Optimizing SSD-Resident Graph Indexing for High-Throughput Vector Search

TL;DR

VeloANN enhances SSD-resident graph indexing for vector search by optimizing data layout and runtime to significantly improve throughput and latency, approaching in-memory performance with minimal memory use.

Contribution

The paper introduces VeloANN, a novel SSD-based graph index system employing locality-aware data placement, asynchronous runtime, and buffer management to boost performance and efficiency.

Findings

Up to 5.8x throughput improvement over state-of-the-art SSD systems.

Achieves 0.92x the throughput of in-memory systems with only 10% memory.

Reduces latency by up to 3.25x compared to existing disk-based solutions.

Abstract

Graph-based approximate nearest neighbor search (ANNS) methods (e.g., HNSW) have become the de facto state of the art for their high precision and low latency. To scale beyond main memory, recent out-of-memory ANNS systems leverage SSDs to store large vector indexes. However, they still suffer from severe CPU underutilization and read amplification (i.e., storage stalls) caused by limited access locality during graph traversal. We present VeloANN, which mitigates storage stalls through a locality-aware data layout and a coroutine-based asynchronous runtime. VeloANN utilizes hierarchical compression and affinity-based data placement scheme to co-locate related vectors within the same page, effectively reducing fragmentation and over-fetching. We further design a record-level buffer pool, where each record groups the neighbors of a vector; by persistently retaining hot records in memory, it eliminates excessive page swapping under constrained memory budgets. To minimize CPU scheduling overheads during disk I/O interruptions, VeloANN employs a coroutine-based asynchronous runtime for lightweight task scheduling. On top of this, it incorporates asynchronous prefetching and a beam-aware search strategy to prioritize cached data, ultimately improving overall search efficiency. Extensive experiments show that VeloANN outperforms state-of-the-art disk-based ANN systems by up to 5.8x in throughput and 3.25x in latency reduction, while achieving 0.92x the throughput of in-memory systems using only 10% of their memory footprint.