Fix Cronjob name (#2717)

* Fix Cronjob name

Signed-off-by: Janario Oliveira <[email protected]>

* Mapped Job permissions

Signed-off-by: Janario Oliveira <[email protected]>

* Add changelog

Signed-off-by: Janario Oliveira <[email protected]>

* Add Job rbac permissions

Signed-off-by: Janario Oliveira <[email protected]>

* Add e2e test case

Signed-off-by: Janario Oliveira <[email protected]>

* Parent resources unit test

Signed-off-by: Janario Oliveira <[email protected]>

* ChooseServiceName unit test

Signed-off-by: Janario Oliveira <[email protected]>

* Generated manifest

Signed-off-by: Janario Oliveira <[email protected]>

* Rename e2e

Signed-off-by: Janario Oliveira <[email protected]>

* Fix e2e tests

Signed-off-by: Janario Oliveira <[email protected]>

* Fix lint

Signed-off-by: Janario Oliveira <[email protected]>

---------

Signed-off-by: Janario Oliveira <[email protected]>

Author: janario

.chloggen/cronjob-service-name.yaml

@@ -0,0 +1,19 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: auto-instrumentation
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: CronJob name propagated to the OTEL Service Name
+
+# One or more tracking issues related to the change
+issues: [2716]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: |
+  When instrumenting a `CronJob` it would generate a `Job` and then a `Pod`.
+  Previously it would use the `Job` name as the Service name, generating too many different services on each cron execution.
+  This release fixed to collect the `Job` parent's name, if it has one. 

bundle/manifests/opentelemetry-operator.clusterserviceversion.yaml

@@ -65,7 +65,7 @@ metadata:
     categories: Logging & Tracing,Monitoring
     certified: "false"
     containerImage: ghcr.io/open-telemetry/opentelemetry-operator/opentelemetry-operator
-    createdAt: "2024-03-25T08:38:05Z"
+    createdAt: "2024-04-02T20:37:56Z"
     description: Provides the OpenTelemetry components, including the Collector
     operators.operatorframework.io/builder: operator-sdk-v1.29.0
     operators.operatorframework.io/project_layout: go.kubebuilder.io/v3
@@ -236,6 +236,14 @@ spec:
           - patch
           - update
           - watch
+        - apiGroups:
+          - batch
+          resources:
+          - jobs
+          verbs:
+          - get
+          - list
+          - watch
         - apiGroups:
           - config.openshift.io
           resources:

config/rbac/role.yaml

@@ -69,6 +69,14 @@ rules:
   - patch
   - update
   - watch
+- apiGroups:
+  - batch
+  resources:
+  - jobs
+  verbs:
+  - get
+  - list
+  - watch
 - apiGroups:
   - config.openshift.io
   resources:

internal/webhook/podmutation/webhookhandler.go

@@ -34,6 +34,7 @@ import (
 // +kubebuilder:rbac:groups=opentelemetry.io,resources=opentelemetrycollectors,verbs=get;list;watch
 // +kubebuilder:rbac:groups=opentelemetry.io,resources=instrumentations,verbs=get;list;watch
 // +kubebuilder:rbac:groups="apps",resources=replicasets,verbs=get;list;watch
+// +kubebuilder:rbac:groups="batch",resources=jobs,verbs=get;list;watch
 
 var _ WebhookHandler = (*podMutationWebhook)(nil)
 

pkg/instrumentation/sdk.go

@@ -31,6 +31,7 @@ import (
 	"go.opentelemetry.io/otel/attribute"
 	semconv "go.opentelemetry.io/otel/semconv/v1.7.0"
 	appsv1 "k8s.io/api/apps/v1"
+	batchv1 "k8s.io/api/batch/v1"
 	corev1 "k8s.io/api/core/v1"
 	apierrors "k8s.io/apimachinery/pkg/api/errors"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -398,16 +399,19 @@ func chooseServiceName(pod corev1.Pod, resources map[string]string, index int) s
 	if name := resources[string(semconv.K8SDeploymentNameKey)]; name != "" {
 		return name
 	}
+	if name := resources[string(semconv.K8SReplicaSetNameKey)]; name != "" {
+		return name
+	}
 	if name := resources[string(semconv.K8SStatefulSetNameKey)]; name != "" {
 		return name
 	}
 	if name := resources[string(semconv.K8SDaemonSetNameKey)]; name != "" {
 		return name
 	}
-	if name := resources[string(semconv.K8SJobNameKey)]; name != "" {
+	if name := resources[string(semconv.K8SCronJobNameKey)]; name != "" {
 		return name
 	}
-	if name := resources[string(semconv.K8SCronJobNameKey)]; name != "" {
+	if name := resources[string(semconv.K8SJobNameKey)]; name != "" {
 		return name
 	}
 	if name := resources[string(semconv.K8SPodNameKey)]; name != "" {
@@ -526,6 +530,26 @@ func (i *sdkInjector) addParentResourceLabels(ctx context.Context, uid bool, ns
 			if uid {
 				resources[semconv.K8SJobUIDKey] = string(owner.UID)
 			}
+
+			// parent of Job can be CronJob which we are interested to know
+			j := batchv1.Job{}
+			nsn := types.NamespacedName{Namespace: ns.Name, Name: owner.Name}
+			backOff := wait.Backoff{Duration: 10 * time.Millisecond, Factor: 1.5, Jitter: 0.1, Steps: 20, Cap: 2 * time.Second}
+
+			checkError := func(err error) bool {
+				return apierrors.IsNotFound(err)
+			}
+
+			getJob := func() error {
+				return i.client.Get(ctx, nsn, &j)
+			}
+
+			// use a retry loop to get the Job. A single call to client.get fails occasionally
+			err := retry.OnError(backOff, checkError, getJob)
+			if err != nil {
+				i.logger.Error(err, "failed to get job", "job", nsn.Name, "namespace", nsn.Namespace)
+			}
+			i.addParentResourceLabels(ctx, uid, ns, j.ObjectMeta, resources)
 		case "cronjob":
 			resources[semconv.K8SCronJobNameKey] = owner.Name
 			if uid {