Adaptive co-scheduling for periodic application and update transactions in real-time database systems

详细信息	查看全文 | 推荐本文 |

• 作者：Song Han^a ; ^{shan@cs.utexas.edu}  ; [Author Vitae] ; Kam-yiu Lam^b ; ^{cskylam@cityu.edu.hk}  ; [Author Vitae] ; Jiantao Wang^b ; ^{jiantwang2@student.cityu.edu.hk}  ; [Author Vitae] ; Sang H. Son^c ; ^{son@virginia.edu}  ; [Author Vitae] ; Aloysius K. Mok^a ; ^{mok@cs.utexas.edu}  ; [Author Vitae]
• 关键词：Real-time database systems ; Data freshness ; Real-time co-scheduling ; Update generation and processing
• 刊名：Journal of Systems and Software
• 出版年：2012
• 期刊代码：80_01641212
• 类别：cp
• 出版时间：August, 2012
• 卷：85
• 期：8
• 页码：1729-1743
• 文件大小：2059 K

摘要

In this paper, we study the co-scheduling problem of periodic application transactions and update transactions in real-time database systems for surveillance of critical events. To perform the surveillance functions effectively, it is important to meet the deadlines of the application transactions and maintain the quality of the real-time data objects for their executions. Unfortunately, these two goals are conflicting and difficult to be achieved at the same time. To address the co-scheduling problem, we propose a real-time co-scheduling algorithm, called Adaptive Earliest Deadline First Co-Scheduling (AEDF-Co). In AEDF-Co, a dynamic scheduling approach is adopted to adaptively schedule the update and application jobs based on their deadlines. The performance goal of AEDF-Co is to determine a schedule for given sets of periodic application and update transactions such that the deadline constraints of all the application transactions are satisfied and at the same time the quality of data (QoD) of the real-time data objects is maximized. Extensive simulation experiments have been performed to evaluate the performance of AEDF-Co. The results show that by adaptively adjusting the release times of update jobs and scheduling the update and application jobs dynamically based on their urgencies, AEDF-Co is effective in achieving the performance goals and maximizing the overall system performance.