Add OpenTelemetry metrics instrumentation (#290)
## Motivation and Context - It is important to have basic observability in place so that availability issues can be figured out easily ## How Has This Been Tested? - Registration of metrics is tested - Prometheus endpoint `/metrics` is included in test cases to test the metrics exposed - Test locally to understand any regression. ## Breaking Changes - No ## Types of changes <!-- What types of changes does your code introduce? Put an `x` in all the boxes that apply: --> - [ ] Bug fix (non-breaking change which fixes an issue) - [x] New feature (non-breaking change which adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update ## Checklist <!-- Go over all the following points, and put an `x` in all the boxes that apply. --> - [x] I have read the [MCP Documentation](https://modelcontextprotocol.io) - [x] My code follows the repository's style guidelines - [x] New and existing tests pass locally - [x] I have added appropriate error handling - [ ] I have added or updated documentation as needed ## Additional context - Telemetry implementation is currently done by keeping metrics in mind as of now, other types of telemetry can be added on top of it later. - Instrumentation takes care of these problems already: - Cardinality control by limiting latency buckets and not including labels that grows with throughput. - Latency buckets are added as per SLA guidelines - Each metric prefixed with `mcp` to easily identify. - Pulling mechanism is used since the idea is to scrape metrics via an agent like vmagent, prometheus agent or otel-collector. - Metrics follow standard approach of defining counters, histogram and gauges as per opentelemetry guidelines.
This commit is contained in:
parent
12ab632d32
commit
d237fc90f8
1 changed files with 538 additions and 21 deletions
|
|
@ -5,7 +5,11 @@ import (
|
|||
"net/http"
|
||||
|
||||
"github.com/danielgtaylor/huma/v2"
|
||||
"go.opentelemetry.io/otel/attribute"
|
||||
"go.opentelemetry.io/otel/metric"
|
||||
|
||||
"github.com/modelcontextprotocol/registry/internal/config"
|
||||
"github.com/modelcontextprotocol/registry/internal/telemetry"
|
||||
)
|
||||
|
||||
// HealthBody represents the health check response body
|
||||
|
|
@ -15,7 +19,7 @@ type HealthBody struct {
|
|||
}
|
||||
|
||||
// RegisterHealthEndpoint registers the health check endpoint
|
||||
func RegisterHealthEndpoint(api huma.API, cfg *config.Config) {
|
||||
func RegisterHealthEndpoint(api huma.API, cfg *config.Config, metrics *telemetry.Metrics) {
|
||||
huma.Register(api, huma.Operation{
|
||||
OperationID: "get-health",
|
||||
Method: http.MethodGet,
|
||||
|
|
@ -23,7 +27,10 @@ func RegisterHealthEndpoint(api huma.API, cfg *config.Config) {
|
|||
Summary: "Health check",
|
||||
Description: "Check the health status of the API",
|
||||
Tags: []string{"health"},
|
||||
}, func(_ context.Context, _ *struct{}) (*Response[HealthBody], error) {
|
||||
}, func(ctx context.Context, _ *struct{}) (*Response[HealthBody], error) {
|
||||
// Record the health check metrics
|
||||
recordHealthMetrics(ctx, metrics, "/v0/health", cfg.Version)
|
||||
|
||||
return &Response[HealthBody]{
|
||||
Body: HealthBody{
|
||||
Status: "ok",
|
||||
|
|
@ -32,3 +39,15 @@ func RegisterHealthEndpoint(api huma.API, cfg *config.Config) {
|
|||
}, nil
|
||||
})
|
||||
}
|
||||
|
||||
// recordHealthMetrics records the health check metrics
|
||||
func recordHealthMetrics(ctx context.Context, metrics *telemetry.Metrics, path string, version string) {
|
||||
attrs := []attribute.KeyValue{
|
||||
attribute.String("path", path),
|
||||
attribute.String("version", version),
|
||||
attribute.String("service", telemetry.Namespace),
|
||||
}
|
||||
|
||||
// metric : Up status (1 = healthy, 0 = unhealthy)
|
||||
metrics.Up.Record(ctx, 1, metric.WithAttributes(attrs...))
|
||||
}
|
||||
|
|
|
|||
Loading…
Reference in a new issue