A clean slate 4D approach to network control and management

By Albert G. Greenberg, G. Hjálmtýsson, David A. Maltz, A. Myers, Jennifer Rexford, G. Xie, Hong Yan, Jibin Zhan, Hui Zhang. CCRV, 2005

731 citations recorded by the source corpus.

Today's data networks are surprisingly fragile and difficult to manage. We argue that the root of these problems lies in the complexity of the control and management planes--the software and protocols coordinating network elements--and particularly the way the decision logic and the distributed-systems issues are inexorably intertwined. We advocate a complete refactoring of the functionality and propose three key principles--network-level objectives, network-wide views, and direct control--that we believe should underlie a new architecture. Following these principles, we identify an extreme design point that we call "4D," after the architecture's four planes: decision, dissemination, discovery, and data. The 4D architecture completely separates an AS's decision logic from pro-tocols that govern the interaction among network elements. The AS-level objectives are specified in the decision plane, and en-forced through direct configuration of the state that drives how the data plane forwards packets. In the 4D architecture, the routers and switches simply forward packets at the behest of the decision plane, and collect measurement data to aid the decision plane in controlling the network. Although 4D would involve substantial changes to today's control and management planes, the format of data packets does not need to change; this eases the deployment path for the 4D architecture, while still enabling substantial innovation in network control and management. We hope that exploring an extreme design point will help focus the attention of the research and industrial communities on this crucially important and intellectually challenging area.

Subfields: Computer Networks and Communications, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/e0316402a241c875540efc26744c27128bfb57d0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Electrical and Electronic Engineering

Citations in the corpus

A security enforcement kernel for OpenFlow networks (2012, neutral): “, [5], [9]).”
A survey of network virtualization (2010, methodology): “On the other hand, it enables infrastructure providers to automatically discover and manage their physical infrastructure by running a discovery plane of their own [96].”
Software-Defined Network Function Virtualization: A Survey (2015, background): “, to support a dedicate networking processing and applications [14]–[16].”
HyperFlow: A Distributed Control Plane for OpenFlow (2010, background): “The root cause of these problems is the overly complicated control plane running on top of all switches and routers throughout the network [2].”
SANE: A Protection Architecture for Enterprise Networks (2006, background): “[24, 15] argue that the decentralized routing policy, access control and management has resulted in complex routers and cumbersome, difficult to manage networks.”
Design and Implementation of a Consolidated Middlebox Architecture (2012, background): “Finally, the use of centralization to simplify network management is also well known [31] [21] [15].”
Towards an elastic distributed SDN controller (2013, background): “…an Elastic Distributed SDN Controller Advait Dixit, Fang Hao, Sarit Mukherjee, T.V. Lakshman, Ramana Kompella Purdue University, Bell Labs Alcatel-Lucent ABSTRACT Distributed controllers have been proposed for Software De.ned Networking to address the issues of scalability and reliability…”
B4: experience with a globally-deployed software defined wan (2013, background): “ere is a rich heritage of work in Soware Dened Networking [7, 8, 19, 21, 27] and OpenFlow [28, 31] that informed and inspired our B4 design.”
Software defined networking: State of the art and research challenges (2014, neutral): “The concept of SDN emerged in 2005, when the authors of [80] proposed a 4D approach to network control and management.”
Dynamic scheduling of network updates (2014, background): “Categories and Subject Descriptors: C.2.1 [ComputerCommunication Networks]: Network Architecture and Design— Network communications; C.2.3 [Computer-Communication Networks]: Network Operations—Network management Keywords: Software-defined networking; network update”
Participatory networking: an API for application control of SDNs (2013, methodology): “nisms to control the network, such as 4D [24], MPLS, or a collection of middleboxes.”
DevoFlow: scaling flow management for high-performance networks (2011, background): “Our work here derives from a long line of related work that aims to allow operators to specify high-level policies at a logically centralized controller, which are then enforced across the network without the headache of manually crafting switch-by-switch conﬁgurations [10,12,25,26].”
FRESCO: Modular Composable Security Services for Software-Defined Networks (2013, neutral): “, [6], [10]).”
Maestro: A System for Scalable OpenFlow Control (2010, methodology): “Inspired by the 4D architecture [6], the emerging OpenFlow [9] switch architecture separates the two main functions of a classical router/switch: data plane packet switching and control plane routing decision making.”