Multibit Tries Packet Classification with Deep Reinforcement Learning

TL;DR

This paper introduces a scalable, learning-based packet classification engine that leverages deep reinforcement learning to select effective bits, significantly improving lookup speed and reducing memory usage in high-speed network applications.

Contribution

It presents a novel multibit tries classification method using deep reinforcement learning to select effective bits, enhancing performance and scalability over traditional approaches.

Findings

Outperforms traditional decision trees with 55% faster lookup times.

Reduces memory footprint compared to existing methods.

Effective bits learning is independent of ruleset, enabling adaptability.

Abstract

High performance packet classification is a key component to support scalable network applications like firewalls, intrusion detection, and differentiated services. With ever increasing in the line-rate in core networks, it becomes a great challenge to design a scalable and high performance packet classification solution using hand-tuned heuristics approaches. In this paper, we present a scalable learning-based packet classification engine and its performance evaluation. By exploiting the sparsity of ruleset, our algorithm uses a few effective bits (EBs) to extract a large number of candidate rules with just a few of memory access. These effective bits are learned with deep reinforcement learning and they are used to create a bitmap to filter out the majority of rules which do not need to be full-matched to improve the online system performance. Moreover, our EBs learning-based selection method is independent of the ruleset, which can be applied to varying rulesets. Our multibit tries classification engine outperforms lookup time both in worst and average case by 55% and reduce memory footprint, compared to traditional decision tree without EBs.