An optimization-based approach for efficient network monitoring using in-band network telemetry

Abstract

In recent years, as a result of the proliferation of non-elastic services and the adoption of novel paradigms, monitoring networks with high level of detail is becoming crucial to correctly identify and characterize situations related to faults, performance, and security. In-band Network Telemetry (INT) emerges in this context as a promising approach to meet this demand, enabling production packets to directly report their experience inside a network. This type of telemetry enables unprecedented monitoring accuracy and precision, but leads to performance degradation if applied indiscriminately using all network traffic. One alternative to avoid this situation is to orchestrate telemetry tasks and use only a portion of traffic to monitor the network via INT. The general problem, in this context, consists in assigning subsets of traffic to carry out INT and provide full monitoring coverage while minimizing the overhead. In this paper, we introduce and formalize two variations of the In-band Network Telemetry Orchestration (INTO) problem, prove that both are NP-Complete, and propose polynomial computing time heuristics to solve them. In our evaluation using real WAN topologies, we observe that the heuristics produce solutions close to optimal to any network in under one second, networks can be covered assigning a linear number of flows in relation to the number of interfaces in them, and that it is possible to minimize telemetry load to one interface per flow in most networks.

Passive In-Band Network Telemetry Systems: The Potential of Programmable Data Plane on Network-Wide Telemetry

“…This problem consists in obtaining the most efficient and effective set of network elements to be monitored to provide full monitoring coverage while minimising the overhead. In particular, works such as [60] [61] [62] propose heuristic solutions to this challenging problem, which will undoubtedly and directly affect the design of in-band telemetry systems. This problem will be extremely important in Internet of Things (IoT) networks, which will require millions of traffic flows between IoT devices to be monitored.…”

6G and Beyond: The Future of Wireless Communications Systems

“…As packets traverses the network, they keep accumulating additional metadata, which can be extracted as desired, thus providing highly-detailed accurate sets of network data. To this end, there is a need to quantify the impact of INT on network performance [129]. In particular, metrics such as the relationship between the amount of metadata and packet size, the additional processing burden introduced, and the accuracy of the measurements obtained are all important parameters that merit careful consideration.…”

From 2D to Next Generation VR/AR Videos: Enabling Efficient Streaming via QoE-aware Mobile Networks

“…• Five papers in top-tier SBC, IEEE and ACM conferences/journals (first author) [da Costa Filho et al 2016b, da Costa Filho et al 2016a, da Costa Filho et al 2018a, da Costa Filho et al 2018b, da Costa Filho et al 2020]. • Five papers in conferences/journals (co-author) [Marques et al 2019, Kagami et al 2019, Roesler et al 2018, Lautenschläger et al 2016, Lazzari et al 2017]. • Ph.D. defense awarded with Honors Thesis High Distinction.…”