用强化学习动态调优数据库内存，省下多余内存还保性能达标。
Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization
- 基于强化学习在线调整数据库缓冲区大小，自动适应负载变化。
- 实测比基线节省大量内存，且SLA违规更少。
- 适合关注数据库资源优化的运维与研发人员。
管理数据库管理系统（DBMS）需在服务等级协议（SLA）性能与资源消耗间权衡，常导致内存过度分配而浪费。我们提出MicroTune，一个基于强化学习的在线缓冲区自适应系统，在确保SLA合规的前提下最小化不必要的内存占用。通过在多种基准工作负载下评估多个算法，将MicroTune训练于大量外部指标（延迟、吞吐量）和内部DBMS指标（状态变量与性能统计）的轨迹数据。实验表明，MicroTune能随工作负载波动动态调整缓冲区大小，相比基线实现显著内存节省且减少SLA违规。这些结果凸显了强化学习在数据库系统自适应资源管理中的潜力。
原文摘要 · Abstract (English)
Administering Database Management Systems (DBMS) instances requires Database Administrators (DBA) to balance performance in terms of Service Level Agreement (SLA) against resource usage, often prompting RAM over-allocation that wastes memory. We introduce MicroTune, an online RL-based buffer adjustment system that minimizes unnecessary memory allocation while ensuring SLA compliance. To identify the most effective RL core, we evaluate multiple algorithms under diverse benchmark workloads, training MicroTune on extensive traces of both external metrics (latency, throughput) and internal DBMS metrics (status variables and performance statistics). Experimental results demonstrate that MicroTune dynamically adapts buffer sizes to workload fluctuations, outperforming baselines by achieving significant memory savings with fewer SLA violations. These findings underscore the promise of reinforcement learning for adaptive resource management in DBMS environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。