drbd: move start io accounting before activity log transaction

The IO accounting of the drbd "queue depth" was misleading.
We only started IO accounting once we already wrote the activity log.
Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

drivers/block/drbd/drbd_req.c

@@ -1056,6 +1056,9 @@ drbd_request_prepare(struct drbd_conf *mdev, struct bio *bio, unsigned long star
 		req->private_bio = NULL;
 	}
 
+	/* Update disk stats */
+	_drbd_start_io_acct(mdev, req);
+
 	if (rw == WRITE && req->private_bio && req->i.size
 	&& !test_bit(AL_SUSPENDED, &mdev->flags)) {
 		if (!drbd_al_begin_io_fastpath(mdev, &req->i)) {
@@ -1095,9 +1098,6 @@ static void drbd_send_and_submit(struct drbd_conf *mdev, struct drbd_request *re
 		goto out;
 	}
 
-	/* Update disk stats */
-	_drbd_start_io_acct(mdev, req);
-
 	/* We fail READ/READA early, if we can not serve it.
 	 * We must do this before req is registered on any lists.
 	 * Otherwise, drbd_req_complete() will queue failed READ for retry. */