arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.13488cs.NI
收藏

快速逆模型变换:面向快速数据平面验证的代数框架

Fast Inverse Model Transformation: Algebraic Framework for Fast Data Plane Verification

Shenshen Chen, Jian Luo, Dong Guo, Kai Gao, Yang Richard Yang

AI总结:

本文提出首个系统化建模集中式数据平面验证的代数框架FIMT,基于其指导重构出优化的NeoFlash系统,实验证明其性能优于现有同类最先进系统,为快速数据平面验证提供理论与实践支撑。

摘要:

数据平面验证(DPV)通过分析路由表,检测网络运行与规划过程中的路由异常和策略违规,因此已成为强化网络基础设施及上层计算系统的重要工具。过去十年该领域取得了长足进展,当前最先进的DPV系统可在亚微秒级完成单条转发规则更新的验证。\n本文提出快速逆模型变换(FIMT),这是首个可对集中式DPV系统进行系统化建模与分析的理论框架。FIMT揭示了模型更新过程中的代数结构——这是快速DPV系统的核心步骤,因此可借助代数性质系统化分析多款DPV系统的正确性。该理论还指导了NeoFlash的设计与实现,NeoFlash是Flash的重构版本,融入了新型优化技术。评估结果显示,在多种数据集上NeoFlash的性能均优于现有最先进的集中式DPV系统,同时揭示了实现快速DPV关键技术的相关洞见。

英文摘要:

Data plane verification (DPV) analyzes routing tables and detects routing abnormalities and policy violations during network operation and planning. Thus, it has become an important tool to harden the networking infrastructure and the computing systems building on top. Substantial advancements have been made in the last decade and state-of-the-art DPV systems can achieve sub-us verification for an update of a single forwarding rule. In this paper, we introduce fast inverse model transformation (FIMT), the first theoretical framework to systematically model and analyze centralized DPV systems. FIMT reveals the algebraic structure in the model update process, a key step in fast DPV systems. Thus, it can systematically analyze the correctness of several DPV systems, using algebraic properties. The theory also guides the design and implementation of NeoFlash, a refactored version of Flash with new optimization techniques. Evaluations show that NeoFlash outperforms existing state-of-the-art centralized DPV systems in various datasets and reveal insights to key techniques towards fast DPV.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑