用微秒级学习动态选最优数据库执行核，提速最高2倍。
Piece of CAKE: Adaptive Execution Engines via Microsecond-Scale Learning
- 通过反事实反馈在微秒内选择最佳执行核
- 相比静态启发式，端到端延迟降低最高2倍
- 适合对查询性能敏感的实时数据库系统
低层数据库操作常有多个语义等价但性能差异显著的物理实现（即“内核”）。现有数据库系统通常依赖静态启发式或最坏情况最优默认策略选择内核，常错失显著性能提升机会。本文提出CAKE（反事实自适应内核执行），一种利用微秒级上下文多臂赌博机学习为每个数据片段选择最优内核的系统。CAKE通过利用反事实的低成本——选择性运行多个内核以获取完整反馈——规避了传统强化学习的高延迟问题，并将策略编译为低延迟遗憾树。实验表明，相较于最先进的静态启发式，CAKE可将端到端工作负载延迟降低高达2倍。
原文摘要 · Abstract (English)
Low-level database operators often admit multiple physical implementations ("kernels") that are semantically equivalent but have vastly different performance characteristics depending on the input data distribution. Existing database systems typically rely on static heuristics or worst-case optimal defaults to select these kernels, often missing significant performance opportunities. In this work, we propose CAKE (Counterfactual Adaptive Kernel Execution), a system that learns to select the optimal kernel for each data "morsel" using a microsecond-scale contextual multi-armed bandit. CAKE circumvents the high latency of traditional reinforcement learning by exploiting the cheapness of counterfactuals -- selectively running multiple kernels to obtain full feedback -- and compiling policies into low-latency regret trees. Experimentally, we show that CAKE can reduce end-to-end workload latency by up to 2x compared to state-of-the-art static heuristics.
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。