Whamcloud - gitweb
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).
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
girish [Fri, 22 May 2009 17:11:37 +0000 (17:11 +0000)]
b=19625
i=johann
ext4 patches for SLES11 ldiskfs support
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
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).
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.
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.
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.
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
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.
grev [Thu, 21 May 2009 22:25:53 +0000 (22:25 +0000)]
b=19618
i=Tom.Wang
test_101c fix
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:.
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
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
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
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
tappro [Wed, 20 May 2009 13:28:43 +0000 (13:28 +0000)]
- remove obsoleted message
b:3633
i:vitaly,adilger
bobijam [Wed, 20 May 2009 08:48:30 +0000 (08:48 +0000)]
Branch b_release_1_8_1
b=16417
Indent reformating.
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.
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.
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.
grev [Tue, 19 May 2009 13:13:10 +0000 (13:13 +0000)]
b=19523
i=Vladimir.Saveliev
test_100: exit 1 from subshell
johann [Tue, 19 May 2009 12:59:31 +0000 (12:59 +0000)]
Branch b_release_1_8_1
fix changelog.
tianzy [Tue, 19 May 2009 12:36:59 +0000 (12:36 +0000)]
*** empty log message ***
tianzy [Tue, 19 May 2009 11:15:50 +0000 (11:15 +0000)]
add an entry on Changelog for bug19495
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
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
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.
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
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.
grev [Fri, 15 May 2009 20:17:00 +0000 (20:17 +0000)]
b=19451
i=Brian
IOR load for recovery scale tests
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
stinson1947 [Fri, 15 May 2009 19:15:26 +0000 (19:15 +0000)]
Updated version for weekly build of 1.8.1.
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
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.
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
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.
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.
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
isaac [Wed, 13 May 2009 16:28:16 +0000 (16:28 +0000)]
i=liang,b=18450:
- added more debug info for connection management.
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.
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.
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
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.
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.
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.
brian [Tue, 12 May 2009 19:29:34 +0000 (19:29 +0000)]
b=17671
Update the lnet/ChangeLog with the supported versions of OFED.
brian [Tue, 12 May 2009 18:58:32 +0000 (18:58 +0000)]
b=17605
Somehow a couple of the changes escaped assimilation.
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
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.
anserper [Tue, 12 May 2009 00:49:38 +0000 (00:49 +0000)]
b=18192
i=Alexey Lyashkov
i=Girish Shilamkar
update to unified format
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
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
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
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
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
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
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
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
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
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
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
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
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.
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.
isaac [Fri, 8 May 2009 17:03:35 +0000 (17:03 +0000)]
i=wangdi,b=19448:
- fix liblustre_init_random file handle leak.
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.
grev [Fri, 8 May 2009 11:05:40 +0000 (11:05 +0000)]
b=19026
i=Brian
recovery-double-scale error message cleanup
grev [Fri, 8 May 2009 08:20:18 +0000 (08:20 +0000)]
b=18921
i=Robert.Read
rename type2 tests to parallel-scale
isaac [Thu, 7 May 2009 19:26:03 +0000 (19:26 +0000)]
i=brian,b=15870:
- added missing quotes.
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
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.
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.
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.
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
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.
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()
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.
stinson1947 [Tue, 5 May 2009 18:58:21 +0000 (18:58 +0000)]
cleaned up unneeded template line.
stinson1947 [Tue, 5 May 2009 18:52:52 +0000 (18:52 +0000)]
cleaned up unneeded template line.
stinson1947 [Tue, 5 May 2009 18:39:18 +0000 (18:39 +0000)]
Updated service tags version for 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'.
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
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
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
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
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.
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.
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).
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).
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).
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
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
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
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
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
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
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
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
liangzhen [Mon, 4 May 2009 04:51:16 +0000 (04:51 +0000)]
Branch HEAD
Enable obdecho connecting
b=18096
o=ericm
i=liang