About Microservices, Containers and their Underestimated Impact on Network Performance

TL;DR

This paper investigates how microservices, containers, and software defined networking affect network performance, revealing notable impacts of containers and encryption, and providing design recommendations for cloud systems.

Contribution

It provides benchmark analysis quantifying the performance impacts of containers, SDN, and encryption on network throughput and latency in microservice architectures.

Findings

Containers significantly impact network performance despite being lightweight.

Encryption and SDN introduce measurable latency and throughput reductions.

Performance impacts can be mitigated through specific system design strategies.

Abstract

Microservices are used to build complex applications composed of small, independent and highly decoupled processes. Recently, microservices are often mentioned in one breath with container technologies like Docker. That is why operating system virtualization experiences a renaissance in cloud computing. These approaches shall provide horizontally scalable, easily deployable systems and a high-performance alternative to hypervisors. Nevertheless, performance impacts of containers on top of hypervisors are hardly investigated. Furthermore, microservice frameworks often come along with software defined networks. This contribution presents benchmark results to quantify the impacts of container, software defined networking and encryption on network performance. Even containers, although postulated to be lightweight, show a noteworthy impact to network performance. These impacts can be minimized on several system layers. Some design recommendations for cloud deployed systems following the microservice architecture pattern are derived.