Adaptive Software Implemented Fault-Tolerance for Networked Systems

网络系统的自适应软件实现容错（项目摘要）该项目将进行一项实验研究，以调查在网络环境中开发一套通用的容错服务。研究重点是设计软件实现的容错（SIFT）层变色龙（Chameleon），该层将为用户应用程序提供容错服务，管理跨网络的用户进程，提供快速错误检测，并从硬件、操作系统、应用程序和SIFT层的错误中启动恢复。换句话说，变色龙将保护分布式系统中的所有关键组件，包括它自己。我们开发变色龙的主要目标是定义和演示SIFT架构，其中包括静态和动态可重构性以及集成环境中的大量错误检测和恢复协议。我们将研究使变色龙静态和动态可重构的方法。动态可重构性将允许变色龙改变其在目标生命周期内提供的可靠性服务级别。此外，Chameleon的构造将有助于为硬件、操作系统和应用程序创建新的容错技术。对于静态可重构性，我们设想提供一个容错技术库，从中可以为目标应用程序提供自定义容错解决方案。特定的解决方案将由一系列分布式错误检测和恢复技术组成，以提供应用程序所需的可靠性级别。

Adaptive Software-Implemented Fault Tolerance for Networked Systems (Project Summary)This project will conduct an experimental study to investigatedeveloping a set of general-purpose, fault tolerance services in anetworked environment. The research will focus on designing asoftware-implemented fault tolerance (SIFT) layer, Chameleon,which will provide fault tolerance services to user applications,manage user processes across the network, provide rapid errordetection, and initiate recovery from errors in the hardware,the operating system, applications, and the SIFT layer. In otherwords, Chameleon will protect all of the key components in adistributed system, including itself.Our primary objective in developing Chameleon is to defineand demonstrate the SIFT architecture, which includes static anddynamic reconfigurability and an extensive suite of errordetection and recovery protocols in an integrated environment.We will investigate ways to make Chameleon both statically anddynamically reconfigurable. Dynamic reconfigurability will allowChameleon to change the level of reliability services that itprovides during the lifetime of the target. In addition,Chameleon will be constructed to facilitate the creation of newfault tolerance techniques for the hardware, operating system,and applications. For static reconfigurability, we envisionproviding a library of fault tolerance techniques from which acustomized fault tolerance solution can be provided to a targetapplication. A specific solution will be composed of a range ofdistributed error detection and recovery techniques to providethe level of dependability required by the application.