Designs for distributed systems must consider the possibility that failures will arise and must adopt specific failure detection strategies. We describe and analyze a self-regulating failure-detection algorithm that bounds resource usage and failure-detection latency, while automatically reassigning resources to improve failure-detection latency as system size decreases. We apply the algorithm to (1) Jini leasing, (2) service registration in the Service Location Protocol (SLP), and (3) SLP service polling.
