r=phil, andreas

bump LLOG_CHUNKSIZE to 8k to allow for larger clusters

r=robert

overwrite log when running lconf --write_conf

r=robert

fix llog_destroy to work with named logs

r=jacob

remove __attribute__ ((packed)) from ptl_event_t to fix 'kernel unaligned
access...' messages on ia64

the individual OSC to recover on it's own.

b=1530

during a forced cleanup.  Otherwise, we will end up pointing to work_list,
which is on the stack, and a list_del_init() on exp_obd_chain will end up
stomping on some innocent variable on the stack, ending its already-short
life just a bit too early.
b=2908
r=robert

l_lvb_data check l_lvb_len != 0 before using, and tested of course.
b=1012

happens for zero-length files, and without this we will revoke our own
lock the next time we write to the file because osc_enqueue() won't match.
b=2818

b=2633

even if a test is excluded.
Rename "test_foo" files to "f<testno>" so they are deleted at the end of
the sanity.sh run.

export from the device from the export list.  This still isn't possible
for --force disconnects, so we don't do filter_grant_sanity_check() at
that time.

Also, change the LASSERTs to CERRORs in case this happens again.  First of
all to see if these errors are just transient during export disconnection
which means they are just overly-aggressive assertions, or if there is a
permanent accounting error that indicates some other problem.  Secondly, it
isn't possible to stop the use of existing export references, so there will
always be some small race during client eviction as completing operations
might update the export before it is destroyed.
b=2663

r=adilger

 * clean up bugs in previous patch
 * print basename(argv[0]) instead of "mount" with error messages

r Jacob

add a missing arg to printf, make the program exit with 1 on args error

r Adilger

fix a llmount, mount.lustre segment fault bug

b=2464

Land initial b_bgl fixes.  Includes compile and a couple of swabbing
fixes.

enqueue reply if the extent was changed and granted immediately.  This
avoids overwriting the policy data if it was updated in the completion callback
before the reply was processed.
b=2901
r=phil

b=2818

b=2167

a failed object creation instead of in advance.  Otherwise, if there is a
down OST the following one will have twice as many objects allocated on it
(observed with watch-lustre on ALC while running IOR with one OST inactive
on the MDS).

b=2733, b=2773, b=2529, b=2730, b=2819, b=2814, b=2822, b=1450, b=2676, b=2681
b=2817, b=2706, b=2816, b=1987, b=2884, b=1191, b=2809, b=2765, b=2805, b=1972

 - don't build mpi programs by default, as Bob's suggestion

 - another inode drop fix
 - fix a stupid error of last checkin