b=3462
i=adilger, johann

Description: Fix a replay issue
Details    : In some cases, older replay request will revert the
             mcd->mcd_last_xid on MDS which is used to record the client's
             latest sent request.

i=nathan.rutman

force AT tests to be more flexible with /sys files

i=adilger
except until fixed

i=Adilger

Use TESTSUITE in tdir

b=12599
i=Nathan

lost fix

i=johann, deen

replay-single tests: |X| open and close req or reply while two MDC requests
in flight

i=Nathan
i=Huanghua

test_50 fix for remote mds

i=adilger
i=eeb
Track actual lock callback times, instead of the rpc times, for setting ldlm
timeouts.  Add a module parameter for the minimum lock wait time.
Also add a module parameter for a minimum AT time in general.

i=Nathan
i=Scjody

use multiop instead of exec

b=13659
i=nathan

enable D_OTHER (= D_ADAPTTO) for AT test.

i=adilger
i=green
send early replies even after we've packed the final reply.

i=Adilger

Wait recovery complete before AFTERUSED is checked.

i=Nathan

get rid of "./"

i=green
changes from eeb's inspection

i=adilger
i=eeb (pending)
adaptive timeouts

b=13367
i=Adilger
i=Nathan

t-f skip(); use logs for all test scripts
hepler remote_mds() remote_ost()

cleanup sanity test scripts and move some common funcs to test-frame.sh.
b=12599
i=adilger
i=brian
i=mjmac

i=Adilger
i=Shadow

replay-dual, replay-single, sanityN cleanup (patchless unrelated)

i=Nathan

Correct replay-dual, replay-single ALWAYS_EXCEPT list.

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