---
title: "Performance view | Grafana Cloud documentation"
description: "Monitor service performance with RED metrics, insight rings, and sparkline visualizations."
---

> For a curated documentation index, see [llms.txt](/llms.txt). For the complete documentation index, see [llms-full.txt](/llms-full.txt).

# 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:

Expand table

| Column        | Description                                                                                                            |
|---------------|------------------------------------------------------------------------------------------------------------------------|
| Insights      | Colored rings indicating active knowledge graph insights for the service (Saturation, Amend, Anomaly, Failure, Error). |
| Name          | The service name and namespace, derived from OTel resource attributes.                                                 |
| Technology    | The detected technology or language, inferred from `telemetry.sdk.language`.                                           |
| Latency P95   | The 95th percentile request latency with a sparkline trend.                                                            |
| Error Ratio % | The percentage of requests resulting in errors with a sparkline trend.                                                 |
| Request Rate  | Requests 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](/docs/grafana-cloud/knowledge-graph/introduction/insights/).

## 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](/docs/grafana-cloud/observe-and-act/monitor-applications/application-observability-kg/setup/instrumentation/).

## Next steps

- Click a service name to open its [service detail page](/docs/grafana-cloud/observe-and-act/monitor-applications/application-observability-kg/service-detail/).
- Switch to the [Instrumentation quality](/docs/grafana-cloud/observe-and-act/monitor-applications/application-observability-kg/services/instrumentation-quality/) tab to assess data coverage.