Initial commit

templates/config/monitoring/prometheus/alert/Alertmanager.rules

@@ -0,0 +1,12 @@
+groups:
+- name: Alertmanager_Alerts
+  rules:
+
+  - alert: AlertmanagerConfigurationReload
+    expr: alertmanager_config_last_reload_successful != 1
+    for: 5m
+    labels:
+      severity: page
+    annotations:
+      summary: "AlertManager configuration reload (instance {{ $labels.instance }})"
+      description: "AlertManager configuration reload error\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"

templates/config/monitoring/prometheus/alert/Prometheus.rules

@@ -0,0 +1,12 @@
+groups:
+- name: Prometheus_Alerts
+  rules:
+
+  - alert: PrometheusConfigurationReload
+    expr: prometheus_config_last_reload_successful != 1
+    for: 2m
+    labels:
+      severity: error
+    annotations:
+      summary: "Prometheus configuration reload (instance {{ $labels.instance }})"
+      description: "Prometheus configuration reload error\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"

templates/config/monitoring/prometheus/prometheus.yml.erb

@@ -0,0 +1,41 @@
+global:
+  scrape_interval:     30s
+  evaluation_interval: 30s
+
+  # Attach these labels to any time series or alerts when communicating with
+  # external systems (federation, remote storage, Alertmanager).
+  external_labels:
+      monitor: 'prom'
+
+# Load and evaluate rules in this file every 'evaluation_interval' seconds.
+rule_files:
+  - 'alerts/*.rules'
+
+# alert
+alerting:
+  alertmanagers:
+  - scheme: http
+    static_configs:
+    - targets:
+        - "alertmanager:9093"
+
+scrape_configs:
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  - job_name: 'alertmanager'
+    static_configs:
+      - targets: ['alertmanager:9093']
+
+  - job_name: 'grafana'
+    static_configs:
+      - targets: ['grafana:3000']
+
+  - job_name: 'cadvisor'
+    static_configs:
+      - targets: ['cadvisor:8080']
+
+  - job_name: 'node-exporter'
+    static_configs:
+      - targets: ['node-exporter:9100']