Customer Reviews

Building Linux Clusters

5 star:		(3)
4 star:		(1)
3 star:		(2)
2 star:		(2)
1 star:		(5)

 

 

Buyer Beware! Having tried to actually build a linux cluster using David Spector's book - I am disappointed and concerned. I wish to add to the other negative reviews (has there been a positive review?) and submit the proposal that either the author is only out to sell books under the false pretense that his "How To" book can actually lead the reader to success, knowing that the instructions and software enclosed don't work; or that he has attempted to publish a book based on limited subject matter understanding of building linux clusters. Deception or Incompetence...or maybe just poor editing? I do want to try and make this linux cluster thing actually work so if anyone out there has encountered problems and has overcome them, please send me an email. This invitation also extends to the author, David Spector, of course.

The beginning of this book is a great introduction to clustering of various types but slowly declinced in usefulness the further I read.

Let me back up a step or two.. My work wanted me to build a Beowulf cluster to have on hand for a possible product down the line. At the time this book was not available so I resorted to reading all I could online in the form of FAQ's, HOW-TO's and general information sites. They were very informative and gave me a good base and reference when it came to building the cluster.

While I was building the cluster, I finally received this book and was rather disappointed. The beginning was great, but the chapters regarding software to run the cluster were terrible. Too many pages were spent talking about cluster administration using -one- software package and installation instructions were too rudimentary. I figure, if you don't know how to install RedHat, you shouldn't be building a Beowulf cluster. There was also very little info about creating applications for the cluster. The book -is- titled Building Linux Clusters, but what good is a cluster without any software to run on it.

I guess I make it sound worse than it really is but the previous reviews make it sound better than it is. It's a great introduction to Beowulf clusters but coming from someone that built one, read as much as you can about clusters online, read this book, then just build one from the ground up. Don't use the included software the first time around. It may be a pain to setup at first, but once it works and comes time to building applications or using it for something useful, you'll be glad.

While I can sympathize with some readers who may have been expecting a different book that covered the topic of cluster building in a different way, I would like to respond with several facts to clarify issues surrounding "Building Linux Clusters":

1) The book, as published, is not the final draft given to the editors at O'Reilly. When the book was ready to be put into O'Reilly's publishing system the then-editor of this series left to pursue a career at VALinux; the copy of the book put into the system is missing was over 2 months old and missing 50-100 pages of changes/additions/updates and other corrections that are not reflected in the printed book. This was discovered by me only when the book was delivered to stores -- at which time (obviously) it was too late to do anything about it.

2) Despite the issues surrounding which version of the book went into production, the book sold over 10,000 copies out of a printing of 12,000: O'Reilly decided not to issue a 2nd edition for a number of reasons, including the fact that many of the facilities I documented in the book (such as MPI, PVM and tools for cluster management, parallel rendering, etc.) were subsequently available pre-installed in many major Linux distributions which obviated the need for a dedicated book on cluster building.

3) Many, many readers have had great success with the book and have written to tell me so, including several readers who were able to build 100+ node clusters in a matters of a few hours using the software provided with the book.

4) A large number of software-related problems experienced by readers came about as readers attempted to build new distributions (RedHat7, RedHat8, etc.) based on the original software (based on RedHat6.2) provided with the book. Where possible I proved many hundred of hours of assistance to such readers.

5) Updated software and other tools were made available both at O'Reilly's web site as well as my own to help readers who found that certain tools would not work on their configurations and have been downloaded and successfully used thousands of times.

After purchasing this book and reading a few chapters I was real excited about building a cluster only to discover the numerous errors and the software bundle included a complete waste. I really wonder if those who rated this book 5 stars actually tried building the cluster with the enclosed software?? The Perl scripts for populating the database are missing, the web pages are all wrong, the apache configuration is also wrong. Many of the cgi scripts do not work properly. I sure hope O'reilly does a better job of checking this stuff out before they sell it.

If you're good a hacking and want a challenge this may be a good start.

I never thought I'd find an O'Reilly book that wasn't worth even a look, now I have. The errors are too numerous to count, the scripts do not work and the setup is ridiculous. Stick to the primers on the web, this book is a waste of trees. There are much better resources for beginners on the web. It is harder to build a cluster using the methods in the book (I've done a few and am always after easier ways) Now you know. (cross-posting to O'Reilly web site to save others the trouble)

This is my first attempt at building a cluster, so I bought this book. The book has the potential to be a great starter book, but the text is so poorly edited, it makes for a tough read. Another problem, is that nothing in the installation seems to work exactly as it is supposed to. I take one step, debug, fix. Take another step, debug, fix, etc. Not being a Redhat fan (I use slackware), it is very frustrating to try and fix these problems. I am still trying to get my cluster to run, so can't comment on the rest of the book, but after reading the errata on O'Reilly's web site, it appears there are more software problems awaiting me down the road. The reason I bought this book, instead of just reading HOWTO's, FAQ's, website's, etc. was to have a smoother entry in cluster building, but I am not seeing that benefit with this book.

This book describes a good overview of what a cluster is and how it operates, but the installation instructions were horrible, directories on CDROM were different than stated in the text, files were located in the wrong directories, kernel had to be modified to use network card, etc. Didn't anyone try to build a cluster using this text before it went to print? I'll keep looking for another book on clustering.

Building Linux Clusters by David HM Spector describes how Beowulf software can be used to turn network clusters of ordinary PC's into a virtual supercomputer. The first four chapters are a good introduction to the concept of effeciently connecting numerous computers together to act as a single computer. The author goes into useful detail about how a multiprocessor environment can use parallelism to get the most out of CPUs, high speed cache memory and slower main memory, refresh rates, wait states, bus speeds, and other machine level topics such as syncronization. There is detailed information about what kinds of hardware is and is not recomended for clusters.

The software used to harness the parallel power of the cluster is also introduced in detail, discussing different technologies such as Symmetric Multi-Processing (SMP), Multiple Instruction Multiple Data (MIMD), and others. The basics of Ethernet, TCP/IP, and routing are reviewed and applied to Clustering. There is lots of intersting information about network speed and configuration as is applies to clusters, such as Cube and Hyper-cube clusters. Software included with Beowulf to provide RAID support accross the hard drives on the cluster is explained, and comes with good advice about how to handle storage on the cluster as a whole rather than on individual machines.

There are examples of applications that run on clusters, such as MUDs, POVRAYs, and MP3 crunchers, and parallel programming and compilers.

This book was easy to read and very informative, and has put me well on my way to building my own hetrogeneous cluster. I have always wanted to study parallel computing and programming, and now I will have a chance.

Much of the information in this book is out of date. In addition, because of the time sensitive nature of hardware environments, Most of the discussion about hardware is mute as well. Too much of this book covers information that anyone serious about building a cluster would already know before they picked it up. By now the 6.2 version of Red Hat Linux is old and not likely to be a good starting point for any installation. This book needs more networking configuration discussion. It might look like the only book out there but, try the web for more up to date resources.

I just wanted to make sure that people understood there were problems with the example provided in this book before they bought it. There are errors and acknowledge problems (see O'Reilly). I am still trying to work through the example and estimate that if everything was correct in the book, this would have only taken me about 16 hours Max to set up. I am now on 24hrs and estimate it will take another 24 hrs to setup. This is not a book for people with just some experience with Linux. If not experienced, you had better be ready to spend a lot of time figuring things out and debugging. The sad and frustrating part about this book is that the author came so close to a great book. There were so many examples of scripting and using Linux included in this book and on the CD-ROM I would have highly recommended people to use this book as an intermediate learning tool. But because of the errors in the book and scripts I think someone at a beginning-intermediate level would become totally frustrated. The authors writing style and presentation are excellent. Unfortunately the information is crippled. I would strongly encourage the author to finish what he started. This could be a classic example of how to write a How-To. My guess is a deadline required the book be published before it was thoroughly proof read and tested.