Introduction to Presto: The SQL Engine for Data Platform Teams
summary
Presto is a disaggregated SQL query engine that runs on top of data lakes and databases to analyze petabytes of data; it claims 10–15× faster performance by streaming columnar data in memory and using predicate pushdown. Deployments show ~30+ connectors for sources including Delta Lake (native read‑only) and Hive, and a RaptorX multi‑level cache for metadata/file/header/block caching. Roadmap items include spilling and fault tolerance via running Presto as a library on Spark and migrating workers to C++ workers with orders of magnitude throughput.
AI-written summary · about
chapters (7)
- 0:00Introduction to Presto
- 1:42Architecture and basics
- 4:25Technical deep dive
- 6:49Connectors and performance
- 11:00Query execution lifecycle
- 12:09Use cases and lake house
- 16:05Roadmap and future outlook
related talks
46mPresto - Today and Beyond - The Open Source SQL Engine for Querying all Data Lakes
22mPresto for Your Fast, Open SQL Lakehouse
51mPresto Open Source SQL Engine for Massive Scale Data Lakehouses
50mPresto: SQL-on-Anything using Kubernetes
35mIntroducing Prestissimo, Presto's Next-Gen Query Execution Engine
06mDriving enterprise open source adoption, from data lake to AI
34mBuilding Presto SQL experience on Flink
49mPresto in the Cloud