Abstract. Failure is an ordinary characteristic of large-scale distributed environments. Resubmission is a general strategy employed to cope with failures in grids. Here, we analytically and experimentally study resubmission in the case of random brokering (jobs are dispatched to a computing elements with a probability proportional to its computing power). We compare two cases when jobs are resubmitted to the broker or to the computing element. Results show that resubmit to the broker is a better strategy. Our approach is different from most existing race-based one as it is a bottom-up one: we start from a simple model of a grid and derive its characteristics.