监控与分析 - MCPHub Documentation

概述

MCPHub 提供全面的监控和分析功能，帮助您跟踪 MCP 服务器的性能、健康状况和使用模式。系统提供实时指标、历史分析和智能警报。

实时监控

仪表板概览

主监控仪表板显示关键指标：

# 访问监控仪表板
curl -X GET http://localhost:3000/api/monitoring/dashboard \
  -H "Authorization: Bearer $TOKEN"

响应示例：

{
  "overview": {
    "totalServers": 12,
    "activeServers": 10,
    "totalRequests": 15420,
    "avgResponseTime": "245ms",
    "errorRate": "0.3%",
    "uptime": "99.9%"
  },
  "realtime": {
    "requestsPerMinute": 85,
    "activeConnections": 156,
    "memoryUsage": "68%",
    "cpuUsage": "42%"
  }
}

服务器健康状态

# 获取所有服务器状态
curl -X GET http://localhost:3000/api/monitoring/servers/health \
  -H "Authorization: Bearer $TOKEN"

性能指标

响应时间监控

{
  "responseTime": {
    "metrics": [
      {
        "serverId": "server-1",
        "average": "180ms",
        "p50": "150ms",
        "p95": "300ms",
        "p99": "500ms"
      }
    ],
    "alerts": {
      "slowResponse": {
        "threshold": "1s",
        "current": "180ms",
        "status": "normal"
      }
    }
  }
}

吞吐量分析

# 获取吞吐量统计
curl -X GET http://localhost:3000/api/monitoring/throughput \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "timeRange=1h" -d "granularity=5m"

响应示例：

{
  "timeRange": "1h",
  "granularity": "5m",
  "data": [
    {
      "timestamp": "2024-01-01T12:00:00Z",
      "totalRequests": 450,
      "successfulRequests": 448,
      "failedRequests": 2,
      "avgResponseTime": "230ms"
    }
  ],
  "summary": {
    "peakThroughput": 520,
    "averageThroughput": 412,
    "totalRequests": 4944
  }
}

资源使用监控

{
  "resources": {
    "cpu": {
      "usage": "42%",
      "cores": 8,
      "processes": [
        { "name": "mcp-server-1", "cpu": "15%" },
        { "name": "mcp-server-2", "cpu": "12%" }
      ]
    },
    "memory": {
      "total": "32GB",
      "used": "21.6GB",
      "available": "10.4GB",
      "byProcess": [
        { "name": "mcp-server-1", "memory": "2.1GB" },
        { "name": "mcp-server-2", "memory": "1.8GB" }
      ]
    },
    "network": {
      "bytesIn": "1.2GB",
      "bytesOut": "890MB",
      "packetsIn": 1250000,
      "packetsOut": 980000
    },
    "disk": {
      "total": "1TB",
      "used": "340GB",
      "available": "660GB",
      "iops": 1200
    }
  }
}

日志管理

集中化日志收集

配置日志聚合：

{
  "logging": {
    "centralized": true,
    "storage": {
      "type": "elasticsearch",
      "config": {
        "hosts": ["localhost:9200"],
        "index": "mcphub-logs",
        "retention": "30d"
      }
    },
    "levels": ["error", "warn", "info", "debug"],
    "sources": ["application", "mcp-servers", "nginx", "system"]
  }
}

实时日志查看

# 获取实时日志流
curl -X GET http://localhost:3000/api/monitoring/logs/stream \
  -H "Authorization: Bearer $TOKEN" \
  -H "Accept: text/event-stream"

# 过滤日志
curl -X GET http://localhost:3000/api/monitoring/logs \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "level=error" -d "server=server-1" -d "limit=100"

日志分析

# 错误模式分析
curl -X GET http://localhost:3000/api/monitoring/logs/analysis \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "type=error-patterns" -d "timeRange=24h"

响应示例：

{
  "analysis": {
    "errorPatterns": [
      {
        "pattern": "Connection timeout",
        "occurrences": 45,
        "trend": "increasing",
        "affectedServers": ["server-2", "server-3"]
      },
      {
        "pattern": "Memory allocation failed",
        "occurrences": 12,
        "trend": "stable",
        "affectedServers": ["server-1"]
      }
    ],
    "recommendations": ["检查服务器网络连接", "增加内存限制配置"]
  }
}

警报系统

配置警报规则

{
  "alerts": [
    {
      "name": "high-response-time",
      "description": "响应时间过高警报",
      "condition": "avg(response_time) > 1000ms over 5m",
      "severity": "warning",
      "notifications": {
        "email": ["admin@company.com"],
        "slack": "#alerts",
        "webhook": "https://hooks.company.com/alerts"
      }
    },
    {
      "name": "server-down",
      "description": "服务器宕机警报",
      "condition": "server_status == 'down'",
      "severity": "critical",
      "notifications": {
        "email": ["oncall@company.com"],
        "sms": ["+1234567890"],
        "pagerduty": "service-key"
      }
    },
    {
      "name": "high-error-rate",
      "description": "错误率过高",
      "condition": "error_rate > 5% over 10m",
      "severity": "error",
      "notifications": {
        "slack": "#dev-team"
      }
    }
  ]
}

警报通知

# 测试警报通知
curl -X POST http://localhost:3000/api/monitoring/alerts/test \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "alertName": "high-response-time",
    "channel": "email"
  }'

警报历史

# 获取警报历史
curl -X GET http://localhost:3000/api/monitoring/alerts/history \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "timeRange=7d" -d "severity=critical"

用户活动监控

用户会话跟踪

{
  "userActivity": {
    "activeSessions": 156,
    "totalUsers": 89,
    "sessionsByUser": [
      {
        "userId": "user123",
        "sessions": 3,
        "lastActivity": "2024-01-01T12:30:00Z",
        "totalRequests": 245
      }
    ],
    "topUsers": [
      { "userId": "power-user", "requests": 1250 },
      { "userId": "regular-user", "requests": 890 }
    ]
  }
}

使用模式分析

# 获取使用模式分析
curl -X GET http://localhost:3000/api/monitoring/usage-patterns \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "timeRange=30d"

响应示例：

{
  "patterns": {
    "peakHours": [9, 10, 14, 15, 16],
    "peakDays": ["tuesday", "wednesday", "thursday"],
    "toolUsage": [
      {"tool": "filesystem", "usage": 45%},
      {"tool": "web-search", "usage": 30%},
      {"tool": "database", "usage": 25%}
    ],
    "userBehavior": {
      "avgSessionDuration": "45m",
      "avgRequestsPerSession": 23,
      "returnRate": "78%"
    }
  }
}

容量规划

资源预测

{
  "capacityPlanning": {
    "currentCapacity": {
      "cpu": "42%",
      "memory": "68%",
      "network": "35%",
      "storage": "34%"
    },
    "predictions": {
      "timeHorizon": "30d",
      "cpuForecast": [
        { "date": "2024-01-07", "usage": "48%" },
        { "date": "2024-01-14", "usage": "52%" },
        { "date": "2024-01-21", "usage": "56%" },
        { "date": "2024-01-28", "usage": "61%" }
      ],
      "recommendations": [
        "考虑在第3周增加CPU资源",
        "内存使用稳定，暂不需要扩容",
        "建议监控网络带宽趋势"
      ]
    }
  }
}

自动扩缩容

{
  "autoScaling": {
    "enabled": true,
    "policies": [
      {
        "metric": "cpu_usage",
        "scaleUp": {
          "threshold": "80%",
          "duration": "5m",
          "action": "add_instance"
        },
        "scaleDown": {
          "threshold": "30%",
          "duration": "15m",
          "action": "remove_instance"
        }
      },
      {
        "metric": "request_queue_length",
        "scaleUp": {
          "threshold": 100,
          "duration": "2m",
          "action": "add_instance"
        }
      }
    ]
  }
}

性能分析报告

生成性能报告

# 生成周报
curl -X POST http://localhost:3000/api/monitoring/reports \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "type": "performance",
    "timeRange": "7d",
    "format": "pdf",
    "sections": [
      "overview",
      "response_times",
      "error_analysis",
      "resource_usage",
      "recommendations"
    ],
    "recipients": ["manager@company.com"]
  }'

自定义报告

{
  "customReport": {
    "name": "monthly-summary",
    "schedule": "0 0 1 * *",
    "template": "executive-summary",
    "data": {
      "kpis": ["uptime", "avg_response_time", "total_requests", "error_rate", "user_satisfaction"],
      "comparisons": {
        "previousMonth": true,
        "yearOverYear": true
      }
    },
    "distribution": {
      "email": ["executives@company.com"],
      "dashboard": true,
      "archive": true
    }
  }
}

监控 API

指标查询

# 查询自定义指标
curl -X POST http://localhost:3000/api/monitoring/query \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "query": "avg(response_time) by (server_id)",
    "timeRange": "1h",
    "step": "5m"
  }'

事件跟踪

# 记录自定义事件
curl -X POST http://localhost:3000/api/monitoring/events \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $TOKEN" \
  -d '{
    "type": "deployment",
    "title": "服务器更新",
    "description": "部署新版本 v2.1.0",
    "tags": ["deployment", "version-2.1.0"],
    "metadata": {
      "version": "2.1.0",
      "servers": ["server-1", "server-2"]
    }
  }'

第三方集成

Prometheus 集成

# prometheus.yml
global:
  scrape_interval: 15s

scrape_configs:
  - job_name: 'mcphub'
    static_configs:
      - targets: ['localhost:3000']
    metrics_path: '/api/monitoring/prometheus'
    scrape_interval: 30s

Grafana 仪表板

{
  "dashboard": {
    "title": "MCPHub 监控",
    "panels": [
      {
        "title": "请求率",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(mcphub_requests_total[5m])",
            "legendFormat": "{{server_id}}"
          }
        ]
      },
      {
        "title": "响应时间",
        "type": "graph",
        "targets": [
          {
            "expr": "histogram_quantile(0.95, mcphub_response_time_histogram)",
            "legendFormat": "95th percentile"
          }
        ]
      }
    ]
  }
}

ELK Stack 集成

{
  "logstash": {
    "input": {
      "beats": {
        "port": 5044
      }
    },
    "filter": {
      "if": "[fields][service] == 'mcphub'",
      "json": {
        "source": "message"
      },
      "date": {
        "match": ["timestamp", "ISO8601"]
      }
    },
    "output": {
      "elasticsearch": {
        "hosts": ["localhost:9200"],
        "index": "mcphub-logs-%{+YYYY.MM.dd}"
      }
    }
  }
}

故障排除

监控问题诊断

# 检查监控服务状态
curl -X GET http://localhost:3000/api/monitoring/health \
  -H "Authorization: Bearer $TOKEN"

# 验证指标收集
curl -X GET http://localhost:3000/api/monitoring/metrics/validation \
  -H "Authorization: Bearer $TOKEN"

性能问题分析

# 性能瓶颈分析
curl -X GET http://localhost:3000/api/monitoring/performance/bottlenecks \
  -H "Authorization: Bearer $TOKEN" \
  -G -d "timeRange=1h"

常见监控问题

指标丢失
- 检查收集器配置
- 验证网络连接
- 检查存储空间
警报不触发
- 验证警报规则语法
- 检查通知配置
- 测试通知渠道
仪表板加载缓慢
- 优化查询时间范围
- 增加数据聚合
- 检查数据库性能

最佳实践

监控层次化: 建立应用、基础设施和业务三层监控
合理的警报: 避免警报疲劳，设置合适的阈值
数据保留: 根据业务需求设置适当的数据保留期
安全监控: 监控安全相关的指标和事件
持续优化: 定期审查和优化监控配置

有关更多信息，请参阅智能路由和服务器管理文档。

​概述

​实时监控

​仪表板概览

​服务器健康状态

​性能指标

​响应时间监控

​吞吐量分析

​资源使用监控

​日志管理

​集中化日志收集

​实时日志查看

​日志分析

​警报系统

​配置警报规则

​警报通知

​警报历史

​用户活动监控

​用户会话跟踪

​使用模式分析

​容量规划

​资源预测

​自动扩缩容

​性能分析报告

​生成性能报告

​自定义报告

​监控 API

​指标查询

​事件跟踪

​第三方集成

​Prometheus 集成

​Grafana 仪表板

​ELK Stack 集成

​故障排除

​监控问题诊断

​性能问题分析

​常见监控问题

​最佳实践

概述

实时监控

仪表板概览

服务器健康状态

性能指标

响应时间监控

吞吐量分析

资源使用监控

日志管理

集中化日志收集

实时日志查看

日志分析

警报系统

配置警报规则

警报通知

警报历史

用户活动监控

用户会话跟踪

使用模式分析

容量规划

资源预测

自动扩缩容

性能分析报告

生成性能报告

自定义报告

监控 API

指标查询

事件跟踪

第三方集成

Prometheus 集成

Grafana 仪表板

ELK Stack 集成

故障排除

监控问题诊断

性能问题分析

常见监控问题

最佳实践