Congestion Avoidance and Synchronized Rate Control in Data Center Network

Abstract

TCP Incast, also known as TCP throughput collapse, is a term used to de- scribe a link capacity under-utilization phenomenon in certain many-to-one communication patterns, typically in many datacenter applications. The main root cause of TCP Incast analyzed by prior works is attributed to packet drops at the congestion switch that result in TCP timeout. Conges- tion control algorithms have been developed to reduce or eliminate packet drops at the congestion switch. In this paper, the performance of Quantized Congestion Noti?cation (QCN) with respect to the TCP incast problem dur- ing data access from clustered servers in datacenters are investigated. QCN can e ectively control link rates very rapidly in a datacenter environment. However, it performs poorly when TCP Incast is observed. To explain this low link utilization, we examine the rate ?uctuation of di erent ?ows within one synchronous reading request, and ?nd that the poor performance of TCP throughput with QCN is due to the rate unfairness of di erent ?ows. There- fore, an enhanced QCN congestion control algorithm, called fair Quantized Congestion Noti?cation (FQCN), is proposed to improve fairness of multiple ?ows sharing one bottleneck link. We evaluate the performance of FQCN as compared to that of QCN in terms of fairness and convergence with four simultaneous and eight staggered source ?ows. As compared to QCN, fair- ness is improved greatly and the queue length at the bottleneck link con- verges to the equilibrium queue length very fast. The e ects of FQCN to TCP throughput collapse are also investigated. Simulation results show that FQCN signi?cantly enhances TCP throughput performance in a TCP Incast setup