Branch b1_6
b=16492
i=umka
i=tappro

decay qos ost/oss penalties if MDS is not creating objects
i=nathan
i=johann

r=adilger,behlendorf1

- avoid div/mod in lustre_hash code

r=shadow,adilger

Lift 4G limit on stripe_size*stripe_count
4G limit on stripe_size remains in place, though.

r=tappro,wangdi

- fixes ost cleanup issue due to missed llcd_put() in the case ost does not receive disconnect from mds;

  - do not sleep on hanging llcd. Instead assert on it _after_ stopping recov_thread's ptlrpcd which should kill any remeining llcds;

  - fixes and cleanups, comments.

r=adilger,johann

- removes deadlock possibility by disabling rehash in hash_del() operations and moving hash_add()
out of spin_locks when calling. Hash table has own mechanisms for protecting its structures and it
also has hash_add_unique() method for using in concurrent run contexts;

- fixed missed lh_put() in hash_add_unique() which led to extra refs in some cases (extra ref to
export) and inability to cleanup;

- fixed __lustre_hash_set_theta() which set @max theta into ->lh_min_theta;

- in lustre_hash_rehash_size() disable rehash also for the case when new and old hash sizes equal
in corner cases (max_size or min_size). Before this fix it could be possible to do needless
rehashes when size is actually did not change but we do this expensive operation;

- disable rehash in hash_add_unique() if no actual add happened since entry with the same key is
already found in the table;

- some cleanups in hash table code;

b=16860
i=nathan
i=rread

Description: Excessive recovery window
Details    : With AT enabled, the recovery window can be excessively long (6000+
	     seconds). To address this problem, we no longer use
	     OBD_RECOVERY_FACTOR when extending the recovery window (the connect
	     timeout no longer depends on the service time, it is set to
	     INITIAL_CONNECT_TIMEOUT now) and clients report the old service
	     time via pb_service_time.

r=johann,shadow

- fixes ptlrpcd blocking on very long reply unlink waiting. To do so new rpc phase introduced
RQ_PHASE_UNREGISTERING in which request stay until we have reply_in_callback() called by lnet
signaling that reply is unlinked. All requests in this state are skipped in processing by prlrcd
instead of waiting n * 300s on each of them. This allows ptlrpcd to process other rpcs in the set;

- make sure that inflight count is coherent with being present on sending or delay list. That is,
if we see inflight != 0, rpc must be on one of these lists. This is very helpful in
ptlrpc_invalidate_import() to show all rpcs still waiting after invalidating import;

- in ptlrpc_invalidate_import() wait maximal rq_deadline - now from all inflight rpcs instead of
obd_timeout which may be much longer. If calculated timeout is 0, obd_timeout is used. This fixes
the issue that rq_deadline - now > obd_timeout (very easy to see in logs) which led to inflight !=
0 assert because inflight rpcs timed out later than our wait period is finished;

- in ptlrpc_invalidate_import() wait forever for rpcs in UNREGISTERING phase. Check in assert for
inflight == 0 for wait timed out case if no rpcs in UNREGISTERING phase. Only those in
UNREGISTERING phase are allowed to stay longer than obd_timeout;

- added ptlrpc_move_rqphase() function. All phase changes go through it. Add debug_req() there to
track down all phase changes;

- conf_sanity.sh test_45 added to emulate very long reply unlink and also situation when
rq_deadline - now > obd_timeout;

- do not wait forever in ptlrpc_unregister_reply() for async case (using it from sets). sync case
left unchanged;

- make sure that ptlrpc_set_next_timeout() yields 1s timeout (instead of 0s) for the set with rpcs
in "unregistering" stage to prevent ptlrpcd from sleeping forever and hanging in test_45;

- in ptlrpcd() make sure that we do not sleep on 0 timeout.

b=15715
r=adilger,green

Fixed the race of destroying and enqueuing a ldlm lock at OST side.

b=17493
i=Andreas Dilger
i=Johann Lombardi
handling of a broken readonly key

without protection.

Branch b1_6
b=16693
i=umka
i=tappro

b=1819
i=adilger
i=nathan

Add an import file to the osc, mdc, and mgc proc dir,
and include test for new proc file.

r=adilger,johann

- handle log_cancel resent correctly;
- some cleanups in llog.

Add in OBD_CONNECT flags from b1_8 so that they are not mistakenly used for
something else.

b=17403

i=adilger
i=yury.umanets
create objects in correct directory on OST.

b=17302
i=Johann Lombardi
i=ZhiYong Tian

pass QFMT through qc_id to be compatible with older Lustre versions

Backport warning fixes from b1_8.
i=girish (original patch)
i=robert

i=adilger
i=green
i=nikita

 - oss read-only cache feature

i=adilger
i=nathan
rename MAXPOOLNAME to LOV_MAXPOOLNAME

b=17309
i=johann

backport from bz 16266 for proper using write lock in lprocfs_remove().

r=adilger,tappro

- truncate last_rcvd for abort recovey case.

fix compiling error when CONFIG_QUOTA isn't set.
b=16481
i=shadow
i=panda

Fix writing over quota too much. Add a proc entry so that sync writes can
be triggered earlier, which improve accuracy of quota.
b=16642
i=johann
i=panda

i=nikita
i=robert
winnt libcfs/lnetcleanup

a=19432
i=manoj.joseph
i=vladimir.saveliev
add conf_param settings to mdd

b=17180
a=19402
i=nathan
i=johann
rename pools tests to a common base

b=17234
a=19563
i=yury.umanets
i=nathan
set pools for all MDTs for CMD

Branch HEAD
b=17157
i=johann
i=wangdi

r=adilger,tappro

- if aborting recovery, don't force sync IO to last_rcvd file

parallel llog init
Branch HEAD
b=16679
i=umka

Branch b1_6
b=17059
i=ZhiYong Tian
i=Johann Lombardi

Always build client with quota support

Branch b1_6
b=17157
i=johann
i=wangdi

r=adilger,shadow

- various CMD related fixes.

b=16771
i=adilger, johann

Use fix size timestamp instead of time_t in the cfg_marker and keep
compitibility for old cfg_marker on 32bit system.

b=16771
i=adilger, johann

Use fix size timestamp instead of time_t in the cfg_marker and keep
compitibility for old cfg_marker on 32bit system.

r=shadow

- final part of 16776 being already landed to 1.6.x after shadow's inspection.

r=shadow,vitaly,adilger,robert

- new class_hash.c. Using new hashtable for connections, quota, held locks on mds, etc.

- fix race of handling early reply in sptlrpc.
- port AT api changes from b1_8 (b16972)
b=16999
r=rread
r=wangdi

b=16788
i=adilger
i=nathan.rutman

add per-nid statistics on HEAD.

i=nathan
i=adilger
OST pools on HEAD, comprehensive patch including 17054:19007;
16935:18918,19012,19089,19128; 16978:18872

b=15949
i=adilger
i=shadow

mds_body.capability fix