Open AccessHierarchical Scheduling for Real-Time Periodic Tasks in Symmetric Multiprocessing
Author(s) -
Tom Springer,
Peiyi Zhao
Publication year - 2021
Publication title -
computer science and information technology ( cs and it )
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5121/csit.2021.110810
Subject(s) - computer science , multiprocessing , scheduling (production processes) , parallel computing , multiprocessor scheduling , distributed computing , benchmark (surveying) , dynamic priority scheduling , fixed priority pre emptive scheduling , response time , earliest deadline first scheduling , two level scheduling , rate monotonic scheduling , operating system , mathematical optimization , mathematics , schedule , geodesy , geography
In this paper, we present a new hierarchical scheduling framework for periodic tasks in symmetric multiprocessor (SMP) platforms. Partitioned and global scheduling are the two main approaches used by SMP based systems where global scheduling is recommended for overall performance and partitioned scheduling is recommended for hard real-time performance. Our approach combines both the global and partitioned approaches of traditional SMP-based schedulers to provide hard real-time performance guarantees for critical tasks and improved response times for soft real-time tasks. Implemented as part of VxWorks, the results are confirmed using a real-time benchmark application, where response times were improved for soft real-time tasks while still providing hard real-time performance.