[k8sclusterreceiver] add k8s.pod.status_reason optional metric

.chloggen/k8sclusterreceiver-pod-status-reason.yaml

@@ -0,0 +1,20 @@
+# Use this changelog template to create an entry for release notes.
+# If your change doesn't affect end users, such as a test fix or a tooling change,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+
+# 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. filelogreceiver)
+component: k8sclusterreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add k8s.pod.status_reason option metric"
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [24034]
+
+# (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:

receiver/k8sclusterreceiver/documentation.md

@@ -386,6 +386,24 @@ The usage for a particular resource with a configured limit.
 | ---- | ----------- | ------ |
 | resource | the name of the resource on which the quota is applied | Any Str |
 
+## Optional Metrics
+
+The following metrics are not emitted by default. Each of them can be enabled by applying the following configuration:
+
+```yaml
+metrics:
+  <metric_name>:
+    enabled: true
+```
+
+### k8s.pod.status_reason
+
+Current status reason of the pod (1 - Evicted, 2 - NodeAffinity, 3 - NodeLost, 4 - Shutdown, 5 - UnexpectedAdmissionError, 6 - Unknown)
+
+| Unit | Metric Type | Value Type |
+| ---- | ----------- | ---------- |
+| 1 | Gauge | Int |
+
 ## Resource Attributes
 
 | Name | Description | Values | Enabled |

receiver/k8sclusterreceiver/internal/metadata/testdata/config.yaml

@@ -57,6 +57,8 @@ all_set:
       enabled: true
     k8s.pod.phase:
       enabled: true
+    k8s.pod.status_reason:
+      enabled: true
     k8s.replicaset.available:
       enabled: true
     k8s.replicaset.desired:
@@ -206,6 +208,8 @@ none_set:
       enabled: false
     k8s.pod.phase:
       enabled: false
+    k8s.pod.status_reason:
+      enabled: false
     k8s.replicaset.available:
       enabled: false
     k8s.replicaset.desired:

receiver/k8sclusterreceiver/internal/pod/pods.go

@@ -70,6 +70,7 @@ func Transform(pod *corev1.Pod) *corev1.Pod {
 
 func RecordMetrics(logger *zap.Logger, mb *metadata.MetricsBuilder, pod *corev1.Pod, ts pcommon.Timestamp) {
 	mb.RecordK8sPodPhaseDataPoint(ts, int64(phaseToInt(pod.Status.Phase)))
+	mb.RecordK8sPodStatusReasonDataPoint(ts, int64(reasonToInt(pod.Status.Reason)))
 	rb := mb.NewResourceBuilder()
 	rb.SetK8sNamespaceName(pod.Namespace)
 	rb.SetK8sNodeName(pod.Spec.NodeName)
@@ -83,6 +84,23 @@ func RecordMetrics(logger *zap.Logger, mb *metadata.MetricsBuilder, pod *corev1.
 	}
 }
 
+func reasonToInt(reason string) int32 {
+	switch reason {
+	case "Evicted":
+		return 1
+	case "NodeAffinity":
+		return 2
+	case "NodeLost":
+		return 3
+	case "Shutdown":
+		return 4
+	case "UnexpectedAdmissionError":
+		return 5
+	default:
+		return 6
+	}
+}
+
 func phaseToInt(phase corev1.PodPhase) int32 {
 	switch phase {
 	case corev1.PodPending:

receiver/k8sclusterreceiver/internal/pod/pods_test.go

@@ -59,6 +59,32 @@ func TestPodAndContainerMetricsReportCPUMetrics(t *testing.T) {
 	)
 }
 
+func TestPodStatusReasonAndContainerMetricsReportCPUMetrics(t *testing.T) {
+	pod := testutils.NewPodWithContainer(
+		"1",
+		testutils.NewPodSpecWithContainer("container-name"),
+		testutils.NewEvictedTerminatedPodStatusWithContainer("container-name", containerIDWithPreifx("container-id")),
+	)
+
+	mbc := metadata.DefaultMetricsBuilderConfig()
+	mbc.Metrics.K8sPodStatusReason.Enabled = true
+	ts := pcommon.Timestamp(time.Now().UnixNano())
+	mb := metadata.NewMetricsBuilder(mbc, receivertest.NewNopCreateSettings())
+	RecordMetrics(zap.NewNop(), mb, pod, ts)
+	m := mb.Emit()
+
+	expected, err := golden.ReadMetrics(filepath.Join("testdata", "expected_evicted.yaml"))
+	require.NoError(t, err)
+	require.NoError(t, pmetrictest.CompareMetrics(expected, m,
+		pmetrictest.IgnoreTimestamp(),
+		pmetrictest.IgnoreStartTimestamp(),
+		pmetrictest.IgnoreResourceMetricsOrder(),
+		pmetrictest.IgnoreMetricsOrder(),
+		pmetrictest.IgnoreScopeMetricsOrder(),
+	),
+	)
+}
+
 var containerIDWithPreifx = func(containerID string) string {
 	return "docker://" + containerID
 }

receiver/k8sclusterreceiver/internal/pod/testdata/expected_evicted.yaml

@@ -0,0 +1,95 @@
+resourceMetrics:
+  - resource:
+      attributes:
+        - key: k8s.namespace.name
+          value:
+            stringValue: test-namespace
+        - key: k8s.node.name
+          value:
+            stringValue: test-node
+        - key: k8s.pod.name
+          value:
+            stringValue: test-pod-1
+        - key: k8s.pod.uid
+          value:
+            stringValue: test-pod-1-uid
+        - key: opencensus.resourcetype
+          value:
+            stringValue: k8s
+    schemaUrl: https://opentelemetry.io/schemas/1.18.0
+    scopeMetrics:
+      - metrics:
+          - description: Current phase of the pod (1 - Pending, 2 - Running, 3 - Succeeded, 4 - Failed, 5 - Unknown)
+            gauge:
+              dataPoints:
+                - asInt: "4"
+            name: k8s.pod.phase
+            unit: "1"
+          - description: Current status reason of the pod (1 - Evicted, 2 - NodeAffinity, 3 - NodeLost, 4 - Shutdown, 5 - UnexpectedAdmissionError, 6 - Unknown)
+            gauge:
+              dataPoints:
+                - asInt: "1"
+            name: k8s.pod.status_reason
+            unit: "1"
+        scope:
+          name: otelcol/k8sclusterreceiver
+          version: latest
+  - resource:
+      attributes:
+        - key: container.id
+          value:
+            stringValue: container-id
+        - key: container.image.name
+          value:
+            stringValue: container-image-name
+        - key: container.image.tag
+          value:
+            stringValue: latest
+        - key: k8s.container.name
+          value:
+            stringValue: container-name
+        - key: k8s.namespace.name
+          value:
+            stringValue: test-namespace
+        - key: k8s.node.name
+          value:
+            stringValue: test-node
+        - key: k8s.pod.name
+          value:
+            stringValue: test-pod-1
+        - key: k8s.pod.uid
+          value:
+            stringValue: test-pod-1-uid
+        - key: opencensus.resourcetype
+          value:
+            stringValue: container
+    schemaUrl: https://opentelemetry.io/schemas/1.18.0
+    scopeMetrics:
+      - metrics:
+          - description: How many times the container has restarted in the recent past. This value is pulled directly from the K8s API and the value can go indefinitely high and be reset to 0 at any time depending on how your kubelet is configured to prune dead containers. It is best to not depend too much on the exact value but rather look at it as either == 0, in which case you can conclude there were no restarts in the recent past, or > 0, in which case you can conclude there were restarts in the recent past, and not try and analyze the value beyond that.
+            gauge:
+              dataPoints:
+                - asInt: "3"
+            name: k8s.container.restarts
+            unit: "1"
+          - description: Whether a container has passed its readiness probe (0 for no, 1 for yes)
+            gauge:
+              dataPoints:
+                - asInt: "1"
+            name: k8s.container.ready
+            unit: "1"
+          - description: Resource requested for the container. See https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#resourcerequirements-v1-core for details
+            gauge:
+              dataPoints:
+                - asDouble: 10
+            name: k8s.container.cpu_request
+            unit: "{cpu}"
+          - description: Maximum resource limit set for the container. See https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.23/#resourcerequirements-v1-core for details
+            gauge:
+              dataPoints:
+                - asDouble: 20
+            name: k8s.container.cpu_limit
+            unit: "{cpu}"
+        scope:
+          name: otelcol/k8sclusterreceiver
+          version: latest