ELMo-Tune-V2: LLM-Assisted Full-Cycle Auto-Tuning to Optimize LSM-Based Key-Value Stores

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Thakkar, Viraj, Lin, Qi, Prasetyo, Kenanya Keandra Adriel, Wisjnunandono, Raden Haryosatyo, Kistijantoro, Achmad Imam, Rachmadi, Reza Fuad, Cao, Zhichao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929729969324032
author Thakkar, Viraj
Lin, Qi
Prasetyo, Kenanya Keandra Adriel
Wisjnunandono, Raden Haryosatyo
Kistijantoro, Achmad Imam
Rachmadi, Reza Fuad
Cao, Zhichao
author_facet Thakkar, Viraj
Lin, Qi
Prasetyo, Kenanya Keandra Adriel
Wisjnunandono, Raden Haryosatyo
Kistijantoro, Achmad Imam
Rachmadi, Reza Fuad
Cao, Zhichao
contents Log-Structured Merge-tree-based Key-Value Store (LSM-KVS) is a foundational storage engine serving diverse modern workloads, systems, and applications. To suit varying use cases, LSM-KVS allows a vast configuration space that controls core parameters like compaction, flush, and cache sizes, each consuming a shared pool of CPU, Memory, and Storage resources. Navigating the LSM-KVS configuration space necessitates knowledge of the impact of each configuration on the expected workload and underlying hardware. Beyond expensive and time-intensive human-expert-based tuning, existing LSM-KVS tuning solutions focus on tuning with specific workload expectations while limited to a narrow subset of parameters. This paper introduces ELMo-Tune-V2, a framework that integrates Large Language Models (LLMs) at its foundation to demonstrate the potential of applying modern LLMs in data system optimization problems. ELMo-Tune-V2 leverages the contextual reasoning, cross-domain, and generative capabilities of LLMs to perform 1) self-navigated characterization and modeling of LSM-KVS workloads, 2) automatic tuning across a broad parameter space using cross-domain knowledge, and 3) real-time dynamic configuration adjustments for LSM-KVS. ELMo-Tune-V2 integrates three innovations: LLM-based workload synthesis for adaptive benchmark generation, feedback-driven iterative fine-tuning for configuration refinement, and real-time tuning to handle evolving workloads. Through detailed evaluation using RocksDB under several real-world applications across diverse scenarios, ELMo-Tune-V2 achieves performance improvements up to ~14X our YCSB benchmarks compared against default RocksDB configurations, and our end-to-end tests with upper-level applications, NebulaGraph and Kvrocks, demonstrate performance gains of 34% and 26%, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17606
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ELMo-Tune-V2: LLM-Assisted Full-Cycle Auto-Tuning to Optimize LSM-Based Key-Value Stores
Thakkar, Viraj
Lin, Qi
Prasetyo, Kenanya Keandra Adriel
Wisjnunandono, Raden Haryosatyo
Kistijantoro, Achmad Imam
Rachmadi, Reza Fuad
Cao, Zhichao
Databases
Log-Structured Merge-tree-based Key-Value Store (LSM-KVS) is a foundational storage engine serving diverse modern workloads, systems, and applications. To suit varying use cases, LSM-KVS allows a vast configuration space that controls core parameters like compaction, flush, and cache sizes, each consuming a shared pool of CPU, Memory, and Storage resources. Navigating the LSM-KVS configuration space necessitates knowledge of the impact of each configuration on the expected workload and underlying hardware. Beyond expensive and time-intensive human-expert-based tuning, existing LSM-KVS tuning solutions focus on tuning with specific workload expectations while limited to a narrow subset of parameters. This paper introduces ELMo-Tune-V2, a framework that integrates Large Language Models (LLMs) at its foundation to demonstrate the potential of applying modern LLMs in data system optimization problems. ELMo-Tune-V2 leverages the contextual reasoning, cross-domain, and generative capabilities of LLMs to perform 1) self-navigated characterization and modeling of LSM-KVS workloads, 2) automatic tuning across a broad parameter space using cross-domain knowledge, and 3) real-time dynamic configuration adjustments for LSM-KVS. ELMo-Tune-V2 integrates three innovations: LLM-based workload synthesis for adaptive benchmark generation, feedback-driven iterative fine-tuning for configuration refinement, and real-time tuning to handle evolving workloads. Through detailed evaluation using RocksDB under several real-world applications across diverse scenarios, ELMo-Tune-V2 achieves performance improvements up to ~14X our YCSB benchmarks compared against default RocksDB configurations, and our end-to-end tests with upper-level applications, NebulaGraph and Kvrocks, demonstrate performance gains of 34% and 26%, respectively.
title ELMo-Tune-V2: LLM-Assisted Full-Cycle Auto-Tuning to Optimize LSM-Based Key-Value Stores
topic Databases
url https://arxiv.org/abs/2502.17606