Btrfs: improve the performance of the csums lookup

It is very likely that there are several blocks in bio, it is very
inefficient if we get their csums one by one. This patch improves
this problem by getting the csums in batch.

According to the result of the following test, the execute time of
__btrfs_lookup_bio_sums() is down by ~28%(300us -> 217us).

 # dd if=<mnt>/file of=/dev/null bs=1M count=1024

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>

1 files changed, 58 insertions, 0 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1e4627c33548..617b5779b95b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1777,6 +1777,64 @@ out:
 	return ret;
 }
 
+void extent_cache_csums_dio(struct extent_io_tree *tree, u64 start, u32 csums[],
+			    int count)
+{
+	struct rb_node *node;
+	struct extent_state *state;
+
+	spin_lock(&tree->lock);
+	/*
+	 * this search will find all the extents that end after
+	 * our range starts.
+	 */
+	node = tree_search(tree, start);
+	BUG_ON(!node);
+
+	state = rb_entry(node, struct extent_state, rb_node);
+	BUG_ON(state->start != start);
+
+	while (count) {
+		state->private = *csums++;
+		count--;
+		state = next_state(state);
+	}
+	spin_unlock(&tree->lock);
+}
+
+static inline u64 __btrfs_get_bio_offset(struct bio *bio, int bio_index)
+{
+	struct bio_vec *bvec = bio->bi_io_vec + bio_index;
+
+	return page_offset(bvec->bv_page) + bvec->bv_offset;
+}
+
+void extent_cache_csums(struct extent_io_tree *tree, struct bio *bio, int bio_index,
+			u32 csums[], int count)
+{
+	struct rb_node *node;
+	struct extent_state *state = NULL;
+	u64 start;
+
+	spin_lock(&tree->lock);
+	do {
+		start = __btrfs_get_bio_offset(bio, bio_index);
+		if (state == NULL || state->start != start) {
+			node = tree_search(tree, start);
+			BUG_ON(!node);
+
+			state = rb_entry(node, struct extent_state, rb_node);
+			BUG_ON(state->start != start);
+		}
+		state->private = *csums++;
+		count--;
+		bio_index++;
+
+		state = next_state(state);
+	} while (count);
+	spin_unlock(&tree->lock);
+}
+
 int get_state_private(struct extent_io_tree *tree, u64 start, u64 *private)
 {
 	struct rb_node *node;