DobLIX: A Dual-Objective Learned Index for Log-Structured Merge Trees
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914016639582208 |
|---|---|
| author | Heidari, Alireza Ahmadi, Amirhossein Zhang, Wei |
| author_facet | Heidari, Alireza Ahmadi, Amirhossein Zhang, Wei |
| contents | In this paper, we introduce DobLIX, a dual-objective learned index specifically designed for Log-Structured Merge(LSM) tree-based key-value stores. Although traditional learned indexes focus exclusively on optimizing index lookups, they often overlook the impact of data access from storage, resulting in performance bottlenecks. DobLIX addresses this by incorporating a second objective, data access optimization, into the learned index training process. This dual-objective approach ensures that both index lookup efficiency and data access costs are minimized, leading to significant improvements in read performance while maintaining write efficiency in real-world LSM-tree systems. Additionally, DobLIX features a reinforcement learning agent that dynamically tunes the system parameters, allowing it to adapt to varying workloads in real-time. Experimental results using real-world datasets demonstrate that DobLIX reduces indexing overhead and improves throughput by 1.19 to 2.21 times compared to state-of-the-art methods within RocksDB, a widely used LSM-tree-based storage engine. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05369 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DobLIX: A Dual-Objective Learned Index for Log-Structured Merge Trees Heidari, Alireza Ahmadi, Amirhossein Zhang, Wei Databases Machine Learning Optimization and Control In this paper, we introduce DobLIX, a dual-objective learned index specifically designed for Log-Structured Merge(LSM) tree-based key-value stores. Although traditional learned indexes focus exclusively on optimizing index lookups, they often overlook the impact of data access from storage, resulting in performance bottlenecks. DobLIX addresses this by incorporating a second objective, data access optimization, into the learned index training process. This dual-objective approach ensures that both index lookup efficiency and data access costs are minimized, leading to significant improvements in read performance while maintaining write efficiency in real-world LSM-tree systems. Additionally, DobLIX features a reinforcement learning agent that dynamically tunes the system parameters, allowing it to adapt to varying workloads in real-time. Experimental results using real-world datasets demonstrate that DobLIX reduces indexing overhead and improves throughput by 1.19 to 2.21 times compared to state-of-the-art methods within RocksDB, a widely used LSM-tree-based storage engine. |
| title | DobLIX: A Dual-Objective Learned Index for Log-Structured Merge Trees |
| topic | Databases Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2502.05369 |