Distributed computing

Distributed computing is the process of running a single computational task on more than one distinct computer.

Introduction

This differs from cluster computing in that computers in a distributed computing environment are typically not exclusively running 'group' tasks, whereas clustered computers are usually much more tightly coupled. The difference makes distributed computing attractive because, when properly configured, it can use computational resources that would otherwise be unused. It can also make available computing resources which would otherwise be impossible. For example, the SETI@Home project uses 'idle time' on many thousands of computers throughout the world, and is able to analyze received signals that would have been impossible otherwise. Such arrangements permit handling of data that would otherwise require the power of expensive supercomputers.

Distributed computing is very attractive in part because interactive operation leaves most computers in 'idle' most of the time. The process which implements the distributed aspect (ie: that running on a machine normally devoted to other work) is usually specially designed to be a low priority process, using only computing power that would be 'wasted' anyway.

However, having a low-priority process constantly running prevents operating system power management routines from putting the processor into a low-power mode, resulting in increased electricity consumption. For some (typically recent, and high speed) CPUs, the difference can be on the order of tens of watts.

Distributed computing also often involves competition with other distributed systems. This competition may be for prestige, or it may be a means of enticing users to donate processing power to a specific project. For example, there is the so-called "stat race": a measure of what project has managed to perform the most distributed work over the past day or week. This has been found to be so important in practice that virtually all distributed computing projects offer on-line statistical analyses of their performances, updated at least daily, if not in real-time.

Distributed computing is also an active area of research with an abundant literature. The best known distributed computing conferences are The International Conference on Dependable Systems and Networks [1] and the ACM Symposium on Principles of Distributed Computing [2]. Journals include the Journal of Parallel and Distributed Computing [3], IEEE transactions on Parallel and Distributed Systems [4], and Distributed Computing [5].

See also

• Distributed programming
• Application server
• Grid computing
• Logical clocks
• Parallel computing
• Peer to peer
• Snapshot algorithm
• Software componentry
• Network of Workstations
• List of important publications in distributed computing

Distributed computing infrastructure

• CORBA
• SOAP
• XML-RPC
• GLOBE - http://www.cs.vu.nl/~steen/globe/ (Andrew S. Tanenbaum and others!!!)

Proprietary

• Xgrid
• ICE

Distributed computing projects

• Amoeba distributed operating system
• Berkeley NOW Project
• Berkeley Open Infrastructure for Network Computing (BOINC) [6] a distributed computing infrastructure founded and developed by the SETI@home project ([7])
• Climateprediction.net [8] seeks to forcast the climate of the Earth in the 21st century.
• D2OL [9] works to discover drug candidates against Anthrax, Smallpox, Ebola and SARS and other potentially devastating infectious diseases.
• Distributed.net [10] has many projects, one of which is a search for optimal Golomb rulers. Some will venture that Distributed.net is not a non-profit project since the main RC5-72 project they do is indeed for a cash prize from RSA Labs.
• Distributed Folding [11] is doing work similar to that of Folding at Home, but with a genetic algorithm to attempt to improve the results over time. Distributed Folding closed on October 5, 2004.
• Einstein@Home [12] gravitational wave project
• FAFNER
• Find-a-drug [13] is a non-profit organisation using Internet-based computing for drug discovery. Preliminary results from the Cancer and HIV projects are very promising. More information here.
• Folding at Home [14] University of Illinois at Urbana-Champaign report on October 22, 2002 states that their distributed simulations of protein folding are demonstrably accurate.
• Genome@Home [15] Due to funding, Genome@home was shut down. It now acts as a deadline-less work unit server for Folding@home.
• GIMPS -- Great Internet Mersenne Prime Search, dedicated to finding ever larger Mersenne primes.
• JHDC [16] -- Open source programmable Java distributed computing system.
• Lifemapper[17] Attempts to build global archive of biological species distributions.
• MD5CRK[18] Attempts to crack the commonly used cryptographic hash function MD5. This project ended August 24, 2004 due to findings by Wang, Feng, Lai, and Yu. Read more at http://eprint.iacr.org/2004/199.pdf
• Predictor@home [19], a project predicting protein structures from their sequences
• Seventeen or bust [20] Attempts to find prime numbers in 17 sequences, to solve the Sierpinski problem. - So far primes in 6 sequences have been found.
• SETI@home [21], a project searching for signs of extra-terrestrial intelligence (SETI).
• United Devices [22] is the largest commercial distributed computing network.
• DIMES [23] is a distributed computing project which maps the structure and evolution of the Internet infrastructure, allowing users to see how the Internet looks from their home.
• Project Dolphin [24] is a project to track how many keys you type and keep statistics of it, and you can compare yourself to others.

Distributed projects directories

• grid.org A grid computing project for large scale research studies (mostly medical) with over two and a half million computers working under it.
• Internet-based Distributed Computing Projects Lists ongoing, future and past projects, edited by Kirk Pearson.

External links

• A primer on distributed computing is an article that explains the technical basics of distributed computing.