Applications with real-time constraints are not only growing in the field of embedded system,but gainingpopularity in the desktop environment as well. At the same time, using an opened source system,Linux,as the sup-p...Applications with real-time constraints are not only growing in the field of embedded system,but gainingpopularity in the desktop environment as well. At the same time, using an opened source system,Linux,as the sup-ported OS is more and more appealing to many developers. So it is regarded as a potential aspect by many users to im-prove Linux performance to satisfy the real-time requirements. The article discusses the mutex implementation ofLinux in depth and on the basis of that, gives rise to methods to improve the deficiency. An implementation underversion of 2.2 series is brought forward.展开更多
随着测控设备数量增加、数据码率的不断提高,传统的测控中心实时存储系统采用的串行化处理逻辑已经难以适应高负载的测控任务需要。采用SPMD(Single Program Multiple Data)思想,基于OpenMP和Qt设计并实现了一套并行实时测控数据存储系...随着测控设备数量增加、数据码率的不断提高,传统的测控中心实时存储系统采用的串行化处理逻辑已经难以适应高负载的测控任务需要。采用SPMD(Single Program Multiple Data)思想,基于OpenMP和Qt设计并实现了一套并行实时测控数据存储系统框架。该系统通过引入M/M/1模型的排队系统,设计了一种适合并行实时测控数据存储系统的静态负载均衡算法,基于互斥锁完成了线程间的细粒度通信同步机制,借助于事件循环机制将Qt的信号与槽特性成功地嵌入OpenMP线程,保留了Qt图形界面良好的人机交互性能。实验结果表明该系统在高负载的情况下,相比串行测控数据存储系统而言具有更好的扩展性和实时性,能更好地利用现行单机多核系统的计算资源,获得更好的实时性能。展开更多
文摘Applications with real-time constraints are not only growing in the field of embedded system,but gainingpopularity in the desktop environment as well. At the same time, using an opened source system,Linux,as the sup-ported OS is more and more appealing to many developers. So it is regarded as a potential aspect by many users to im-prove Linux performance to satisfy the real-time requirements. The article discusses the mutex implementation ofLinux in depth and on the basis of that, gives rise to methods to improve the deficiency. An implementation underversion of 2.2 series is brought forward.
文摘随着测控设备数量增加、数据码率的不断提高,传统的测控中心实时存储系统采用的串行化处理逻辑已经难以适应高负载的测控任务需要。采用SPMD(Single Program Multiple Data)思想,基于OpenMP和Qt设计并实现了一套并行实时测控数据存储系统框架。该系统通过引入M/M/1模型的排队系统,设计了一种适合并行实时测控数据存储系统的静态负载均衡算法,基于互斥锁完成了线程间的细粒度通信同步机制,借助于事件循环机制将Qt的信号与槽特性成功地嵌入OpenMP线程,保留了Qt图形界面良好的人机交互性能。实验结果表明该系统在高负载的情况下,相比串行测控数据存储系统而言具有更好的扩展性和实时性,能更好地利用现行单机多核系统的计算资源,获得更好的实时性能。