Presto: SQL-on-Anything using Kubernetes
summary
Presto is a distributed SQL engine that separates compute from storage, runs vectorized in-memory execution with runtime bytecode generation, and supports connectors to S3, HDFS, relational and nonrelational systems. The team packages Presto as a container and an Presto Kubernetes Operator for OpenShift/Kubernetes, demoing a 6-node cluster with 5 active workers and a TPC-H query that completes in roughly ten seconds. Starburst adds a cost-based optimizer, Ranger security integration, JDBC/ODBC drivers and a Mission Control UI; major users report clusters from hundreds to 10,000+ nodes and hundreds of petabytes.
AI-written summary · about
chapters (23)
- 0:00Intro
- 0:32What is Presto?
- 3:47Presto Architecture
- 4:47Query Execution Performance
- 6:46Presto Extensibility with Connectors
- 7:58Deployment for HDFS
- 9:02Apache Hive Connector
- 10:09Relational Database Connectors (JDBC based)
- 10:43Non Relational Data Sources
- 11:04SQL Support
- 11:41Security
- 13:55The Presto Fon Club
- 15:31Joining the Presto Community
- 16:09Starburst Overview
- 17:04Key Presto contributions from Starburst team
- 19:35Try Starburst
- 31:03Custom Resource Definition
- 32:54Resources for building Operators
- 35:03Managing Operators
- 37:09Publishing your Operator
- 39:29Testing your Operator
- 40:59Kubernetes Operators Workshop
- 41:18Useful Links
related talks
51mPresto Open Source SQL Engine for Massive Scale Data Lakehouses
22mIntroduction to Presto: The SQL Engine for Data Platform Teams
22mPresto for Your Fast, Open SQL Lakehouse
49mPresto in the Cloud
35mIntroducing Prestissimo, Presto's Next-Gen Query Execution Engine
06mDriving enterprise open source adoption, from data lake to AI
48mContinuous Optimization for distributed BigData analysis
34mBuilding Presto SQL experience on Flink