SSL : A surrogate-based method for large-scale statistical latency measurement

Understanding the statistical latency between two groups of hosts in a period of time is of great significance to a wide variety of Internet applications and services, such as Service-Level Agreement (SLA) compliance monitoring and Virtual Network Function (VNF) placement. However, direct latency measurement methods are not always applicable to large-scale situations while the existing indirect methods often incur extra deployment costs or security problems. To address this challenge, we design an indirect method based on widely-distributed clients called SSL (Surrogate-based method for large-scale Statistical Latency measurement). SSL estimates the latency between two arbitrary hosts using the measured latencies from several selected clients near one end host, which are called the host's surrogates, to the other end host. To overcome the limited capacity of the volatile clients with unstable CPU, memory, and bandwidth resources, we propose an innovative two-step measurement task assignment mechanism for SSL that can achieve high accuracy measurement results while satisfying the resource constraints simultaneously. Moreover, SSL adopts a sampling technique to reduce the overhead in large-scale measurements, and a resampling technique to determine the confidence interval. Simulation experiments show that SSL can achieve more than 90 percent accuracy in most situations with 10 percent client density and 15 percent sampling rate.