标题：SLO-Driven Task Scheduling in MapReduce Environments
作者：Wang, Jie; Li, Qingzhong; Shi, Yuliang
作者机构：[Wang, Jie; Li, Qingzhong; Shi, Yuliang] Shandong Univ, Sch Comp Sci & Technol, Jinan 250100, Peoples R China.
会议名称：10th Web Information System and Application Conference (WISA)
会议日期：NOV 01-03, 2013
来源：2013 10TH WEB INFORMATION SYSTEM AND APPLICATION CONFERENCE (WISA 2013)
关键词：MapReduce; Hadoop; SLO; task scheduling; performance management
摘要：MapReduce is emerging as an important programming model for massive data processing. A key challenge in Map Reduce environments is the ability to efficiently control resource allocation and task scheduling for achieving Service Level Objectives (SLOs) of Map Reduce jobs. However, there are few effective task scheduling methods to guarantee Map Reduce jobs' SLOs. Therefore, we address this challenge by proposing a SLO-driven task scheduling mechanism in this paper. Based on the Map Reduce performance model we build, our mechanism dynamically adjusts resource allocation and task scheduling in order to guarantee the SLOs of jobs and improve global job utility. Experimental results show that our SLO-driven task scheduler effectively meets the specified job latency SLOs and enhances job utility on tested Map Reduce programs.