ED FD: Improving the phi accrual failure detector
Naixue N. Xiong, Xavier Défago · Institutional Repositories DataBase (IRDB) · 2007
Failure detection is a fundamental issue for supporting dependability in distributed systems, and often is an important performance bottleneck in providing generic service (similar to IP address lookup) in the event of node failure. It is very necessary to find an acceptable, optimized failure detector (FD) before the FD is actually implemented. Ensuring acceptable quality of service (QoS) is made difficult by the relative unpredictability of the network environment. This paper compares QoS of several parametric and adaptive failure detection schemes. Also, we introduce an optimization over the existing methods, called exponential distribution failure detector (ED FD), which significantly improves QoS, especially in the design of real-time missioncritical systems. Extensive experiments have been carried out over several kinds of networks (a cluster group, a wired LAN, a wireless LAN, and a WAN). The experimental results have shown the properties of the adaptive FDs, and demonstrated that the proposed ED FD outperforms the existing FDs in terms of short detection time, low mistake rate and high query accuracy probability.