Keeping a Pulse on the Cluster: Monitoring Presto at Petabyte Scale (Hands-On)

In this interactive, hands-on session, you'll deploy a distributed Presto cluster along with a complete observability stack using Prometheus, Grafana, JMX Exporter, and Alertmanager. You'll learn how to collect metrics, build dashboards, analyze query execution, monitor JVM health, and identify performance bottlenecks using real telemetry from a running cluster.

Register here

What you'll learn

• Understanding Presto's monitoring architecture
• Exposing Presto and JVM metrics using JMX Exporter
• Collecting metrics with Prometheus
• Building Grafana dashboards for cluster health and query performance
• Monitoring coordinators, workers, memory, CPU, and query execution
• Creating alerts for production incidents
• Troubleshooting common operational issues using observability

Prerequisites

• Basic SQL knowledge
• Familiarity with Docker and Docker Compose
• A laptop with Docker installed

Register here