Hash tables – which map “keys ” onto “values” – are an essential building block in modern software systems. We believe a similar functionality would be equally valuable to large distributed systems. In this paper, we introduce the concept of a Content-Addressable Network (CAN) as a distributed infrastructure that provides hash table-like functionality on Internet-like scales. The CAN is scalable, fault-tolerant and completely self-organizing, and we demonstrate its scalability, robustness and low-latency properties through simulation.

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

The Cooperative File System (CFS) is a new peer-to-peer readonly storage system that provides provable guarantees for the efficiency, robustness, and load-balance of file storage and retrieval. CFS does this with a completely decentralized architecture that can scale to large systems. CFS servers provide a distributed hash table (DHash) for block storage. CFS clients interpret DHash blocks as a file system. DHash distributes and caches blocks at a fine granularity to achieve load balance, uses replication for robustness, and decreases latency with server selection. DHash finds blocks using the Chord location protocol, which operates in time logarithmic in the number of servers. CFS is implemented using the SFS file system toolkit and runs on Linux, OpenBSD, and FreeBSD. Experience on a globally deployed prototype shows that CFS delivers data to clients as fast as FTP. Controlled tests show that CFS is scalable: with 4,096 servers, looking up a block of data involves contacting only seven servers. The tests also demonstrate nearly perfect robustness and unimpaired performance even when as many as half the servers fail.

This paper presents and evaluates the storage management and caching in PAST, a large-scale peer-to-peer persistent storage utility. PAST is based on a self-organizing, Internetbased overlay network of storage nodes that cooperatively route file queries, store multiple replicas of files, and cache additional copies of popular files. In the PAST system, storage nodes and files are each assigned uniformly distributed identifiers, and replicas of a file are stored at nodes whose identifier matches most closely the file’s identifier. This statistical assignment of files to storage nodes approximately balances the number of files stored on each node. However, non-uniform storage node capacities and file sizes require more explicit storage load balancing to permit graceful behavior under high global storage utilization; likewise, non-uniform popularity of files requires caching to minimize fetch distance and to balance the query load. We present and evaluate PAST, with an emphasis on its storage management and caching system. Extensive tracedriven experiments show that the system minimizes fetch distance, that it balances the query load for popular files, and that it displays graceful degradation of performance as the global storage utilization increases beyond 95%.

We describe a new scalable application-layer multicast protocol, specifically designed for low-bandwidth, data streaming applications with large receiver sets. Our scheme is based upon a hierarchical clustering of the application-layer multicast peers and can support a number of different data delivery trees with specific desirable properties. We show that group members maintain state for a constant number of other membersand the control overhead is also a constant.

This paper argues that a new class of geographically distributed network services is emerging, and that the most effective way to design, evaluate, and deploy these services is by using an overlay-based testbed. Unlike conventional network testbeds, however, we advocate an approach that supports both researchers that want to develop new services, and clients that want to use them. This dual use, in turn, suggests four design principles that are not widely supported in existing testbeds: services should be able to run continuously and access a slice of the overlay’s resources, control over resources should be distributed, overlay management services should be unbundled and run in their own slices, and APIs should be designed to promote application development. We believe a testbed that supports these design principles will facilitate the emergence of a new serviceoriented network architecture. Towards this end, the paper also briefly describes PlanetLab, an overlay network being designed with these four principles in mind. 1.

A fundamental problem that confronts peer-to-peer applications is the efficient location of the node that stores a desired data item. This paper presents Chord, a distributed lookup protocol that addresses this problem. Chord provides support for just one operation: given a key, it maps the key onto a node. Data location can be easily implemented on top of Chord by associating a key with each data item, and storing the key/data item pair at the node to which the key maps. Chord adapts efficiently as nodes join and leave the system, and can answer queries even if the system is continuously changing. Results from theoretical analysis and simulations show that Chord is scalable: communication cost and the state maintained by each node scale logarithmically with the number of Chord nodes.

This paper presents Scribe, a scalable application-level multicast infrastructure. Scribe supports large numbers of groups, with a potentially large number of members per group. Scribe is built on top of Pastry, a generic peer-to-peer object location and routing substrate overlayed on the Internet, and leverages Pastry's reliability, self-organization, and locality properties. Pastry is used to create and manage groups and to build efficient multicast trees for the dissemination of messages to each group. Scribe provides best-effort reliability guarantees, but we outline how an application can extend Scribe to provide stronger reliability. Simulation results, based on a realistic network topology model, show that Scribe scales across a wide range of groups and group sizes. Also, it balances the load on the nodes while achieving acceptable delay and link stress when compared to IP multicast.

We describe a peer-to-peer system which has provable consistency and performance in a fault-prone environment. Our system routes queries and locates nodes using a novel XOR-based metric topology that simplifies the algorithm and facilitates our proof. The topology has the property that every message exchanged conveys or reinforces useful contact information. The system exploits this information to send parallel, asynchronous query messages that tolerate node failures without imposing timeout delays on users.

We present Tapestry, a peer-to-peer overlay routing infrastructure offering efficient, scalable, locationindependent routing of messages directly to nearby copies of an object or service using only localized resources. Tapestry supports a generic Decentralized Object Location and Routing (DOLR) API using a self-repairing, softstate based routing layer. This paper presents the Tapestry architecture, algorithms, and implementation. It explores the behavior of a Tapestry deployment on PlanetLab, a global testbed of approximately 100 machines. Experimental results show that Tapestry exhibits stable behavior and performance as an overlay, despite the instability of the underlying network layers. Several widely-distributed applications have been implemented on Tapestry, illustrating its utility as a deployment infrastructure.