IA-TCP: A Rate Based Incast-Avoidance Algorithm for TCP in Data Center Networks
10 June 2012
In recent years, the data center networks commonly accommodate applications such as MapReduce and web search that inherently shows the incast communication pattern; multiple servers simultaneously transmit TCP data to a single aggregator. In this environment, the TCP performance is significantly degraded in terms of goodput and query completion time, as a result of the severe packet loss at Top of Rack (ToR) switches. The TCP senders aggressively transmit packets causing throughput collapse even though the network pipe size, i.e., bandwidth-delay product, is extremely small. In this paper, we introduce a novel end-to-end congestion control algorithm that avoids the TCP incast congestion problem. While previous studies mainly focused on window-based control algorithms, we employ the rate-based control to ensure that the total number of outstanding packets does not exceed the network pipe size. Through extensive NS-2 simulations, we validate that our algorithm is scalable in terms of the number of senders achieving enhanced goodput and zero timeouts.
