Apache Iceberg is an open table format for huge analytic datasets. Many companies like Twitter use it widely to improve performance of interactive querying on data lakes. At Twitter, engineers built the integrations between Presto and Iceberg to bring high-performance and efficiency of Iceberg to the Presto ecosystem. During this session, Daniel will present an introduction to Apache Iceberg and Chunxu will discuss the Presto - Iceberg integration and share what they’ve learned during the development and usage of these next gen projects.
Speakers:
Chunxu Tang, Sr. Software Engineer at Twitter
Chunxu is a software engineer in Twitter's Interactive Query team where he works on developing and maintaining Presto and Druid services. He received his doctoral degree from Syracuse University, where he did research on machine learning and distributed collaboration systems.
Daniel Weeks, Co-Founder, Tabular
Daniel Weeks is the Co-creator of Apache Iceberg and the Cofounder of Tabular. He led the Big Data Compute team at Netflix, which focuses on building out big data processing engines like Spark, Presto, Druid, etc., in the cloud. He has spent the last 18+ years designing and developing large scale distributed systems with a focus on data processing and open source technologies.