Investigating Causes of Jitter in Container Networking
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2021-08-23
Department
Major/Subject
Security and Cloud Computing
Mcode
SCI3084
Degree programme
Master’s Programme in Security and Cloud Computing (SECCLO)
Language
en
Pages
7+68
Series
Abstract
Clustered container infrastructures are increasingly popular for deploying applications. The networking in these clusters is provided by specialized container networking solutions that often lead to complex network configurations on the nodes hosting the containers. Thereby, they can have a significant impact on the performance of the applications hosted in the cluster. While the throughput that can be achieved by the container networking solutions is regularly studied, the latency and subsequently jitter introduced by them is often underreported. This thesis investigates the latency and jitter introduced by the packet processing in the Linux kernel using different container networking solutions. This requires very detailed data about the processing of packets, which existing tracing tools for Linux fail to provide. Therefore, a custom tracing application is developed using eBPF that focuses on the flow of packets through the kernel. The application is evaluated and then used to compare the latency and jitter behavior of commonly used container networking solutions. The results show that the choice of transport protocols for real-time applications has a significant impact on the latency introduced by the kernel irrespective of the container networking. Also, some container networking solutions fall short of providing their proclaimed benefits in their default configurations. This highlights the need for performance evaluation in environments representative of the production setting and the need for tuning the configuration of container networking solutions and system resources to match the requirements of real-time use cases. The data also show that there is a need for more lightweight tracing technologies for packet processing.Description
Supervisor
Chiesa, MarcoDi Francesco, Mario
Thesis advisor
Ferlin-Reiter, SimoneBarbette, Tom
Keywords
container networking, tracing, eBPF, Linux