Hi,

Some workloads issue batches of small I/O, and the performance is poor
due to the call to blk_run_address_space for every single iocb.  Nathan
Roberts pointed this out, and suggested that by deferring this call
until all I/Os in the iocb array are submitted to the block layer, we
can realize some impressive performance gains (up to 30% for sequential
4k reads in batches of 16).
Signed-off-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Hi,

The WRITE_ODIRECT flag is only used in one place, and that code path
happens to also call blk_run_address_space.  The introduction of this
flag, then, could result in the device being unplugged twice for every
I/O.

Further, with the batching changes in the next patch, we don't want an
O_DIRECT write to imply a queue unplug.
Signed-off-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Commit a9327cac added seperate read
and write statistics of in_flight requests. And exported the number
of read and write requests in progress seperately through sysfs.

But  Corrado Zoccolo <czoccolo@gmail.com> reported getting strange
output from "iostat -kx 2". Global values for service time and
utilization were garbage. For interval values, utilization was always
100%, and service time is higher than normal.

So this was reverted by commit 0f78ab98

The problem was in part_round_stats_single(), I missed the following:
        if (now == part->stamp)
                return;

-       if (part->in_flight) {
+       if (part_in_flight(part)) {
                __part_stat_add(cpu, part, time_in_queue,
                                part_in_flight(part) * (now - part->stamp));
                __part_stat_add(cpu, part, io_ticks, (now - part->stamp));

With this chunk included, the reported regression gets fixed.
Signed-off-by: NNikanth Karthikesan <knikanth@suse.de>

--
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This reverts commit a9327cac.

Corrado Zoccolo <czoccolo@gmail.com> reports:

"with 2.6.32-rc1 I started getting the following strange output from
"iostat -kx 2":
Linux 2.6.31bisect (et2) 	04/10/2009 	_i686_	(2 CPU)

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
          10,70    0,00    3,16   15,75    0,00   70,38

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s
avgrq-sz avgqu-sz   await  svctm  %util
sda              18,22     0,00    0,67    0,01    14,77     0,02
43,94     0,01   10,53 39043915,03 2629219,87
sdb              60,89     9,68   50,79    3,04  1724,43    50,52
65,95     0,70   13,06 488437,47 2629219,87

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           2,72    0,00    0,74    0,00    0,00   96,53

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s
avgrq-sz avgqu-sz   await  svctm  %util
sda               0,00     0,00    0,00    0,00     0,00     0,00
0,00     0,00    0,00   0,00 100,00
sdb               0,00     0,00    0,00    0,00     0,00     0,00
0,00     0,00    0,00   0,00 100,00

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           6,68    0,00    0,99    0,00    0,00   92,33

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s
avgrq-sz avgqu-sz   await  svctm  %util
sda               0,00     0,00    0,00    0,00     0,00     0,00
0,00     0,00    0,00   0,00 100,00
sdb               0,00     0,00    0,00    0,00     0,00     0,00
0,00     0,00    0,00   0,00 100,00

avg-cpu:  %user   %nice %system %iowait  %steal   %idle
           4,40    0,00    0,73    1,47    0,00   93,40

Device:         rrqm/s   wrqm/s     r/s     w/s    rkB/s    wkB/s
avgrq-sz avgqu-sz   await  svctm  %util
sda               0,00     0,00    0,00    0,00     0,00     0,00
0,00     0,00    0,00   0,00 100,00
sdb               0,00     4,00    0,00    3,00     0,00    28,00
18,67     0,06   19,50 333,33 100,00

Global values for service time and utilization are garbage. For
interval values, utilization is always 100%, and service time is
higher than normal.

I bisected it down to:
[a9327cac] Seperate read and write
statistics of in_flight requests
and verified that reverting just that commit indeed solves the issue
on 2.6.32-rc1."

So until this is debugged, revert the bad commit.
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

On a 256M filesystem, doing this in a loop:

        xfs_io -F -f -d -c 'pwrite 0 64m' test
        rm -f test

eventually leads to ENOSPC.  (the xfs_io command does a
64m direct IO write to the file "test")

As with other block allocation callers, it looks like we need to
potentially retry the allocations on the initial ENOSPC.
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This fixes the following warning:

fs/ext4/inode.c: In function 'ext4_dirty_inode':
fs/ext4/inode.c:5615: warning: unused variable 'current_handle'

We remove the jbd_debug() statement which does use current_handle, as
it's not terribly important in the grand scheme of things.

Thanks to Stephen Rothwell for pointing this out.
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

It's just a wrapper for <linux/fscache.h>, so remove it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NDavid Howells <dhowells@redhat.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

[akpm@linux-foundation.org: fix KVM]
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Acked-by: NMike Frysinger <vapier@gentoo.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

There is a problem where page_mkwrite can be called on a dirtied page that
already has a delalloc range associated with it.  The fix is to clear any
delalloc bits for the range we are dirtying so the space accounting gets
handled properly.  This is the same thing we do in the normal write case, so we
are consistent across the board.  With this patch we no longer leak reserved
space.
Signed-off-by: NJosef Bacik <jbacik@redhat.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

As mentioned in Documentation/CodingStyle, move EXPORT* macro's
to the line immediately after the closing function brace line.
Signed-off-by: NH Hartley Sweeten <hsweeten@visionengravers.com>
Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

Use filemap_fdatawrite_range and filemap_fdatawait_range instead of
local copies of the functions.  For filemap_fdatawait_range that
also means replacing the awkward old wait_on_page_writeback_range
calling convention with the regular filemap byte offsets.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs_file_write was incorrectly calling generic_write_checks without
taking i_mutex.  This lead to problems with racing around i_size when
doing O_APPEND writes.

The fix here is to move i_mutex higher.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

wait_on_page_writeback_range/btrfs_wait_on_page_writeback_range takes
a pagecache offset, not a byte offset into the file.  Shift the arguments
around to wait for the correct range
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Kconfig & super.c promised it'd be gone by 2.6.31, so it's
about time to drop it.
Signed-off-by: NEric Sandeen <sandeen@redhat.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

In ext4_num_dirty_pages() we were calling page_buffers() before
checking to see if the page actually had pages attached to it; this
would cause a BUG check crash in the inline function page_buffers().

Thanks to Markus Trippelsdorf for reporting this bug.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

"Looking at ext4.h, I think the setting of extra time fields forgets to
mask the epoch bits so the epoch part overwrites nsec part. The second
change is only for coherency (2 -> EXT4_EPOCH_BITS)."

Thanks to Damien Guibouret for pointing out this problem.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

The /proc/fs/jbd2/<dev>/history was maintained manually; by using
tracepoints, we can get all of the existing functionality of the /proc
file plus extra capabilities thanks to the ftrace infrastructure.  We
save memory as a bonus.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

The /proc/fs/ext4/<dev>/mb_history was maintained manually, and had a
number of problems: it required a largish amount of memory to be
allocated for each ext4 filesystem, and the s_mb_history_lock
introduced a CPU contention problem.  

By ripping out the mb_history code and replacing it with ftrace
tracepoints, and we get more functionality: timestamps, event
filtering, the ability to correlate mballoc history with other ext4
tracepoints, etc.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

If an ioctl-initiated transaction is open, we can't force a commit during
the free space checks in order to free up pinned extents or else we
deadlock.  Just ENOSPC instead.

A more satisfying solution that reserves space for the entire user
transaction up front is forthcoming...
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Fix leak of vfsmount write reference and open_ioctl_trans reference on
ENOMEM.  Clean up the error paths while we're at it.
Signed-off-by: NSage Weil <sage@newdream.net>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

There are a number of kernel printk's which are printed when an ext4
filesystem is mounted and unmounted.  Disable them to economize space
in the system logs.  In addition, disabling the mballoc stats by
default saves a number of unneeded atomic operations for every block
allocation or deallocation.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

We've already defined CONFIG_BTRFS_POSIX_ACL in Kconfig, but we're
currently not using it and are testing CONFIG_FS_POSIX_ACL instead.
CONFIG_FS_POSIX_ACL states "Never use this symbol for ifdefs".
Signed-off-by: NChris Ball <cjb@laptop.org>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Error handling code following a kzalloc should free the allocated data.

The semantic match that finds the problem is as follows:
(http://www.emn.fr/x-info/coccinelle/)

// <smpl>
@r exists@
local idexpression x;
statement S;
expression E;
identifier f,f1,l;
position p1,p2;
expression *ptr != NULL;
@@

x@p1 = \(kmalloc\|kzalloc\|kcalloc\)(...);
...
if (x == NULL) S
<... when != x
     when != if (...) { <+...x...+> }
(
x->f1 = E
|
 (x->f1 == NULL || ...)
|
 f(...,x->f1,...)
)
...>
(
 return \(0\|<+...x...+>\|ptr\);
|
 return@p2 ...;
)

@script:python@
p1 << r.p1;
p2 << r.p2;
@@

print "* file: %s kmalloc %s return %s" % (p1[0].file,p1[0].line,p2[0].line)
// </smpl>
Signed-off-by: NJulia Lawall <julia@diku.dk>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

We currently set sb->s_flags |= MS_POSIXACL unconditionally, which is
incorrect -- it tells the VFS that it shouldn't set umask because we
will, yet we don't set it ourselves if we aren't using POSIX ACLs, so
the umask ends up ignored.
Signed-off-by: NChris Ball <cjb@laptop.org>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This patch fixes a problem with handling nested calls to
ext4_journal_start/ext4_journal_stop, when there is no journal present.
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This patch a problem that ext4_dirty_inode() was not calling
ext4_mark_inode_dirty() if the current_handle is not valid, which it
is the case in no journal mode.

It also removes a test for non-matching transaction which can never
happen.
Signed-off-by: NCurt Wohlgemuth <curtw@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

This is a cleanup of commit 91ac6f43.  Since ext4_mark_inode_dirty()
has already called ext4_mark_iloc_dirty(), which in turn calls
ext4_do_update_inode(), it's not necessary to have ext4_write_inode()
call ext4_do_update_inode() in no journal mode.  Indeed, it would be
duplicated work.
Reviewed-by: N"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: NFrank Mayhar <fmayhar@google.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

The i_dir_start_lookup field in nilfs_inode_info objects should be
cleared when the objects are allocated, but the the initialization was
missing in case of reading from disk.  This adds the initialization.

Since the variable just gives a start page on directory lookups, the
bug was nonfatal until now.
Signed-off-by: NRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>

This will fix file system corruption which infrequently happens after
mount.  The problem was reported from users with the title "[NILFS
users] Fail to mount NILFS." (Message-ID:
<200908211918.34720.yuri@itinteg.net>), and so forth.  I've also
experienced the corruption multiple times on kernel 2.6.30 and 2.6.31.

The problem turned out to be caused due to discordance between
mapping->nrpages of a btree node cache and the actual number of pages
hung on the cache; if the mapping->nrpages becomes zero even as it has
pages, truncate_inode_pages() returns without doing anything.  Usually
this is harmless except it may cause page leak, but garbage collection
fairly infrequently sees a stale page remained in the btree node cache
of DAT (i.e. disk address translation file of nilfs), and induces the
corruption.

I identified a missing initialization in btree node caches was the
root cause.  This corrects the bug.

I've tested this for kernel 2.6.30 and 2.6.31.
Reported-by: NYuri Chislov <yuri@itinteg.net>
Signed-off-by: NRyusuke Konishi <konishi.ryusuke@lab.ntt.co.jp>
Cc: stable <stable@kernel.org>

At the start of a transaction we do a btrfs_reserve_metadata_space() and
specify how many items we plan on modifying.  Then once we've done our
modifications and such, just call btrfs_unreserve_metadata_space() for
the same number of items we reserved.

For keeping track of metadata needed for data I've had to add an extent_io op
for when we merge extents.  This lets us track space properly when we are doing
sequential writes, so we don't end up reserving way more metadata space than
what we need.

The only place where the metadata space accounting is not done is in the
relocation code.  This is because Yan is going to be reworking that code in the
near future, so running btrfs-vol -b could still possibly result in a ENOSPC
related panic.  This patch also turns off the metadata_ratio stuff in order to
allow users to more efficiently use their disk space.

This patch makes it so we track how much metadata we need for an inode's
delayed allocation extents by tracking how many extents are currently
waiting for allocation.  It introduces two new callbacks for the
extent_io tree's, merge_extent_hook and split_extent_hook.  These help
us keep track of when we merge delalloc extents together and split them
up.  Reservations are handled prior to any actually dirty'ing occurs,
and then we unreserve after we dirty.

btrfs_unreserve_metadata_for_delalloc() will make the appropriate
unreservations as needed based on the number of reservations we
currently have and the number of extents we currently have.  Doing the
reservation outside of doing any of the actual dirty'ing lets us do
things like filemap_flush() the inode to try and force delalloc to
happen, or as a last resort actually start allocation on all delalloc
inodes in the fs.  This has survived dbench, fs_mark and an fsx torture
test.
Signed-off-by: NJosef Bacik <jbacik@redhat.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Move the check to make sure the original and donor inodes are
different earlier, to avoid a potential deadlock by trying to lock the
same inode twice.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

For async direct IO that covers holes or fallocate, the end_io
callback function now queued the convertion work on workqueue but
don't flush the work rightaway as it might take too long to afford.

But when fsync is called after all the data is completed, user expects
the metadata also being updated before fsync returns.

Thus we need to flush the conversion work when fsync() is called.
This patch keep track of a listed of completed async direct io that
has a work queued on workqueue.  When fsync() is called, it will go
through the list and do the conversion.
Signed-off-by: NMingming Cao <cmm@us.ibm.com>

Currently the DIO VFS code passes create = 0 when writing to the
middle of file.  It does this to avoid block allocation for holes, so
as not to expose stale data out when there is a parallel buffered read
(which does not hold the i_mutex lock).  Direct I/O writes into holes
falls back to buffered IO for this reason.

Since preallocated extents are treated as holes when doing a
get_block() look up (buffer is not mapped), direct IO over fallocate
also falls back to buffered IO.  Thus ext4 actually silently falls
back to buffered IO in above two cases, which is undesirable.

To fix this, this patch creates unitialized extents when a direct I/O
write into holes in sparse files, and registering an end_io callback which
converts the uninitialized extent to an initialized extent after the
I/O is completed.
Singed-Off-By: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

When writing into an unitialized extent via direct I/O, and the direct
I/O doesn't exactly cover the unitialized extent, split the extent
into uninitialized and initialized extents before submitting the I/O.
This avoids needing to deal with an ENOSPC error in the end_io
callback that gets used for direct I/O.

When the IO is complete, the written extent will be marked as initialized.

Singed-Off-By: Mingming Cao <cmm@us.ibm.com> 
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

ext4_da_reserve_space() can reserve quota blocks multiple times if
ext4_claim_free_blocks() fail and we retry the allocation. We should
release the quota reservation before restarting.

Bug found by Jan Kara.
Signed-off-by: NMingming Cao <cmm@us.ibm.com>
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

Work around problems in the writeback code to force out writebacks in
larger chunks than just 4mb, which is just too small.  This also works
around limitations in the ext4 block allocator, which can't allocate
more than 2048 blocks at a time.  So we need to defeat the round-robin
characteristics of the writeback code and try to write out as many
blocks in one inode before allowing the writeback code to move on to
another inode.  We add a a new per-filesystem tunable,
max_writeback_mb_bump, which caps this to a default of 128mb per
inode.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

The hueristic was designed to avoid using locality group preallocation
when writing the last segment of a closed file.  Fix it by move
setting size to the maximum of size and isize until after we check
whether size == isize.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>

* mark struct vm_area_struct::vm_ops as const
* mark vm_ops in AGP code

But leave TTM code alone, something is fishy there with global vm_ops
being used.
Signed-off-by: NAlexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This allows the user to see what filesystem was involved with a
particular ext4_da_writepage() error.  Also, use KERN_CRIT which is
more appropriate than KERN_EMERG.
Signed-off-by: N"Theodore Ts'o" <tytso@mit.edu>