嵌入式分布实时系统自适应资源管理架构

分析了开放嵌入式分布实时(Distributed Real-time and Embedded,DRE)系统的自适应资源管理需求,针对传统静态资源管理方法的不足,提出了一种面向开放DRE系统的自适应资源管理架构;该架构采用动态任务管理、实时资源分配和自适应控制三种关键技术,能够更加适用于开放、动态的环境,有效应对资源约束和资源状态、应用程序QoS的变化;提高系统性能和稳定性;屏蔽底层硬件资源的异构性,为上层应用提供统一的服务接口。     

嵌入式自适应实时资源管理

现存的资源管理方法是针对传统的封闭嵌入实时系统设计的,在动态环境时难以保证系统的服务质量。为此,依据新一代典型动态实时系统的需求,运用基于控制论的自适应实时资源管理方法,改进Red Hat公司的eCos操作系统,在原eCos操作系统中加入基于控制论的实时调度架构、RM调度器、实时任务API和系统监视器,实现一个嵌入式自适应实时资源管理架构。实验结果证明,该架构具有更精确和高效的服务质量,保证系统实时动态的资源需求和实时任务的正确性。     

Trade-Off Analysis of Real-Time Control Performance and Schedulability*

Most real-time computer-controlled systems are developed in two separate stages: controller design followed by its digital implementation. Computational tasks that implement the control algorithms are usually scheduled by treating their execution times and periods as unchangeable parameters. Task schedulability therefore depends only on the limited computing resources available. On the other hand, controller design is primarily based on the continuous-time dynamics of the physical system being controlled. The set of tasks resulting from this controller design may not be schedulable with the limited computing resources available. Even if the given set of tasks is schedulable, their overall performance may not be optimal in the sense that they do not make a full use of the computing resources. In this paper, we propose an integrated approach to controller design and task scheduling. Specifically, task frequencies (or periods) are allowed to vary within a certain range as long as such changes do not affect critical control functions such as the maintenance of system stability. We present an algorithm that determines the task frequencies such that a prescribed aspect of system performance is optimized subject to satisfaction of computing resource constraints. The tasks are then scheduled with the chosen frequencies. The proposed approach also addresses the issue of choosing controller processors.     

On Schedulability Analysis of AADL Architecture with Storage Resource Constraint

Embedded systems have been widely applied in real-time automatic control systems, and most of these systems are safety-critical, for example, the engine control systems in an automobile and the avionics in an airplane. It is very important to verify the schedulability of such a real-time embedded system in its early design stages, so as to avoid unexpected loss for the debugging of architecture design problems. However, it has been proved to be a tough challenge to evaluate the schedulability of a Preemptive-Scheduling Real-Time (PSRT) system, especially when the constraints of system resources are taken into consideration. The cache memory built inside the processor is an exclusive-accessing resource shared by all the tasks deployed on the processor. In addition, the Cache-Related Preemption Delay (CRPD) caused by preemptive task scheduling will bring extra time to the execution time for all the tasks. Thus, the CRPD should be taken into consideration when the Worst-Case Execution Time (WCET) of tasks is estimated in a real-time system. A model-based evaluation and verification method of architecture schedulability, which is designed for priority-based PSRT systems, is proposed in this study to make cache resource constrained and CRPD related schedulability evaluation based on the AADL system architecture model. In the first step, the study enhances the property set of AADL storage elements to make it compatible with cache memory properties in a system architecture model. Secondly, the study proposes a set of algorithms to estimate the CRPDs of a task before it is completed; run system schedule simulation and construct the schedule sequence with the constraint of cache resources and CRPDs involved; and make WCET estimation of the tasks in such a CRPD considered, preemptive-scheduling execution sequence. Finally, the methods mentioned above are implemented within a prototype software toolkit, which is designed to make evaluation and verification of system schedulability within CRPD constraints. The toolkit is tested with a use case of aircraft airborne open-architecture intelligent information system. The result shows that, compared with the schedule sequence constructed without cache memory resource constraints, the WCET estimated for most tasks is extended, and the sequence order is changed. In some extreme cases, when CRPD is taken into consideration, some tasks are evaluated to be incompletable. The test shows that the method and algorithms proposed in this study are feasible.     

资源预留调度算法在虚拟化环境中的设计与实现

虚拟化技术在服务器领域已经得到广泛应用,可以在一台服务器或服务器集群上同时运行几个不同的操作系统,诸多优点包括:故障隔离、高效利用资源、负载均衡、安全性等.常用的虚拟化系统如VMware、Virtual PC等采用全虚拟化技术,比较消耗资源,因此不适用于嵌入式领域的应用.而Xen采用半虚拟化技术,性能方面得到了很大提升,为虚拟化技术在嵌入式领域的应用创造了条件.由于嵌入式设备有着数据实时采集、现场控制、高危环境等特殊应用背景,嵌入式系统对实时性都有一定的要求.目前的虚拟化技术没有很好的方法来保障系统的实时性.本文在XEN虚拟化环境中设计并实现基于资源预留的实时调度算法,即在虚拟机监视器(Virtual Machine Monitor,VMM)层面实现常量带宽服务器(Constant Bandwidth Server,CBS)调度算法,用于有效调度实时和非实时的虚拟机子系统,并保障不同子系统之间的性能隔离.     

基于概率的实时任务调度分析

在某些软实时系统中,为了降低系统成本,允许系统过载,并且允许过载时少量任务能错失时限;对于这样的系统,常常能设法获得其任务的执行时间所服从的概率分布。针对这样的系统,提出了基于概率的可调度分析方法,对系统的性能作出概率上的估计,在概率意义上预测系统的可行性;并提出以数据挖掘技术估算任务执行时间的分类方法,这对预测系统的性能和提高系统利用率有重要的意义。     

Resource Management Middleware for Dynamic,Dependable Real-Time Systems

Thispaper presents resource management techniques that achieve thequality of service (QoS) requirements of dynamic real-time systemsusing open architectures and commercial off-the-shelf technologies(COTS). Dynamic real-time systems are subject to constant changessuch as a varying external environment, overload of internalsystems, component failure, and evolving operational requirements.Examples of such systems include the emerging generation of computer-based,command and control systems of the U.S. Navy. To enable the engineeringof such systems, we present adaptive resource management middlewaretechniques that achieve the QoS requirements of the system. Themiddleware performs QoS monitoring and failure detection, QoSdiagnosis, and reallocation of resources to adapt the systemto achieve acceptable levels of QoS. Experimental characterizationsof the middleware using a real-time benchmark illustrate itseffectiveness for adapting the system for achieving the desiredreal-time and survivability QoS during overload situations.     

实时中间件自适应资源管理策略的分析与实现

本文介绍了一种分布式实时计算环境下自适应资源管理概念,提出了实时中间件的自适应资源管理策略和相关的实现机制,并给出了该策略的QoS模型和服务管理器层次结构     

基于服务质量(QoS-Based)的ASOS资源分配与调度研究

论文针对嵌入式实时操作系统的特性提出了一种基于服务质量的ASOS系统资源管理、任务调度的模型框架,以该框架为基础,采用模糊反馈控制算法实现了对智能交通路口控制器的软件设计和具体实现。     

A DVS-assisted hard real-time I/O device scheduling algorithm

The I/O subsystem has become a major source of energy consumption in a hard real-time monitoring and control system. To reduce its energy consumption without missing deadlines, a dynamic power management (DPM) policy must carefully consider the power parameters of a device, such as its break-even time and wake-up latency, when switching off idle devices. This problem becomes extremely complicated when dynamic voltage scaling (DVS) is applied to change the execution time of a task. In this paper, we present COLORS, a composite low-power scheduling framework that includes DVS in a DPM policy to maximize the energy reduction on the I/O subsystem. COLORS dynamically predicts the earliest-access time of a device and switches off idle devices. It makes use of both static and dynamic slack time to extend the execution time of a task by DVS, in order to create additional switch-off opportunities. Task workloads, processor profiles, and device characteristics all impact the performance of a low-power real-time algorithm. We also identify a key metric that primarily determines its performance. The experimental results show that, compared with previous work, COLORS achieves additional energy reduction up to 20%, due to the efficient utilization of slack time.

A concept of dynamically reconfigurable real-time vision system for autonomous mobile robotics

This paper describes specific constraints of vision systems that are dedicated to be embedded in mobile robots. If PC-based hardware architecture is convenient in this field because of its versatility, flexibility, performance, and cost, current real-time operating systems are not completely adapted to long processing with varying duration, and it is often necessary to oversize the system to guarantee fail-safe functioning. Also, interactions with other robotic tasks having more priority are difficult to handle. To answer this problem, we have developed a dynamically reconfigurable vision processing system, based on the innovative features of Cleopatre real-time applicative layer concerning scheduling and fault tolerance. This framework allows to define emergency and optional tasks to ensure a minimal quality of service for the other subsystems of the robot, while allowing to adapt dynamically vision processing chain to an exceptional overlasting vision process or processor overload. Thus, it allows a better cohabitation of several subsystems in a single hardware, and to develop less expensive but safe systems, as they will be designed for the regular case and not rare exceptional ones. Finally, it brings a new way to think and develop vision systems, with pairs of complementary operators.     

检修公司人事劳资管理系统

检修公司人事劳资管理系统是典型的管理信息系统(MIS),本系统所创建的模块实现了如下功能:基本信息管理模块包含部门信息管理模块和员工信息管理模块,可以实现部门信息和员工信息的增加、删除、修改、查看功能;考勤考评管理模块可以实现记录的创建、修改、删除、查看功能;员工工资管理模块可以实现对员工的基本工资进行设定,对奖金以及福利补贴进行设置,用户可根据当月的情况对实发工资计算公式进行调整,根据出勤统计结果来计算本月各项实际金额以及对统计出的工资进行浏览;系统用户管理模块可以实现对普通用户的创建、密码复位、删除用户、修改自身密码,并且实现了用户的分权限管理,系统管理员具有操作本系统的所有权限,而普通用户只具有浏览权限;日志管理模块具有操作日志功能,普通用户只能浏览日志信息,管理员用户既可以浏览,又可以清空操作日志记录。     

一种动态自适应的计算网格资源管理方法

提出了资源组的原子性分配,保证了同一作业相关资源的协同分配,并避免了资源申请的死锁问题和资源昀无效占用。首先,给出了网格资源管理框架;然后提出了资源分配方法的数学模型,并引入了资源分配求解的近似算法。     

基于绩效管理的人力资源管理分析

随着社会经济的不断发展,企业的生存发展越来越离不开人力资源管理。人力资源的发掘、培养以及之后的人力资源绩效考核已经成为每个企业的工作重点。绩效管理有利于提高企业的经济效益,也是激励员工的重要手段。     

基于反馈控制理论的流媒体服务器资源管理模型

如何合理地分配系统资源，使流媒体服务器能够在满足客户基本QoS的前提下，支持尽可能多的并发服务，是流媒体研究领域的重要组成部分．提出了基于反馈控制理论的流媒体服务器资源调度模型及核心调度算法．该模型通过周期地采集系统的工作状态，并以此为根据调整任务在下一个采样周期内的运行属性，达到在满足任务的QoS的前提下，提高系统的并发程度的目的．详细分析了模型结构和核心算法的实现机制，并利用模拟平台对该算法进行了性能分析．     

嵌入式软件跟踪调试技术的研究与设计

针对在嵌入式实时操作系统环境下高低优先级任务切换过程引起的跟踪信息乱序和丢失问题,对跟踪信息嵌套缓存机制和解析机制进行了设计,提出了物理缓存管理机制与递归调用解析机制相结合、备份缓存管理机制与普通查询解析机制相结合的两种跟踪方案,解决了跟踪信息乱序和丢失问题,提高了跟踪系统的运行效率。     

时间Petri网的可调度分析及在FMS中的应用

在实时系统中,检查任务执行的计划是否满足要求的时间约束称为可调度分析.通过把时间特性与其他行为特性分离,提出了一种以时间Petri网建模的实时系统调度分析方法.如果特定任务的执行是可调度的,则可以计算任务执行的时间跨度,否则确定出不可调度的变迁以便于调整时间约束和纠正设计错误.提出了一种通过把复杂的任务序列分解成一些子序列来进行可调度性分析的综合时序分析技术,它不仅提高了效率,也有助于关于调度的可达性问题的讨论.讨论了柔性制造系统FMS中的车间装配子系统的可调度性.     

Using Markets to Engineer Resource Management for the Information Grid

Information systems are continually expanding as evidenced by the doubling of Internet connections every year. Similar growth is exhibited by information systems in defense. The Air Force's goals to achieve global awareness, dynamic planning/execution, and global information exchange involve the technologies to provide information to the warrior anywhere, anytime, and for any mission. This far-reaching enterprise will necessarily span multiple networks and computing domains of both the commercial and military varieties. As a result, many users with different goals and priorities vie for the communication and computing resources of the information grid. Managing this vast system to assure dependable operation that maintains users' quality of service levels has led researchers to propose economic models to solve the resource management problem. Information technology has begun to fundamentally alter the way business is conducted, and there is synergy between e-commerce and the management of the underlying information resources on which it runs.This paper examines the envisioned market-based, large-scale information systems for defense. Due to their criticality, these systems must also manage resources to provide survivability in the presence of information attacks. This potential for technology transfer from the defense sector to the commercial sector are described. Conversely, the leveraging of research performed in the non-military realm of e-commerce to reach the Air Force's goals will also be explored.     

弹性资源约束的动态调度决策

针对产品开发过程中由于活动变化导致原调度需要重新调整的问题,提出一种利用弹性资源特性进行动态测度决策的方法.以活动添加的变化为对象,根据活动间时序约束、资源约束等特点,分别构建时序冲突消解模型以及基于资源推拉技术的资源冲突消解模型.为提高活动冲突消解效率,提出一种虚拟前置活动和虚拟后续活动的构建方法,并确定动态调度决策指标值.最后通过船舶分段制造实例,验证了弹性资源约束的动态调度决策方法的可行性和有效性.     

实现数据存储、数据计算和资源管理的分离

在传统操作系统中,数据存储的抽象(进程虚拟地址空间)、数据计算的抽象(线程)和资源管理的抽象(进程)是不可分离的.首先分析了在操作系统中由于3类抽象不可分离而存在的问题,根据分析提出了数据存储抽象、数据计算抽象和资源管理抽象互相分离的思想,进而根据这一思想提出了虚拟地址空间基于文件操作系统,分析该操作系统的体系结构模型,研究了实现3类抽象分离的线程迁移技术和指令对文件寻址技术,最后讨论了系统的实现，测试和性能评价.此项研究说明了在操作系统中实现数据储存、数据计算和资源管理的分离是可行的.