作者：YuqiFan,LunfeiWang,JieChen,ZhifengJin, LeiShi, JuanXu

发表刊物：WASA 2020

年份：September 2020

摘要：The jobs processed in cloud computing systems may consist of multiple associated tasks which need to be executed under ordering constraints. The tasks of each job are run on different nodes, and communication is required to transfer data between nodes. The processing and communication capacities of different components have great heterogeneity. For multiple jobs, simple task scheduling policies cannot fully utilize cloud resources and hence may degrade the performance of job processing. Therefore, careful multi-job task scheduling is critical to achieve efficient job processing. The performance of existing research on associated task scheduling for multiple jobs needs to be improved. In this paper, we tackle the problem of associated task scheduling of multiple jobs with the aim to minimize jobs’ makespan. We propose a task Duplication and Insertion based List Scheduling algorithm (DILS) which incorporates dynamic finish time prediction, task replication, and task insertion. The algorithm dynamically schedules the tasks based on the finish time of scheduled tasks, replicates some of the tasks on different nodes, and inserts the tasks into idle time slots to expedite successive task execution. We finally conduct experiments through simulations. Experimental results demonstrate that the proposed algorithm can effectively reduce the jobs’ makespan.

参考文献拷贝字段：YuqiFan,Lunfei Wang, Jie Chen, Zhifeng Jin, Lei Shi, Juan Xu. Multi-job Associated Task Scheduling Based on Task Duplication and Insertion for Cloud Computing [C].The 15th International Conference on Wireless Algorithms, Systems, and Applications (WASA), Qingdao, China, September 13-15, 2020: 109-120