linux-stable.git/fs/ext4/ext4.h, branch linux-3.3.y

ext4: address scalability issue by removing extent cache statistics

2012-04-22T22:38:56+00:00

commit 9cd70b347e9761ea2d2ac3d758c529a48a8193e6 upstream.

Andi Kleen and Tim Chen have reported that under certain circumstances
the extent cache statistics are causing scalability problems due to
cache line bounces.

Signed-off-by: "Theodore Ts'o" 
Signed-off-by: Greg Kroah-Hartman

ext4: fix race between sync and completed io work

2012-04-02T17:32:20+00:00

commit 491caa43639abcffaa645fbab372a7ef4ce2975c upstream.

The following command line will leave the aio-stress process unkillable
on an ext4 file system (in my case, mounted on /mnt/test):

aio-stress -t 20 -s 10 -O -S -o 2 -I 1000 /mnt/test/aiostress.3561.4 /mnt/test/aiostress.3561.4.20 /mnt/test/aiostress.3561.4.19 /mnt/test/aiostress.3561.4.18 /mnt/test/aiostress.3561.4.17 /mnt/test/aiostress.3561.4.16 /mnt/test/aiostress.3561.4.15 /mnt/test/aiostress.3561.4.14 /mnt/test/aiostress.3561.4.13 /mnt/test/aiostress.3561.4.12 /mnt/test/aiostress.3561.4.11 /mnt/test/aiostress.3561.4.10 /mnt/test/aiostress.3561.4.9 /mnt/test/aiostress.3561.4.8 /mnt/test/aiostress.3561.4.7 /mnt/test/aiostress.3561.4.6 /mnt/test/aiostress.3561.4.5 /mnt/test/aiostress.3561.4.4 /mnt/test/aiostress.3561.4.3 /mnt/test/aiostress.3561.4.2

This is using the aio-stress program from the xfstests test suite.
That particular command line tells aio-stress to do random writes to
20 files from 20 threads (one thread per file). The files are NOT
preallocated, so you will get writes to random offsets within the
file, thus creating holes and extending i_size. It also opens the
file with O_DIRECT and O_SYNC.

On to the problem. When an I/O requires unwritten extent conversion,
it is queued onto the completed_io_list for the ext4 inode. Two code
paths will pull work items from this list. The first is the
ext4_end_io_work routine, and the second is ext4_flush_completed_IO,
which is called via the fsync path (and O_SYNC handling, as well).
There are two issues I've found in these code paths. First, if the
fsync path beats the work routine to a particular I/O, the work
routine will free the io_end structure! It does not take into account
the fact that the io_end may still be in use by the fsync path. I've
fixed this issue by adding yet another IO_END flag, indicating that
the io_end is being processed by the fsync path.

The second problem is that the work routine will make an assignment to
io->flag outside of the lock. I have witnessed this result in a hang
at umount. Moving the flag setting inside the lock resolved that
problem.

The problem was introduced by commit b82e384c7b ("ext4: optimize
locking for end_io extent conversion"), which first appeared in 3.2.
As such, the fix should be backported to that release (probably along
with the unwritten extent conversion race fix).

Signed-off-by: Jeff Moyer
Signed-off-by: "Theodore Ts'o"
Signed-off-by: Greg Kroah-Hartman

ext4: fix race between unwritten extent conversion and truncate

2012-04-02T17:32:20+00:00

commit 266991b13890049ee1a6bb95b9817f06339ee3d7 upstream.

The following comment in ext4_end_io_dio caught my attention:

	/* XXX: probably should move into the real I/O completion handler */
        inode_dio_done(inode);

The truncate code takes i_mutex, then calls inode_dio_wait.  Because the
ext4 code path above will end up dropping the mutex before it is
reacquired by the worker thread that does the extent conversion, it
seems to me that the truncate can happen out of order.  Jan Kara
mentioned that this might result in error messages in the system logs,
but that should be the extent of the "damage."

The fix is pretty straight-forward: don't call inode_dio_done until the
extent conversion is complete.

Reviewed-by: Jan Kara 
Signed-off-by: Jeff Moyer 
Signed-off-by: "Theodore Ts'o" 
Signed-off-by: Greg Kroah-Hartman

Merge branch 'for_linus' into for_linus_merged

2012-01-10T16:54:07+00:00

Conflicts:
	fs/ext4/ioctl.c

ext4: make more symbols static

2012-01-05T03:33:28+00:00

A couple more functions can reasonably be made static if desired.

Signed-off-by: Eric Sandeen 
Signed-off-by: "Theodore Ts'o"

ext4: reserve new feature flag codepoints

2012-01-05T03:01:53+00:00

Reserve the ext4 features flags EXT4_FEATURE_RO_COMPAT_METADATA_CSUM,
EXT4_FEATURE_INCOMPAT_INLINEDATA, and EXT4_FEATURE_INCOMPAT_LARGEDIR.

Signed-off-by: "Theodore Ts'o"

ext4: add new online resize interface

2012-01-04T22:09:44+00:00

This patch adds new online resize interface, whose input argument is a
64-bit integer indicating how many blocks there are in the resized fs.

In new resize impelmentation, all work like allocating group tables
are done by kernel side, so the new resize interface can support
flex_bg feature and prepares ground for suppoting resize with features
like bigalloc and exclude bitmap. Besides these, user-space tools just
passes in the new number of blocks.

We delay initializing the bitmaps and inode tables of added groups if
possible and add multi groups (a flex groups) each time, so new resize
is very fast like mkfs.

Signed-off-by: Yongqiang Yang 
Signed-off-by: "Theodore Ts'o"

ext4: add a function which sets up group blocks of a flex bg

2012-01-04T04:32:52+00:00

This patch adds a function named setup_new_flex_group_blocks() which
sets up group blocks of a flex bg.

Signed-off-by: Yongqiang Yang 
Signed-off-by: "Theodore Ts'o"

ext4: propagate umode_t

2012-01-04T03:54:59+00:00

Signed-off-by: Al Viro

ext4: use proper little-endian bitops

2011-12-29T01:32:07+00:00

ext4_{set,clear}_bit() is defined as __test_and_{set,clear}_bit_le() for
ext4.  Only two ext4_{set,clear}_bit() calls check the return value.  The
rest of calls ignore the return value and they can be replaced with
__{set,clear}_bit_le().

This changes ext4_{set,clear}_bit() from __test_and_{set,clear}_bit_le()
to __{set,clear}_bit_le() and introduces ext4_test_and_{set,clear}_bit()
for the two places where old bit needs to be returned.

This ext4_{set,clear}_bit() change is considered safe, because if someone
uses these macros without noticing the change, new ext4_{set,clear}_bit
don't have return value and causes compiler errors where the return value
is used.

This also removes unused ext4_find_first_zero_bit().

Signed-off-by: Akinobu Mita 
Signed-off-by: Andrew Morton 
Signed-off-by: "Theodore Ts'o"