Whamcloud - gitweb
fs/lustre-release.git
13 years agob=23878 add debug info
Johann Lombardi [Thu, 7 Oct 2010 08:06:12 +0000 (10:06 +0200)]
b=23878 add debug info

13 years agoAdd support for OFED 1.5.2
Johann Lombardi [Thu, 7 Oct 2010 07:55:36 +0000 (09:55 +0200)]
Add support for OFED 1.5.2

13 years agob=22168 write_disjoint: retry if write receives EINTR.
Eric Mei [Wed, 6 Oct 2010 15:16:23 +0000 (09:16 -0600)]
b=22168 write_disjoint: retry if write receives EINTR.

o=robert.read
r=eric.mei

13 years agob=23216 a fix for a possible memory leak in echo_client_kbrw
Andrew Perepechko [Wed, 6 Oct 2010 15:17:45 +0000 (19:17 +0400)]
b=23216 a fix for a possible memory leak in echo_client_kbrw

b=Oleg Drokin
b=Hong-Chao Zhang

13 years agoMerge branch 'b1_8' of git.lustre.org:prime/lustre into b1_8
Andrew Perepechko [Wed, 6 Oct 2010 15:14:25 +0000 (19:14 +0400)]
Merge branch 'b1_8' of git.lustre.org:prime/lustre into b1_8

13 years agob=23827 fix per-NID reporting on outstanding writes
Andrew Perepechko [Wed, 6 Oct 2010 15:12:52 +0000 (19:12 +0400)]
b=23827  fix per-NID reporting on outstanding writes

a=Kevin Van Maren
i=Johann Lombardi
i=Andreas Dilger

13 years agob=23780 hold write reference on i_data_sem for walk_space
Johann Lombardi [Wed, 6 Oct 2010 13:51:13 +0000 (15:51 +0200)]
b=23780 hold write reference on i_data_sem for walk_space

i=girish

Restore the old behavior and live with the fiemap locking issue for now.

13 years agob=23701 a build fix
Andrew Perepechko [Tue, 5 Oct 2010 17:55:38 +0000 (21:55 +0400)]
b=23701 a build fix

13 years agob=23710 reduce stack pressure by uninlining mds_log_lost_precreated
Andrew Perepechko [Tue, 5 Oct 2010 16:56:14 +0000 (20:56 +0400)]
b=23710 reduce stack pressure by uninlining mds_log_lost_precreated

i=Johann Lombardi

13 years agob=22546 sanity-quota test_18c: @@@@@@ FAIL: expect 104857600, got 102760448. Verifyin...
Elena Gryaznova [Tue, 5 Oct 2010 16:46:33 +0000 (20:46 +0400)]
b=22546 sanity-quota test_18c: @@@@@@ FAIL: expect 104857600, got 102760448. Verifying file failed!

o=James.Simmons <simmonsja@ornl.gov>
i=Brian.Murrell
i=grev
i=landen

13 years agob=23701 reduce stack pressure in ptlrpc_server_handle_request
Andrew Perepechko [Tue, 5 Oct 2010 16:43:18 +0000 (20:43 +0400)]
b=23701 reduce stack pressure in ptlrpc_server_handle_request

i=Oleg Drokin
i=Alexander Zarochentsev
i=Johann Lombardi

13 years agoUpdated for 1.8.5 build 03. v1_8_4_53
Terry Rutledge [Fri, 1 Oct 2010 14:53:48 +0000 (07:53 -0700)]
Updated for 1.8.5 build 03.

13 years agob=22107 a fix for the warning message in filter_destroy_internal
Andrew Perepechko [Thu, 30 Sep 2010 12:45:54 +0000 (16:45 +0400)]
b=22107 a fix for the warning message in filter_destroy_internal

filter_destroy_internal is entered with inode references from
lookup and from the resource used by the extent lock, so the
check is changed to i_count != 2.

i=Vitaly Fertman
i=Johann Lombardi

13 years agob=22766 cascading_rw: take lmm_stripe_count returned by ioctl(LL_IOC_LOV_SETSTRIPE)
Vladimir Saveliev [Wed, 29 Sep 2010 21:21:37 +0000 (01:21 +0400)]
b=22766 cascading_rw: take lmm_stripe_count returned by ioctl(LL_IOC_LOV_SETSTRIPE)

+cleanup in ll_dir_ioctl(): do not save return code of copy_to_user and copy_from_user

i=adilger

13 years agob=22770 Removed the LASSERT since (conn == NULL) is a legitimate case.
yangsheng [Mon, 20 Sep 2010 14:32:01 +0000 (22:32 +0800)]
b=22770 Removed the LASSERT since (conn == NULL) is a legitimate case.

i=adigler
i=panda

13 years agobump version to 1.8.4.52
Johann Lombardi [Tue, 28 Sep 2010 14:01:37 +0000 (16:01 +0200)]
bump version to 1.8.4.52

13 years agob=23781 fix obdo leak issue
hongchao.zhang [Sun, 12 Sep 2010 19:52:59 +0000 (03:52 +0800)]
b=23781 fix obdo leak issue

in ll_setattr_raw, if ll_extent_lock call fails, the newly allocated
obdo has not been freed before return.

i=johann

13 years agob=23706 sles11sp1: jbd2 stat patch is missing
Dmitry Zogin [Fri, 24 Sep 2010 19:05:47 +0000 (15:05 -0400)]
b=23706 sles11sp1: jbd2 stat patch is missing

 Temp patch to disable obdfilter-survey.sh 1b/2b tests,
 if jbd stats are not available.

 i=grev

13 years agoexplicitly set KVERS; allow all automake packages
Brian J. Murrell [Thu, 23 Sep 2010 15:23:34 +0000 (11:23 -0400)]
explicitly set KVERS; allow all automake packages

Explicitly set KVERS to what it'd default value would be if it's
not set by the caller.
Allow any of the compatible automake* packages in debian/control.

13 years agob=22117 Patch to limit mmp interval.
Girish Shilamkar [Thu, 2 Sep 2010 18:03:34 +0000 (23:33 +0530)]
b=22117 Patch to limit mmp interval.

i=adilger
i=kalpak

13 years agomove .debs into /debs
Brian J. Murrell [Sun, 19 Sep 2010 04:27:13 +0000 (00:27 -0400)]
move .debs into /debs

Move the built .debs from .. into a /debs subdir of the build tree.
We in fact could almost make debian/rules do this using dh_builddeb's
--destdir argument, however dpkg-genchanges wants to find them in ..
and there is no way to pass dpkg-genchange's -u argument to it from
dpkg-buildpackage.  So thus, our hack.

13 years agob=22934 conf_sanity writeconf method is never tested
Elena Gryaznova [Thu, 16 Sep 2010 18:40:22 +0000 (22:40 +0400)]
b=22934 conf_sanity writeconf method is never tested

i=Andrew.Perepechko

use the correct mds dev

13 years agob=17682 Improve debug capability for production systems
Dmitry Zogin [Thu, 16 Sep 2010 12:16:41 +0000 (08:16 -0400)]
b=17682 Improve debug capability for production systems

 Improve performance of D_RPCTRACE debugging.

 i=andreas.dilger
 i=andrew.perepechko

13 years agob=22378 Correct MDS client stats
Dmitry Zogin [Thu, 16 Sep 2010 12:13:08 +0000 (08:13 -0400)]
b=22378 Correct MDS client stats

 Interoperability fix for test_133[abc]  sanity.sh tests

 o=grev
 i=dmitry.zoguine

13 years agoIgnore generated ll_decode_filter_fid file
Andreas Dilger [Wed, 1 Sep 2010 09:07:53 +0000 (03:07 -0600)]
Ignore generated ll_decode_filter_fid file

13 years agob=23271 handle e2fsck and lfsck return values
Vladimir Saveliev [Tue, 14 Sep 2010 11:45:05 +0000 (15:45 +0400)]
b=23271 handle e2fsck and lfsck return values

to avoid test-framework.sh' trap

i=grev
i=jian.yu

13 years agob=20101 lfs ost enhancements
Andrew Perepechko [Thu, 16 Sep 2010 11:12:40 +0000 (15:12 +0400)]
b=20101 lfs ost enhancements

a=James Simmons <simmonsja@ornl.gov>
i=Andreas Dilger
i=Brian Murrell

13 years agob=23200 1.8<->2.0 interop: sanityN test_12: @@@@@@ FAIL: test_12 failed with 1
Rahul Deshmukh [Thu, 16 Sep 2010 08:08:09 +0000 (13:38 +0530)]
b=23200 1.8<->2.0 interop: sanityN test_12: @@@@@@ FAIL: test_12 failed with 1

b=23200 1.8<->2.0 interop: sanityN test_12: @@@@@@ FAIL: test_12 failed with 1

This patch fixed the 1.8<->2.0 interop: sanityN test_12

i=rread

13 years agob=23216 a fix for a possible memory leak in filter_server_init_data
Andrew Perepechko [Wed, 15 Sep 2010 21:11:56 +0000 (01:11 +0400)]
b=23216 a fix for a possible memory leak in filter_server_init_data

i=Alexander Zarochentsev
i=Dmitry Zogin

13 years agob=21137 sles11 with 1.8 is slower than 1.6 sles10 for O_DIRECT single file IOR writes
Dmitry Zogin [Wed, 15 Sep 2010 19:41:32 +0000 (15:41 -0400)]
b=21137 sles11 with 1.8 is slower than 1.6 sles10 for O_DIRECT single file IOR writes

 Extra debug logging in filter_do_bio()

 i=andreas.dilger
 i=andrew.perepechko

13 years agob=22820 too many default ACLs break directory access on new directories
Andrew Perepechko [Wed, 15 Sep 2010 17:28:02 +0000 (21:28 +0400)]
b=22820 too many default ACLs break directory access on new directories

The attached patch was a result of the discussion with Andreas Dilger on lustre
discuss starting here: http://lists.lustre.org/pipermail/lustre-discuss/2010-May/013177.html

a=Frederik Ferner <frederik.ferner@diamond.ac.uk>
i=Johann Lombardi
i=Andreas Dilger

13 years agob=23179 MDS node unresponsive
Isaac Huang [Mon, 13 Sep 2010 16:43:48 +0000 (10:43 -0600)]
b=23179 MDS node unresponsive

Better hash distribution, doubled hash size for the lnet cookie hash.

i=zhen.liang
i=andreas.dilger

13 years agob=23683 Bring upstream patch for ldiskfs.
yangsheng [Sat, 11 Sep 2010 18:54:23 +0000 (02:54 +0800)]
b=23683 Bring upstream patch for ldiskfs.

13 years agob=23701 remove a variable from stack, allocate from slab
Andrew Perepechko [Sat, 11 Sep 2010 17:45:35 +0000 (21:45 +0400)]
b=23701 remove a variable from stack, allocate from slab

Through the assembly of mds_open from the crash dump, it seems,
although the iattr var declaration is put into a compound statement,
the stack for the variable is reserved from the beginning to the
end of mds_open processing. According to crash, the size of iattr is 80 bytes.

i=Oleg Drokin
i=Alexander Zarochentsev

13 years agob=23701 remove a variable from stack, allocate from slab
Andrew Perepechko [Sat, 11 Sep 2010 17:43:59 +0000 (21:43 +0400)]
b=23701 remove a variable from stack, allocate from slab

i=Oleg Drokin
i=Alexander Zarochentsev

13 years agobz=23673 add "updates" dir to lustre-modules location.
Vitaly Fertman [Fri, 10 Sep 2010 21:48:40 +0000 (01:48 +0400)]
bz=23673 add "updates" dir to lustre-modules location.

o=grev
i=vitaly

13 years agob=22378 Correct MDS client stats
Dmitry Zogin [Fri, 10 Sep 2010 18:45:35 +0000 (14:45 -0400)]
b=22378 Correct MDS client stats

 Fixing sanity.sh test_133c

 i=grev
 i=andrew.perepechko

13 years agob=23669 change pios parameters according to space available
Elena Gryaznova [Thu, 9 Sep 2010 19:54:49 +0000 (23:54 +0400)]
b=23669 change pios parameters according to space available

i=Andrew.Perepechko

13 years agob=23174 Lustre inode size is not coherent across nodes.
Dmitry Zogin [Tue, 7 Sep 2010 15:36:01 +0000 (11:36 -0400)]
b=23174 Lustre inode size is not coherent across nodes.

 Update lvbo from disk when AST fails with EINVAL. Lvbo is updated on EINVAL
 error in ldlm_handle_ast_error(). The updates in filter_intent_policy() and
 ldlm_cb_interpret() have been removed as redundant.

 i=vitaly.fertman
 i=andrew.perepechko

13 years agopackage liblustre tests for debian
Brian J. Murrell [Wed, 1 Sep 2010 00:03:12 +0000 (20:03 -0400)]
package liblustre tests for debian

The liblustre tests were not being packaged into lustre-tests.

13 years agomake debs refinement
Brian J. Murrell [Wed, 1 Sep 2010 00:03:11 +0000 (20:03 -0400)]
make debs refinement

When looking for the most recent tag, look for only tags matching v*.
That should hopefully weed out any non-versioning tags.

Don't convert debian/changelog commits to patches since the changelog
has to be in place right when dpkg-buildpackage starts.
This does mean that one should NEVER commit to another file in the same
commit as a debian/changelog commit.

Make sure debian/patche{s,d} are clean before starting.

13 years agoRevert "b=22117 Patch to limit mmp interval."
Andrew Perepechko [Mon, 6 Sep 2010 15:34:04 +0000 (19:34 +0400)]
Revert "b=22117 Patch to limit mmp interval."

This reverts commit 0791b46099339efcf608ff99822be01766f90656.

13 years agob=22589 llite_lib.c:234: undefined-reference to `__stack_chk_fail_local'
Brian J. Murrell [Tue, 31 Aug 2010 23:49:00 +0000 (19:49 -0400)]
b=22589 llite_lib.c:234: undefined-reference to `__stack_chk_fail_local'

If liblustre.so is linked with -nostdlib it produces errors such as:
./llite_lib.o: In function `liblustre_process_log':
lustre/liblustre/llite_lib.c:234: undefined reference to `__stack_chk_fail_local'
on platforms where the stack-smashing protector is used (i.e. Ubuntu).

i=johann

13 years agob=22117 Patch to limit mmp interval.
Girish Shilamkar [Thu, 2 Sep 2010 18:03:34 +0000 (23:33 +0530)]
b=22117 Patch to limit mmp interval.

i=adilger
i=kalpak

13 years agob=23363 obdfilter-survey: no echo client and ost_name not set
Elena Gryaznova [Fri, 3 Sep 2010 14:04:18 +0000 (18:04 +0400)]
b=23363 obdfilter-survey: no echo client and ost_name not set

i=Andrew.Perepechko

libecho fix: use NETTYPE instead of tcp only

13 years agob=17748 fix sanityn test 33 to support multiple OSS nodes
Jian Yu [Fri, 3 Sep 2010 14:23:28 +0000 (22:23 +0800)]
b=17748 fix sanityn test 33 to support multiple OSS nodes

i=vitaly.fertman
i=grev

13 years agob=23702 removed space for compiler.
yangsheng [Sat, 4 Sep 2010 00:44:15 +0000 (08:44 +0800)]
b=23702 removed space for compiler.

i=panda

13 years agob=21563 Metadata performance has degraded for some operations between 1.6.5 and 1.8.1
Dmitry Zogin [Tue, 31 Aug 2010 19:54:08 +0000 (15:54 -0400)]
b=21563 Metadata performance has degraded for some operations between 1.6.5 and 1.8.1

 Change mdsrate tool to handle time with double resolution and use MPI_Wtime().
 Also stat operations measurements do not require --iter argument anymore, and do
 not use readdir() internally.

 i=johann
 i=iandrew.perepechko
 i=robert.read

13 years agob=22978 better conformation to coding standards
Brian J. Murrell [Tue, 31 Aug 2010 19:07:47 +0000 (15:07 -0400)]
b=22978 better conformation to coding standards

Per adilger:
- the preferred Lustre coding style is to not use assignments inside
  conditionals
- Lustre coding style recommends against using negation on non-boolean
  values
- while fixing this code, we may as well print the flag in octal, which
is how it is normally defined.

i=whitebear
i=panda

13 years agob=23216 a fix for echo_client_async_page memory allocation failure handling
Andrew Perepechko [Tue, 31 Aug 2010 13:18:28 +0000 (17:18 +0400)]
b=23216 a fix for echo_client_async_page memory allocation failure handling

i=Dmitry Zogin
i=ZhiYong Tian

13 years agob=23014 SGPDDSURVEY typo fix
Elena Gryaznova [Mon, 30 Aug 2010 12:13:25 +0000 (16:13 +0400)]
b=23014 SGPDDSURVEY typo fix

i=Andrew.Perepechko

set default SGPDDSURVEY value properly

13 years agob=21128 ldlm_cancel_lru fixes for stack overflow v4 and handle PF_MEMALLOC
pravin [Mon, 30 Aug 2010 09:27:47 +0000 (14:57 +0530)]
b=21128 ldlm_cancel_lru fixes for stack overflow v4 and handle PF_MEMALLOC

i=oleg
i=rahul
        avoid stack overflow by delegating work to separate thread

13 years agobump version to 1.8.4.51 v1_8_4_51
Johann Lombardi [Fri, 27 Aug 2010 22:00:36 +0000 (00:00 +0200)]
bump version to 1.8.4.51

13 years agob=23503 Oops at __percpu_counter_add+0x1b
Dmitry Zogin [Fri, 13 Aug 2010 16:52:12 +0000 (12:52 -0400)]
b=23503 Oops at __percpu_counter_add+0x1b

 Use bdi_init()/bdi_destroy() to proper initialize backing_dev_info
 structure regardless of HAVE_NEW_BACKING_DEV_INFO.

 i=sheng.yang
 i=johann.lombardi

13 years agob=22588 fix compile issue with gcc 4.4
Robert Read [Fri, 27 Aug 2010 21:36:31 +0000 (23:36 +0200)]
b=22588 fix compile issue with gcc 4.4

i=brian
i=andrew

add may_alias attribute to struct lov_user_md_v1

13 years agob=23645 remove warning printed at mount time with 2.6.32
Johann Lombardi [Fri, 27 Aug 2010 21:32:11 +0000 (23:32 +0200)]
b=23645 remove warning printed at mount time with 2.6.32

Make sure inode mutex on the CWD is taken when calling lookup_on_len().

13 years agob=23663 fix buffer overflow in liblustre
Brian J. Murrell [Fri, 27 Aug 2010 21:12:51 +0000 (23:12 +0200)]
b=23663 fix buffer overflow in liblustre

i=dmitry
i=andrew

The space allocated to ll_instance to store the "%p" notation for a
pointer was failing to allocate enough space for the leading "0x" in
addition to the space for the actual address bytes.

13 years agob=23371 Define fsfilt_{up,down}_truncate_sem() does nothing when WALK_SPACE_HAS_DATA_...
yangsheng [Fri, 27 Aug 2010 20:44:57 +0000 (22:44 +0200)]
b=23371 Define fsfilt_{up,down}_truncate_sem() does nothing when WALK_SPACE_HAS_DATA_SEM defined

i=adilger
i=andrew

13 years agob=22418 2.6.32 compat synchronize_rcu already defined
Brian J. Murrell [Wed, 25 Aug 2010 22:56:05 +0000 (18:56 -0400)]
b=22418 2.6.32 compat synchronize_rcu already defined

In 2.6.32 kernels when !CONFIG_TREE_PREEMPT_RCU synchronize_rcu is a #define
instead of being exported symbol.  In 2.6.33 kernels it  is an exported as
a symbol regardless of the configure option.  To handle this when the symbol
is not exported use the kernels provided define if available.  Otherwise
fallback to providing our own for older kernels.

o=brian.behlendorf
i=andreas
i=kalpak

13 years agob=20563 move definition of ll_need_32bit_api() after the one of ll_sb_info
Johann Lombardi [Thu, 26 Aug 2010 15:33:44 +0000 (17:33 +0200)]
b=20563 move definition of ll_need_32bit_api() after the one of ll_sb_info

13 years agob=18213 Handle the signal to avoid process hang.
yangsheng [Wed, 25 Aug 2010 16:22:31 +0000 (00:22 +0800)]
b=18213 Handle the signal to avoid process hang.

i=johann
i=hongchao.zhang

13 years agob=13752 Remove 2.4 kernel definition of cfs_waitq_wait_event_interruptible_timeout()
yangsheng [Wed, 25 Aug 2010 16:18:46 +0000 (00:18 +0800)]
b=13752 Remove 2.4 kernel definition of cfs_waitq_wait_event_interruptible_timeout()

i=issac

13 years agob=21610 Add lbuild-sles11sp1 file.
yangsheng [Wed, 25 Aug 2010 13:03:20 +0000 (21:03 +0800)]
b=21610 Add lbuild-sles11sp1 file.

i=johann

13 years agob=23515 recovery_*_scale tests need more than 2 clients
Elena Gryaznova [Wed, 25 Aug 2010 12:48:00 +0000 (16:48 +0400)]
b=23515 recovery_*_scale tests need more than 2 clients

i=Mikhail.Pershin

skip these tests by env for number of remote clients < 2

13 years agob=20563 add llite mount option to generate 32bit ino v2
pravin [Wed, 25 Aug 2010 11:50:43 +0000 (17:20 +0530)]
b=20563 add llite mount option to generate 32bit ino v2

i=vitaly
i=andreas
        patch adds mount option to generate 32bit ino, this can be used
for 32bit application compatibility.

13 years agob=22935 keep reference count for "lli_sai" to prevent it to be released when "statahe...
Fan Yong [Wed, 25 Aug 2010 05:15:41 +0000 (13:15 +0800)]
b=22935 keep reference count for "lli_sai" to prevent it to be released when "statahead_enter()" and "statahead_exit()"

keep reference count for "lli_sai" to prevent it to be released when "statahead_enter()" and "statahead_exit()"

i=eric.mei
i=di.wang

13 years agob=19151 use single-level test directory for large-scale test 3a
Jian Yu [Wed, 25 Aug 2010 02:42:23 +0000 (10:42 +0800)]
b=19151 use single-level test directory for large-scale test 3a

$tdir is a two-level directory which causes the mode setting issue
while running MPI programs. Let's use a single-level test directory
for large-scale test 3a.

i=grev
i=robert.read

13 years agodebian/patches and non-GA tags
Brian J. Murrell [Tue, 24 Aug 2010 21:53:17 +0000 (17:53 -0400)]
debian/patches and non-GA tags

Make the code to populate debian/patches work better with non-GA tags
such as v1_8_3_53.

13 years agob=22967 s/LB_LINUX_CONFTEST/AC_LANG_CONFTEST/
Brian J. Murrell [Tue, 24 Aug 2010 21:53:16 +0000 (17:53 -0400)]
b=22967 s/LB_LINUX_CONFTEST/AC_LANG_CONFTEST/

There was a macro update in more recent releases of autoconf that
requires us to use AC_LANG_CONFTEST instead of the LB_LINUX_CONFTEST
that we currently use.  The problem using LB_LINUX_CONFTEST causes
is that as configure is determining capabilities and setting capability
flags, these are not being used when compiling further conftest.c
programs.

So for example if a macro determines if foo is available and then sets
FOO if it is, and then a test in a subsequent macro tries to use FOO,
it will find it undefined.

i=michael.macdonald
i=andreas.dilger

13 years agob=22378 Correct MDS client stats
Dmitry Zogin [Tue, 24 Aug 2010 20:45:25 +0000 (16:45 -0400)]
b=22378 Correct MDS client stats

 Move some of the MDS stats from obdfilter layer to MDS layer.

 i=andreas.dilger
 i=amoly.liu

13 years agob=16890 llapi_quotactl man page update with additional explanation of igrace/bgrace...
Andrew Perepechko [Tue, 24 Aug 2010 20:35:54 +0000 (00:35 +0400)]
b=16890 llapi_quotactl man page update with additional explanation of igrace/bgrace/itime/btime

13 years agob=22378 Correct MDS client stats
Dmitry Zogin [Tue, 24 Aug 2010 20:30:07 +0000 (16:30 -0400)]
b=22378 Correct MDS client stats

 test_133 sanity.sh has been added

 i=andreas.dilger

13 years agob=23408 disable failure temporarily while we collect performance stats
Nathan Rutman [Tue, 24 Aug 2010 17:02:06 +0000 (10:02 -0700)]
b=23408 disable failure temporarily while we collect performance stats

i=vitaly

13 years agob=23595 fix broken patch
Johann Lombardi [Tue, 24 Aug 2010 20:09:06 +0000 (22:09 +0200)]
b=23595 fix broken patch

13 years agob=23595 return registration errors
Nathan Rutman [Mon, 23 Aug 2010 17:59:22 +0000 (10:59 -0700)]
b=23595 return registration errors

i=johann
i=vitaly

13 years agob=21174 fix tiny nit in previous landing
Johann Lombardi [Tue, 24 Aug 2010 16:26:33 +0000 (18:26 +0200)]
b=21174 fix tiny nit in previous landing

13 years agob=23216 a fix for a memory leak in echo_commitrw
Andrew Perepechko [Fri, 20 Aug 2010 21:51:56 +0000 (01:51 +0400)]
b=23216 a fix for a memory leak in echo_commitrw

i=Andreas Dilger
i=Zhen Liang

13 years agob=23573 skip conf-sanity fs2 tests for HARD failure mode
Elena Gryaznova [Fri, 20 Aug 2010 21:46:06 +0000 (01:46 +0400)]
b=23573 skip conf-sanity fs2 tests for HARD failure mode

i=Andrew.Perepechko

13 years agob=20407 replay-ost-single: do not skip for HARD mode and mixed_ost_devs
Elena Gryaznova [Fri, 20 Aug 2010 21:40:41 +0000 (01:40 +0400)]
b=20407 replay-ost-single: do not skip for HARD mode and mixed_ost_devs

i=Brian.Murrell

13 years agob=23595 fix conf-sanity 57 for remote ost
Nathan Rutman [Fri, 20 Aug 2010 21:16:04 +0000 (14:16 -0700)]
b=23595 fix conf-sanity 57 for remote ost

i=vitaly.fertman

13 years agob=22934 fix writeconf, redeux
Nathan Rutman [Fri, 20 Aug 2010 18:54:56 +0000 (11:54 -0700)]
b=22934 fix writeconf, redeux

13 years agob=21174 allow quotacheck over OSTs with sparse indices
Andrew Perepechko [Fri, 20 Aug 2010 11:15:25 +0000 (13:15 +0200)]
b=21174 allow quotacheck over OSTs with sparse indices

i=Elena Gryznova

13 years agob=23335 Allocate echo objects that can be mapped to a valid FID
Elena Gryaznova [Wed, 18 Aug 2010 13:31:59 +0000 (17:31 +0400)]
b=23335 Allocate echo objects that can be mapped to a valid FID

With the change to using valid FIDs for all OST objects in bug 19427,
the echo objid needs to be below 2^32, because regular FID numbers
are limited to 2^32 objects in a single sequence number.

o=andreas.dilger
i=aleksandr.guzovskiy
i=mikhail.pershin

13 years agob=23278 replay-single test 86 does not remount client
Elena Gryaznova [Tue, 17 Aug 2010 15:46:03 +0000 (19:46 +0400)]
b=23278 replay-single test 86 does not remount client

o=Oleg.Drokin
i=Elena.Gryaznova

13 years agob=20407 TF: "HARD" failovers with multiple targets per server
Elena Gryaznova [Mon, 16 Aug 2010 16:23:10 +0000 (20:23 +0400)]
b=20407 TF: "HARD" failovers with multiple targets per server

i=Brian.Murrell
i=Li.Wei

13 years agob=21174 allow quotacheck over OSTs with sparse indices
Andrew Perepechko [Mon, 16 Aug 2010 12:00:02 +0000 (16:00 +0400)]
b=21174 allow quotacheck over OSTs with sparse indices

i=Johann Lombardi
i=ZhiYong Tian

13 years agob=21610 Update changelog & which_kernel for sles11 sp1.
yangsheng [Mon, 16 Aug 2010 05:07:58 +0000 (23:07 -0600)]
b=21610 Update changelog & which_kernel for sles11 sp1.

13 years agob=21610 Kernel update for SLES11 SP1. v1_8_4_50
yangsheng [Fri, 13 Aug 2010 20:26:18 +0000 (04:26 +0800)]
b=21610 Kernel update for SLES11 SP1.

Update SLES11 SP1 to 2.6.32.13-0.5.1.

i=adilger, johann, kalpak
i=girish, rahul, whitebear
i=brian, wangyb

13 years agob=23206 performance-sanity test_8 FAIL
Dmitry Zogin [Wed, 11 Aug 2010 14:27:14 +0000 (10:27 -0400)]
b=23206 performance-sanity test_8 FAIL

 Debug patch

13 years agob=23409 add -i to the setstripe usage and man page
Andreas Dilger [Tue, 10 Aug 2010 05:57:50 +0000 (01:57 -0400)]
b=23409 add -i to the setstripe usage and man page

Add the "-i" option to the "lfs setstripe" usage and man page.
Fix nroff formatting in the "lfs setstripe" and "lfs getstripe".

i=sheila.barthel

13 years agob=21720 fix test 18 to interleave tests increase pass margin
Nathan Rutman [Mon, 9 Aug 2010 19:20:29 +0000 (12:20 -0700)]
b=21720 fix test 18 to interleave tests increase pass margin

i=rread

backport 2.0's fractional-second createmany

13 years agob=23270 simplify "lctl osts" (llapi_ostlist) code
Andreas Dilger [Mon, 9 Aug 2010 14:25:34 +0000 (10:25 -0400)]
b=23270 simplify "lctl osts" (llapi_ostlist) code

Simplify "lfs osts" command so that it avoids the filesystem traversal code
entirely, and just calls setup_osts() to print the OST list.

13 years agob=23316 BUG: soft lockup - CPU#2 stuck for 10s! [ll_cfg_requeue:2851]
Dmitry Zogin [Mon, 9 Aug 2010 12:59:45 +0000 (08:59 -0400)]
b=23316 BUG: soft lockup - CPU#2 stuck for 10s! [ll_cfg_requeue:2851]

 Use SHARED_DIR_LOGS in error_noexit().
 i=grev

13 years agob=22891 Objects not getting deleted for files which have been removed
Dmitry Zogin [Mon, 9 Aug 2010 12:51:27 +0000 (08:51 -0400)]
b=22891 Objects not getting deleted for files which have been removed

 ll_have_md_lock() should differentiate between CR and CW OPEN locks.
 Also sanityN.sh test_36b was added.

 i=oleg.drokin
 i=johann.lombardi

13 years agob=22979 ignore the case of zero unused lock before recovery for replay-single test_85
Fan Yong [Mon, 9 Aug 2010 09:02:57 +0000 (17:02 +0800)]
b=22979 ignore the case of zero unused lock before recovery for replay-single test_85

Ignore the case of zero unused lock before recovery for replay-single test_85.

i=johann.lombardi
i=Hongchao.zhang

13 years agob=22596 Avoid test failed on single OST.
yangsheng [Mon, 9 Aug 2010 08:54:59 +0000 (16:54 +0800)]
b=22596 Avoid test failed on single OST.

i=adilger, grev

Use OSTCOUNT instead hard code 2 to adapt single OST case. This test
isn't necessary OSTCOUNT > 1.

13 years agob=13585 Remove i_filterdata patches.
yangsheng [Mon, 9 Aug 2010 08:51:31 +0000 (16:51 +0800)]
b=13585 Remove i_filterdata patches.

i=adilger

13 years agob=22514 Update to latest RHEL5.5 kernel.
yangsheng [Mon, 9 Aug 2010 08:45:33 +0000 (16:45 +0800)]
b=22514 Update to latest RHEL5.5 kernel.

13 years agob=22906 mke2fs needs ~16TB LUNs to be 16TB-1 block
Andreas Dilger [Fri, 6 Aug 2010 19:43:04 +0000 (13:43 -0600)]
b=22906 mke2fs needs ~16TB LUNs to be 16TB-1 block

Adjust LUNs at or just over 16TB to be 1 block below 16TB, to avoid
problems with current (1.41) mke2fs being unhappy with this size.

i=zhiqi.tao
i=girish.shilamkar

13 years agob=13698 LL_IOC_RECREATE_FID (1.8)
Vladimir Saveliev [Sun, 1 Aug 2010 05:21:42 +0000 (09:21 +0400)]
b=13698 LL_IOC_RECREATE_FID (1.8)

define new ioctl for object replicate
it uses IDIF FID instead of truct ll_recreate_obj
old LL_IOC_RECREATE is kept for compatibility

i=andreas.dilger
i=di.wang