The Vespa Cloud Metrics Dashboard

A guide to using the Vespa Cloud metrics dashboard for production troubleshooting. Covers a three-question framework (system health, latency source, resource saturation) and walks through the Overview, Query, Feed, and Resources tabs. Also highlights recent additions: a Health Indicators row with five stat panels, new annotations for service restarts and core dumps, per-configuration container thread pool rows, and a JVM memory breakdown separating heap, direct, and native memory. Includes a practical incident workflow for moving from symptom to bottleneck quickly.