Update OpenCensus to OpenTelemetry

Change is meant to be transparent to user.

Using OTel SDK for metric composing in: kmetrics, core metrics, resource
group metrics;

Using otlp receiver in otel-agent and otel-collector;

Configured deployment for new ports and component;

Refactor metric composing and recording;

Metric prefix remain the same to minimize breaking change.

Tests updated.

Author: tiffanny29631

cmd/hydration-controller/main.go

@@ -79,19 +79,19 @@ func main() {
 	profiler.Service()
 	ctrl.SetLogger(textlogger.NewLogger(textlogger.NewConfig()))
 
-	// Register the kustomize usage metric views.
-	if err := kmetrics.RegisterKustomizeMetricsViews(); err != nil {
-		klog.Fatalf("Failed to register OpenCensus views: %v", err)
+	// Initialize the kustomize metrics
+	if err := kmetrics.InitializeOTelKustomizeMetrics(); err != nil {
+		klog.Fatalf("Failed to initialize kustomize metrics: %v", err)
 	}
 
 	// Register the OC Agent exporter
-	oce, err := kmetrics.RegisterOCAgentExporter(reconcilermanager.HydrationController)
+	oce, err := kmetrics.RegisterOTelExporter(reconcilermanager.HydrationController)
 	if err != nil {
 		klog.Fatalf("Failed to register the OC Agent exporter: %v", err)
 	}
 
 	defer func() {
-		if err := oce.Stop(); err != nil {
+		if err := oce.Shutdown(context.Background()); err != nil {
 			klog.Fatalf("Unable to stop the OC Agent exporter: %v", err)
 		}
 	}()

cmd/reconciler-manager/main.go

@@ -182,20 +182,20 @@ func main() {
 	}
 	setupLog.Info("OtelSA controller registration successful")
 
-	// Register the OpenCensus views
-	if err := metrics.RegisterReconcilerManagerMetricsViews(); err != nil {
-		setupLog.Error(err, "failed to register OpenCensus views")
+	// Initialize the metrics
+	if err := metrics.InitializeOTelMetrics(); err != nil {
+		setupLog.Error(err, "failed to initialize metrics")
 	}
 
 	// Register the OC Agent exporter
-	oce, err := metrics.RegisterOCAgentExporter(reconcilermanager.ManagerName)
+	oce, err := metrics.RegisterOTelExporter(reconcilermanager.ManagerName)
 	if err != nil {
 		setupLog.Error(err, "failed to register the OC Agent exporter")
 		os.Exit(1)
 	}
 
 	defer func() {
-		if err := oce.Stop(); err != nil {
+		if err := oce.Shutdown(context.Background()); err != nil {
 			setupLog.Error(err, "failed to stop the OC Agent exporter")
 		}
 	}()
@@ -206,7 +206,7 @@ func main() {
 	if err := mgr.Start(ctrl.SetupSignalHandler()); err != nil {
 		setupLog.Error(err, "problem running manager")
 		// os.Exit(1) does not run deferred functions so explicitly stopping the OC Agent exporter.
-		if err := oce.Stop(); err != nil {
+		if err := oce.Shutdown(context.Background()); err != nil {
 			setupLog.Error(err, "failed to stop the OC Agent exporter")
 		}
 		os.Exit(1)

cmd/reconciler/main.go

@@ -15,6 +15,7 @@
 package main
 
 import (
+	"context"
 	"flag"
 	"fmt"
 	"os"
@@ -140,19 +141,19 @@ func main() {
 		status.EnablePanicOnMisuse()
 	}
 
-	// Register the OpenCensus views
-	if err := ocmetrics.RegisterReconcilerMetricsViews(); err != nil {
-		klog.Fatalf("Failed to register OpenCensus views: %v", err)
+	// Initialize the metrics
+	if err := ocmetrics.InitializeOTelMetrics(); err != nil {
+		klog.Fatalf("Failed to initialize metrics: %v", err)
 	}
 
 	// Register the OC Agent exporter
-	oce, err := ocmetrics.RegisterOCAgentExporter(reconcilermanager.Reconciler)
+	oce, err := ocmetrics.RegisterOTelExporter(reconcilermanager.Reconciler)
 	if err != nil {
 		klog.Fatalf("Failed to register the OC Agent exporter: %v", err)
 	}
 
 	defer func() {
-		if err := oce.Stop(); err != nil {
+		if err := oce.Shutdown(context.Background()); err != nil {
 			klog.Fatalf("Unable to stop the OC Agent exporter: %v", err)
 		}
 	}()

docs/custom-metric-filter.md

@@ -171,7 +171,7 @@ To **turn off the custom metrics** in Cloud Monitoring, remove this section:
 ```yaml
 # Remove this entire section
 metrics/cloudmonitoring:
-  receivers: [opencensus]
+  receivers: [otlp]
   processors: [batch, filter/cloudmonitoring, metricstransform/cloudmonitoring, resourcedetection]
   exporters: [googlecloud]
 ```
@@ -183,7 +183,7 @@ To **turn off the report to Cloud Monarch**, remove this section:
 ```yaml
 # Remove this entire section
 metrics/kubernetes:
-  receivers: [opencensus]
+  receivers: [otlp]
   processors: [batch, filter/kubernetes, metricstransform/kubernetes, resourcedetection]
   exporters: [googlecloud/kubernetes]
 ```
@@ -235,7 +235,12 @@ metadata:
 data:
   otel-collector-config.yaml: |
     receivers:
-      opencensus:
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
     exporters:
       debug:
         verbosity: detailed
@@ -245,7 +250,7 @@ data:
       batch:
       pipelines:
         metrics:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch]
           exporters: [debug]
 ```

e2e/nomostest/prometheus_metrics.go

@@ -150,13 +150,12 @@ func TestOtelCollectorDeployment(t *testing.T) {
 	nt.Must(rootSyncGitRepo.CommitAndPush("Adding foo namespace"))
 	nt.Must(nt.WatchForAllSyncs())
 
-	nt.T.Log("Watch for metrics in GCM, timeout 2 minutes")
+	nt.T.Log("Watch for default metrics in GCM")
 	ctx := nt.Context
 	client, err := createGCMClient(ctx)
 	if err != nil {
 		nt.T.Fatal(err)
 	}
-	// retry for 2 minutes until metric is accessible from GCM
 	nt.Must(validateMetricTypes(ctx, nt, client, startTime, DefaultGCMMetricTypes))
 
 	nt.T.Log("Checking the otel-collector log contains no failure...")
@@ -237,10 +236,10 @@ func TestGCMMetrics(t *testing.T) {
 
 	nt.T.Log("Apply custom otel-collector ConfigMap that exports full metric list to GCM")
 	nt.MustKubectl("apply", "-f", "../testdata/otel-collector/otel-cm-full-gcm.yaml")
+	nt.Must(nt.Watcher.WatchForCurrentStatus(kinds.Deployment(), csmetrics.OtelCollectorName, configmanagement.MonitoringNamespace))
 
 	startTime := time.Now().UTC()
 
-	nt.T.Log("Watch for full list of metrics in GCM, timeout 2 minutes")
 	ctx := nt.Context
 	client, err := createGCMClient(ctx)
 	if err != nil {
@@ -308,7 +307,7 @@ func TestOtelCollectorGCMLabelAggregation(t *testing.T) {
 		nt.T.Fatal(err)
 	}
 	// retry for 2 minutes until metric is accessible from GCM
-	nt.Must(validateMetricTypes(ctx, nt, client, startTime, metricsWithCommitLabel, metricDoesNotHaveLabel(metrics.KeyCommit.Name())))
+	nt.Must(validateMetricTypes(ctx, nt, client, startTime, metricsWithCommitLabel, metricDoesNotHaveLabel(string(metrics.KeyCommit))))
 }
 
 func setupMetricsServiceAccount(nt *nomostest.NT) {

e2e/testcases/otel_collector_test.go

@@ -16,8 +16,12 @@ apiVersion: v1
 data:
   otel-collector-config.yaml: |-
     receivers:
-      opencensus:
-        endpoint: 0.0.0.0:55678
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
     exporters:
       prometheus:
         endpoint: 0.0.0.0:8675
@@ -71,10 +75,6 @@ data:
           enabled: false
     processors:
       batch:
-      # resourcedetection: This processor is needed to correctly mirror resource
-      # labels from OpenCensus to OpenTelemetry. We also want to keep this same
-      # processor in Otel Agent configuration as the resource labels are added from
-      # there
       resourcedetection:
         detectors: [env, gcp]
       # Aggregate some metrics sent to Cloud Monitoring to remove high-cardinality labels (e.g. "commit")
@@ -309,15 +309,15 @@ data:
       extensions: [health_check]
       pipelines:
         metrics/cloudmonitoring:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/cloudmonitoring, metricstransform/cloudmonitoring, resourcedetection]
           exporters: [googlecloud]
         metrics/prometheus:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch]
           exporters: [prometheus]
         metrics/kubernetes:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/kubernetes, metricstransform/kubernetes, resourcedetection]
           exporters: [googlecloud/kubernetes]
 kind: ConfigMap

e2e/testdata/otel-collector/otel-cm-full-gcm.yaml

@@ -20,8 +20,12 @@ apiVersion: v1
 data:
   otel-collector-config.yaml: |-
     receivers:
-      opencensus:
-        endpoint: 0.0.0.0:55678
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
     exporters:
       prometheus:
         endpoint: 0.0.0.0:8675
@@ -75,10 +79,6 @@ data:
           enabled: false
     processors:
       batch:
-      # resourcedetection: This processor is needed to correctly mirror resource
-      # labels from OpenCensus to OpenTelemetry. We also want to keep this same
-      # processor in Otel Agent configuration as the resource labels are added from
-      # there
       resourcedetection:
         detectors: [env, gcp]
       filter/cloudmonitoring:
@@ -264,15 +264,15 @@ data:
       extensions: [health_check]
       pipelines:
         metrics/cloudmonitoring:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/cloudmonitoring, metricstransform/cloudmonitoring, resourcedetection]
           exporters: [googlecloud]
         metrics/prometheus:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch]
           exporters: [prometheus]
         metrics/kubernetes:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/kubernetes, metricstransform/kubernetes, resourcedetection]
           exporters: [googlecloud/kubernetes]
 kind: ConfigMap

e2e/testdata/otel-collector/otel-cm-kustomize-rejected-labels.yaml

@@ -20,8 +20,12 @@ apiVersion: v1
 data:
   otel-collector-config.yaml: |-
     receivers:
-      opencensus:
-        endpoint: 0.0.0.0:55678
+      otlp:
+        protocols:
+          grpc:
+            endpoint: 0.0.0.0:4317
+          http:
+            endpoint: 0.0.0.0:4318
     exporters:
       prometheus:
         endpoint: 0.0.0.0:8675
@@ -75,10 +79,6 @@ data:
           enabled: false
     processors:
       batch:
-      # resourcedetection: This processor is needed to correctly mirror resource
-      # labels from OpenCensus to OpenTelemetry. We also want to keep this same
-      # processor in Otel Agent configuration as the resource labels are added from
-      # there
       resourcedetection:
         detectors: [env, gcp]
       filter/cloudmonitoring:
@@ -173,15 +173,15 @@ data:
       extensions: [health_check]
       pipelines:
         metrics/cloudmonitoring:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/cloudmonitoring, resourcedetection]
           exporters: [googlecloud]
         metrics/prometheus:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch]
           exporters: [prometheus]
         metrics/kubernetes:
-          receivers: [opencensus]
+          receivers: [otlp]
           processors: [batch, filter/kubernetes, metricstransform/kubernetes, resourcedetection]
           exporters: [googlecloud/kubernetes]
 kind: ConfigMap

e2e/testdata/otel-collector/otel-cm-monarch-rejected-labels.yaml

@@ -8,7 +8,6 @@ require (
 	cloud.google.com/go/logging v1.13.0
 	cloud.google.com/go/monitoring v1.24.3
 	cloud.google.com/go/trace v1.11.7
-	contrib.go.opencensus.io/exporter/ocagent v0.7.0
 	github.com/GoogleContainerTools/kpt-functions-catalog/functions/go/set-namespace v0.4.1-0.20220713210718-d955e7d3a800
 	github.com/GoogleContainerTools/kpt-functions-sdk/go/fn v0.0.0-20220706221933-7181f451a663
 	github.com/Masterminds/semver v1.5.0
@@ -33,7 +32,11 @@ require (
 	github.com/spf13/cobra v1.10.1
 	github.com/spyzhov/ajson v0.9.6
 	github.com/stretchr/testify v1.11.1
-	go.opencensus.io v0.24.0
+	go.opentelemetry.io/otel v1.38.0
+	go.opentelemetry.io/otel/exporters/otlp/otlpmetric/otlpmetricgrpc v1.38.0
+	go.opentelemetry.io/otel/metric v1.38.0
+	go.opentelemetry.io/otel/sdk v1.38.0
+	go.opentelemetry.io/otel/sdk/metric v1.38.0
 	go.uber.org/multierr v1.11.0
 	go.uber.org/zap v1.27.0
 	golang.org/x/exp v0.0.0-20241217172543-b2144cdd0a67
@@ -76,7 +79,7 @@ require (
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/blang/semver/v4 v4.0.0 // indirect
 	github.com/bmatcuk/doublestar/v4 v4.0.2 // indirect
-	github.com/census-instrumentation/opencensus-proto v0.4.1 // indirect
+	github.com/cenkalti/backoff/v5 v5.0.3 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
 	github.com/chai2010/gettext-go v1.0.2 // indirect
 	github.com/containerd/stargz-snapshotter/estargz v0.16.3 // indirect
@@ -108,7 +111,7 @@ require (
 	github.com/googleapis/gax-go/v2 v2.15.0 // indirect
 	github.com/gorilla/websocket v1.5.4-0.20250319132907-e064f32e3674 // indirect
 	github.com/gregjones/httpcache v0.0.0-20190611155906-901d90724c79 // indirect
-	github.com/grpc-ecosystem/grpc-gateway/v2 v2.26.3 // indirect
+	github.com/grpc-ecosystem/grpc-gateway/v2 v2.27.2 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
 	github.com/jonboulle/clockwork v0.5.0 // indirect
 	github.com/josharian/intern v1.0.0 // indirect
@@ -145,12 +148,12 @@ require (
 	github.com/vbatts/tar-split v0.12.1 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
 	github.com/xlab/treeprint v1.2.0 // indirect
+	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/auto/sdk v1.1.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.61.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 // indirect
-	go.opentelemetry.io/otel v1.37.0 // indirect
-	go.opentelemetry.io/otel/metric v1.37.0 // indirect
-	go.opentelemetry.io/otel/trace v1.37.0 // indirect
+	go.opentelemetry.io/otel/trace v1.38.0 // indirect
+	go.opentelemetry.io/proto/otlp v1.7.1 // indirect
 	go.uber.org/atomic v1.11.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
 	go.yaml.in/yaml/v3 v3.0.4 // indirect
@@ -166,7 +169,7 @@ require (
 	golang.org/x/tools/go/packages/packagestest v0.1.1-deprecated // indirect
 	gomodules.xyz/jsonpatch/v2 v2.4.0 // indirect
 	google.golang.org/genproto v0.0.0-20250603155806-513f23925822 // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20250818200422-3122310a409c // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20250825161204-c5933d9347a5 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20251002232023-7c0ddcbb5797 // indirect
 	google.golang.org/grpc v1.75.1 // indirect
 	google.golang.org/protobuf v1.36.10 // indirect