Llm system designs faster database protocols for specific apps
HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols
DatabasesDistributed, Parallel, and Cluster ComputingMultiagent Systems
Summary
Concurrency control protocols help databases manage many users working at once without errors, but picking the best one needs expert skills. The authors created HakiCC, a system using large language models to automatically design and improve these protocols for specific workloads. It first generates and verifies a protocol, then fine-tunes it to boost performance. Tests on common benchmarks show HakiCC makes database protocols both correct and notably faster.
What this means in practice
- •For database engineers: Automatically build and optimize concurrency protocols customized for specific database workloads to improve throughput and correctness.
- •For cloud service providers: Tailor concurrency control protocols to cloud-hosted applications for improved database performance without manual expert tuning.
Authors
Farzad Habibi, Juncheng Fang, Faisal Nawab
Abstract
Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineering effort through cost-efficient automation. Decades of research have produced a rich landscape of concurrency control (CC) protocols, each encoding distinct trade-offs in correctness, throughput, and abort behavior. However, most applications in practice default to 2PL or OCC, because selecting and adapting a protocol to a specific application requires expert knowledge that is rarely available to application designers. This is a wasted opportunity, as an application-specific CC protocol can yield significant performance advantages over a generic baseline, but designing one requires deep expertise in CC protocol design. In this paper, we propose HakiCC, an LLM-driven multi-agent pipeline that automatically designs, verifies, and optimizes concurrency control protocols tailored to a given target application. HakiCC provides a two-stage pipeline. In Stage 1, a multi-agent system takes a workload description as input and generates an application-specific CC protocol implementation, which is iteratively repaired and verified for conflict-serializability. In Stage 2, the verified protocol is further optimized for that application through an LLM-driven evolutionary loop targeting correctness and throughput. We evaluate HakiCC on TPC-C and AuctionMark as target workloads, producing and reporting ten application-specific CC protocols. All ten are conflict-serializable after Stage 1; Stage 2 improves throughput for every protocol, with average gains of +50.6% for TPC-C protocols and +92.2% for AuctionMark protocols.