High Performance Linux Clusters With Oscar, Rocks,openmosix, And Mpi (Paperback)

Description:

To the outside world, a "supercomputer" appears to be a single system. In fact, it's a cluster of computers that share a local area network and have the ability to work together on a single problem as a team. Many businesses used to consider supercomputing beyond the reach of their budgets, but new Linux applications have made high-performance clusters more affordable than ever. These days, the promise of low-cost supercomputing is one of the main reasons many businesses choose Linux over other operating systems.

This new guide covers everything a newcomer to clustering will need to plan, build, and deploy a high-performance Linux cluster. The book focuses on clustering for high-performance computation, although much of its information also applies to clustering for high-availability (failover and disaster recovery). The book discusses the key tools you'll need to get started, including good practices to use while exploring the tools and growing a system. You'll learn about planning, hardware choices, bulk installation of Linux on multiple systems, and other basic considerations. Then, you'll learn about software options that can save you hours--or even weeks--of deployment time.

Since a wide variety of options exist in each area of clustering software, the author discusses the pros and cons of the major free software projects and chooses those that are most likely to be helpful to new cluster administrators and programmers. A few of the projects introduced in the book include:

• MPI, the most popular programming library for clusters. This book offers simple but realistic introductory examples along with some pointers for advanced use.
  
• OSCAR and Rocks, two comprehensive installation and administrative systems
  
• openMosix (a convenient tool for distributing jobs), Linux kernel extensions that migrate processes transparently for load balancing
  
• PVFS, one of the parallel filesystems that make clustering I/O easier
  
• C3, a set of commands for administering multiple systems

Ganglia, OpenPBS, and cloning tools (Kickstart, SIS and G4U) are also covered. The book looks at cluster installation packages (OSCAR & Rocks) and then considers the core packages individually for greater depth or for folks wishing to do a custom installation. Guidelines for debugging, profiling, performance tuning, and managing jobs from multiple users round out this immensely useful book.

 

Preface
Part I. An Introduction to Clusters
1. Cluster Architecture
      Modern Computing and the Role of Clusters
      Types of Clusters
      Distributed Computing and Clusters
      Limitations
      My Biases
2. Cluster Planning
      Design Steps
      Determining Your Cluster's Mission
      Architecture and Cluster Software
      Cluster Kits
      CD-ROM-Based Clusters
      Benchmarks
3. Cluster Hardware
      Design Decisions
      Environment
4. Linux for Clusters
      Installing Linux
      Configuring Services
      Cluster Security
Part II. Getting Started Quickly
5. openMosix
      What is openMosix?
      How openMosix Works
      Selecting an Installation Approach
      Installing a Precompiled Kernel
      Using openMosix
      Recompiling the Kernel
      Is openMosix Right for You?
6. OSCAR
      Why OSCAR?
      What's in OSCAR
      Installing OSCAR
      Security and OSCAR
      Using switcher
      Using LAM/MPI with OSCAR
7. Rocks
      Installing Rocks
      Managing Rocks
      Using MPICH with Rocks
Part III. Building Custom Clusters
8. Cloning Systems
      Configuring Systems
      Automating Installations
      Notes for OSCAR and Rocks Users
9. Programming Software
      Programming Languages
      Selecting a Library
      LAM/MPI
      MPICH
      Other Programming Software
      Notes for OSCAR Users
      Notes for Rocks Users
10. Management Software
      C3
      Ganglia
      Notes for OSCAR and Rocks Users
11. Scheduling Software
      OpenPBS
      Notes for OSCAR and Rocks Users
12. Parallel Filesystems
      PVFS
      Using PVFS
      Notes for OSCAR and Rocks Users
Part IV. Cluster Programming
13. Getting Started with MPI
      MPI
      A Simple Problem
      An MPI Solution
      I/O with MPI
      Broadcast Communications
14. Additional MPI Features
      More on Point-to-Point Communication
      More on Collective Communication
      Managing Communicators
      Packaging Data
15. Designing Parallel Programs
      Overview
      Problem Decomposition
      Mapping Tasks to Processors
      Other Considerations
16. Debugging Parallel Programs
      Debugging and Parallel Programs
      Avoiding Problems
      Programming Tools
      Rereading Code
      Tracing with printf
      Symbolic Debuggers
      Using gdb and ddd with MPI
      Notes for OSCAR and Rocks Users
17. Profiling Parallel Programs
      Why Profile?
      Writing and Optimizing Code
      Timing Complete Programs
      Timing C Code Segments
      Profilers
      MPE
      Customized MPE Logging
      Notes for OSCAR and Rocks Users
Part V. Appendix
             References
      Books
      URLs
Index

描述：
對外界而言，「超級電腦」似乎是一個單一的系統。實際上，它是一個共享本地區域網絡並能夠作為一個團隊共同解決問題的計算機集群。許多企業曾經認為超級計算超出了他們的預算範圍，但新的Linux應用程序使高性能集群比以往更具成本效益。如今，低成本超級計算的承諾是許多企業選擇Linux而不是其他操作系統的主要原因之一。

這本新指南涵蓋了一個新手在集群中規劃、構建和部署高性能Linux集群所需的一切。該書專注於高性能計算的集群，雖然其中的許多信息也適用於高可用性集群（故障轉移和災難恢復）。該書討論了您開始所需的關鍵工具，包括在探索工具和擴展系統時使用的良好實踐。您將了解規劃、硬件選擇、在多個系統上批量安裝Linux以及其他基本考慮因素。然後，您將了解可以節省部署時間的軟件選項，甚至可以節省數小時甚至數週的時間。

由於在每個集群軟件領域都存在各種各樣的選擇，作者討論了主要免費軟件項目的優點和缺點，並選擇了對新的集群管理員和程序員最有幫助的項目。書中介紹的一些項目包括：
- MPI，最受歡迎的集群編程庫。本書提供了簡單但實用的入門示例以及一些進階使用的指南。
- OSCAR和Rocks，兩個全面的安裝和管理系統。
- openMosix（一個方便的工具，用於分發作業），Linux內核擴展，用於透明地遷移進程以實現負載平衡。
- PVFS，一種使集群I/O更加容易的並行文件系統。
- C3，用於管理多個系統的一組命令。

書中還介紹了Ganglia、OpenPBS和克隆工具（Kickstart、SIS和G4U）。該書介紹了集群安裝包（OSCAR和Rocks），然後逐個考慮核心包以獲得更深入的了解，或者供希望進行自定義安裝的人使用。調試、性能分析、性能調優和管理多個用戶的作業的指南使這本書變得非常有用。

目錄：
前言
第一部分：集群介紹
1. 集群架構
- 現代計算和集群的角色
- 集群類型
- 分散計算和集群
- 限制
- 我的偏見
2. 集群規劃
- 設計步驟
- 確定集群的任務
- 架構和集群軟件
- 集群套件
- 基於CD-ROM的集群
- 基準測試
3. 集群硬件
- 設計決策
- 環境
4. Linux用於集群
- 安裝Linux
- 配置服務