feat: add option for adding k8s.cluster.name resource attribute

api/dash0monitoring/v1alpha1/operator_configuration_types.go

@@ -37,6 +37,12 @@ type Dash0OperatorConfigurationSpec struct {
 	//
 	// +kubebuilder:default=true
 	KubernetesInfrastructureMetricsCollectionEnabled *bool `json:"kubernetesInfrastructureMetricsCollectionEnabled,omitempty"`
+
+	// If set, the value will be added as the resource attribute k8s.cluster.name to all telemetry. This setting is
+	// optional. By default, k8s.cluster.name will not be added to telemetry.
+	//
+	// +kubebuilder:validation:Optional
+	ClusterName string `json:"clusterName,omitempty"`
 }
 
 // SelfMonitoring describes how the operator will report telemetry about its working to the backend.

cmd/main.go

@@ -128,6 +128,7 @@ func main() {
 	var operatorConfigurationApiEndpoint string
 	var operatorConfigurationSelfMonitoringEnabled bool
 	var operatorConfigurationKubernetesInfrastructureMetricsCollectionEnabled bool
+	var operatorConfigurationClusterName string
 	var isUninstrumentAll bool
 	var metricsAddr string
 	var enableLeaderElection bool
@@ -194,6 +195,13 @@ func main() {
 		true,
 		"Whether to set kubernetesInfrastructureMetricsCollectionEnabled on the operator configuration resource; "+
 			"will be ignored if operator-configuration-endpoint is not set.")
+	flag.StringVar(
+		&operatorConfigurationClusterName,
+		"operator-configuration-cluster-name",
+		"",
+		"The clusterName to set on the operator configuration resource; will be ignored if"+
+			"operator-configuration-endpoint is not set. If set, the value will be added as the resource attribute "+
+			"k8s.cluster.name to all telemetry.")
 	flag.StringVar(
 		&metricsAddr,
 		"metrics-bind-address",
@@ -309,6 +317,7 @@ func main() {
 			SelfMonitoringEnabled: operatorConfigurationSelfMonitoringEnabled,
 			//nolint:lll
 			KubernetesInfrastructureMetricsCollectionEnabled: operatorConfigurationKubernetesInfrastructureMetricsCollectionEnabled,
+			ClusterName: operatorConfigurationClusterName,
 		}
 		if len(operatorConfigurationApiEndpoint) > 0 {
 			operatorConfiguration.ApiEndpoint = operatorConfigurationApiEndpoint

config/crd/bases/operator.dash0.com_dash0operatorconfigurations.yaml

@@ -41,6 +41,11 @@ spec:
             description: Dash0OperatorConfigurationSpec describes cluster-wide configuration
               settings for the Dash0 operator.
             properties:
+              clusterName:
+                description: |-
+                  If set, the value will be added as the resource attribute k8s.cluster.name to all telemetry. This setting is
+                  optional. By default, k8s.cluster.name will not be added to telemetry.
+                type: string
               export:
                 description: |-
                   The configuration of the default observability backend to which telemetry data will be sent by the operator, as

helm-chart/dash0-operator/README.md

@@ -71,6 +71,7 @@ helm install \
   --set operator.dash0Export.endpoint=REPLACE THIS WITH YOUR DASH0 INGRESS ENDPOINT \
   --set operator.dash0Export.apiEndpoint=REPLACE THIS WITH YOUR DASH0 API ENDPOINT \
   --set operator.dash0Export.token=REPLACE THIS WITH YOUR DASH0 AUTH TOKEN \
+  --set operator.clusterName=REPLACE THIS WITH YOUR THE NAME OF THE CLUSTER (OPTIONAL) \
   dash0-operator \
   dash0-operator/dash0-operator
 ```
@@ -86,6 +87,7 @@ helm install \
   --set operator.dash0Export.apiEndpoint=REPLACE THIS WITH YOUR DASH0 API ENDPOINT \
   --set operator.dash0Export.secretRef.name=REPLACE THIS WITH THE NAME OF AN EXISTING KUBERNETES SECRET \
   --set operator.dash0Export.secretRef.key=REPLACE THIS WITH THE PROPERTY KEY IN THAT SECRET \
+  --set operator.clusterName=REPLACE THIS WITH YOUR THE NAME OF THE CLUSTER (OPTIONAL) \
   dash0-operator \
   dash0-operator/dash0-operator
 ```
@@ -116,7 +118,7 @@ That is, providing `--set operator.dash0Export.enabled=true` and the other backe
 On its own, the operator will not do much.
 To actually have the operator monitor your cluster, two more things need to be set up:
 1. a [Dash0 backend connection](#configuring-the-dash0-backend-connection) has to be configured and
-2. monitoring workloads has to be [enabled per namespace](#enable-dash0-monitoring-for-a-namespace).
+2. monitoring workloads and collecting metrics has to be [enabled per namespace](#enable-dash0-monitoring-for-a-namespace).
 
 Both steps are described in the following sections.
 
@@ -147,6 +149,8 @@ spec:
         token: auth_... # TODO needs to be replaced with the actual value, see below
 
       apiEndpoint: https://api.....dash0.com # TODO needs to be replaced with the actual value, see below
+
+  clusterName: my-kubernetes-cluster # optional, see below
 ```
 
 Here is a list of configuration options for this resource:
@@ -190,6 +194,8 @@ Here is a list of configuration options for this resource:
 * `spec.kubernetesInfrastructureMetricsCollectionEnabled`: If enabled, the operator will collect Kubernetes
   infrastructure metrics.
   This setting is optional, it defaults to true.
+* `spec.clusterName`: If set, the value will be added as the resource attribute `k8s.cluster.name` to all telemetry.
+  This setting is optional. By default, `k8s.cluster.name` will not be added to telemetry.
 
 After providing the required values (at least `endpoint` and `authorization`), save the file and apply the resource to
 the Kubernetes cluster you want to monitor:
@@ -228,6 +234,9 @@ If you want to monitor the `default` namespace with Dash0, use the following com
 kubectl apply -f dash0-monitoring.yaml
 ```
 
+Note: Collecting Kubernetes infrastructure metrics (which are not neccessarily related to specific workloads or
+namespaces) also requires that at least one namespace has a Dash0Monitoring resource.
+
 ### Additional Configuration Per Namespace
 
 The Dash0 monitoring resource supports additional configuration settings:
@@ -452,6 +461,8 @@ spec:
 
 ### Configure Metrics Collection
 
+Note: Collecting metrics requires that at least one namespace has a Dash0Monitoring resource.
+
 By default, the operator collects metrics as follows:
 * The operator collects node, pod, container, and volume metrics from the API server on
   [kubelets](https://kubernetes.io/docs/concepts/architecture/#kubelet)
@@ -461,9 +472,8 @@ By default, the operator collects metrics as follows:
   via the
   [Kubernetes Cluster Receiver](https://github.com/open-telemetry/opentelemetry-collector-contrib/blob/main/receiver/k8sclusterreceiver/README.md)
   This can be disabled per cluster by setting `kubernetesInfrastructureMetricsCollectionEnabled: false` in the Dash0
-  operator configuration resource (or by using
-  `--operator-configuration-kubernetes-infrastructure-metrics-collection-enabled=false` when deploying the operator
-  configuration resource via the Helm chart).
+  operator configuration resource (or setting the value `operator.kubernetesInfrastructureMetricsCollectionEnabled` to
+  `false` when deploying the operator configuration resource via the Helm chart).
 * The Dash0 operator scrapes Prometheus endpoints on pods annotated with the `prometheus.io/*` annotations, as
   described in the section [Scraping Prometheus endpoints](#scraping-prometheus-endpoints). This can be disabled per
   namespace by explicitly setting `prometheusScrapingEnabled: false` in the Dash0 monitoring resource.

helm-chart/dash0-operator/templates/operator/custom-resource-definition-operator-configuration.yaml

@@ -41,6 +41,11 @@ spec:
             description: Dash0OperatorConfigurationSpec describes cluster-wide configuration
               settings for the Dash0 operator.
             properties:
+              clusterName:
+                description: |-
+                  If set, the value will be added as the resource attribute k8s.cluster.name to all telemetry. This setting is
+                  optional. By default, k8s.cluster.name will not be added to telemetry.
+                type: string
               export:
                 description: |-
                   The configuration of the default observability backend to which telemetry data will be sent by the operator, as

helm-chart/dash0-operator/templates/operator/deployment-and-webhooks.yaml

@@ -107,7 +107,10 @@ spec:
 {{- end }}
         - --operator-configuration-self-monitoring-enabled={{ .Values.operator.selfMonitoringEnabled }}
         - --operator-configuration-kubernetes-infrastructure-metrics-collection-enabled={{ .Values.operator.kubernetesInfrastructureMetricsCollectionEnabled }}
+{{- if .Values.operator.clusterName }}
+        - --operator-configuration-cluster-name={{ .Values.operator.clusterName }}
 {{- end }}
+{{- end }} # closes if .Values.operator.dash0Export.enabled
 {{- if .Values.operator.dash0Export.dataset }}
         - --operator-configuration-dataset={{ .Values.operator.dash0Export.dataset }}
 {{- end }}

helm-chart/dash0-operator/tests/operator/__snapshot__/custom-resource-definition-operator-configuration_test.yaml.snap

@@ -40,6 +40,11 @@ custom resource definition should match snapshot:
                 spec:
                   description: Dash0OperatorConfigurationSpec describes cluster-wide configuration settings for the Dash0 operator.
                   properties:
+                    clusterName:
+                      description: |-
+                        If set, the value will be added as the resource attribute k8s.cluster.name to all telemetry. This setting is
+                        optional. By default, k8s.cluster.name will not be added to telemetry.
+                      type: string
                     export:
                       description: |-
                         The configuration of the default observability backend to which telemetry data will be sent by the operator, as

helm-chart/dash0-operator/tests/operator/deployment-and-webhooks_test.yaml

@@ -301,6 +301,38 @@ tests:
           path: spec.template.spec.containers[0].args[8]
           value: --operator-configuration-dataset=test-dataset
 
+  - it: should add args for creating an operator configuration resource with a cluster name to the deployment
+    documentSelector:
+      path: metadata.name
+      value: dash0-operator-controller
+    set:
+      operator:
+        dash0Export:
+          enabled: true
+          endpoint: https://ingress.dash0.com
+          token: "very-secret-dash0-auth-token"
+          apiEndpoint: https://api.dash0.com
+        clusterName: "cluster-name"
+    asserts:
+      - equal:
+          path: spec.template.spec.containers[0].args[3]
+          value: --operator-configuration-endpoint=https://ingress.dash0.com
+      - equal:
+          path: spec.template.spec.containers[0].args[4]
+          value: --operator-configuration-token=very-secret-dash0-auth-token
+      - equal:
+          path: spec.template.spec.containers[0].args[5]
+          value: --operator-configuration-api-endpoint=https://api.dash0.com
+      - equal:
+          path: spec.template.spec.containers[0].args[6]
+          value: --operator-configuration-self-monitoring-enabled=true
+      - equal:
+          path: spec.template.spec.containers[0].args[7]
+          value: --operator-configuration-kubernetes-infrastructure-metrics-collection-enabled=true
+      - equal:
+          path: spec.template.spec.containers[0].args[8]
+          value: --operator-configuration-cluster-name=cluster-name
+
   - it: should add args for creating an operator configuration resource with a secretRef to the deployment
     documentSelector:
       path: metadata.name

helm-chart/dash0-operator/values.yaml

@@ -80,6 +80,13 @@ operator:
   # resource will be created by the Helm chart then.
   kubernetesInfrastructureMetricsCollectionEnabled: true
 
+  # If set, the value will be added as the resource attribute k8s.cluster.name to all telemetry. This setting is
+  # optional. Per default, the resource attribute k8s.cluster.name will not be added.
+  #
+  # This setting has no effect if operator.dash0Export.enabled is false, as no Dash0OperatorConfiguration
+  # resource will be created by the Helm chart then.
+  clusterName: ""
+
   # number of replica for the controller manager deployment
   replicaCount: 1
 

images/instrumentation/test/build_time_profiling

@@ -9,37 +9,37 @@ store_build_step_duration() {
   local step_label=$1
   local start=$2
   local end=$(date +%s)
-  local duration=$(($end-$start))
+  local duration=$((end - start))
   all_build_step_times["$step_label"]="$duration"
 }
 
 print_build_step_duration() {
   local step_label=$1
   local start=$2
   local end=$(date +%s)
-  local duration=$(($end-$start))
+  local duration=$((end - start))
   printf "[build time] $step_label:"'\t'"$(print_time "$duration")"'\n'
 }
 
 print_total_build_time_info() {
   local total_build_end=$(date +%s)
-  local total_build_duration=$(($total_build_end-$start_time_build))
+  local total_build_duration=$((total_build_end - start_time_build))
   local accounted_for_total=0
   echo
   echo "**build step durations**"
   for label in "${!all_build_step_times[@]}"; do
     local d="${all_build_step_times[$label]}"
     printf "[build time] $label:"'\t'"$(print_time "$d")"'\n'
-    accounted_for_total=$(($accounted_for_total+$d))
+    accounted_for_total=$((accounted_for_total + d))
   done
 
   echo ----------------------------------------
   echo "**summary**"
   print_build_step_duration "**total build time**" "$start_time_build"
 
   # check that we are actually measuring all relevant build steps:
-  local unaccounted=$(($total_build_duration-$accounted_for_total))
-  printf "[build time] build time account for by individual build steps:"'\t'"$(print_time "$accounted_for_total")"'\n'
+  local unaccounted=$((total_build_duration - accounted_for_total))
+  printf "[build time] build time accounted for by individual build steps:"'\t'"$(print_time "$accounted_for_total")"'\n'
   printf "[build time] build time unaccounted for by individual build steps:"'\t'"$(print_time "$unaccounted")"'\n'
 }
 

images/instrumentation/test/test-all.sh

@@ -28,6 +28,7 @@ all_docker_platforms=linux/arm64,linux/amd64
 script_dir="test"
 exit_code=0
 summary=""
+slow_test_threshold_seconds=15
 
 build_or_pull_instrumentation_image() {
   # shellcheck disable=SC2155
@@ -68,10 +69,15 @@ build_or_pull_instrumentation_image() {
 }
 
 run_tests_for_runtime() {
-  local runtime="${1:-}"
-  local image_name_test="${2:-}"
-  local base_image="${3:?}"
+  local docker_platform="${1:-}"
+  local runtime="${2:-}"
+  local image_name_test="${3:-}"
+  local base_image="${4:-}"
 
+  if [[ -z $docker_platform ]]; then
+    echo "missing parameter: docker_platform"
+    exit 1
+  fi
   if [[ -z $runtime ]]; then
     echo "missing parameter: runtime"
     exit 1
@@ -80,6 +86,10 @@ run_tests_for_runtime() {
     echo "missing parameter: image_name_test"
     exit 1
   fi
+  if [[ -z $base_image ]]; then
+    echo "missing parameter: base_image"
+    exit 1
+  fi
 
   for t in "${script_dir}"/"${runtime}"/test-cases/*/ ; do
     # shellcheck disable=SC2155
@@ -103,6 +113,7 @@ run_tests_for_runtime() {
     esac
 
     if docker_run_output=$(docker run \
+      --platform "$docker_platform" \
       --env-file="${script_dir}/${runtime}/test-cases/${test}/.env" \
       "$image_name_test" \
       "${test_cmd[@]}" \
@@ -116,6 +127,16 @@ run_tests_for_runtime() {
       exit_code=1
       summary="$summary\n${runtime}/${base_image}\t- ${test}:\tfailed"
     fi
+
+    # shellcheck disable=SC2155
+    local end_time_test_case=$(date +%s)
+    # shellcheck disable=SC2155
+    local duration_test_case=$((end_time_test_case - start_time_test_case))
+    if [[ "$duration_test_case" -gt "$slow_test_threshold_seconds" ]]; then
+      echo "! slow test case: $image_name_test/$base_image/$test: took $duration_test_case seconds, logging output:"
+      echo "$docker_run_output"
+    fi
+
     store_build_step_duration "test case $image_name_test/$base_image/$test" "$start_time_test_case"
   done
 }
@@ -162,7 +183,7 @@ run_tests_for_architecture() {
         exit 1
       fi
       store_build_step_duration "docker build $arch/$runtime/$base_image" "$start_time_docker_build"
-      run_tests_for_runtime "${runtime}" "$image_name_test" "$base_image"
+      run_tests_for_runtime "$docker_platform" "${runtime}" "$image_name_test" "$base_image"
       echo
     done
   done

internal/backendconnection/otelcolresources/collector_config_maps.go

@@ -20,6 +20,7 @@ type collectorConfigurationTemplateValues struct {
 	Exporters                                        []OtlpExporter
 	IgnoreLogsFromNamespaces                         []string
 	KubernetesInfrastructureMetricsCollectionEnabled bool
+	ClusterName                                      string
 	NamespacesWithPrometheusScraping                 []string
 	SelfIpReference                                  string
 	DevelopmentMode                                  bool
@@ -102,9 +103,10 @@ func assembleCollectorConfigMap(
 					config.Namespace,
 				},
 				KubernetesInfrastructureMetricsCollectionEnabled: config.KubernetesInfrastructureMetricsCollectionEnabled,
-				NamespacesWithPrometheusScraping:                 namespacesWithPrometheusScraping,
-				SelfIpReference:                                  selfIpReference,
-				DevelopmentMode:                                  config.DevelopmentMode,
+				ClusterName:                      config.ClusterName,
+				NamespacesWithPrometheusScraping: namespacesWithPrometheusScraping,
+				SelfIpReference:                  selfIpReference,
+				DevelopmentMode:                  config.DevelopmentMode,
 			})
 		if err != nil {
 			return nil, fmt.Errorf("cannot render the collector configuration template: %w", err)