Customer comments on this selection.
 Beginner's Perspective:
I bought this book because I started thinking of building a cluster in my basement just to experiment with parallel programming. Over the past few weeks reading and rereading sections of the book I've developed the confidence to get started. This won't be the only book I'll need. The author is very clear and unapologetic about that. I still need a good book on Linux and programming with MPI. I don't know everything I'll need to know, but I know far more about what I DON'T know and what other work I need to do.
br /
br /All in all an excellent and very readable overview.
br /
 The best book for architecting Linux clusters by far.
This book provides an exhaustive step-by-step examination of all of the elements that need to be considered for architecting a Linux cluster. The coverage is application neutral: High Performance Computing (HPC), Web load-balancing clusters, Enterprise computing centers; no matter. The details common to all clusters are thoroughly discussed.
br /As a Linux cluster developer of 7 years, I was able to expand and improve my own design processes to better cover all of the issues necessary to architect my designs. I heartily recommended this book to anyone designing a cluster of any size.
Outstanding value
This book is a very straightforward, clearly written and valuable introduction to Linux clustering. Geared toward system folks, it also provides numerous `on-ramps' into the basics of clustering to accommodate quick, relevant review of supporting technology for the reader. It is essentially a map for getting from start to finish in any Linux cluster project. Specific situations, conditions, and expectations differ across projects, of course, and such points are identified well in the text with pointers to additional information provided.
br /
br /Scientific computing (HPC) is addressed well, and is more of the topic than any other cluster flavor, though the others are discussed as well (after all, who wouldn't want a side order of high availability with their HPC?). My cluster background personally was mostly high availability (Microsoft Wolfpack), so I appreciated the HPC overview, especially since I was already building a Linux cluster for my bio-algorithms that depended on HPC. This book helped me get every gflop out of my admittedly 2ndhand student hardware.
br /
br /If you are getting involved with a cluster project or have one potentially on the horizon, and need a clear overview of what may lay ahead, pick up this book. For its measly sticker price, you get two solid discussion weeks with an expert. Go calculate that one:)
br /5 stars
Hard to beat. Full Marks !!
The book describes in simple reproducable steps how to build a medium to medium big sized cluster. It also devides the clusters into the three main types,
br /
br /HPC *High performance computing,
br /High Throughput and
br /High Availability cluster
br /
br /and describes their usages. The book is describing cluster projects more from a bird view and gives a whole sight overview including budget calculations, comparing several architectures also by their technology and environmental conditions (Power usage, Cooling requirements etc.).
br /
br /The book is not only hard to beat but also the perfect companion to the Linux Enterprise Cluster from Karl Kopper. While Karls book is a bit more practical it concentrates only on the technical configuration of "small" clusters.
br /
br /Here is where Lubke comes in and extends that knowledge by the many environmental factors *Budget, technical considerations, Calculations, Estimates, Planning what to expect from your hardware *Performance, Weight, Heat, Flooring considerations etc.
br /
br /After you read the book, you will have learned all necessary steps to build your own clusters. The "only" thing left to you is to put the ship to water ;-)
br /
br /An incredible book and a real eye opener !!
Very good book. My only complains are:
* a little bit too chatty (e.g. on page 162 he starts lecturing you about the meaning of 'freedom' after using the book's and your minds real estate telling you on page 36 about disposing of packaging hardware, ... @@, ;-))
br / * still using RH for 'serious' Linux work?
br / * pg 172, statement about Debian not supporting AMD "as of this writing" (?!) Could have just included the sentence. "check as of your reading of the book"
br / * no mention of transmeta's technological hardware advances (company itself may very soon go south) but their 'ideas' are really promising (for servers with very low power comsumption)
br / * pg 209, problems with RAID and root filesystem and things. You could just run Debian from a Live CD and leave all writable RAID disks along
|
