add connect

prometheus/install-prometheus.sh

@@ -15,4 +15,28 @@ kubectl wait --for=condition=available --timeout=300s deployment/prometheus
 echo "Prometheus 安装完成！"
 echo "查看状态: kubectl get pods -l app=prometheus"
 
+echo ""
+echo "=========================================="
+echo "Prometheus 与 Alertmanager 集成配置"
+echo "注意：此部分需要在安装完 Alertmanager 后执行"
+echo "=========================================="
+
+echo "应用告警规则配置..."
+kubectl apply -f prometheus-rules-configmap.yaml
+
+echo "更新 Prometheus 配置以集成 Alertmanager..."
+kubectl apply -f prometheus-configmap.yaml
+kubectl apply -f prometheus-deployment.yaml
+
+echo "等待 Prometheus 重新启动..."
+kubectl wait --for=condition=available --timeout=300s deployment/prometheus
+
+echo "=========================================="
+echo "Prometheus 与 Alertmanager 集成完成！"
+echo "=========================================="
+echo "访问地址: https://prometheus-ops.t-aaron.com"
+echo "告警管理: https://alertmanager-ops.t-aaron.com"
+echo "已集成 Alertmanager，告警规则已加载"
+echo "=========================================="
+
 

prometheus/prometheus-configmap.yaml

@@ -8,7 +8,16 @@ data:
     global:
       scrape_interval: 15s
       evaluation_interval: 15s
+    
     rule_files:
+      - "/etc/prometheus/rules/*.yml"
+    
+    alerting:
+      alertmanagers:
+        - static_configs:
+            - targets:
+              - alertmanager-service:9093
+    
     scrape_configs:
     - job_name: 'prometheus'
       static_configs:

prometheus/prometheus-deployment.yaml

@@ -42,12 +42,17 @@ spec:
         volumeMounts:
         - name: prometheus-config
           mountPath: /etc/prometheus/
+        - name: prometheus-rules
+          mountPath: /etc/prometheus/rules/
         - name: prometheus-storage
           mountPath: /prometheus/
       volumes:
       - name: prometheus-config
         configMap:
           name: prometheus-config
+      - name: prometheus-rules
+        configMap:
+          name: prometheus-rules
       - name: prometheus-storage
         hostPath:
           path: /opt/prometheus/data

prometheus/prometheus-rules-configmap.yaml

@@ -0,0 +1,56 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-rules
+  namespace: default
+data:
+  kubernetes-alerts.yml: |
+    groups:
+    - name: kubernetes-alerts
+      rules:
+      - alert: PodCrashLooping
+        expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 15 > 0
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping"
+          description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is restarting {{ printf \"%.2f\" $value }} times / 15 minutes."
+
+      - alert: PodNotReady
+        expr: kube_pod_status_phase{phase=~"Pending|Unknown"} > 0
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is not ready"
+          description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for more than 5 minutes."
+
+      - alert: NodeNotReady
+        expr: kube_node_status_condition{condition="Ready",status="true"} == 0
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Node {{ $labels.node }} is not ready"
+          description: "Node {{ $labels.node }} has been unready for more than 5 minutes."
+
+    - name: prometheus-alerts
+      rules:
+      - alert: PrometheusDown
+        expr: up{job="prometheus"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Prometheus is down"
+          description: "Prometheus has been down for more than 1 minute."
+
+      - alert: PrometheusConfigReloadFailed
+        expr: prometheus_config_last_reload_successful == 0
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Prometheus configuration reload failed"
+          description: "Prometheus configuration reload has been failing for more than 5 minutes."