Load balance algorithm for an OPSquare datacenter network under real application traffic

Autor: Bitao Pan, Jingyan Wang, Elham Khani, Gonzalo Guelbenzu, Fulong Yan, Nicola Calabretta, Shaojuan Zhang, Xiaotao Guo, Xuwei Xue
Přispěvatelé: Eindhoven Hendrik Casimir institute, Electro-Optical Communication, Low Latency Interconnect Networks
Rok vydání: 2020
Předmět:
Zdroj: Journal of Optical Communications and Networking, 12(8):9132990, 239-250. Institute of Electrical and Electronics Engineers
Journal of Optical Communications and Networking
ISSN: 1943-0639
1943-0620
DOI: 10.1364/jocn.394023
Popis: To cope with the dynamic datacenter (DC) traffic matrix generated by multiple applications, load balancing algorithms can be deployed to improve the datacenter network (DCN) performance. OPSquare, as a promising optical DCN architecture, adopts fast optical switches to provide high bandwidth, low latency, large scalability, and cost and energy efficiency. Current load balancing algorithms are not optimal for improving the network performance of an OPSquare DCN. To optimize the network performance of OPSquare, a dedicated load balancing algorithm considering the peculiarity of OPSquare should be addressed. Moreover, network virtualization in today’s data DC creates new heterogeneous traffic patterns different from what so far have been reported in the literature. A synthetic virtualized DC traffic model is needed to properly evaluate the performance of the load balancing algorithms. In this paper, we provide a synthetic traffic model by capturing the traffic traces of the virtualized DC applications running in a DC. The captured traffic model is used in the simulator to quantitatively evaluate the network performance of an OPSquare DCN. Then we propose and evaluate the lowest path buffer (LPB) algorithm to optimize the OPSquare DCN performance. LPB considers the buffer occupation in the whole path (from the source to the destination) rather than the local buffer occupation. The network performance improvements of LPB are demonstrated under different central controller update periods, traffic destination distributions, and network sizes. Compared with the round-robin, DRILL, and LocalFlow load balancing algorithms, LPB could achieve 23.7%, 46%, and 32.1% less latency, respectively. Besides, LPB provides lower packet loss in comparison with round-robin, DRILL, and LocalFlow.
Databáze: OpenAIRE