|Author's Email Address
||This thesis had been viewed 5353 times. Download 278 times.|
||Computer Science and Engineering|
|Type of Document
||The Design of Cloud-Economical Computing Services for|
|Date of Defense
||Program Trading has gotten more popular recent years. According to thestatistics, there was about 53.6% of daily volume in the United States, and increased to 73% in 2009. With the universal of program trading, more people have begun to research program trading.|
The purpose of this paper is constructing a developed platform of program trading for researching or developing. In addition to developed platform, we provide the run-time environment, and three main functions:
1. The job scheduler
2. The high scalability
3. The developed platform
In this paper, we use SLURM to implement an economical computing service for program trading. SLURM is a resource management software for some large clusters.
However it lacked for an easy interface to the ended users. We modify Xinetd as the external interface for SLURM, and implement the program trading development platform for researching or developing.
According to the result, using our scheduler and the external interface that modify from Xinetd can be effective in controlling the server resource and increase the availability.
||Jain-Shing Liu - chair|
Hsiao-Kuang Wu - co-chair
Ying-Chih Lin - co-chair
Shi-Huang Chen - co-chair
Chun-Hung Lin - advisor
Indicate in-campus at 5 year and off-campus access at 5 year.|
|Date of Submission