DCCS: A dual congestion control signals based TCP for datacenter networks

Abstract

As cloud computing advances, datacenter networks (DCNs) face unprecedented pressure due to the increasing prevalence of high bandwidth and low delay applications. Current reliable transmission protocols such as TCP harness packet loss, network delay, and Explicit Congestion Notification (ECN) for congestion control, aiming to maintain low latency and high throughput. We investigate the efficacy of ECN-based protocols against incast congestion in one-hop networks and delay-based protocols for maintaining low end-to-end delay in multi-hop networks, at the expense of throughput fairness. Thus, we introduce a novel TCP protocol, Dual Congestion Control Signals (DCCS), merging ECN and delay signals for a broader congestion control mechanism. DCCS effectively handles burst traffic, prevents packet loss, ensures low end-to-end delay, and resolves throughput unfairness by determining a precise minimum round-trip time (RTT) for each flow through a drain signal. Simulations on ns-3 confirm that DCCS surpasses ECN-based (i.e., DCTCP), delay-based (i.e., DC-Vegas and Swift), and hybrid-based protocols (i.e., EAR) in fat-tree topology under realistic workload, cutting down Flow Completion Time (FCT) by 3.8%–20.5%. This substantiates DCCS’s competency in providing high-quality service for DCNs.