Criso: An Incremental Scalable and Cost-Effective Network Architecture for Data Centers

Hao Feng, Yuhui Deng, Xiao Qin, Geyong Min

Abstract

With the explosive data growth, an enormous number of computing and networking components (e.g., servers, switches, and wires) are continuously being augmented to data centers. Data center networks (DCNs) - maintaining a high network capacity - must be cost efficient, incrementally scalable, and fault-tolerant. To address these challenges, we propose in this study a new type of DCN architecture referred to as Criso . Different from the existing network architectures, Criso is designed hierarchically and recursively by employing two ports servers and commodity switches. Criso is constructed based on numerous isomorphic pod s, each of which leverages external interfaces supplied by switches to connect with neighboring pods. Additionally, a pod -based and fault-tolerant routing algorithm is designed to handle multiple failures. Criso has an array of promising features, including being cost-efficient and delivering a high-network capacity that can be extended to millions of nodes. The analytic results demonstrate that Criso is significantly superior to the four state-of-the-art data center structures in terms of network capacity, scalability, cost, power consumption, and other static characteristics. Furthermore, the experimental results unveil that Criso satisfies the fault-tolerant demands of modern data centers. Compared to the four existing topologies (i.e., DCell , BCube , FiConn , Fat-Tree ) that have been widely investigated, Criso is adroit at maintaining a balanced performance in terms of throughput and latency.
BibTeX
@article{feng2021criso,
  author = {Hao Feng and Yuhui Deng and Xiao Qin and Geyong Min},
  title = {{Criso: An Incremental Scalable and Cost-Effective Network Architecture for Data Centers}},
  journal = {IEEE Trans. Netw. Serv. Manag.},
  year = {2021},
  url = {https://openreview.net/forum?id=Lv5i2kdvqC},
}

Loading related content...

Figure