Tracking elephant flows in internet backbone traffic with an FPGA-based cache

This paper presents an FPGA-friendly approach to tracking elephant flows in network traffic. Our approach, single step segmented least recently used (S³-LRU) policy, is a network traffic-friendly replacement policy for maintaining flow states in a Naiumlive hash table (NHT). We demonstrate that our S³-LRU approach preserves elephant flows: conservatively promoting potential elephants and evicting lowrate flows in LRU manner. Our approach keeps flow-state of any elephant since start-of-day and provides a significant improvement over filtering approaches proposed in previous work. Our FPGA-based implementation of the S³-LRU in combination with an NHT suites well the parallel access to block memories while capitalising on the retuning of parameters through dynamic-reprogramming.