Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (3): 657-661.DOI: 10.11772/j.issn.1001-9081.2020091424

Special Issue: 第37届CCF中国数据库学术会议(NDBC 2020)

• The 37th CCF National Database Conference (NDBC 2020) • Previous Articles     Next Articles

Dynamic workload matching method for automatic parameter tuning

SHEN Chen, TAI Lingxiang, PENG Yuwei   

  1. School of Computer Science, Wuhan University, Wuhan Hubei 430072, China
  • Received:2020-09-07 Revised:2020-10-24 Online:2021-03-10 Published:2020-11-10

面向自动参数调优的动态负载匹配方法

沈忱, 邰凌翔, 彭煜玮   

  1. 武汉大学 计算机学院, 武汉 430072
  • 通讯作者: 彭煜玮
  • 作者简介:沈忱(1996-),男,湖北安陆人,硕士研究生,主要研究方向:数据库系统;邰凌翔(1993-),男,江苏南京人,硕士研究生,主要研究方向:数据库系统;彭煜玮(1980-),男,湖北天门人,副教授,博士,CCF会员,主要研究方向:数据库系统、数字水印。

Abstract: A dynamic workload description method and a dynamic workload matching algorithm were proposed to improve the accuracy of workload matching in automatic parameter tuning systems, such as OtterTune, with static workload description. First, a dynamic workload description method was proposed to describe the workload changes more accurately. Then, for the problems such as irregular sequences in workload matching and that the Euclidean distance algorithm is no longer applicable, a dynamic workload matching algorithm using data alignment was proposed based on the Dynamic Time Warping (DTW) algorithm. Finally, the proposed methods were applied to OtterTune to form a dynamic workload-based tuning tool D-OtterTune (Dynamic workload based OtterTune), and several experiments were conducted on it. Experimental results showed that, compared with the original method OtterTune, with the stable improvement in the workload matching accuracy for automatic parameter tuning brought by the dynamic workload matching method, D-OtterTune had the accuracy increased by 3%. It can be seen that D-OtterTune can have a significant impact on the overall business performance in data-intensive applications.

Key words: automatic parameter tuning, dynamic workload description, dynamic workload matching, Dynamic Time Warping (DTW)

摘要: 针对OtterTune等自动参数调优方法采用静态负载描述不够准确的问题,提出了一种动态负载的时序描述方式和动态负载匹配方法。首先,提出一种动态负载描述方法来更准确地刻画负载变化;接着,对于负载匹配中序列不规则、欧氏距离算法不再适用等问题,基于动态时间规整(DTW)算法提出了一种使用数据对齐思想的动态负载匹配算法;最后,将所提出的方法应用于OtterTune上从而形成了基于动态负载的调优工具D-OtterTune,并对其进行若干实验。实验结果表明,和OtterTune原方法相比,动态负载匹配方法对自动参数调优的负载匹配的准确度有稳定幅度的提升,使D-OtterTune准确度提升达到3%。可见在数据密集型应用中,D-OtterTune对整体业务性能可以产生明显影响。

关键词: 自动参数调优, 动态负载描述, 动态负载匹配, 动态时间规整

CLC Number: