On page 10 of introduction pdf, it lists many features openEM provides. Most of them are easy to understand. But this statement that "Low and predictable latency (per QoS level)" is not so straightforward. By setting priority on queue, it can give some event opportunity to be processed before others, which means short latency. But how the latency be predictable? As the number of packets in one high priority queue is random, my understanding is the latency should be random.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
On page 10 of introduction pdf, it lists many features openEM provides. Most of them are easy to understand. But this statement that "Low and predictable latency (per QoS level)" is not so straightforward. By setting priority on queue, it can give some event opportunity to be processed before others, which means short latency. But how the latency be predictable? As the number of packets in one high priority queue is random, my understanding is the latency should be random.