WATuning: A Workload-Aware Tuning System with Attention-Based Deep Reinforcement Learning
WATuning: A Workload-Aware Tuning System with Attention-Based Deep Reinforcement Learning
复制标题
WATuning：具有基于注意力的深度强化学习的工作负载感知调优系统
DOI：
10.1007/s11390-021-1350-8
复制
发表时间：
2021-07
影响因子：
0.7
通讯作者：
Chai Yun-Peng
中科院分区：
文献类型：
--
作者：
Ge Jia-Ke;Chai Yan-Feng;Chai Yun-Peng
配置调优对于优化系统性能至关重要（例如，数据库、键值存储）。高性能通常表示高吞吐量和低延迟。目前，系统的大多数调优任务都是人工执行的（例如，数据库管理员），但是他们很难通过在各种类型的系统和各种环境中进行调优来实现高性能。近年来，人们对传统数据库系统的调优进行了一些研究，但这些方法都有一定的局限性。本文提出了一种基于注意力深度强化学习的调优系统WATuning，该系统能够适应负载特征的变化，高效地优化系统性能。首先，我们设计了WATuning的核心算法ATT-Tune来完成系统的调优任务。该算法利用工作负载特征生成权重矩阵，并作用于系统的内部指标，然后ATT-Tune使用分配了权重值的内部指标来选择合适的配置。其次，WATuning可以根据工作负载的变化生成多个实例模型，从而可以针对不同类型的工作负载完成有针对性的推荐服务。最后，Watuning还可以根据实际应用中不断变化的工作负载，对自身进行动态微调，使其能够更好地贴合实际环境提出建议。实验结果表明，WATuning的吞吐量和延迟分别比现有的优化调优方法CDBTune的吞吐量和延迟提高了52.6%和31%。
Configuration tuning is essential to optimize the performance of systems (e.g., databases, key-value stores). High performance usually indicates high throughput and low latency. At present, most of the tuning tasks of systems are performed artificially (e.g., by database administrators), but it is hard for them to achieve high performance through tuning in various types of systems and in various environments. In recent years, there have been some studies on tuning traditional database systems, but all these methods have some limitations. In this article, we put forward a tuning system based on attention-based deep reinforcement learning named WATuning, which can adapt to the changes of workload characteristics and optimize the system performance efficiently and effectively. Firstly, we design the core algorithm named ATT-Tune for WATuning to achieve the tuning task of systems. The algorithm uses workload characteristics to generate a weight matrix and acts on the internal metrics of systems, and then ATT-Tune uses the internal metrics with weight values assigned to select the appropriate configuration. Secondly, WATuning can generate multiple instance models according to the change of the workload so that it can complete targeted recommendation services for different types of workloads. Finally, WATuning can also dynamically fine-tune itself according to the constantly changing workload in practical applications so that it can better fit to the actual environment to make recommendations. The experimental results show that the throughput and the latency of WATuning are improved by 52.6% and decreased by 31%, respectively, compared with the throughput and the latency of CDBTune which is an existing optimal tuning method.
登录
查看更多内容
影响因子：
6.8
作者：
T. Ban
通讯作者：
T. Ban
影响因子：
5.3
作者：
Dang Quang Nguyen;Ngo Anh Vien;Viet-Hung Dang;TaeChoong Chung
通讯作者：
Dang Quang Nguyen;Ngo Anh Vien;Viet-Hung Dang;TaeChoong Chung
DOI：
10.1007/978-3-319-09333-8_1
发表时间：
2014-08
期刊：
--
影响因子：
--
作者：
Conghuan Zheng;Zuohua Ding;Jue-liang Hu
通讯作者：
Conghuan Zheng;Zuohua Ding;Jue-liang Hu
DOI：
10.14778/3137765.3137833
发表时间：
2017-08
期刊：
Proc. VLDB Endow.
影响因子：
--
作者：
Guoliang Li
通讯作者：
Guoliang Li
行人防撞与人机协同驾驶的深度强化学习
影响因子：
8.1
作者：
Li, Junxiang;Yao, Liang;Ren, Junkai
通讯作者：
Ren, Junkai