lk/linux-kernel-test
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Btrfs: finish ordered extents in their own thread

Browse Source 
We noticed that the ordered extent completion doesn't really rely on having
a page and that it could be done independantly of ending the writeback on a
page.  This patch makes us not do the threaded endio stuff for normal
buffered writes and direct writes so we can end page writeback as soon as
possible (in irq context) and only start threads to do the ordered work when
it is actually done.  Compression needs to be reworked some to take
advantage of this as well, but atm it has to do a find_get_page in its endio
handler so it must be done in its own thread.  This makes direct writes
quite a bit faster.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
This commit is contained in:
Josef Bacik
2012-05-02 14:00:54 -04:00
parent 4e89915220
commit 5fd0204355
7 changed files with 164 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
fs/btrfs/extent_io.c
View File

@@ -1172,9 +1172,8 @@ int set_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
cached_state, mask);
}
static int clear_extent_uptodate(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state,
gfp_t mask)
int clear_extent_uptodate(struct extent_io_tree *tree, u64 start, u64 end,
struct extent_state **cached_state, gfp_t mask)
{
return clear_extent_bit(tree, start, end, EXTENT_UPTODATE, 0, 0,
cached_state, mask);
@@ -2221,17 +2220,7 @@ int end_extent_writepage(struct page *page, int err, u64 start, u64 end)
uptodate = 0;
}
if (!uptodate && tree->ops &&
tree->ops->writepage_io_failed_hook) {
ret = tree->ops->writepage_io_failed_hook(NULL, page,
start, end, NULL);
/* Writeback already completed */
if (ret == 0)
return 1;
}
if (!uptodate) {
clear_extent_uptodate(tree, start, end, NULL, GFP_NOFS);
ClearPageUptodate(page);
SetPageError(page);
}