to fix bug introduced by lu_dirent-change patch

b=15188

individual file sync to eliminate dangerous inode locking
with I_LOCK that can lead to a deadlock.

b=15188
i=green
i=shadow

ksocknal_send_hell() hits ASSERTION while connecting races with closing

b=13983
i=isaac

b=13397

Fixed last commit lost part.

i=yury.umanets
i=adilger

this patch extends lu_dirent->lde_hash element, which is required for dmu based mdd.
but I am keeping MEA_MAGIC_HASH_SEGMENT hash within 32 bit.

b=13397
i=shadow
i=johann

Update Lustre server to support 2.6.22.14 vanilla kernel.

b=13397
i=johann
i=shadow

Split the export journal-api part as a separate patch.

b=14661
i=green
i=shadow

-- remove BL_AST lock from lru once we mark the lock as a such;
-- do not place BL_AST lock into lru even if the lock is matched and put later;
   => no BL_AST locks in lru at all;
-- CANCELING locks are not so numerous, but to avoid its traversal by another
   thread another time, drop them from the unused list once come them across.

i=Oleg.Drokin
load crc16 module if it exists

b=14230
i=h.huang
i=manoj.joseph

cleanup for umds, this patch replaces kernel api call with equivalent
api from lustre library.

make b_som compilable

i=Adilger
sanity test_71, recovery-small test_26 fixes
renumbering test_26->test_26a
FAIL_ON_ERROR initialization in cfg
error, remote_mds, remote_ost fn fixes (b=14763, comment 19)

b=14751
i=green
i=bzzz

reset the time reference between calls to fsfilt_check_slow to prevent
useless slow brw_start/direct_io/... messages.

b=15288
i=wangdi, shadow

fix stride_len assertion.

when current ra window is consumed, and 2 consequent read requires to enlarge
the read ahead window, and the enlargement action met window_start 0,
window_len 80, because the latest read consumes the whole window content,
stride_offset is 80, so the left of current ra window is 0, and the assertion
of stride_len should be ">= 0" rather than "> 0"

b=14257

Do not include LdLM_FLOCK locks into ldlm_pool sanity calculations.

b=14134
i=shadow, nathan

change non-fatal error messages about contacting the MGS.

b=15291
i=eric.mei
i=jian.yu

fix rmtacl test scripts issues for different OS platforms.

b=14855
i=shadow
i=adilger

On SLES10/PPC, fs.h includes idr.h which requires BITS_PER_LONG to
be defined. Add a hack in mkfs_lustre.c to work around this compile
issue.

b=14948
i=green
i=shadow

2.6.18 calls truncate_inode_pages() only if op->delete_inode() is
not installed, whereas 2.6.9 calls it in both cases.

b=15326
r=nikita

In order to make new llite to be compilable for liblustre

i=Adilger
load crc16

Remove specialized titech patch, as Scjody suggested.

b=15335
i=isaac

Release pending txs before shutdown connection and destroy peer.

b=14424
r=johann, bwzhou

Add severl module parameters for lustre tunables

b=14746
r=adilger, bwzhou

patch for _IOWR redefined build error on SLES10 environment

b=14576
i=eric.mei
i=adilger

Wrap the crypto api to adapt upstream kernel changes and keep compatible to old style.

b=13397
i=adilger
i=shadow

Add kernel patches for vanilla-2.6.22.14.

b=14533

a spontaneous change got into the commit and prevented HEAD to unmount

b=15283
r=walter

use "get_param version" instead of "lustre_build_version"

update to latest e2fsprogs version

b=14413;          14763
r=shadow, johann; bwzhou

fix leak-finder and add a test for conf-sanity.sh (including andreas's patch
to suppress the false negative of test 39)

b=14731
i=adilger

Remove conf-sanity test 33a from the always except list

b=15002
i=isaac

Fix a race between ksocknal_terminate_conn and ksocknal_scheduler