Commit 52b029f4 authored by Ethan Lien's avatar Ethan Lien Committed by David Sterba

btrfs: remove unnecessary EXTENT_UPTODATE state in buffered I/O path

After we copied data to page cache in buffered I/O, we
1. Insert a EXTENT_UPTODATE state into inode's io_tree, by
   endio_readpage_release_extent(), set_extent_delalloc() or
   set_extent_defrag().
2. Set page uptodate before we unlock the page.

But the only place we check io_tree's EXTENT_UPTODATE state is in
btrfs_do_readpage(). We know we enter btrfs_do_readpage() only when we
have a non-uptodate page, so it is unnecessary to set EXTENT_UPTODATE.

For example, when performing a buffered random read:

	fio --rw=randread --ioengine=libaio --direct=0 --numjobs=4 \
		--filesize=32G --size=4G --bs=4k --name=job \
		--filename=/mnt/file --name=job

Then check how many extent_state in io_tree:

	cat /proc/slabinfo | grep btrfs_extent_state | awk '{print $2}'

w/o this patch, we got 640567 btrfs_extent_state.
w/  this patch, we got    204 btrfs_extent_state.

Maintaining such a big tree brings overhead since every I/O needs to insert
EXTENT_LOCKED, insert EXTENT_UPTODATE, then remove EXTENT_LOCKED. And in
every insert or remove, we need to lock io_tree, do tree search, alloc or
dealloc extent states. By removing unnecessary EXTENT_UPTODATE, we keep
io_tree in a minimal size and reduce overhead when performing buffered I/O.
Reviewed-by: default avatarFilipe Manana <fdmanana@suse.com>
Reviewed-by: default avatarRobbie Ko <robbieko@synology.com>
Signed-off-by: default avatarEthan Lien <ethanlien@synology.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 7059c658
...@@ -211,7 +211,7 @@ static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start, ...@@ -211,7 +211,7 @@ static inline int set_extent_delalloc(struct extent_io_tree *tree, u64 start,
struct extent_state **cached_state) struct extent_state **cached_state)
{ {
return set_extent_bit(tree, start, end, return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | extra_bits, EXTENT_DELALLOC | extra_bits,
0, NULL, cached_state, GFP_NOFS, NULL); 0, NULL, cached_state, GFP_NOFS, NULL);
} }
...@@ -219,7 +219,7 @@ static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start, ...@@ -219,7 +219,7 @@ static inline int set_extent_defrag(struct extent_io_tree *tree, u64 start,
u64 end, struct extent_state **cached_state) u64 end, struct extent_state **cached_state)
{ {
return set_extent_bit(tree, start, end, return set_extent_bit(tree, start, end,
EXTENT_DELALLOC | EXTENT_UPTODATE | EXTENT_DEFRAG, EXTENT_DELALLOC | EXTENT_DEFRAG,
0, NULL, cached_state, GFP_NOFS, NULL); 0, NULL, cached_state, GFP_NOFS, NULL);
} }
......
...@@ -2924,9 +2924,6 @@ static void endio_readpage_release_extent(struct processed_extent *processed, ...@@ -2924,9 +2924,6 @@ static void endio_readpage_release_extent(struct processed_extent *processed,
* Now we don't have range contiguous to the processed range, release * Now we don't have range contiguous to the processed range, release
* the processed range now. * the processed range now.
*/ */
if (processed->uptodate && tree->track_uptodate)
set_extent_uptodate(tree, processed->start, processed->end,
&cached, GFP_ATOMIC);
unlock_extent_cached_atomic(tree, processed->start, processed->end, unlock_extent_cached_atomic(tree, processed->start, processed->end,
&cached); &cached);
...@@ -3613,7 +3610,6 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, ...@@ -3613,7 +3610,6 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
u64 extent_offset; u64 extent_offset;
u64 last_byte = i_size_read(inode); u64 last_byte = i_size_read(inode);
u64 block_start; u64 block_start;
u64 cur_end;
struct extent_map *em; struct extent_map *em;
int ret = 0; int ret = 0;
size_t pg_offset = 0; size_t pg_offset = 0;
...@@ -3672,7 +3668,6 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, ...@@ -3672,7 +3668,6 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
this_bio_flag = em->compress_type; this_bio_flag = em->compress_type;
iosize = min(extent_map_end(em) - cur, end - cur + 1); iosize = min(extent_map_end(em) - cur, end - cur + 1);
cur_end = min(extent_map_end(em) - 1, end);
iosize = ALIGN(iosize, blocksize); iosize = ALIGN(iosize, blocksize);
if (this_bio_flag != BTRFS_COMPRESS_NONE) if (this_bio_flag != BTRFS_COMPRESS_NONE)
disk_bytenr = em->block_start; disk_bytenr = em->block_start;
...@@ -3743,20 +3738,9 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, ...@@ -3743,20 +3738,9 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,
continue; continue;
} }
/* the get_extent function already copied into the page */ /* the get_extent function already copied into the page */
if (test_range_bit(tree, cur, cur_end,
EXTENT_UPTODATE, 1, NULL)) {
unlock_extent(tree, cur, cur + iosize - 1);
end_page_read(page, true, cur, iosize);
cur = cur + iosize;
pg_offset += iosize;
continue;
}
/* we have an inline extent but it didn't get marked up
* to date. Error out
*/
if (block_start == EXTENT_MAP_INLINE) { if (block_start == EXTENT_MAP_INLINE) {
unlock_extent(tree, cur, cur + iosize - 1); unlock_extent(tree, cur, cur + iosize - 1);
end_page_read(page, false, cur, iosize); end_page_read(page, true, cur, iosize);
cur = cur + iosize; cur = cur + iosize;
pg_offset += iosize; pg_offset += iosize;
continue; continue;
......
...@@ -6868,7 +6868,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, ...@@ -6868,7 +6868,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct btrfs_key found_key; struct btrfs_key found_key;
struct extent_map *em = NULL; struct extent_map *em = NULL;
struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map_tree *em_tree = &inode->extent_tree;
struct extent_io_tree *io_tree = &inode->io_tree;
read_lock(&em_tree->lock); read_lock(&em_tree->lock);
em = lookup_extent_mapping(em_tree, start, len); em = lookup_extent_mapping(em_tree, start, len);
...@@ -7031,8 +7030,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode, ...@@ -7031,8 +7030,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
} }
flush_dcache_page(page); flush_dcache_page(page);
} }
set_extent_uptodate(io_tree, em->start,
extent_map_end(em) - 1, NULL, GFP_NOFS);
goto insert; goto insert;
} }
not_found: not_found:
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment