Applied Research Of Strong Real-time QNX Operating System Scheduling Mechanism Under The Multi-core Architecture

With the emergence of multi-core processors, task scheduling for multi-core processors has become one of the focuses in high efficient multi-core processors study. For the past few years, many experts and scientific research institute both home and abroad do a lot of research in task scheduling. In order to shorten the scheduling length, they minimize the communication costs that between two tasks and change the order of execution. However, the efficiency of task scheduling presently is very low. The problems such as high communication costs, low priority for crucial task and too much redundant tasks reduce the scheduling efficiency for multi-core processors greatly. In order to improve system performance significantly, multi-core processors provide a good hardware platform, and in order to give full use to the high-performance advantage of multi-core processors, the hardware should combine software. The structure of multi-core processor system is very complex, under the multi-core environment, the strong real-time operating system QNX task scheduling mechanism and resource management is more complex than on single-core architecture. The design of the multi-processor architecture is one of the hot topics, task scheduling is the most important part. Effective task scheduling method will greatly improve the computing power of multi-processor systems and it can reduce unnecessary energy consumption.Based on the study and analysis of existing task scheduling algorithms for multi-core processors, comprehensively analysis QNX RTOS kernel characteristics and analysis the QNX scheduling mechanism, followed by the study of the strong real-time characteristic base on real-time QNX operating system. In order to reflect the strong QNX’s real-time characteristics, through the performance test and compares it with Linux2.6.32. Knowing the intelligent vehicle as the studying object, this paper designs a simple intelligent vehicle scheduling model, in order to meet the requirements of intelligent vehicle system, and considering tasks synchronization, a variety of scheduling algorithms based on tasks priority table under the analysis of traditional algorithms is used. The article analyses how to undertake vehicular task in multi-core environment, and puts forward a solution to resolve the priority inversion in real-time QNX RTOS, and proposed a new priority table based on real-time scheduling algorithm and an improved CDF algorithm. The scheduling algorithm is tested and analyzed, and the effectiveness and feasibility of the algorithm is demonstrated with QNX development kits which developed the intelligent vehicle scheduling system based on Strong real-time QNX operating system under the quad-core Architecture, tests have shown that the system basically realizes the quad-core load balancing. This article analyses and realizes the multi-core optimization technology. Through the research, this paper pave the way for studying the intelligent vehicle critical task scheduling.