b=17153
i=johann, adilger

Remove 2.4 compatibility.

fix the false qunit_put in qctxt_wait_pending_dqacq()
b=17794
i=tianzy
i=panda

Restore the changes I made yesterday which broke build because I used a stale kernel.

b=17371
i=Elena
fail each time cleanup/setup went wrong

i=Brian
load_modules fn modprobe.d fix

i=Huang Hua
check_config fn default network type fix

b=17630

Add a comment to explain the change.

b=17359
i=adilger,bzzz
use time obtained from a client to update inode timestamps on mds
mds_reint_link, mds_reint_unlink and mds_reint_rename updated
inode timestamps with local server time

i=umka
i=panda
b=17611

don't override lcm->lcm_name

Branch b1_6
b=16492

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

change target_handle_dqacq_callback() error handling
b=16890
i=johann
i=panda

Fixed the raid5 patches.
- rebuild policy for rhel5 .21 kernel
- soft lockups fixed

b=17084
r=adilger,jay

b=17786

i=adilger, huanghua

Initialize the request.

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