云计算与分布式系统：从并行处理到物联网

基本信息

书名:云计算与分布式系统：从并行处理到物联网

定价：99.00元

作者:[美] kai Hwang 等 著

出版社：机械工业出版社

出版日期：2012-05-01

ISBN：9787111382270

字数：

页码：668

版次：668

装帧：平装

开本：16开

商品重量：

编辑推荐

内容提要

随着信息技术的广泛应用和快速发展，云计算作为一种新兴的商业计算模型日益受到人们的广泛关注。本书是一本完整讲述云计算与分布式系统基本理论及其应用的教材。书中从现代分布式模型概述开始，介绍了并行、分布式与云计算系统的设计原理、系统体系结构和创新应用，并通过开源应用和商业应用例子，阐述了如何为科研、电子商务、社会网络和超级计算等创建高性能、可扩展的、可靠的系统。　　
n　　《云计算与分布式系统：从并行处理到物联网（英文版）》特色：
n　　全面覆盖现代分布式计算技术，包括集群、网格、面向服务的体系结构、大规模并行处理器、对等网络和云计算。
n　　提供的案例研究来自主流分布式计算供应商，如、微软、谷歌等。
n　　解释如何利用虚拟化来促进管理、调试、迁移和灾难恢复。
n　　专为本科生或研究生的分布式系统课程而设计——每章后都配有习题和进一步阅读建议，并为教师提供配套的PPT等教辅资源。

目录

Preface
nAbout the Authors.
nPART SYSTEMS MODELING, CLUSTERING
nAND VIRTUALIZATION
nCHAPTER Distributed System Models and Enabling Technologies
nSummary
n1.1 Scalable Computing over the Inter
n1.1.1 The Age of Inter Computing
n1.1.2 Scalable Computing Trends and New Paradigms8
n1.1.3 The Inter of Things and Cyber-Physical Systems
n1.2 Technologies for Network-Based Systems.13
n1.2.1 Multicore CPUs and Multithreading Technologies
n1.2.2 GPU Computing to Exascale and Beyond.
n1.2.3 Memory, Storage, and Wide-Area Networking.
n1.2.4 Virtual Machines and VirtualizatioMiddleware.
n1.2.5 Data Center Virtualizatiofor Cloud Computing.
n1.3 System Models for Distributed and Cloud Computing.
n1.3.1 Clusters of Cooperative Computers.
n1.3.2 Grid Computing Infrastructures.
n1.3.3 Peer-to-Peer Network Families
n1.3.4 Cloud Computing over the Inter.
n1.4 Software Environments for Distributed Systems and Clouds.
n1.4.1 Service-Oriented Architecture (SOA)
n1.4.2 Trends toward Distributed Operating Systems.
n1.4.3 Parallel and Distributed Programming Models.
n1.5 Performance, Security, and Energy Efficiency
n1.5.1 Performance Metrics and Scalability Analysis.
n1.5.2 Fault Tolerance and System Availability.
n1.5.3 Network Threats and Data Integrity
n1.5.4 Energy Efficiency iDistributed Computing.
n1.6 Bibliographic Notes and Homework Problems.
nAcknowledgments.
nReferences
nHomework Problems.
nForeword.
nCHAPTER Computer Clusters for Scalable Parallel Computing
nSummary.
n2.1 Clustering for Massive Parallelism
n2.1.1 Cluster Development Trends
n2.1.2 DesigObjectives of Computer Clusters.
n2.1.3 Fundamental Cluster DesigIssues.
n2.1.4 Analysis of the Top Superputers.
n2.2 Computer Clusters and MPP Architectures
n2.2.1 Cluster Organizatioand Resource Sharing
n2.2.2 Node Architectures and MPP Packaging.
n2.2.3 Cluster System Interconnects
n2.2.4 Hardware, Software, and Middleware Support.
n2.2.5 GPU Clusters for Massive Parallelism
n2.3 DesigPrinciples of Computer Clusters
n2.3.1 Single-System Image Features
n2.3.2 High Availability through Redundancy.
n2.3.3 Fault-Tolerant Cluster Configurations
n2.3.4 Checkpointing and Recovery Techniques
n2.4 Cluster Job and Resource Management
n2.4.1 Cluster Job Scheduling Methods
n2.4.2 Cluster Job Management Systems.
n2.4.3 Load Sharing Facility (LSF) for Cluster Computing
n2.4.4 MOSIX: AOS for Linux Clusters and Clouds.
n2.5 Case Studies of Top Superputer Systems.
n2.5.1 Tianhe-1A: The World Fastest Superputer i10
n2.5.2 Cray XT5 Jaguar: The Top Superputer i09
n2.5.3 IBM Roadrunner: The Top Superputer i08
n2.6 Bibliographic Notes and Homework Problems
nAcknowledgments. 1
nReferences.
nHomework Problems.
nCHAPTER Virtual Machines and Virtualizatioof Clusters and Data Centers.
nSummary
n3.1 ImplementatioLevels of Virtualizatio
n3.1.1 Levels of VirtualizatioImplementation.
n3.1.2 VMM DesigRequirements and Providers.
n3.1.3 VirtualizatioSupport at the OS Level
n3.1.4 Middleware Support for Virtualizatio
n3.2 VirtualizatioStructures/Tools and Mechanisms.
n3.2.1 Hypervisor and XeArchitecture.
n3.2.2 Binary Translatiowith Full Virtualization.
n3.2.3 Para-Virtualizatiowith Compiler Support.
ni Contents
n3.3 Virtualizatioof CPU, Memory, and I/O Devices.
n3.3.1 Hardware Support for Virtualizatio
n3.3.2 CPU Virtualizatio
n3.3.3 Memory Virtualization.
n3.3.4 I/O Virtualization150
n3.3.5 VirtualizatioiMulti-Core Processors.
n3.4 Virtual Clusters and Resource Management.
n3.4.1 Physical versus Virtual Clusters
n3.4.2 Live VM MigratioSteps and Performance Effects.
n3.4.3 Migratioof Memory, Files, and Network Resources.
n3.4.4 Dynamic Deployment of Virtual Clusters
n3.5 Virtualizatiofor Data-Center Automatio
n3.5.1 Server ConsolidatioiData Centers
n3.5.2 Virtual Storage Management. 1
n3.5.3 Cloud OS for Virtualized Data Centers.
n3.5.4 Trust Management iVirtualized Data Centers.
n3.6 Bibliographic Notes and Homework Problems
nAcknowledgments.
nReferences.
nHomework Problems.
nPART PUTING CLOUDS, SERVICE-ORIENTED
nARCHITECTURE, AND PROGRAMMING
nCHAPTER Cloud Platform Architecture over Virtualized Data Centers
nSummary
n4.1 Cloud Computing and Service Models.
n4.1.1 Public, Private, and Hybrid Clouds.
n4.1.2 Cloud Ecosystem and Enabling Technologies.
n4.1.3 Infrastructure-as-a-Service (IaaS)
n4.1.4 Platform-as-a-Service (PaaS) and Software-as-a-Service (SaaS).
n4.2 Data-Center Desigand InterconnectioNetworks206
n4.2.1 Warehouse-Scale Data-Center Design206
n4.2.2 Data-Center InterconnectioNetworks
n4.2.3 Modular Data Center iShipping Containers.
n4.2.4 Interconnectioof Modular Data Centers
n4.2.5 Data-Center Management Issues
n4.3 Architectural Desigof Compute and Storage Clouds.
n4.3.1 A Generic Cloud Architecture Desig
n4.3.2 Layered Cloud Architectural Development.
n4.3.3 VirtualizatioSupport and Disaster Recovery.
n4.3.4 Architectural DesigChallenges
nContents ii
n4.4 Public Cloud Platforms: GAE, AWS, and Azure
n4.4.1 Public Clouds and Service Offerings.
n4.4.2 Google App Engine (GAE)229
n4.4.3 AmazoWeb Services (AWS).
n4.4.4 Microsoft Windows Azure.
n4.5 Inter-cloud Resource Management
n4.5.1 Extended Cloud Computing Services.
n4.5.2 Resource Provisioning and Platform Deployment
n4.5.3 Virtual Machine Creatioand Management.
n4.5.4 Global Exchange of Cloud Resources
n4.6 Cloud Security and Trust Management.
n4.6.1 Cloud Security Defense Strategies.
n4.6.2 Distributed Intrusion/Anomaly Detection
n4.6.3 Data and Software ProtectioTechniques
n4.6.4 Reputation-Guided Protectioof Data Centers
n4.7 Bibliographic Notes and Homework Problems
nAcknowledgements
nReferences.
nHomework Problems.
nCHAPTER Service-Oriented Architectures for Distributed Computing
nSummary
n5.1 Services and Service-Oriented Architecture
n5.1.1 REST and Systems of Systems.
n5.1.2 Services and Web Services.
n5.1.3 Enterprise Multitier Architecture
n5.1.4 Grid Services and OGSA.
n5.1.5 Other Service-Oriented Architectures and Systems.
n5.2 Message-Oriented Middleware
n5.2.1 Enterprise Bus.
n5.2.2 Publish-Subscribe Model and Notificatio
n5.2.3 Queuing and Messaging Systems.
n5.2.4 Cloud or Grid Middleware Applications.
n5.3 Portals and Science Gateways
n5.3.1 Science Gateway Exemplars
n5.3.2 HUBzero Platform for Scientific Collaboration
n5.3.3 OpeGateway Computing Environments (OGCE).
n5.4 Discovery, Registries, Metadata, and Databases.
n5.4.1 UDDI and Service Registries.
n5.4.2 Databases and Publish-Subscribe
n5.4.3 Metadata Catalogs308
n5.4.4 Semantic Web and Grid
n5.4.5 Job ExecutioEnvironments and Monitoring.
nv Contents
n5.5 Workflow iService-Oriented Architectures.
n5.5.1 Basic Workflow Concepts.315
n5.5.2 Workflow Standards316
n5.5.3 Workflow Architecture and Specification.
n5.5.4 Workflow ExecutioEngine319
n5.5.5 Scripting Workflow System Swift.
n5.6 Bibliographic Notes and Homework Problems
nAcknowledgements
nReferences.
nHomework Problems.
nCHAPTER Cloud Programming and Software Environments.
nSummary
n6.1 Features of Cloud and Grid Platforms
n6.1.1 Cloud Capabilities and Platform Features
n6.1.2 Traditional Features Commoto Grids and Clouds.
n6.1.3 Data Features and Databases.
n6.1.4 Programming and Runtime Support341
n6.2 Parallel and Distributed Programming Paradigms
n6.2.1 Parallel Computing and Programming Paradigms
n6.2.2 MapReduce, Twister, and Iterative MapReduce.
n6.2.3 Hadoop Library from Apache.355
n6.2.4 Dryad and DryadLINQ from Microsoft.
n6.2.5 Sawzall and Pig LatiHigh-Level Languages.
n6.2.6 Mapping Applications to Parallel and Distributed Systems
n6.3 Programming Support of Google App Engine
n6.3.1 Programming the Google App Engine
n6.3.2 Google File System (GFS).
n6.3.3 BigTable, Google’s NOSQL System
n6.3.4 Chubby, Google’s Distributed Lock Service.
n6.4 Programming oAmazoAWS and Microsoft Azure.
n6.4.1 Programming oAmazoEC2.
n6.4.2 AmazoSimple Storage Service (S3).
n6.4.3 AmazoElastic Block Store (EBS) and SimpleDB.
n6.4.4 Microsoft Azure Programming Support.
n6.5 Emerging Cloud Software Environments.
n6.5.1 OpeSource Eucalyptus and Nimbus.
n6.5.2 OpenNebula, Sector/Sphere, and OpenStack.
n6.5.3 Manjrasoft Aneka Cloud and Appliances.
n6.6 Bibliographic Notes and Homework Problems399
nAcknowledgement
nReferences.
nHomework Problems.
nContents xv
nPART GRIDS, P2P, AND THE FUTURE INTERNET
nCHAPTER Grid Computing Systems and Resource Management
nSummary 16
n7.1 Grid Architecture and Service Modeling.
n7.1.1 Grid History and Service Families.
n7.1.2 CPU Scavenging and Virtual Superputers419
n7.1.3 OpeGrid Services Architecture (OGSA)
n7.1.4 Data-Intensive Grid Service Models425
n7.2 Grid Projects and Grid Systems Built
n7.2.1 National Grids and International Projects.
n7.2.2 NSF TeraGrid ithe United States.
n7.2.3 DataGrid ithe EuropeaUnio
n7.2.4 The ChinaGrid DesigExperiences
n7.3 Grid Resource Management and Brokering
n7.3.1 Resource Management and Job Scheduling.
n7.3.2 Grid Resource Monitoring with CGSP
n7.3.3 Service Accounting and Economy Model
n7.3.4 Resource Brokering with Gridbus.
n7.4 Software and Middleware for Grid Computing
n7.4.1 OpeSource Grid Middleware Packages.
n7.4.2 The Globus Toolkit Architecture (GT4).
n7.4.3 Containers and Resources/Data Management.
n7.4.4 The ChinaGrid Support Platform (CGSP)
n7.5 Grid ApplicatioTrends and Security Measures
n7.5.1 Grid Applications and Technology Fusio
n7.5.2 Grid Workload and Performance Prediction.
n7.5.3 Trust Models for Grid Security Enforcement
n7.5.4 Authenticatioand AuthorizatioMethods
n7.5.5 Grid Security Infrastructure (GSI).
n7.6 Bibliographic Notes and Homework Problems
nAcknowledgments
nReferences471
nHomework Problems
nCHAPTER Peer-to-Peer Computing and Overlay Networks
nSummary
n8.1 Peer-to-Peer Computing Systems.
n8.1.1 Basic Concepts of P2P Computing Systems.
n8.1.2 Fundamental Challenges iP2P Computing.
n8.1.3 Taxonomy of P2P Network Systems.
n8.2 P2P Overlay Networks and Properties
n8.2.1 Unstructured P2P Overlay Networks
nxvi Contents
n8.2.2 Distributed Hash Tables (DHTs)
n8.2.3 Structured P2P Overlay Networks.
n8.2.4 Hierarchically Structured Overlay Networks
n8.3 Routing, Promity, and Fault Tolerance
n8.3.1 Routing iP2P Overlay Networks.
n8.3.2 Network Promity iP2P Overlays
n8.3.3 Fault Tolerance and Failure Recovery
n8.3.4 ChurResilience against Failures.
n8.4 Trust, Reputation, and Security Management
n8.4.1 Peer Trust and ReputatioSystems
n8.4.2 Trust Overlay and DHT Implementation
n8.4.3 PowerTrust: A Scalable ReputatioSystem.
n8.4.4 Securing Overlays to Prevent DDoS Attacks.
n8.5 P2P File Sharing and Copyright Protectio
n8.5.1 Fast Search, Replica, and Consistency
n8.5.2 P2P Content Delivery Networks
n8.5.3 Copyright ProtectioIssues and Solutions
n8.5.4 Collusive Piracy PreventioiP2P Networks
n8.6 Bibliographic Notes and Homework Problems
nAcknowledgements
nReferences
nHomework Problems.
nCHAPTER Ubiquitous Clouds and the Inter of Things
nSummary
n9.1 Cloud Trends iSupporting Ubiquitous Computing
n9.1.1 Use of Clouds for HPC/HTC and Ubiquitous Computing
n9.1.2 Large-Scale Private Clouds at NASA and CERN
n9.1.3 Cloud Mashups for Agility and Scalability
n9.1.4 Cloudlets for Mobile Cloud Computing
n9.2 Performance of Distributed Systems and the Cloud
n9.2.1 Review of Science and Research Clouds
n9.2.2 Data-Intensive Scalable Computing (DISC)
n9.2.3 Performance Metrics for HPC/HTC Systems
n9.2.4 Quality of Service iCloud Computing
n9.2.5 Benchmarking MPI, Azure, EC2, MapReduce, and Hadoop
n9.3 Enabling Technologies for the Inter of Things
n9.3.1 The Inter of Things for Ubiquitous Computing
n9.3.2 Radio-Frequency Identificatio(RFID)
n9.3.3 Sensor Networks and ZigBee Technology
n9.3.4 Global Positioning System (GPS)
n9.4 Innovative Applications of the Inter of Things
n9.4.1 Applications of the Inter of Things
nContents xvii
n9.4.2 Retailing and Supply-ChaiManagement
n9.4.3 Smart Power Grid and Smart Buildings
n9.4.4 Cyber-Physical System (CPS)
n9.5 Online Social and Professional Networking
n9.5.1 Online Social Networking Characteristics
n9.5.2 Graph-Theoretic Analysis of Social Networks
n9.5.3 Communities and Applications of Social Networks
n9.5.4 Facebook: The World’s Largest Social Network
n9.5.5 Twitter for Microblogging, News, and Alert Services
n9.6 Bibliographic Notes and Homework Problems
nAcknowledgements
nReferences.
nHomework Problems
nIndex

作者介绍

Kai Hwang（黄铠）美国南加州大学电子工程与计算机科学教授，互联网/云计算研究实验室主任；清华大学IV客座讲席教授；IEEE终身会士。他拥有加州大学伯克利分校 EECS博士学位，主要研究领域为云计算、分布式系统、高性能计算、普适计算、信任网格计算等。 现已发表论文220多篇，出版8本计算机体系结构、数字运算、并行处理、分布式系统、互联网安全和云计算方面的相关著作。他还创建了《the Journal of Parallel and Distributed Computing》，并获得了中国计算机学会2004杰出成就奖、IEEE2011 IPDPS创立者奖。
n　　Geoffrey Fox 美国印第安那大学计算机科学、信息与物理学杰出教授，社会网格实验室主任。之前曾在加州理工和锡拉丘兹大学任教，并领导多个研究组。他拥有英国剑桥大学的 博士学位。Fox在并行体系结构、分布式编程、网格计算、Web服务和互联网应用方面做了广泛的工作并发表了大量作品。
n　　Jack Dongarra 美国田纳西大学电子工程与计算机科学杰出教授，橡树岭国家实验室杰出研究员，曼彻斯特大学Turning Fellow。他是ACM/IEEE/SIAM/AAAS 会士，是超级计算机基准测试、数值分析、线性代数解算器和高性能计算领域的先驱。多年以来，他都在负责Top 500 快计算机的Linpack基准测试评估。基于他在超级计算和高性能领域的巨大贡献，他被评为美国国家工程院院士。

序言