Btrfs: make balance code choose more wisely when relocating

Currently, we can panic the box if the first block group we go to move is of a
type where there is no space left to move those extents.  For example, if we
fill the disk up with data, and then we try to balance and we have no room to
move the data nor room to allocate new chunks, we will panic.  Change this by
checking to see if we have room to move this chunk around, and if not, return
-ENOSPC and move on to the next chunk.  This will make sure we remove block
groups that are moveable, like if we have alot of empty metadata block groups,
and then that way we make room to be able to balance our data chunks as well.
Tested this with an fs that would panic on btrfs-vol -b normally, but no longer
panics with this patch.

V1->V2:
-actually search for a free extent on the device to make sure we can allocate a
chunk if need be.

-fix btrfs_shrink_device to make sure we actually try to relocate all the
chunks, and then if we can't return -ENOSPC so if we are doing a btrfs-vol -r
we don't remove the device with data still on it.

-check to make sure the block group we are going to relocate isn't the last one
in that particular space

-fix a bug in btrfs_shrink_device where we would change the device's size and
not fix it if we fail to do our relocate

Signed-off-by: Josef Bacik <jbacik@redhat.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 87 insertions, 0 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4bd04f3fa8bb..4c7c9467f224 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -7402,6 +7402,93 @@ out:
 }
 #endif
 
+/*
+ * checks to see if its even possible to relocate this block group.
+ *
+ * @return - -1 if it's not a good idea to relocate this block group, 0 if its
+ * ok to go ahead and try.
+ */
+int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr)
+{
+	struct btrfs_block_group_cache *block_group;
+	struct btrfs_space_info *space_info;
+	struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
+	struct btrfs_device *device;
+	int full = 0;
+	int ret = 0;
+
+	block_group = btrfs_lookup_block_group(root->fs_info, bytenr);
+
+	/* odd, couldn't find the block group, leave it alone */
+	if (!block_group)
+		return -1;
+
+	/* no bytes used, we're good */
+	if (!btrfs_block_group_used(&block_group->item))
+		goto out;
+
+	space_info = block_group->space_info;
+	spin_lock(&space_info->lock);
+
+	full = space_info->full;
+
+	/*
+	 * if this is the last block group we have in this space, we can't
+	 * relocate it.
+	 */
+	if (space_info->total_bytes == block_group->key.offset) {
+		ret = -1;
+		spin_unlock(&space_info->lock);
+		goto out;
+	}
+
+	/*
+	 * need to make sure we have room in the space to handle all of the
+	 * extents from this block group.  If we can, we're good
+	 */
+	if (space_info->bytes_used + space_info->bytes_reserved +
+	    space_info->bytes_pinned + space_info->bytes_readonly +
+	    btrfs_block_group_used(&block_group->item) <
+	    space_info->total_bytes) {
+		spin_unlock(&space_info->lock);
+		goto out;
+	}
+	spin_unlock(&space_info->lock);
+
+	/*
+	 * ok we don't have enough space, but maybe we have free space on our
+	 * devices to allocate new chunks for relocation, so loop through our
+	 * alloc devices and guess if we have enough space.  However, if we
+	 * were marked as full, then we know there aren't enough chunks, and we
+	 * can just return.
+	 */
+	ret = -1;
+	if (full)
+		goto out;
+
+	mutex_lock(&root->fs_info->chunk_mutex);
+	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
+		u64 min_free = btrfs_block_group_used(&block_group->item);
+		u64 dev_offset, max_avail;
+
+		/*
+		 * check to make sure we can actually find a chunk with enough
+		 * space to fit our block group in.
+		 */
+		if (device->total_bytes > device->bytes_used + min_free) {
+			ret = find_free_dev_extent(NULL, device, min_free,
+						   &dev_offset, &max_avail);
+			if (!ret)
+				break;
+			ret = -1;
+		}
+	}
+	mutex_unlock(&root->fs_info->chunk_mutex);
+out:
+	btrfs_put_block_group(block_group);
+	return ret;
+}
+
 static int find_first_block_group(struct btrfs_root *root,
 		struct btrfs_path *path, struct btrfs_key *key)
 {