mirror of
https://github.com/samanhappy/mcphub.git
synced 2026-01-01 04:08:52 -05:00
generate documents using mintlify (#153)
This commit is contained in:
samanhappy
613
docs/zh/features/monitoring.mdx
Normal file
613
docs/zh/features/monitoring.mdx
Normal file
@@ -0,0 +1,613 @@
|
||||
---
|
||||
title: '监控与分析'
|
||||
description: '全面监控 MCP 服务器性能、健康状况和使用情况'
|
||||
---
|
||||
|
||||
## 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：
|
||||
|
||||
```bash
|
||||
# 访问监控仪表板
|
||||
curl -X GET http://localhost:3000/api/monitoring/dashboard \
|
||||
-H "Authorization: Bearer $TOKEN"
|
||||
```
|
||||
|
||||
响应示例：
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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：
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```json
|
||||
{
|
||||
"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：
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```bash
|
||||
# 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：
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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：
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```yaml
|
||||
# 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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```json
|
||||
{
|
||||
"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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
```bash
|
||||
# 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
|
||||
|
||||
1. **指标丢失**
|
||||
|
||||
- 检查收集器配置
|
||||
- 验证网络连接
|
||||
- 检查存储空间
|
||||
|
||||
2. **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
|
||||
|
||||
3. **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
|
||||
|
||||
1. **监控层次化**: 建立应用、基础设施和业务三层监控
|
||||
2. **合理的警报**: 避免警报疲劳，设置合适的阈值
|
||||
3. **数据保留**: 根据业务需求设置适当的数据保留期
|
||||
4. **安全监控**: 监控安全相关的指标和事件
|
||||
5. **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](/zh/features/smart-routing) 和 [服务器管理](/zh/features/server-management) 文档。
|
||||
Reference in New Issue
Block a user