zitadel/internal/telemetry/http_handler.go

35 lines
879 B
Go
Raw Permalink Normal View History

package telemetry
import (
"net/http"
"strings"
"go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp"
"github.com/zitadel/zitadel/internal/telemetry/metrics"
)
func shouldNotIgnore(endpoints ...string) func(r *http.Request) bool {
return func(r *http.Request) bool {
for _, endpoint := range endpoints {
if strings.HasPrefix(r.URL.RequestURI(), endpoint) {
return false
}
}
return true
}
}
func TelemetryHandler(handler http.Handler, ignoredEndpoints ...string) http.Handler {
return otelhttp.NewHandler(handler,
"zitadel",
otelhttp.WithFilter(shouldNotIgnore(ignoredEndpoints...)),
otelhttp.WithPublicEndpoint(),
otelhttp.WithSpanNameFormatter(spanNameFormatter),
otelhttp.WithMeterProvider(metrics.GetMetricsProvider()))
}
func spanNameFormatter(_ string, r *http.Request) string {
fix(OTEL): reduce high cardinality in traces and metrics (#9286) # Which Problems Are Solved There were multiple issues in the OpenTelemetry (OTEL) implementation and usage for tracing and metrics, which lead to high cardinality and potential memory leaks: - wrongly initiated tracing interceptors - high cardinality in traces: - HTTP/1.1 endpoints containing host names - HTTP/1.1 endpoints containing object IDs like userID (e.g. `/management/v1/users/2352839823/`) - high amount of traces from internal processes (spooler) - high cardinality in metrics endpoint: - GRPC entries containing host names - notification metrics containing instanceIDs and error messages # How the Problems Are Solved - Properly initialize the interceptors once and update them to use the grpc stats handler (unary interceptors were deprecated). - Remove host names from HTTP/1.1 span names and use path as default. - Set / overwrite the uri for spans on the grpc-gateway with the uri pattern (`/management/v1/users/{user_id}`). This is used for spans in traces and metric entries. - Created a new sampler which will only sample spans in the following cases: - remote was already sampled - remote was not sampled, root span is of kind `Server` and based on fraction set in the runtime configuration - This will prevent having a lot of spans from the spooler back ground jobs if they were not started by a client call querying an object (e.g. UserByID). - Filter out host names and alike from OTEL generated metrics (using a `view`). - Removed instance and error messages from notification metrics. # Additional Changes Fixed the middleware handling for serving Console. Telemetry and instance selection are only used for the environment.json, but not on statically served files. # Additional Context - closes #8096 - relates to #9074 - back ports to at least 2.66.x, 2.67.x and 2.68.x
2025-02-04 09:55:26 +01:00
return strings.Split(r.RequestURI, "?")[0]
}