Add monitoring replacement baseline

2026-05-17 11:22:38 +02:00
parent 0c308ff352
commit c95fa601f0
10 changed files with 490 additions and 5 deletions
@@ -0,0 +1,145 @@
+{
+  "uid": "homelab-availability",
+  "title": "Homelab / Availability",
+  "tags": ["homelab", "blackbox", "uptime"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "templating": {
+    "list": [
+      {
+        "name": "target",
+        "label": "Target",
+        "type": "query",
+        "datasource": "Prometheus",
+        "query": "label_values(probe_success{job=\"blackbox-http\"}, instance)",
+        "refresh": 1,
+        "includeAll": true,
+        "multi": true,
+        "allValue": ".+",
+        "current": {
+          "selected": true,
+          "text": "All",
+          "value": "$__all"
+        }
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "stat",
+      "title": "Endpoints up",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 5, "w": 6, "x": 0, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum(probe_success{job=\"blackbox-http\", instance=~\"${target:regex}\"})"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {"color": "red", "value": null},
+              {"color": "green", "value": 1}
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}}
+    },
+    {
+      "id": 2,
+      "type": "stat",
+      "title": "Endpoints down",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 5, "w": 6, "x": 6, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "count(probe_success{job=\"blackbox-http\", instance=~\"${target:regex}\"}) - sum(probe_success{job=\"blackbox-http\", instance=~\"${target:regex}\"})"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {"color": "green", "value": null},
+              {"color": "red", "value": 1}
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "options": {"reduceOptions": {"calcs": ["lastNotNull"], "fields": "", "values": false}}
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Probe duration",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "probe_duration_seconds{job=\"blackbox-http\", instance=~\"${target:regex}\"}",
+          "legendFormat": "{{instance}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "s"}, "overrides": []},
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}}
+    },
+    {
+      "id": 4,
+      "type": "timeseries",
+      "title": "Availability",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 5},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "probe_success{job=\"blackbox-http\", instance=~\"${target:regex}\"}",
+          "legendFormat": "{{instance}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "bool"}, "overrides": []},
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}}
+    },
+    {
+      "id": 5,
+      "type": "table",
+      "title": "HTTP status",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 9, "w": 24, "x": 0, "y": 13},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "probe_http_status_code{job=\"blackbox-http\", instance=~\"${target:regex}\"}",
+          "format": "table",
+          "instant": true
+        }
+      ],
+      "transformations": [
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {"Time": true, "__name__": true, "job": true},
+            "renameByName": {"Value": "status_code", "instance": "target"}
+          }
+        }
+      ]
+    }
+  ]
+}
@@ -0,0 +1,109 @@
+{
+  "uid": "homelab-containers-logs",
+  "title": "Homelab / Containers + Logs",
+  "tags": ["homelab", "cadvisor", "loki", "dozzle-replacement"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "templating": {
+    "list": [
+      {
+        "name": "service",
+        "label": "Service",
+        "type": "query",
+        "datasource": "Loki",
+        "query": "label_values(compose_service)",
+        "refresh": 1,
+        "includeAll": true,
+        "multi": true,
+        "allValue": ".+",
+        "current": {
+          "selected": true,
+          "text": "All",
+          "value": "$__all"
+        }
+      },
+      {
+        "name": "search",
+        "label": "Regex Match",
+        "type": "textbox",
+        "query": ".+",
+        "current": {
+          "selected": true,
+          "text": ".+",
+          "value": ".+"
+        }
+      }
+    ]
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "timeseries",
+      "title": "Container CPU",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[5m]))",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "cores"}, "overrides": []}
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Container memory",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (name) (container_memory_working_set_bytes{name!=\"\"})",
+          "legendFormat": "{{name}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "bytes"}, "overrides": []}
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Log error rate",
+      "datasource": "Loki",
+      "gridPos": {"h": 8, "w": 24, "x": 0, "y": 8},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "sum by (compose_service) (count_over_time({compose_service=~\"${service:regex}\", container=~\".+\"} |~ \"(?i)error|exception|panic|fatal|traceback|oom|killed\" [$__interval]))",
+          "legendFormat": "{{compose_service}}"
+        }
+      ]
+    },
+    {
+      "id": 4,
+      "type": "logs",
+      "title": "Live logs",
+      "datasource": "Loki",
+      "gridPos": {"h": 14, "w": 24, "x": 0, "y": 16},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "{compose_service=~\"${service:regex}\", container=~\".+\"} |~ \"$search\""
+        }
+      ],
+      "options": {
+        "showLabels": false,
+        "showTime": true,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      }
+    }
+  ]
+}
@@ -0,0 +1,102 @@
+{
+  "uid": "homelab-host-overview",
+  "title": "Homelab / Host Overview",
+  "tags": ["homelab", "node-exporter", "glances-replacement"],
+  "timezone": "browser",
+  "schemaVersion": 39,
+  "version": 1,
+  "refresh": "30s",
+  "time": {
+    "from": "now-6h",
+    "to": "now"
+  },
+  "panels": [
+    {
+      "id": 1,
+      "type": "timeseries",
+      "title": "CPU usage",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)",
+          "legendFormat": "CPU"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []}
+    },
+    {
+      "id": 2,
+      "type": "timeseries",
+      "title": "Memory usage",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "100 * (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes))",
+          "legendFormat": "Memory"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []}
+    },
+    {
+      "id": 3,
+      "type": "timeseries",
+      "title": "Filesystem usage",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 9, "w": 12, "x": 0, "y": 8},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "100 * (1 - node_filesystem_avail_bytes{fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{fstype!~\"tmpfs|overlay\"})",
+          "legendFormat": "{{mountpoint}}"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "percent", "min": 0, "max": 100}, "overrides": []},
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}}
+    },
+    {
+      "id": 4,
+      "type": "timeseries",
+      "title": "Network throughput",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 9, "w": 12, "x": 12, "y": 8},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "rate(node_network_receive_bytes_total{device!~\"lo|veth.*|br-.*|docker.*\"}[5m])",
+          "legendFormat": "{{device}} RX"
+        },
+        {
+          "refId": "B",
+          "expr": "rate(node_network_transmit_bytes_total{device!~\"lo|veth.*|br-.*|docker.*\"}[5m])",
+          "legendFormat": "{{device}} TX"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "Bps"}, "overrides": []},
+      "options": {"legend": {"displayMode": "list", "placement": "bottom"}}
+    },
+    {
+      "id": 5,
+      "type": "timeseries",
+      "title": "Disk IO",
+      "datasource": "Prometheus",
+      "gridPos": {"h": 8, "w": 24, "x": 0, "y": 17},
+      "targets": [
+        {
+          "refId": "A",
+          "expr": "rate(node_disk_read_bytes_total[5m])",
+          "legendFormat": "{{device}} read"
+        },
+        {
+          "refId": "B",
+          "expr": "rate(node_disk_written_bytes_total[5m])",
+          "legendFormat": "{{device}} write"
+        }
+      ],
+      "fieldConfig": {"defaults": {"unit": "Bps"}, "overrides": []}
+    }
+  ]
+}