Analyzing the Latency of Sparse Flows in the FQ-CoDel Queue Management Algorithm

The FQ-CoDel queue management algorithm was recently published as an IETF RFC. It achieves low latency especially for low-volume (or sparse) traffic flows competing with bulk flows. However, the exact conditions for when a particular flow are considered to be sparse has not been well-explored. In this work, we analyze the performance characteristics of the sparse flow optimization of FQ-CoDel, formulating the constraints that flows must satisfy to be considered sparse in a given scenario. We also formulate expressions for the expected queuing latency for sparse flows. Then, using a numerical example, we show that for a given link and a given type of sparse flows (VoIP traffic), the number of sparse flows that a given bottleneck can service with low sparse flow latency is only dependent on the number of backlogged bulk flows at the bottleneck. Furthermore, as long as the maximum number of sparse flows is not exceeded, all sparse flows can expect a very low queuingqueuing latency through the bottleneck.