ChessBrain: a Linux-Based Distributed Computing Experiment
On May 27, 2003, 646 machines worked together to play a single game of chess. This was the first time such a feat had been accomplished, and it was made possible by the power of Linux, open-source software and hundreds of contributors from over 37 different countries.
ChessBrain (chessbrain.net) is a distributed computation project that uses the idle processing power of distributed machines to solve computationally intensive problems. ChessBrain is a system focused on playing chess, but the underlying system can be adapted for other games as well as for non-game-related applications.
Imagine playing a game against an opponent, except every time he moves, you grab the phone and start calling friends for help. You call Sue, describe the current position and ask her to call you back when she has an answer. Then you call Ryan to ask whether you should worry about a pending attack; again, you ask for a call back when he has an answer. After calling 20 other friends, you sit back and wait for replies. This is similar to how ChessBrain plays chess.
ChessBrain consists of a Linux-based server application, the SuperNode, and client software known as PeerNodes. The SuperNode connects to an on-line game server, which allows visiting members to play against one another, challenge ChessBrain to a game or watch ChessBrain play against its current opponent. While ChessBrain plays, it examines positions, dispatches hundreds of potential moves to remote PeerNodes for analysis, collects feedback from the PeerNodes, processes that information and makes its best move. ChessBrain exists as an ever-changing pool of networked machines. Philosophically and scientifically, it's a beautiful thing.
I started ChessBrain as a distributed computing experiment in the summer of 2001. By the end of that year, I had a working prototype and needed a place to host the server. My longtime friend, Walter Howard, the webmaster of HackerWhacker (hackerwhacker.com), offered to host the server on his personal T1 line.
On June 9, 2002, ChessBrain appeared on Slashdot, and the positive exposure resulted in hundreds of new PeerNode operators. Gavin Roy, one of the new members, owns the bteg network (www.bteg.net) and offered to host a SuperNode server free of charge. On June 27, I met Gavin for dinner and handed this near stranger a SuperNode server on a Pentium III machine. ChessBrain gained another server, I gained another friend, and Gavin has become an important supporter of the ChessBrain Project. I transitioned the SuperNode over to Gavin's site, and Walt continued to host the original SuperNode as a secondary backup and experimental server.
During the months that followed, we gained an amazing amount of exposure. Few seemed to mind that ChessBrain couldn't actually play chess. The first eight months of 2002 were spent working on the SuperNode server and porting the PeerNode client to Microsoft Windows and Apple's Mac OS X.
Once the server and clients worked well, the focus was on getting ChessBrain actually to play. The wbec-ridderkerk (www.wbec-ridderkerk.nl) site in the Netherlands lists nearly 200 freely available chess-playing programs. I reviewed a few, looking for one with relatively clean code and the ability to compile under several operating systems. I found an ideal program in Beowulf, written by Colin Frayn, who was then a PhD candidate at Cambridge University in England. We exchanged several e-mails and Colin joined the project. We collaborated entirely on-line using e-mail and instant messaging (IM) and began making necessary modifications. Colin adapted his chess program for distributed computing, and I modified the SuperNode and PeerNode clients to use his engine. The time difference between London and Los Angeles proved ideal. I would IM Colin at my 3AM and again during the day. By my late afternoon, Colin would head for bed, and I would work through his night. Before crashing, I would leave feedback for Colin. This round-the-clock cycle continued for months.
Colin adapted his original Beowulf chess engine to become two chess-playing components, BeoServer and BeoClient. He developed the pair to support distributed chess play within the ChessBrain framework. On December 22, 2002, ChessBrain played its first game of distributed chess. By January 2003, the ChessBrain community had provided 62 machines and was testing regular builds.
|Designing Electronics with Linux||May 22, 2013|
|Dynamic DNS—an Object Lesson in Problem Solving||May 21, 2013|
|Using Salt Stack and Vagrant for Drupal Development||May 20, 2013|
|Making Linux and Android Get Along (It's Not as Hard as It Sounds)||May 16, 2013|
|Drupal Is a Framework: Why Everyone Needs to Understand This||May 15, 2013|
|Home, My Backup Data Center||May 13, 2013|
- Designing Electronics with Linux
- Making Linux and Android Get Along (It's Not as Hard as It Sounds)
- Dynamic DNS—an Object Lesson in Problem Solving
- Using Salt Stack and Vagrant for Drupal Development
- New Products
- Validate an E-Mail Address with PHP, the Right Way
- Build a Skype Server for Your Home Phone System
- Why Python?
- A Topic for Discussion - Open Source Feature-Richness?
- Tech Tip: Really Simple HTTP Server with Python
- Not free anymore
12 min 9 sec ago
3 hours 59 min ago
- Reply to comment | Linux Journal
4 hours 7 min ago
- Understanding the Linux Kernel
6 hours 22 min ago
8 hours 51 min ago
- Kernel Problem
18 hours 54 min ago
- BASH script to log IPs on public web server
23 hours 21 min ago
1 day 2 hours ago
- Reply to comment | Linux Journal
1 day 3 hours ago
- All the articles you talked
1 day 5 hours ago
Enter to Win an Adafruit Pi Cobbler Breakout Kit for Raspberry Pi
It's Raspberry Pi month at Linux Journal. Each week in May, Adafruit will be giving away a Pi-related prize to a lucky, randomly drawn LJ reader. Winners will be announced weekly.
Fill out the fields below to enter to win this week's prize-- a Pi Cobbler Breakout Kit for Raspberry Pi.
Congratulations to our winners so far:
- 5-8-13, Pi Starter Pack: Jack Davis
- 5-15-13, Pi Model B 512MB RAM: Patrick Dunn
- 5-21-13, Prototyping Pi Plate Kit: Philip Kirby
- Next winner announced on 5-27-13!
Free Webinar: Hadoop
How to Build an Optimal Hadoop Cluster to Store and Maintain Unlimited Amounts of Data Using Microservers
Realizing the promise of Apache® Hadoop® requires the effective deployment of compute, memory, storage and networking to achieve optimal results. With its flexibility and multitude of options, it is easy to over or under provision the server infrastructure, resulting in poor performance and high TCO. Join us for an in depth, technical discussion with industry experts from leading Hadoop and server companies who will provide insights into the key considerations for designing and deploying an optimal Hadoop cluster.
Some of key questions to be discussed are:
- What is the “typical” Hadoop cluster and what should be installed on the different machine types?
- Why should you consider the typical workload patterns when making your hardware decisions?
- Are all microservers created equal for Hadoop deployments?
- How do I plan for expansion if I require more compute, memory, storage or networking?