利用網際網路免費服務建構個人化資料網格

Using Internet Free Services to Build A Personal Data Grid

張育銘(Yu-Ming Chang)

指導教授 ： 李道明

共同指導教授 ： 林祺政

國立臺北藝術大學/美術學院學術論文/科技藝術研究所碩士班/碩士(2014年)

https://doi.org/10.6835/TNUA.2014.00066

摘要

過去十年內網格運算已經成為國際性研究計畫常用的資源，但因現有的網格架構需要昂貴的硬體設備與高速光纖網路，離一般人的生活仍然非常遙遠。
　　本文試圖用網際網路上可以免費取得的Gmail信箱，建立一個具備傳統資料網格大部份功能，適合個人使用者使用的『個人化資料網格』，這些功能包括：
‥ 供使用者上傳與下載檔案的一致性介面
‥ 過大的檔案會切割成多個片段以存入Gmail信箱，下載時自動組合
‥ 增加Gmail信箱就能增加資料網格的總容量
‥ 存入系統的檔案會製作多份複本並存入不同信箱，提升系統的容錯能力
‥ 完整的複本定位服務，可以部份或全部檔案名稱作為搜尋關鍵字
並運用在科技藝術領域中需要大量儲存空間的場合，以讓更多人享受到網格運算帶給我們的便利。

關鍵字

網際網路 ； 資料網格 ； 免費 ； 個人化 ； 服務

並列摘要

Grid Computing has become a regular resource of international research projects for the past ten years. Since current grid structures still need expensive hardware and fiber network connections, the gap between grid computing and general users is still very large.

In this paper, we try to build a data grid system suitable for general users using free Gmail mailbox. It has most of the functions belong to traditional data grid system like:

‥ A uniform interface that allow users to upload and download files. The size of files is only limited to the total storage capacity of this data grid.
‥ When file size exceeds the limit of single message of Gmail, the system will split the file into many slices and save each slice as a plain file. These slices will be merged into the original file when downloads.
‥ The total capacity of this data grid will grow as the number of mail accounts used as storage grows.
‥ Files uploaded will have multiple replicas. These replicas will be saved to the mail accounts that have the freest space. This mechanism prevents the system to fail when single mail account cannot be accessed.
‥ A complete Replica Location Service that allows users to search files stored in the data grid using part or the full name of files. This service will list all the files and their replicas meet the query requirements.

This system can be used in any circumstances of Technical Art area which needs huge storage space, and let more people to benefit from the grid computing research.

並列關鍵字

Internet ； Grid Computing ； Data Grid ； Free ； Personal ； Services

參考文獻

4. Allcock, W. (2003). GridFTP: Protocol Extensions to FTP for the Grid. Argonne, IL, USA: Argonne National Laboratory.

7. Chervenak, A. Foster, I., Kesselman, C., Salisbury, C., & Tuecke, S. (2000). The Data Grid: Towards an Architecture for the Distributed Management and Analysis of Large Scientific Datasets. Journal of Network and Computer Applications, 23(3) (pp. 187-200). New York: Elsevier.

9. Chervenak, A., Palavalli, N., Bharathi, S., Kesselman, C., Schwartzkopf, R. (2004). Performance and Scalability of a Replica Location Service. Proceedings of the International IEEE Symposium on High Performance Distributed Computing 2004 (HPDC-13).

12. Foster, I., Geisler J., Nickless B., Smith W., & Tuecke S. (1997). Software Infrastructure for the I-WAY High-Performance Distributed Computing Experiment. Proceedings of 5th IEEE Symposium on High Performance Distributed Computing (pp. 562-571). Los Alamitos, CA, USA: IEEE Publication Office.

15. Klensin, J. (2001). Simple Mail Transfer Protocol. The Internet Engineering Task Force RFC 2821. http://www.ietf.org/rfc/rfc2821.txt .