Whamcloud - gitweb
fs/lustre-release.git
15 years agoBranch b_release_1_8_1
johann [Fri, 22 May 2009 20:40:41 +0000 (20:40 +0000)]
Branch b_release_1_8_1
b=16893
i=johann (patch from girish)
i=adilger

lustre changes (mainly fsfilt) to support ext4 (in SLES11 & RHEL5).

15 years agob=19612
anserper [Fri, 22 May 2009 18:52:00 +0000 (18:52 +0000)]
b=19612
i=Johann Lombardi
i=ZhiYong Tian

additional parameter checking for lfs quota and lustre ioctls

15 years agob=19625
girish [Fri, 22 May 2009 17:11:37 +0000 (17:11 +0000)]
b=19625
i=johann

ext4 patches for SLES11 ldiskfs support

15 years agob=19625
girish [Fri, 22 May 2009 16:46:24 +0000 (16:46 +0000)]
b=19625
i=johann
i=adilger

JBD2 kernel patch needed for ext4 support for SLES11

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 22 May 2009 16:33:47 +0000 (16:33 +0000)]
Branch b_release_1_8_1
b=18668

i=brian, johann.

lbuild changes for SLES11(provide the Module.symvers).

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 22 May 2009 15:47:59 +0000 (15:47 +0000)]
Branch b_release_1_8_1
b=18668

Get rid of the fuzz.

15 years agob=19457
brian [Fri, 22 May 2009 11:29:13 +0000 (11:29 +0000)]
b=19457
i=sheng.yang
i=yibin.wang

Disable a kernel option that is enabling the in-kernel ISCSI stack.
We provide ISCSI with the OFED kernel-ib RPM.

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 22 May 2009 10:51:58 +0000 (10:51 +0000)]
Branch b_release_1_8_1
b=18503

i=adilger, girish

Changes for ldiskfs based on ext4.

15 years agoBranch b_release_1_8_1
tianzy [Fri, 22 May 2009 08:36:25 +0000 (08:36 +0000)]
Branch b_release_1_8_1
fix "rhel5 i686 patchless build failure"
b=19590
i=johann
i=brian

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 22 May 2009 05:16:37 +0000 (05:16 +0000)]
Branch b_release_1_8_1
b=18668

i=shadow, johann

SLES11 kernel patches.

15 years agob=19618
grev [Thu, 21 May 2009 22:25:53 +0000 (22:25 +0000)]
b=19618
i=Tom.Wang
test_101c fix

15 years agob=16312
brian [Thu, 21 May 2009 19:00:06 +0000 (19:00 +0000)]
b=16312
i=wangyb
i=jack

This makes the "old school" kernel RPM match the requirements of the
current lustre-modules RPM, which itself has been previous updated to
match the vendor's kernel RPM Provides:.

15 years agoBranch b_release_1_8_1
liangzhen [Thu, 21 May 2009 09:44:20 +0000 (09:44 +0000)]
Branch b_release_1_8_1

b=19520
i=isaac
- handle new CM events in OFED 1.4

15 years agoBranch b_release_1_8_1
bobijam [Thu, 21 May 2009 02:01:17 +0000 (02:01 +0000)]
Branch b_release_1_8_1
b=19380
i=johann
i=sheng.yang

* limit recursive symlink depth to 7 on 8k stack machine
* fix sanity test_140() accordingly.
* revert local_nid_dist_zero=0 patch

15 years agob=19481
anserper [Wed, 20 May 2009 23:59:37 +0000 (23:59 +0000)]
b=19481
i=Johann Lombardi
i=Gryaznova Elena

fix for the quota_save_version function to allow it to be called before quota files are created

15 years agob=19523
grev [Wed, 20 May 2009 17:03:40 +0000 (17:03 +0000)]
b=19523
o=Robert.Read
i=grev
test_100: fix both calls to error

15 years ago- remove obsoleted message
tappro [Wed, 20 May 2009 13:28:43 +0000 (13:28 +0000)]
- remove obsoleted message
  b:3633
  i:vitaly,adilger

15 years agoBranch b_release_1_8_1
bobijam [Wed, 20 May 2009 08:48:30 +0000 (08:48 +0000)]
Branch b_release_1_8_1
b=16417

Indent reformating.

15 years agoBranch b_release_1_8_1
bobijam [Wed, 20 May 2009 03:15:57 +0000 (03:15 +0000)]
Branch b_release_1_8_1
b=16417
i=grev
i=alexey.lyashkov (shadow)

Revise sanityN.sh test_36()
- need sleep some time before getting 'after' value from 'lfs df', because
  if 'multiop & kill' happens too fast, 'lfs df' sometimes only get old df
  value from cache w/o reissuing statfs RPC request.

15 years agoBranch b_release_1_8_1
bobijam [Wed, 20 May 2009 02:07:31 +0000 (02:07 +0000)]
Branch b_release_1_8_1
b=19404
i=alexey.lyashkov (shadow)
i=oleg.drokin (green)

lov_obd_unregister_page_removal_cb() needs call osc_obd_unregister_page_removal_cb
before clearing lov's lov_page_removal_cb.

15 years agoBranch b_release_1_8_1
zam [Tue, 19 May 2009 13:28:55 +0000 (13:28 +0000)]
Branch b_release_1_8_1
b=19195
i=alex.zhuravlev

remove unused fields from ost_thread_cache_local_cache.

15 years agob=19523
grev [Tue, 19 May 2009 13:13:10 +0000 (13:13 +0000)]
b=19523
i=Vladimir.Saveliev
test_100: exit 1 from subshell

15 years agoBranch b_release_1_8_1
johann [Tue, 19 May 2009 12:59:31 +0000 (12:59 +0000)]
Branch b_release_1_8_1

fix changelog.

15 years ago*** empty log message ***
tianzy [Tue, 19 May 2009 12:36:59 +0000 (12:36 +0000)]
*** empty log message ***

15 years agoadd an entry on Changelog for bug19495
tianzy [Tue, 19 May 2009 11:15:50 +0000 (11:15 +0000)]
add an entry on Changelog for bug19495

15 years agoBranch b_release_1_8_1
tianzy [Tue, 19 May 2009 10:23:42 +0000 (10:23 +0000)]
Branch b_release_1_8_1
This patch fixes:
1. I checked quota_check_common(). This function will check quota
for user and group, but only send one return via "pending". In
most cases, the pendings should be same. But that is not always
the case.
2. if quotaoff runs between lquota_chkquota() and
lquota_pending_commit(), the same thing will happen too. That is
why it comes:
-        if (!ll_sb_any_quota_active(qctxt->lqc_sb))
-                RETURN(0);
3. change some format of quota log, based upon
https://bugzilla.lustre.org/show_bug.cgi?id=18574#c65
b=19495
i=johann
i=panda

15 years agoBranch b_release_1_8_1
tianzy [Tue, 19 May 2009 07:46:41 +0000 (07:46 +0000)]
Branch b_release_1_8_1
fix the problem of "if fsfilt_add_journal_cb() will fail,
export ref will be took twice."
b=19321
i=tappro
i=tianzy

15 years agoBranch b_release_1_8_1
yangsheng [Tue, 19 May 2009 04:16:06 +0000 (04:16 +0000)]
Branch b_release_1_8_1
b=18503

i=adilger, girish

Build system changes for ldiskfs based on ext4.

15 years agocorrectly wait until mds<>ost link will be established.
shadow [Mon, 18 May 2009 11:40:23 +0000 (11:40 +0000)]
correctly wait until mds<>ost link will be established.

Branch b_release_1_8_1
b=19280
i=rread

15 years agoBranch b_release_1_8_1
bobijam [Mon, 18 May 2009 08:26:01 +0000 (08:26 +0000)]
Branch b_release_1_8_1
b=19478
i=adilger
i=sheng.yang

Fix last commit's overkill.

15 years agob=19451
grev [Fri, 15 May 2009 20:17:00 +0000 (20:17 +0000)]
b=19451
i=Brian
IOR load for recovery scale tests

15 years agofile run_IOR.sh was added on branch b_release_1_8_1 on 2009-05-15 20:17:00 +0000
grev [Fri, 15 May 2009 20:10:37 +0000 (20:10 +0000)]
file run_IOR.sh was added on branch b_release_1_8_1 on 2009-05-15 20:17:00 +0000

15 years agoUpdated version for weekly build of 1.8.1.
stinson1947 [Fri, 15 May 2009 19:15:26 +0000 (19:15 +0000)]
Updated version for weekly build of 1.8.1.

15 years agob=19380
grev [Fri, 15 May 2009 13:21:54 +0000 (13:21 +0000)]
b=19380
i=Johann
i=He.Huang
add local_nid_dist_zero=0 to LNETOPTS

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 15 May 2009 12:27:35 +0000 (12:27 +0000)]
Branch b_release_1_8_1
b=18668

i=johann, brian

SLES11 patchless client support.

15 years agoBranch b_release_1_8_1
yangsheng [Thu, 14 May 2009 15:15:26 +0000 (15:15 +0000)]
Branch b_release_1_8_1
b=18668

Fixed the autoconf warning message.

Author: adilger

15 years agoBranch b_release_1_8_1
yangsheng [Thu, 14 May 2009 14:32:13 +0000 (14:32 +0000)]
Branch b_release_1_8_1
b=18668

i=adilger, johann

Remove AS_TR_CPP marco to avoid autoconf compatibility issue.

15 years agoBranch b_release_1_8_1
yangsheng [Thu, 14 May 2009 09:58:11 +0000 (09:58 +0000)]
Branch b_release_1_8_1
b=18668

i=panda, johann

Quota patch for SLES11 support.

15 years agoBranch b_release_1_8_1
tianzy [Thu, 14 May 2009 07:15:22 +0000 (07:15 +0000)]
Branch b_release_1_8_1
fix the problem when mdt.quota_type or ost.quota_type is set and there
is not any quota set before
b=19442
i=johann
i=panda

15 years agoi=liang,b=18450:
isaac [Wed, 13 May 2009 16:28:16 +0000 (16:28 +0000)]
i=liang,b=18450:
- added more debug info for connection management.

15 years agob=19163
brian [Wed, 13 May 2009 11:16:32 +0000 (11:16 +0000)]
b=19163
i=wangyb
i=rread

Because we rename our repackaging of the vendor kernel to include "lustre"
in the name, this changes the packages implicit Provides: attribute.  So we
make our repackaged RPMs provide the %name-%version-%release explictly so
that our kernel RPMs will satisfy the vendor's other RPMs' Requires:
attributes.

Introduce the "$BUILD_GEN" variable.  This allows the build software
engineers to force the reuse hash to be a new unique value when they update
the build software in a way that will change the resulting kernel RPMs.

15 years agoBranch b_release_1_8_0
bobijam [Wed, 13 May 2009 09:47:58 +0000 (09:47 +0000)]
Branch b_release_1_8_0
b=19478
i=johann
i=sheng.yang

Port back patch from bz12836 to handle slow run of sanity test_65l.

15 years agob=18800
zhanghc [Wed, 13 May 2009 09:01:01 +0000 (09:01 +0000)]
b=18800

add flag during create llog_ctxt to fix
a bug caused by using uninitialized llog_ctxt

i=johann
i=wangdi

15 years agoBranch b_release_1_8_1
zam [Wed, 13 May 2009 06:51:17 +0000 (06:51 +0000)]
Branch b_release_1_8_1
b=19195
i=johann
i=tappro
i=oleg.drokin

Temporarily attach ost_thread_cache_local object to non ost_io thread if an
i/o request comes to that thread during ost recovery.

15 years agoBranch b_release_1_8_1
yangsheng [Wed, 13 May 2009 06:48:18 +0000 (06:48 +0000)]
Branch b_release_1_8_1
b=18668

Revert the change broken autoconf 2.59.

15 years agob_release_1_8_1
yangsheng [Wed, 13 May 2009 04:57:53 +0000 (04:57 +0000)]
b_release_1_8_1
b=18668

i=johann, shadow

Some fixes and cleanup for 2.6.27 support.

15 years agob=17671
brian [Tue, 12 May 2009 19:29:34 +0000 (19:29 +0000)]
b=17671

Update the lnet/ChangeLog with the supported versions of OFED.

15 years agob=17605
brian [Tue, 12 May 2009 18:58:32 +0000 (18:58 +0000)]
b=17605

Somehow a couple of the changes escaped assimilation.

15 years agoBranch b_release_1_8_1
liangzhen [Tue, 12 May 2009 15:56:37 +0000 (15:56 +0000)]
Branch b_release_1_8_1

Cleanup of o2iblnd protocol V2:
. check whether ofed can support iWARP
. enable map-on-demand for (nfrags >= kib_map_on_demand)
  instead of (nfrags > kib_map_on_demand)

b=19327
i=isaac

15 years agob=17605
brian [Tue, 12 May 2009 15:34:57 +0000 (15:34 +0000)]
b=17605
i=rread
i=grev

Use the mpicc wrapper for building MPI programs rather than trying to
discover all the bits and pieces of the installed MPI library.

Due to the way the autotools work, this requires putting the sources
into their own subdir, so that the CC command can be overridden.

Fix the pointers to in-tree MPI programs in test-framework.sh.

15 years agob=18192
anserper [Tue, 12 May 2009 00:49:38 +0000 (00:49 +0000)]
b=18192
i=Alexey Lyashkov
i=Girish Shilamkar

update to unified format

15 years agoi=isaac,b=18654:
isaac [Mon, 11 May 2009 23:23:09 +0000 (23:23 +0000)]
i=isaac,b=18654:
- MXLND updates from upstream: eliminate hosts file, use arp for peer nic_id resolution

15 years agob=19115
anserper [Mon, 11 May 2009 20:41:11 +0000 (20:41 +0000)]
b=19115
i=Andreas Dilger
i=Nathan Rutman

additional error-checking in lov_setstripe

15 years agofile write_disjoint.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57...
brian [Mon, 11 May 2009 20:05:07 +0000 (20:05 +0000)]
file write_disjoint.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57 +0000

15 years agofile write_append_truncate.c was added on branch b_release_1_8_1 on 2009-05-12 15...
brian [Mon, 11 May 2009 20:05:06 +0000 (20:05 +0000)]
file write_append_truncate.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57 +0000

15 years agofile parallel_grouplock.c was added on branch b_release_1_8_1 on 2009-05-12 15:34...
brian [Mon, 11 May 2009 20:05:05 +0000 (20:05 +0000)]
file parallel_grouplock.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57 +0000

15 years agofile mdsrate.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57 +0000
brian [Mon, 11 May 2009 20:05:04 +0000 (20:05 +0000)]
file mdsrate.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:57 +0000

15 years agofile lp_utils.h was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000
brian [Mon, 11 May 2009 20:05:03 +0000 (20:05 +0000)]
file lp_utils.h was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000

15 years agofile lp_utils.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000
brian [Mon, 11 May 2009 20:05:02 +0000 (20:05 +0000)]
file lp_utils.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000

15 years agofile createmany-mpi.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:56...
brian [Mon, 11 May 2009 20:05:01 +0000 (20:05 +0000)]
file createmany-mpi.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000

15 years agofile Makefile.am was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000
brian [Mon, 11 May 2009 20:05:00 +0000 (20:05 +0000)]
file Makefile.am was added on branch b_release_1_8_1 on 2009-05-12 15:34:56 +0000

15 years agofile test_lock_cancel.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:48...
brian [Mon, 11 May 2009 20:04:52 +0000 (20:04 +0000)]
file test_lock_cancel.c was added on branch b_release_1_8_1 on 2009-05-12 15:34:48 +0000

15 years agofile Makefile.am was added on branch b_release_1_8_1 on 2009-05-12 15:34:48 +0000
brian [Mon, 11 May 2009 20:04:51 +0000 (20:04 +0000)]
file Makefile.am was added on branch b_release_1_8_1 on 2009-05-12 15:34:48 +0000

15 years agoBranch b_release_1_8_1
yangsheng [Mon, 11 May 2009 03:55:52 +0000 (03:55 +0000)]
Branch b_release_1_8_1
b=18668

i=adilger, johann

Remove the 8kstack patch.

15 years agoBranch b_release_1_8_1
yangsheng [Mon, 11 May 2009 03:04:27 +0000 (03:04 +0000)]
Branch b_release_1_8_1
b=11505

i=brian(LLNL), shadow

Check whether print_trace_address() with "reliable" argument.

15 years agoi=wangdi,b=19448:
isaac [Fri, 8 May 2009 17:03:35 +0000 (17:03 +0000)]
i=wangdi,b=19448:
- fix liblustre_init_random file handle leak.

15 years agoBranch b_release_1_8_1
yangsheng [Fri, 8 May 2009 15:26:24 +0000 (15:26 +0000)]
Branch b_release_1_8_1
b=19212

i=bobijam, brian

Get rid of the fuzz chunk for as vendor's convention.

15 years agob=19026
grev [Fri, 8 May 2009 11:05:40 +0000 (11:05 +0000)]
b=19026
i=Brian
recovery-double-scale error message cleanup

15 years agob=18921
grev [Fri, 8 May 2009 08:20:18 +0000 (08:20 +0000)]
b=18921
i=Robert.Read
rename type2 tests to parallel-scale

16 years agoi=brian,b=15870:
isaac [Thu, 7 May 2009 19:26:03 +0000 (19:26 +0000)]
i=brian,b=15870:
- added missing quotes.

16 years agoBranch b_release_1_8_1
bobijam [Thu, 7 May 2009 03:17:44 +0000 (03:17 +0000)]
Branch b_release_1_8_1
b=18896
o=alexey.lyashkov (shadow)
i=tappro
i=alexander.zarochentsev

16 years agoBranch b_release_1_8_1
johann [Wed, 6 May 2009 13:44:10 +0000 (13:44 +0000)]
Branch b_release_1_8_1
b=18946
i=shadow
i=johann (patch from tappro)

don't cleanup namespace during lock replay, that may lead to deadlocks.

16 years agoBranch b_release_1_8_1
bobijam [Wed, 6 May 2009 02:31:02 +0000 (02:31 +0000)]
Branch b_release_1_8_1
b=12069
i=adilger
i=tom.wang (wangdi)

Enable adjusting grant_shrink_interval and grant target value via /proc.

16 years agoBranch b_release_1_8_1
johann [Tue, 5 May 2009 22:15:33 +0000 (22:15 +0000)]
Branch b_release_1_8_1
b=19128
i=tappro
i=adilger

disable async journal commit on bulk write feature because of recovery issues.
remove SLES9 & RHEL4 from which_patch.

16 years ago�� b=18948
anserper [Tue, 5 May 2009 21:08:28 +0000 (21:08 +0000)]
�� b=18948
�� o=Brian Behlendorf
�� i=Nathan Rutman
�� i=Robert Read
��
�� Recovery console messages cleanup

16 years agoBranch b_release_1_8_1
johann [Tue, 5 May 2009 20:15:35 +0000 (20:15 +0000)]
Branch b_release_1_8_1
b=18674
i=shadow
i=bobijam

print the correct number of active rpcs.

16 years agoBranch b_release_1_8_1
johann [Tue, 5 May 2009 20:14:44 +0000 (20:14 +0000)]
Branch b_release_1_8_1
b=18674
i=adilger
i=bobijam

print op code in ptlrpc_expire_one_request()

16 years agoBranch b_release_1_8_1
johann [Tue, 5 May 2009 20:12:54 +0000 (20:12 +0000)]
Branch b_release_1_8_1
b=18206
i=green
i=bzzz

Disable per-stripe locking for O_DIRECT.

16 years agocleaned up unneeded template line.
stinson1947 [Tue, 5 May 2009 18:58:21 +0000 (18:58 +0000)]
cleaned up unneeded template line.

16 years agocleaned up unneeded template line.
stinson1947 [Tue, 5 May 2009 18:52:52 +0000 (18:52 +0000)]
cleaned up unneeded template line.

16 years agoUpdated service tags version for 1.8.1.
stinson1947 [Tue, 5 May 2009 18:39:18 +0000 (18:39 +0000)]
Updated service tags version for 1.8.1.

16 years agoThis commit was manufactured by cvs2svn to create branch 'b_release_1_8_1'.
cvs2svn [Tue, 5 May 2009 13:44:41 +0000 (13:44 +0000)]
This commit was manufactured by cvs2svn to create branch 'b_release_1_8_1'.

16 years agob=16818
zhanghc [Tue, 5 May 2009 13:44:40 +0000 (13:44 +0000)]
b=16818

fix a bug in previous patch for the bug

i=nathan.rutman
i=robert.read

16 years agoBranch b1_8
tianzy [Tue, 5 May 2009 11:03:10 +0000 (11:03 +0000)]
Branch b1_8
use lqs to judge which uid/gid are set quota limitaton and
which uid/gid are not, and treat them differently.
b=18574
i=johann
i=panda

16 years agoBranch b1_8
tianzy [Tue, 5 May 2009 10:57:38 +0000 (10:57 +0000)]
Branch b1_8
part I
1. mainly fix the lqs_key of lustre_qunit_size.
2. clean quota_compute_lqs().
3. only supply quota_search_lqs() to outside and make quota_create_lqs() internal.
b=18616
i=johann
i=panda

16 years agoBranch b1_8
liuy [Tue, 5 May 2009 08:31:52 +0000 (08:31 +0000)]
Branch b1_8
 some improvements:
  -use fd->hints structure instead of MPI Info routines
  -change hints name as romio requires
  -check lustre/lustre_user.h header file in configure instead of giving
   the lustre structs/constants
  -add new MPE logging
  -revert the hint settings in ad_lustre_open.c
  -remove the two confusing hints "contig_data" and "samesize"
  -fix avail_cb_node calculation in ad_lustre_aggregate.c

16 years agoBranch b1_8
bobijam [Tue, 5 May 2009 02:12:07 +0000 (02:12 +0000)]
Branch b1_8
b=17402
i=vitaly.fertman
i=eric.mei

Clear up nid_stat's nid_exp_ref_count usage.

16 years agob=17671
brian [Mon, 4 May 2009 21:45:44 +0000 (21:45 +0000)]
b=17671
i=zhen.liang
i=sheng.yang

Enable building of OFED 1.4.1 RC4 on b1_8 for testing in anticipation of
a 1.8.1 release with OFED 1.4.1 GA.
This includes RHEL5, which disables it's current "inkernel" specification
and reverts it's kernel configs accordingly.

16 years agob=17671
brian [Mon, 4 May 2009 21:30:59 +0000 (21:30 +0000)]
b=17671
i=zhen.liang
i=sheng.yang

Enable Lustre to be built with OFED 1.4.1.

This is just the glue needed for the build with OFED 1.4.1 to actually work.
OFED 1.4.1 won't actually get built with a Lustre branch until a target file
specifies:

OFED_VERSION=1.4.1-rc4

Note that OFED 1.4.1 only supports RHEL4, RHEL5 and SLES10 targets.  SLES9
users are out of luck (but have been for some time with OFED).

16 years agob=17671
brian [Mon, 4 May 2009 21:30:57 +0000 (21:30 +0000)]
b=17671
i=zhen.liang
i=sheng.yang

Enable Lustre to be built with OFED 1.4.1.

This is just the glue needed for the build with OFED 1.4.1 to actually work.
OFED 1.4.1 won't actually get built with a Lustre branch until a target file
specifies:

OFED_VERSION=1.4.1-rc4

Note that OFED 1.4.1 only supports RHEL4, RHEL5 and SLES10 targets.  SLES9
users are out of luck (but have been for some time with OFED).

16 years agob=17671
brian [Mon, 4 May 2009 21:30:56 +0000 (21:30 +0000)]
b=17671
i=zhen.liang
i=sheng.yang

Enable Lustre to be built with OFED 1.4.1.

This is just the glue needed for the build with OFED 1.4.1 to actually work.
OFED 1.4.1 won't actually get built with a Lustre branch until a target file
specifies:

OFED_VERSION=1.4.1-rc4

Note that OFED 1.4.1 only supports RHEL4, RHEL5 and SLES10 targets.  SLES9
users are out of luck (but have been for some time with OFED).

16 years agob=19319
anserper [Mon, 4 May 2009 20:03:34 +0000 (20:03 +0000)]
b=19319
i=Alexander Zarochentsev

don't pass garbage in mode with O_CREAT

16 years agob=16312
brian [Mon, 4 May 2009 19:10:39 +0000 (19:10 +0000)]
b=16312
i=wangyb
i=jack

- allow the download functions to take a "force" argument to force a download
  even if we have the file locally (maybe it's corrupt or something)
- download_srpm() should respect the $DOWNLOAD variable
- better detect failed downloads
- return failure if the untar of the OFED tarball fails
- gather diagnostic info if configure for lustre fails
- handle OFED RC and daily release filenames which have an extra tag appended
  to them
- move the kernel-ib-devel unpacking to outside the building function so that
  it's unpacked even if a cached build is used
- properly return failure if build_lustre() fails
- wipe the KABI whitelist when building the RHEL5 kernel as we do indeed alter
  the KABI by using an external OFED stack instead of the inkernel OFED stack
- replace a perl s/// usage with sed for efficiency and portability

16 years agob=16312
brian [Mon, 4 May 2009 19:05:05 +0000 (19:05 +0000)]
b=16312
i=wangyb
i=jack

- add "lnxmin" to the sles10 target file to deal with the breakage that bug
  19336 will aim to fix properly
  - this meets up with the recent commit to the build module

16 years agob=16312
brian [Mon, 4 May 2009 18:50:25 +0000 (18:50 +0000)]
b=16312
i=wangyb
i=jack

- fixes vanilla build: typo
- enhanced incomplete cache detection
- put ext3 source into kernel-devel for rhel5 to get rid of ugly lbuild hack
- clean up the RPM smp type specification as well as .config selection
  - we can actually get rid of the rhel5 -smp .configs in the lustre tree now
- find the kernel rpm by looking at rpm attributes instead of just filenames
- fix a bug where some old code was setting global variables it is no longer
  able to set
- add "lnxmin" to the sles10 target file to deal with the breakage that bug
  19336 will aim to fix properly

16 years agob=16312
brian [Mon, 4 May 2009 18:50:24 +0000 (18:50 +0000)]
b=16312
i=wangyb
i=jack

- fixes vanilla build: typo
- enhanced incomplete cache detection
- put ext3 source into kernel-devel for rhel5 to get rid of ugly lbuild hack
- clean up the RPM smp type specification as well as .config selection
  - we can actually get rid of the rhel5 -smp .configs in the lustre tree now
- find the kernel rpm by looking at rpm attributes instead of just filenames
- fix a bug where some old code was setting global variables it is no longer
  able to set
- add "lnxmin" to the sles10 target file to deal with the breakage that bug
  19336 will aim to fix properly

16 years agob=19143
grev [Mon, 4 May 2009 12:34:16 +0000 (12:34 +0000)]
b=19143
i=Robert.Read
t-f pri-facet sec-facet different devs names fix

16 years agob=19143
grev [Mon, 4 May 2009 12:26:42 +0000 (12:26 +0000)]
b=19143
i=Robert.Read
t-f pri-facet sec-facet different devs names fix

16 years agoBranch HEAD
liangzhen [Mon, 4 May 2009 05:01:09 +0000 (05:01 +0000)]
Branch HEAD

Fix memory leak in obdecho

b=18096
i=wangdi
i=johann

16 years agoBranch HEAD
liangzhen [Mon, 4 May 2009 04:51:16 +0000 (04:51 +0000)]
Branch HEAD

Enable obdecho connecting

b=18096
o=ericm
i=liang