- fixes build issues

meta blocks ignored can lead to occasional -EDQUOT occasionally
b=16542
i=johann
i=alex.zhuravlev

  r=johann,shadow

  - handles -EINTR while waiting for lock + race with bl_ast;
  - adds sanityN.sh test_34 for testing/reproducing this situation.

b=16522
i=adilger
i=wangdi

enable OBD_CONNECT_MDT flag when connecting from the MDS so that
the OSTs know that the MDS "UUID" can be reused for the same export
from a different NID, so we do not need to wait for the export to be
evicted.

b=16522
i=adilger
i=wangdi

enable OBD_CONNECT_MDT flag when connecting from the MDS so that
the OSTs know that the MDS "UUID" can be reused for the same export
from a different NID, so we do not need to wait for the export to be
evicted.

b=17288

att=20766
i=adilger
i=rahul.deshmukh
i=nathan.rutman

ignore direct "trusted.{lma, link}" setting on client and server.

b=17465
i=adilger
i=johann

b=17855
i=huanghua, pravin

Revert patch as this breaks CMD. CMD uses child operations

Branch HEAD
b=16492
i=umka

b=17855
i=h.huang
i=tappro

mdo_{create,unlink} should use parent object's operations

i=johann
i=nathan
add pool refcount
replace rwlock with semaphore

i=andreas
i=nikita
i=nathan
i=manoj

Changelogs, a lightweight mechanism to track filesystem metadata and
namespace changes.

b=17644
i=green
i=adilger

send 1 extra rpc in flight if this is a high priority request

b=17461
i=adilger
i=alex.zhuravlev

Ptlrpc optimizations to minimize COS overhead:
. reply state object use own locking instead of ptlrpc service one
. per-cpu dedicated threads for reply handling
. resource hash table size increase

during refreshing locks waiting its I/O to complete,
take current service time into account, not only using
the timeout gotten by ldlm_get_enqueue_timeout

i=Andreas
i=Nathan.Rutman

b=17031

during refreshing locks waiting its I/O to complete,
take current service time into account, not only using
the timeout gotten by ldlm_get_enqueue_timeout

i=Andreas
i=Nathan.Rutman

b=17752
i=yury.umanets
i=tianzy

Disable quota support for CMD case temporary.

i=Nikita
i=umka

	compact FLD feature.

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.

b=12749
i=nathan,deen

Third of three patches for the root squash feature

map root UID/GID to UID/GID set via configuration parameter root_squash
with the exception for NID range set via configuration parameter nosquash_nids

b=12749
i=nathan,deen

Second of three patches for the root squash feature

This patch is to allow configuration parameters to contain spaces
It is accopmpished with
1. in mgs_write_log_params (renamed to mgs_write_log_param)
    assume the incoming string is a single parameter (the while loop is removed)
2. in mgs_write_log_target, call mgs_write_log_params for each parameter
a) new funcion class_get_next_param copies the entire next parameter into a temp buffer
   spaces are included if they are inside quotes (single or double)
   the first space outside of quotes is the terminator
   the quotes are stripped in the copy
   the copy is null-terminated
b) repeatedly call class_get_next_param and mgs_write_log_param in a loop from mgs_write_log_target

b=17153
i=johann, adilger

Remove 2.4 compatibility.

i=Huang hua
i=Rahul

This patch contains llo API interface change. Now it allows to create object
in specified path.
Fixes bug in object create in directory other than "/"
Adds llo unregister api.

support gss on mgc-mgs connection.
b=16054
r=umka
r=vitaly

rewrite part of sptlrpc configuration system to be able to interoperate
with 1.8.
b=15363
r=nathan
r=fanyong

r=shadow,panda

- fixes long sync bulk unlink in ptlrpcd which stops other rpcs from being handled and also causes asstion in umount time;

- make sure that long unlink wait is done with 1 sec interval to return quickly.

- fix previous wrong commit in part related to changes in ptlrpc_abort_bulk()

r=panda,shadow

- fixes possible sync long bulk unlink in ptlrpcd which would lead to assertion in forced umount time. Basically the fix is identical to 17310 where we move req to special phase UNREGISTERING and go processing other rpcs until bulk unlink is done;

- in sync bulk and reply unlink we check for wakeup condition every 1 sec to act quckly if unlink come instead of doing it every 20 sec as before.

b=16129
i=adilger
i=green

- a high priority request list is added into service;
- once a lock is canceled, all the IO requests, including coming
ones, under this lock, are moved into this list;
- PING is also added into this list;
- once a lock cancel timeout occurs, the timeout is prolonged
if there is an IO rpc under this lock;
- another request list is added into the export, used to speed up
the rpc-lock matching.

not send LOV EA under replay, we can't know about they size at this
time. Don't allow client connect to mds before any ost connected,
for avoid problems with LOV EA size and returning EIO to client.

Branch HEAD
b=16080
i=umka
i=tappro

b=16129
i=adilger
i=green

- a high priority request list is added into service;
- once a lock is canceled, all the IO requests, including coming
ones, under this lock, are moved into this list;
- PING is also added into this list;
- once a lock cancel timeout occurs, the timeout is prolonged
if there is an IO rpc under this lock;
- another request list is added into the export, used to speed up
the rpc-lock matching.

r=shadow,panda

- fixes race in ptlrpcd caused busy obd and inability to cleanup;
- cleanups and debugs in llcd code.

r=panda,shadow

- fixes race in ptlrpcd which leads to busy import and obd;
- cleanups and debugs in llcd code.

b=11826
i=nikita
i=adilger

Branch b1_6
b=16492
i=umka
i=tappro

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

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

b=13058
i=johann
i=yury.umanets

reserve some space in mdt_body and mdt_rec_xxx structures and add
MDS_SETATTR64_REC to allow possible expansion of uid/gid to 64 bits
in the future.
b=17601
r=adilger
r=huanghua
r=fanyong

r=adilger,behlendorf1

- avoid div/mod in lustre_hash code