if client will evicted at this time - we start invalidate
thread without reference to import and import can be freed
at same time.

Branch HEAD
b=17802
i=nathan
i=johann

b=16860
i=nathan
i=rread

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.

Fix broken whitespace in error message.

r=shadow,vitaly

- check rq_phase correctly in ptlrpc_expired_set() and couple of other places.

b=17176

fixed a bug in 14774 patch -- compare peer's nid instead of self's nid
in ptlrpc_connection during select failover MDS/OST nodes

i=deen

b=14166

r=johann,shadow

- fixes in ptlrcp to handle possible long reply unlink for HEAD.

b=11089
i=nathan.rutman
i=adilger

per-nid client statistics for MDT.

there. Actual usage will be in CLIO.
b=16450

b=16907
o=Brian Behlendorf <behlendorf1@llnl.gov>
i=yury.umanets
i=robert.read

Description: Prevent import from entering FULL state when server in recovery

r=vitaly,robert

- new class_hash.c and using it in conncetions, nids, etc. Using it for held locks on server will come shortly.

Branch HEAD
b=16611
i=green
i=rread

b=16098

Add URL for GPLv2 license in copyright headers

b=16098

change CFS license headers to Sun headers

b=15981
i=adilger
i=rread

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

fix KEY_IS macro

Branch HEAD
b=14032
i=umka
i=deen

Branch HEAD
b=15716
i=rread
i=tappro

- reverting part of 15716 as it causes constant assert and stops all testing. Shadow is informed and will clean this up shortly.

b=15716
i=rread
i=johann

always call deactivate import for imports without recovery.
b=15069
i=rread
i=wangdi
i=johan

b=14995
i=wangdi, rread

send activate event only for evicted imports.

move platform independed part of chksum into separate include
i=johann
i=green

ptlrpc connect with V2 message format.

b=13464
Set import disconnection before mgc reconnection, and refine the previous
13464 fix.
i=nathan,adilger

b=13805
i=ericm
i=bobijam

add support for several checksum algorithms. Currently, CRC32 and
Adler-32 are supported. The checksum type can be changed on the fly
through /proc/fs/lustre/osc/*/checksum_type.

b=14775
i=green
i=nathan
i=johann

b=13715
i=johann
i=nathan
i=adilger

protect accessing imp->generation w/ imp_lock.

to have two identical connections in imp_conn_list. We must
compare not conn's pointers but NIDs, otherwise we can defeat
connection throttling.

b=14774
i=adilger
i=johann

b=13537
i=umka
i=vitaly

i=yong.fan
i=rahul.deshmukh
i=nikita.danilov

- use req_capsule interface for client.
- add some interoperability support on server side.

- redesigned remote acl support, by FanYong
  b=11842
  r=pravin.shelar, eric.mei
- new sptlrpc configure interface
  b=13642
  r=yong.fan, rahul.deshmukh
- split kerberos keytab for lustre_root
  b=13873
  r=yong.fan, h.huang
- fix setuid for gss with linux keyring
  b=13899
  r=yong.fan, h.huang

b=13715
i=nathan
i=johann

* Activate import on intial connection.
* Don't let outdated timeout request invalidate import.

and exist connect request in flight, this can produce access to
NULL pointer (or already free pointer) when connect_interpret
store ocd flags in obd_namespace.

b=14260
i=adilger
i=johann

r=adilger,nathan
- enable/disable lru resize via proc.

  b:13816
  i:shadow,yury

r=vitaly,nikita
- landed lru resize code with all fixes and cleanups existing in 1_6.

land b1_8_gssfix (20070919_1543): various gss fixes (b11841)

b=12459
i=adilger,tianzy
i=scjody

Severity   : normal
Bugzilla   : 12459
Description: Client eviction due to failover config
Details    : after a connection loss, the lustre client should attempt to
	     reconnect to the last active server first before trying the
	     other potential connections.

i=tappro
i=fanyong
block reactivating mgc import until all deactivates complete
Only an issue when failing back MDT/MGS to itself (testing)