feat: add CSE integration for node-exporter service startup

Author: chmill-zz

parts/linux/cloud-init/artifacts/cse_config.sh

@@ -792,6 +792,25 @@ EOF
     systemctlEnableAndStart mig-partition 300
 }
 
+configureNodeExporter() {
+    echo "Configuring Node Exporter"
+    # Check for skip file to determine if node-exporter was installed on this VHD
+    if [ ! -f /etc/node-exporter.d/skip_vhd_node_exporter ]; then
+        echo "Node Exporter assets not found on this VHD (missing /etc/node-exporter.d/skip_vhd_node_exporter); skipping configuration."
+        return 0
+    fi
+
+    if ! systemctlEnableAndStart node-exporter 30; then
+        echo "Failed to start node-exporter service"
+        return $ERR_NODE_EXPORTER_START_FAIL
+    fi
+    if ! systemctlEnableAndStart node-exporter-restart.path 30; then
+        echo "Failed to start node-exporter-restart.path"
+        return $ERR_NODE_EXPORTER_START_FAIL
+    fi
+    echo "Node Exporter started successfully"
+}
+
 ensureSysctl() {
     SYSCTL_CONFIG_FILE=/etc/sysctl.d/999-sysctl-aks.conf
     mkdir -p "$(dirname "${SYSCTL_CONFIG_FILE}")"

parts/linux/cloud-init/artifacts/cse_helpers.sh

@@ -75,6 +75,8 @@ ERR_KUBECTL_INSTALL_FAIL=122 # Error installing kubectl
 # Error code 124 is returned when a `timeout` command times out, and --preserve-status is not specified: https://man7.org/linux/man-pages/man1/timeout.1.html
 ERR_VHD_BUILD_ERROR=125 # Reserved for VHD CI exit conditions
 
+ERR_NODE_EXPORTER_START_FAIL=128 # Error starting or enabling node-exporter service
+
 ERR_SWAP_CREATE_FAIL=130 # Error allocating swap file
 ERR_SWAP_CREATE_INSUFFICIENT_DISK_SPACE=131 # Error insufficient disk space for swap file creation
 

parts/linux/cloud-init/artifacts/cse_main.sh

@@ -461,6 +461,8 @@ function nodePrep {
 
     logs_to_events "AKS.CSE.ensureKubelet" ensureKubelet
 
+    logs_to_events "AKS.CSE.configureNodeExporter" configureNodeExporter
+
     if $REBOOTREQUIRED; then
         echo 'reboot required, rebooting node in 1 minute'
         /bin/bash -c "shutdown -r 1 &"

parts/linux/cloud-init/artifacts/manifest.json

@@ -22,3 +22,4 @@
         "versions": []
     }
 }
+#EOF