i=Nathan.Rutman
test_67b fix

let AT estimation cool down before doing AT tests.
b=16990
r=nathan

i=Tappro
several clients config fixed

b=16570
i=h.huang, robert.read

Make MDS_SETXATTR request replayable.

b=16570
i=robert.read, h.huang

Make MDS_SETXATTR request replayable.

i=Nathan.Rutman
restore the original at_max on all nodes

i=Nathan.Rutman
restore the original at_max on all nodes

i=Tappro
tests 20c, 32, 37 fixes: let pid to be killed

tests 20c, 32, 37 fixes: let pid to be killed

i=Tappro
test_34 fix: let pid to be killed

i=Tappro
test_34 fix: let pid to be killed

b=16570
i=h.huang

add a testcase on replaying setxattr op.

i=Adilger
test_70a: fix sed pattern

i=Adilger
test_70a: fix sed pattern

b=16002
i=wangdi

Add regression test for bug 13913.

Create subdirectory before trying to create files therein.
b=16369
i=johann

port Adaptive Timeouts from b1_6 to HEAD.
b=14071
r=nathan
r=adilger

i=Adilger
remove tdir creation from run_one: the test has to create tdir by
itself if it needs this dir

i=Adilger
remove tdir creation from run_one: the test has to create tdir by
itself if it needs this dir

r=nikita,shadow

- fixed handling for OBD_FAIL_$PREF_$OPC_NET fail_ids in mdt. Former code did not
check it correctly (due to typo with && instead of &) in mdt_req_handle() and
they all did not work. In same time, some handlers like mdt_close() and
mdt_enqueue() tried to check them again (result of some wrong fix) but again, did
it not correctly. They returned 0 error without doing anything. This should
have to emulate network failure. But as they did not allocate reply buffer and
returned 0 error, they caused rs != NULL assert in ptlrpc. Fxing this also fixed
replay-single.sh test_53* and replay_dual.sh test_12 and possibly others;

- removed checking for NET fail_id in mdt_close() and mdt_enqueue() - sources
of recent assert;

- added sanity check in mdt_req_handle() for any other invalid situation about
returning 0 error and not allocating reply buffers;

- removed mdt_reply(), move its one line call into mdt_req_handle(). This was
needed to simplify handling NET fail_ids in which case we should just return 0
and make sure that no reply is sent;

- comments and cleanups;

- in reply-dual.sh - remove test 8 from ALWAYS_EXCEPT. It passes in HEAD.
Originally for placed into ALWAYS_EXCEPT for old mds code and later moved to
HEAD test scripts but as mds in HEAD is completely new this bug is making any
sense there;

- in reply-single.sh - remove tests 0b 39 56 from ALWAYS_EXCEPT. They are
passing in HEAD. Also they are obsolete and related to closed bugs.

b=15929
i=grev

Cleanup PATH in tests so absolute paths are used, and
each path is added at most once.

b=15929
i=grev

Cleanup PATH in tests so absolute paths are used, and
each path is added at most once.

i=Adilger

rename subtests to skipping mechanism works properly

i=Adilger

rename subtests to skipping mechanism works properly

a better way to fix the script.
b=13659

fix test script: at_start return correct value.
b=13659
r=grev

r=adilger

to replace the sysctl lustre.* and lnet.* instances with lctl {get,set}_param

r=Andreas
 to replace the sysctl lustre.* and lnet.* instances with lctl {get,set}_param

do not drop replay according to msg flags, instead we check the
per-export recovery request queue for duplication of transno.
b=15756
r=adilger
r=rread

i=Adilger

config for several remote clients; replay-single test_70a, test_70b

i=Adilger

config file for several remote clients; replay-single test_70a, test_70b

r=Andreas

replace /proc/fs/lustre access with lctl set_param

r=Adilger

Changed replay-single.sh to use 'lctl {get,set}_param'

i=Adilger

replay-single test_61* fixes: set fail loc on all oss

change at_max according to AT status.
b=13659
r=nathan
r=rread
r=grev

i=Yury.Umanets
force test_66b to use FSNAME

i=Scjody
i=Adilger
multiop race fix

i=Scjody
i=Adilger
multiop race fix

only ignore error code of 67a, not 67b.
b=13721
r=nathan

because this bugs fixed already.