• The Transactions of the Korea Information Processing Society
• /
• v.6 no.11
• /
• pp.3131-3139
• /
• 1999

Satisfying the rigid timing requirements of various real-time activities in real-time systems often requires some special methods to tune the systems run-time behaviors. Unbounded blocking can be caused when a high priority activity cannot preempt a low priority activity. In such situation, it is said that a priority inversion has occurred. The priority inversion is one of the problems which may prevent threads from meeting the deadlines in the real-time systems. It is difficult to remove such priority inversion problems in the kernel at the same time to bound the worst case blocking time for the threads. A thread is a piece of executable code which has access to data and stack. In this paper, a new real-time systems. It is difficult to remove such priority inversion problems in the kernel at the same time to bound the worst case blocking time for the threads. A threads is a piece of executable code which has access to data and stack. In this paper, a new real-time server model, which minimizes the duration of priority inversion, is proposed to reduce the priority inversion problem. The proposed server model provides a framework for building a better server structure, which can not only minimize the duration of the priority inversion, but also reduce the deadline miss ratio of higher priority threads.

• The KIPS Transactions:PartA
• /
• v.13A no.5 s.102
• /
• pp.405-412
• /
• 2006

Real-time operating systems have been used in various computing environments, where a job must be completed in its deadline, with various conditions, such as effective scheduling policies, the minimum of an interrupt delay, and the solutions of priority inversion problems, that should be perfectly satisfied to design and develop optimal real-time operating systems. Up to now, in order to solve priority inversion problems among several those conditions. There have been two representative protocols: basic priority inheritance protocol and priority ceiling emulation protocol. However, these protocols cannot solve complicated priority inversion problems. In this paper, we design a protocol, called recursive priority inheritance (RPI), protocol that effectively solves the complicated priority inversion problems. Our proposed protocol is also implemented in the Linux kernel and is compared with other existing protocols in the aspect of qualitative analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.199-201
• /
• 2003

실시간 운영체제(Real-Time OS)는 우선순위 기반의 선점형 스케줄링을 제공하는 운영체제로서 시간 결정성 (Determinism)을 보장하는 특징이 있다. 그러나, 우선순위가 높은 태스크가 우선순위가 낮은 태스크에 의해 CPU를 점유 당하는 우선순위 역전(Priority Inversion)이 발생하여 시간 결정성이 보장되지 못하면 시스템의 심각한 결함을 야기할 수 있다. 본 논문에서는 우선순위 역전을 해결하기 위하여 Priority Inheritance Protocol 을 적용한 세마포 (Semaphore)의 구현에 대해 기술한다.

• The KIPS Transactions:PartA
• /
• v.16A no.6
• /
• pp.463-472
• /
• 2009

Real-time operating systems must have satisfying various conditions such as effective scheduling policies, minimized interrupt delay, resolved priority inversion problems, and its applications to be completed within desired deadline. The real-time operating systems, therefore, should be designed and developed to be optimal for these requirements. MicroC/OS-II, a kind of Real-time operating systems, uses the basic priority inheritance with a mutex to solve priority inversion problems. For the implementation of mutex, the kernel in an operating system should provide supports for numerous tasks with same priority. However, MicroC/OS-II does not provide this support for the numerous tasks of same priority. To solve this problem, MicroC/OS-II cannot but using priority reservation, which leads to the waste of unnecessary resources. In this study, we have dealt with new design a protocol, so called TPSP(Temporary Priority Swap Protocol), by an effective solution for above-mentioned problem, eventually enabling embedded systems with constrained resources environments to run applications.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.913-915
• /
• 2005

실시간 시스템에서는 두 개 이상의 태스크가 공유자원을 사용한다. 이러한 자원에 의해서 높은 우선순위 태스크가 낮은 우선순위 태스크에 의해서 CPU를 점유 당하는 우선순위 역전현상(Priority Inversion)이 발생한다. 우선순위 역전 문제는 실시간 시스템의 스케줄 가능성과 예측성에 심각한 결함을 야기할 수 있다. 이를 해결하기 위해 본 논문에서는 비교적 크기가 작으면서도 실시간 운영체제의 핵심적 특징을 잘 갖추고 있는 $iRTOS^{TM}$ 커널을 사용하였고 우선순위 역전을 해결하기 위해서 Priority Inheritance Protocol을 사용하여 확장된 MuTexS를 구현하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.28 no.11
• /
• pp.573-580
• /
• 2001

When tasks access shared resources in real-time systems, the unbounded priority inversion may occur. In such cases it is impossible to guarantee the schedulability of real-time tasks. Several resource access protocols have been proposed to bound the duration of priority inversion and sufficient conditions are given to guarantee the schedulability of periodic task set. In this paper, we show an improved sufficient condition for schedulability when the dynamic priority ceiling protocol is used. Our approach exploits the fact that a lower priority task can continue to execute as far as the higher priority tasks do not miss their deadlines. This permitting execution time of the higher priority tasks for a lower priority task can be excluded from the worst-case blocking time of the higher priority tasks. Since the worst-case blocking time of tasks can be reduced, the sufficient condition for schedulability of dynamic priority ceiling protocol becomes further tight.

• Journal of Computing Science and Engineering
• /
• v.9 no.2
• /
• pp.108-117
• /
• 2015

Interrupt handling is generally separated from process scheduling. This can lead to a scheduling anomaly and priority inversion. The processor can interrupt a higher priority process that is currently executing, in order to handle a network packet reception interruption on behalf of its intended lower priority receiver process. We propose a new network interrupt handling scheme that combines interrupt handling with process scheduling and the priority of the process. The proposed scheme employs techniques to identify the intended receiver process of an incoming packet at an earlier phase. We implement a prototype system of the proposed scheme on Linux 2.6, and our experiment results show that the prototype system supports the predictable real-time behavior of higher priority processes even when excessive traffic is sent to lower priority processes.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.19-22
• /
• 2018

현재 자동차 산업계에서 AUTOSAR는 효율적인 차량용 소프트웨어 개발을 위해 필수로 적용되고 있으며 자동차의 실시간 요구사항을 만족시키기 위해 실시간 운영체제를 사용한다. 하지만 AUTOSAR에서 제공하는 코어 간 클라이언트-서버 통신은 클라이언트 태스크에서 보낸 서비스 요청을 FIFO 순서로 처리하기 때문에 우선순위가 높은 태스크의 서비스가 낮은 태스크의 서비스 때문에 늦게 처리될 수 있다. 이는 우선순위 역전 현상이며 서비스의 처리 결과를 기다리느라 우선순위가 높은 태스크의 응답시간이 지연되므로, 이 태스크가 차량 안전에 있어 중요하다면 치명적일 수 있다. 이 논문에서는 서비스의 처리 순서가 결과에 무관한 경우에 한해 우선순위 큐를 도입함으로써 이 문제를 해결하였다. 제안된 기법은 Infineon 사의 TC297 MCU와 ETAS 사의 AUTOSAR 소프트웨어에서 실험했으며 우선순위가 높은 태스크의 응답시간이 1.42%의 오버헤드를 통해 1.26배 감소하였다.

• The KIPS Transactions:PartA
• /
• v.16A no.3
• /
• pp.189-198
• /
• 2009

The traditional interrupt-based protocol processing at end hosts has two priority-inversion problems. First, low-priority packets may interrupt and delay high-priority process executionssince interrupts have the highest priority in most operating systems. Second, low-priority packet may delay high priority packets when they arrive almost simultaneously since interrupt processing is performed in a FCFS (first come, first served) order. These problems can be solved by a priority-based protocol processing policy and implementation. However, general priority-based schemes commonly have the problem of starvation and cannot support the each network flow requiring the mutually exclusive QoS since the packets are processed in the FCFS order. Therefore, the priority-based schemes are not appropriate for different QoS-demanding applications. In this paper, we present a bottom-half-based approach that relies on priority- and budget-based processing. The proposed approach allows us to solve both the starvation and priority-inversion problems, and further enables effective QoS isolation between different network connections. This feature also enables bounding the protocol processing time at an end host. We finally show through experiments that the proposed approach achieves QoS isolation and control.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.6
• /
• pp.36-46
• /
• 2002

This paper proposes an integrated scheduling mechanism for embedded system with real-time web server to meet the characteristics of real time task. The proposed scheduling mechanism may solve the so-called priority inversion problem in scheduling between urgent web requests and tasks with low priorities. The priority inversion problem happens because of operating two independent schedulers, web scheduler and operating system scheduler in a system without considering the requirements of each other. In the proposed mechanism, two schedulers are integrated in an operating system and the integrated scheduler schedules tasks for urgent web requests with real time characteristics and other application tasks together. Since all tasks are scheduled by one unified scheduler that knows the characteristics of tasks, the tasks are scheduled with their absolute priorities and thus the priority inversion problem can be eliminated. The performance is measured on a prototype embedded system with the proposed algorithm.