Nemo: A Low-Write-Amplification Cache for Tiny Objects on Log-Structured Flash Devices
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910047920979968 |
|---|---|
| author | Yang, Xufeng Tan, Tingting Hu, Jingxin Gao, Congming Liu, Mingyang Jiang, Tianyang Chen, Jian Long, Linbo Lv, Yina Shu, Jiwu |
| author_facet | Yang, Xufeng Tan, Tingting Hu, Jingxin Gao, Congming Liu, Mingyang Jiang, Tianyang Chen, Jian Long, Linbo Lv, Yina Shu, Jiwu |
| contents | Modern storage systems predominantly use flash-based SSDs as a cache layer due to their favorable performance and cost efficiency. However, in tiny-object workloads, existing flash cache designs still suffer from high write amplification. Even when deploying advanced log-structured flash devices (e.g., Zoned Namespace SSDs and Flexible Data Placement SSDs) with low device-level write amplification, application-level write amplification still dominates. This work proposes Nemo, which enhances set-associative cache design by increasing hash collision probability to improve set fill rate, thereby reducing application-level write amplification. To satisfy caching requirements, including high memory efficiency and low miss ratio, we introduce a bloom filter-based indexing mechanism that significantly reduces memory overhead, and adopt a hybrid hotness tracking to achieve low miss ratio without losing memory efficiency. Experimental results show that Nemo simultaneously achieves three key objectives for flash cache: low write amplification, high memory efficiency, and low miss ratio. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09605 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Nemo: A Low-Write-Amplification Cache for Tiny Objects on Log-Structured Flash Devices Yang, Xufeng Tan, Tingting Hu, Jingxin Gao, Congming Liu, Mingyang Jiang, Tianyang Chen, Jian Long, Linbo Lv, Yina Shu, Jiwu Hardware Architecture Modern storage systems predominantly use flash-based SSDs as a cache layer due to their favorable performance and cost efficiency. However, in tiny-object workloads, existing flash cache designs still suffer from high write amplification. Even when deploying advanced log-structured flash devices (e.g., Zoned Namespace SSDs and Flexible Data Placement SSDs) with low device-level write amplification, application-level write amplification still dominates. This work proposes Nemo, which enhances set-associative cache design by increasing hash collision probability to improve set fill rate, thereby reducing application-level write amplification. To satisfy caching requirements, including high memory efficiency and low miss ratio, we introduce a bloom filter-based indexing mechanism that significantly reduces memory overhead, and adopt a hybrid hotness tracking to achieve low miss ratio without losing memory efficiency. Experimental results show that Nemo simultaneously achieves three key objectives for flash cache: low write amplification, high memory efficiency, and low miss ratio. |
| title | Nemo: A Low-Write-Amplification Cache for Tiny Objects on Log-Structured Flash Devices |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2603.09605 |