INT-MC: Low-Overhead In-Band Network-Wide Telemetry Based on Matrix Completion
Xin Zeng, Kun Xie, Yanbiao Li, Ke Xu, Gaogang Xie, Jigang Wen, Yinchuan Cong, Wei Yan Liang · Proceedings of the ACM on Measurement and Analysis of Computing Systems · 2024
In-band Network Telemetry (INT) enhances real-time, high-resolution network monitoring capabilities by incorporating fine-grained internal state information into packets. Utilizing INT for network-wide visualization can significantly bolster network management and operation. Although existing studies have made significant contributions, they have not been able to simultaneously meet the following two objectives: 1) Comprehensive visibility of the network's internal state, which refers to obtaining information on all switch ports and their corresponding link states; 2) Low measurement overhead, which involves reducing measurement bandwidth overhead and minimizing the impact of the measurement process on the network. We designed INT-MC to meet both of these objectives. INT-MC is an efficient and cost-effective network-wide telemetry solution based on matrix completion. By modeling link metadata as a matrix and leveraging its low-rank property, INT-MC selectively measures certain links. It then employs matrix completion algorithms to infer information about unmeasured links, thereby achieving low-overhead network-wide telemetry. Designing paths to cover the target links involves an NP-complete problem, and the high computational complexity may delay the measurement tasks. To circumvent this, we propose an improved scheme based on Eulerian digraph decomposition, transforming the path calculation problem into a high-information path selection problem, significantly reducing computational costs. We have implemented an INT-MC prototype within the NSFNet topology, consisting of 14 Tofino switches and 10 end-hosts, and conducted extensive experiments and evaluations. The results indicate that INT-MC incurs only 16% of the measurement overhead compared to existing network-wide telemetry solutions, while achieving nearly identical accuracy. Even under high-frequency measurements of 20 times per second, the bandwidth overhead of INT-MC is approximately 0.075% of the total bandwidth, exerting minimal impact on the network.