btrfs_search_slot: reduce lock contention by cowing in two stages

A btree block cow has two parts, the first is to allocate a destination
block and the second is to copy the old bock over.

The first part needs locks in the extent allocation tree, and may need to
do IO.  This changeset splits that into a separate function that can be
called without any tree locks held.

btrfs_search_slot is changed to drop its path and start over if it has
to COW a contended block.  This often means that many writers will
pre-alloc a new destination for a the same contended block, but they
cache their prealloc for later use on lower levels in the tree.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 16 insertions, 0 deletions

diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index d43e14c7471..0cc314c10d6 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -56,3 +56,19 @@ int btrfs_tree_locked(struct extent_buffer *eb)
 {
 	return mutex_is_locked(&eb->mutex);
 }
+
+int btrfs_path_lock_waiting(struct btrfs_path *path, int level)
+{
+	int i;
+	struct extent_buffer *eb;
+	for (i = level; i <= level + 1 && i < BTRFS_MAX_LEVEL; i++) {
+		eb = path->nodes[i];
+		if (!eb)
+			break;
+		smp_mb();
+		if (!list_empty(&eb->mutex.wait_list))
+			return 1;
+	}
+	return 0;
+}
+