Towards real-time non-preemptive multicast scheduling in reconfigurable data center networks

Multicast has emerged as a primary communication pattern in datacenter networks due to the increasing demand for distributed data-parallel applications. To accelerate multicast traffic, the emerging reconfigurable circuit technology, which can establish circuit connections among switches, has been proposed as a promising paradigm for datacenter networks. This paper investigates how to accelerate the non-preemptive multicast flows in a demand-aware manner in reconfigurable datacenter networks. Firstly, the problem of scheduling circuit switches to minimize the average completion time is formulated and proved to be NP-hard. To address the conflicts between different multicast flows under the bandwidth constraint, a connection based hypergraph is constructed and then a two round matching algorithm is proposed under the bandwidth constraint. Additionally, to further reduce the average completion time, we introduce a method to utilize the remaining capacity of the ToR switches by splitting the unscheduled flows. The proposed algorithm is proved to have an approximation ratio of 22n\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$2\sqrt{2n}$$\end{document}, where n represents the number of Top-of-Rack (ToR) switches. Finally, the extensive simulations demonstrate the effectiveness of the proposed algorithm in reducing the average completion time of flows compared to state-of-the-art algorithms.