一句话：提出 Nemo 缓存，通过提高哈希冲突提升组填充率，并用 Bloom filter 索引与混合热度跟踪降低微小对象写放大及缺失率。
现代存储系统常用闪存 SSD 作为缓存层，但在微小对象负载下，即使使用 Zoned Namespace SSD、Flexible Data Placement SSD 等低设备级写放大的日志结构闪存设备，应用级写放大仍很高。Nemo 改进组相联缓存设计，通过提高哈希冲突概率来提升组填充率，从而降低应用级写放大；为兼顾高内存效率与低缺失率，它引入基于 Bloom filter 的索引机制以显著减少内存开销，并采用混合热度跟踪。实验结果表明，Nemo 能同时实现闪存缓存的三个关键目标：低写放大、高内存效率和低缺失率。
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.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2603-09605,
title = {Nemo: A Low-Write-Amplification Cache for Tiny Objects on Log-Structured Flash Devices},
author = {Xufeng Yang and Tingting Tan and Jingxin Hu and Congming Gao and Mingyang Liu and Tianyang Jiang and Jian Chen and Linbo Long and Yina Lv and Jiwu Shu},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790191}
}