CSR---PDOS: Liberating Personal Computing from Hardware

CSR---PDOS：将个人计算从硬件中解放出来

• 批准号: 0509004
• 负责人: Mahadev Satyanarayanan
• 金额: --
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2005
• 资助国家: 美国
• 起止时间: 2005-07-01 至 2010-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0509004&HistoricalAwards=false
• 关键词: CSR; PDOS; Liberating; Personal; Computing

The goal of this research is to remove the tight binding of userstate to specific computing hardware. This tight binding aroseat the birth of personal computing nearly three decades ago, andhas continued unchanged since that time. It has many negativeconsequences: hardware upgrades are painful, disaster recovery iscomplex, and total cost of ownership is high. It also forcesmobile computing into a paradigm of each user carrying personalhardware, rather than traveling hands-free and taking advantageof pervasive hardware.The proposed research aims for a new vision of on-demand personalcomputing called "Internet Suspend/Resume (ISR)" that exploitsthe ubiquitous presence of the Internet. This research exploresissues at the intersection of two well-established technologies:virtual machine (VM) technology and distributed file systemtechnology. By layering a VM on a distributed file system thatperforms aggressive client caching, a user's entire personalcomputing environment (operating system, applications and userfiles) can be accurately and safely delivered anywhere on theInternet.The proposed research spans operating systems, distributedsystems, mobile and pervasive computing, and security andprivacy. Its has three major thrusts: (a) Coping with Huge VMState, (b) Preserving Privacy of VM State, and (c) Dynamically VaryingClient Thickness. The work in each thrust includes conceptualdevelopment of novel techniques and algorithms, as well as theirimplementation and experimental validation in the context of aprototype. This prototype will be disseminated in open sourceform, for use by other researchers and by industry.

这项研究的目标是消除用户状态与特定计算硬件的紧密绑定。这种紧密的结合体现了近30年前个人计算机的诞生，并从那时起一直没有改变。它有许多负面后果：硬件升级痛苦，灾难恢复复杂，总拥有成本高。它还迫使移动计算进入一种模式，即每个用户都携带个人硬件，而不是免提旅行，并利用普及硬件。拟议的研究旨在提出一种新的按需个性化计算愿景，称为“互联网挂起/恢复(ISR)”，它利用了互联网的无处不在的存在。本研究探索了两种成熟的技术：虚拟机(VM)技术和分布式文件系统技术。通过将虚拟机分层在执行主动客户端缓存的分布式文件系统上，用户的整个个人计算环境(操作系统、应用程序和用户文件)可以准确而安全地交付到互联网上的任何位置。拟议的研究涵盖操作系统、分布式系统、移动和普及计算以及安全和隐私。它有三个主要方面：(A)处理巨大的VMState，(B)保护VM状态的隐私，(C)动态变化客户端厚度。每一项工作都包括新技术和算法的概念开发，以及它们在原型环境中的实现和实验验证。这个原型将以开放源码的形式发布，供其他研究人员和工业界使用。