计算机工程与应用 ›› 2013, Vol. 49 ›› Issue (6): 131-134.

• 数据库、数据挖掘、机器学习 • 上一篇    下一篇

数据库系统交易型负载自适应管理

赵建光,施  剑,牛保宁   

  1. 太原理工大学 计算机科学与技术学院,太原 030024
  • 出版日期:2013-03-15 发布日期:2013-03-14

Adaptive management of transactional workload for database systems

ZHAO Jianguang, SHI Jian, NIU Baoning   

  1. College of Computer Science and Technology, Taiyuan University of Technology, Taiyuan 030024, China
  • Online:2013-03-15 Published:2013-03-14

摘要: 数据库系统的负载自适应是指数据库系统通过对负载的过滤和控制有效利用系统资源去满足负载性能要求的过程。自治数据库系统负载管理框架(Autonomic Workload Management Framework,AWMF)是一种负载自适应的总体框架,给出了负载自适应的基本组件和主要工作过程。研究AWMF对交易型负载(Transactional Workload)的有效性,提出了基于查询成本(Query Cost)的交易型负载的排队网络模型,以该模型作为性能预测部件实现了AWMF的原型实现——查询调度器,通过实验验证了AWMF对交易型负载的有效性。

关键词: 负载自适应, 自治数据库系统负载管理框架(AWMF), 终端型负载, 批处理型负载, 交易型负载

Abstract: Workload adaptation is a process in which a database management system makes use of its resources effectively to meet the performance objectives of workload by filtering and controlling workload requests. Autonomic Workload Management Framework(AWMF) is a general framework for workload adaptation, which lays out the basic components and the important processes for workload adaptation. This paper studies the effectiveness of AWMF for transactional workload. A cost-based queuing network model for transactional workload is developed and used as the performance prediction component for Query Scheduler, a prototype implementation of AWMF. A set of experiments are conducted to verify the effectiveness of Query Scheduler for transactional workload.

Key words: workload adaptation, Autonomic Workload Management Framework(AWMF), terminal workload, batch workload, transactional workload