Go微服务监控实战指南

引言

在微服务架构中，监控系统的重要性不言而喻。本文将详细介绍如何使用Prometheus、Grafana等工具构建完整的Go微服务监控体系。

监控指标

基础指标收集

package metrics

import (
    "github.com/prometheus/client_golang/prometheus"
    "github.com/prometheus/client_golang/prometheus/promauto"
)

var (
    // HTTP请求计数器
    RequestCounter = promauto.NewCounterVec(
        prometheus.CounterOpts{
            Name: "http_requests_total",
            Help: "Total number of HTTP requests",
        },
        []string{"method", "endpoint", "status"},
    )
    
    // 请求延迟直方图
    RequestDuration = promauto.NewHistogramVec(
        prometheus.HistogramOpts{
            Name: "http_request_duration_seconds",
            Help: "HTTP request duration in seconds",
            Buckets: []float64{0.1, 0.3, 0.5, 0.7, 1, 2, 5},
        },
        []string{"method", "endpoint"},
    )
    
    // 系统资源指标
    GoroutineCount = promauto.NewGauge(
        prometheus.GaugeOpts{
            Name: "goroutine_count",
            Help: "Number of goroutines",
        },
    )
)

中间件实现

func MetricsMiddleware() gin.HandlerFunc {
    return func(c *gin.Context) {
        start := time.Now()
        path := c.Request.URL.Path
        method := c.Request.Method

        c.Next()

        // 记录请求延迟
        duration := time.Since(start).Seconds()
        RequestDuration.WithLabelValues(method, path).Observe(duration)

        // 记录请求状态
        status := strconv.Itoa(c.Writer.Status())
        RequestCounter.WithLabelValues(method, path, status).Inc()
    }
}

链路追踪

Jaeger集成

func InitTracer(serviceName string) (opentracing.Tracer, error) {
    cfg := jaegercfg.Configuration{
        ServiceName: serviceName,
        Sampler: &jaegercfg.SamplerConfig{
            Type:  jaeger.SamplerTypeConst,
            Param: 1,
        },
        Reporter: &jaegercfg.ReporterConfig{
            LogSpans:           true,
            CollectorEndpoint: "http://jaeger:14268/api/traces",
        },
    }

    tracer, closer, err := cfg.NewTracer(jaegercfg.Logger(jaeger.StdLogger))
    if err != nil {
        return nil, err
    }
    
    opentracing.SetGlobalTracer(tracer)
    return tracer, nil
}

日志管理

结构化日志

type Logger struct {
    *zap.SugaredLogger
}

func NewLogger() (*Logger, error) {
    config := zap.NewProductionConfig()
    config.EncoderConfig.TimeKey = "timestamp"
    config.EncoderConfig.EncodeTime = zapcore.ISO8601TimeEncoder

    logger, err := config.Build()
    if err != nil {
        return nil, err
    }

    return &Logger{logger.Sugar()}, nil
}

健康检查

服务健康检查

type HealthCheck struct {
    db     *gorm.DB
    redis  *redis.Client
    logger *Logger
}

func (h *HealthCheck) Check(c *gin.Context) {
    status := map[string]string{
        "status": "healthy",
        "db":     "up",
        "redis":  "up",
    }

    // 检查数据库连接
    if err := h.db.Raw("SELECT 1").Error; err != nil {
        status["db"] = "down"
        status["status"] = "unhealthy"
    }

    // 检查Redis连接
    if err := h.redis.Ping(c).Err(); err != nil {
        status["redis"] = "down"
        status["status"] = "unhealthy"
    }

    if status["status"] == "healthy" {
        c.JSON(http.StatusOK, status)
    } else {
        c.JSON(http.StatusServiceUnavailable, status)
    }
}

告警配置

Prometheus告警规则

groups:
- name: service_alerts
  rules:
  - alert: HighErrorRate
    expr: |
      sum(rate(http_requests_total{status=~"5.."}[5m])) 
      / 
      sum(rate(http_requests_total[5m])) > 0.05
    for: 5m
    labels:
      severity: critical
    annotations:
      summary: High error rate detected
      description: Error rate is above 5% for the last 5 minutes

  - alert: ServiceDown
    expr: up == 0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: Service is down
      description: Service has been down for more than 1 minute

监控面板

Grafana仪表板

{
  "dashboard": {
    "title": "Service Monitoring",
    "panels": [
      {
        "title": "Request Rate",
        "type": "graph",
        "datasource": "Prometheus",
        "targets": [
          {
            "expr": "sum(rate(http_requests_total[5m])) by (endpoint)",
            "legendFormat": "{{endpoint}}"
          }
        ]
      },
      {
        "title": "Error Rate",
        "type": "graph",
        "datasource": "Prometheus",
        "targets": [
          {
            "expr": "sum(rate(http_requests_total{status=~\"5..\"}[5m])) by (endpoint) / sum(rate(http_requests_total[5m])) by (endpoint)",
            "legendFormat": "{{endpoint}}"
          }
        ]
      }
    ]
  }
}

最佳实践

1. 监控覆盖全面

   • 基础设施监控
   • 应用性能监控
   • 业务指标监控

2. 合理的告警阈值

   • 避免误报
   • 分级告警
   • 告警收敛

3. 日志最佳实践

   • 统一日志格式
   • 合理的日志级别
   • 关键信息脱敏

4. 链路追踪

   • 采样率配置
   • 关键节点埋点
   • 异常链路分析

5. 性能优化

   • 监控数据采集优化
   • 存储策略优化
   • 查询性能优化

总结

完善的监控体系是保障微服务稳定运行的关键。通过合理配置Prometheus、Jaeger等工具，结合告警和日志管理，可以构建一个全面的监控系统。

参考资料

1. Prometheus官方文档
2. Jaeger分布式追踪
3. Google SRE手册
4. Grafana可视化平台