Commit Graph

285 Commits

Author SHA1 Message Date
Chris Mason
3bf3d9e9c2 Btrfs: Avoid recursive chunk allocations
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:02 -04:00
Chris Mason
8f18cf1339 Btrfs: Make the resizer work based on shrinking and growing devices
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:02 -04:00
Chris Mason
bce4eae986 Btrfs: Fix balance_level to free the middle block if there is room in the left one
balance level starts by trying to empty the middle block, and then
pushes from the right to the middle.  This might empty the right block
and leave a small number of pointers in the middle.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:02 -04:00
Chris Mason
3c12ac7205 Btrfs: Simplify device selection for mirrored reads
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:02 -04:00
Chris Mason
3b951516ed Btrfs: Use the extent map cache to find the logical disk block during data retries
The data read retry code needs to find the logical disk block before it
can resubmit new bios.  But, finding this block isn't allowed to take
the fs_mutex because that will deadlock with a number of different callers.

This changes the retry code to use the extent map cache instead, but
that requires the extent map cache to have the extent we're looking for.
This is a problem because btrfs_drop_extent_cache just drops the entire
extent instead of the little tiny part it is invalidating.

The bulk of the code in this patch changes btrfs_drop_extent_cache to
invalidate only a portion of the extent cache, and changes btrfs_get_extent
to deal with the results.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
699122f559 Btrfs: Don't wait on tree block writeback before freeing them anymore
This isn't required anymore because we don't reallocate blocks that
have already been written in this transaction.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
321aecc656 Btrfs: Add RAID10 support
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
e17cade25f Btrfs: Add chunk uuids and update multi-device back references
Block headers now store the chunk tree uuid

Chunk items records the device uuid for each stripes

Device extent items record better back refs to the chunk tree

Block groups record better back refs to the chunk tree

The chunk tree format has also changed.  The objectid of BTRFS_CHUNK_ITEM_KEY
used to be the logical offset of the chunk.  Now it is a chunk tree id,
with the logical offset being stored in the offset field of the key.

This allows a single chunk tree to record multiple logical address spaces,
upping the number of bytes indexed by a chunk tree from 2^64 to
2^128.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
98d20f67cf Add a min size parameter to btrfs_alloc_extent
On huge machines, delayed allocation may try to allocate massive extents.
This change allows btrfs_alloc_extent to return something smaller than
the caller asked for, and the data allocation routines will loop over
the allocations until it fills the whole delayed alloc.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Miguel
a5eb62e345 Btrfs: Endianess bug fix for v0.13 with kernels
Fix for a endianess BUG when using btrfs v0.13 with kernels older than 2.6.23

Problem:

Has of v0.13, btrfs-progs is using crc32c.c equivalent to the one found on
linux-2.6.23/lib/libcrc32c.c Since crc32c_le() changed in linux-2.6.23, when
running btrfs v0.13 with older kernels we have a missmatch between the versions
of crc32c_le() from btrfs-progs and libcrc32c in the kernel.  This missmatch
causes a bug when using btrfs on big endian machines.

Solution:
btrfs_crc32c() macro that when compiling for kernels older than 2.6.23, does
endianess conversion to parameters and return value of crc32c().
This endianess conversion nullifies the differences in implementation
of crc32c_le().
If kernel 2.6.23 or better, it calls crc32c().

Signed-off-by: Miguel Sousa Filipe <miguel.filipe@gmail.com>
---

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
ce9adaa5a7 Btrfs: Do metadata checksums for reads via a workqueue
Before, metadata checksumming was done by the callers of read_tree_block,
which would set EXTENT_CSUM bits in the extent tree to show that a given
range of pages was already checksummed and didn't need to be verified
again.

But, those bits could go away via try_to_releasepage, and the end
result was bogus checksum failures on pages that never left the cache.

The new code validates checksums when the page is read.  It is a little
tricky because metadata blocks can span pages and a single read may
end up going via multiple bios.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
d18a2c4475 Btrfs: Fix allocation profile init
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
6bc34676c0 Btrfs: Don't allow written blocks from this transaction to be reallocated
When a block is freed, it can be immediately reused if it is from
the current transaction.  But, an extra check is required to make sure
the block had not been written yet.  If it were reused after being written,
the transid in the block header might match the transid of the
next time the block was allocated.

The parent node records the transaction ID of the block it is pointing to,
and this is used as part of validating the block on reads.  So, there
can only be one version of a block per transaction.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
611f0e00a2 Btrfs: Add support for duplicate blocks on a single spindle
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
8790d502e4 Btrfs: Add support for mirroring across drives
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
0999df54f8 Btrfs: Verify checksums on tree blocks found without read_tree_block
Checksums were only verified by btrfs_read_tree_block, which meant the
functions to probe the page cache for blocks were not validating checksums.
Normally this is fine because the buffers will only be in cache if they
have already been validated.

But, there is a window while the buffer is being read from disk where
it could be up to date in the cache but not yet verified.  This patch
makes sure all buffers go through checksum verification before they
are used.

This is safer, and it prevents modification of buffers before they go
through the csum code.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
ecbe2402cb Btrfs: Keep fs_mutex during reads done by snapshot deletion
There was an optimization to drop the fs_mutex when doing snapshot deletion
reads, but this can lead to false positives on checksumming errors.  Keep
the lock for now.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
593060d756 Btrfs: Implement raid0 when multiple devices are present
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
239b14b32d Btrfs: Bring back mount -o ssd optimizations
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
a9218f6b00 Add /dev/btrfs-control for device scanning ioctls
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
7d1660d411 Btrfs: Bring back find_free_extent CPU usage optimizations
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
6324fbf334 Btrfs: Dynamic chunk and block group allocation
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:01 -04:00
Chris Mason
0b86a832a1 Btrfs: Add support for multiple devices per filesystem
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
7f93bf8d27 Match the extent tree code to btrfs-progs for multi-device merging
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
952fccac50 Btrfs: Remove extent back refs in batches, and avoid duplicate searches
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
d7fc640e6f Btrfs: Allocator improvements
Reduce CPU time searching for free blocks by optimizing find_first_extent_bit

Fix find_free_extent to make better use of the last_alloc hint.  Before it
was often finding blocks just before the hint.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
9afbb0b752 Btrfs: Disable tree defrag in SSD mode
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
5d196fc15d Btrfs: Use 2MB as the empty_size for clustered allocations
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
068fe39fa1 Btrfs: Add checks for last byte in disk to allocator grouping
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
f594706643 Btrfs: Add debugging for block group update failure
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
60cde612c8 Btrfs: Use last_alloc optimizations for metadata, even without -o ssd
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
21a4989d26 Btrfs: Hash in the offset and owner for file extent backref keys
This makes searches for backrefs and backref insertion much more efficient
when there are many backrefs for a single extent

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
47e4bb988c Btrfs: Insert extent record and the first backref in a single balance
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
4529ba495c Btrfs: Add data block hints to SSD mode too
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
291d673e6a Btrfs: Do delalloc accounting via hooks in the extent_state code
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:04:00 -04:00
Chris Mason
bea495e5b4 Btrfs: Tune readahead during defrag to avoid reading too much at once
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
d1310b2e0c Btrfs: Split the extent_map code into two parts
There is now extent_map for mapping offsets in the file to disk and
extent_io for state tracking, IO submission and extent_bufers.

The new extent_map code shifts from [start,end] pairs to [start,len], and
pushes the locking out into the caller.  This allows a few performance
optimizations and is easier to use.

A number of extent_map usage bugs were fixed, mostly with failing
to remove extent_map entries when changing the file.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
e18e4809b1 Btrfs: Add mount -o ssd, which includes optimizations for seek free storage
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
55c69072d6 Btrfs: Fix extent_buffer usage when nodesize != leafsize
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
c31f8830f0 Btrfs: online shrinking fixes
While shrinking the FS, the allocation functions need to make sure
they don't try to allocate bytes past the end of the FS.

nodatacow needed an extra check to force cows when the existing extents are
past the end of the FS.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
b0331a4c4c Btrfs: Disable btree reada during extent backref lookups.
This reada is generally not effective.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
dc17ff8f11 Btrfs: Add data=ordered support
This forces file data extents down the disk along with the metadata that
references them.  The current implementation is fairly simple, and just
writes out all of the dirty pages in an inode before the commit.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
725c8463ea Btrfs: resizer: don't hold the fs_mutex for long periods of time
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Chris Mason
1372f8e609 Properly call btrfs_search_slot while shrinking
The shrinking code used btrfs_next_leaf to find the next item, but
this does not cow the blocks it touches.  This fix calls search_slot after
finding the next item to do appropriate cow and balancing.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:59 -04:00
Yan
73e48b277a Btrfs: Properly handle overlapping extent in shrink_extent_tree
The patch fixes the overlapping extent issue in shrink_extent_tree.
It checks whether there is an overlapping extent by using
find_previous_extent. If there is an overlapping extent, it setups
key.objectid and cur_byte properly.

---

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Yan
d548ee5182 Btrfs: Add a helper that finds previous extent item
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
bd09835d9a count_snapshots: Properly update the leaf pointer after btrfs_next_leaf
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
98ed51747b Btrfs: Force inlining off in a few places to save stack usage
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
f9ef6604ac Btrfs: 32 bit compile fixes for the resizer and enospc checks
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
4313b3994d Btrfs: Reduce stack usage in the resizer, fix 32 bit compiles
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
56b453c92f Btrfs: Explicitly send a root objectid to count_snapshots_in_path
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
8f662a76c6 Btrfs: Add readahead to the online shrinker, and a mount -o alloc_start= for testing
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
e52ec0eb62 Btrfs: Fix NULL block groups on reading the inode
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
edbd8d4efe Btrfs: Support for online FS resize (grow and shrink)
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
be20aa9dba Btrfs: Add mount option to turn off data cow
A number of workloads do not require copy on write data or checksumming.
mount -o nodatasum to disable checksums and -o nodatacow to disable
both copy on write and checksumming.

In nodatacow mode, copy on write is still performed when a given extent
is under snapshot.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
f6dbff55d7 Btrfs: Reorder extent back refs to differentiate btree blocks from file data
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
6caab489c5 Fix btrfs_inc_ref to add backref hints
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
70b043f0c7 Btrfs: Extra NULL block group checks in find_free_extent
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
d8d5f3e16d Btrfs: Add lowest key information to back refs for extent tree blocks as well.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
7bb86316c3 Btrfs: Add back pointers from extents to the btree or file referencing them
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
74493f7a59 Btrfs: Implement generation numbers in block pointers
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
1a2b2ac78a Btrfs: Fix extent allocation for btree blocks as the disk fills
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
87ee04eb0f Btrfs: Add simple stripe size parameter
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
00f5c795fc btrfs_drop_extents: make sure the item is getting smaller before truncate
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
015a739c7c Btrfs: Handle writeback under high memory pressure better
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Chris Mason
0e4de58432 Btrfs: Add check for null block group to find_search_start
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:58 -04:00
Yan
5cf664263b Btrfs: Off by one fixes for extent-tree.c
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Yan
5e5745dcaf Btrfs: Add full_scan parameter to find_search_start
This patch adds a new parameter 'full_scan' to 'find_search_start',
thereby 'find_search_start' can know whether 'find_free_extent' is in
full scan phrase. I feel that 'find_search_start' should skip calling
'btrfs_find_block_group' when 'find_free_extent' is in full scan
phrase. In my test on a 2GB volume, Oops occurs when space usage is
about 76%. After apply the patch,  Oops occurs when space usage is
near 100%.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Yan
324ae4df00 Btrfs: Add block group pinned accounting back
This patch adds a helper function 'update_pinned_extents' to
extent-tree.c. The usage of the helper function is similar to
'update_block_group',  the last parameter of the function indicates
pin vs unpin.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Chris Mason
257d0ce36f Btrfs: Allow large data extents in a single file to span into metadata block groups
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Chris Mason
f84a8b362d Btrfs: Optimize allocations as we need to mix data and metadata into one group
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Yan
c549228ff6 Btrfs: Properly update free space cache in __free_extent
When pin_down_bytes decides not to pin a block because it was from the
current transaction, make sure the in memory cache of free extents is updated

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Yan
b97f9203b4 Btrfs: Fix typo and memory leak in extent-tree.c
This patch fixes a typo in update_block_group and memory leak in
btrfs_free_block_groups.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Jens Axboe
ae2f5411c4 btrfs: 32-bit type problems
An assorted set of casts to get rid of the warnings on 32-bit archs.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:57 -04:00
Chris Mason
19c00ddcc3 Btrfs: Add back metadata checksumming
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
0f82731fc5 Breakout BTRFS_SETGET_FUNCS into a separate C file, the inlines were too big.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
4dc119046d Btrfs: Add an extent buffer LRU to reduce radix tree hits
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
e19caa5f0e Btrfs: Fix allocation routines to avoid intermixing data and metadata allocations
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
6b80053d02 Btrfs: Add back the online defragging code
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
db94535db7 Btrfs: Allow tree blocks larger than the page size
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
1a5bc167f6 Btrfs: Change the remaining radix trees used by extent-tree.c to extent_map trees
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
96b5179d0d Btrfs: Stop using radix trees for the block group cache
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
f510cfecfc Btrfs: Fix extent_buffer and extent_state leaks
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
5f39d397df Btrfs: Create extent_buffer interface for large blocksizes
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
cf67582bb2 Btrfs: Fix duplicate ENOSPC checks in find_free_extent
find_free_extent would fail to wrap around to the start of the drive because
it was doing the enospc case checking twice in some cases, causing it
to return -ENOSPC early.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:03:56 -04:00
Chris Mason
d3c2fdcf7b Btrfs: Use balance_dirty_pages_nr on btree blocks
btrfs_btree_balance_dirty is changed to pass the number of pages dirtied
for more accurate dirty throttling.  This lets the VM make better decisions
about when to force some writeback.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2008-09-25 11:00:48 -04:00
Yan
7d7d6068be Btrfs: Fix cache_block_group to catch holes at the start of the group
Cache block group was overly complex and missed free blocks at the very start
of the group.  This patch simplifies things significantly.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-09-14 16:15:28 -04:00
Yan
e9fe395e47 Btrfs: Fix oopsen in extent_tree.c during enospc
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-29 09:11:44 -04:00
Josef Bacik
58176a9604 Btrfs: Add per-root block accounting and sysfs entries
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-29 15:47:34 -04:00
Chris Mason
b888db2bd7 Btrfs: Add delayed allocation to the extent based page tree code
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-27 16:49:44 -04:00
Chris Mason
2cc58cf24f Btrfs: Do more extensive readahead during tree searches
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-27 16:49:44 -04:00
Chris Mason
f2183bde1a Btrfs: Add BH_Defrag to mark buffers that are in need of defragging
This allows the tree walking code to defrag only the newly allocated
buffers, it seems to be a good balance between perfect defragging and the
performance hit of repeatedly reallocating blocks.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-10 14:42:37 -04:00
Chris Mason
e9d0b13b5b Btrfs: Btree defrag on the extent-mapping tree as well
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-10 14:06:19 -04:00
Chris Mason
409eb95d7f Btrfs: Further reduce the concurrency penalty of defrag and drop_snapshot
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-08 20:17:12 -04:00
Chris Mason
26b8003f10 Btrfs: Replace extent tree preallocation code with some bit radix magic.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-08 20:17:12 -04:00
Chris Mason
f4468e94c8 Btrfs: Let some locks go during defrag and snapshot dropping
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-08 10:08:58 -04:00
Chris Mason
6702ed490c Btrfs: Add run time btree defrag, and an ioctl to force btree defrag
This adds two types of btree defrag, a run time form that tries to
defrag recently allocated blocks in the btree when they are still in ram,
and an ioctl that forces defrag of all btree blocks.

File data blocks are not defragged yet, but this can make a huge difference
in sequential btree reads.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-07 16:15:09 -04:00
Chris Mason
3c69faecb8 Btrfs: Fold some btree readahead routines into something more generic.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-07 15:52:22 -04:00
Chris Mason
9f3a742736 Btrfs: Do snapshot deletion in smaller chunks.
Before, snapshot deletion was a single atomic unit.  This caused considerable
lock contention and required an unbounded amount of space.  Now,
the drop_progress field in the root item is used to indicate how far along
snapshot deletion is, and to resume where it left off.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-08-07 15:52:19 -04:00
Zach Brown
ec6b910fb3 Btrfs: trivial include fixups
Almost none of the files including module.h need to do so,
remove them.

Include sched.h in extent-tree.c to silence a warning about cond_resched()
being undeclared.

Signed-off-by: Zach Brown <zach.brown@oracle.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-07-11 10:00:37 -04:00
Chris Mason
ccd467d60e Btrfs: crash recovery fixes
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-28 15:57:36 -04:00
Chris Mason
f2654de42a Btrfs: Allow find_free_extent callers to pass in an exclusion range
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-26 12:20:46 -04:00
Chris Mason
4b52dff6d3 Btrfs: Fix super block updates during transaction commit
The super block written during commit was not consistent with the state of
the trees.  This change adds an in-memory copy of the super so that we can
make sure to write out consistent data during a commit.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-26 10:06:50 -04:00
Chris Mason
54aa1f4dfd Btrfs: Audit callers and return codes to make sure -ENOSPC gets up the stack
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-22 14:16:25 -04:00
Chris Mason
e011599b0f Btrfs: reada while dropping snapshots
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-19 16:23:05 -04:00
Chris Mason
85e55b13e4 Btrfs: cache the extent tree preallocation
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-19 15:50:51 -04:00
Chris Mason
8c2383c3dd Subject: Rework btrfs_file_write to only allocate while page locks are held
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-18 09:57:58 -04:00
Aneesh
f1ace244c8 btrfs: Code cleanup
Attaching below is some of the code cleanups that i came across while
reading the code.

a) alloc_path already calls init_path.
b) Mention that btrfs_inode is the in memory copy.Ext4 have ext4_inode_info as
the in memory copy ext4_inode as the disk copy

Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-13 16:18:26 -04:00
Chris Mason
6cbd557078 Btrfs: add GPLv2
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-12 09:07:21 -04:00
Chris Mason
5af3981c18 Btrfs: printk fixes
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-12 07:50:13 -04:00
Chris Mason
84f54cfa78 Btrfs: 64 bit div fixes
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-12 07:43:08 -04:00
Chris Mason
5276aedab0 Btrfs: fix oops after block group lookup
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-11 21:33:38 -04:00
Chris Mason
fabb568183 Btrfs: d_type optimization
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-06-07 22:13:21 -04:00
Chris Mason
fbdc762b4e Btrfs: use a separate flag for search_start vs a hint in find_free_extent
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-30 10:22:12 -04:00
Chris Mason
1e2677e000 Btrfs: block group switching
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-29 16:52:18 -04:00
Chris Mason
3a68637562 Btrfs: sparse files!
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-24 13:35:57 -04:00
Chris Mason
de428b63b1 Btrfs: allocator optimizations, truncate readahead
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-18 13:28:27 -04:00
Chris Mason
8d7be552a7 Btrfs: fix check_node and check_leaf to use less cpu
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-10 11:24:42 -04:00
Chris Mason
e37c9e6921 Btrfs: many allocator fixes, pretty solid
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-09 20:13:14 -04:00
Chris Mason
3e1ad54fe2 Btrfs: allocator and tuning
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-07 20:03:49 -04:00
Chris Mason
be74417553 Btrfs: more allocator enhancements
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-06 10:15:01 -04:00
Chris Mason
be08c1b9f8 Btrfs: early metadata/data split
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-03 09:06:49 -04:00
Chris Mason
35b7e47610 Btrfs: fix page cache memory leak
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-02 15:53:43 -04:00
Chris Mason
090d18753c Btrfs: directory readahead
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-05-01 08:53:32 -04:00
Chris Mason
31f3c99b73 Btrfs: allocator improvements, inode block groups
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-30 15:25:45 -04:00
Chris Mason
308535a05e Btrfs: prealloc more blocks for the extent map
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-28 15:17:08 -04:00
Chris Mason
7c4452b9a6 Btrfs: smarter transaction writeback
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-28 09:29:35 -04:00
Chris Mason
06a2f9fa4c Btrfs: try to drop dead cow pages from ram
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-28 08:48:10 -04:00
Chris Mason
28b8bb9e00 Btrfs: allocator tweaks
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-27 11:42:05 -04:00
Chris Mason
cd1bc4653d Btrfs: more block allocator work
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-27 10:08:34 -04:00
Chris Mason
9078a3e1e4 Btrfs: start of block group code
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-26 16:46:15 -04:00
Chris Mason
f2458e1d8c Btrfs: change around extent-tree prealloc
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-25 15:52:25 -04:00
Chris Mason
c62a1920ce Btrfs: get rid of the extent_item type field
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-24 12:07:39 -04:00
Chris Mason
5d0c3e60fe Btrfs: fix extent owner/type setting on extent tree blocks
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-23 17:01:05 -04:00
Chris Mason
4d77567309 Btrfs: add owner and type fields to the extents aand block headers
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-20 20:23:12 -04:00
Chris Mason
236454dfff Btrfs: many file_write fixes, inline data
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-19 13:37:44 -04:00
Chris Mason
a429e51371 Btrfs: working file_write, reorganized key flags
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-18 16:15:28 -04:00
Chris Mason
b18c668581 Btrfs: progress on file_write
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-17 13:26:50 -04:00
Chris Mason
7eccb903a8 Btrfs: create a logical->phsyical block number mapping scheme
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-11 15:53:25 -04:00
Chris Mason
d0dbc6245c Btrfs: drop owner and parentid
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-10 12:36:36 -04:00
Chris Mason
c5739bba52 Btrfs: snapshot progress
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-10 09:27:04 -04:00
Chris Mason
5f26f772e5 Btrfs: more inode indexed directory work
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-05 10:38:44 -04:00
Chris Mason
b1a4d96509 Btrfs: tweak the inode-map and free extent search starts on cold mount
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-04 15:27:52 -04:00
Chris Mason
2da566edd8 Btrfs: csum_verify_file_block locking fix
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-02 15:43:21 -04:00
Chris Mason
5caf2a0029 Btrfs: dynamic allocation of path struct
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-02 11:20:42 -04:00
Chris Mason
2c90e5d658 Btrfs: still corruption hunting
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-04-02 10:50:19 -04:00
Chris Mason
d602557953 Btrfs: corruption hunt continues
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-03-30 14:27:56 -04:00
Chris Mason
d98237b3ed Btrfs: use a btree inode instead of sb_getblk
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-03-28 13:57:48 -04:00
Chris Mason
f4b9aa8d3b btrfs_truncate
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-03-27 11:05:53 -04:00
Chris Mason
6407bf6d7c Btrfs: reference counts on data extents
Signed-off-by: Chris Mason <chris.mason@oracle.com>
2007-03-27 06:33:00 -04:00