ext4: add support for extent pre-caching

Add a new fiemap flag which forces the all of the extents in an inode
to be cached in the extent_status tree.  This is critically important
when using AIO to a preallocated file, since if we need to read in
blocks from the extent tree, the io_submit(2) system call becomes
synchronous, and the AIO is no longer "A", which is bad.

In addition, for most files which have an external leaf tree block,
the cost of caching the information in the extent status tree will be
less than caching the entire 4k block in the buffer cache.  So it is
generally a win to keep the extent information cached.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

1 files changed, 72 insertions, 1 deletions

diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 08c1ac97647..01838875fca 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -482,7 +482,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
 		if (err < 0)
 			goto errout;
 	}
-	if (buffer_verified(bh))
+	if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE))
 		return bh;
 	err = __ext4_ext_check(function, line, inode,
 			       ext_block_hdr(bh), depth, pblk);
@@ -526,6 +526,71 @@ errout:
 	__read_extent_tree_block(__func__, __LINE__, (inode), (pblk),   \
 				 (depth), (flags))
 
+/*
+ * This function is called to cache a file's extent information in the
+ * extent status tree
+ */
+int ext4_ext_precache(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct ext4_ext_path *path = NULL;
+	struct buffer_head *bh;
+	int i = 0, depth, ret = 0;
+
+	if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		return 0;	/* not an extent-mapped inode */
+
+	down_read(&ei->i_data_sem);
+	depth = ext_depth(inode);
+
+	path = kzalloc(sizeof(struct ext4_ext_path) * (depth + 1),
+		       GFP_NOFS);
+	if (path == NULL) {
+		up_read(&ei->i_data_sem);
+		return -ENOMEM;
+	}
+
+	/* Don't cache anything if there are no external extent blocks */
+	if (depth == 0)
+		goto out;
+	path[0].p_hdr = ext_inode_hdr(inode);
+	ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0);
+	if (ret)
+		goto out;
+	path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr);
+	while (i >= 0) {
+		/*
+		 * If this is a leaf block or we've reached the end of
+		 * the index block, go up
+		 */
+		if ((i == depth) ||
+		    path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) {
+			brelse(path[i].p_bh);
+			path[i].p_bh = NULL;
+			i--;
+			continue;
+		}
+		bh = read_extent_tree_block(inode,
+					    ext4_idx_pblock(path[i].p_idx++),
+					    depth - i - 1,
+					    EXT4_EX_FORCE_CACHE);
+		if (IS_ERR(bh)) {
+			ret = PTR_ERR(bh);
+			break;
+		}
+		i++;
+		path[i].p_bh = bh;
+		path[i].p_hdr = ext_block_hdr(bh);
+		path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr);
+	}
+	ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED);
+out:
+	up_read(&ei->i_data_sem);
+	ext4_ext_drop_refs(path);
+	kfree(path);
+	return ret;
+}
+
 #ifdef EXT_DEBUG
 static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path)
 {
@@ -4766,6 +4831,12 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			return error;
 	}
 
+	if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) {
+		error = ext4_ext_precache(inode);
+		if (error)
+			return error;
+	}
+
 	/* fallback to generic here if not in extents fmt */
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return generic_block_fiemap(inode, fieinfo, start, len,