Abstract

With the development of SDN, packet classifiers nowadays need to be provided with low update latency besides fast lookup performance because switches need to respond to update control messages from controllers in time to guarantee real-time service in SDN implementations. Classification in this scenario is called online packet classification. In this paper, we put forward an improved trie-based algorithm for online packet classification (ITOC), in which we provide a trie selection strategy to avoid occasional high update latency in the update process of online trie-based algorithms. Experiments are conducted to validate the effectiveness of our optimization and compare the performance of ITOC with the offline methods, DPDK ACL. Experimental results demonstrate that ITOC has the same level of lookup speed with DPDK ACL and greatly decreased the update latency as well. The update latency of ITOC is only 6.85% of DPDK ACL library in the best case.

Highlights

  • Motivation and Problem StatementAs one of the most important parts of network implementation, packet classification plays an important role when we provide network services, such as forwarding, routing, firewall, and some other complex services

  • As improved trie-based algorithm for online packet classification (ITOC) is an online packet classification algorithm improved from Data Plane Development Kit (DPDK) ACL, we conducted these experiments in the simulation environment

  • Our paper is based on the contribution of DPDK ACL library and aimed to improve the performance of trie-based packet classification algorithms in online problems

Read more

Summary

Motivation and Problem Statement

As one of the most important parts of network implementation, packet classification plays an important role when we provide network services, such as forwarding, routing, firewall, and some other complex services. The working status of the switches remains unchanged Such a kind of packet classification is viewed as offline packet classification problem. The network is changeable, and the working status of SDN switches dynamically changes during working. This kind of packet classification is called online packet classification problem. In online packet classification problem, low latency must be taken into consideration while implementing packet classification methods. The update latency of the packet classification method in SDN switches influences the forward speed of the switches when the lookup table changes. Many new network implementations [3] put forward the same demands, so a packet classification method for online problems is intensively needed

Summary and Limitations of Prior Art
Classification Based on Trie
Optimizations in Trie-Based Algorithm
Update Latency Prediction
Optimization
Implementation in DPDK
Simulation Results
Conclusions
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call