Performance Analysis of gNMI Streaming Telemetry-Based Monitoring Systems Using Containerlab Network Simulation

Abstract

The rapid growth of the Internet has impacted the digital service development. This surge in demand has created opportunities for digital service industry players. Despite its positive impact, the growth of the Internet also poses technical challenges. In managing the increasing data traffic, resource monitoring plays a vital role. One of the latest methods for monitoring these resources is the utilization of the Google’s Remote Procedure Call (gRPC) Network Management Interface (gNMI) streaming telemetry system. While it seems superior to current protocols, there is a need for further exploration into the implementation of streaming telemetry systems. This paper specifically investigates the trade-offs and performance of gNMI streaming telemetry. The design and simulation were conducted utilizing containerlab, a Docker-based networking lab tool. In the Docker-based simulation, integration between the monitoring system and network topology was implemented. The results from observing each protocol indicate that the monitoring system’s metric retrieval activity had minimal impact on network conditions. This is evident in the consistently low average network latency and nearly uniform throughput, except in instances of packet loss and congestion. Simulation observations indicate that the gNMI monitoring system utilized input/output (I/O) resources more intensively compared to other protocols. The research also examined the integration of gNMI streaming telemetry and log monitoring, revealing a 70 MB rise in memory usage and a 33% increase in Disk I/O resources. Furthermore, the study uncovered signs of a 50% increase in CPU utilization by the gNMI monitoring system compared to the average data recorded in the observations.