用聚类+固态硬盘，让大规模近似搜索省下90%硬件成本。
The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman
- 基于聚类设计新系统，用用户态存储和GPU加速降低延迟。
- 在40台机器上完成百亿级索引构建，耗时数小时。
- 适合需要低成本、高吞吐的推荐与搜索系统部署。
红笔记（Xiaohongshu）作为全球规模社交平台，广泛采用近似最近邻搜索（ANNS）支撑搜索、推荐与广告服务。为满足严格的SLA要求，需依赖内存图结构的ANNS（如HNSW）以实现高吞吐与低延迟。然而用户与内容量持续增长，导致内存占用爆炸式上升，带来巨大资本支出（CapEx）与运营支出（OpEx）。探索多种方案后，我们发现基于全闪存服务器构建聚类式ANNS具有潜力。但此前仍面临内核I/O栈开销大、固定剪枝策略效率低、索引构建慢等问题。本文提出HELMSMAN：一种面向ANNS优化的用户态存储栈、基于学习的分级剪枝模块，以及GPU加速的构建流水线。该系统节省超90%硬件成本，支持百亿级索引数小时内完成重建。当前生产环境已稳定运行数月，40台机器承载原需约35,000核心与0.35 PB DRAM的ANNS负载。
原文摘要 · Abstract (English)
RedNote (a.k.a., Xiaohongshu, a global-scale social network platform) widely adopts approximate nearest neighbor search (ANNS) to power its search, recommendation, and advertising services. Due to the demanding Service Level Agreements (SLAs), we have to rely on in-memory graph-based ANNS (i.e., HNSW) to provide high throughput and low latency. However, the ever-growing user base and content volume have led to an explosive increase in memory footprint and consequently huge CapEx and OpEx. After exploring various alternatives, we find that building a clustering-based ANNS on top of all-flash servers can be promising. Yet, we still experience severe overheads from the kernel I/O stack, a fixed pruning strategy, and slow index construction. We present HELMSMAN, a high-performance and cost-effective clustering-based ANNS system, which combines an ANNS-oriented userspace storage stack, a leveling-learned pruning module, and GPU-accelerated pipelines of construction. HELMSMAN saves over 90% of hardware costs and enables billion-scale index (re)builds within hours. In the current production deployment, operating stably for several months, 40 machines now host ANNS workloads that previously required about 35,000 cores and 0.35 PB DRAM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。