云环境下基于阶段划分的数据密集型工作流调度
Data-intensive workflow scheduling based on phase division in cloud environment
  
DOI:
中文关键词:  云环境;数据密集型;工作流调度;完成时间
英文关键词:cloud environment;data intensive;workflow scheduling;completion time
基金项目:国家自然科学基金(61602260)资助项目
作者单位
陈俊宇 南京邮电大学 计算机学院,江苏南京210023
南京邮电大学 江苏省大数据安全与智能处理重点实验室,江苏南京210023 
刘茜萍 南京邮电大学 计算机学院,江苏南京210023
南京邮电大学 江苏省大数据安全与智能处理重点实验室,江苏南京210023 
摘要点击次数: 962
全文下载次数: 384
中文摘要:
      云计算这种新兴计算模型的出现为数据密集型工作流提供了良好的运行环境,云环境下数据密集型工作流的合理调度是其高效运行的关键,而调度方法的优劣往往以完成时间作为一个重要指标。现有调度研究大多基于各个任务的执行时间和时序逻辑计算完成时间,而对于云环境下数据密集型工作流的调度而言,任务之间的传输时间对完成时间的计算也非常重要。为此,提出了一种云环境下基于阶段划分的数据密集型工作流调度方法,首先基于任务的数据依赖将工作流划分为多个阶段,再根据预估的任务执行时间和任务之间的数据传输时间通过分配算法逐阶段完成任务的调度,最后通过具体实验演示了该方法的可行性和有效性。
英文摘要:
      The cloud computing,as an emerging computing model,provides a good operating environment for data-intensive workflows.The reasonable scheduling of data-intensive workflows in cloud environments is the key to its efficient operation,the performance of scheduling methods often take completion time as an important indicator.Most of the existing scheduling research calculate the completion time based on the execution time and the sequential logic of each task.For the scheduling of data-intensive workflows in the cloud environment,the transmission time between tasks is also important to the completion time.Based on it,a data-intensive workflow scheduling method based on stage division in cloud environments is proposed.Firstly,the workflow is divided into several stages based on data dependence of tasks,and then according to the estimated task execution time and data transmission time between tasks,the task scheduling is completed stage by stage by the allocation algorithm.Finally,the feasibility and the effectiveness of the method are demonstrated by specific experiments.
查看全文  查看/发表评论  下载PDF阅读器

你是第3811653访问者
版权所有《南京邮电大学学报(自然科学版)》编辑部
Tel:86-25-85866913 E-mail:xb@njupt.edu.cn
技术支持:本系统由北京勤云科技发展有限公司设计