Commits · d7fc640e6fed46932f7c74e14f9b58b8637c66cf · nexedi / linux

25 Sep, 2008 40 commits

Btrfs: Allocator improvements · d7fc640e

Chris Mason authored Feb 18, 2008

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>

d7fc640e

Btrfs: Disable tree defrag in SSD mode · 9afbb0b7
Chris Mason authored Feb 15, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
9afbb0b7

Btrfs: unaligned access fixes · df68b8a7

David Miller authored Feb 15, 2008

Btrfs set/get macros lose type information needed to avoid
unaligned accesses on sparc64.
ere is a patch for the kernel bits which fixes most of the
unaligned accesses on sparc64.

btrfs_name_hash is modified to return the hash value instead
of getting a return location via a (potentially unaligned)
pointer.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

df68b8a7

Btrfs: Fix "no csum found for inode" issue. · 39b5637f

Yan authored Feb 15, 2008

A few codes were not properly updated for changes of extent map.  This
may be the causes of "no csum found for inode" issue.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

39b5637f

Btrfs: Fix i_blocks accounting · 9069218d

Chris Mason authored Feb 08, 2008

Now that delayed allocation accounting works, i_blocks accounting is changed
to only modify i_blocks when extents inserted or removed.

The fillattr call is changed to include the delayed allocation byte count
in the i_blocks result.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

9069218d

Btrfs: Create larger bios for btree blocks · a86c12c7
Chris Mason authored Feb 07, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
a86c12c7
Btrfs: Don't case unsigned long to int in bio submission · 961d0232
Chris Mason authored Feb 06, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
961d0232
Btrfs: Use 2MB as the empty_size for clustered allocations · 5d196fc1
Chris Mason authored Feb 06, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
5d196fc1

btrfs_drop_extents: handle BTRFS_INODE_REF_KEY types · 7261009c

Yan authored Feb 05, 2008

It's possible "key.type == BTRFS_INODE_REF_KEY" and "key.offset >= end".
Signed-off-by: Chris Mason <chris.mason@oracle.com>

7261009c

Btrfs: Add checks for last byte in disk to allocator grouping · 068fe39f
Chris Mason authored Feb 05, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
068fe39f
Btrfs: Fix hole creation in file_write · dacb473a
Yan authored Feb 05, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
dacb473a
Btrfs: Update magic · 47b0c4f8
Chris Mason authored Feb 04, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
47b0c4f8
Btrfs: Add debugging for block group update failure · f5947066
Chris Mason authored Feb 04, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
f5947066
Btrfs: Fix typo in extent_io.c · c2e639f0
Yan authored Feb 04, 2008
```
---
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
c2e639f0
Btrfs: Lower stack usage in transaction.c · 80b6794d
Chris Mason authored Feb 01, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
80b6794d
Btrfs: Fix delalloc account on state deletion · ae9d1285
Chris Mason authored Feb 01, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
ae9d1285

Call btrfs_cow_block while lowering tree level. · 2f375ab9

Yan authored Feb 01, 2008

When freeing root block of a tree,  btrfs_free_extent' parameter
'ref_generation' is from root block itseft.  When freeing non-root
block,  'ref_generation' is from its parent. so when converting a
non-root block to root block, we must guarantee its generation is
equal to its parent's generation.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

2f375ab9

Btrfs: Use last_alloc optimizations for metadata, even without -o ssd · 60cde612
Chris Mason authored Feb 01, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
60cde612

Btrfs: Hash in the offset and owner for file extent backref keys · 21a4989d

Chris Mason authored Feb 01, 2008

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>

21a4989d

Btrfs: Insert extent record and the first backref in a single balance · 47e4bb98
Chris Mason authored Feb 01, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
47e4bb98
Btrfs: Add a lookup cache to the extent state tree · 80ea96b1
Chris Mason authored Feb 01, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
80ea96b1
Btrfs: Add data block hints to SSD mode too · 4529ba49
Chris Mason authored Jan 31, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
4529ba49
Btrfs: Enable delalloc accounting · b0c68f8b
Chris Mason authored Jan 31, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
b0c68f8b

btrfs_drop_extent fixe for inline items > 8K · 0181e58f

Yan authored Jan 30, 2008

When truncating a inline extent, btrfs_drop_extents doesn't properly
handle the case "key.offset > inline_limit". This bug can only happen
when max line size is larger than 8K.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

0181e58f

Fix hole start calculation in btrfs_settar · 1b0f7c29
Chris Mason authored Jan 30, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
1b0f7c29
Properly align the hole size in btrfs_setattr · f392a938
Chris Mason authored Jan 30, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
f392a938
Btrfs: Align extent length to sectorsize in · b1632b10
Yan authored Jan 30, 2008
```
---
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
b1632b10
Btrfs: Copy correct tree when inserting into slot 0 · 5a01a2e3
Chris Mason authored Jan 30, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
5a01a2e3
Btrfs: Leave on the tree defragger in mount -o ssd, it still helps there · b3236e68
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
b3236e68
Btrfs: mount -o max_inline=size to control the maximum inline extent size · 6f568d35
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
6f568d35
Btrfs: Do delalloc accounting via hooks in the extent_state code · 291d673e
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
291d673e
Btrfs: Add inode item and backref in one insert, reducing cpu usage · 9c58309d
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
9c58309d
Btrfs: During deletes and truncate, remove many items at once from the tree · 85e21bac
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
85e21bac

Btrfs: extent_io and extent_state optimizations · 70dec807

Chris Mason authored Jan 29, 2008

The end_bio routines are changed to take a pointer to the extent state
struct, and the state tree is walked in order to set/clear appropriate
bits as IO completes.  This greatly reduces the number of rbtree searches
done by the end_bio handlers, and reduces lock contention.

The extent_io releasepage function is changed to avoid expensive searches
for locked state.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

70dec807

Btrfs: Add some extra debugging around file data checksum failures · aadfeb6e
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
aadfeb6e
Btrfs: Force f_pos to the max when a readdir hits the end of the directory. · c2a8b6e1
Chris Mason authored Jan 29, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
c2a8b6e1
Btrfs: Tune readahead during defrag to avoid reading too much at once · bea495e5
Chris Mason authored Jan 24, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
bea495e5

Btrfs: Split the extent_map code into two parts · d1310b2e

Chris Mason authored Jan 24, 2008

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>

d1310b2e

Btrfs: Fix hole insertion corner cases · 5f56406a

Chris Mason authored Jan 22, 2008

There were a few places that could cause duplicate extent insertion,
this adjusts the code that creates holes to avoid it.

lookup_extent_map is changed to correctly return all of the extents in a
range, even when there are none matching at the start of the range.
Signed-off-by: Chris Mason <chris.mason@oracle.com>

5f56406a

Btrfs: Include sched.h in the acl code for current (fixes compile on 2.6.23) · c1e32da6
Chris Mason authored Jan 22, 2008
```
Signed-off-by: Chris Mason <chris.mason@oracle.com>
```
c1e32da6