Aluno: Jonatas Adilson Marques
Orientador: Prof. Dr. Luciano Paschoal Gaspary
Título: Advancing Network Monitoring with Data Plane Programmability and In-band Network Telemetry
Linha de Pesquisa: Arquitetura protocolo e Gerência de redes e serviços
Local: Prédio 43412 – Sala 218 do Instituto de Informática
– Prof. Dr. Juan Felipe Botero Vega (Universidad de Antioquia – por videoconferência)
– Prof. Dr. Rafael Rodrigues Obelheiro (UDESC – por videoconferência)
– Prof. Dr. Alberto Egon Shaeffer Filho (UFRGS)
Presidente da Banca: Prof. Dr. Luciano Paschoal Gaspary
Abstract: In recent years, as a result of the proliferation of non-elastic services, 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) — backed by the recent advances in Software-Defined Networking and Data Plane Programmability — 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 to all packet flows in a network. 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 thesis proposal, 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. We also observe that networks can be covered assigning a linear number of flows in relation to the number of device interfaces and, finally, that it is possible to minimize telemetry load to one interface per flow for most networks. As the next steps to conclude our research work, we intend to further investigate ways to leverage the flexibility introduced by data plane programmability to offload network problem detection, diagnosis and possibly reaction to forwarding devices inside the network.
Keywords: Network Monitoring, Software-Defined Networking, Data Plane Programmability, P4, In-band Network Telemetry.