监控、日志与告警

  console.debug('详细调试信息') // 开发时使用
console.info('一般信息') // 正常流程记录
console.warn('警告信息') // 潜在问题
console.error('错误信息') // 需要关注的错误
  

  2024-01-15 10:23:45 ERROR User john failed to login, attempts=3, ip=192.168.1.100
  

  {
  "timestamp": "2024-01-15T10:23:45Z",
  "level": "ERROR",
  "message": "User login failed",
  "user": "john",
  "attempts": 3,
  "ip": "192.168.1.100",
  "service": "auth-service"
}
  

  // 示例：使用 OpenTelemetry 记录 Span
import { trace } from '@opentelemetry/api'

const tracer = trace.getTracer('my-service')

async function processOrder(orderId) {
  // 创建一个 Span
  const span = tracer.startSpan('processOrder')

  try {
    // 设置属性
    span.setAttribute('order.id', orderId)

    // 业务逻辑...
    await validateOrder(orderId)
    await saveToDatabase(orderId)

    span.setStatus({ code: SpanStatusCode.OK })
  } catch (error) {
    span.recordException(error)
    span.setStatus({ code: SpanStatusCode.ERROR, message: error.message })
  } finally {
    span.end() // 结束 Span
  }
}
  

  # 查看 CPU 最高的前 5 个线程
$ top -H -p 12345

# 查看某个方法的调用耗时
$ trace com.example.OrderService createOrder

# 查看类的静态字段
$ getstatic com.example.Config MAX_CONNECTIONS

# 热更新代码（无需重启）
$ mc /tmp/Test.java
$ redefine /tmp/Test.class
  

  用户感知
  ↓
前端优化（减少请求、CDN、懒加载）
  ↓
网络优化（HTTP/2、压缩、长连接）
  ↓
后端优化（缓存、异步、批处理）
  ↓
数据库优化（索引、查询优化、分库分表）
  ↓
系统优化（内核参数、JVM 调优）
  

  -- 查询慢（无索引）
SELECT * FROM orders WHERE user_id = 12345;

-- 创建索引后快 100 倍
CREATE INDEX idx_user_id ON orders(user_id);
  

  -- ❌ 避免 SELECT *
SELECT * FROM users WHERE id = 123;

-- ✅ 只查需要的字段
SELECT id, name, email FROM users WHERE id = 123;

-- ❌ 避免 IN 子句太多
SELECT * FROM orders WHERE user_id IN (1, 2, 3, ..., 10000);

-- ✅ 使用 JOIN 或批量查询
SELECT * FROM orders o JOIN user_ids u ON o.user_id = u.id;
  

  浏览器缓存 (CDN)
  ↓
本地缓存 (内存/Guava)
  ↓
分布式缓存 (Redis/Memcached)
  ↓
数据库 (MySQL/PostgreSQL)
  

  # 安装 wrk
$ brew install wrk  # macOS
$ apt install wrk   # Ubuntu

# 压测 HTTP 接口（10 线程，持续 30 秒）
$ wrk -t10 -c100 -d30s http://example.com/api/users

# 输出：
# Running 30s test @ http://example.com/api/users
#   10 threads and 100 connections
#   Thread Stats   Avg      Stdev     Max   +/- Stdev
#     Latency    45.32ms   12.45ms 120.50ms   87.56%
#     Req/Sec     2.12k   123.45    3.45k    89.01%
#   632450 requests in 30.00s, 1.23GB read
# Requests/sec:  21081.67
  

  # Kubernetes HPA (Horizontal Pod Autoscaler)
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
  name: my-app-hpa
spec:
  scaleTargetRef:
    apiVersion: apps/v1
    kind: Deployment
    name: my-app
  minReplicas: 2
  maxReplicas: 10
  metrics:
    - type: Resource
      resource:
        name: cpu
        target:
          type: Utilization
          averageUtilization: 70
  

  # npm audit 示例
$ npm audit

found 3 vulnerabilities (1 moderate, 2 high)

Package         Severity  Vulnerable versions
lodash          high      <4.17.21
express         moderate  4.0.0 - 4.18.2

# 自动修复
$ npm audit fix
  

  # .gitlab-ci.yml 示例
stages:
  - test
  - build
  - deploy

test:
  stage: test
  script:
    - npm install
    - npm test
  tags:
    - docker

build:
  stage: build
  script:
    - docker build -t myapp:$CI_COMMIT_SHA .
    - docker push registry.example.com/myapp:$CI_COMMIT_SHA
  only:
    - main

deploy:
  stage: deploy
  script:
    - kubectl set image deployment/myapp myapp=registry.example.com/myapp:$CI_COMMIT_SHA
  environment:
    name: production
  when: manual # 手动触发部署
  

  # main.tf
resource "aws_instance" "web" {
  ami           = "ami-0c55b159cbfafe1f0"
  instance_type = "t2.micro"

  tags = {
    Name = "WebServer"
    Env  = "production"
  }
}

resource "aws_security_group" "web" {
  name = "web-sg"

  ingress {
    from_port   = 80
    to_port     = 80
    protocol    = "tcp"
    cidr_blocks = ["0.0.0.0/0"]
  }
}
  

  1. 修改配置文件（push 到 Git）
   ↓
2. Git 仓库变更触发 CI/CD
   ↓
3. 自动执行terraform apply/kubectl apply
   ↓
4. 基础设施自动更新
   ↓
5. 监控对比实际状态与期望状态
  

  09:00 - 查看夜间告警，确认系统状态
10:00 - 处理用户反馈的问题
11:00 - 参加研发周会，评估新方案运维风险
14:00 - 优化慢查询，提升性能
15:00 - 代码审查（Code Review）
16:00 - 编写部署文档，更新监控规则
17:00 - 故障演练（Chaos Engineering）
18:00 - 值班交接