ITR: Collaborative Research: Morphable Software Sevices: Self-Modifying Programs for Distributed Embedded Systems

点击翻译按钮获取中文摘要

Future embedded system applications and infrastructures will beincreasingly dynamic. Moreover, the devices used in such infrastructureswill vary widely, from sensors and embedded devices, to handhelds, to high endserver systems, all of which interact continuously in order to collect,collate, and deliver information from where it is produced to where it isneeded. This project addresses the dynamic nature of distributed embeddedsystems, by developing new information technologies that integrate acrossmultiple areas of Computer Science, including computer architecture, operatingand real-time systems, compilers, and middleware. The key intent is to createmorphable embedded services, that is, services that continuously self-modifyand adapt in order to meet dynamic application needs and environmental/resourceconstraints, including power budgets, end-to-end quality of service (QoS) guarantees(e.g., timing constraints), and security constraints.There are many Useful examples of morphable services. In limited forms, theyare already present in today's cellphone platforms, for instance, where end usersdynamically download new rings or acquire new games (possibly displacing existingones), etc. Service morphing, however, goes much beyond such configurationcapabilities. Imagine a cellphone, for example, which dynamically morphs intoan portable wand, using its sensing (e.g., its built-in camera) andcommunication abilities (e.g., by interacting with other nearby phones)to guide its owner out of a disaster site. Then, in contrast to suchfunctionality-centric morphing, consider this cellphone drawing on thepower of nearby server systems (or other phones) to provide suitable levelsof service to its user, despite the fact that its power is running low. Thiscan be done, for instance, by dynamically offloading services onto otherplatforms, by (re)partitioning services across the device and cooperating serversystems, and/or by deploying more power-efficient and perhaps, less graphics-capableservice code to the phone itself. Another interesting aspect of our work is itsability to go beyond performance and power as the only critical elements of futuresystems. With our approach, for instance, compiler methods and middleware can be usedto enhance information security rather than system performance. This can be doneby scattering critical application state to reduce its exposure toexternal intrusions. As a result, information security can become an integralelement of the QoS needs of applications.A concrete example of security-focused service morphing is to `scatter'critical and vulnerable values across multiple cooperating distributedplatforms and to `assemble' them only to the extent needed by the applicationunder compiler control. Moreover, when the last use of the `assembled'value is complete, the `assembled' value is destroyed. Each use of an `assembled' value is verified by compiler-generated code that authenticates it. For example, consider the use of last four digits of the social security numberused for authenticating a transaction. The entire social security number willnever be stored in a memory location as a value (that could be hacked into).The value will be scattered in a form known only to the compiler which it willthen use to `assemble' the value just in time only for the extent of the use.The different service morphing techniques to be developed in this researchinclude dynamic component (re)deployment, (re)specialization, and (re)partitioning.Such actions are supported by system-level mechanisms that efficiently carry theperformance, usage, and requirements information needed for runtime component morphing,principally addressing components' processing and communication actions.The intent is for self-modifying components to be able to acquire runtimeinformation about current resource availabilities and Quality of Servicedemands. While developing these software technologies, we will concurrentlyexplore new application-specific techniques and methods that take advantageof morphable software services, targeting remote sensing and autonomous roboticsapplications. Finally, while most of our work will utilize current embeddedsystems platforms, using XScale boards, we will also consider how tofurther improve hardware platforms to better enable morphable services.Such work essentially broadens the optimization space in which morphableservices are able to operate.Our technical approach integrates across multiple CS disciplines, by exploiting,for instance, detailed knowledge about computer architecture (e.g., power usagerelated to memory footprint) to develop compiler techniques that dynamically generatecode with functionality and the performance/power profiles more suitable tocurrent application needs. Compiler-level and architectural knowledge is maintainedas meta-information at the middleware level, and lightweight middleware dynamicallydeploys newly morphed code to target platforms. Kernel-level mechanisms collect anddistribute the resource information needed for such actions. They also help integratethe application-level with the system-level actions being taken, the latter beingparticularly important when satisfying certain end-to-end constraints(e.g., timing or power constraints) desired by distributed embedded applications.A key goal of this research is to demonstrate the importance and utility ofmorphable services for critical applications. This implies the need tojointly develop application techniques and ideas with morphable service technologies.By grounding our research in a challenging application domain, autonomous robots used inemergency management situations, our technological solutions must ``close the loop'',integrating system-level information about resource constraints, withmiddleware-level options to morph services, with application-level opportunitiesfor making tradeoffs and choices about how to best meet current requirements.The result are systems in which changed application needs result in new codemodules deployed and specialized to meet these needs, jointly with changes inunderlying system configurations and properties. In other words, applications andsystems are continuously `morphed' to best match end user requirements.A concrete example of extending application-level research to exploitservice morphing is to extend mission-centric notions of `value' in autonomousrobots. In robotics, `value' captures an individual robot's contribution to a missionundertaken by a robot team, and `value' helps a robot determine its next actions.Our new research will extend these solutions: instead of considering onlymovement alternatives, the robots will also consider the `values' ofother activities like communication, computation and observation. This approachdepends significantly on other components of this proposal, namely QoSmanagement and cooperative service morphing, so that the communication linksavailable to a robot team and the CPU power needed for interpreting distributedsensor inputs can be deployed appropriately.