btrfs: use cached state when looking for delalloc ranges with fiemap

During fiemap, whenever we find a hole or prealloc extent, we will look
for delalloc in that range, and one of the things we do for that is to
find out ranges in the inode's io_tree marked with EXTENT_DELALLOC, using
calls to count_range_bits().

Since we process file extents from left to right, if we have a file with
several holes or prealloc extents, we benefit from keeping a cached extent
state record for calls to count_range_bits(). Most of the time the last
extent state record we visited in one call to count_range_bits() matches
the first extent state record we will use in the next call to
count_range_bits(), so there's a benefit here. So use an extent state
record to cache results from count_range_bits() calls during fiemap.

This change is part of a patchset that has the goal to make performance
better for applications that use lseek's SEEK_HOLE and SEEK_DATA modes to
iterate over the extents of a file. Two examples are the cp program from
coreutils 9.0+ and the tar program (when using its --sparse / -S option).
A sample test and results are listed in the changelog of the last patch
in the series:

  1/9 btrfs: remove leftover setting of EXTENT_UPTODATE state in an inode's io_tree
  2/9 btrfs: add an early exit when searching for delalloc range for lseek/fiemap
  3/9 btrfs: skip unnecessary delalloc searches during lseek/fiemap
  4/9 btrfs: search for delalloc more efficiently during lseek/fiemap
  5/9 btrfs: remove no longer used btrfs_next_extent_map()
  6/9 btrfs: allow passing a cached state record to count_range_bits()
  7/9 btrfs: update stale comment for count_range_bits()
  8/9 btrfs: use cached state when looking for delalloc ranges with fiemap
  9/9 btrfs: use cached state when looking for delalloc ranges with lseek

Reported-by: Wang Yugui <wangyugui@e16-tech.com>
Link: https://lore.kernel.org/linux-btrfs/20221106073028.71F9.409509F4@e16-tech.com/
Link: https://lore.kernel.org/linux-btrfs/CAL3q7H5NSVicm7nYBJ7x8fFkDpno8z3PYt5aPU43Bajc1H0h1Q@mail.gmail.com/
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 10 insertions, 1 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 33cc3a9a2b68..704ae7c08867 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3698,6 +3698,7 @@ static int fiemap_search_slot(struct btrfs_inode *inode, struct btrfs_path *path
 static int fiemap_process_hole(struct btrfs_inode *inode,
 			       struct fiemap_extent_info *fieinfo,
 			       struct fiemap_cache *cache,
+			       struct extent_state **delalloc_cached_state,
 			       struct btrfs_backref_share_check_ctx *backref_ctx,
 			       u64 disk_bytenr, u64 extent_offset,
 			       u64 extent_gen,
@@ -3722,6 +3723,7 @@ static int fiemap_process_hole(struct btrfs_inode *inode,
 		bool delalloc;
 
 		delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end,
+							delalloc_cached_state,
 							&delalloc_start,
 							&delalloc_end);
 		if (!delalloc)
@@ -3892,6 +3894,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 {
 	const u64 ino = btrfs_ino(inode);
 	struct extent_state *cached_state = NULL;
+	struct extent_state *delalloc_cached_state = NULL;
 	struct btrfs_path *path;
 	struct fiemap_cache cache = { 0 };
 	struct btrfs_backref_share_check_ctx *backref_ctx;
@@ -3966,6 +3969,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 			const u64 range_end = min(key.offset, lockend) - 1;
 
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
+						  &delalloc_cached_state,
 						  backref_ctx, 0, 0, 0,
 						  prev_extent_end, range_end);
 			if (ret < 0) {
@@ -4006,6 +4010,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 						 extent_len, flags);
 		} else if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
+						  &delalloc_cached_state,
 						  backref_ctx,
 						  disk_bytenr, extent_offset,
 						  extent_gen, key.offset,
@@ -4013,6 +4018,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo,
 		} else if (disk_bytenr == 0) {
 			/* We have an explicit hole. */
 			ret = fiemap_process_hole(inode, fieinfo, &cache,
+						  &delalloc_cached_state,
 						  backref_ctx, 0, 0, 0,
 						  key.offset, extent_end - 1);
 		} else {
@@ -4070,7 +4076,8 @@ check_eof_delalloc:
 	path = NULL;
 
 	if (!stopped && prev_extent_end < lockend) {
-		ret = fiemap_process_hole(inode, fieinfo, &cache, backref_ctx,
+		ret = fiemap_process_hole(inode, fieinfo, &cache,
+					  &delalloc_cached_state, backref_ctx,
 					  0, 0, 0, prev_extent_end, lockend - 1);
 		if (ret < 0)
 			goto out_unlock;
@@ -4088,6 +4095,7 @@ check_eof_delalloc:
 			delalloc = btrfs_find_delalloc_in_range(inode,
 								prev_extent_end,
 								i_size - 1,
+								&delalloc_cached_state,
 								&delalloc_start,
 								&delalloc_end);
 			if (!delalloc)
@@ -4102,6 +4110,7 @@ check_eof_delalloc:
 out_unlock:
 	unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state);
 out:
+	free_extent_state(delalloc_cached_state);
 	btrfs_free_backref_share_ctx(backref_ctx);
 	btrfs_free_path(path);
 	return ret;