Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.08826 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908647321239552 |
|---|---|
| author | Guo, Zonglin Givargis, Tony |
| author_facet | Guo, Zonglin Givargis, Tony |
| contents | Key-value stores are a fundamental class of NoSQL databases that offer a simple yet powerful model for data storage and retrieval, representing information as pairs of unique keys and associated values. Their minimal structure enables exceptionally fast access times, scalability, and flexibility in storing diverse data types, making them ideal for high-performance applications such as caching, session management, and distributed systems. As modern computing increasingly demands responsiveness and scalability, key-value stores have become a critical component of the data infrastructure in both industry and research contexts. In this work, we present FlashMap, a high-performance key-value store optimized for Flash-based solid-state drives (SSDs). Experiments show that FlashMap achieves outstanding throughput, averaging 19.8 million inserts and 23.8 million random lookups per second with a 100-byte payload, all on a single data center-grade server. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_08826 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlashMap: A Flash Optimized Key-Value Store Guo, Zonglin Givargis, Tony Databases Key-value stores are a fundamental class of NoSQL databases that offer a simple yet powerful model for data storage and retrieval, representing information as pairs of unique keys and associated values. Their minimal structure enables exceptionally fast access times, scalability, and flexibility in storing diverse data types, making them ideal for high-performance applications such as caching, session management, and distributed systems. As modern computing increasingly demands responsiveness and scalability, key-value stores have become a critical component of the data infrastructure in both industry and research contexts. In this work, we present FlashMap, a high-performance key-value store optimized for Flash-based solid-state drives (SSDs). Experiments show that FlashMap achieves outstanding throughput, averaging 19.8 million inserts and 23.8 million random lookups per second with a 100-byte payload, all on a single data center-grade server. |
| title | FlashMap: A Flash Optimized Key-Value Store |
| topic | Databases |
| url | https://arxiv.org/abs/2511.08826 |