一种面向分布式数据库的多并发OLAP型查询性能预测方法  

A Concurrent OLAP Query Performance Prediction Approach for Distributed Database

作　　者：刘骥超 杜建华 谢寒生[1,2] 刘霄燕 谢召干 LIU Jichao;DU Jianhua;XIE Hansheng;LIU Xiaoyan;XIE Zhaogan(Meteorological Information Center of Hainan Province,Haikou 570203,China;Key Laboratory of South China Sea Meteorological Disaster Prevention and Mitigation of Hainan Province,Haikou 570203,China;Meteorological Bureau of Chengmai County,Chengmai 571900,China)

机构地区：[1]海南省气象信息中心,海口570203 [2]海南省南海气象防灾减灾重点实验室,海口570203 [3]海南省澄迈县气象局,海南澄迈571900

出　　处：《计算机测量与控制》2022年第10期209-215,221,共8页Computer Measurement &Control

基　　金：海南省自然科学基金青年基金(420QN373);海南省气象局科研项目(hnqxSJ202104)。

摘　　要：数据库查询性能预测即预测查询的执行延迟时间,数据库查询延迟预测技术能够用于查询调度和查询进度显示等;当前的查询性能预测技术都具有一定的局限性,不能准确预测分布式数据库中多并发查询导致CPU、I/O资源争用情形下的查询延迟;针对这一问题,文章提出了一种在分布式数据库中预测并发OLAP型查询延迟的技术,该技术通过建立查询干扰度和查询敏感度模型来衡量资源(I/O,网络)竞争的激烈程度,并据此来预测不同执行环境下的查询性能;TPC-DS的实验结果表明,分析型查询预测的误差率在25%以下,说明该技术能够较准确地预测查询执行时间。Database query performance prediction is predicting query latency time.Database query latency prediction technology can be used for query scheduling and query progress display.However,current query performance prediction techniques often have some limitations and be hard to accurately predict the query latency caused by the concurrency queries in the distributed database,because of the CPU and I/O resource contention.Aimed at this problem,a prediction concurrent OLAP query latency technique is proposed in distributed database.The proposed method measures the intensity of competition in the resources of I/O and network by setting up the concurrent query interference(CQI)and query sensitivity(QS)models,And accordingly predicts the query performance under the different execution environments.The experimental results of the TPC-DS show that the mean relative error of analytical query prediction is less than 25%,which shows that the technology can predict the query execution time more accurately.

关 键 词：性能预测 查询延迟 并发查询 分布式数据库 并发OLAP 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]