FlowMap: A Fine-Grained Flow Measurement Approach for Data-Center Networks
Xiong Wang, Hanyu Liu, Jun Zhang, Jing Ren, Sheng Wang, Shizhong Xu · 2019
Due to the hard constraint of measurement resources in switches, accurately and timely measuring a huge number of fine-grained flows is very challenging. To handle this challenge, we design FlowMap, which is a Bloom filter and hash-based approach to keep track of fine-grained flows with small bandwidth as well as computation and memory overheads. In each switch, FlowMap stores flow IDentifiers (IDs) in the FlowID table and encodes flow counters in the counting table with small memory space and constant operation time. To get the per-flow counters, FlowMap leverages the computing power of the remote controller to decode the encoded flow statistics collected from switches periodically. In addition, to achieve scalable flow counter decoding, FlowMap divides the cells of the counting table into several groups, and then uses a two-level flow mapping scheme to map flows to different groups, each of which can be decoded independently and concurrently at the remote controller. The simulation results show that FlowMap can provide per-flow counters with high accuracy for all the flows in short time scales with low overheads, and comparing with the existing approach, FlowMap is more scalable and robust.