Some optimization possibilities in data plane programming

TL;DR

This paper reviews challenges in data plane programming within SDN and proposes optimization techniques like language enrichment, compression, caching, and offloading, with practical implementation in P4 to enhance packet processing.

Contribution

It introduces novel optimization strategies for data plane programming and demonstrates their feasibility through implementation in P4 language.

Findings

Optimizations can significantly improve packet processing performance.

Practical implementations show the feasibility of proposed solutions.

Enhanced data plane programming can lead to better network efficiency.

Abstract

Software-defined networking (SDN) technology aims to create a highly flexible network by decoupling control plane and the data plane and programming them independently. There has been a lot of research on improving and optimizing the control plane, and data plane programming is a relatively new concept, so study on it is one of the hot topics for researchers. At the 2019 Dagstuhl Seminar, well-known scientists on computer networking discussed challenges and problems in the field of data plane programming that need to be addressed over the next 10 years. Based on this seminar issues and papers review, we suggested some possible solutions which are for optimizing data plane to improve packet processing performance and link utilization. The suggestions include (i) enriching data plane language with asynchronous external function, (ii) compression based on payload size, (iii) in-network caching for fast packet processing, and (iv) offloading external functions to an additional thread, virtual machine (VM) or server, etc. In addition, we implemented some of these in the P4 data plane language to illustrate the practicality.