Minimizing Transient Congestion during Network Update in Data Centers

Data centers are increasingly relying on software defined networking (SDN) to orchestrate data transmission. To maximize network utilization, the SDN controller needs to frequently update the data plane as the network conditions change. Due to its asynchronous nature, data plane update may result in serious transient congestion and packet loss. Prior work strives to find a congestion-free update plan with multiple stages, each of which guarantees that there will be no congestion independent of the update order. This approach prevents the network from being fully utilized and requires solving a series of LP with scalability challenges. In this paper, we study the general problem of minimizing transient congestion during network update, given the number of intermediate stages. This exposes the tradeof between update speed and transient congestion, which may be absorbed by switch buffers, and allows the operator to navigate a broader design space. We formulate the minimum congestion update problem (MCUP) as an optimization pro- gram, and propose heuristics to find the update sequence efficiently. Preliminary results show that our approach in-creases link utilization by 20% and reduces update time by 50% compared to prior work.