时间敏感网络中基于网络演算的队列分析与优化

Analysis and Optimization of Queues Based on Network Calculusin Time-Sensitive Networking

时间敏感网络(TSN)中循环队列转发(CQF)机制保留了时间感知整形中门控调度的转发可控特性,同时又降低了门控列表配置的复杂度,但是缓存队列的长度作为一个关键参数直接影响着网络的调度性能,并且在实现时受到硬件资源的约束。为了寻找到合适的CQF队列长度值以实现网络系统设计的性能和成本的优化,提出了一个基于网络演算的CQF性能分析方法。通过曲线模型的构建和计算,分析流量传输时延和积压的性能上界值,从而选择出合适的队列长度值。通过不同场景的实验,得到了不同流特性参数对队列长度选择的影响。

Cyclic queue forwarding(CQF)in time-sensitive networking(TSN)remains the forwarding controllability based on gated scheduling in time-aware shaper and reduces the complexity of the configuration of gate control lists.However,as a key parameter,the length of CQF queues directly affects the performance of network scheduling and is constrained by hardware resources in implementation.In order to find the appropriate value of CQF queue length to realize the performance and cost optimization of network system design,a performance analysis method of CQF-based networks based on network calculus is proposed.Through the construction of curve model and calculation,the upper bounds of delay and backlog of data traffic transmission are analyzed.Then the appropriate length of CQF queues can be selected according to these analysis results.Experiments are conducted in different scenarios,and the influence of different flow characteristic parameters on the selection of queue length is obtained.