Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
For a set of periodic real-time tasks running on a multi-processor system, some tasks need access to shared resources, while the remaining tasks do not. This article aims to solve the problem of priority inversion caused by simultaneous access to shared resources by tasks in a multi-processor real-time system. We propose a task allocation model and partition scheduling algorithm based on the MSRP protocol, which is called SASR-MSRP. Firstly, the algorithm divides the task set into two categories based on whether the task accesses shared resources or not. Secondly, calculate the system utilization rate U of the task that accesses the shared resource and determine the execution priority of the task according to its non-increasing order and assign it to the corresponding processor. Finally, we use the EDF scheduling algorithm to sequentially allocate the remaining independent tasks to the idle time period of the application processor. This algorithm not only reduces the problem of priority inversion, but also improves the overall scheduling efficiency of the system.