📚 第二章：安装部署与环境配置

2.1 系统要求

硬件要求

最小配置

• CPU：1 核心
• 内存：512MB
• 磁盘：1GB 可用空间
• 网络：100Mbps

推荐配置

• CPU：2+ 核心
• 内存：2GB+
• 磁盘：10GB+ SSD
• 网络：1Gbps

生产环境配置

• CPU：4+ 核心
• 内存：8GB+
• 磁盘：50GB+ SSD（RAID 1）
• 网络：10Gbps

软件要求

操作系统支持

• Linux：Ubuntu 18.04+, CentOS 7+, RHEL 7+
• Windows：Windows Server 2016+
• macOS：macOS 10.14+

依赖软件

• Go：1.17+（源码编译）
• Docker：20.10+（容器部署）
• Kubernetes：1.20+（K8s 部署）

网络要求

端口配置

• 9093：Web UI 和 API 端口
• 9094：集群通信端口
• 9095：额外的集群端口（可选）

防火墙规则

# Ubuntu/Debian
sudo ufw allow 9093/tcp
sudo ufw allow 9094/tcp

# CentOS/RHEL
sudo firewall-cmd --permanent --add-port=9093/tcp
sudo firewall-cmd --permanent --add-port=9094/tcp
sudo firewall-cmd --reload

2.2 二进制安装

下载安装包

# 设置版本变量
VERSION="0.25.0"
ARCH="linux-amd64"

# 下载二进制包
wget https://github.com/prometheus/alertmanager/releases/download/v${VERSION}/alertmanager-${VERSION}.${ARCH}.tar.gz

# 解压安装包
tar xzf alertmanager-${VERSION}.${ARCH}.tar.gz
cd alertmanager-${VERSION}.${ARCH}

# 查看文件内容
ls -la
# alertmanager  amtool  alertmanager.yml  LICENSE  NOTICE

安装配置

# 创建用户和目录
sudo useradd --no-create-home --shell /bin/false alertmanager
sudo mkdir -p /etc/alertmanager /var/lib/alertmanager
sudo chown alertmanager:alertmanager /etc/alertmanager /var/lib/alertmanager

# 复制二进制文件
sudo cp alertmanager amtool /usr/local/bin/
sudo chown alertmanager:alertmanager /usr/local/bin/alertmanager /usr/local/bin/amtool
sudo chmod +x /usr/local/bin/alertmanager /usr/local/bin/amtool

# 复制配置文件
sudo cp alertmanager.yml /etc/alertmanager/
sudo chown alertmanager:alertmanager /etc/alertmanager/alertmanager.yml

创建系统服务

# 创建 systemd 服务文件
sudo tee /etc/systemd/system/alertmanager.service > /dev/null <<EOF
[Unit]
Description=Alertmanager
Wants=network-online.target
After=network-online.target

[Service]
User=alertmanager
Group=alertmanager
Type=simple
ExecStart=/usr/local/bin/alertmanager \
    --config.file=/etc/alertmanager/alertmanager.yml \
    --storage.path=/var/lib/alertmanager/ \
    --web.external-url=http://localhost:9093
Restart=always
RestartSec=5

[Install]
WantedBy=multi-user.target
EOF

# 重新加载 systemd 配置
sudo systemctl daemon-reload

# 启用并启动服务
sudo systemctl enable alertmanager
sudo systemctl start alertmanager

# 检查服务状态
sudo systemctl status alertmanager

验证安装

# 检查进程
ps aux | grep alertmanager

# 检查端口
ss -tlnp | grep 9093

# 测试 API
curl http://localhost:9093/api/v1/status

# 访问 Web UI
# 浏览器访问：http://localhost:9093

2.3 Docker 部署

基础 Docker 部署

# 创建配置目录
mkdir -p /opt/alertmanager/config
mkdir -p /opt/alertmanager/data

# 创建基础配置文件
cat > /opt/alertmanager/config/alertmanager.yml <<EOF
global:
  smtp_smarthost: 'localhost:587'
  smtp_from: 'alertmanager@example.com'

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'web.hook'

receivers:
- name: 'web.hook'
  webhook_configs:
  - url: 'http://127.0.0.1:5001/'
EOF

# 运行 Alertmanager 容器
docker run -d \
  --name alertmanager \
  --restart unless-stopped \
  -p 9093:9093 \
  -v /opt/alertmanager/config:/etc/alertmanager \
  -v /opt/alertmanager/data:/alertmanager \
  prom/alertmanager:latest \
  --config.file=/etc/alertmanager/alertmanager.yml \
  --storage.path=/alertmanager \
  --web.external-url=http://localhost:9093

Docker Compose 部署

# docker-compose.yml
version: '3.8'

services:
  alertmanager:
    image: prom/alertmanager:v0.25.0
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./config/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - ./templates:/etc/alertmanager/templates:ro
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
      - '--web.route-prefix=/'
      - '--log.level=info'
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

volumes:
  alertmanager_data:
    driver: local

networks:
  monitoring:
    driver: bridge

完整监控栈部署

# monitoring-stack.yml
version: '3.8'

services:
  prometheus:
    image: prom/prometheus:v2.40.0
    container_name: prometheus
    restart: unless-stopped
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--storage.tsdb.retention.time=15d'
      - '--web.enable-lifecycle'
      - '--alertmanager.url=http://alertmanager:9093'
    networks:
      - monitoring
    depends_on:
      - alertmanager

  alertmanager:
    image: prom/alertmanager:v0.25.0
    container_name: alertmanager
    restart: unless-stopped
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - ./alertmanager/templates:/etc/alertmanager/templates:ro
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:9.3.0
    container_name: grafana
    restart: unless-stopped
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin123
      - GF_USERS_ALLOW_SIGN_UP=false
    networks:
      - monitoring
    depends_on:
      - prometheus

  node-exporter:
    image: prom/node-exporter:v1.5.0
    container_name: node-exporter
    restart: unless-stopped
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring

volumes:
  prometheus_data:
  alertmanager_data:
  grafana_data:

networks:
  monitoring:
    driver: bridge

启动和管理

# 启动服务
docker-compose -f monitoring-stack.yml up -d

# 查看服务状态
docker-compose -f monitoring-stack.yml ps

# 查看日志
docker-compose -f monitoring-stack.yml logs alertmanager

# 重启服务
docker-compose -f monitoring-stack.yml restart alertmanager

# 停止服务
docker-compose -f monitoring-stack.yml down

# 更新配置后重新加载
docker-compose -f monitoring-stack.yml exec alertmanager \
  kill -HUP 1

2.4 Kubernetes 部署

命名空间和 RBAC

# namespace.yaml
apiVersion: v1
kind: Namespace
metadata:
  name: monitoring
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: alertmanager
  namespace: monitoring
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: alertmanager
rules:
- apiGroups: [""]
  resources: ["nodes", "services", "endpoints", "pods"]
  verbs: ["get", "list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: alertmanager
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: alertmanager
subjects:
- kind: ServiceAccount
  name: alertmanager
  namespace: monitoring

ConfigMap 配置

# configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: monitoring
data:
  alertmanager.yml: |
    global:
      smtp_smarthost: 'smtp.gmail.com:587'
      smtp_from: 'alerts@example.com'
      smtp_auth_username: 'alerts@example.com'
      smtp_auth_password: 'app-password'
      resolve_timeout: 5m
    
    templates:
      - '/etc/alertmanager/templates/*.tmpl'
    
    route:
      group_by: ['alertname', 'cluster', 'service']
      group_wait: 10s
      group_interval: 10s
      repeat_interval: 1h
      receiver: 'default'
      routes:
      - match:
          severity: critical
        receiver: 'critical-alerts'
        group_wait: 5s
        repeat_interval: 30m
      - match:
          severity: warning
        receiver: 'warning-alerts'
        repeat_interval: 2h
      - match_re:
          service: '^(web|api|database).*'
        receiver: 'app-team'
    
    receivers:
    - name: 'default'
      email_configs:
      - to: 'admin@example.com'
        subject: '[ALERT] {{ .GroupLabels.alertname }}'
        body: |
          {{ range .Alerts }}
          Alert: {{ .Annotations.summary }}
          Description: {{ .Annotations.description }}
          Labels: {{ range .Labels.SortedPairs }}{{ .Name }}={{ .Value }} {{ end }}
          {{ end }}
    
    - name: 'critical-alerts'
      email_configs:
      - to: 'oncall@example.com'
        subject: '[CRITICAL] {{ .GroupLabels.alertname }}'
        body: |
          CRITICAL ALERT!
          
          {{ range .Alerts }}
          Alert: {{ .Annotations.summary }}
          Description: {{ .Annotations.description }}
          Severity: {{ .Labels.severity }}
          Instance: {{ .Labels.instance }}
          Time: {{ .StartsAt }}
          {{ end }}
      slack_configs:
      - api_url: 'https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK'
        channel: '#critical-alerts'
        title: 'Critical Alert'
        text: '{{ range .Alerts }}{{ .Annotations.summary }}{{ end }}'
    
    - name: 'warning-alerts'
      email_configs:
      - to: 'team@example.com'
        subject: '[WARNING] {{ .GroupLabels.alertname }}'
        body: |
          {{ range .Alerts }}
          Alert: {{ .Annotations.summary }}
          Description: {{ .Annotations.description }}
          Labels: {{ range .Labels.SortedPairs }}{{ .Name }}={{ .Value }} {{ end }}
          {{ end }}
    
    - name: 'app-team'
      email_configs:
      - to: 'app-team@example.com'
        subject: '[APP] {{ .GroupLabels.alertname }}'
        body: |
          Application Alert:
          {{ range .Alerts }}
          Service: {{ .Labels.service }}
          Alert: {{ .Annotations.summary }}
          Description: {{ .Annotations.description }}
          {{ end }}
    
    inhibit_rules:
    - source_match:
        severity: 'critical'
      target_match:
        severity: 'warning'
      equal: ['alertname', 'instance']
  
  notification.tmpl: |
    {{ define "cluster" }}{{ .ExternalURL | reReplaceAll ".*alertmanager\\.(.*?)\\:.*" "$1" }}{{ end }}
    
    {{ define "slack.default.title" }}
    [{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}] {{ .GroupLabels.SortedPairs.Values | join " " }} {{ if gt (len .GroupLabels) 0 }}({{ template "cluster" . }}){{ end }}
    {{ end }}
    
    {{ define "slack.default.text" }}
    {{ range .Alerts }}
    {{ if .Annotations.summary }}{{ .Annotations.summary }}{{ end }}
    {{ if .Annotations.description }}{{ .Annotations.description }}{{ end }}
    {{ end }}
    {{ end }}

Deployment 部署

# deployment.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: alertmanager
  namespace: monitoring
  labels:
    app: alertmanager
spec:
  replicas: 1
  selector:
    matchLabels:
      app: alertmanager
  template:
    metadata:
      labels:
        app: alertmanager
    spec:
      serviceAccountName: alertmanager
      containers:
      - name: alertmanager
        image: prom/alertmanager:v0.25.0
        ports:
        - containerPort: 9093
          name: web
        - containerPort: 9094
          name: cluster
        args:
          - '--config.file=/etc/alertmanager/alertmanager.yml'
          - '--storage.path=/alertmanager'
          - '--web.external-url=http://alertmanager.monitoring.svc.cluster.local:9093'
          - '--web.route-prefix=/'
          - '--log.level=info'
        volumeMounts:
        - name: config-volume
          mountPath: /etc/alertmanager
        - name: storage-volume
          mountPath: /alertmanager
        resources:
          requests:
            memory: "256Mi"
            cpu: "100m"
          limits:
            memory: "512Mi"
            cpu: "200m"
        livenessProbe:
          httpGet:
            path: /-/healthy
            port: 9093
          initialDelaySeconds: 30
          timeoutSeconds: 10
        readinessProbe:
          httpGet:
            path: /-/ready
            port: 9093
          initialDelaySeconds: 5
          timeoutSeconds: 5
      volumes:
      - name: config-volume
        configMap:
          name: alertmanager-config
      - name: storage-volume
        emptyDir: {}

Service 和 Ingress

# service.yaml
apiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: monitoring
  labels:
    app: alertmanager
spec:
  selector:
    app: alertmanager
  ports:
  - name: web
    port: 9093
    targetPort: 9093
    protocol: TCP
  - name: cluster
    port: 9094
    targetPort: 9094
    protocol: TCP
  type: ClusterIP
---
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: alertmanager
  namespace: monitoring
  annotations:
    nginx.ingress.kubernetes.io/rewrite-target: /
    nginx.ingress.kubernetes.io/ssl-redirect: "true"
spec:
  tls:
  - hosts:
    - alertmanager.example.com
    secretName: alertmanager-tls
  rules:
  - host: alertmanager.example.com
    http:
      paths:
      - path: /
        pathType: Prefix
        backend:
          service:
            name: alertmanager
            port:
              number: 9093

部署和验证

# 应用配置
kubectl apply -f namespace.yaml
kubectl apply -f configmap.yaml
kubectl apply -f deployment.yaml
kubectl apply -f service.yaml

# 检查部署状态
kubectl get pods -n monitoring
kubectl get svc -n monitoring
kubectl get ingress -n monitoring

# 查看日志
kubectl logs -f deployment/alertmanager -n monitoring

# 端口转发测试
kubectl port-forward svc/alertmanager 9093:9093 -n monitoring

# 访问 Web UI
# 浏览器访问：http://localhost:9093

2.5 高可用集群部署

集群架构设计

graph TB
    subgraph "Load Balancer"
        LB[HAProxy/Nginx]
    end
    
    subgraph "Alertmanager Cluster"
        AM1[Alertmanager-1<br/>:9093]
        AM2[Alertmanager-2<br/>:9093]
        AM3[Alertmanager-3<br/>:9093]
    end
    
    subgraph "Prometheus Instances"
        P1[Prometheus-1]
        P2[Prometheus-2]
    end
    
    subgraph "Notification Channels"
        EMAIL[Email]
        SLACK[Slack]
        WEBHOOK[Webhook]
    end
    
    P1 --> LB
    P2 --> LB
    LB --> AM1
    LB --> AM2
    LB --> AM3
    
    AM1 -.->|Gossip| AM2
    AM2 -.->|Gossip| AM3
    AM3 -.->|Gossip| AM1
    
    AM1 --> EMAIL
    AM2 --> SLACK
    AM3 --> WEBHOOK

Docker Swarm 集群部署

# alertmanager-cluster.yml
version: '3.8'

services:
  alertmanager:
    image: prom/alertmanager:v0.25.0
    networks:
      - monitoring
    volumes:
      - alertmanager-config:/etc/alertmanager:ro
      - alertmanager-data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://alertmanager:9093'
      - '--cluster.listen-address=0.0.0.0:9094'
      - '--cluster.peer=tasks.alertmanager:9094'
      - '--cluster.reconnect-timeout=10m'
      - '--cluster.gossip-interval=200ms'
      - '--cluster.pushpull-interval=60s'
    deploy:
      replicas: 3
      placement:
        max_replicas_per_node: 1
        constraints:
          - node.role == worker
      resources:
        limits:
          memory: 512M
          cpus: '0.5'
        reservations:
          memory: 256M
          cpus: '0.25'
      restart_policy:
        condition: on-failure
        delay: 5s
        max_attempts: 3
      update_config:
        parallelism: 1
        delay: 10s
        failure_action: rollback
        order: stop-first
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s

  alertmanager-lb:
    image: nginx:alpine
    ports:
      - "9093:80"
    networks:
      - monitoring
    volumes:
      - alertmanager-nginx-config:/etc/nginx/conf.d:ro
    deploy:
      replicas: 2
      placement:
        constraints:
          - node.role == manager
      resources:
        limits:
          memory: 128M
          cpus: '0.25'
        reservations:
          memory: 64M
          cpus: '0.1'
    depends_on:
      - alertmanager

volumes:
  alertmanager-config:
    external: true
  alertmanager-data:
  alertmanager-nginx-config:
    external: true

networks:
  monitoring:
    external: true

Kubernetes StatefulSet 部署

# statefulset.yaml
apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: alertmanager
  namespace: monitoring
spec:
  serviceName: alertmanager-headless
  replicas: 3
  selector:
    matchLabels:
      app: alertmanager
  template:
    metadata:
      labels:
        app: alertmanager
    spec:
      serviceAccountName: alertmanager
      containers:
      - name: alertmanager
        image: prom/alertmanager:v0.25.0
        ports:
        - containerPort: 9093
          name: web
        - containerPort: 9094
          name: cluster
        args:
          - '--config.file=/etc/alertmanager/alertmanager.yml'
          - '--storage.path=/alertmanager'
          - '--web.external-url=http://alertmanager.monitoring.svc.cluster.local:9093'
          - '--cluster.listen-address=0.0.0.0:9094'
          - '--cluster.peer=alertmanager-0.alertmanager-headless.monitoring.svc.cluster.local:9094'
          - '--cluster.peer=alertmanager-1.alertmanager-headless.monitoring.svc.cluster.local:9094'
          - '--cluster.peer=alertmanager-2.alertmanager-headless.monitoring.svc.cluster.local:9094'
          - '--cluster.reconnect-timeout=10m'
        volumeMounts:
        - name: config-volume
          mountPath: /etc/alertmanager
        - name: storage-volume
          mountPath: /alertmanager
        resources:
          requests:
            memory: "256Mi"
            cpu: "100m"
          limits:
            memory: "512Mi"
            cpu: "200m"
        livenessProbe:
          httpGet:
            path: /-/healthy
            port: 9093
          initialDelaySeconds: 30
          timeoutSeconds: 10
        readinessProbe:
          httpGet:
            path: /-/ready
            port: 9093
          initialDelaySeconds: 5
          timeoutSeconds: 5
      volumes:
      - name: config-volume
        configMap:
          name: alertmanager-config
  volumeClaimTemplates:
  - metadata:
      name: storage-volume
    spec:
      accessModes: ["ReadWriteOnce"]
      storageClassName: "fast-ssd"
      resources:
        requests:
          storage: 10Gi
---
apiVersion: v1
kind: Service
metadata:
  name: alertmanager-headless
  namespace: monitoring
spec:
  clusterIP: None
  selector:
    app: alertmanager
  ports:
  - name: web
    port: 9093
    targetPort: 9093
  - name: cluster
    port: 9094
    targetPort: 9094

负载均衡配置

# nginx.conf
upstream alertmanager {
    least_conn;
    server alertmanager-0.alertmanager-headless.monitoring.svc.cluster.local:9093 max_fails=3 fail_timeout=30s;
    server alertmanager-1.alertmanager-headless.monitoring.svc.cluster.local:9093 max_fails=3 fail_timeout=30s;
    server alertmanager-2.alertmanager-headless.monitoring.svc.cluster.local:9093 max_fails=3 fail_timeout=30s;
}

server {
    listen 80;
    server_name alertmanager.example.com;
    
    location / {
        proxy_pass http://alertmanager;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        
        # 健康检查
        proxy_next_upstream error timeout invalid_header http_500 http_502 http_503 http_504;
        proxy_connect_timeout 5s;
        proxy_send_timeout 10s;
        proxy_read_timeout 10s;
    }
    
    location /-/healthy {
        access_log off;
        proxy_pass http://alertmanager;
    }
}

2.6 配置验证和测试

配置文件验证

# 使用 amtool 验证配置
amtool config check /etc/alertmanager/alertmanager.yml

# 验证路由配置
amtool config routes show --config.file=/etc/alertmanager/alertmanager.yml

# 测试路由匹配
amtool config routes test \
  --config.file=/etc/alertmanager/alertmanager.yml \
  alertname=TestAlert severity=warning

API 测试

# 检查状态
curl -s http://localhost:9093/api/v1/status | jq .

# 获取配置信息
curl -s http://localhost:9093/api/v1/status | jq '.data.configYAML'

# 检查集群状态
curl -s http://localhost:9093/api/v1/status | jq '.data.clusterStatus'

# 发送测试告警
curl -XPOST http://localhost:9093/api/v1/alerts -H "Content-Type: application/json" -d '[
  {
    "labels": {
      "alertname": "TestAlert",
      "severity": "warning",
      "instance": "localhost:9090"
    },
    "annotations": {
      "summary": "This is a test alert",
      "description": "This alert is for testing purposes"
    },
    "startsAt": "'$(date -u +%Y-%m-%dT%H:%M:%S.%3NZ)'"
  }
]'

健康检查脚本

#!/bin/bash
# healthcheck.sh

ALERTMANAGER_URL="http://localhost:9093"
TIMEOUT=10

# 检查服务是否运行
check_service() {
    if ! pgrep -f alertmanager > /dev/null; then
        echo "ERROR: Alertmanager process not running"
        return 1
    fi
    echo "OK: Alertmanager process is running"
}

# 检查端口是否监听
check_port() {
    if ! nc -z localhost 9093; then
        echo "ERROR: Port 9093 is not listening"
        return 1
    fi
    echo "OK: Port 9093 is listening"
}

# 检查 API 响应
check_api() {
    local response
    response=$(curl -s --max-time $TIMEOUT "$ALERTMANAGER_URL/api/v1/status")
    
    if [ $? -ne 0 ]; then
        echo "ERROR: Failed to connect to Alertmanager API"
        return 1
    fi
    
    if ! echo "$response" | jq -e '.status == "success"' > /dev/null 2>&1; then
        echo "ERROR: Alertmanager API returned error: $response"
        return 1
    fi
    
    echo "OK: Alertmanager API is responding"
}

# 检查配置文件
check_config() {
    if ! amtool config check /etc/alertmanager/alertmanager.yml > /dev/null 2>&1; then
        echo "ERROR: Configuration file is invalid"
        return 1
    fi
    echo "OK: Configuration file is valid"
}

# 主检查函数
main() {
    echo "=== Alertmanager Health Check ==="
    echo "Timestamp: $(date)"
    echo
    
    local exit_code=0
    
    check_service || exit_code=1
    check_port || exit_code=1
    check_api || exit_code=1
    check_config || exit_code=1
    
    echo
    if [ $exit_code -eq 0 ]; then
        echo "✅ All checks passed"
    else
        echo "❌ Some checks failed"
    fi
    
    return $exit_code
}

main "$@"

2.7 性能调优

系统级优化

# 调整文件描述符限制
echo "alertmanager soft nofile 65536" >> /etc/security/limits.conf
echo "alertmanager hard nofile 65536" >> /etc/security/limits.conf

# 调整内核参数
echo "net.core.somaxconn = 1024" >> /etc/sysctl.conf
echo "net.ipv4.tcp_max_syn_backlog = 1024" >> /etc/sysctl.conf
sysctl -p

# 调整 systemd 服务限制
mkdir -p /etc/systemd/system/alertmanager.service.d
cat > /etc/systemd/system/alertmanager.service.d/limits.conf <<EOF
[Service]
LimitNOFILE=65536
LimitNPROC=65536
EOF

systemctl daemon-reload
systemctl restart alertmanager

应用级优化

# 优化启动参数
/usr/local/bin/alertmanager \
    --config.file=/etc/alertmanager/alertmanager.yml \
    --storage.path=/var/lib/alertmanager/ \
    --web.external-url=http://localhost:9093 \
    --web.max-connections=512 \
    --cluster.tcp-timeout=10s \
    --cluster.gossip-interval=200ms \
    --cluster.pushpull-interval=60s \
    --cluster.settle-timeout=60s \
    --log.level=warn

监控指标

# 关键监控指标
prometheus_rules:
- alert: AlertmanagerDown
  expr: up{job="alertmanager"} == 0
  for: 5m
  labels:
    severity: critical
  annotations:
    summary: "Alertmanager instance is down"

- alert: AlertmanagerHighMemoryUsage
  expr: process_resident_memory_bytes{job="alertmanager"} / 1024 / 1024 > 512
  for: 10m
  labels:
    severity: warning
  annotations:
    summary: "Alertmanager memory usage is high"

- alert: AlertmanagerConfigReloadFailed
  expr: increase(alertmanager_config_last_reload_successful[5m]) == 0
  for: 5m
  labels:
    severity: warning
  annotations:
    summary: "Alertmanager config reload failed"

本章小结

本章详细介绍了 Alertmanager 的各种安装部署方式：

部署方式对比

部署方式	适用场景	优点	缺点
二进制安装	传统环境、性能要求高	性能最佳、资源占用少	管理复杂、升级困难
Docker 部署	开发测试、快速部署	部署简单、环境隔离	性能略低、依赖 Docker
Kubernetes	云原生环境、大规模部署	自动化管理、高可用	复杂度高、学习成本大
集群部署	生产环境、高可用要求	高可用、负载分担	配置复杂、资源消耗大

最佳实践

1. 环境选择：根据实际需求选择合适的部署方式
2. 资源规划：合理分配 CPU、内存和存储资源
3. 网络配置：确保端口开放和网络连通性
4. 安全配置：使用专用用户和适当的权限
5. 监控告警：部署监控和健康检查
6. 备份策略：定期备份配置和数据

下一步学习

在下一章中，我们将深入学习 Alertmanager 的配置文件详解，包括： - 配置文件结构和语法 - 全局配置选项 - 路由规则配置 - 接收器配置详解 - 抑制规则设置

---

下一章： 配置文件详解