High-Throughput S3 Object Hashing: 3GB/s with Rust and Tokio

A high-speed S3 object hasher built with Rust, processing at up to 3 GB/s. We use a channel-based architecture to concurrently stream and hash S3 objects. We process a 12 TB dataset in just over an hour, demonstrating Rust’s capability for efficient, large-scale data processing.

July 30, 2024