Btrfs: cache extent states in defrag code path

When locking file ranges in the inode's io_tree, cache the first
extent state that belongs to the target range, so that when unlocking
the range we don't need to search in the io_tree again, reducing cpu
time and making and therefore holding the io_tree's lock for a shorter
period.

Signed-off-by: Filipe David Borba Manana <fdmanana@gmail.com>
Signed-off-by: Chris Mason <clm@fb.com>
This commit is contained in:
Filipe Manana 2014-03-11 13:56:15 +00:00 committed by Chris Mason
parent 3bbb24b20a
commit 308d9800b2
1 changed files with 9 additions and 4 deletions

View File

@ -986,10 +986,13 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
read_unlock(&em_tree->lock);
if (!em) {
struct extent_state *cached = NULL;
u64 end = start + len - 1;
/* get the big lock and read metadata off disk */
lock_extent(io_tree, start, start + len - 1);
lock_extent_bits(io_tree, start, end, 0, &cached);
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
unlock_extent(io_tree, start, start + len - 1);
unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
if (IS_ERR(em))
return NULL;
@ -1128,10 +1131,12 @@ again:
page_start = page_offset(page);
page_end = page_start + PAGE_CACHE_SIZE - 1;
while (1) {
lock_extent(tree, page_start, page_end);
lock_extent_bits(tree, page_start, page_end,
0, &cached_state);
ordered = btrfs_lookup_ordered_extent(inode,
page_start);
unlock_extent(tree, page_start, page_end);
unlock_extent_cached(tree, page_start, page_end,
&cached_state, GFP_NOFS);
if (!ordered)
break;