EDOM: Improving energy efficiency of database operations on multicore servers
EDOM: Improving energy efficiency of database operations on multicore servers
复制标题
DOI：
10.1016/j.future.2017.02.043
复制
发表时间：
2020-04-01
影响因子：
7.5
通讯作者：
Zhang, Jifu
中科院分区：
文献类型：
--
作者：
Zhou, Yi;Taneja, Shubbhi;Zhang, Jifu
在本文中，我们提出了一个名为 EDOM 的工具包，有助于评估和优化基于节能多核的数据库系统。 EDOM 的两个核心组件是基准测试工具包和多核管理器，用于提高在多核服务器上运行的数据库系统的能源效率。我们通过分析多核处理器上处理的两种流行数据库操作（即交叉连接和外连接）的能源效率来开始这项研究。我们描述了为多核服务器上的数据库构建能效基准的标准和挑战。我们构建了一个基准测试工具包，其中包括配置模块、测试驱动程序和功率监视器。我们开发了一个多核管理器来优化核心数量，从而在多核数据库服务器的性能和能源效率之间取得良好的权衡。多核管理器的核心是内存使用模型，它根据查询和数据库特征估计内存利用率。使用估计的内存使用量来确定适当的核心数量，以避免不必要的内存交换。我们利用建议的基准测试工具包来定量评估我们新型多核管理器的性能。我们的 EDOM 基准测试工具显示多核和 CPU 利用率对能源效率有显着影响。更重要的是，大量的实验结果表明，EDOM 中的多核管理器为提高多核服务器上运行的数据库应用程序的能源效率提供了一个简单而强大的解决方案。 (C) 2017 Elsevier B.V. 保留所有权利。
In this paper, we propose a toolkit called EDOM facilitating the evaluation and optimization of energy-efficient multicore-based database systems. The two core components in EDOM are a benchmarking toolkit and a multicore manager to improve energy efficiency of database systems running on multicore servers. We start this study by analyzing the energy efficiency of two popular database operations (i.e., cross join and outer join) processed on multicore processors. We describe the criteria and challenges of building an energy efficiency benchmark for databases on multicore servers. We build a benchmarking toolkit, which is comprised a configuration module, a test driver, and a power monitor. We develop a multicore manager to optimize the number of cores, thereby making good tradeoff between performance and energy efficiency in multicore database servers. At the heart of the multicore manager is a memory usage model that estimates memory utilization from queries and database characteristics. An appropriate number of cores is determined using the estimated memory usage to avert unnecessary memory swapping. We make use of the proposed benchmark toolkit to quantitatively evaluate the performance of our novel multicore manager. Our benchmarking tool of EDOM shows that the multicore and CPU utilizations have significant impacts on energy efficiency. More importantly, extensive experimental results show that our multicore manager in EDOM provides a simple yet powerful solution for improving energy efficiency of database applications running on multicore servers. (C) 2017 Elsevier B.V. All rights reserved.