b=14289
i=johann
i=scjody

Update to RHEL5 Update-1 kernel-2.6.18-53.el5.

b=14265
i=deen
i=scjody

Fix build failes for RHEL3.

b=14138
r=adilger, nikita

resolve deadlock on i_size_read() introduced by race condition of i_size_write();
Use old size assignment to avoid deadlock (bz14326).

b=14156

Use b1_8_iam tag for b_mount_perm branch.

CVSe --------------------------------------------------------------------- Entero Log.  Lines beginning with `CVS:' are removed automatically

i=Adilger

wait delete completed before check kbytesavail

update from HEAD (20071213_1836)

b=12974
i=nikita
i=adilger

1) set as "inline" for such large function ("obd_fail_check()") is not suitable,
   replaced with normal function "__obd_fail_check_set()".
2) atomic operations for obd_fail_count (replace "static count" in obd_fail_check).
3) use "test_and_set_bit()" for "OBD_FAILED/OBD_FAIL_ONCE" check and set to avoid
   unexpected racing condition between multi-thread ops.
4) some cleanup for OBD_FAIL_XXX macro.

b=13377
i=umka
i=nikita

"comments" patch.

b=11842

Use b1_8_iam tag for b_remote_acl branch.

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

b=14418
i=green
i=johann

b=12211
i=green, adilger

commit the missing part and use a proper macro (thanks shadow for finding it out).

b=12211
i=green, adilger

Description: make lustre randomly fail allocating memory
Details    : Make lustre randomly failed allocating memory for testing purpose.

i=Adilger

report the slow and excluded tests separately

b=12646
i=johann, shadow

Add opc parameter to ost_checksum_bulk().

i=Adilger

force test_5c to use mount_client

i=Adilger

typo fixed (found by Huang Hua)

i=Adilger

test_29 cleanup

r=adilger,shadow,deen
- enable OBD_CONNECT_LRU_RESIZE only if lru resize is enabled in configure time.

b=13563
i=green
i=shadow

does not check for LDLM_FL_BL_AST in ldlm_cli_cancel(),
as this is already a CANCEL rpc, no separate rpc is needed.

r=nikita,adilger,shadow

- lots of fixes and cleanups in ldlm pools code.

-   NULL md_me in lnet_md_unlink().
-   iterate ptl_ml safely since 'me' can be removed within the loop.

use b1_8_iam ldiskfs for b_mixed_layout_req.

b=13843
i=adilger
i=nathan

Dynamically create DLM blocking callback threads
+ fix an issue with MacOS implementation of atomic_sub_and_test().

b=13317
r=shadow, johann

enable liblustre to connect to mds with acl

b=13843
i=adilger
i=nathan

Dynamically create DLM blocking callback threads
+ fix an issue with MacOS implementation of atomic_sub_and_test().

b=13397
i=adilger
i=alex

-- Use GFP_NOFS instead of SLAB_NOFS.
-- Avoid fork the ext3-mballoc3-core patch.

add sles10 support.

actualy finished recovery (mds_postrecov->mds_notify code path).
Always set next id if we ask ost about last id, this fixes problems from
bug 14222.

b=12702
i=tappro
i=yury.umanets

b=13284
r=green,issac

Fixed the problem that the memory trace can't work in interrupt context.

Walking on eggs to land a patch, hope it works.

b=14208
i=zhenyu.xu, johann

Original patch by Brian Behlendorf <behlendorf1@llnl.gov>

Replace macro __LINUX__ with __linux__.

b=14208
i=zhenyu.xu, johann

Replace macro __LINUX__ with __linux__.

b=12829
i=adilger
i=bobijam

When CRAY_XT3 is defined, the fsgid supplied by the client is
overridden with the primary group provided by the group upcall,
whereas the supplied fsgid can be trusted if it is in the list of
supplementary groups returned by the group upcall.