Documentationbreadcrumb arrow Grafana Cloudbreadcrumb arrow Observe and actbreadcrumb arrow Monitor applicationsbreadcrumb arrow Application Observabilitybreadcrumb arrow Services catalogbreadcrumb arrow Performance
Grafana Cloud

Performance view

The Performance tab in the services catalog displays key performance indicators for all discovered services. It provides an at-a-glance view of service health using RED metrics and knowledge graph insights.

Columns

The performance table displays the following columns:

ColumnDescription
InsightsColored rings indicating active knowledge graph insights for the service (Saturation, Amend, Anomaly, Failure, Error).
NameThe service name and namespace, derived from OTel resource attributes.
TechnologyThe detected technology or language, inferred from telemetry.sdk.language.
Latency P95The 95th percentile request latency with a sparkline trend.
Error Ratio %The percentage of requests resulting in errors with a sparkline trend.
Request RateRequests per second with a sparkline trend.

Insight rings

Each service displays colored insight rings based on the knowledge graph’s insight categories:

  • Saturation: resource utilization approaching limits
  • Amend: configuration changes detected
  • Anomaly: unusual behavior patterns
  • Failure: service failures
  • Error: elevated error rates

For details on how insights work, refer to the knowledge graph insights documentation.

RED metrics

The RED method (Rate, Errors, Duration) provides a consistent framework for monitoring request-driven services:

  • Rate: the number of requests per second the service handles.
  • Errors: the percentage of requests that fail.
  • Duration: the time it takes to process a request (shown as P95 latency).

These metrics are generated from span metrics. For details on how they’re produced, refer to Set up instrumentation.

Next steps