> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nvcf/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nvcf/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nvcf/_mcp/server.

# Metrics Overview

Per-service metrics reference for the NVCF self-hosted control plane. Each linked page lists metric names, types, sources, descriptions, and the labels and filters that make the metric useful in queries and dashboards.

## Control plane services

- [NVCF API](/nvcf/nvcf-api): request rates, response status codes, and log event counts for the NVCF API service.
- [Invocation Service](/nvcf/invocation-service): HTTP request counts, durations, and invocation error metrics for the invocation path.
- [ESS](/nvcf/ess): template rendering counters and HTTP client metrics for the Encrypted Secrets Service.
- [State Metrics Service](/nvcf/state-metrics): per-function instance count, stage durations, request latency, and function metadata.
- [SIS/Spot](/nvcf/sis-spot): HTTP client metrics for the Spot Instance Service.
- [Function Autoscaler](/nvcf/autoscaler-observability): OpenTelemetry metrics emitted by the function autoscaler service.

## LLM services

- [LLM API Gateway](/nvcf/llm-api-gateway): request and routing metrics for the LLM API gateway.
- [LLM Function Invocation Metrics Report](/nvcf/llm-function-invocation-metrics-report): end-to-end LLM invocation path report.
- [LLM Request Router](/nvcf/llm-request-router): request router metrics for LLM traffic.

## Per-function containers

- [Init Container](/nvcf/init-container): restart counts and termination reasons for function init containers.
- [Utils Container](/nvcf/utils-container): restart counts, termination reasons, and worker service response metrics for function utils containers.

## Datastores

- [Cassandra](/nvcf/cassandra): client request latency, timeouts, authentication failures, and endpoint connection metrics.
- [Vault/OpenBao](/nvcf/vault-open-bao): pointer to upstream OpenBao telemetry documentation.

## See also

- [Observability](/nvcf/observability) for logging, tracing, and overall observability configuration.
- [Example Dashboards](/nvcf/example-dashboards) for reference Grafana dashboards.