Version 1
: Received: 23 January 2024 / Approved: 1 February 2024 / Online: 1 February 2024 (12:55:20 CET)
How to cite:
SONG, C.; YU, H.; Gil, J. MkRP: Multiple k Registry Placement for Fast Container Deployment on Edge Computing. Preprints2024, 2024020064. https://doi.org/10.20944/preprints202402.0064.v1
SONG, C.; YU, H.; Gil, J. MkRP: Multiple k Registry Placement for Fast Container Deployment on Edge Computing. Preprints 2024, 2024020064. https://doi.org/10.20944/preprints202402.0064.v1
SONG, C.; YU, H.; Gil, J. MkRP: Multiple k Registry Placement for Fast Container Deployment on Edge Computing. Preprints2024, 2024020064. https://doi.org/10.20944/preprints202402.0064.v1
APA Style
SONG, C., YU, H., & Gil, J. (2024). MkRP: Multiple k Registry Placement for Fast Container Deployment on Edge Computing. Preprints. https://doi.org/10.20944/preprints202402.0064.v1
Chicago/Turabian Style
SONG, C., HEONCHANG YU and Joon-Min Gil. 2024 "MkRP: Multiple k Registry Placement for Fast Container Deployment on Edge Computing" Preprints. https://doi.org/10.20944/preprints202402.0064.v1
Abstract
Edge computing reduces the response time of real-time services with handling dynamic traffics reliably. Edge servers with limited resources utilize container technology that provides a lightweight execution environment. When deploying containers in edge servers, a container image is required and is downloaded from a remote registry. Therefore, these operations are dependent on network overhead between the container deployment system and the remote registry. Through motivation experiments, we show that container pooling time increases in proportion to physical distance and has characteristics that vary flexibly depending on runtime time. In this study, we define a system model for high-speed registry deployment in this edge system and propose a clustering technique into k groups based on the network overhead and affinity of the regionally distributed edge servers that make up the edge system. Also, considering idle resources, we propose a technique to deploy a registry after electing a leader for each cluster. A simulation experiment is conducted to verify the performance of the proposed technique and shows that performance improvement can be achieved regardless of the number of edge servers and the k value.
Computer Science and Mathematics, Information Systems
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
