feat(metrics)!: use otel by default

.changelog/3284.breaking.txt

@@ -0,0 +1 @@
+feat(metrics)!: use otel by default

deploy/helm/sumologic/Chart.yaml

@@ -35,4 +35,4 @@ dependencies:
   - name: opentelemetry-operator
     version: 0.35.0
     repository: https://open-telemetry.github.io/opentelemetry-helm-charts
-    condition: opentelemetry-operator.enabled
+    condition: opentelemetry-operator.enabled,sumologic.metrics.collector.otelcol.enabled

deploy/helm/sumologic/values.yaml

@@ -441,9 +441,8 @@ sumologic:
     collector:
       ### Otel metrics collector. Replaces Prometheus.
       ## To enable, you need opentelemetry-operator enabled as well.
-      ## Stability: Beta.
       otelcol:
-        enabled: false
+        enabled: true
 
         ## Default scrape interval
         scrapeInterval: 30s
@@ -539,7 +538,7 @@ sumologic:
     ## This is an advanced feature, enable only if you're experiencing performance
     ## issues with metrics metadata enrichment.
     remoteWriteProxy:
-      enabled: true
+      enabled: false
       config:
         ## Increase this if you've increased samples_per_send in Prometheus to prevent nginx
         ## from spilling proxied request bodies to disk
@@ -946,6 +945,7 @@ kube-prometheus-stack:
     enabled: false
     defaultDashboardsEnabled: false
   prometheusOperator:
+    enabled: false
     ## Labels to add to the operator pod
     podLabels: {}
     ## Annotations to add to the operator pod
@@ -1101,6 +1101,7 @@ kube-prometheus-stack:
             regex: (?:node_load1|node_load5|node_load15|node_cpu_seconds_total|node_disk_io_time_weighted_seconds_total|node_disk_io_time_seconds_total|node_vmstat_pgpgin|node_vmstat_pgpgout|node_memory_MemFree_bytes|node_memory_Cached_bytes|node_memory_Buffers_bytes|node_memory_MemTotal_bytes|node_network_receive_drop_total|node_network_transmit_drop_total|node_network_receive_bytes_total|node_network_transmit_bytes_total|node_filesystem_avail_bytes|node_filesystem_size_bytes)
             sourceLabels: [__name__]
   prometheus:
+    enabled: false
     additionalServiceMonitors: []
     prometheusSpec:
       ## Prometheus default scrape interval, default from upstream Kube Prometheus Stack Helm chart
@@ -2373,7 +2374,7 @@ tailing-sidecar-operator:
 ## Configure OpenTelemetry Operator - Instrumentation
 ## ref: https://github.com/open-telemetry/opentelemetry-helm-charts/tree/main/charts/opentelemetry-operator
 opentelemetry-operator:
-  enabled: false
+  enabled: true
 
   ## Specific for Sumo Logic chart - Instrumentation resource creation
   instrumentationJobImage:

tests/helm/prometheus_test.go

@@ -24,6 +24,7 @@ func TestServiceMonitors(t *testing.T) {
 			ValuesYaml: `
 kube-prometheus-stack:
   prometheus:
+    enabled: true
     additionalServiceMonitors:
       - name: collection-sumologic-fluentd-logs-test
         additionalLabels:
@@ -55,6 +56,7 @@ kube-prometheus-stack:
 			ValuesYaml: `
 kube-prometheus-stack:
   prometheus:
+    enabled: true
     additionalServiceMonitors:
       - name: collection-sumologic-fluentd-logs-test
         additionalLabels:

tests/helm/testdata/goldenfile/metrics_collector_otc/basic.input.yaml

@@ -1,6 +0,0 @@
-sumologic:
-  metrics:
-    enabled: true
-    collector:
-      otelcol:
-        enabled: true

tests/helm/testdata/goldenfile/metrics_collector_otc/custom.input.yaml

@@ -1,9 +1,7 @@
 sumologic:
   metrics:
-    enabled: true
     collector:
       otelcol:
-        enabled: true
         scrapeInterval: 60s
         autoscaling:
           enabled: true

tests/helm/utils.go

@@ -17,6 +17,7 @@ import (
 	"github.com/gruntwork-io/go-commons/files"
 	"github.com/gruntwork-io/terratest/modules/helm"
 	"github.com/gruntwork-io/terratest/modules/logger"
+	otoperator "github.com/open-telemetry/opentelemetry-operator/apis/v1alpha1"
 	prometheus "github.com/prometheus-operator/prometheus-operator/pkg/apis/monitoring/v1"
 	"github.com/stretchr/testify/require"
 	"gopkg.in/yaml.v3"
@@ -123,6 +124,11 @@ func UnmarshalMultipleK8sObjectsFromYaml(yamlDocs string) (objects []runtime.Obj
 		return objects, err
 	}
 
+	err = otoperator.AddToScheme(scheme)
+	if err != nil {
+		return objects, err
+	}
+
 	decoder := serializer.NewCodecFactory(scheme).UniversalDeserializer()
 	multidocReader := utilyaml.NewYAMLReader(bufio.NewReader(bytes.NewReader([]byte(yamlDocs))))
 

tests/integration/helm_ot_default_namespaceoverride_test.go

@@ -17,7 +17,14 @@ type ctxKey string
 
 func Test_Helm_Default_OT_NamespaceOverride(t *testing.T) {
 
-	expectedMetrics := internal.DefaultExpectedMetrics
+	expectedMetrics := []string{}
+	// defaults without otel metrics collector metrics, but with Prometheus metrics
+	expectedMetricsGroups := make([][]string, len(internal.DefaultExpectedMetricsGroups))
+	copy(expectedMetricsGroups, internal.DefaultExpectedMetricsGroups)
+	expectedMetricsGroups = append(expectedMetricsGroups, internal.PrometheusMetrics, internal.DefaultOtelcolMetrics)
+	for _, metrics := range expectedMetricsGroups {
+		expectedMetrics = append(expectedMetrics, metrics...)
+	}
 	// we have tracing enabled, so check tracing-specific metrics
 	expectedMetrics = append(expectedMetrics, internal.TracingOtelcolMetrics...)
 
@@ -26,7 +33,7 @@ func Test_Helm_Default_OT_NamespaceOverride(t *testing.T) {
 		CheckOtelcolMetadataLogsInstall,
 		CheckOtelcolMetadataMetricsInstall,
 		CheckOtelcolEventsInstall,
-		CheckPrometheusInstall,
+		CheckOtelcolMetricsCollectorInstall,
 		CheckOtelcolLogsCollectorInstall,
 		CheckTracesInstall,
 	}

tests/integration/helm_ot_default_test.go

@@ -20,16 +20,16 @@ func Test_Helm_Default_OT(t *testing.T) {
 		CheckOtelcolMetadataLogsInstall,
 		CheckOtelcolMetadataMetricsInstall,
 		CheckOtelcolEventsInstall,
-		CheckPrometheusInstall,
+		CheckOtelcolMetricsCollectorInstall,
 		CheckOtelcolLogsCollectorInstall,
 		CheckTracesInstall,
 	}
 
 	featInstall := GetInstallFeature(installChecks)
 
-	featMetrics := GetMetricsFeature(expectedMetrics, Prometheus)
+	featMetrics := GetMetricsFeature(expectedMetrics, Otelcol)
 
-	featTelegrafMetrics := GetTelegrafMetricsFeature(internal.DefaultExpectedNginxAnnotatedMetrics, Prometheus, true)
+	featTelegrafMetrics := GetTelegrafMetricsFeature(internal.DefaultExpectedNginxAnnotatedMetrics, Otelcol, true)
 
 	featLogs := GetLogsFeature()
 

tests/integration/helm_otc_fips_metadata_installation_test.go

@@ -20,14 +20,16 @@ func Test_Helm_Default_OT_FIPS(t *testing.T) {
 		CheckOtelcolMetadataLogsInstall,
 		CheckOtelcolMetadataMetricsInstall,
 		CheckOtelcolEventsInstall,
-		CheckPrometheusInstall,
+		CheckOtelcolMetricsCollectorInstall,
 		CheckOtelcolLogsCollectorInstall,
 		CheckTracesInstall,
 	}
 
 	featInstall := GetInstallFeature(installChecks)
 
-	featMetrics := GetMetricsFeature(expectedMetrics, Prometheus)
+	featMetrics := GetMetricsFeature(expectedMetrics, Otelcol)
+
+	featTelegrafMetrics := GetTelegrafMetricsFeature(internal.DefaultExpectedNginxAnnotatedMetrics, Otelcol, true)
 
 	featLogs := GetLogsFeature()
 
@@ -37,5 +39,5 @@ func Test_Helm_Default_OT_FIPS(t *testing.T) {
 
 	featTraces := GetTracesFeature()
 
-	testenv.Test(t, featInstall, featMetrics, featLogs, featMultilineLogs, featEvents, featTraces)
+	testenv.Test(t, featInstall, featMetrics, featTelegrafMetrics, featLogs, featMultilineLogs, featEvents, featTraces)
 }

tests/integration/helm_otlp_test.go

@@ -10,7 +10,6 @@ import (
 )
 
 func Test_Helm_OTLP(t *testing.T) {
-
 	expectedMetrics := internal.DefaultExpectedMetrics
 	// we have tracing enabled, so check tracing-specific metrics
 	expectedMetrics = append(expectedMetrics, internal.TracingOtelcolMetrics...)
@@ -27,13 +26,17 @@ func Test_Helm_OTLP(t *testing.T) {
 
 	featInstall := GetInstallFeature(installChecks)
 
-	featLogs := GetLogsFeature()
-
 	featMetrics := GetMetricsFeature(expectedMetrics, Prometheus)
 
-	featTraces := GetTracesFeature()
+	featTelegrafMetrics := GetTelegrafMetricsFeature(internal.DefaultExpectedNginxAnnotatedMetrics, Prometheus, true)
+
+	featLogs := GetLogsFeature()
+
+	featMultilineLogs := GetMultipleMultilineLogsFeature()
 
 	featEvents := GetEventsFeature()
 
-	testenv.Test(t, featInstall, featLogs, featMetrics, featEvents, featTraces)
+	featTraces := GetTracesFeature()
+
+	testenv.Test(t, featInstall, featMetrics, featTelegrafMetrics, featLogs, featMultilineLogs, featEvents, featTraces)
 }

tests/integration/helm_prometheus_metrics_test.go

@@ -0,0 +1,35 @@
+//go:build onlylatest
+// +build onlylatest
+
+package integration
+
+import (
+	"testing"
+
+	"github.com/SumoLogic/sumologic-kubernetes-collection/tests/integration/internal"
+)
+
+func Test_Helm_Prometheus_Metrics(t *testing.T) {
+	expectedMetrics := []string{}
+	// defaults without otel metrics collector metrics, but with Prometheus metrics
+	expectedMetricsGroups := make([][]string, len(internal.DefaultExpectedMetricsGroups))
+	copy(expectedMetricsGroups, internal.DefaultExpectedMetricsGroups)
+	expectedMetricsGroups = append(expectedMetricsGroups, internal.PrometheusMetrics, internal.DefaultOtelcolMetrics)
+	for _, metrics := range expectedMetricsGroups {
+		expectedMetrics = append(expectedMetrics, metrics...)
+	}
+
+	installChecks := []featureCheck{
+		CheckSumologicSecret(9),
+		CheckOtelcolMetadataMetricsInstall,
+		CheckPrometheusInstall,
+	}
+
+	featInstall := GetInstallFeature(installChecks)
+
+	featMetrics := GetMetricsFeature(expectedMetrics, Prometheus)
+
+	featTelegrafMetrics := GetTelegrafMetricsFeature(internal.DefaultExpectedNginxAnnotatedMetrics, Prometheus, true)
+
+	testenv.Test(t, featInstall, featMetrics, featTelegrafMetrics)
+}

tests/integration/internal/constants.go

@@ -339,7 +339,6 @@ var (
 		CoreDNSMetrics,
 		CAdvisorMetrics,
 		NodeExporterMetrics,
-		PrometheusMetrics,
 		OtherMetrics,
 	}
 	DefaultExpectedNginxAnnotatedMetricsGroups = [][]string{
@@ -372,7 +371,7 @@ func InitializeConstants() error {
 	}
 
 	DefaultExpectedMetrics = []string{}
-	metricsGroupsWithOtelcol := append(DefaultExpectedMetricsGroups, DefaultOtelcolMetrics, LogsOtelcolMetrics)
+	metricsGroupsWithOtelcol := append(DefaultExpectedMetricsGroups, DefaultOtelcolMetrics, LogsOtelcolMetrics, MetricsCollectorOtelcolMetrics)
 	for _, metrics := range metricsGroupsWithOtelcol {
 		DefaultExpectedMetrics = append(DefaultExpectedMetrics, metrics...)
 	}

tests/integration/values/values_common.yaml

@@ -12,6 +12,13 @@ sumologic:
   endpoint: http://receiver-mock.receiver-mock:3000/terraform/api/
 
   metrics:
+    collector:
+      otelcol:
+        scrapeInterval: 15s
+        resources:
+          requests:
+            memory: 128Mi
+            cpu: 50m
     remoteWriteProxy:
       resources:
         requests:
@@ -132,6 +139,7 @@ otellogs:
         name: run-log-journal
 
 telegraf-operator:
+  enabled: true
   resources:
     requests:
       cpu: 5m

tests/integration/values/values_helm_default_ot.yaml

@@ -1,5 +1,3 @@
-telegraf-operator:
-  enabled: true
 metadata:
   logs:
     multiline:

tests/integration/values/values_helm_default_ot_namespaceoverride.yaml

@@ -1,3 +1,4 @@
+# This file uses Prometheus metrics, as the opentelemetry-operator Helm Chart doesn't support namespaceOverride
 namespaceOverride: "test-override"
 
 kube-prometheus-stack:
@@ -8,3 +9,14 @@ kube-prometheus-stack:
 
   prometheus-node-exporter:
     namespaceOverride: "test-override"
+
+  prometheus:
+    enabled: true
+  prometheusOperator:
+    enabled: true
+
+sumologic:
+  metrics:
+    collector:
+      otelcol:
+        enabled: false

tests/integration/values/values_helm_prometheus_metrics.yaml

@@ -0,0 +1,18 @@
+sumologic:
+  logs:
+    enabled: false
+  traces:
+    enabled: false
+  events:
+    enabled: false
+  metrics:
+    enabled: true
+    collector:
+      otelcol:
+        enabled: false
+
+kube-prometheus-stack:
+  prometheus:
+    enabled: true
+  prometheusOperator:
+    enabled: true