Aspects of provisioning computing units based on improved failure resiliency are described. In one embodiment, an infrastructure component shared between a pair of computing units is identified. A failure rate for the infrastructure component is obtained, and a failure probability for a class of assigned computing units is computed based in part on the failure rate. A spread request related to the class of assigned computing units is also received. In response to the spread request, an altered composition of computing units is determined, and a difference between a failure probability for the altered composition of computing units and the failure probability for the class of assigned computing units is computed. In one embodiment, when a spread score improvement value associated with the difference meets a spread criteria of the spread request, the altered composition of computing units may be provisioned for use.