Using leases to support server-driven consistency in large-scale systems

Abstract This paper introduces volume leases as a mechanismfor providing cache consistency for large-scale, geographically distributed networks. Volume leases are a variationof leases, which were originally designed for distributed file systems. Using trace-driven simulation, we comparetwo new algorithms against four existing cache consistency algorithms and show that our new algorithms providestrong consistency while maintaining scalability and faulttolerance. For a trace-based workload of web accesses,we find that volumes can reduce message traffic at servers by 40 % compared to a standard lease algorithm, and thatvolumes can considerably reduce the peak load at servers when popular objects are modified.