b=15655
i=brian, mjmac

Fixed the sles10 patchless rpm built against smp config for i686.
Fixed the new download site.

b=15517
i=johann

b=15556
i=nikita.danilov
i=yury.umanets

- do not produce zero inode number;
- hash VFS inode by FID;
- start FID sequence from 0x100000400.

Description: MDS may lose file striping (and hence file data) in some cases
Details    : If there are additional extended attributes stored on the MDS,
	     in particular ACLs, SELinux, or user attributes (if user_xattr
	     is specified for the client mount options) then there is a risk
	     of attribute loss.  Additionally, the Lustre file striping
	     needs to be larger than default (e.g. striped over all OSTs),
	     and an additional attribute must be stored initially in the
	     inode and then increase in size enough to be moved to the
	     external attribute block (e.g. ACL growing in size) for file
	     data to be lost.
i=kalpak.shah
i=alex.zhuravlev
b=15777

Sync ChangeLog from b_release_1_6_5.

b=12375
i=deen
i=grev

Ignore generated file.

b=14929
i=zam
i=nikita

i=Adilger

replay-single test_61* fixes: set fail loc on all oss

 #error "lustre_msg_v1 has been deprecated since 1.6.0, please remove it"
need too complex patch.

Update build version to 1.9.50, to avoid any confusion that this is
a pre-1.8 branch.

b=14340
i=h.huang
i=nikita.danilov

lu_dirent structure was inconsistent after lu_dirent->lde_hash
element extension to 64 bit change patch.
size of structure is different on 32 and 64 bit platform.
patch fixes that bug.

b=12888
i=johann, green

Description: mds_mfd_close() ASSERTION(rc == 0)
Details    : In mds_mfd_close(), we need protect inode's writecount change
             within its orphan write semaphore to prevent possible races.

i=Adilger

keep conf-sanity test_32a and test_32b in sync with b1_6

Reinitialize optind to 0 on each lfs_* call, in case lfs is being used interactively.  Most lfs_* functions do this already, but a few (find, setstripe, quotachown) do not.
 b=15212
 i=rupesh
 i=johann

b=15563
update buildcvs

Fix typo in error message.

b=15521
r=adilger, grev

the test case for bug 15521

i=liangzhen,i=maxim:
-   ensure UNLINK event when MD unlinked via LNetMEUnlink.
-   removed trailing spaces.

i=walter

Land Andreas' original fix for catamount build errors

i=adilger

fix compile warnings which are treated as errors on Cray XT3 catamount
build

b=15521
r=adilger, bobijam

fix the wrong lprcfs stats

Allow mds2, mds3, mds4 to be specified on other hosts.

b=14740
r=johann, bobijam

allocating one percpu struct each time instead of all in one time

b=14219
r=adilger, shadow

use obd_punch_rqset() instead of obd_setattr() to change size

b=14034
r=adilger, bobijam

error handling for the ENOMEM case when failing to allocate ldlm resource

r=Wangdi, Adilger
To remove direct instances of proc file system.

b=14929
i=zam

b=14645
i=johan
i=alex

b=13707
r=bobijam, johann

exported debug_file_path as a module param of libcfs

i=Adilger

disable LIBLUSTRE test for NETTYPE != tcp

Small logic thinko that fails the case where no o2iblnd tree is specifed.

i=Adilger

sanity test_118* fixes; set fail loc on all oss nodes

b=14949

b=14949
i=johan
i=deen

i=vitaly.vertman
i=oleg.drokin

Lockless i/o and lockless truncate code and sanityN tests.

i=he.huang
i=adilger

fix for build errors on Cray catamount builds

i=he.huang
i=adilger

fix for user-tcpip.c build errors on Cray catamount builds

i=cliffw
i=wangyb

Build OFED 1.3 kernel-ib* RPMs for the vendor kernels we support patchless
clients on (RHEL5 and SLES10).
Build Lustre with the above OFED 1.3 support (i.e. for patchless clients).