Fix Linux Node Exporter

clusterloader2/go.mod

@@ -49,7 +49,6 @@ require (
 	github.com/stretchr/testify v1.10.0
 	golang.org/x/crypto v0.37.0
 	golang.org/x/oauth2 v0.29.0
-	golang.org/x/sync v0.13.0
 	golang.org/x/time v0.11.0
 	gopkg.in/yaml.v2 v2.4.0
 	k8s.io/api v0.32.3
@@ -113,6 +112,7 @@ require (
 	go.uber.org/atomic v1.10.0 // indirect
 	go.uber.org/goleak v1.3.0 // indirect
 	golang.org/x/net v0.38.0 // indirect
+	golang.org/x/sync v0.13.0 // indirect
 	golang.org/x/sys v0.32.0 // indirect
 	golang.org/x/term v0.31.0 // indirect
 	golang.org/x/text v0.24.0 // indirect

clusterloader2/pkg/prometheus/manifests/exporters/node_exporter/linux-exporter-podmonitor.yaml

@@ -0,0 +1,19 @@
+apiVersion: monitoring.coreos.com/v1
+kind: PodMonitor
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app: node-exporter  # must match your Prometheus CR's `podMonitorSelector`
+spec:
+  selector:
+    matchLabels:
+      app: node-exporter
+  namespaceSelector:
+    matchNames:
+      - monitoring
+  podMetricsEndpoints:
+    - port: metrics
+      path: /metrics
+      interval: 5s
+

clusterloader2/pkg/prometheus/manifests/exporters/node_exporter/node-exporter-daemonset.yaml

@@ -0,0 +1,56 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app: node-exporter
+spec:
+  selector:
+    matchLabels:
+      app: node-exporter
+  template:
+    metadata:
+      labels:
+        app: node-exporter
+    spec:
+      hostNetwork: true
+      hostPID: true
+      containers:
+        - name: node-exporter
+          image: quay.io/prometheus/node-exporter:latest
+          args:
+            - "--path.procfs=/host/proc"
+            - "--path.sysfs=/host/sys"
+            - "--collector.disable-defaults"
+            - "--collector.cpu"
+            - "--collector.meminfo"
+            - "--collector.loadavg"
+            - "--collector.stat"
+          ports:
+            - containerPort: 9100
+              hostPort: 9100
+              name: metrics
+          resources:
+            limits:
+              memory: 100Mi
+            requests:
+              cpu: 100m
+              memory: 50Mi
+          volumeMounts:
+            - name: proc
+              mountPath: /host/proc
+              readOnly: true
+            - name: sys
+              mountPath: /host/sys
+              readOnly: true
+      nodeSelector:
+        kubernetes.io/os: linux
+      volumes:
+        - name: proc
+          hostPath:
+            path: /proc
+        - name: sys
+          hostPath:
+            path: /sys
+      terminationGracePeriodSeconds: 30

clusterloader2/pkg/prometheus/prometheus.go

@@ -27,7 +27,6 @@ import (
 	"sync"
 	"time"
 
-	"golang.org/x/sync/errgroup"
 	authenticationv1 "k8s.io/api/authentication/v1"
 	corev1 "k8s.io/api/core/v1"
 	rbacv1 "k8s.io/api/rbac/v1"
@@ -59,7 +58,7 @@ const (
 	kubeStateMetricsManifests    = "exporters/kube-state-metrics/*.yaml"
 	masterIPServiceMonitors      = "master-ip/*.yaml"
 	metricsServerManifests       = "exporters/metrics-server/*.yaml"
-	nodeExporterPod              = "exporters/node_exporter/node-exporter.yaml"
+	nodeExporterManifests        = "exporters/node_exporter/*.yaml"
 	windowsNodeExporterManifests = "exporters/windows_node_exporter/*.yaml"
 	pushgatewayManifests         = "pushgateway/*.yaml"
 )
@@ -260,7 +259,7 @@ func (pc *Controller) SetUpPrometheusStack() error {
 		return err
 	}
 	if pc.clusterLoaderConfig.PrometheusConfig.ScrapeNodeExporter {
-		if err := pc.runNodeExporter(); err != nil {
+		if err := pc.applyDefaultManifests(nodeExporterManifests); err != nil {
 			return err
 		}
 	}
@@ -520,46 +519,6 @@ func (pc *Controller) configureRBACForMetrics(testClusterClientSet kubernetes.In
 	return nil
 }
 
-// runNodeExporter adds node-exporter as master's static manifest pod.
-// TODO(mborsz): Consider migrating to something less ugly, e.g. daemonset-based approach,
-// when master nodes have configured networking.
-func (pc *Controller) runNodeExporter() error {
-	klog.V(2).Infof("Starting node-exporter on master nodes.")
-	kubemarkFramework, err := framework.NewFramework(&pc.clusterLoaderConfig.ClusterConfig, numK8sClients)
-	if err != nil {
-		return err
-	}
-
-	// Validate masters first
-	nodes, err := client.ListNodes(kubemarkFramework.GetClientSets().GetClient())
-	if err != nil {
-		return err
-	}
-
-	var g errgroup.Group
-	numMasters := 0
-	for _, node := range nodes {
-		node := node
-		if util.LegacyIsMasterNode(&node) || util.IsControlPlaneNode(&node) {
-			numMasters++
-			g.Go(func() error {
-				f, err := manifestsFS.Open(nodeExporterPod)
-				if err != nil {
-					return fmt.Errorf("unable to open manifest file: %v", err)
-				}
-				defer f.Close()
-				return pc.ssh.Exec("sudo tee /etc/kubernetes/manifests/node-exporter.yaml > /dev/null", &node, f)
-			})
-		}
-	}
-
-	if numMasters == 0 {
-		return fmt.Errorf("node-exporter requires master to be registered nodes")
-	}
-
-	return g.Wait()
-}
-
 func (pc *Controller) waitForPrometheusToBeHealthy() error {
 	klog.V(2).Info("Waiting for Prometheus stack to become healthy...")
 	return wait.PollImmediate(