In today’s chaotic network, data and services are mobile and replicated widely for availability, durability, and locality. Components within this infrastructure interact in rich and complex ways, greatly stressing traditional approaches to name service and routing. This paper explores an alternative to traditional approaches called Tapestry. Tapestry is an overlay location and routing infrastructure that provides location-independent routing of messages directly to the closest copy of an object or service using only point-to-point links and without centralized resources. The routing and directory information within this infrastructure is purely soft state and easily repaired. Tapestry is self-administering, faulttolerant, and resilient under load. This paper presents the architecture and algorithms of Tapestry and explores their advantages through a number of experiments. 1

Remote procedure calls (RPC) appear to be a useful paradig m for providing communication across a network between programs written in a high-level language. This paper describes a package providing a remote procedure call facility, the options that face the designer of such a package, and the decisions ~we made. We describe the overall structure of our RPC mechanism, our facilities for binding RPC clients, the transport level communication protocol, and some performance measurements. We include descriptioro ~ of some optimizations used to achieve high performance and to minimize the load on server machines that have many clients.

In this paper we consider the problem of choosing among a collection of replicated servers, focusing on the question of how to make choices that segregate client/server traffic according to network topology.We explore the cost and effectiveness of a variety of approaches, ranging from those requiring routing layer support (e.g., anycast) to those that build location databases using application-level probe tools like traceroute. Weuncover a number of tradeoffs between effectiveness, network cost, ease of deployment, and portability across differenttypes of networks. We performed our experiments using a simulation parameterized by a topology collected from 7 survey sites across the United States, exploring a global collection of Network Time Protocol servers.

The V kernel supports an abstraction of processes, with operations for interprocess communication, process management, and memory management. This abstraction is used as a software base for constructing distributed systems. As a distributed kernel, the V kernel makes intermachine bound-aries largely transparent. In this environment of many cooperating processes on different machines, there are many logical groups of processes. Examples include the group of tile servers, a group of processes executing a particular job, and a group of processes executing a distributed parallel computation. In this paper we describe the extension of the V kernel to support process groups. Operations on groups include group interprocess communication, which provides an application-level abstraction of network multicast. Aspects of the implementation and performance, and initial experience with applications are discussed.

Naming is an important aspect of distributed system design. A naming system allows users and programs to assign character-string names to objects and subsequently use the names to refer to those objects. With the interconnection of clusters of computers by wide-area networks and internetworks, the domain over which naming systems must function is growing to encompass the entire world. In this paper, we address the problem of a global naming system, proposing a three-level naming architecture that consists of global, administrational, and managerial naming mechanisms, each optimized to meet the performance, reliability, and security requirements at its own level. We focus in particular on a decentralized approach to the lower levels, in which naming is handled directly by the managers of the named objects. Client name caching and multicast are exploited to implement name mapping with almost optimum performance and fault tolerance. We also show how the naming system can be made...

this memo is unlimited

Internet evolves and operates largely without a central coordination, the lack of which was and is critically important to the rapid growth and evolution of Internet. However, the lack of management in turn makes it very difficult to guarantee proper performance and to deal systematically with performance problems. Meanwhile, the available network bandwidth and server capacity continue to be overwhelmed by the skyrocketing Internet utilization and the accelerating growth of bandwidth intensive content. As a result, Internet service quality perceived by customers is largely unpredictable and unsatisfactory. Content Distribution Network (CDN) is an e ective approach to improve Internet service quality. CDN replicates the content from the place of origin to the replica servers scattered over the Internet and serves a request from a replica server close to where the request originates. In this paper, we first give an overview about CDN. We then present the critical issues involved in designing and implementing an effective CDN and survey the approaches proposed in literature to address these problems. An example of CDN is described to show how a real commercial CDN operates. After this, we present a scheme that provides fast service location for peer-to-peer systems, a special type of CDN with no infrastructure support. We conclude with a brief projection about CDN.

In this paper, we present Mobile Tapestry, an extension to the Tapestry overlay network protocol, that enables scalable, fault-tolerant, and timely delivery of network messages, including multimedia streams, to and from rapidly moving nodes. Mobile Tapestry efficiently supports individual mobile nodes and, by using an approach we call hierarchical mobility, it also supports large groups of mobile nodes simultaneously moving together. Mobile Tapestry leverages the Tapestry's locality mechanisms to reduce the latency and bandwidth of mobility update traffic, while eliminating the routing inefficiencies and availability problems of IP-based mobility protocols, such as Mobile IP. Our

Virtual networks are an important tool for deploying new services on top of the Internet. We present the TAO algorithm to automatically manage the topology of virtual networks, allowing nodes to be added and removed automatically, and adjusting the topology to optimize performance. By automating the tasks of maintaining the set of nodes and configuring the tunnels between them, we can reduce the administrative costs and allow scaling to much larger virtual networks than what is currently practical. We focus primarily on the Active Networks testbed, or ABone, though our work has applications in all classes of virtual networks. 1 Introduction Virtual networks are an important tool used to deploy a variety of new services and algorithms on top of the Internet. Our work is focused on automating the management of virtual networks, both to ease administrative costs and improve network performance as the number of nodes in a virtual network grows. 1.1 Virtual networks Often referred ...

Abstract. Today networks suffer from various challenges like distributed denial of service attacks or worms. Multiple different anomaly-based detection systems try to detect and counter such challenges. Anomaly-based systems, however, often show high false negative rates. One reason for this is that detection systems work as single instances that base their decisions on local knowledge only. In this paper we propose a collaboration of neighboring detection systems that enables receiving systems to search specifically for that attack which might have been missed by using local knowledge only. Once such attack information is received a decision process has to determine if a search for this attack should be started. The design of our system is based on several principles which guide this decision process. Finally, the attack information will be forwarded to the next neighbors increasing the area of collaborating systems. 1