land 10800(adding llog ctxt refcount) to b1_6.
b=10800
i=green
i=shadow

i=brian
add ONLY, debugsave
fix iozone test size
remove some test output

Modify test-framework tests to run on real hardware - based on a patch
by Nic Henke <nic@cray.com>

b=11217
i=mjmac
i=nathan

Remove the extra checkstat call, which should have been removed with the
landing of the original patch.
b=10818 b=12623
i=scjody
i=nathan

The catlog should be initialized anyway even in recovery.
b=12086
i=nathan
i=adilger

Minor cleanups to tests, improved error messages.
b=12560
i=scjody

Fix lov_mds_md in mdd_create_objects error handler.
Checking whether obd_fail before fsfilt_start.
Free fcc no matter whether fsfilt_commit success or failed.
b=10818
i=adilger
i=green

fix broken test

r=wangdi,adigler

Take import reference before releasing llog record semaphore

- regression test for the case

shouldn't touch this.

fixes:
* previous implementation doesn't support multi-open/truncate by different
  users on the same inode.
* update DLD.
* cleanup.

 - open file by fid in REPLAY|RESENT case because parent can disapper by
   that time

- setting owner/group on OSS (needed for quotas)

- some fixes:
  - deadlock on soc client lock.
  - idr_remove() issue.
  - forwarding to wrong MDS in lmv_link()
  - f_dput(dentry) before using it in filter_lvbo_update()
  - filter_sync() assert(group > 0) due to missed GROUP flag oa->o_valid in ll_fsync().
  - cleanups, comments and more debugging messages.
  - jump to wrong label in mds_create_objects() on error path.
  - few missed/wrong ENTRY/RETURN things

sanityN, sanity-ldlm.

replace mds1 with SINGLEMDS according to andreas advice

some fix in replay-single.sh
b:6068

 * remote uid/gid handling
 * various gss fixes
 * fix broken local ACL

r=adilger

- replay of unlink. landed for testing on china cluster

I've seen the "server went back in time" message while testing HEAD,
so this will fix that.  Patch already on 1.4.

- Fix insanity.sh, still using the insanity-local.sh config by default.
- More cleanups in replay-single.sh. We need to generalize failures a
bit more, so we can choose a different mds each time, if more than one
is available.

Fix replay-single.sh and recovery-small.sh so they can run with the
default lmv config or "-f cfg/local.sh" config.

- b1_4 is basically the parent of HEAD, because that's the direction
  that changes flow, as strange as that sounds.  so there's a
  HEAD_BASE tag which sits on b1_4

b_cmobd_merge should not be used for any further development or testing!

cMD_PRE_CMD_SMASH are the relevant tags.

The pre-smashing contents of HEAD will be committed by yury into b_cmd as a
merge of the two branches.  These will be stabilized on b_cmd and eventually
landed onto HEAD.

b=2094, b=3138, b=3335, b=3274, b=3293, b=2862, b=3147, b=2350, b=3313
b=3265, b=3315, b=3301, b=3325, b=3329, b=3125, b=3098

b=3284, b=3285, b=3043, b=3236, revert liblustre group changes

b=3043, b=3258, b=3219, b=2410

r=zab (partial)

Better handling for OST eviction.  Fixes for clearing the page cache,
imp_invalid handling, and improved import_event interface. Also
includes the tests and fixes added from 2732; one of those tests does
not yet passed so it is excepted for now.

Protect conn_cnt check and update with exp_lock in
target_handle_connect.

Add a test to replay since, and add an OBD_FAIL style macro to create
a race condition in a specific location called OBD_RACE.

the individual OSC to recover on it's own.

b=1530