diff options
author | Chris Mason <chris.mason@oracle.com> | 2009-09-02 20:53:46 (GMT) |
---|---|---|
committer | Chris Mason <chris.mason@oracle.com> | 2009-09-11 17:31:07 (GMT) |
commit | 8b62b72b26bcd72082c4a69d179dd906bcc22200 (patch) | |
tree | ceee20dfebe45654cb3a25d8916c195836cdbabf /fs/btrfs/extent_io.c | |
parent | 9655d2982b53fdb38a9e0f2f11315b99b92d66e2 (diff) | |
download | linux-fsl-qoriq-8b62b72b26bcd72082c4a69d179dd906bcc22200.tar.xz |
Btrfs: Use PagePrivate2 to track pages in the data=ordered code.
Btrfs writes go through delalloc to the data=ordered code. This
makes sure that all of the data is on disk before the metadata
that references it. The tracking means that we have to make sure
each page in an extent is fully written before we add that extent into
the on-disk btree.
This was done in the past by setting the EXTENT_ORDERED bit for the
range of an extent when it was added to the data=ordered code, and then
clearing the EXTENT_ORDERED bit in the extent state tree as each page
finished IO.
One of the reasons we had to do this was because sometimes pages are
magically dirtied without page_mkwrite being called. The EXTENT_ORDERED
bit is checked at writepage time, and if it isn't there, our page become
dirty without going through the proper path.
These bit operations make for a number of rbtree searches for each page,
and can cause considerable lock contention.
This commit switches from the EXTENT_ORDERED bit to use PagePrivate2.
As pages go into the ordered code, PagePrivate2 is set on each one.
This is a cheap operation because we already have all the pages locked
and ready to go.
As IO finishes, the PagePrivate2 bit is cleared and the ordered
accoutning is updated for each page.
At writepage time, if the PagePrivate2 bit is missing, we go into the
writepage fixup code to handle improperly dirtied pages.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/extent_io.c')
-rw-r--r-- | fs/btrfs/extent_io.c | 29 |
1 files changed, 10 insertions, 19 deletions
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c9a438d..a102422 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -885,13 +885,6 @@ int set_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, NULL, mask); } -int set_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask) -{ - return set_extent_bit(tree, start, end, EXTENT_ORDERED, 0, NULL, NULL, - mask); -} - int set_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, int bits, gfp_t mask) { @@ -921,13 +914,6 @@ int clear_extent_dirty(struct extent_io_tree *tree, u64 start, u64 end, NULL, mask); } -int clear_extent_ordered(struct extent_io_tree *tree, u64 start, u64 end, - gfp_t mask) -{ - return clear_extent_bit(tree, start, end, EXTENT_ORDERED, 1, 0, - NULL, mask); -} - int set_extent_new(struct extent_io_tree *tree, u64 start, u64 end, gfp_t mask) { @@ -1373,7 +1359,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, int clear_unlock, int clear_delalloc, int clear_dirty, int set_writeback, - int end_writeback) + int end_writeback, + int set_private2) { int ret; struct page *pages[16]; @@ -1392,7 +1379,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, clear_bits |= EXTENT_DELALLOC; clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS); - if (!(unlock_pages || clear_dirty || set_writeback || end_writeback)) + if (!(unlock_pages || clear_dirty || set_writeback || end_writeback || + set_private2)) return 0; while (nr_pages > 0) { @@ -1400,6 +1388,10 @@ int extent_clear_unlock_delalloc(struct inode *inode, min_t(unsigned long, nr_pages, ARRAY_SIZE(pages)), pages); for (i = 0; i < ret; i++) { + + if (set_private2) + SetPagePrivate2(pages[i]); + if (pages[i] == locked_page) { page_cache_release(pages[i]); continue; @@ -2792,7 +2784,7 @@ int try_release_extent_state(struct extent_map_tree *map, int ret = 1; if (test_range_bit(tree, start, end, - EXTENT_IOBITS | EXTENT_ORDERED, 0, NULL)) + EXTENT_IOBITS, 0, NULL)) ret = 0; else { if ((mask & GFP_NOFS) == GFP_NOFS) @@ -2835,8 +2827,7 @@ int try_release_extent_mapping(struct extent_map_tree *map, } if (!test_range_bit(tree, em->start, extent_map_end(em) - 1, - EXTENT_LOCKED | EXTENT_WRITEBACK | - EXTENT_ORDERED, + EXTENT_LOCKED | EXTENT_WRITEBACK, 0, NULL)) { remove_extent_mapping(map, em); /* once for the rb tree */ |