On Scalable Integrity Checking for Secure Cloud Disks

2024-05-06

AI Summary

Integrity verification in cloud block storage incurs substantial I/O performance degradation. Method: This paper proposes Dynamic Merkle Tree (DMT), the first approach to model and analyze overhead root causes based on real-world workload characteristics, enabling adaptive optimization of hash tree structure. DMT decouples integrity verification from the I/O critical path and lightweightens it via storage-layer hash modeling, fine-grained workload analysis, and dynamic tree restructuring. Contribution/Results: Under guaranteed data integrity and freshness, DMT achieves up to 2.2× higher throughput and up to 2.2× lower latency compared to the state-of-the-art, significantly improving cloud storage I/O efficiency.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Search and Optimization: Distributed Search
• Machine Learning: Hardware-aware ML

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Merkle hash trees are the standard method to protect the integrity and freshness of stored data. However, hash trees introduce additional compute and I/O costs on the I/O critical path, and prior efforts have not fully characterized these costs. In this paper, we quantify performance overheads of storage-level hash trees in realistic settings. We then design an optimized tree structure called Dynamic Merkle Trees (DMTs) based on an analysis of root causes of overheads. DMTs exploit patterns in workloads to deliver up to a 2.2x throughput and latency improvement over the state of the art. Our novel approach provides a promising new direction to achieve integrity guarantees in storage efficiently and at scale.

Problem

• Cloud Storage
• Data Security
• I/O Efficiency

Innovation

• Dynamic Merkle Trees
• Performance Optimization
• Cloud Storage