feat: moved prometheus node exporter to alloy

services/monitoring/deploy/alloy/node-scraper/helm-values.yaml

@@ -10,7 +10,19 @@ controller:
       - name: etc-machine-id
         hostPath:
           path: /etc/machine-id
-  
+      - name: rootfs
+        hostPath:
+          path: /
+      - name: proc
+        hostPath:
+          path: /proc
+      - name: sys
+        hostPath:
+          path: /sys
+      - name: dev
+        hostPath:
+          path: /dev
+
   tolerations:
     - key: "node-role.kubernetes.io/control-plane"
       operator: "Exists"
@@ -31,7 +43,18 @@ alloy:
       - name: etc-machine-id
         mountPath: /etc/machine-id
         readOnly: true
-
+      - name: rootfs
+        mountPath: /host
+        readOnly: true
+      - name: proc
+        mountPath: /host/proc
+        readOnly: true
+      - name: sys
+        mountPath: /host/sys
+        readOnly: true
+      - name: dev
+        mountPath: /host/dev
+        readOnly: true 
   # https://grafana.com/docs/alloy/latest/collect/logs-in-kubernetes/
   configMap:
     content: |
@@ -100,6 +123,108 @@ alloy:
 
         forward_to = [loki.write.loki_srv.receiver]
       }
+      // ============================================
+      // prometheus unix exporter
+      // ============================================
+      prometheus.exporter.unix "node_exporter" {
+        rootfs_path = "/host"
+        disable_collectors = ["ipvs", "btrfs", "infiniband", "xfs", "zfs"]
+        enable_collectors = [
+          "cpu",
+          "meminfo",
+          "vmstat",
+          "loadavg",
+          "filesystem",
+          "netdev",
+          "uname",
+        ]
+
+        filesystem {
+          mount_points_exclude = "^/(dev|proc|sys|run/containerd/.+|var/lib/docker/.+|var/lib/kubelet/.+)($|/)"
+          fs_types_exclude     = "^(autofs|binfmt_misc|bpf|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs|erofs)$"
+          mount_timeout        = "5s"
+        }
+
+        netclass {
+          ignored_devices = "^(veth.*|cali.*|[a-f0-9]{15})$"
+        }
+
+        netdev {
+          device_exclude = "^(veth.*|cali.*|[a-f0-9]{15})$"
+        }
+      }
+    
+      prometheus.scrape "node_exporter" {
+        targets         = prometheus.exporter.unix.node_exporter.targets
+        scrape_interval = "30s"
+
+        forward_to = [prometheus.relabel.node_exporter.receiver]
+      }
+
+      prometheus.relabel "node_exporter" {
+
+        rule {
+          target_label = "instance"
+          replacement  = env("NODE_IP") + ":9100"
+        }
+
+        rule {
+          target_label = "nodename"
+          replacement  = env("HOSTNAME")
+        }
+
+        rule {
+          target_label = "node"
+          replacement  = env("HOSTNAME")
+        }
+
+        rule {
+          target_label = "kubernetes_node"
+          replacement  = env("HOSTNAME")
+        }
+
+        rule {
+          target_label = "cluster"
+          replacement  = env("CLUSTER_NAME")
+        }
+
+        rule {
+          target_label = "job"
+          replacement  = env("JOB")
+        }
+
+        rule {
+
+          target_label = "container"
+          replacement  = env("CONTAINER")
+        }
+        rule {
+
+          target_label = "NS"
+          replacement  = env("NS")
+        }
+
+        rule {
+          target_label = "pod"
+          replacement  = env("POD")
+        }
+
+        rule {
+          target_label = "service"
+          replacement  = env("SERVICE")
+        }
+
+        forward_to = [prometheus.remote_write.metrics_service.receiver]
+
+      }
+
+      prometheus.remote_write "metrics_service" {
+
+        endpoint {
+          url = "https://prometheus.monitoring.limbosolutions.com/api/v1/write"
+        }
+
+      }
 
   extraEnv:
     - name: NODE_NAME
@@ -108,6 +233,16 @@ alloy:
           fieldPath: spec.nodeName
     - name: CLUSTER_NAME
       value: casa
+    - name: JOB
+      value: node-exporter
+    - name: CONTAINER
+      value: node-exporter
+    - name: NS
+      value: monitoring
+    - name: POD
+      value: alloy-node-scraper
+    - name: SERVICE
+      value: alloy-node-scraper
     - name: ZONE
       value: casa-vlan
     - name: LOKI_URL

services/monitoring/deploy/prometheus/helm-values.yaml

@@ -15,21 +15,12 @@ kubeStateMetrics:
   enabled: true
 
 nodeExporter:
-  enabled: true
+  enabled: false
 
 prometheus-node-exporter:
   prometheus:
     monitor:
-      enabled: true
-      relabelings:
-      # https://github.com/dotdc/grafana-dashboards-kubernetes
-      - action: replace
-        sourceLabels: [__meta_kubernetes_pod_node_name]
-        targetLabel: nodename
-      - targetLabel: cluster
-        replacement: casa
-
-
+      enabled: false
 
 coreDns: 
   enabled: true