Measuring the Cost of Online Load-Balancing in Distributed Range-Queriable Systems

Free registration required

Executive Summary

Data skew is a well-documented concern for a variety of applications. For instance, it has been widely observed that most Internet-scale applications, including P2P ones, exhibit highly skewed workloads. Failing or departing nodes further reduce the availability of various content. Consequently, resources become scarce, servers get overloaded and throughput can diminish due to high workloads that can by themselves cause denial of service. Data replication techniques is one commonly utilized solution to remedy these situations. Nevertheless, there are cases in which the requested resources cannot be arbitrarily replicated and retrieved across a distributed set of nodes.

  • Format: PDF
  • Size: 223.89 KB