<< 1 >>
Rating: 
Summary: A "Must Have" book for OS professionals and students.
Review: I just recently discovered this book and I wish I knew about it a couple of years ago. Not only did I learn a lot but it improved my understanding of things I thought I knew. The things you learn in this book are applicable to any operating system. The examples use standard UNIX to illustrate things, but everything applies just as easily to Linux, NT, or any other operating system you're working on.
Rating:
Summary: Great Book for Linux Kernel People
Review: I recently started working on the Linux kernel and found myself
perplexed by the multiprocessor code I found. After asking
around, a number of the more experienced Linux kernel developers
recommended this book. It's excellent! It taught me everything
I needed to know to get my work done. Plus there's the added
bonus that this book thoroughly covers cache architecture and its
interaction with the operating system. I highly recommend this
book to anyone working on the Linux kernel. It has far more depth and detail on multiprocessing and cache management than any
of the Linux books I've seen. And it's the only book I've ever
seen that so thoroughly explains the hardware involved in caches
and multiprocessors and their effects on the operating system in
a way that's easy to understand.
Rating:
Summary: THE book if you are a kernel/threading developer.
Review: I work on MP SVR4 kernels and this book is where I got most of my basics on MP from. I didn't understand the contents all at once - especially the initial intro to memory models in chapter 8, but after reading the SPARC specs (V8 & V9) and chapter 13, I can see how all this is relevant.If you are porting a unix or any OS for that matter to todays architectures, this book should help clear up what issues you would encounter and how best to solve them. For example the memory models and consistency guarantees of the source architecture and how they compare to the destination. And ofcourse its a great aid to understanding any contemporary OS' kernel code. veliath
Rating:
Summary: Great Book for Linux Kernel People
Review: In many ways this is a great book. The subject is one that is known to induce headaches, and the author covers it with truly admirable clarity. It's worth buying the book for the chapter on cache consistency alone; like many others, I had to spend years piecing the same information together from varied sources, and it would be hard to overstate the value of having it all in one place. So why only three stars? The problem is that the book is incomplete. Cache systems and virtual-memory systems interact in myriad ways, but you wouldn't know that from reading this book. Similarly, storage and networking subsystems are often the bloodiest battlegrounds with respect to multiprocessor synchronization, and yet special considerations in those areas are not covered. Many old architectures (e.g. Apollo, ELXSI) are mentioned, and yet NUMA never even gets a nod. I know that covering all of these topics in any kind of depth would be impossible in a single book of any reasonable length, but their *total* omission is something I consider unacceptable. This is a book I would recommend without hesitation to any number of people. Unfortunately, that recommendation would always have to be accompanied by recommendations for other books that pick up where this one inexplicably leaves off.
Rating: 
Summary: What's there is good, but...
Review: In many ways this is a great book. The subject is one that is known to induce headaches, and the author covers it with truly admirable clarity. It's worth buying the book for the chapter on cache consistency alone; like many others, I had to spend years piecing the same information together from varied sources, and it would be hard to overstate the value of having it all in one place. So why only three stars? The problem is that the book is incomplete. Cache systems and virtual-memory systems interact in myriad ways, but you wouldn't know that from reading this book. Similarly, storage and networking subsystems are often the bloodiest battlegrounds with respect to multiprocessor synchronization, and yet special considerations in those areas are not covered. Many old architectures (e.g. Apollo, ELXSI) are mentioned, and yet NUMA never even gets a nod. I know that covering all of these topics in any kind of depth would be impossible in a single book of any reasonable length, but their *total* omission is something I consider unacceptable. This is a book I would recommend without hesitation to any number of people. Unfortunately, that recommendation would always have to be accompanied by recommendations for other books that pick up where this one inexplicably leaves off.
Rating:
Summary: The best book I've seen on the subject.
Review: This book clearly explains the operation of caches and MP systems in a way I've never seen before. The books used in my computer architecture class always left me with a somewhat vague feeling on how things worked, plus they only barely mentioned the software issues. Similarly, my OS class never really got into MP subjects like memory ordering and the effect of caches on the OS. But this book brought everything into focus with clear explanations and good examples. The best way to describe this book is that it's part computer architecture book and part operating systems book. The operation of the hardware is presented in good detail, without going as far as worrying about gates and transistors. The software issues are also described in detail along with various solutions and trade-offs between them. I highly recommend this book for anyone who wants to understand the operation of caches and SMP systems from both the hardware and software point of view.
Rating:
Summary: An Excellent Book!
Review: This book contains a very complete treatment of the subject and is very well organized. Two things impressed me about the organization. First, you can read and understand the book in one pass. All the concepts are presented in an order such that they build upon one another in a logical manner. This makes it so much easier to understand things. Second, I was impressed by the fact that the author anticipated the questions readers would have. For instance, a number of times I'd be reading a section and a question would occur to me. Then I would find the answer to my question in the very next paragraph or section. You can really tell the author put a lot of thought into how to best present the material. On the technical side, I like the fact that the book presents different alternatives for the various implementations and discusses the trade-offs between them. This is one of the things that has made this my most frequently used desk reference here at work.
Rating:
Summary: Wonderful Book
Review: This book is amazing. I wanted to learn more about synchronization on multiprocessor systems, this book covers that better than any other source I have found. If you want to understand SMP systems and the programming issues they cause, this is the book.
<< 1 >>
| 
