Analytical modeling and comparison of fault-tolerant message flow control mechanisms in torus-connected networks

作者：Safaei F^*; Khonsari A

来源：Journal of Supercomputing, 2012, 59(2): 941-974.

DOI：10.1007/s11227-010-0480-5

• Fault-tolerance
• Torus
• Scouting switching
• Pipelined circuit switching
• Circuit switching
• Adaptive routing
• Virtual channels
• Message latency
• Queuing theory
• Performance evaluation

In many environments, rather than minimizing message latency or maximizing network performance, the ability to survive beyond the failure of individual network components is the main issue of interests. The nature of Wormhole Switching (WS) leads to high network throughput and low message latencies. However, in the vicinity of faulty regions, these behaviors cause rapid congestion, provoking the network becomes deadlocked. While techniques such as adaptive routing can alleviate the problem, they cannot completely solve the problem. Thus, there have been extreme studies on other types of switching mechanisms in networking and multicomputers communities. In this paper, we present a general mathematical model to assess the relative performance merits of three well-known fault-tolerant switching methods in tori, namely Scouting Switching (SS), Pipelined Circuit Switching (PCS), and Circuit Switching (CS). We have carried out extensive simulation experiments, the results of which are used to validate the proposed analytical models. We have also conducted an extensive comparative performance analysis, by means of analytical modeling, of SS, PCS, and CS under various working conditions. The analytical results reveal that SS shows substantial performance improvements for low to moderate failure rates over PCS and CS, which achieves close to WS performance. PCS can provide superior performance over CS and behaves the same or in some occasions worse than SS, under light and moderate traffic, especially with the same hardware requirements.

• 出版日期2012-2