Indexer++: workload-aware online index tuning with transformers and reinforcement learning
Indexer++: workload-aware online index tuning with transformers and reinforcement learning
复制标题
DOI：
10.1145/3477314.3507691
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
V. Sharma;Curtis E. Dyreson
中科院分区：
文献类型：
--
作者：
V. Sharma;Curtis E. Dyreson
随着现代数据库中工作负载复杂性的增加，索引选择的手动过程是一项具有挑战性的任务。人们越来越需要一个能够学习和适应不断变化的工作负载的数据库。本文提出了Indexer++，一个自治的，工作负载感知的，在线索引调谐器。与现有的方法不同，Indexer++对DBMS的开销很低，对查询工作负载的变化做出响应，并迅速选择索引。我们的方法结合了文本分析技术和强化学习。Indexer++由两个阶段组成：阶段（i）使用基于预训练的Transformer模型的新型趋势检测技术来学习工作负载趋势。阶段（ii）在线执行，即，连续或当DBMS正在处理工作负载时，使用我们提出的优先级经验扫描的新型在线深度强化学习技术进行索引选择。本文使用基准测试（TPC-H）和真实世界数据集（IMDB）在多个场景中对Indexer++进行了实验评估。在我们的实验中，Indexer++有效地识别了工作负载趋势的变化，并选择了一组最佳索引。
With the increasing workload complexity in modern databases, the manual process of index selection is a challenging task. There is a growing need for a database with an ability to learn and adapt to evolving workloads. This paper proposes Indexer++, an autonomous, workload-aware, online index tuner. Unlike existing approaches, Indexer++ imposes low overhead on the DBMS, is responsive to changes in query workloads and swiftly selects indexes. Our approach uses a combination of text analytic techniques and reinforcement learning. Indexer++ consist of two phases: Phase (i) learns workload trends using a novel trend detection technique based on a pre-trained transformer model. Phase (ii) performs online, i.e., continuous or while the DBMS is processing workloads, index selection using a novel online deep reinforcement learning technique using our proposed priority experience sweeping. This paper provides an experimental evaluation of Indexer++ in multiple scenarios using benchmark (TPC-H) and real-world datasets (IMDB). In our experiments, Indexer++ effectively identifies changes in workload trends and selects the set of optimal indexes.