Network virtualization is crucial in data centers environments for interconnecting all physical and virtualized resources to create a complete semblance of an integrated computing infrastructure. Much of the existing research on data center networking has focused on network mechanisms inside the datacenter. Little attention has been paid to networking mechanisms for integrating multiple data centers. In this paper we introduce Virtual Transits, a flexible platform providing a novel solution to dynamically build and manage virtual networks across multiple data centers. Virtual Transits can also incorporate several important datacenter networking schemes into a coherent platform that enables seamless integration of intracloud and intercloud traffic. Through our implementation and performance evaluation on a real deployment, we show that our system provides a promising and efficient solution for inter-cloud networking, test beds federation, and software-defined networking test beds.

The federated cloud system provides the ability to integrate, manage, and use third-party resources from multiple institutions and combines the resources into one infrastructure. A virtual network management system is needed to supporting a seemingly infrastructure where services can be deployed on-demand and across different network domains. We present our work on designing and implementing an integrated system to enable virtual network services across federated clouds. We also propose a novel mechanism to enable network stitching via translating VLAN tag dynamically. The service can be partitioned on hosts across different network domain using different underlying layer-2 or layer-3 network technologies. This paper also provides the results of performance measurement from the implementation based on real production networks.

Cloud computing, in particular its system spread across several data centers, poses a unique set of networking challenges and management problems. This paper presents our design, implementation, and experience in tackling these challenges by using the concepts and technologies of software-defined network (SDN). We define a network abstraction to incorporate the physical and virtual data plane within a data center. We propose a new network primitive to address the interconnection issues among multiple data centers. A policy plane consolidating these mechanisms provides a programmable interface to enable a wide range of policies and new networking mechanisms. We present the performance result on a real deployment over the production networks. The experience and initial performance results demonstrate that the SDN is a promising solution to cloud networking.

Pervasive high speed networks and emerging cloud computing concepts offer a new capability and an opportunity to rethink approaches for delivering information services. However, little attention has been paid to how the legacy monolithic systems can be migrated to the cloud computing paradigm. The paper shares our experience and solutions on building a federated cloud infrastructure for E-learning services. The federated cloud system provides the ability to integrate, manage, and use third-party resources from multiple institutions and combines the resources into one infrastructure. We also provide experience and performance data from six month real trace of the system. While the discussion and experiments focus on cloud paradigm with education services, this research can serve as a reference design for other service providers who want to deploy services in the form of cloud computing.

Over the past few years, there has been a significant interest in content-aware routing that use the information found in the payload of packets to provide intelligent control on load distribution in Web clusters. This paper reexamines the idea of content-aware routing and finds that routing Web traffic based on more information of packet payload dose not always yield better performance. We then propose a mechanism that can effectively remedy the deficiencies of existing approaches. The results of performance measurements show that the proposed solution can improve the benefits of the content-aware clustering techniques.

As the Web becomes an important business service delivery infrastructure, the demands for providing service differentiation or QoS support on the Web system have become more strident recently. A Web switch (or server load balancer in the industry parlance) is needed in a server cluster to route the incoming request to the server best suited to respond. Because of the key role the Web switch plays in determining the responsiveness of Web services in a server cluster, it is critical to consider how they can support the quality of service for Web-based applications. This paper describes the design, implementation, and performance of an efficient approach to address this issue.

Service replication on the server cluster is becoming increasingly important and widespread as the explosive growth of the Web is straining the architecture of many Internet sites. Layer-7 routing (also known as content-aware routing), routing packets based on requested content, has been recognized as a powerful approach to distribute workload among these server farms. However, managing a server cluster with the layer-7 routing mechanism faces numerous challenges. This paper presents a management system that can support a configurable and high-performance layer-7 routing system. In the proposed system, we devise a data structure termed URL table to hold content-related information for making content-aware routing decisions. We also propose a novel idea termed "URL formalization" that provides an efficient solution to speedup the content-aware request routing. The proposed mechanisms are integrated into a management system, which provides a specification interface and enforcement mechanisms so that the system policy can be specified and enforced.

Modern Web services must support large and rapidly growing user populations, and remain available 24 hours per day, 7 day per week. Server-cluster is the most promising approach to address this challenge. We further augment the server-cluster schemes with a novel mechanism that enables a Web request to be smoothly migrated and recovered on another working node in the presence of server failure or overload. The new mechanism provides a powerful solution to fault tolerance and dynamic load-distribution for Web services. The administrator can explicitly specify some services to be guaranteed for fault-tolerance or higher performance support. We present the details of our design, implementation, and performance data. The performance results show that the proposed mechanism is efficient and with low associated overhead.

Clusters of commodity computers are becoming an increasingly popular approach for building cost-effective high-performance Internet servers. However, how to place and manage content in such a distributed and complex system is becoming a challenging problem. In particular, such distributed servers tend to be more heterogeneous, and this heterogeneity will further increase the management burden. This paper describes the motivation, design, implementation and performance of a content placement and management system for a heterogeneous distributed Web server.

Clustered server architecture is increasingly being viewed as a successful and cost-effective approach to building a high-performance Web server. Existing server-clustering schemes have typically concentrated on the following issues: scalability, high availability, and user transparency. In this paper, we argue that the design goals of the Web server cluster should include adaptability, fault tolerance, and high manageability. In the presence of the Internet's highly unpredictable workload, the server system should be self-adapting to changing circumstances. We address this problem by building a Web server on a cluster of non-dedicated workstations. Such a server can easily recruit non-dedicated nodes dynamically in response to load bursts. Based on such a scheme, we designed and implemented an innovative approach that enables an ongoing request to be smoothly migrated to another node either in response to a node failure or overload. We also designed and implemented a management system that enables the Web site manager to manage and maintain the distributed server as a single large system.

Clustered server architectures have been employed for many years on the Internet as a way to improve performance, reliability and scalability in the presence of the Internet's explosive growth. Placing and managing content in such a complex system poses a number of challenging problems. In this paper, we describe the work that we are pursuing to design and implement a content placement and management system for the cluster-based Web server.

Today, a successful Internet service is absolutely critical to be up 100 percent of the time. Server clustering is the most promising approach to meet this requirement. However, the existing Web server-clustering solutions merely can provide high availability derived from its redundancy nature, but offer no guarantee about fault resilience for the service. In this paper, we address this problem by implementing an innovative mechanism that enables a Web request to be smoothly migrated and recovered on another working node in the presence of server failure. We will show that the request migration and recovery could be efficiently achieved in the manner of user transparency. The achieved capability of fault resilience is important and essential for a variety of critical services (e.g., E-commerce), which are increasingly widespread used. Our approach takes an important step toward providing a highly reliable Web service.