Add monitoring stack: Prometheus, Alertmanager, Grafana

monitoring/grafana/dashboards/webapp.json

@@ -0,0 +1,35 @@
+{
+  "title": "Webapp Overview",
+  "uid": "webapp-overview",
+  "schemaVersion": 39,
+  "refresh": "10s",
+  "time": { "from": "now-15m", "to": "now" },
+  "panels": [
+    {
+      "id": 1, "type": "stat", "title": "Webapp up (1 = yes)",
+      "gridPos": { "x": 0, "y": 0, "w": 6, "h": 6 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [ { "refId": "A", "expr": "up{job=\"webapp\"}" } ]
+    },
+    {
+      "id": 2, "type": "timeseries", "title": "Request rate by path (req/s)",
+      "gridPos": { "x": 6, "y": 0, "w": 18, "h": 6 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "targets": [ { "refId": "A", "expr": "sum by (path) (rate(http_requests_total[1m]))", "legendFormat": "{{path}}" } ]
+    },
+    {
+      "id": 3, "type": "timeseries", "title": "5xx error ratio",
+      "gridPos": { "x": 0, "y": 6, "w": 12, "h": 8 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "fieldConfig": { "defaults": { "unit": "percentunit" }, "overrides": [] },
+      "targets": [ { "refId": "A", "expr": "sum(rate(http_requests_total{status=~\"5..\"}[1m])) / sum(rate(http_requests_total[1m]))", "legendFormat": "5xx ratio" } ]
+    },
+    {
+      "id": 4, "type": "timeseries", "title": "p95 latency (s)",
+      "gridPos": { "x": 12, "y": 6, "w": 12, "h": 8 },
+      "datasource": { "type": "prometheus", "uid": "prometheus" },
+      "fieldConfig": { "defaults": { "unit": "s" }, "overrides": [] },
+      "targets": [ { "refId": "A", "expr": "histogram_quantile(0.95, sum by (le) (rate(http_request_duration_seconds_bucket[5m])))", "legendFormat": "p95" } ]
+    }
+  ]
+}

monitoring/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,7 @@
+apiVersion: 1
+providers:
+  - name: default
+    folder: ""
+    type: file
+    options:
+      path: /var/lib/grafana/dashboards

monitoring/grafana/provisioning/datasources/prometheus.yml

@@ -0,0 +1,8 @@
+apiVersion: 1
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true