The Clustering Strikes Back: Building Cost-Effective and High-Performance ANNS at Scale with Helmsman
For large-scale platforms like RedNote, Helmsman drastically reduces the memory footprint and cost of ANNS while maintaining performance, addressing a critical operational bottleneck.
Helmsman reduces hardware costs by over 90% for billion-scale ANNS by replacing in-memory graph-based search with clustering-based search on all-flash servers, achieving stable production deployment where 40 machines replace 35,000 cores and 0.35 PB DRAM.
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.