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

- fix previous wrong commit in part related to changes in ptlrpc_abort_bulk()

This means "if OSC is slow and it is not the requested
start OST, then it can be skipped, otherwise skip it only
if it is inactive/recovering/out-of-space.

Branch b1_6
b=16081
i=shadow
i=green

b=17752
i=umka
i=shadow

b=17630

i=green, adilger

Disable NFS export when the THREAD_SIZE < 8192.

r=panda,shadow

- fixes possible sync long bulk unlink in ptlrpcd which would lead to assertion in forced umount time. Basically the fix is identical to 17310 where we move req to special phase UNREGISTERING and go processing other rpcs until bulk unlink is done;

- in sync bulk and reply unlink we check for wakeup condition every 1 sec to act quckly if unlink come instead of doing it every 20 sec as before.

r=shadow,deen

- fixes writing cookie beyond of llcd boundaries.

r=shadow

- fixes in replay-single.sh test_59b

r=grev

- fixes and cleanups in test_124a from sanity.sh

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

b=17201

i=shadow, bobijam

Update to RHEL5 kernel-2.6.18-92.1.17.el5.

b=16208

i=adilger, johann

Add utility for showing mounted hosts

b=17132
i=adilger

Use raid5/6 rhel5 improvements

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.

b=16947
i=h.huang
i=yury.umanets

Hold lli_lock when access lli_sai to prevent NULL pointer.

b=17371
i=Johann Lombardi

testcase for 17371

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

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

r=panda,shadow

- fixes race in ptlrpcd which leads to busy import and obd;
- cleanups and debugs in llcd code.

i=Adilger
test_21c fix: restore config

Branch b1_6
b=16492
i=umka
i=tappro

b=16992
o=johann
i=oleg.drokin (green)
i=zhenyu.xu (bobijam)

During ll_intent_lock(), server looks up parent and child, lock them, between these events parent could be deleted, then vfs_create may_access() fails with -ENOENT.

Then client intent disposition got DISP_OPEN_CREATE | DISP_LOOKUP_NEG | DISP_LOOKUP_EXECD | DISP_IT_EXECD, and the request got double free.

Solution: Clear DISP_ENQ_COMPLETE when we are going to release the intent (request cannot be reused anyway)

b=12433
i=Oleg Drokin
i=Yury Umanets

fix the message about imp_inval

decay qos ost/oss penalties if MDS is not creating objects
i=nathan
i=johann

fix lov_brw_check() calls lov_stripe_intersects() with incorrect parameter.
written by nikita

fix the error handling on quota slaves
i=johann
i=panda

Remove trailing whitespace.

i=Oleg.Drokin
RACER acc-sm test suit

i=Adilger
skip sanity test_100 for NETTYPE != tcp

r=adilger,behlendorf1

- avoid div/mod in lustre_hash code

fix lquota.ko fails to install with --disable-liblustre used
b=17620
i=johann
i=brian

r=shadow,adilger

Lift 4G limit on stripe_size*stripe_count
4G limit on stripe_size remains in place, though.

i=Yury.Umanets
insanity cleanup (remove dup fn, sync with HEAD t-f)

r=shadow,vitaly
- correct check for phase in ptlrpc_expired_set() and couple of other places.

i=Oleg.Drokin
new runracer script

r=tappro,wangdi

- fixes ost cleanup issue due to missed llcd_put() in the case ost does not receive disconnect from mds;

  - do not sleep on hanging llcd. Instead assert on it _after_ stopping recov_thread's ptlrpcd which should kill any remeining llcds;

  - fixes and cleanups, comments.

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

b=17505

remove "mfd" from "cloing_list" for the "mfd" will be freed in mds_mfd_close

i=robert.read

b=17602
i=yury.umanets
i=tappro

use 1.8/2.0 compatible MDT config for 1.6 mds, easy to upgrade.