=shadow
i=wangdi
clean log_commit_master properly at cleanup in llog_commit_thread()
shadow [Thu, 29 May 2008 05:55:02 +0000 (05:55 +0000)]
cleanup in ptlrpc code, related to ppc platform
avoid twice swabing one msg buffer
fix get LOV_GET_INFO on ppc platform.
b=14856
i=nikita
i=adilger
bobijam [Thu, 29 May 2008 02:35:27 +0000 (02:35 +0000)]
Branch b1_6
b=13310
o=eeb
i=joahnn, nikita
The bug is that target_send_reply_msg() calls ptlrpc_error() if 'rc != 0', but
"difficult" replies may not be passed to rpc_error().
vs [Thu, 29 May 2008 00:13:04 +0000 (00:13 +0000)]
b=15346
i=green,shadow,vitaly
skiplists are used to group compatible locks on granted list
that was implemented as tracking first and last lock of each lock group
the patch changes that to using doubly linked lists
grev [Wed, 28 May 2008 20:02:53 +0000 (20:02 +0000)]
b=15876
i=Adilger
skip LFSCK test for remote MDS also
grev [Wed, 28 May 2008 19:28:51 +0000 (19:28 +0000)]
b=14773
i=Adilger
rename subtests to skipping mechanism works properly
ericm [Wed, 28 May 2008 19:21:43 +0000 (19:21 +0000)]
branch: b1_6
a better way to fix the script.
b=13659
brian [Wed, 28 May 2008 19:14:21 +0000 (19:14 +0000)]
b=15908
i=johann
i=zhenyu.xu:
Small message correction.
ericm [Wed, 28 May 2008 18:33:44 +0000 (18:33 +0000)]
branch: b1_6
fix test script: at_start return correct value.
b=13659
r=grev
komaln [Wed, 28 May 2008 05:46:18 +0000 (05:46 +0000)]
b=14471
r=Andreas
to replace the sysctl lustre.* and lnet.* instances with lctl {get,set}_param
girish [Tue, 27 May 2008 17:52:15 +0000 (17:52 +0000)]
Upstream fix for memory leak when verifying checksums in the journal.
ericm [Mon, 26 May 2008 23:27:28 +0000 (23:27 +0000)]
branch: b1_6
do not drop replay according to msg flags, instead we check the
per-export recovery request queue for duplication of transno.
b=15756
r=adilger
r=rread
grev [Mon, 26 May 2008 14:17:31 +0000 (14:17 +0000)]
b=15255
i=Adilger
config for several remote clients; replay-single test_70a, test_70b
yangsheng [Mon, 26 May 2008 13:47:45 +0000 (13:47 +0000)]
Branch b1_6
b=15649
i=oleg, shadow
Enable debug options in vanilla kernel config file.