DB-BERT: making database tuning tools “read” the manual
DB-BERT: making database tuning tools “read” the manual
复制标题
DOI：
10.1007/s00778-023-00831-y
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Immanuel Trummer
中科院分区：
文献类型：
--
作者：
Immanuel Trummer
DB-BERT 是一种数据库调优工具，它利用通过手册和其他相关文本文档的自然语言分析获得的信息。它使用文本来标识要调整的数据库系统参数以及建议的参数值。 DB-BERT 应用大型预训练语言模型（特别是 BERT 模型）进行文本分析。在初始训练阶段，它会微调模型权重，以便将自然语言提示转换为推荐设置。在运行时，DB-BERT 学习聚合、调整提示并确定其优先级，以实现特定数据库系统和基准测试的最佳性能。这两个阶段都是迭代的，并使用强化学习来指导选择要评估的调整设置（惩罚数据库系统拒绝的设置，同时奖励提高性能的设置）。在我们的实验中，我们利用数百个有关数据库调优的文本文档作为 DB-BERT 的输入。我们将 DB-BERT 与各种基准进行比较，考虑不同的基准（TPC-C 和 TPC-H）、指标（吞吐量和运行时间）以及数据库系统（PostgreSQL 和 MySQL）。实验清楚地表明，DB-BERT 受益于将从文本文档中挖掘的有关数据库调优的一般信息与通过试运行获得的特定场景的见解相结合。 DB-BERT 的完整源代码可在线获取：https://itrummer.github.io/dbbert/。
DB-BERT is a database tuning tool that exploits information gained via natural language analysis of manuals and other relevant text documents. It uses text to identify database system parameters to tune as well as recommended parameter values. DB-BERT applies large, pre-trained language models (specifically, the BERT model) for text analysis. During an initial training phase, it fine-tunes model weights in order to translate natural language hints into recommended settings. At run time, DB-BERT learns to aggregate, adapt, and prioritize hints to achieve optimal performance for a specific database system and benchmark. Both phases are iterative and use reinforcement learning to guide the selection of tuning settings to evaluate (penalizing settings that the database system rejects while rewarding settings that improve performance). In our experiments, we leverage hundreds of text documents about database tuning as input for DB-BERT. We compare DB-BERT against various baselines, considering different benchmarks (TPC-C and TPC-H), metrics (throughput and run time), as well as database systems (PostgreSQL and MySQL). The experiments demonstrate clearly that DB-BERT benefits from combining general information about database tuning, mined from text documents, with scenario-specific insights, gained via trial runs. The full source code of DB-BERT is available online at https://itrummer.github.io/dbbert/.