Today’s data centers offer tremendous aggregate bandwidth to clusters of tens of thousands of machines. However, because of limited port densities in even the highest-end switches, data center topologies typically consist of multi-rooted trees with many equal-cost paths between any given pair of hosts. Existing IP multipathing protocols usually rely on per-flow static hashing and can cause substantial bandwidth losses due to longterm collisions. In this paper, we present Hedera, a scalable, dynamic flow scheduling system that adaptively schedules a multi-stage switching fabric to efficiently utilize aggregate network resources. We describe our implementation using commodity switches and unmodified hosts, and show that for a simulated 8,192 host data center, Hedera delivers bisection bandwidth that is 96 % of optimal and up to 113 % better than static load-balancing methods. 1

Applications hosted in today’s data centers suffer from internal fragmentation of resources, rigidity, and bandwidth constraints imposed by the architecture of the network connecting the data center’s servers. Conventional architectures statically map web services to Ethernet VLANs, each constrained in size to a few hundred servers owing to control plane overheads. The IP routers used to span traffic across VLANs and the load balancers used to spray requests within a VLAN across servers are realized via expensive customized hardware and proprietary software. Bisection bandwidth is low, severly constraining distributed computation. Further, the conventional architecture concentrates traffic in a few pieces of hardware that must be frequently upgraded and replaced to keep pace with demand- an approach that directly contradicts the prevailing philosophy in the rest of the data center, which is to scale

Enterprise networks are important, with size and complexity even surpassing carrier networks. Yet, the design of enterprise networks remains ad-hoc and poorly understood. In this paper, we show how a systematic design approach can handle two key areas of enterprise design: virtual local area networks (VLANs) and reachability control. We focus on these tasks given their complexity, prevalence, and time-consuming nature. Our contributions are three-fold. First, we show how these design tasks may be formulated in terms of networkwide performance, security, and resilience requirements. Our formulations capture the correctness and feasibility constraints on the design, and they model each task as one of optimizing desired criteria subject to the constraints. The optimization criteria may further be customized to meet operator-preferred design strategies. Second, we develop a set of algorithms to solve the problems that we formulate. Third, we demonstrate the feasibility and value of our systematic design approach through validation on a large-scale campus network with hundreds of routers and VLANs.

We present a novel approach to optimize the performance of IEEE 802.11-based multi-hop wireless networks. A unique feature of our approach is that it enables an accurate prediction of the resulting throughput of individual flows. At its heart lies a simple yet realistic model of the network that captures interference, traffic, and MAC-induced dependencies. Unless properly accounted for, these dependencies lead to unpredictable behaviors. For instance, we show that even a simple network of two links with one flow is vulnerable to severe performance degradation. We design algorithms that build on this model to optimize the network for fairness and throughput. Given traffic demands as input, these algorithms compute rates at which individual flows must send to meet the objective. Evaluation using a multi-hop wireless testbed as well as simulations show that our approach is very effective. When optimizing for fairness, our methods result in close to perfect fairness. When optimizing for throughput, they lead to 100-200 % improvement for UDP traffic and 10-50 % for TCP traffic.

Ideally, enterprise administrators could specify fine-grain policies that drive how the underlying switches forward, drop, and measure traffic. However, existing techniques for flowbased networking rely too heavily on centralized controller software that installs rules reactively, based on the first packet of each flow. In this paper, we propose DIFANE, a scalable and efficient solution that keeps all traffic in the data plane by selectively directing packets through intermediate switches that store the necessary rules. DIFANE relegates the controller to the simpler task of partitioning these rules over the switches. DIFANE can be readily implemented with commodity switch hardware, since all data-plane functions can be expressed in terms of wildcard rules that perform simple actions on matching packets. Experiments with our prototype on Click-based OpenFlow switches show that DI-FANE scales to larger networks with richer policies.

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 endpoints. Although the software is physically running on endpoints, 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 endpoints. 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. 1

Enterprise network architecture and management have followed the Internet’s design principles despite different requirements and characteristics: enterprise hosts are administered by a single authority, which intrinsically assigns different values to traffic from different business applications. We advocate a new approach where hosts are no longer relegated to the network’s periphery, but actively participate in network-related decisions. To enable host participation, network information, such as dynamic network topology and per-link characteristics and costs, is exposed to the hosts, and network administrators specify conditions on the propagated network information that trigger actions to be performed while a condition holds. The combination of a condition and its actions embodies the concept of the network exception handler, defined analogous to a program exception handler. Conceptually, network exception handlers execute on hosts with actions parameterized by network and host state. Network exception handlers allow hosts to participate in network management, traffic engineering and other operational decisions by explicitly controlling host traffic under predefined conditions. This flexibility improves overall performance by allowing efficient use of network resources. We outline several sample network exception handlers, present an architecture to support them, and evaluate them using data collected from our own enterprise network.

We present HomeMaestro, a distributed system for monitoring and instrumentation of home networks. HomeMaestro performs extensive measurements at the host level to infer application network requirements, and identifies networkrelated problems through time-series analysis. By sharing and correlating information across hosts in the home network, our system automatically detects and resolves contention over network resources among applications based on predefined policies. Finally, HomeMaestro implements a distributed virtual queue to enforce those policies by prioritizing applications without additional assistance from network equipment such as routers or access points. We outline the challenges in managing home networks, describe the design choices and architecture of our system, and highlight the performance of HomeMaestro components in typical home scenarios. 1.

Network operation is inherently complex because it consists of many functions such as routing, firewalling, VPN provisioning, traffic load-balancing, network maintenance, etc. To cope with this, network designers have created modular components to handle each function. Unfortunately, in reality, unavoidable dependencies exist between some of the components and they may interact accidentally. At the same time, some policies are realized by compositions of different components, but the methods of composition are ad hoc and fragile. In other words, there is no single mechanism for systematically governing the interactions between the various components. To address these problems, we propose a clean-late system called Maestro. Maestro is an “operating system ” that orchestrates the network control applications that govern the behavior of a network, and directly controls the underlying network devices. Maestro provides abstractions for the modular implementation of network control applications, and is the first system to address the fundamental problems originating from the concurrent operations of network control applications, namely communication between applications, scheduling of application executions, feedback management, concurrency management, and network state transition management. As the

OpenFlow assumes a logically centralized controller, which ideally can be physically distributed. However, current deployments rely on a single controller which has major drawbacks including lack of scalability. We present HyperFlow, a distributed event-based control plane for OpenFlow. HyperFlow is logically centralized but physically distributed: it provides scalability while keeping the benefits of network control centralization. By passively synchronizing network-wide views of OpenFlow controllers, HyperFlow localizes decision making to individual controllers, thus minimizing the control plane response time to data plane requests. HyperFlow is resilient to network partitioning and component failures. It also enables interconnecting independently managed OpenFlow networks, an essential feature missing in current OpenFlow deployments. We have implemented HyperFlow as an application for NOX. Our implementation requires minimal changes to NOX, and allows reuse of existing NOX applications with minor modifications. Our preliminary evaluation shows that, assuming sufficient control bandwidth, to bound the window of inconsistency among controllers by a factor of the delay between the farthest controllers, the network changes must occur at a rate lower than 1000 events per second across the network. 1.