• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05c
• /
• pp.1757-1760
• /
• 2003

실시간 시스템에서 주기 태스크의 마감시간을 보장하며 도착 시간을 예측할 수 없는 비주기 태스크를 처리되도록 스케줄링 하는 것은 매우 중요하다. 본 논문에서는 정적 우선순위 스케줄링 방식 중 최적인 RM방식으로 주기 태스크를 스케줄링하고, 비주기 태스크의 발생시 비주기 태스크를 EDF 방식으로 스케줄링하여 오프라인에서 구한 슬랙을 비주기 태스크에 할당한다. 제안한 방식은 비주기 태스크의 마감시한내의 슬랙과 비주기 태스크의 실행 시간을 비교하여 비주기 태스크가 마감시한 내에 실행되지 못하는 경우 주기 태스크와 슬랙을 최적적합으로 교환하는 방식을 사용하여 비주기 태스크의 처리를 가능하게 하였다. 제안된 방식은 경성 비주기 태스크와 연성 비주기 태스크에 적용이 가능하며, 실험 결과 교환 알고리즘을 적용한 스케줄링 방식이 적용하지 않은 스케줄링 방식에 비해 비주기 태스크의 처리율이 높게 나왔다.

• Journal of Digital Contents Society
• /
• v.9 no.4
• /
• pp.561-568
• /
• 2008

Research on the flow shop model has mainly been centered around periodic tasks scheduling. In this paper, we present an algorithm using synthetic utilization that can check the schedulability of aperiodic local tasks and aperiodic end-to-end tasks with precedence relation in the flow shop model. If the scheduling algorithm for aperiodic end-to-end tasks executed in the multiple stage pipeline is applied to the flow shop model, sometimes the actually schedulable tasks are decided to be not schedulable because of the fact that the actually unschedulable tasks are decided to be schedulable. The algorithm presented in this paper solves the problem, and the simulation shows that the schedulability increases 10%.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.882-892
• /
• 2007

In this paper, we propose a mechanism for both scheduling the hybrid-task set which consists of periodic and aperiodic tasks and recovering tasks with transient faults on the level of the operating system. Existing embedded operating systems would not provide the scheduling of both periodic and aperiodic tasks. Also because of not supporting the recovery of task failures, they can not prevent system failure from transient task faults. Proposed method, on the level of operating system, is able to not only meet the deadlines of all periodic tasks but also complete the execution of aperiodic tasks. In addition, it is able to prevent the system failure from transient task faults by recovering the task faults.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.1
• /
• pp.9-20
• /
• 2009

In a real-time system with both hard real-time periodic tasks and soft real-time aperiodic tasks, it is important to guarantee the deadlines of each periodic task as well as obtain fast response time for each aperiodic task. This paper proposes Enhanced Total Bandwidth Server (ETBS) with possibly shorter response time than Total Bandwidth Server (TBS), which is efficient and widely used for servicing aperiodic tasks. For uniprocessor system using Earliest Deadline First (EDF) scheduling algorithm, ETBS assigns an on-line deadline to each aperiodic task considering a surplus slack time which gained for every unit execution time of periodic job. The proposed method can fully utilize the processor while meeting all the deadlines of periodic tasks. We show that the proposed ETBS provides better response time of aperiodic tasks than TBS theoretically, but has the same computational complexity as TBS, O(1). Simulation results show that the response time of aperiodic tasks with ETBS are shorter than one with TBS.

• The KIPS Transactions:PartA
• /
• v.8A no.1
• /
• pp.16-26
• /
• 2001

This paper proposes an extended scheduler model that is an extension of the existing model proposed already in [4, 5], which consists of upper layer task scheduler and lower layer scheduling framework. However, in order to support aperiodic task scheduling, the task scheduler has been divided into two parts, such as periodic task control component and aperiodic task control component. Thus, the proposed model can support various bandwidth-preserving servers that can service aperiodic tasks. The model distinctly separates a classic monolithic kernel scheduler into several kernel components according to their functionality. This enables system developers to implement a new scheduling algorithm or aperiodic task server independent of complex low kernel mechanism, and reconfigure the system at need. In Real-Time Linux [6], we implemented the proposed scheduling framework representative scheduling algorithms, and server bandwidth-preserving servers on purpose to test. Throughout these implementations, we confirmed that a new algorithm or server could be developed independently without updates of complex low kernel modules. In order to verify efficiency of the proposed model, we measured the performance of several aperiodic task servers. The results showed this the performance of model, which even consisted of two hierarchical components and several modules, didnt have such high run-time overhead, and could efficiently support reconfiguration and scheduler development.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.5
• /
• pp.866-874
• /
• 2006

This paper proposes a new Dynamic Voltage Scaling(DVS) algorithm to achieve low-power scheduling of aperiodic hard real-time tasks. Aperiodic tasks schedulingcannot be applied to the conventional DVS algorithm and result in consuming energy more than periodic tasks because they have no period, non predictable worst case execution time, and release time. In this paper, we defined Virtual Periodic Task Set(VTS) which has constant period and worst case execution time, and released aperiodic tasks are assigned to this VTS. The period and worst case execution time of the virtual task can be obtained by calculating task utilization rate of both periodic and aperiodic tasks. The proposed DVS algorithm scales the frequency of both periodic and aperiodic tasks in VTS. Simulation results show that the energy consumption of the proposed algorithm is reduced by 11% over the conventional DVS algorithm for only periodic task.

• Korea Information Processing Society Review
• /
• v.5 no.4
• /
• pp.12-21
• /
• 1998

실시간 시스템은 범용 시스템과는 달리 계산 결과의 정확성뿐만 아니라 계산이 종료되는 시점에 의해 그 가치가 결정되는 시스템을 말한다. 따라서 실시간 태스크는 시간적 제한 조건으로서 마감 시한(deadline)을 가지고 있으며 실시간 스케줄링 방법은 범용 시스템에서 사용되는 스케줄링 방법과는 달리 태스크가 마감 시한 내에 종료될수 있음을 보장해 주어야 한다 또한 실시간 스케줄링 방법은 새로운 태스크의 실행을 허가하기 전에 새로운 태스크 집합의 스케줄 가능성을 분석함으로써 시스템 전체의 안전을 유지할 수 있어야 한다. 실시간 스케줄링 방법은 크게 시간 구동형 방식과 우선 순위 기반의 이벤트 구동형 방식으로 우선 순위 기반의 이벤트 구동형 방식으로 나누어지는데 본 논문에서는 주로 우선 순위 기반의 이벤트 구동형 방식으로 나누어지는데 본 논문에서는 주로 우선순위 기반의 스케줄링 방법에 대해서 살펴본다 또한 비주기적인 태스크를 우선 순위기반 스케줄링 방법에 적용하기 위한 여러 가지 기법들에 대해서도 살펴본다.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.7
• /
• pp.2229-2237
• /
• 2000

This paper intends to improve the problems of the slack stealing algorithm scheduling for periodic tasks with fixed priority and aperiodic tasks which occur dynamically. The Slack stealing algorithm reduces unnecessary waiting time by making the service possible immediately when the slack stealing server gives suitable priority to aperiodic tasks according to the status of aperiodic tasks arrivals at runtime. But no performs the slack stealing, we must calculate execution time of periodic tasks till the point of random. And, execution time of periodic tasks is being repeatedly every hours while the slack algorithm is applied. We show time complexity hen is used as to O(n) if the nubmer of tasks which is applied to the calculation is n. In this appear, due to stored in tables slack times and the execution times of the scheduled periodic tasks, the complexity of aperiodic tasks which is occurring dynamically reduced to O(log n) and improves the responses times. We prove the algorithm proposed in this paper through the simulation.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.76-84
• /
• 2011

Embedded Systems need to ensure real-time of the task response time depending on the applied fields of it. And task could be faulty due to various reasons in real time systems. Therefore in this paper, we design a task scheduler that guarantees deadlines of periodic tasks and considers a fault tolerance of defective task in embedded system with a single processor. In order to provide real-time, we classify tasks with periodic/aperiodic tasks and applies RMS(Rate Monotonic Scheduling) method to schedule periodic tasks and can guarantees execution of aperiodic tasks by managing surplus times obtained after analyzing the execution time of periodic tasks. In order to provide fault tolerance, we manage backup times and reexecute a fault task to restore it's conditions.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.97-99
• /
• 2004

본 논문에서는 주기와 비주기 실시간 태스크가 혼합된 태스크 집합에 대하여 이용율 요구 분석(utilization demand analysis)에 기반한 수락제어 기법을 제안한다. 이용율 요구는 혼합 태스크 집합의 모든 태스크가 종료시한 내에 수행을 마치기 위한 프로세서의 이용율로 정의된다. 본 논문에서는 비주기 태스크 집합과 주기 태스크 집합 각각의 이용율 요구를 정의하고 혼합 태스크 집합에 대한 이용율 요구 분석 기법을 제공한다. 제안된 기법은 비주기 태스크에 대한 이용율 요구를 재귀적으로 계산하여 태스크의 수락여부를 결정한다. 이러한 기법은 O(n)에 스케줄링 분석을 수행하고 복잡한 자료구조가 필요하지 않아서 실시간 수락제어를 가능하게 한다.