Results 1 -
3 of
3
Tapestry: An infrastructure for fault-tolerant wide-area location and routing
, 2001
"... 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 ..."
Abstract
-
Cited by 928 (30 self)
- Add to MetaCart
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
A Decentralized Location and Routing Infrastructure for Fault-tolerant Wide-area Network Applications
"... and network bandwidth, combined with the increasing reach of networks into diverse environments and devices, offer new opportunities to and stretch the bounds of traditional network applications. More specifically, new challenges of scalability, fault-tolerance and manageability stretch the limits o ..."
Abstract
- Add to MetaCart
and network bandwidth, combined with the increasing reach of networks into diverse environments and devices, offer new opportunities to and stretch the bounds of traditional network applications. More specifically, new challenges of scalability, fault-tolerance and manageability stretch the limits of the communication components of applications. In this work, we propose the use of a globalscale routing and location infrastructure that leverages the abundant computational and network resources to facilitate a decentralized wide-area computing model. We present an infrastructure prototype named Tapestry, and demonstrate its usefulness with novel large-scale network applications. Finally, we evaluate it by measuring its effectiveness against current challenges, and the resource costs these benefits incur in tradeoffs. 1
Wide-area Location and Routing
, 2001
"... 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 alternati ..."
Abstract
- Add to MetaCart
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.

