第一次提交

monitoring/alert_rules.yml

@@ -0,0 +1,185 @@
+# Prometheus 告警规则
+# 定义 KaMiXiTong 系统的告警阈值和条件
+
+groups:
+  - name: kamaxitong_alerts
+    rules:
+      # ==========================================
+      # 🔥 高优先级告警
+      # ==========================================
+
+      # 服务不可用
+      - alert: ServiceDown
+        expr: up == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: "KaMiXiTong 服务不可用"
+          description: "KaMiXiTong 服务已宕机超过 0 分钟"
+
+      # API 响应时间过长
+      - alert: HighResponseTime
+        expr: http_request_duration_seconds{quantile="0.95"} > 2
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "API 响应时间过长"
+          description: "95% 的请求响应时间超过 2 秒，已持续 5 分钟"
+
+      # 错误率过高
+      - alert: HighErrorRate
+        expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.1
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          summary: "API 错误率过高"
+          description: "5xx 错误率超过 10%，已持续 5 分钟"
+
+      # 数据库连接失败
+      - alert: DatabaseConnectionDown
+        expr: mysql_up == 0
+        for: 0m
+        labels:
+          severity: critical
+        annotations:
+          summary: "数据库连接失败"
+          description: "无法连接到数据库"
+
+      # ==========================================
+      # ⚠️ 中优先级告警
+      # ==========================================
+
+      # CPU 使用率过高
+      - alert: HighCPUUsage
+        expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "CPU 使用率过高"
+          description: "CPU 使用率超过 80%，已持续 10 分钟"
+
+      # 内存使用率过高
+      - alert: HighMemoryUsage
+        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "内存使用率过高"
+          description: "内存使用率超过 85%，已持续 10 分钟"
+
+      # 磁盘使用率过高
+      - alert: HighDiskUsage
+        expr: (1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100 > 90
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "磁盘使用率过高"
+          description: "磁盘使用率超过 90%，已持续 10 分钟"
+
+      # 数据库连接数过多
+      - alert: HighDatabaseConnections
+        expr: mysql_global_status_threads_connected / mysql_global_variables_max_connections * 100 > 80
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "数据库连接数过多"
+          description: "数据库连接数使用率超过 80%"
+
+      # 活跃会话数异常
+      - alert: HighActiveSessions
+        expr: flask_session_active > 1000
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "活跃会话数异常"
+          description: "活跃会话数超过 1000"
+
+      # ==========================================
+      # 📊 业务指标告警
+      # ==========================================
+
+      # 卡密验证失败率过高
+      - alert: HighLicenseVerificationFailure
+        expr: rate(license_verification_total{status="failed"}[5m]) > 0.05
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "卡密验证失败率过高"
+          description: "卡密验证失败率超过 5%"
+
+      # 订单支付失败率过高
+      - alert: HighPaymentFailureRate
+        expr: rate(payment_total{status="failed"}[5m]) > 0.1
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "订单支付失败率过高"
+          description: "订单支付失败率超过 10%"
+
+      # 活跃卡密数量异常
+      - alert: AbnormalActiveLicenses
+        expr: change(license_active_total[1h]) < -0.2
+        for: 30m
+        labels:
+          severity: warning
+        annotations:
+          summary: "活跃卡密数量异常下降"
+          description: "活跃卡密数量在 1 小时内下降超过 20%"
+
+      # ==========================================
+      # 🔍 安全告警
+      # ==========================================
+
+      # 频繁登录失败
+      - alert: HighLoginFailures
+        expr: rate(login_failures_total[5m]) > 0.5
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+频繁登录失败"
+          summary: "          description: "登录失败率过高，可能存在暴力破解攻击"
+
+      # API 频率限制触发
+      - alert: RateLimitTriggered
+        expr: rate(rate_limit_triggered_total[5m]) > 10
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "API 频率限制频繁触发"
+          description: "API 频率限制触发次数过多，可能存在 API 滥用"
+
+      # ==========================================
+      # 💡 信息性告警
+      # ==========================================
+
+      # 证书即将过期
+      - alert: SSLCertificateExpiring
+        expr: (ssl_certificate_expiry_seconds - time()) / 86400 < 30
+        for: 0m
+        labels:
+          severity: info
+        annotations:
+          summary: "SSL 证书即将过期"
+          description: "SSL 证书将在 30 天内过期"
+
+      # 数据库备份失败
+      - alert: DatabaseBackupFailed
+        expr: time() - database_backup_last_success_timestamp > 86400
+        for: 0m
+        labels:
+          severity: warning
+        annotations:
+          summary: "数据库备份失败"
+          description: "数据库备份已超过 24 小时未成功"

monitoring/grafana_dashboard.json

@@ -0,0 +1 @@
+{"dashboard": {"id": null, "title": "KaMiXiTong 系统监控", "tags": ["kamaxitong", "monitoring"], "timezone": "browser", "panels": [{"id": 1, "title": "系统概览", "type": "stat", "targets": [{"expr": "up{job=\"kamaxitong\"}", "legendFormat": "服务状态"}], "fieldConfig": {"defaults": {"color": {"mode": "thresholds"}, "thresholds": {"steps": [{"color": "red", "value": 0}, {"color": "green", "value": 1}]}}}}, {"id": 2, "title": "API 响应时间", "type": "graph", "targets": [{"expr": "http_request_duration_seconds{quantile=\"0.50\"}", "legendFormat": "50%"}, {"expr": "http_request_duration_seconds{quantile=\"0.95\"}", "legendFormat": "95%"}, {"expr": "http_request_duration_seconds{quantile=\"0.99\"}", "legendFormat": "99%"}]}, {"id": 3, "title": "请求量", "type": "graph", "targets": [{"expr": "rate(http_requests_total[5m])", "legendFormat": "{{method}} {{status}}"}]}, {"id": 4, "title": "错误率", "type": "graph", "targets": [{"expr": "rate(http_requests_total{status=~\"4..|5..\"}[5m]) / rate(http_requests_total[5m]) * 100", "legendFormat": "错误率"}]}, {"id": 5, "title": "CPU 使用率", "type": "graph", "targets": [{"expr": "100 - (avg by(instance) (irate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)", "legendFormat": "CPU 使用率"}]}, {"id": 6, "title": "内存使用率", "type": "graph", "targets": [{"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100", "legendFormat": "内存使用率"}]}, {"id": 7, "title": "磁盘使用率", "type": "graph", "targets": [{"expr": "(1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100", "legendFormat": "{{mountpoint}}"}]}, {"id": 8, "title": "数据库连接数", "type": "graph", "targets": [{"expr": "mysql_global_status_threads_connected", "legendFormat": "活跃连接"}, {"expr": "mysql_global_variables_max_connections", "legendFormat": "最大连接数"}]}, {"id": 9, "title": "卡密统计", "type": "stat", "targets": [{"expr": "license_total", "legendFormat": "总卡密数"}, {"expr": "license_active", "legendFormat": "活跃卡密"}, {"expr": "license_expired", "legendFormat": "过期卡密"}]}, {"id": 10, "title": "订单统计", "type": "stat", "targets": [{"expr": "order_total", "legendFormat": "总订单数"}, {"expr": "order_paid", "legendFormat": "已支付"}, {"expr": "order_pending", "legendFormat": "待支付"}]}], "time": {"from": "now-1h", "to": "now"}, "refresh": "5s"}}

monitoring/prometheus.yml

@@ -0,0 +1,56 @@
+# Prometheus 监控配置
+# 用于监控 KaMiXiTong 系统的性能和健康状态
+
+global:
+  scrape_interval: 15s  # 全局采集间隔
+  evaluation_interval: 15s  # 告警规则评估间隔
+
+# 告警管理器配置
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          - alertmanager:9093
+
+# 告警规则文件
+rule_files:
+  - "alert_rules.yml"
+
+# 采集配置
+scrape_configs:
+  # Prometheus 自身监控
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  # KaMiXiTong 应用监控
+  - job_name: 'kamaxitong'
+    static_configs:
+      - targets: ['localhost:5000']
+    metrics_path: '/api/v1/metrics'
+    scrape_interval: 15s
+    scrape_timeout: 10s
+
+  # 系统监控（需要安装 node_exporter）
+  - job_name: 'node'
+    static_configs:
+      - targets: ['localhost:9100']
+    scrape_interval: 15s
+
+  # 数据库监控（需要安装 mysqld_exporter 或 postgres_exporter）
+  - job_name: 'mysql'
+    static_configs:
+      - targets: ['localhost:9104']
+    scrape_interval: 15s
+
+  # Redis 监控（需要安装 redis_exporter）
+  - job_name: 'redis'
+    static_configs:
+      - targets: ['localhost:9121']
+    scrape_interval: 15s
+
+  # Nginx 监控（需要安装 nginx-prometheus-exporter）
+  - job_name: 'nginx'
+    static_configs:
+      - targets: ['localhost:9113']
+    scrape_interval: 15s