ETTM: a scalable fault tolerant network manager

Abstract

In this paper, we design, implement, and evaluate a new scalable and fault tolerant network manager, called ETTM, for securely and efficiently managing network resources at a packet granularity. Our aim is to provide network administrators a greater degree of control over network behavior at lower cost, and network users a greater degree of performance, reliability, and flexibility, than existing solutions. In our system, network resources are managed via software running in trusted execution environments on participating end-hosts. Although the software is physically running on end-hosts, it is logically controlled centrally by the network administrator. Our approach leverages the trend to open management interfaces on network switches as well as trusted computing hardware and multicores at end-hosts. We show that functionality that seemingly must be implemented inside the network, such as network address translation and priority allocation of access link bandwidth, can be simply and efficiently implemented in our system.