Initial commit

templates/config/monitoring/alertmanager/config.yml.erb

@@ -0,0 +1,20 @@
+global:
+  # The smarthost and SMTP sender used for mail notifications.
+  smtp_smarthost: 'mail.fibitex.com:587'
+  smtp_from: 'info@fibitex.com'
+  smtp_auth_username: 'info@fibitex.com'     
+  smtp_auth_password: '1qaz2wsx!QAZ@WSX'
+  smtp_auth_identity: 'info@fibitex.com'
+
+route:
+  group_by: ['instance', 'severity']
+  group_wait: 30s
+  group_interval: 30s
+  repeat_interval: 30m
+  receiver: 'stage'
+
+receivers:
+- name: 'stage'
+  email_configs:
+    - send_resolved: true
+      to: 'EMAIL-MAILBOX-FOR-RECEIVER'

templates/config/monitoring/loki/local-config.yaml.erb

@@ -0,0 +1,37 @@
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+  grpc_listen_port: 9095
+
+ingester:
+  lifecycler:
+    address: 127.0.0.1
+    ring:
+      kvstore:
+        store: inmemory
+      replication_factor: 1
+  chunk_idle_period: 15m
+  wal:
+    enabled: true
+    dir: /loki/wal
+
+schema_config:
+  configs:
+  - from: 2022-01-01
+    store: boltdb
+    object_store: filesystem
+    schema: v11
+    index:
+      prefix: index_
+      period: 168h
+
+storage_config:
+  boltdb:
+    directory: ./loki/index
+
+  filesystem:
+    directory: ./loki/chunks
+
+limits_config:
+  enforce_metric_name: false

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']

templates/config/monitoring/promtail/docker-config.yaml.erb

@@ -0,0 +1,19 @@
+server:
+  http_listen_port: 9080
+  grpc_listen_port: 0
+
+positions:
+  filename: /tmp/positions.yaml
+
+clients:
+  - url: http://loki:3100/api/prom/push
+
+scrape_configs:
+- job_name: system
+  static_configs:
+  - targets:
+      - localhost
+    labels:
+      job: varlogs
+      host: monitoring
+      __path__: /var/log/*.log