Btrfs uses kernel threads to create async work queues for cpu intensive
operations such as checksumming and decompression.  These work well,
but they make it difficult to keep IO order intact.

A single writepages call from pdflush or fsync will turn into a number
of bios, and each bio is checksummed in parallel.  Once the checksum is
computed, the bio is sent down to the disk, and since we don't control
the order in which the parallel operations happen, they might go down to
the disk in almost any order.

The code deals with this somewhat by having deep work queues for a single
kernel thread, making it very likely that a single thread will process all
the bios for a single inode.

This patch introduces an explicitly ordered work queue.  As work structs
are placed into the queue they are put onto the tail of a list.  They have
three callbacks:

->func (cpu intensive processing here)
->ordered_func (order sensitive processing here)
->ordered_free (free the work struct, all processing is done)

The work struct has three callbacks.  The func callback does the cpu intensive
work, and when it completes the work struct is marked as done.

Every time a work struct completes, the list is checked to see if the head
is marked as done.  If so the ordered_func callback is used to do the
order sensitive processing and the ordered_free callback is used to do
any cleanup.  Then we loop back and check the head of the list again.

This patch also changes the checksumming code to use the ordered workqueues.
One a 4 drive array, it increases streaming writes from 280MB/s to 350MB/s.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Make sure we keep page->mapping NULL on the pages we're getting
via alloc_page.  It gets set so a few of the callbacks can do the right
thing, but in general these pages don't have a mapping.

Don't try to truncate compressed inline items in btrfs_drop_extents.
The whole compressed item must be preserved.

Don't try to create multipage inline compressed items.  When we try to
overwrite just the first page of the file, we would have to read in and recow
all the pages after it in the same compressed inline items.  For now, only
create single page inline items.

Make sure we lock pages in the correct order during delalloc.  The
search into the state tree for delalloc bytes can return bytes before
the page we already have locked.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This patch updates btrfs-progs for fallocate support.

fallocate is a little different in Btrfs because we need to tell the
COW system that a given preallocated extent doesn't need to be
cow'd as long as there are no snapshots of it.  This leverages the
-o nodatacow checks.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

This patch simplifies the nodatacow checker. If all references
were created after the latest snapshot, then we can avoid COW
safely. This patch also updates run_delalloc_nocow to do more
fine-grained checking.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

When dropping middle part of an extent, btrfs_drop_extents truncates
the extent at first, then inserts a bookend extent.

Since truncation and insertion can't be done atomically, there is a small
period that the bookend extent isn't in the tree. This causes problem for
functions that search the tree for file extent item. The way to fix this is
lock the range of the bookend extent before truncation.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

This patch splits the hole insertion code out of btrfs_setattr
into btrfs_cont_expand and updates btrfs_get_extent to properly
handle the case that file extent items are not continuous.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

When compression was on, we were improperly ignoring -o nodatasum.  This
reworks the logic a bit to properly honor all the flags.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The byte walk counting was awkward and error prone.  This uses the
number of pages sent the higher layer to build bios.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This is a large change for adding compression on reading and writing,
both for inline and regular extents.  It does some fairly large
surgery to the writeback paths.

Compression is off by default and enabled by mount -o compress.  Even
when the -o compress mount option is not used, it is possible to read
compressed extents off the disk.

If compression for a given set of pages fails to make them smaller, the
file is flagged to avoid future compression attempts later.

* While finding delalloc extents, the pages are locked before being sent down
to the delalloc handler.  This allows the delalloc handler to do complex things
such as cleaning the pages, marking them writeback and starting IO on their
behalf.

* Inline extents are inserted at delalloc time now.  This allows us to compress
the data before inserting the inline extent, and it allows us to insert
an inline extent that spans multiple pages.

* All of the in-memory extent representations (extent_map.c, ordered-data.c etc)
are changed to record both an in-memory size and an on disk size, as well
as a flag for compression.

From a disk format point of view, the extent pointers in the file are changed
to record the on disk size of a given extent and some encoding flags.
Space in the disk format is allocated for compression encoding, as well
as encryption and a generic 'other' field.  Neither the encryption or the
'other' field are currently used.

In order to limit the amount of data read for a single random read in the
file, the size of a compressed extent is limited to 128k.  This is a
software only limit, the disk format supports u64 sized compressed extents.

In order to limit the ram consumed while processing extents, the uncompressed
size of a compressed extent is limited to 256k.  This is a software only limit
and will be subject to tuning later.

Checksumming is still done on compressed extents, and it is done on the
uncompressed version of the data.  This way additional encodings can be
layered on without having to figure out which encoding to checksum.

Compression happens at delalloc time, which is basically singled threaded because
it is usually done by a single pdflush thread.  This makes it tricky to
spread the compression load across all the cpus on the box.  We'll have to
look at parallel pdflush walks of dirty inodes at a later time.

Decompression is hooked into readpages and it does spread across CPUs nicely.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Creating a subvolume is in many ways like a normal VFS ->mkdir, and we
really need to play with the VFS topology locking rules.  So instead of
just creating the snapshot on disk and then later getting rid of
confliting aliases do it correctly from the start.  This will become
especially important once we allow for subvolumes anywhere in the tree,
and not just below a hidden root.

Note that snapshots will need the same treatment, but do to the delay
in creating them we can't do it currently.  Chris promised to fix that
issue, so I'll wait on that.
Signed-off-by: NChristoph Hellwig <hch@lst.de>

Due to the optimization for truncate, tree leaves only containing
checksum items can be deleted without being COW'ed first. This causes
reference cache misses. The way to fix the miss is create cache
entries for tree leaves only contain checksum.

This patch also fixes a -EEXIST issue in shared reference cache.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

The offset field in struct btrfs_extent_ref records the position
inside file that file extent is referenced by. In the new back
reference system, tree leaves holding references to file extent
are recorded explicitly. We can scan these tree leaves very quickly, so the
offset field is not required.

This patch also makes the back reference system check the objectid
when extents are in deleting.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

This patch makes btrfs count space allocated to file in bytes instead
of 512 byte sectors.

Everything else in btrfs uses a byte count instead of sector sizes or
blocks sizes, so this fits better.
Signed-off-by: NYan Zheng <zheng.yan@oracle.com>

On 32 bit machines without CONFIG_LBD, the bi_sector field is only 32 bits.
Btrfs needs to cast it before shifting up, or we end up doing IO into
the wrong place.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Checksum items take up a significant portion of the metadata for large files.
It is possible to avoid reading them during truncates by checking the keys in
the higher level nodes.

If a given leaf is followed by another leaf where the lowest key is a checksum
item from the same file, we know we can safely delete the leaf without
reading it.

For a 32GB file on a 6 drive raid0 array, Btrfs needs 8s to delete
the file with a cold cache.  It is read bound during the run.

With this change, Btrfs is able to delete the file in 0.5s
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This improves the comments at the top of many functions.  It didn't
dive into the guts of functions because I was trying to
avoid merging problems with the new allocator and back reference work.

extent-tree.c and volumes.c were both skipped, and there is definitely
more work todo in cleaning and commenting the code.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs-vol -a /dev/xxx will zero the first and last two MB of the device.
The kernel code needs to wait for this IO to finish before it adds
the device.

btrfs metadata IO does not happen through the block device inode.  A
separate address space is used, allowing the zero filled buffer heads in
the block device inode to be written to disk after FS metadata starts
going down to the disk via the btrfs metadata inode.

The end result is zero filled metadata blocks after adding new devices
into the filesystem.

The fix is a simple filemap_write_and_wait on the block device inode
before actually inserting it into the pool of available devices.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

* Add an EXTENT_BOUNDARY state bit to keep the writepage code
from merging data extents that are in the process of being
relocated.  This allows us to do accounting for them properly.

* The balancing code relocates data extents indepdent of the underlying
inode.  The extent_map code was modified to properly account for
things moving around (invalidating extent_map caches in the inode).

* Don't take the drop_mutex in the create_subvol ioctl.  It isn't
required.

* Fix walking of the ordered extent list to avoid races with sys_unlink

* Change the lock ordering rules.  Transaction start goes outside
the drop_mutex.  This allows btrfs_commit_transaction to directly
drop the relocation trees.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Btrfs had compatibility code for kernels back to 2.6.18.  These have
been removed, and will be maintained in a separate backport
git tree from now on.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The code to update the on disk i_size happens before the
ordered_extent record is removed.  So, it is possible for multiple
ordered_extent completion routines to run at the same time, and to
find each other in the ordered tree.

The end result is they both decide not to update disk_i_size, leaving
it too small.  This temporary fix just puts the updates inside
the extent_mutex.  A real solution would be stronger ordering of
disk_i_size updates against removing the ordered extent from the tree.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This patch makes the back reference system to explicit record the
location of parent node for all types of extents. The location of
parent node is placed into the offset field of backref key. Every
time a tree block is balanced, the back references for the affected
lower level extents are updated.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

1) replace the per fs_info extent_io_tree that tracked free space with two
rb-trees per block group to track free space areas via offset and size.  The
reason to do this is because most allocations come with a hint byte where to
start, so we can usually find a chunk of free space at that hint byte to satisfy
the allocation and get good space packing.  If we cannot find free space at or
after the given offset we fall back on looking for a chunk of the given size as
close to that given offset as possible.  When we fall back on the size search we
also try to find a slot as close to the size we want as possible, to avoid
breaking small chunks off of huge areas if possible.

2) remove the extent_io_tree that tracked the block group cache from fs_info and
replaced it with an rb-tree thats tracks block group cache via offset.  also
added a per space_info list that tracks the block group cache for the particular
space so we can lookup related block groups easily.

3) cleaned up the allocation code to make it a little easier to read and a
little less complicated.  Basically there are 3 steps, first look from our
provided hint.  If we couldn't find from that given hint, start back at our
original search start and look for space from there.  If that fails try to
allocate space if we can and start looking again.  If not we're screwed and need
to start over again.

4) small fixes.  there were some issues in volumes.c where we wouldn't allocate
the rest of the disk.  fixed cow_file_range to actually pass the alloc_hint,
which has helped a good bit in making the fs_mark test I run have semi-normal
results as we run out of space.  Generally with data allocations we don't track
where we last allocated from, so everytime we did a data allocation we'd search
through every block group that we have looking for free space.  Now searching a
block group with no free space isn't terribly time consuming, it was causing a
slight degradation as we got more data block groups.  The alloc_hint has fixed
this slight degredation and made things semi-normal.

There is still one nagging problem I'm working on where we will get ENOSPC when
there is definitely plenty of space.  This only happens with metadata
allocations, and only when we are almost full.  So you generally hit the 85%
mark first, but sometimes you'll hit the BUG before you hit the 85% wall.  I'm
still tracking it down, but until then this seems to be pretty stable and make a
significant performance gain.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Drop i_mutex during the commit

Don't bother doing the fsync at all unless the dir is marked as dirtied
and needing fsync in this transaction.  For directories, this means
that someone has unlinked a file from the dir without fsyncing the
file.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Signed-off-by: NChris Mason <chris.mason@oracle.com>

Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs_ilookup is unused, which is good because a normal filesystem
should never have to use ilookup anyway.  Remove it.
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

File syncs and directory syncs are optimized by copying their
items into a special (copy-on-write) log tree.  There is one log tree per
subvolume and the btrfs super block points to a tree of log tree roots.

After a crash, items are copied out of the log tree and back into the
subvolume.  See tree-log.c for all the details.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

btrfs actually stores the whole xattr name, including the prefix ondisk,
so using the generic resolver that strips off the prefix is not very
helpful.  Instead do the real ondisk xattrs manually and only use the
generic resolver for synthetic xattrs like ACLs.

(Sorry Josef for guiding you towards the wrong direction here intially)
Signed-off-by: NChristoph Hellwig <hch@lst.de>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Date: Sun, 17 Aug 2008 17:12:56 +0100
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Date: Sun, 17 Aug 2008 17:08:36 +0100
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Date: Sun, 17 Aug 2008 15:14:48 +0100
We never get asked by the VFS to lookup either of them, and we can
handle the readdir() case a lot more simply, too.
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Date: Wed, 6 Aug 2008 19:42:33 +0100
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Date: Mon, 21 Jul 2008 02:01:04 +0530
This patch introduces a btrfs_iget helper to be used in NFS support.
Signed-off-by: NBalaji Rao <balajirrao@gmail.com>
Signed-off-by: NDavid Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This optimization had been removed because I thought it was triggering
csum errors.  The real cause of the errors was elsewhere, and so
this optimization is back.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

add_extent_mapping was allowing the insertion of overlapping extents.
This never used to happen because it only inserted the extents from disk
and those were never overlapping.

But, with the data=ordered code, the disk and memory representations of the
file are not the same.  add_extent_mapping needs to ensure a new extent
does not overlap before it inserts.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

This takes the csum mutex deeper in the call chain and releases it
more often.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

The writeback_index field is used by write_cache_pages to pick up where
writeback on a given inode left off.  But, it is never set to a sane
value, so writeback can often start at a random offset in the file.

Kernels 2.6.28 and higher will have this fixed, but for everyone else,
we also fill in the value in btrfs.
Signed-off-by: NChris Mason <chris.mason@oracle.com>

Signed-off-by: NChris Mason <chris.mason@oracle.com>

Signed-off-by: NChris Mason <chris.mason@oracle.com>

rename and link don't always have a lock on the source inode, and
our use of a per-inode index variable was racy.  This changes things to
store the index in a local variable instead.
Signed-off-by: NChris Mason <chris.mason@oracle.com>