基于双层调度框架的开放式实时系统非实时应用调度

在开放式实时系统中,多类型实时和非实时应用同时并存,这给系统调度机制带来了新的需求和挑战。对一种开放式实时系统调度机制进行了简单的介绍,指出了非实时应用调度时不可抢占区可能影响系统可调度性,并提出了一种解决方案,弥补了原有调度机制的缺点,完善了开放式实时系统的双层调度框架,保证了开放式实时系统并存多类型实时及非实时应用的可调度性。     

实时操作系统调度策略的分析与改进

在RT-Linux的基础上提出一个能统一支持硬实时、软实时和尽力而为应用的调度框架,在该框架之下,硬实时应用的响应时间短且可预测.对软实时应用进行接入控制,从而可以保证软实时应用的QoS.对尽力而为的应用保留CPU资源,从而保证它不会饥饿.     

面向数控系统的三级调度模型研究

针对硬实时系统中多种类型任务并存的特点,提出一种三级实时调度模型--TLRtS(three-level real-time scheduling).该模型将整个系统空间划分为硬实时、软实时和非实时空间,分别用来处理硬实时、软实时和非实时任务.TLRtS模型不仅可以动态加载多种实时调度算法,还可以集成相应的资源访问控制协议,解决了任务之间存在资源竞争的问题.实验结果表明,此方法既保证了所有硬实时任务严格按照其时间约束在截止期前完成,又尽可能地提高了软实时和非实时任务的服务质量.     

开放式实时系统中的自适应调度方法

首先针对开放式实时系统 ,讨论了自适应实时调度的需求情况和自适应技术应用上的关键问题 ;提出了适用于硬实时调度需求的调度参数自适应调整机制 ;重点面向软实时调度需求 ,提出了一种基于模糊控制策略的自适应调度方法 ,它致力于动态跟踪调度对象的负载变化 ,并把截止期错过率控制在期望值附近 .相对于现有方法 ,更适合于解决开放式实时系统中的自适应调度问题     

开放式实时系统资源共享环境下的调度方法分析

介绍Stack Resource Policy及以其为基础的用于开放式实时系统资源共享环境下静态调度策略,分析其存在的两个问题:资源锁定时间过长和任务不可执行,介绍相关解决方法.然后介绍Bandwidth Inheritance及类似的动态调度策略的基本调度规则并重点分析Bandwidth Inheritance在一般情况下,由于软实时任务的动态性,可能出现的软实时任务阻塞硬实时任务,导致硬实时任务截止时间得不到满足的问题.提出一种解决方法:资源隔离机制(Resource Isolation Policy),介绍其基本规则及性质,并分析加入此机制后硬实时任务的可调度性.     

NFRL:一种分布系统的实时容错调度算法

在硬实时系统的应用中,如果硬实时任务不能在规定的时限完成,将会产生人员伤亡, 失等严重后果,为了保证在系统出错的情况下,硬实时任务仍然在能戴止时限之前完成,必须研究实时容错技术。本文从实时容错调度算法的角度出发,提出一种基于分布式系统的实时容错调度算法,并研究了该算法的时间复杂度,同时给出一个实例说明该容错调度算法的调度过程。这种容错调算法称为“无容错需求后调度算法（ＮＦＲＬ）,该实时容错调度算法     

基于有限的共享资源模型实现嵌入式硬实时Linux

首先分析了采用双核方案实现硬实时Linux存在的问题,然后基于有限的共享资源模型提出了一种在单Linux内核上实现嵌入式硬实时Linux的新思路,并在Linux 2.6内核上予以完整实现。在目标平台上实测结果表明,从硬实时任务中断产生到硬实时任务得到调度执行的最大延迟小于100μs,可以满足绝大多数嵌入式硬实时系统的要求。     

基于有限的共享资源模型实现嵌入式硬实时Linux

首先分析了采用双核方案实现硬实时Linux存在的问题，然后基于有限的共享资源模型提出了一种在单Linux内核上实现嵌入式硬实时Linux的新思路，并在Linux2．6内核上予以完整实现。在目标平台上实测结果表明，从硬实时任务中断产生到硬实时任务得到调度执行的最大延迟小于100ps，可以满足绝大多数嵌入式硬实时系统的要求。     

硬实时软件建模与分析的进程代数方法

针对硬实时软件缺乏有效的系统动态行为建模机制,提出了一种用于硬实时软件建模与分析的进程代数方法。首先在时间通信顺序进程的基础上扩展硬实时语义得到硬实时通信顺序进程;然后提出时间调度算法,用于检查硬实时系统单个指令截止期的可满足性以及计算完成任务所需的最少时间;最后通过航空领域的一个实例来说明该方法如何应用于硬实时软件的建模与分析。该方法可以很大程度上提高硬实时软件执行时间计算的准确性,计算结果有助于硬实时系统截止期的量化分析和优化设计。     

一种严格按比例派发服务的混合实时调度算法

在混合实时系统中,调度器必须既保证所有硬实时任务严格按照其时间约束在截止期内完成,又要尽可能地提高软实时任务和非实时任务的服务质量.提出了一种严格按比例派发服务器算法(RPDS),并以此为基础构建了一种层次式调度框架.RPDS将处理器时间流分成连续的小段,并在每一小段中强制为非硬实时任务分配一个时间片.实验结果表明,RPDS可以合理地为各种类型应用分配处理器时间,并且降低了实时任务的截止期错失率.     

An Open Environment for Real-Time Applications

This paper describes an open system architecture that allows independently developed hard real-time applications to run together and supports their reconfiguration at run-time. In the open system, each real-time application is executed by a server. At the lower level, the OS scheduler schedules all the servers on the EDF basis. At the upper level, the server scheduler of each server schedules the ready jobs of the application executed by the server according to the algorithm chosen for the application. The paper describes the two-level CPU scheduling scheme used by the open system and the design and implementation of a uniprocessor open system within the framework of the Windows NT operating system. The implementation consists of three key components: the two-level hierarchical kernel scheduler, common system service providers, and real-time application programming interface.     

一种面向混合实时事务调度的并发控制协议

首先给出了一个两层结构的混合实时数据库系统模型，其中支持采用非定期任务调度算法来改进系统的性能．进一步，针对这种模型下混合事务的数据一致性问题，提出了一种新的并发控制协议——MCC-DATI．该协议采用动态优先级驱动的调度算法，通过限制非定期的软实时事务对硬实时事务的阻塞时间，保证硬实时事务的可调度性；同时，采用非定期任务调度算法以及基于时间戳间隔的动态串行化顺序调整机制来减少软实时事务的截止期错失率．仿真实验表明，相对于先前的混合事务的并发控制协议，该协议在不同的系统负载与截止期约束下都能够改进系统的性能。     

一种基于资源预分配的虚拟机软实时调度方法

虚拟机技术作为云计算的重要技术之一,近年来得到广泛关注,但是由于虚拟机管理层的存在,导致语义鸿沟,使得实时应用程序、并发程序等在虚拟机上的运行性能受到影响。分析和研究了Xen虚拟机管理器的Credit调度算法,针对其在并发调度和软实时调度方面存在的不足,提出了改进调度算法,实现了算法的调度器原型。新的调度算法对软实时虚拟机进行Credit比例预分配,采用动态调度时间片机制,以non-work-conserving方式实现软实时任务周期调度,保障调度周期满足运行周期要求。通过区分并发和非并发软实时虚拟机,采取不同的调度策略,在满足资源利用率的基础上,确保实时任务的顺利运行。测试结果表明,该调度算法在对并发和非并发软实时任务调度上,具有良好的表现,较好满足了软实时应用调度需求。     

实时环境问题求解框架*

实时环境下的问题求解是近年来规划问题研究感兴趣的话题.在讨论了实时规划算法同传统离线规划算法之间的不同之后,提出了一个实现实时规划的统一框架,同时具体阐述了框架中的各个模块.通过框架构造出的调度系统可以适应实际环境的需要,在规定时间内解决系统提出的要求,并能较好地解决不确定性.此外,在框架模型指导下构造了智能装配机器人实时调度系统,并给出了实验结果.最后,给出结论,并且简单地讨论了实时规划算法求解问题的策略以及今后的发展方向.     

Real-time task scheduling by multiobjective genetic algorithm

Real-time tasks are characterized by computational activities with timing constraints and classified into two categories: a hard real-time task and a soft real-time task. In hard real-time tasks, tardiness can be catastrophic. The goal of hard real-time tasks scheduling algorithms is to meet all tasks’ deadlines, in other words, to keep the feasibility of scheduling through admission control. However, in the case of soft real-time tasks, slight violation of deadlines is not so critical.In this paper, we propose a new scheduling algorithm for soft real-time tasks using multiobjective genetic algorithm (moGA) on multiprocessors system. It is assumed that tasks have precedence relations among them and are executed on homogeneous multiprocessor environment.The objective of the proposed scheduling algorithm is to minimize the total tardiness and total number of processors used. For these objectives, this paper combines adaptive weight approach (AWA) that utilizes some useful information from the current population to readjust weights for obtaining a search pressure toward a positive ideal point. The effectiveness of the proposed algorithm is shown through simulation studies.     

一种开放混合实时系统的开放自适应调度算法

开放计算环境下的实时与非实时任务不确定并发,以及多种实时约束混合的复杂约束系统,即开放混合实时系统的需求越来越广泛.通过引入接收控制、调度服务器、自适应调节机制,提出一种开放环境下的自适应实时系统调度架构--OARtS(open adaptive real-time scheduling).它能适应开放计算环境的不确定性,有控制地接受实时任务运行;可根据系统空闲计算带宽变化,自适应地调节任务的实时等级,使得系统运行在最优的实时性能上;对于软实时任务,可根据其计算带宽需求变化,自适应地调节其计算带宽分配,以适应任务执行时间时变引起的实时不确定性.     

A Scheduling Extension Scheme of the Earliest Deadline First Policy for Hard Real-Time Uniprocessor Systems Integrated on Posix Threads Based on Linux

The Linux operating system has been employed to execute numerous real-time applications. However, it is limited to support soft real-time systems by two scheduling policies: First-In-First-Out and Round Robin. For real-time systems with critical constraints, the soft real-time support and these scheduling policies are still insufficient. In this work, the Earliest Deadline First scheduling policy, which has been shown in theory to be an optimal one in uniprocessor systems, is introduced as an extension of the Linux kernel. This policy is implemented into the real-time class, without the necessity of defining an additional class. The Linux kernel affords capabilities of a hard real-time operating system by an RT-Preempt patch, enabling the use of Linux to implement hard realtime systems. The integration is compliant with the POSIX real-time and thread standards, ensuring applications portability, employing the GLIBC library. In order to validate the proposed implementation, a set of experiments is conducted, showing that a real-time system that cannot be feasibly scheduled using existing policies, attains feasibility when it is scheduled using the integrated Earliest Deadline First policy.     

A CORBA Based QOS Support for Distributed Multimedia Applications

Advance object oriented computing platform such as the Common Object Request Broker Architecture (CORBA) provides a conducive and standardized framework for the development of distributed applications. Most of the off-the-shelf CORBA are implemented over legacy network transports and distributed processing platforms such as TCP/IP and RPC. They are not suitable for real-time applications due to their high processing overheads, and lack of features and mechanisms in supporting quality of service both at the network level and at the end-host level. To overcome this limitation we have designed and implemented a CORBA-based Real Time Stream Service (RTSS) that allows real-time streams to be managed through the CORBA channel but by-passing the heavy CORBA protocol stacks. RTSS aims to achieve an integrated QOS framework that incorporates both host scheduling and end-to-end network-level QOS to better support the processing of distributed multimedia applications over ATM networks. For host scheduling, a novel scheme of frequency-based scheduling mechanism has been proposed to cope with dynamic CPU load condition. The scheme has been implemented for a stand-alone host and will be extended to the networked environment. At the network-level QOS, RTSS provides object-oriented application programming interfaces (APIs) which guarantee end-to-end QOS when operating directly over ATM adaptation layers. The benefits of RTSS for the development of real-time multimedia distributed applications are demonstrated through a number of experiments.