Resilience enhancement of container-based cloud load balancing service
- Published
- Accepted
- Subject Areas
- Computer Networks and Communications, Distributed and Parallel Computing, Network Science and Online Social Networks, World Wide Web and Web Science, Software Engineering
- Keywords
- Cloud Computing, Docker, Load Balancer, Distributed Systems, AWS, Resilience, Nginx
- Copyright
- © 2018 Zhang
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2018. Resilience enhancement of container-based cloud load balancing service. PeerJ Preprints 6:e26875v1 https://doi.org/10.7287/peerj.preprints.26875v1
Abstract
Web traffic is highly jittery and unpredictable. Load balancer plays a significant role in mitigating the uncertainty in web environments. With the growing adoption of cloud computing infrastructure, software load balancer becomes more common in recent years. Current load balancer services distribute the network requests based on the number of network connections to the backend servers. However, the load balancing algorithm fails to work when other resources such as CPU or memory in a backend server saturates. We experimented and discussed the resilience evaluation and enhancement of container-based software load balancer services in cloud computing environments. We proposed a pluggable framework that can dynamically adjust the weight assigned to each backend server based on real-time monitoring metrics.
Author Comment
This is a preprint submission to PeerJ Preprints.
Supplemental Information
RTT from each backend server with our policy
Each data point indicates the average performance of 50 runs.
RTT from each backend server without applying our policy
Each data point indicates the average performance of 50 runs.