Control Plane Compression

We develop an algorithm capable of compressing large networks into a smaller ones with similar control plane behavior: For every stable routing solution in the large, original network, there exists a corresponding solution in the compressed network, and vice versa. Our compression algorithm preserve...

Full description

Saved in:
Bibliographic Details
Main Authors Beckett, Ryan, Gupta, Aarti, Mahajan, Ratul, Walker, David
Format Journal Article
LanguageEnglish
Published 22.06.2018
Subjects
Computer Science - Networking and Internet Architecture
Online AccessGet full text

Cover

More Information
Summary:We develop an algorithm capable of compressing large networks into a smaller ones with similar control plane behavior: For every stable routing solution in the large, original network, there exists a corresponding solution in the compressed network, and vice versa. Our compression algorithm preserves a wide variety of network properties including reachability, loop freedom, and path length. Consequently, operators may speed up network analysis, based on simulation, emulation, or verification, by analyzing only the compressed network. Our approach is based on a new theory of control plane equivalence. We implement these ideas in a tool called Bonsai and apply it to real and synthetic networks. Bonsai can shrink real networks by over a factor of 5 and speed up analysis by several orders of magnitude.
DOI:10.48550/arxiv.1806.08744