[receiver/kubeletstats] Emit k8s.node.cpu.utilization as ratio against node's capacity

.chloggen/fix_k8s_node_cpu_util.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: kubeletstatsreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Fixes `k8s.node.cpu.utilization` so as to be properly reported as a ratio against the Node's capacity
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [27885]
+
+# (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:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

receiver/kubeletstatsreceiver/README.md

@@ -218,11 +218,11 @@ receivers:
       - pod
 ```
 
-### Collect `k8s.{container,pod}.{cpu,memory}.node.utilization` as ratio of total node's capacity
+### Collect `k8s.{container,pod}.{cpu,memory}.node.utilization` and `k8s.node.cpu.utilization` as ratio of total node's capacity
 
 In order to calculate the `k8s.container.cpu.node.utilization`, `k8s.pod.cpu.node.utilization`,
-`k8s.container.memory.node.utilization` and `k8s.pod.memory.node.utilization` metrics, the
-information of the node's capacity must be retrieved from the k8s API. In this, the `k8s_api_config` needs to be set.
+`k8s.container.memory.node.utilization`, `k8s.pod.memory.node.utilization` and `k8s.pod.memory.node.utilization` metrics,
+the information of the node's capacity must be retrieved from the k8s API. In this, the `k8s_api_config` needs to be set.
 In addition, the node name must be identified properly. The `K8S_NODE_NAME` env var can be set using the
 downward API inside the collector pod spec as follows:
 
@@ -253,6 +253,8 @@ receivers:
           enabled: true
         k8s.pod.memory.node.utilization:
           enabled: true
+        k8s.node.cpu.utilization:
+          enabled: true
 ```
 
 ### Optional parameters

receiver/kubeletstatsreceiver/internal/kubelet/accumulator.go

@@ -56,7 +56,7 @@ func (a *metricDataAccumulator) nodeStats(s stats.NodeStats) {
 
 	currentTime := pcommon.NewTimestampFromTime(a.time)
 	addUptimeMetric(a.mbs.NodeMetricsBuilder, metadata.NodeUptimeMetrics.Uptime, s.StartTime, currentTime)
-	addCPUMetrics(a.mbs.NodeMetricsBuilder, metadata.NodeCPUMetrics, s.CPU, currentTime, resources{}, 0)
+	addCPUMetrics(a.mbs.NodeMetricsBuilder, metadata.NodeCPUMetrics, s.CPU, currentTime, resources{}, a.metadata.nodeCapacity.CPUCapacity)
 	addMemoryMetrics(a.mbs.NodeMetricsBuilder, metadata.NodeMemoryMetrics, s.Memory, currentTime, resources{}, 0)
 	addFilesystemMetrics(a.mbs.NodeMetricsBuilder, metadata.NodeFilesystemMetrics, s.Fs, currentTime)
 	addNetworkMetrics(a.mbs.NodeMetricsBuilder, metadata.NodeNetworkMetrics, s.Network, currentTime)

receiver/kubeletstatsreceiver/internal/kubelet/cpu.go

@@ -35,7 +35,10 @@ func addCPUUtilizationMetrics(
 	currentTime pcommon.Timestamp,
 	r resources,
 	nodeCPULimit float64) {
-	cpuMetrics.Utilization(mb, currentTime, usageCores)
+
+	if cpuMetrics.Utilization != nil {
+		cpuMetrics.Utilization(mb, currentTime, usageCores)
+	}
 
 	if nodeCPULimit > 0 {
 		cpuMetrics.NodeUtilization(mb, currentTime, usageCores/nodeCPULimit)

receiver/kubeletstatsreceiver/internal/metadata/metrics.go

@@ -28,9 +28,10 @@ type CPUMetrics struct {
 }
 
 var NodeCPUMetrics = CPUMetrics{
-	Time:        (*MetricsBuilder).RecordK8sNodeCPUTimeDataPoint,
-	Usage:       (*MetricsBuilder).RecordK8sNodeCPUUsageDataPoint,
-	Utilization: (*MetricsBuilder).RecordK8sNodeCPUUtilizationDataPoint,
+	Time:  (*MetricsBuilder).RecordK8sNodeCPUTimeDataPoint,
+	Usage: (*MetricsBuilder).RecordK8sNodeCPUUsageDataPoint,
+	//Utilization:     (*MetricsBuilder).RecordK8sNodeCPUUtilizationDataPoint,
+	NodeUtilization: (*MetricsBuilder).RecordK8sNodeCPUUtilizationDataPoint,
 }
 
 var PodCPUMetrics = CPUMetrics{

receiver/kubeletstatsreceiver/metadata.yaml

@@ -92,8 +92,6 @@ metrics:
   k8s.node.cpu.utilization:
     enabled: true
     description: "Node CPU utilization"
-    warnings:
-      if_enabled: "WARNING: This metric will be disabled in a future release. Use metric k8s.node.cpu.usage instead."
     unit: "1"
     gauge:
       value_type: double

receiver/kubeletstatsreceiver/scraper.go

@@ -83,7 +83,8 @@ func newKubletScraper(
 		nodeLimits: &kubelet.NodeCapacity{},
 	}
 
-	if metricsConfig.Metrics.K8sContainerCPUNodeUtilization.Enabled ||
+	if metricsConfig.Metrics.K8sNodeCPUUtilization.Enabled ||
+		metricsConfig.Metrics.K8sContainerCPUNodeUtilization.Enabled ||
 		metricsConfig.Metrics.K8sPodCPUNodeUtilization.Enabled ||
 		metricsConfig.Metrics.K8sContainerMemoryNodeUtilization.Enabled ||
 		metricsConfig.Metrics.K8sPodMemoryNodeUtilization.Enabled {

receiver/kubeletstatsreceiver/scraper_test.go

@@ -102,6 +102,7 @@ func TestScraperWithCPUNodeUtilization(t *testing.T) {
 		metricGroupsToCollect: map[kubelet.MetricGroup]bool{
 			kubelet.ContainerMetricGroup: true,
 			kubelet.PodMetricGroup:       true,
+			kubelet.NodeMetricGroup:      true,
 		},
 		k8sAPIClient: client,
 	}
@@ -117,6 +118,9 @@ func TestScraperWithCPUNodeUtilization(t *testing.T) {
 				K8sPodCPUNodeUtilization: metadata.MetricConfig{
 					Enabled: true,
 				},
+				K8sNodeCPUUtilization: metadata.MetricConfig{
+					Enabled: true,
+				},
 			},
 			ResourceAttributes: metadata.DefaultResourceAttributesConfig(),
 		},
@@ -140,7 +144,7 @@ func TestScraperWithCPUNodeUtilization(t *testing.T) {
 	require.Eventually(t, func() bool {
 		md, err = r.Scrape(context.Background())
 		require.NoError(t, err)
-		return numContainers+numPods == md.DataPointCount()
+		return numContainers+numPods+1 == md.DataPointCount()
 	}, 10*time.Second, 100*time.Millisecond,
 		"metrics not collected")
 

receiver/kubeletstatsreceiver/testdata/scraper/test_scraper_cpu_util_nodelimit_expected.yaml

@@ -1,4 +1,22 @@
 resourceMetrics:
+  - resource:
+      attributes:
+        - key: k8s.node.name
+          value:
+            stringValue: minikube
+    scopeMetrics:
+      - metrics:
+          - description: Node CPU utilization
+            gauge:
+              dataPoints:
+                - asDouble: 0.020717166125
+                  startTimeUnixNano: "1000000"
+                  timeUnixNano: "2000000"
+            name: k8s.node.cpu.utilization
+            unit: "1"
+        scope:
+          name: otelcol/kubeletstatsreceiver
+          version: latest
   - resource:
       attributes:
         - key: k8s.namespace.name