Abstract—Recently, the computing ability of a personal computer (PC) has rapidly evolved with increases of the CPU clock rate, the number of cores, and the memory size. Then, the collection of idling resources of user-PCs will provide an efficient computing platform with very low costs. To realize this concept, we have studied the user-PC computing (UPC) system based on the master-worker model. By adopting the Docker container, our system allows various jobs or applications to run on PCs with different platforms and environments. In this paper, we present the details of the implementations of the UPC system, including the Docker image generation method for a given job. Here, to reduce the required time and file size, the existing environments of the target PC are checked first, and only the necessary ones are included in the image. For evaluations, we prepare four PCs with different specifications for the UPC system and nine jobs with various features as the applications. Then, we compare the CPU time and the file size to generate the Docker image for each job using two different PCs, when the proposed method is adopted or not. Besides, we measure the CPU time on the master and the worker to compute each job and the transmitted data size to the worker.
Index Terms—User-PC computing, distributed system, resource usage, Docker, job management, Docker image generation.
H. Htet, N. Funabiki, A. Kamoyedji, M. Kuribayashi, and F. Akhter are with the Electrical and Communication Engineering Department, Okayama University, Japan (e-mail: heinhtet@s.okayama-u. ac.jp, funabiki@okayama-u. ac.jp, cyberntique@gmail.com, kminoru@okayama-u. ac.jp, p90n6c8t@s.okayama-u. ac.jp).
W.-C. Kao is with the Department of Electrical Engineering, National Taiwan Normal University, Taipei, Taiwan (e-mail: jungkao@ntnu.edu.tw).
[PDF]
Cite: H. Htet, N. Funabiki, A. Kamoyedji, M. Kuribayashi, F. Akhter, and W.-C. Kao, "An Implementation of User-PC Computing System Using Docker Container," International Journal of Future Computer and Communication vol. 9, no. 4, pp. 66-73, 2020.
Copyright © 2020 by the authors. 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
(CC BY 4.0).
