RiftANN：基于RDMA内存解耦的高效图遍历向量检索

中文摘要 AI 辅助

面向十亿级向量集合的图索引可能超出单台服务器的DRAM容量。基于被动RDMA的内存解耦提供了可扩展的容量，且无需内存节点计算，但传统的最佳优先搜索在此设置下表现不佳。细粒度且不必要的远程读取增加了通信开销，而候选评估与后续扩展之间的依赖关系使遍历串行化，导致CPU空闲。我们提出了RiftANN，一个面向被动RDMA内存解耦的基于图的近似最近邻搜索（ANNS）系统。RiftANN在计算节点使用紧凑向量进行导航，并使用根据观测到的近似误差校准的阈值选择性验证精确向量。一个有界单边RDMA流水线将剩余的远程访问与本地处理批量化和重叠。RiftANN并行评估返回的邻居，并增量式地整合已完成的结果。一个影响门控估计未完成的评估是否可能改变候选集，允许在其预期影响较小时继续遍历，同时防止从不完整的搜索状态进行不安全的前进。一个轻量级反馈控制器根据搜索配置和查询负载的变化协调RDMA并发与后台评估容量。我们在SIFT、DEEP和SPACEV的100M规模以及SIFT1B上评估了RiftANN。在匹配召回率下，RiftANN相比DistVS实现了1.6倍至4.3倍的延迟加速和1.1倍至2.2倍的吞吐量提升，相比基于SSD的DiskANN和PipeANN实现了1.6倍至5.6倍的延迟加速。这些结果表明，被动解耦内存可以在内存节点无查询时计算的情况下支持低延迟的基于图的向量检索。

英文摘要

Graph indexes for billion-scale vector collections can exceed a single server's DRAM capacity. Passive RDMA-based disaggregated memory provides scalable capacity without memory-node computation, but conventional best-first search performs poorly in this setting. Fine-grained and unnecessary remote reads increase communication cost, while dependencies between candidate evaluation and subsequent expansion serialize traversal and leave CPUs idle. We present RiftANN, a graph-based approximate nearest neighbor search (ANNS) system for passive RDMA-based disaggregated memory. RiftANN navigates using compact vectors at compute nodes and selectively verifies exact vectors using a threshold calibrated from observed approximation errors. A bounded one-sided RDMA pipeline batches and overlaps the remaining remote accesses with local processing. RiftANN evaluates returned neighbors in parallel and incrementally incorporates completed results. An impact gate estimates whether unfinished evaluations may change the candidate set, allowing traversal to continue when their expected influence is small while preventing unsafe advancement from incomplete search state. A lightweight feedback controller coordinates RDMA concurrency with background evaluation capacity as search configurations and query loads change. We evaluate RiftANN on SIFT, DEEP, and SPACEV at 100M scale and SIFT1B. At matched recall, RiftANN achieves 1.6x to 4.3x latency speedups and 1.1x to 2.2x higher throughput than DistVS, and 1.6x to 5.6x latency speedups over SSD-based DiskANN and PipeANN. These results show that passive disaggregated memory can support low-latency graph-based vector retrieval without query-time computation at memory nodes.

发表机构

• Arizona State University（亚利桑那州立大学）

机构由 AI 辅助整理，请以论文原文为准。