面向资源优化的周期分配方法和总线访问配置研究

汽车系统的功能多样性和智能化发展,引起车内ECU数量的大量增加,给汽车成本的降低带来巨大压力。ECU节点通过TTP总线构成了以周期性任务触发、基于TDMA技术的消息分发、基于抢占的FPS调度等为特点的分布式体系结构。实时性和资源利用率是上述体系结构需要考虑的两个关键问题,特别是随着汽车系统复杂性的快速增长,对解决上述问题提出了严峻的挑战。本文提出一种利用GP进行周期分配和总线访问配置,并结合FPS进行实时调度分析,在保证系统时限的前提下,最小化系统资源利用率的方法,以减缓ECU数量的增加,降低系统成本。在具备工业实用价值的任务集基础之上进行的仿真实验结果表明了该方法的有效性和可扩展性。     

基于改进型统一调度算法改善任务集的可调度性

实时系统要求任务在最差情况下能在其截止时间前获得结果,若超过了其截止时间,也会认为是错误的行为,所以改进任务可调度性分析、提高任务集可调度性尤其重要。统一调度能结合固定优先级调度的优点,防止不必要的抢占,降低资源额外销耗,能够提高任务集合的可调度性;但其任务的可调度性分析方法过于粗糙,影响任务最差响应时间分析的结果,降低了任务集的可调度性。针对存在的问题,基于统一调度,增加任务运行阶段数,重新建立任务模型,并提出通过分配任务抢占阈值、调整运行阶段的抢占阈值与长度,优化任务可容忍阻塞,改善任务集可调度性的算法。最后,实验表明,与统一调度算法及其他算法相比,所提出的调度算法能够有效改善任务集的可调度性。     

Cache-Conscious Limited Preemptive Scheduling

In multi-tasking real-time systems, inter-task cache interference due to preemptions degrades schedulability as well as performance. To address this problem, we propose a novel scheduling scheme, called limited preemptive scheduling (LPS), that limits preemptions to execution points with small cache-related preemption costs. Limiting preemptions decreases the cache-related preemption costs of tasks but increases blocking delay of higher priority tasks. The proposed scheme makes an optimal trade-off between these two factors to maximize the schedulability of a given task set while minimizing cache-related preemption delay of tasks. Experimental results show that the LPS scheme improves the maximum schedulable utilization by up to 40\% compared with the traditional fully preemptive scheduling (FPS) scheme. The results also show that up to 20\% of processor time is saved by the LPS scheme due to reduction in the cache-related preemption costs. Finally, the results show that both the improvement of schedulability and the saving of processor time by the LPS scheme increase as the speed gap between the processor and main memory widens.     

CAN总线固定优先级调度及性能分析软件的设计

在给出通信网络的消息模型后,分析了CAN总线固定优先级调度中消息传输的时间特性参数的计算及系统可调度的必要条件,论述了固定优先级调度性能分析软件的设计,给出了应用实例及总线负载率的测试结果,验证了离线分析的有效性.     

Improved Task and Resource Partitioning Under the Resource-Oriented Partitioned Scheduling

Coordinated partitioning and resource sharing have attracted considerable research interest in the field of real-time multiprocessor systems. However, finding an optimal partition is widely known as NP-hard, even for independent tasks. A recently proposed resource-oriented partitioned (ROP) fixed-priority scheduling that partitions tasks and shared resources respectively has been shown to achieve a non-trivial speedup factor guarantee, which promotes the research of coordinated scheduling to a new level. Despite the theoretical elegance, the schedulability performance of ROP scheduling is restricted by the heuristic partitioning methods used in the original study. In this paper, we address the partitioning problem for tasks and shared resources under the ROP scheduling. A unified schedulability analysis framework for the ROP scheduling is proposed in the first place. A sophisticated partitioning approach based on integer linear programming (ILP) is then proposed based on the unified analysis. Empirical results show that the proposed methods improve the schedulability of ROP scheduling significantly, and the runtime complexity for searching a solution is reduced prominently compared with other ILP-based approaches as well.