fix resend requests for ldlm imports.

Branch HEAD
b=17695
i=umka
i=tappro

i=Adilger
fsx fix: limit bound file size by 1/2 RAM

r=shadow
- take into account the limit on the host because the higher limit the longer it takes to kill some locks.

i=Adilger
i=Tappro
test_7-b fix: use do_nodes instead of loop to run rundbench

i=Adilger
skip liblustre for different client/mds versions

fix an error in the test_18b of sanity-quota.sh
b=17832
i=tianzy

i=Adilger
i=Johann
test_6 fix

b=17752
i=yury.umanets
i=tianzy

Disable quota support for CMD case temporary.

i=Nikita
i=umka

	compact FLD feature.

b=12596
i=grev
i=adilger

check striping after setstripe in recovery-small test 18*.
move get_stripe_info() to t-f.

b=17371
i=Elena
fail each time setup/cleanup does not work

i=Brian
load_modules fn modprobe.d fix

i=Huang Hua
check_config fn default network type fix

Rationale is the following:

* 30 sec we need because in 30 sec locks on client will get old enough to _start_ kiling them;
* 10 sec we need because client checks SLV and kills locks every 10 sec;
* 10 sec more we need to make sure that we did not race in worse case scenario and client really had some time to kill locks.

fix "should take longer" problem of test_18 of sanity-quota.sh
b=17773
i=johann
i=panda

support gss on mgc-mgs connection.
b=16054
r=umka
r=vitaly

rewrite part of sptlrpc configuration system to be able to interoperate
with 1.8.
b=15363
r=nathan
r=fanyong

i=Tappro
FAIL_ON_ERROR=false fix: force suits exit 1 if some tests failed

Add error messages in case of failure in test_27p.
Don't have explicit return inside test_75*, this is already skipped due
to test 75 being listed in ALWAYS_EXCEPT.

Add regression tests for -1 stripe width case.
b=12836

Fix filename formatting to include space for sticky bit.

r=shadow,panda

- fixes long sync bulk unlink in ptlrpcd which stops other rpcs from being handled and also causes asstion in umount time;

- make sure that long unlink wait is done with 1 sec interval to return quickly.

r=shadow

- fixes in test_59b

r=grev

- fixes and cleanups in test_124a

i=Yury.Umanets
check_mem_leak fn: use echo instead of log fn

not send LOV EA under replay, we can't know about they size at this
time. Don't allow client connect to mds before any ost connected,
for avoid problems with LOV EA size and returning EIO to client.

Branch HEAD
b=16080
i=umka
i=tappro

b=17371
i=Johann Lombardi
testcase for 17371

b=16129

the test number fix

b=16129
i=adilger
i=green

- a high priority request list is added into service;
- once a lock is canceled, all the IO requests, including coming
ones, under this lock, are moved into this list;
- PING is also added into this list;
- once a lock cancel timeout occurs, the timeout is prolonged
if there is an IO rpc under this lock;
- another request list is added into the export, used to speed up
the rpc-lock matching.

i=Adilger
test_21c fix: restore config

i=Yury.Umanets
run acc-sm:formatall() only if forced

i=Adilger
force replay-dual to check and mount MOUNT2

b=11826
i=nikita
i=adilger

libcfs proc debug change requires this

b=13058
i=johann
i=yury.umanets

i=Oleg.Drokin
RACER accs-m test suit

i=Adilger
skip sanity test_100 for NETTYPE != tcp

i=Yury.Umanets
insanity cleanup (remove dup fn)

i=Oleg.Drokin
new runracer script

i=Adilger
use current config instead of reformat fs to have single ost

i=adilger

 - fix test checking ROC cache invalidation