Cloud-Native Vector Search: A Comprehensive Performance Analysis

2025-11-18

AI Summary

This paper addresses performance bottlenecks of cloud-native vector search over remote storage by systematically comparing cluster-based and graph-based indexes under high-concurrency, high-recall, and high-dimensional workloads. Through a unified benchmarking framework, we reveal the graph index’s substantial advantages in latency-sensitive and cache-constrained scenarios, and identify the root cause of local tuning parameter failure in cloud environments: a fundamental mismatch between index access granularity and cloud storage caching mechanisms. To resolve this, we propose a cloud-aware graph index parameter redesign method and an index-cache co-optimization strategy that dynamically adapts query granularity and data-fetch patterns to available cache capacity. Experimental evaluation on representative cloud configurations demonstrates an average 37% reduction in query latency and a 5.2% improvement in recall. This work is the first to rigorously characterize the cloud-native applicability boundaries of these two dominant indexing paradigms.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Social Networks and Social Media: Social mining and social search on the Web

Abstract

Vector search has been widely employed in recommender system and retrieval-augmented-generation pipelines, commonly performed with vector indexes to efficiently find similar items in large datasets. Recent growths in both data and task complexity have motivated placing vector indexes onto remote storage -- cloud-native vector search, which cloud providers have recently introduced services for. Yet, despite varying workload characteristics and various available vector index forms, providers default to using cluster-based indexes, which on paper do adapt well to differences between disk and cloud-based environment: their fetch granularities and lack of notable intra-query dependencies aligns with the large optimal fetch sizes and minimizes costly round-trips (i.e., as opposed to graph-based indexes) to remote storage, respectively. This paper systematically studies cloud-native vector search: What and how should indexes be built and used for on-cloud vector search? We analyze bottlenecks of two common index classes, cluster and graph indexes, on remote storage, and show that despite current standardized adoption of cluster indexes on the cloud, graph indexes are favored in workloads requiring high concurrency and recall, or operating on high-dimensional data or large datatypes. We further find that on-cloud search demands significantly different indexing and search parameterizations versus on-disk search for optimal performance. Finally, we incorporate existing cloud-based caching setups into vector search and find that certain index optimizations work against caching, and study how this can be mitigated to maximize gains under various available cache sizes.

Problem

• Analyzes performance bottlenecks of cluster and graph indexes on cloud storage
• Identifies optimal index configurations for different workload characteristics and data types
• Investigates interaction between vector search optimizations and cloud caching mechanisms

Innovation

• Graph indexes favored for high concurrency workloads
• Different parameterizations needed for cloud versus disk search
• Caching strategies integrated with vector index optimizations