Checking intent error before release open handle.
b=11935
i=adilger
i=green

Connect the echo client with the separate REQPORTAL feature.
This ensures that IO requests are sent to the IO portal, since liblustre
clients (and eventually 1.8) default to connecting to the REQPORTAL and
will send IO requests there incorrectly.
b=11813
i=green
i=shadow

Accept the old ost_num_threads parameter but warn that it
is deprecated, and fix an off-by-one error that caused an LBUG.

Original patch by adilger.

b=12470
i=nathan
i=scjody

i=nathan
i=adilger
don't unlock twice.  patch by wangdi

i=scjody
i=brian
modify do_node to work remotely

Add grant check in sanityN.sh for each test case.
b=11662
i=adilger
i=green

Grant the space immediately for ungrant I/O req to avoid grant space > left
available space.
b=11662
i=adilger
i=green

clear grant info when osc do resent and replay bulk write.
b=11662
i=adilger
i=green

i=adilger
i=Johann

Remove the #ifdef HAVE_DISK_INODE_VERSION in lustre_fsfilt.h and have the fsfilt_{get, set}_version return -EOPNOTSUPP if the operation is not supported.

Branch: b1_6
The dir might have multi-aliases, the subdir of all of these aliases should
be iterated and its subdir negative dentries should be dropped.
b=12123
i=green
i=shadow

Use ext3_journal_start/stop (through fsfilt_ext3_journal_start/stop())
instead of journal_start/stop.
+ Fix SLES9 build issue.

b=11743
i=alex
i=adilger

Minor cleanups to tests, improved error messages.
b=12560
i=scjody

Fix /proc/fs/lustre/devices on PPC systems.
b=12234
i=nathan
i=scjody

better "options lnet" grabbing

Add comment about where the default stripe counts are derived.
Whitespace cleanups.

Don't run filter_grant_sanity_check for more than 100 exports
to improve scaling for large numbers of clients.

b=10291
i=wangdi
i=adilger

r=adilger (original patch and inspection of updates to it)
Some updates so that acceptance-small.sh can be run on a patchless client
using a remote OST and MDT.
Credit goes to adilger.  Most of this is his work.  I just shepherded it
through the process.
My batch of updates to the same end is still to come.  Still to be inspected
in fact.

Print better error messages to understand where test failures are being hit.
b=12557

Clear iobuf->dr_error between two uses.

b=11722
i=green
i=adilger

r=Nathan

Correct the bugs with llanalyze script

fix wrong bug no in ChangeLog

Reverve patch from bug 11743 since it breaks SLES9 build.
For the record, the revision associated to the commit was 1.176.2.14.

b=11743

Add the QUOTA mount option on the fly for kernel newer than 2.6.12.
Add a call to fsfilt_setup() in filter_common_setup().

b=12538
i=alex
i=adilger

Use ext3_journal_start/stop (through fsfilt_ext3_journal_start/stop())
instead of journal_start/stop

b=11743
i=alex
i=adilger

The 11737 patch causes various kernel crashes; see bug 12549.
Verified by nathan and adilger.
Reverting.

Allow runtests to run with a non-local config.
b=12499

Update multiop to do aligned read/write for O_DIRECT files.
b=11737

Quiet signed-vs-unsigned pointer warning.

ll_removepage

b=11817
i=shadow
i=adilger

i=nathan
i=scjody
Use friendly hostname in mtab

i=kalpak
cleanup stats on error exit

Fix lov_mds_md in mdd_create_objects error handler.
Checking whether obd_fail before fsfilt_start.
Free fcc no matter whether fsfilt_commit success or failed.
b=10818
i=adilger
i=green

Clear the grant when disconnect the import to prevent the grant being erased
wrongly when the import is evicted.
b=12371
i=green
i=adilger

fix broken test

rather than requested size.

b=11737
i=green
i=shadow

b=11691
i=adilger
i=scjody
deactivate 1.6 mgc to stop reconnect attempts with 1.4 servers

patch you can cause a node to crash when reading from
/proc/scsi/sd_iostats/sdX

b=11654
i=shadow
i=deen

b=10935
r=green(original autor)

Quiet compile warning when CONFIG_LSF is on (large single file).

Make sure that the unlinked file actually releases all of the blocks on
disk, otherwise the next test may fail with ENOSPC.
b=12507