| 摘要 |
The data center networks commonly accommodate applications 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. The present invention introduces a novel end-to-end congestion control algorithm that avoids the TCP incast congestion problem. While prior arts mainly focused on window-based control algorithms, the present invention employs the rate-based control to ensure that the total number of outstanding packets does not exceed the network pipe size. Also, simulations validate that IA-TCP algorithm is scalable in terms of the number of senders achieving enhanced goodput and zero timeouts. |
