Metraipolis › archive › dc_2b018dace2bc

RiftANN: Efficient Graph Traversal for Vector Search with RDMA-Based Memory Disaggregation — arXiv:2610.08990

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08990
License (as archived)
CC0-1.0
Archived
2026-10-08T12:49:33.042Z
SHA-256 of the archived text
a08f9081054e76269903e5042d43ea397505a1792e7dbd5dfcf7ce6db13d29f1
Stable URL of this page
https://metraipolis.com/documento/dc_2b018dace2bc

How to cite

RiftANN: Efficient Graph Traversal for Vector Search with RDMA-Based Memory Disaggregation — arXiv:2610.08990 — arXiv (en), https://arxiv.org/abs/2610.08990 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b018dace2bc (Metraipolis archive dc_2b018dace2bc, sha256 a08f9081054e76269903e5042d43ea397505a1792e7dbd5dfcf7ce6db13d29f1)
BibTeX
@misc{dc2b018dace2bc,
  title = {RiftANN: Efficient Graph Traversal for Vector Search with RDMA-Based Memory Disaggregation — arXiv:2610.08990},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08990},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b018dace2bc; sha256 a08f9081054e76269903e5042d43ea397505a1792e7dbd5dfcf7ce6db13d29f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08990. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.DB, nuovi lavori del giorno).
Categorie arXiv: Databases (cs.DB).
Pagina del lavoro: https://arxiv.org/abs/2610.08990 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:45.280Z dalla pagina https://arxiv.org/list/cs.DB/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).