Peer-to-peer computing : building supercomputers with Web technologies

摘要

Client/Server architecture was first proposed in the late 1980s as an alternative to conventional mainframe systems. Mainframe processing quickly becomes a bottleneck in any information system, but client/server models shift the processing burden to the client computer. Through workload sharing, client/server systems can improve overall efficiency while reducing budgets. Companies are again searching for ways to improve their processing power without further investment in new hardware and software. Many client computers are idle most of the time, and have unused disk space. The next logical step is to maximise the resources of these computers, and the peer-to-peer (P2P) model is the answer. A new and simple peer-to-peer model will be introduced in this book. In it, readers will be taught to install peer-to-peer systems which can then manage and distribute the processing power of any number of clients; the size of network can range from two to over a million computers; the software necessary to implement peer-to-peer systems quickly can be downloaded from the book’s website at www.springer.com/1-84628-381-7/ The deployment of web technologies will enable individuals and organisations of all sizes to use computers across a network as though it were a single supercomputer to solve complex problems, and after reading this book, readers will be able to install a peer-to-peer system of any size.