A Fusion Mechanism for Analyzing Real-Time Performance of Embedded Systems
一种嵌入式系统实时性能分析的融合机制

Many embedded systems require hard or soft real-time execution. To ensure the requirements are met, it is necessary to measure the execution time of individual tasks, as well as establish the overall real-time performance of the system. The traditional software-only methods for measuring the execution times of real-time codes are easy to use and low cost, but provide lower resolution and greater overhead than hardware ones, which impedes using it for analyzing real-time performance, such as identifying whether a specific task set is schedulable. In order to overcome the main two obstacles which cause lower accuracy of software-only methods, based on the information fusion idea of multi-source data and using the improved software-only method for measuring the execution times of real-time codes, which also takes the information fusion idea of multi-source data to improve the accuracy of the measurements, while it reserves the good features owned by traditional ones, this paper presents a fusion mechanism for analyzing the realtime performance of embedded systems. Using the mechanism, the designers and developers can pinpoint the timing problems, find the code to be optimized so as to avoid the missed deadlines, and identify the schedulability of a realtime task set under a specific scheduling environment.