init

prometheus/alert.yml

@@ -0,0 +1,12 @@
+groups:
+- name: Prometheus alert
+  rules:
+  # 对任何实例超过30秒无法联系的情况发出警报
+  - alert: 服务告警
+    expr: up == 0
+    for: 30s
+    labels:
+      severity: critical
+    annotations:
+      instance: "{{ $labels.instance }}"
+      description: "{{ $labels.job }} 服务已关闭"

prometheus/prometheus.yml

@@ -0,0 +1,36 @@
+# 全局配置
+global:
+  scrape_interval:     15s # 将搜刮间隔设置为每15秒一次。默认是每1分钟一次。
+  evaluation_interval: 15s # 每15秒评估一次规则。默认是每1分钟一次。
+
+# Alertmanager 配置
+alerting:
+  alertmanagers:
+  - static_configs:
+    - targets: ['alertmanager:9093']
+
+# 报警(触发器)配置
+rule_files:
+  - "alert.yml"
+
+# 搜刮配置
+scrape_configs:
+  - job_name: 'prometheus'
+    # 覆盖全局默认值，每15秒从该作业中刮取一次目标
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['localhost:9090']
+
+  - job_name: 'cadvisor'
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['cadvisor:8080']
+      labels:
+        instance: Prometheus服务器 
+
+  - job_name: 'node-exporter'
+    scrape_interval: 15s
+    static_configs:
+    - targets: ['node_exporter:9100']
+      labels:
+        instance: Prometheus服务器