Whamcloud - gitweb
Vladimir Saveliev [Fri, 20 Aug 2010 15:03:09 +0000 (19:03 +0400)]
b=17485 Don't reset the lov_objid to last_id sent by OST
https://bugzilla.lustre.org/attachment.cgi?id=30559 for head
i=Hongchao.zhang
i=andrew.perepechko
Vladimir Saveliev [Fri, 20 Aug 2010 15:02:36 +0000 (19:02 +0400)]
b=17485 testcase to verify MDS not to allocate same objid to different files
i=johann.lombardi
i=grev
Mikhail Pershin [Sat, 21 Aug 2010 10:01:48 +0000 (14:01 +0400)]
b=17760 Separate locking for obd bitfield and recovery
i=adilger
i=zam
Ricardo M. Correia [Tue, 17 Aug 2010 17:09:54 +0000 (21:09 +0400)]
b=23267 Make lustre_idl.h include needed definitions from libcfs.
i=nathan.rutman
i=mikhail.pershin
It seems that lustre_idl.h uses symbols such as LASSERT, CLASSERT, LPUX64, etc,
but it doesn't include libcfs.h. This was causing a compilation failure in
b_hd_kdmu. The fix is to include libcfs.h.
Nathan Rutman [Thu, 19 Aug 2010 21:40:05 +0000 (01:40 +0400)]
b=22934 fix writeconf testing: require modules for tunefs, don't use SINGLEMDS
i=johann
Dmitry Zogin [Fri, 20 Aug 2010 14:50:07 +0000 (18:50 +0400)]
b=17682 Improve debug capability for production systems
Add a warning, when debug/subsystem_debug masks are set by
numerical values, rather than by symbolic names.
Dmitry Zogin [Fri, 20 Aug 2010 14:44:44 +0000 (18:44 +0400)]
b=17682 Improve debug capability for production systems
Improve performance of D_RPCTRACE debugging.
i=andreas.dilger
i=andrew.perepechko
Mikhail Pershin [Fri, 20 Aug 2010 19:25:26 +0000 (23:25 +0400)]
b=22610 a truncate_complete_page fix
truncate_complete_page implementation for the patchless
client could arbitrarily unset PG_Uptodate flag for a
page being kicked from the page cache, an uptodate check
right after a readpage call in filemap_fault could fail
because of that as though the page read had been unsuccessful.
i=Oleg Drokin
i=Johann Lombardi
Nathan Rutman [Fri, 20 Aug 2010 19:00:55 +0000 (23:00 +0400)]
b=23595 fix conf-sanity 57 for remote ost
Elena Gryaznova [Fri, 20 Aug 2010 16:47:22 +0000 (20:47 +0400)]
b=14242 test_6g fails when b_release_1_6_4 is run on Cray XT3
i=Andreas.Dilger
Elena Gryaznova [Fri, 20 Aug 2010 16:59:36 +0000 (20:59 +0400)]
b=22364 sanity-quota: remote obsolete test_10, test_16
i=Yong.Fan
Oleg Drokin [Fri, 20 Aug 2010 16:00:39 +0000 (20:00 +0400)]
b=18016 fix index type in ll_read_ahead_page
The page index type in ll_read_ahead_page was int which is wrong
and breaks after we cross ~10T barrier breaking read ahead beyod
that offset. Changred it to pgoff_t
i=wangdi
i=panda
Mikhail Pershin [Fri, 20 Aug 2010 16:29:06 +0000 (20:29 +0400)]
b=22418 2.6.32 compat synchronize_rcu already defined
i=adilger
i=kalpak
Dmitry Zogin [Thu, 19 Aug 2010 14:53:31 +0000 (18:53 +0400)]
b=21980 cache `ll_obdo_cache': Can't free all objects
Always use OBDO_ALLOC/FREE for obdo allocations to prevent slab fragmentation.
Also removing OBD_FL_TEMPORARY flag relicts.
o=johann
i=di.wang
i=dmitry.zoguine
Isaac Huang [Thu, 19 Aug 2010 17:11:46 +0000 (21:11 +0400)]
b=23179 MDS node unresponsive
Better hash distribution, doubled hash size for the lnet cookie hash.
i=zhen.liang
i=andreas.dilger
Nathan Rutman [Thu, 19 Aug 2010 21:36:44 +0000 (01:36 +0400)]
b=23120 eliminate defunct changelog_send_thread processes
o=thomas.leibovici@cea.fr
i=nathan
Cliff White [Thu, 19 Aug 2010 20:28:13 +0000 (00:28 +0400)]
b=16909 Console message cleanup
i=maxim.patlasov
i=johann.lombardi
Use D_NET for DEBUG_REQ
Elena Gryaznova [Thu, 19 Aug 2010 11:23:08 +0000 (15:23 +0400)]
b=22797 notify users that recovery-[random,double]-scale tests are not functional for SOFT failure mode
i=Brian.Murrell
Mikhail Pershin [Thu, 19 Aug 2010 16:36:07 +0000 (20:36 +0400)]
b=22906 limit filesystem size for LUN size close to 16TB
a=adilger
i=zhiqi.tao
i=girish.shilamkar
Mikhail Pershin [Thu, 19 Aug 2010 15:22:42 +0000 (19:22 +0400)]
b=21825 doxygen comments for CMM
i=di.wang
Mikhail Pershin [Thu, 19 Aug 2010 15:01:54 +0000 (19:01 +0400)]
b=20334 fix conflicting ioctl numbers
i=nathan
i=tappro
Isaac Huang [Wed, 18 Aug 2010 05:40:56 +0000 (09:40 +0400)]
b=20973 Doxygen comments for LNet API
Doxygen comments for LNet API. This is a comment-only change.
i=maxim
Liang Zhen [Tue, 17 Aug 2010 07:06:13 +0000 (11:06 +0400)]
b21619 hash ME on RDMA portal i=isaac i=maxim
Rahul Deshmukh [Thu, 19 Aug 2010 06:29:34 +0000 (10:29 +0400)]
b=22882 MMP might sleep negative time
b=22882 MMP might sleep negative time
i=andreas
i=girish
Ported MMP might sleep negative time patch.
Vitaly Fertman [Wed, 18 Aug 2010 20:30:04 +0000 (00:30 +0400)]
bz=21869 improve filter_fid2dentry() error message
o=adilger
i=girish
i=landen
Andrew Perepechko [Wed, 18 Aug 2010 18:12:07 +0000 (22:12 +0400)]
b=23196 take lov reference in lov_quota_adjust_qunit so as to avoid races
a=Johann Lombardi
i=ZhiYong Tian
i=Andrew Perepechko
Andrew Perepechko [Tue, 17 Aug 2010 09:31:39 +0000 (13:31 +0400)]
b=22360 return -EIO in close() if there was any async I/O error
i=Andreas Dilger
i=Johann Lombardi
i=ZhiYong Tian
Elena Gryaznova [Tue, 17 Aug 2010 19:12:57 +0000 (23:12 +0400)]
b=22923 increase show_error timeout from 5 to 10
i=Maxim.Patlasov
Elena Gryaznova [Tue, 17 Aug 2010 19:08:20 +0000 (23:08 +0400)]
b=22923 increase lst stat timeout
i=Maxim.Patlasov
Andrew Perepechko [Mon, 16 Aug 2010 21:42:10 +0000 (01:42 +0400)]
b=22107 pin object's inode in memory to avoid certain timeouts
i=Andreas Dilger
i=Johann Lombardi
Dmitry Zogin [Fri, 13 Aug 2010 14:58:43 +0000 (18:58 +0400)]
b=21259 udev rule to set /dev/obd perms 666
i=christopher.morrone
i=dmitry.zoguine
Mikhail Pershin [Thu, 19 Aug 2010 07:02:05 +0000 (11:02 +0400)]
b=22423 Reconnects are not throttled
Rely on pings to issue reconnects. Conf-sanity.sh test_35 modified.
i=nathan.ruthman
i=dmitry.zoguine
yangsheng [Fri, 13 Aug 2010 13:19:26 +0000 (17:19 +0400)]
b=19102 set default values of filesystem-wide for LOVEA.
i=adilger
i=nathan
Nathan Rutman [Fri, 13 Aug 2010 22:11:07 +0000 (02:11 +0400)]
b=17471 change conf_param syntax to match set_param
i=adilger
i=emoly.liu
Nathan Rutman [Fri, 13 Aug 2010 20:29:51 +0000 (00:29 +0400)]
b=22656 Prevent failover nids from registering with MGS first.
Make the check in mgs_handle_target_reg()
o=Joseph Herring
i=nathan.rutman
i=andreas.dilger
Nathan Rutman [Fri, 13 Aug 2010 16:47:47 +0000 (20:47 +0400)]
b=22464 add writeconf as mount option (includes bz 23228)
i=alexg
i=adilger
Dmitry Zogin [Fri, 13 Aug 2010 13:39:38 +0000 (17:39 +0400)]
b=22137 kernel oops at replay-single test_61d.
replay-single.sh test_61d was modified to operate with MGS in case of
the different MGS and MDS.
i=grev
Liang Zhen [Tue, 17 Aug 2010 06:26:17 +0000 (10:26 +0400)]
b20288 fix a deadlock in kiblnd_check_conns i=isaac i=maxim
Brian J. Murrell [Fri, 13 Aug 2010 15:03:10 +0000 (19:03 +0400)]
b=23185 check for both arches
When we build our version of the SLES kernel, we optimize it for i686
whereas the SUSE kernel is i386. The actual arch makes a difference in
where the Module.symvers can be found, so just look in both locations
to cover both the upstream vendor kernel as well as our patched kernel.
Brian J. Murrell [Fri, 13 Aug 2010 15:03:09 +0000 (19:03 +0400)]
b=23185 use resolve_arch() in the test too
Missed a usage need for resolve_arch() in the test for the file we
extracted, using resolve_arch().
Brian J. Murrell [Fri, 13 Aug 2010 15:03:08 +0000 (19:03 +0400)]
b=23185 properly support sles10 ppc64
We never really have properly supported ppc64 on sles10:
- RPMSMPTYPE for ppc64 on SLES10 is ppc64, not smp
- add a function to resolve an arch to their canonical value
Comment out some code to align the sles distro lbuild with rhel5.
Brian J. Murrell [Fri, 13 Aug 2010 14:17:01 +0000 (18:17 +0400)]
b=21452 kABI tracking
Changes required to build packages that properly interact with
the kABI tracking included in SLES and RHEL kernels:
- take local copies of the find_requires generators and make modif-
ications to them so that they can find the kernel artifacts installed
in our build tree
+ thusly, override the __find_requires macro in all of the RPM
build operations
Fix package versioning of patchless packages to also include the
timestamp, just like patched packages do, for non-release builds.
Also, remove the _lustre from the kernel version in the lustre
package names for patchless packages.
Note that changes needed to enable the external dependency checker
and thus include kABI dependencies in the RPM are not included here
for RHEL5. Once RH have updated their kABI whitelist to include the
symbols we need, the patches in bz attachments 30546-7 need to land
for RHEL5 weak modules to work and a bug needs to be filed with OFA
to land the change in bz attachment 30547.
i=wangyb
i=mjmac
LiuYing [Tue, 17 Aug 2010 03:40:49 +0000 (07:40 +0400)]
b=17166 remove <2.6.9 compatibility code from HEAD
HEAD requires 2.6.9 and above, so we remove older code.
The majority of the remaining compatibility code is in libcfs and lnet.
i=andreas
i=isaac
yangsheng [Fri, 13 Aug 2010 13:12:44 +0000 (17:12 +0400)]
b=13752 Remove 2.4 kernel definition of cfs_waitq_wait_event_interruptible_timeout().
i=issac
yangsheng [Fri, 13 Aug 2010 13:09:41 +0000 (17:09 +0400)]
b=23122 Get ia64/rhel5 build successful.
Mikhail Pershin [Tue, 17 Aug 2010 05:18:37 +0000 (09:18 +0400)]
Merge branch 'master' of git.lustre.org:prime/lustre
Rahul Deshmukh [Sat, 14 Aug 2010 08:09:50 +0000 (12:09 +0400)]
b=19625 ext4 support for SLES11
Bug 19625 ext4 support for SLES11
Ported the ext4 support for SLES11 related changes for master.
unknown [Mon, 16 Aug 2010 22:22:34 +0000 (15:22 -0700)]
Updated for the next bi-weekly build.
Vitaly Fertman [Fri, 13 Aug 2010 08:55:00 +0000 (12:55 +0400)]
b=23221 merge lock descripters if overlapped
i=green
i=ericm
lock descriptors prepared by vvp_mmap_locks() and ccc_io_one_lock_index()
may overlap and must be merged
Andrew Perepechko [Mon, 16 Aug 2010 11:58:06 +0000 (15:58 +0400)]
b=23196 take lov reference in lov_quota_check
i=Johann Lombardi
i=ZhiYong Tian
Liang Zhen [Sun, 15 Aug 2010 16:46:52 +0000 (20:46 +0400)]
b23289 smp improvement for watchdog i=eric.mei i=maxim
Liang Zhen [Sun, 15 Aug 2010 16:46:00 +0000 (20:46 +0400)]
b22078 wrong value is used by parse_net
i=nathan i=robert i=qiang.wu
yangsheng [Fri, 13 Aug 2010 13:05:28 +0000 (17:05 +0400)]
b=17630 Don't export nfs when work with 4k stack.
i=adilger
pravin [Fri, 13 Aug 2010 11:19:11 +0000 (15:19 +0400)]
b=20563
i=vitaly
i=andreas
patch adds mount option to generate 32bit ino, this can be used
for 32bit application compatibility.
Christopher J. Morrone [Mon, 16 Aug 2010 19:09:15 +0000 (23:09 +0400)]
b=22233 Fix types for do_div argument
do_div only support uint64_t as its first argument.
i=johann,adilger,wangdi
Dmitry Zogin [Tue, 10 Aug 2010 19:27:14 +0000 (23:27 +0400)]
b=21137 ext4 extent allocation is slower than in ext3
Increase the default value of MB_DEFAULT_ORDER2_REQS to 8, enlarge ext4
preallocation table for 2048 4K blocks extents creation.
i=alex.zhuravlev
i=andrew.perepechko
Vladimir Saveliev [Tue, 10 Aug 2010 17:07:04 +0000 (21:07 +0400)]
b=23271 fix typo
there has to be no space between the lvalue and the '='
Mikhail Pershin [Fri, 13 Aug 2010 08:52:35 +0000 (12:52 +0400)]
Revert "b=21951 2.6.32-fc13 patchless client support for HEAD"
This reverts commit
8ba026e938688af32d10f598c3af3ab711695789.
Dmitry Zogin [Fri, 6 Aug 2010 17:10:26 +0000 (21:10 +0400)]
b=22301 lustre.lov error when backing up symlinks with extended attributes
Improved logic in ll_listxattr()
i=tom.wang
i=dmitry.zogin
sanity test_17k created
o=grev
i=dmitry.zogin
Mikhail Pershin [Fri, 13 Aug 2010 05:15:06 +0000 (09:15 +0400)]
b=23428 Fix lustre built with --enable-lu_ref
Fix issues found with --enable-lu_ref.
i=adilger
i=oleg
i=zam
Mikhail Pershin [Fri, 13 Aug 2010 04:58:44 +0000 (08:58 +0400)]
b=15936 recovery fixes
Use only target_recovery_fini() to finish recovery.
i=rread
Fan Yong [Fri, 6 Aug 2010 03:05:14 +0000 (07:05 +0400)]
b=22440 more proper error message for "lfs quota"
more proper error message for "lfs quota"
i=landen
i=andrew.perepechko
yangsheng [Mon, 9 Aug 2010 06:27:38 +0000 (10:27 +0400)]
b=22385 Computing result of unsigned variable may < 0.
i=johann
i=wangdi
Landen [Mon, 9 Aug 2010 05:39:09 +0000 (09:39 +0400)]
b=22108 correct number of objects in slow precreating path
i=andreas.dilger
i=landen
Vladimir Saveliev [Fri, 6 Aug 2010 23:19:34 +0000 (03:19 +0400)]
b=23271 handle e2fsck and lfsck return values
to avoid test-framework.sh' trap
i=jian.yu
i=grev
Vitaly Fertman [Fri, 6 Aug 2010 08:26:39 +0000 (12:26 +0400)]
b=23127 osc lock granted fix
enqueue reply & completion ast race makes it possible to grant lock
twice losing intermediate osc_unuse
Andreas Dilger [Mon, 9 Aug 2010 15:08:51 +0000 (19:08 +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.
i=andrew.perepechko
i=sheng.yang
Nathan Rutman [Mon, 9 Aug 2010 17:49:22 +0000 (21:49 +0400)]
b=23408 disable failure temporarily while we collect performance stats
i=vitaly
Mikhail Pershin [Fri, 13 Aug 2010 05:25:22 +0000 (09:25 +0400)]
b=23409 add "-i" to the setstripe usage and manpage
i=sheila.barthel
Fan Yong [Fri, 6 Aug 2010 02:22:50 +0000 (06:22 +0400)]
b=21846 add a test for testing rehash in sanity.sh
1. enable rehash on lqs
2. if long is 64bit, __fls() is wrong. Fix it.
i=landen
i=tappro
Vladimir Saveliev [Fri, 6 Aug 2010 23:06:38 +0000 (03:06 +0400)]
b=22842 do not use bash variable to pass test setup state between sub-test
tests 42, 101, 102 are fixed
i=robert.read
Maxim Patlasov [Fri, 6 Aug 2010 13:21:46 +0000 (17:21 +0400)]
b=18751 Move prng.c to libcfs
i=adilger
i=maxim
Note that some function names were changed:
cfs_get_random_bytes --> cfs_get_random_bytes_prim
ll_get_random_bytes --> cfs_get_random_bytes
ll_rand --> cfs_rand
ll_srand --> cfs_srand
Dmitry Zogin [Thu, 5 Aug 2010 19:32:40 +0000 (23:32 +0400)]
b=19529 Avoid deadlock for local client writes.
Check the OBD_BRW_MEMALLOC flag correctly in the remote buffer.
i=andreas.dilger
i=johann.lombardi
Dmitry Zogin [Thu, 5 Aug 2010 18:48:56 +0000 (22:48 +0400)]
b=21760 Applications hung in direct I/O
Make sure that the bulk is aborted, if a request has been aborted in flight.
Call ptlrpc_abort_bulk() out of ptlrpc_check_set()
i=oleg.drokin
i=andrew.perepechko
Brian J. Murrell [Fri, 6 Aug 2010 17:59:04 +0000 (21:59 +0400)]
b=22612 dig out Module.symvers for sles10
When we build modules in lbuild for sles10 kernels, we point to the
contents of the kernel-source RPM. That does not contain the
Module.symvers file though and thus we get a nice big warning that
the modules built (i.e. ldiskfs) will not contain versions.
This is because we need to unpack the /usr/src/linux-*obj/Module.symvers
file from the kernel-$flavour or kernel-syms RPM into the location pointed to
by --with-linux-obj.
Fix a bug in unpack_linux_devel_rpm-$DISTRO where we were not checking
for the success of the function.
i=mjmac
i=wangyb
hongchao.zhang [Wed, 28 Jul 2010 22:54:29 +0000 (02:54 +0400)]
b=23139 workaround to avoid assertion in osc_init_grant
workaround for 1.6 servers which don't have the patch
from bug20278 applied
i=oleg.drokin
i=eric.mei
Brian J. Murrell [Fri, 6 Aug 2010 14:08:59 +0000 (18:08 +0400)]
b=22978 fix compiler warning error
Fix the warning/error:
sanity.c: In function ‘t21’:
sanity.c:708: error: suggest parentheses around operand of ‘!’ or change ‘&’ to ‘&&’ or ‘!’ to ‘~’
i=panda
i=whitebear
hongchao.zhang [Wed, 28 Jul 2010 23:02:09 +0000 (03:02 +0400)]
b=23352 add debugging information to late lock cancels
print out the arrival time of the delayed cancel RPC, so we can
determine whether it was waiting in the queue a long time, or
whether it arrived late on the network
i=nathan.rutman
i=hongchao.zhang
Landen [Fri, 6 Aug 2010 02:33:07 +0000 (06:33 +0400)]
b=20877 disable test_12 of sanity-quota.sh
i=johann
Manoj Joseph [Fri, 6 Aug 2010 01:22:07 +0000 (05:22 +0400)]
b=23296 Fix the initialization of oti
Fix the initialization of obd_trans_info
i=qiang.wu
i=andreas.dilger
Vitaly Fertman [Wed, 4 Aug 2010 22:17:50 +0000 (02:17 +0400)]
b=22818 exp_queued_rpc under a separate lock
i=green
i=liang
another bh lock is added just to protect exp_queued_rpc in the export
Andrew Perepechko [Thu, 15 Jul 2010 14:49:08 +0000 (18:49 +0400)]
b=16890 a build fix for --disable-quota
i=ZhiYong Tian
i=Yong Fan
attachments 30599 and 30600
Andreas Dilger [Wed, 4 Aug 2010 20:10:16 +0000 (00:10 +0400)]
b=22481 man page for lfs_migrate
Add a manual page for lfs_migrate.
Minor formatting changes of the lfs_migrate::usage() message.
Vitaly Fertman [Tue, 3 Aug 2010 09:49:27 +0000 (13:49 +0400)]
b=11739 eliminate lbug
i=green
i=adilger
don't LBUG on network errors in ldlm_handle_cancel().
Vitaly Fertman [Mon, 2 Aug 2010 10:45:23 +0000 (14:45 +0400)]
b=21528 lower the message severety
i=johann
Jian Yu [Mon, 19 Jul 2010 07:35:11 +0000 (11:35 +0400)]
b=22348 improve get_mdtosc_proc_path() to handle 2.0 server on 1.8 disk
If the 2.0 MDS was mounted on 1.8 device, then the OSC and LOV names
used by MDT would not be changed:
mdt lov: fsname-mdtlov
mdt osc: fsname-OSTXXXX-osc
The patch is to improve get_mdtosc_proc_path() to get correct OSC name
while 2.0 server being mounted on 1.8 disk.
i=robert.read
i=grev
hongchao.zhang [Sat, 10 Jul 2010 08:39:37 +0000 (12:39 +0400)]
b=19069 cleanup on nid_stats entry refcount
introduce reconnect flag in "lprocfs_exp_setup" to cleanup
the refcount of nid_stats
i=andreas.dilger
i=yong.fan
Maxim Patlasov [Thu, 22 Jul 2010 11:29:38 +0000 (15:29 +0400)]
b=16842 Libcfs common code changes
i=rread
i=alex
libcfs: get rid of cfs_alloc/free_pages and cfs_get_blockedsigs, fix __l_wait_event
Matt Wu [Thu, 29 Jul 2010 06:55:31 +0000 (10:55 +0400)]
b=17167 cfs_rcu_head cleanup in lustre source
i=andreas.dilger
i=maxim.patlasov
Elena Gryaznova [Fri, 30 Jul 2010 14:31:49 +0000 (18:31 +0400)]
b=23382 t-f: do_nodes(): wrong sed RE
i=Andrew.Perepechko
Mikhail Pershin [Fri, 30 Jul 2010 18:55:46 +0000 (22:55 +0400)]
Merge branch 'master' of git.lustre.org:prime/lustre
Elena Gryaznova [Fri, 30 Jul 2010 13:36:36 +0000 (17:36 +0400)]
b=22977 re-struct obdfilter-survey.sh
i=Andrew.Perepechko
Brian J. Murrell [Thu, 29 Jul 2010 20:24:43 +0000 (00:24 +0400)]
b=22976 fix bash syntax error
When using "test" to compare strings, both sides of the comparison
should either be quoted or not quoted, not one of each.
= should be used for equality in portable tests.
i=mjmac
i=whitebear
Terry Rutledge [Fri, 30 Jul 2010 17:46:01 +0000 (10:46 -0700)]
Corrected the field that represents pre release version numbers.
This is for 2.1.0 build 01.
Terry Rutledge [Fri, 30 Jul 2010 17:41:02 +0000 (10:41 -0700)]
Updated version strings for 2.1.0 build 01. Updated ChangeLogs
with TBD, Oracle, Inc. and new version info.
Mikhail Pershin [Wed, 28 Jul 2010 17:09:48 +0000 (21:09 +0400)]
Revert "b=22464 add writeconf as mount option (includes bz 23228)"
This reverts commit
adcf9aa295e5c0bf51bc8dd45dde1e900b0e1165.
Landen [Tue, 27 Jul 2010 11:11:04 +0000 (15:11 +0400)]
b=20433 we should recycle dentries and inodes if only cancelling locks existing
i=green
i=adilger
Oleg Drokin [Fri, 23 Jul 2010 10:03:02 +0000 (14:03 +0400)]
b=16919 Async journal commit support
Async journal commit for 2.0 branch. Also reverts patch from bug 22190 as no
longer needed.
Also included changes from b1_8 that were introduced in bug 22241.
Async commit is ENABLED by default.
i=adilger
i=tappro
Oleg Drokin [Fri, 23 Jul 2010 09:54:01 +0000 (13:54 +0400)]
b=22252 allow multiple instances of the same nid in NID hash.
Case of multiple separate clients from the same NID (as with liblustre) is legitimate and so we
should allow multiple instances of the same NID in nid hash
i=rread
i=johann
Fan Yong [Thu, 22 Jul 2010 01:22:12 +0000 (05:22 +0400)]
b=22888 fix memory leak in handle_recovery_req() when export disconnected already
fix memory leak in handle_recovery_req() when export disconnected already
i=Mikhail.Pershin
i=landen