William Schor
Transferring massive datasets (e.g., 50 TB) into online serving systems—without disrupting live applications—poses unique challenges. Traditional methods often lead to high costs, slow transfers, and performance bottlenecks. In this talk, we present a novel system that preprocesses data offline into RocksDB SST files, stages them in the cloud, and loads them into isolated online infrastructure for seamless, near-instantaneous cutovers. Our approach enables robust validation, rapid rollback, and high-scale, low-latency reads, all while dramatically reducing deployment time (by 99%) and cost (by 70%). Attendees will learn about the architectural innovations, technical lessons, and practical strategies that make this system a game-changer for large-scale data operations.
William Schor is a Senior Software Engineer at Netflix, where he works on the KeyValue team building and scaling distributed data systems. He focuses on resilience and high availability, playing a key role in evolving Netflix's data infrastructure to support diverse and fast-growing use cases across the company.
William holds a BS in Computer Science from Brown University and has published research in cryptographic security. His work spans distributed systems, data infrastructure, and security, bringing both academic rigor and practical experience to solving complex engineering challenges at scale.
author = {William Schor},
title = {Low Latency Serving of Offline Data: Efficient, Safe, and Reliable Data Loading At Scale},
year = {2026},
address = {Seattle, WA},
publisher = {USENIX Association},
month = mar
}